From https://github.com/huggingface/diffusers
 * branch                b003a47354ca3a28b4b21fceb4d649656d8cee99 -> FETCH_HEAD
HEAD is now at b003a4735 [Feat] support AutoPipelineForText2Audio (#13511)
M	examples/dreambooth/train_dreambooth_lora_flux.py
Requirement already satisfied: pip in /workspace/emoji-venv/lib/python3.12/site-packages (26.1.1)
Obtaining file:///workspace/diffusers
  Installing build dependencies: started
  Installing build dependencies: finished with status 'done'
  Checking if build backend supports build_editable: started
  Checking if build backend supports build_editable: finished with status 'done'
  Getting requirements to build editable: started
  Getting requirements to build editable: finished with status 'done'
  Preparing editable metadata (pyproject.toml): started
  Preparing editable metadata (pyproject.toml): finished with status 'done'
Requirement already satisfied: importlib_metadata in /workspace/emoji-venv/lib/python3.12/site-packages (from diffusers==0.39.0.dev0) (9.0.0)
Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from diffusers==0.39.0.dev0) (3.20.0)
Requirement already satisfied: httpx<1.0.0 in /usr/local/lib/python3.12/dist-packages (from diffusers==0.39.0.dev0) (0.28.1)
Requirement already satisfied: huggingface-hub<2.0,>=0.34.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from diffusers==0.39.0.dev0) (1.17.0)
Requirement already satisfied: numpy in /usr/local/lib/python3.12/dist-packages (from diffusers==0.39.0.dev0) (2.1.2)
Requirement already satisfied: regex!=2019.12.17 in /workspace/emoji-venv/lib/python3.12/site-packages (from diffusers==0.39.0.dev0) (2026.5.9)
Requirement already satisfied: requests in /usr/local/lib/python3.12/dist-packages (from diffusers==0.39.0.dev0) (2.32.5)
Requirement already satisfied: safetensors>=0.8.0-rc.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from diffusers==0.39.0.dev0) (0.8.0rc0)
Requirement already satisfied: Pillow in /workspace/emoji-venv/lib/python3.12/site-packages (from diffusers==0.39.0.dev0) (12.2.0)
Requirement already satisfied: anyio in /usr/local/lib/python3.12/dist-packages (from httpx<1.0.0->diffusers==0.39.0.dev0) (4.11.0)
Requirement already satisfied: certifi in /usr/local/lib/python3.12/dist-packages (from httpx<1.0.0->diffusers==0.39.0.dev0) (2025.10.5)
Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.12/dist-packages (from httpx<1.0.0->diffusers==0.39.0.dev0) (1.0.9)
Requirement already satisfied: idna in /usr/local/lib/python3.12/dist-packages (from httpx<1.0.0->diffusers==0.39.0.dev0) (3.10)
Requirement already satisfied: h11>=0.16 in /usr/local/lib/python3.12/dist-packages (from httpcore==1.*->httpx<1.0.0->diffusers==0.39.0.dev0) (0.16.0)
Requirement already satisfied: click>=8.4.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from huggingface-hub<2.0,>=0.34.0->diffusers==0.39.0.dev0) (8.4.1)
Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<2.0,>=0.34.0->diffusers==0.39.0.dev0) (2024.6.1)
Requirement already satisfied: hf-xet<2.0.0,>=1.4.3 in /workspace/emoji-venv/lib/python3.12/site-packages (from huggingface-hub<2.0,>=0.34.0->diffusers==0.39.0.dev0) (1.5.0)
Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<2.0,>=0.34.0->diffusers==0.39.0.dev0) (25.0)
Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<2.0,>=0.34.0->diffusers==0.39.0.dev0) (6.0.3)
Requirement already satisfied: tqdm>=4.42.1 in /workspace/emoji-venv/lib/python3.12/site-packages (from huggingface-hub<2.0,>=0.34.0->diffusers==0.39.0.dev0) (4.67.3)
Requirement already satisfied: typer<0.26.0,>=0.20.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from huggingface-hub<2.0,>=0.34.0->diffusers==0.39.0.dev0) (0.25.1)
Requirement already satisfied: typing-extensions>=4.1.0 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<2.0,>=0.34.0->diffusers==0.39.0.dev0) (4.15.0)
Requirement already satisfied: shellingham>=1.3.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from typer<0.26.0,>=0.20.0->huggingface-hub<2.0,>=0.34.0->diffusers==0.39.0.dev0) (1.5.4)
Requirement already satisfied: rich>=13.8.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from typer<0.26.0,>=0.20.0->huggingface-hub<2.0,>=0.34.0->diffusers==0.39.0.dev0) (15.0.0)
Requirement already satisfied: annotated-doc>=0.0.2 in /workspace/emoji-venv/lib/python3.12/site-packages (from typer<0.26.0,>=0.20.0->huggingface-hub<2.0,>=0.34.0->diffusers==0.39.0.dev0) (0.0.4)
Requirement already satisfied: markdown-it-py>=2.2.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from rich>=13.8.0->typer<0.26.0,>=0.20.0->huggingface-hub<2.0,>=0.34.0->diffusers==0.39.0.dev0) (4.2.0)
Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.12/dist-packages (from rich>=13.8.0->typer<0.26.0,>=0.20.0->huggingface-hub<2.0,>=0.34.0->diffusers==0.39.0.dev0) (2.19.2)
Requirement already satisfied: mdurl~=0.1 in /workspace/emoji-venv/lib/python3.12/site-packages (from markdown-it-py>=2.2.0->rich>=13.8.0->typer<0.26.0,>=0.20.0->huggingface-hub<2.0,>=0.34.0->diffusers==0.39.0.dev0) (0.1.2)
Requirement already satisfied: sniffio>=1.1 in /usr/local/lib/python3.12/dist-packages (from anyio->httpx<1.0.0->diffusers==0.39.0.dev0) (1.3.1)
Requirement already satisfied: zipp>=3.20 in /workspace/emoji-venv/lib/python3.12/site-packages (from importlib_metadata->diffusers==0.39.0.dev0) (4.1.0)
Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests->diffusers==0.39.0.dev0) (3.4.3)
Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests->diffusers==0.39.0.dev0) (2.5.0)
Building wheels for collected packages: diffusers
  Building editable for diffusers (pyproject.toml): started
  Building editable for diffusers (pyproject.toml): finished with status 'done'
  Created wheel for diffusers: filename=diffusers-0.39.0.dev0-0.editable-py3-none-any.whl size=11393 sha256=0d6e9b0ac183ef3f01e9acd2c1394d310974ed524960f00a80b06f1e6d03d44a
  Stored in directory: /tmp/pip-ephem-wheel-cache-8devp_kf/wheels/cb/08/4e/66d4da61b678deb6c7483168b8b9991a4a3867cc3ac495dbd6
Successfully built diffusers
Installing collected packages: diffusers
  Attempting uninstall: diffusers
    Found existing installation: diffusers 0.39.0.dev0
    Uninstalling diffusers-0.39.0.dev0:
      Successfully uninstalled diffusers-0.39.0.dev0
Successfully installed diffusers-0.39.0.dev0
Requirement already satisfied: accelerate>=0.31.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from -r examples/dreambooth/requirements_flux.txt (line 1)) (1.13.0)
Requirement already satisfied: torchvision in /usr/local/lib/python3.12/dist-packages (from -r examples/dreambooth/requirements_flux.txt (line 2)) (0.23.0+cu128)
Requirement already satisfied: transformers>=4.41.2 in /workspace/emoji-venv/lib/python3.12/site-packages (from -r examples/dreambooth/requirements_flux.txt (line 3)) (5.9.0)
Requirement already satisfied: ftfy in /workspace/emoji-venv/lib/python3.12/site-packages (from -r examples/dreambooth/requirements_flux.txt (line 4)) (6.3.1)
Requirement already satisfied: tensorboard in /workspace/emoji-venv/lib/python3.12/site-packages (from -r examples/dreambooth/requirements_flux.txt (line 5)) (2.20.0)
Requirement already satisfied: Jinja2 in /usr/local/lib/python3.12/dist-packages (from -r examples/dreambooth/requirements_flux.txt (line 6)) (3.1.6)
Requirement already satisfied: peft>=0.11.1 in /workspace/emoji-venv/lib/python3.12/site-packages (from -r examples/dreambooth/requirements_flux.txt (line 7)) (0.19.1)
Requirement already satisfied: sentencepiece in /workspace/emoji-venv/lib/python3.12/site-packages (from -r examples/dreambooth/requirements_flux.txt (line 8)) (0.2.1)
Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.12/dist-packages (from accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (2.1.2)
Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (25.0)
Requirement already satisfied: psutil in /usr/local/lib/python3.12/dist-packages (from accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (7.1.0)
Requirement already satisfied: pyyaml in /usr/local/lib/python3.12/dist-packages (from accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (6.0.3)
Requirement already satisfied: torch>=2.0.0 in /usr/local/lib/python3.12/dist-packages (from accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (2.8.0+cu128)
Requirement already satisfied: huggingface_hub>=0.21.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (1.17.0)
Requirement already satisfied: safetensors>=0.4.3 in /workspace/emoji-venv/lib/python3.12/site-packages (from accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (0.8.0rc0)
Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from torchvision->-r examples/dreambooth/requirements_flux.txt (line 2)) (12.2.0)
Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (3.20.0)
Requirement already satisfied: typing-extensions>=4.10.0 in /usr/local/lib/python3.12/dist-packages (from torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (4.15.0)
Requirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (80.9.0)
Requirement already satisfied: sympy>=1.13.3 in /usr/local/lib/python3.12/dist-packages (from torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (1.13.3)
Requirement already satisfied: networkx in /usr/local/lib/python3.12/dist-packages (from torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (3.3)
Requirement already satisfied: fsspec in /usr/local/lib/python3.12/dist-packages (from torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (2024.6.1)
Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.8.93 in /usr/local/lib/python3.12/dist-packages (from torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (12.8.93)
Requirement already satisfied: nvidia-cuda-runtime-cu12==12.8.90 in /usr/local/lib/python3.12/dist-packages (from torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (12.8.90)
Requirement already satisfied: nvidia-cuda-cupti-cu12==12.8.90 in /usr/local/lib/python3.12/dist-packages (from torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (12.8.90)
Requirement already satisfied: nvidia-cudnn-cu12==9.10.2.21 in /usr/local/lib/python3.12/dist-packages (from torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (9.10.2.21)
Requirement already satisfied: nvidia-cublas-cu12==12.8.4.1 in /usr/local/lib/python3.12/dist-packages (from torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (12.8.4.1)
Requirement already satisfied: nvidia-cufft-cu12==11.3.3.83 in /usr/local/lib/python3.12/dist-packages (from torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (11.3.3.83)
Requirement already satisfied: nvidia-curand-cu12==10.3.9.90 in /usr/local/lib/python3.12/dist-packages (from torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (10.3.9.90)
Requirement already satisfied: nvidia-cusolver-cu12==11.7.3.90 in /usr/local/lib/python3.12/dist-packages (from torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (11.7.3.90)
Requirement already satisfied: nvidia-cusparse-cu12==12.5.8.93 in /usr/local/lib/python3.12/dist-packages (from torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (12.5.8.93)
Requirement already satisfied: nvidia-cusparselt-cu12==0.7.1 in /usr/local/lib/python3.12/dist-packages (from torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (0.7.1)
Requirement already satisfied: nvidia-nccl-cu12==2.27.3 in /usr/local/lib/python3.12/dist-packages (from torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (2.27.3)
Requirement already satisfied: nvidia-nvtx-cu12==12.8.90 in /usr/local/lib/python3.12/dist-packages (from torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (12.8.90)
Requirement already satisfied: nvidia-nvjitlink-cu12==12.8.93 in /usr/local/lib/python3.12/dist-packages (from torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (12.8.93)
Requirement already satisfied: nvidia-cufile-cu12==1.13.1.3 in /usr/local/lib/python3.12/dist-packages (from torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (1.13.1.3)
Requirement already satisfied: triton==3.4.0 in /usr/local/lib/python3.12/dist-packages (from torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (3.4.0)
Requirement already satisfied: regex>=2025.10.22 in /workspace/emoji-venv/lib/python3.12/site-packages (from transformers>=4.41.2->-r examples/dreambooth/requirements_flux.txt (line 3)) (2026.5.9)
Requirement already satisfied: tokenizers<=0.23.0,>=0.22.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from transformers>=4.41.2->-r examples/dreambooth/requirements_flux.txt (line 3)) (0.22.2)
Requirement already satisfied: typer in /workspace/emoji-venv/lib/python3.12/site-packages (from transformers>=4.41.2->-r examples/dreambooth/requirements_flux.txt (line 3)) (0.25.1)
Requirement already satisfied: tqdm>=4.27 in /workspace/emoji-venv/lib/python3.12/site-packages (from transformers>=4.41.2->-r examples/dreambooth/requirements_flux.txt (line 3)) (4.67.3)
Requirement already satisfied: click>=8.4.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from huggingface_hub>=0.21.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (8.4.1)
Requirement already satisfied: hf-xet<2.0.0,>=1.4.3 in /workspace/emoji-venv/lib/python3.12/site-packages (from huggingface_hub>=0.21.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (1.5.0)
Requirement already satisfied: httpx<1,>=0.23.0 in /usr/local/lib/python3.12/dist-packages (from huggingface_hub>=0.21.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (0.28.1)
Requirement already satisfied: anyio in /usr/local/lib/python3.12/dist-packages (from httpx<1,>=0.23.0->huggingface_hub>=0.21.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (4.11.0)
Requirement already satisfied: certifi in /usr/local/lib/python3.12/dist-packages (from httpx<1,>=0.23.0->huggingface_hub>=0.21.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (2025.10.5)
Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.12/dist-packages (from httpx<1,>=0.23.0->huggingface_hub>=0.21.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (1.0.9)
Requirement already satisfied: idna in /usr/local/lib/python3.12/dist-packages (from httpx<1,>=0.23.0->huggingface_hub>=0.21.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (3.10)
Requirement already satisfied: h11>=0.16 in /usr/local/lib/python3.12/dist-packages (from httpcore==1.*->httpx<1,>=0.23.0->huggingface_hub>=0.21.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (0.16.0)
Requirement already satisfied: shellingham>=1.3.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from typer->transformers>=4.41.2->-r examples/dreambooth/requirements_flux.txt (line 3)) (1.5.4)
Requirement already satisfied: rich>=13.8.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from typer->transformers>=4.41.2->-r examples/dreambooth/requirements_flux.txt (line 3)) (15.0.0)
Requirement already satisfied: annotated-doc>=0.0.2 in /workspace/emoji-venv/lib/python3.12/site-packages (from typer->transformers>=4.41.2->-r examples/dreambooth/requirements_flux.txt (line 3)) (0.0.4)
Requirement already satisfied: wcwidth in /usr/local/lib/python3.12/dist-packages (from ftfy->-r examples/dreambooth/requirements_flux.txt (line 4)) (0.2.14)
Requirement already satisfied: absl-py>=0.4 in /workspace/emoji-venv/lib/python3.12/site-packages (from tensorboard->-r examples/dreambooth/requirements_flux.txt (line 5)) (2.4.0)
Requirement already satisfied: grpcio>=1.48.2 in /workspace/emoji-venv/lib/python3.12/site-packages (from tensorboard->-r examples/dreambooth/requirements_flux.txt (line 5)) (1.80.0)
Requirement already satisfied: markdown>=2.6.8 in /workspace/emoji-venv/lib/python3.12/site-packages (from tensorboard->-r examples/dreambooth/requirements_flux.txt (line 5)) (3.10.2)
Requirement already satisfied: protobuf!=4.24.0,>=3.19.6 in /workspace/emoji-venv/lib/python3.12/site-packages (from tensorboard->-r examples/dreambooth/requirements_flux.txt (line 5)) (7.35.0)
Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from tensorboard->-r examples/dreambooth/requirements_flux.txt (line 5)) (0.7.2)
Requirement already satisfied: werkzeug>=1.0.1 in /workspace/emoji-venv/lib/python3.12/site-packages (from tensorboard->-r examples/dreambooth/requirements_flux.txt (line 5)) (3.1.8)
Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.12/dist-packages (from Jinja2->-r examples/dreambooth/requirements_flux.txt (line 6)) (3.0.3)
Requirement already satisfied: markdown-it-py>=2.2.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from rich>=13.8.0->typer->transformers>=4.41.2->-r examples/dreambooth/requirements_flux.txt (line 3)) (4.2.0)
Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.12/dist-packages (from rich>=13.8.0->typer->transformers>=4.41.2->-r examples/dreambooth/requirements_flux.txt (line 3)) (2.19.2)
Requirement already satisfied: mdurl~=0.1 in /workspace/emoji-venv/lib/python3.12/site-packages (from markdown-it-py>=2.2.0->rich>=13.8.0->typer->transformers>=4.41.2->-r examples/dreambooth/requirements_flux.txt (line 3)) (0.1.2)
Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy>=1.13.3->torch>=2.0.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (1.3.0)
Requirement already satisfied: sniffio>=1.1 in /usr/local/lib/python3.12/dist-packages (from anyio->httpx<1,>=0.23.0->huggingface_hub>=0.21.0->accelerate>=0.31.0->-r examples/dreambooth/requirements_flux.txt (line 1)) (1.3.1)
Requirement already satisfied: datasets in /workspace/emoji-venv/lib/python3.12/site-packages (4.8.5)
Requirement already satisfied: bitsandbytes in /workspace/emoji-venv/lib/python3.12/site-packages (0.49.2)
Requirement already satisfied: wandb in /workspace/emoji-venv/lib/python3.12/site-packages (0.27.0)
Requirement already satisfied: pillow in /workspace/emoji-venv/lib/python3.12/site-packages (12.2.0)
Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from datasets) (3.20.0)
Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.12/dist-packages (from datasets) (2.1.2)
Requirement already satisfied: pyarrow>=21.0.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from datasets) (24.0.0)
Requirement already satisfied: dill<0.4.2,>=0.3.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from datasets) (0.4.1)
Requirement already satisfied: pandas in /workspace/emoji-venv/lib/python3.12/site-packages (from datasets) (3.0.3)
Requirement already satisfied: requests>=2.32.2 in /usr/local/lib/python3.12/dist-packages (from datasets) (2.32.5)
Requirement already satisfied: httpx<1.0.0 in /usr/local/lib/python3.12/dist-packages (from datasets) (0.28.1)
Requirement already satisfied: tqdm>=4.66.3 in /workspace/emoji-venv/lib/python3.12/site-packages (from datasets) (4.67.3)
Requirement already satisfied: xxhash in /workspace/emoji-venv/lib/python3.12/site-packages (from datasets) (3.7.0)
Requirement already satisfied: multiprocess<0.70.20 in /workspace/emoji-venv/lib/python3.12/site-packages (from datasets) (0.70.19)
Requirement already satisfied: fsspec<=2026.2.0,>=2023.1.0 in /usr/local/lib/python3.12/dist-packages (from fsspec[http]<=2026.2.0,>=2023.1.0->datasets) (2024.6.1)
Requirement already satisfied: huggingface-hub<2.0,>=0.25.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from datasets) (1.17.0)
Requirement already satisfied: packaging in /usr/local/lib/python3.12/dist-packages (from datasets) (25.0)
Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.12/dist-packages (from datasets) (6.0.3)
Requirement already satisfied: aiohttp!=4.0.0a0,!=4.0.0a1 in /workspace/emoji-venv/lib/python3.12/site-packages (from fsspec[http]<=2026.2.0,>=2023.1.0->datasets) (3.13.5)
Requirement already satisfied: anyio in /usr/local/lib/python3.12/dist-packages (from httpx<1.0.0->datasets) (4.11.0)
Requirement already satisfied: certifi in /usr/local/lib/python3.12/dist-packages (from httpx<1.0.0->datasets) (2025.10.5)
Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.12/dist-packages (from httpx<1.0.0->datasets) (1.0.9)
Requirement already satisfied: idna in /usr/local/lib/python3.12/dist-packages (from httpx<1.0.0->datasets) (3.10)
Requirement already satisfied: h11>=0.16 in /usr/local/lib/python3.12/dist-packages (from httpcore==1.*->httpx<1.0.0->datasets) (0.16.0)
Requirement already satisfied: click>=8.4.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from huggingface-hub<2.0,>=0.25.0->datasets) (8.4.1)
Requirement already satisfied: hf-xet<2.0.0,>=1.4.3 in /workspace/emoji-venv/lib/python3.12/site-packages (from huggingface-hub<2.0,>=0.25.0->datasets) (1.5.0)
Requirement already satisfied: typer<0.26.0,>=0.20.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from huggingface-hub<2.0,>=0.25.0->datasets) (0.25.1)
Requirement already satisfied: typing-extensions>=4.1.0 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<2.0,>=0.25.0->datasets) (4.15.0)
Requirement already satisfied: shellingham>=1.3.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from typer<0.26.0,>=0.20.0->huggingface-hub<2.0,>=0.25.0->datasets) (1.5.4)
Requirement already satisfied: rich>=13.8.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from typer<0.26.0,>=0.20.0->huggingface-hub<2.0,>=0.25.0->datasets) (15.0.0)
Requirement already satisfied: annotated-doc>=0.0.2 in /workspace/emoji-venv/lib/python3.12/site-packages (from typer<0.26.0,>=0.20.0->huggingface-hub<2.0,>=0.25.0->datasets) (0.0.4)
Requirement already satisfied: torch<3,>=2.3 in /usr/local/lib/python3.12/dist-packages (from bitsandbytes) (2.8.0+cu128)
Requirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from torch<3,>=2.3->bitsandbytes) (80.9.0)
Requirement already satisfied: sympy>=1.13.3 in /usr/local/lib/python3.12/dist-packages (from torch<3,>=2.3->bitsandbytes) (1.13.3)
Requirement already satisfied: networkx in /usr/local/lib/python3.12/dist-packages (from torch<3,>=2.3->bitsandbytes) (3.3)
Requirement already satisfied: jinja2 in /usr/local/lib/python3.12/dist-packages (from torch<3,>=2.3->bitsandbytes) (3.1.6)
Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.8.93 in /usr/local/lib/python3.12/dist-packages (from torch<3,>=2.3->bitsandbytes) (12.8.93)
Requirement already satisfied: nvidia-cuda-runtime-cu12==12.8.90 in /usr/local/lib/python3.12/dist-packages (from torch<3,>=2.3->bitsandbytes) (12.8.90)
Requirement already satisfied: nvidia-cuda-cupti-cu12==12.8.90 in /usr/local/lib/python3.12/dist-packages (from torch<3,>=2.3->bitsandbytes) (12.8.90)
Requirement already satisfied: nvidia-cudnn-cu12==9.10.2.21 in /usr/local/lib/python3.12/dist-packages (from torch<3,>=2.3->bitsandbytes) (9.10.2.21)
Requirement already satisfied: nvidia-cublas-cu12==12.8.4.1 in /usr/local/lib/python3.12/dist-packages (from torch<3,>=2.3->bitsandbytes) (12.8.4.1)
Requirement already satisfied: nvidia-cufft-cu12==11.3.3.83 in /usr/local/lib/python3.12/dist-packages (from torch<3,>=2.3->bitsandbytes) (11.3.3.83)
Requirement already satisfied: nvidia-curand-cu12==10.3.9.90 in /usr/local/lib/python3.12/dist-packages (from torch<3,>=2.3->bitsandbytes) (10.3.9.90)
Requirement already satisfied: nvidia-cusolver-cu12==11.7.3.90 in /usr/local/lib/python3.12/dist-packages (from torch<3,>=2.3->bitsandbytes) (11.7.3.90)
Requirement already satisfied: nvidia-cusparse-cu12==12.5.8.93 in /usr/local/lib/python3.12/dist-packages (from torch<3,>=2.3->bitsandbytes) (12.5.8.93)
Requirement already satisfied: nvidia-cusparselt-cu12==0.7.1 in /usr/local/lib/python3.12/dist-packages (from torch<3,>=2.3->bitsandbytes) (0.7.1)
Requirement already satisfied: nvidia-nccl-cu12==2.27.3 in /usr/local/lib/python3.12/dist-packages (from torch<3,>=2.3->bitsandbytes) (2.27.3)
Requirement already satisfied: nvidia-nvtx-cu12==12.8.90 in /usr/local/lib/python3.12/dist-packages (from torch<3,>=2.3->bitsandbytes) (12.8.90)
Requirement already satisfied: nvidia-nvjitlink-cu12==12.8.93 in /usr/local/lib/python3.12/dist-packages (from torch<3,>=2.3->bitsandbytes) (12.8.93)
Requirement already satisfied: nvidia-cufile-cu12==1.13.1.3 in /usr/local/lib/python3.12/dist-packages (from torch<3,>=2.3->bitsandbytes) (1.13.1.3)
Requirement already satisfied: triton==3.4.0 in /usr/local/lib/python3.12/dist-packages (from torch<3,>=2.3->bitsandbytes) (3.4.0)
Requirement already satisfied: gitpython!=3.1.29,>=1.0.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from wandb) (3.1.50)
Requirement already satisfied: platformdirs in /usr/local/lib/python3.12/dist-packages (from wandb) (4.5.0)
Requirement already satisfied: protobuf!=5.28.0,!=5.29.0,<8,>4.21.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from wandb) (7.35.0)
Requirement already satisfied: pydantic<3,>=2.6 in /workspace/emoji-venv/lib/python3.12/site-packages (from wandb) (2.13.4)
Requirement already satisfied: sentry-sdk>=2.0.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from wandb) (2.61.0)
Requirement already satisfied: annotated-types>=0.6.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from pydantic<3,>=2.6->wandb) (0.7.0)
Requirement already satisfied: pydantic-core==2.46.4 in /workspace/emoji-venv/lib/python3.12/site-packages (from pydantic<3,>=2.6->wandb) (2.46.4)
Requirement already satisfied: typing-inspection>=0.4.2 in /workspace/emoji-venv/lib/python3.12/site-packages (from pydantic<3,>=2.6->wandb) (0.4.2)
Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests>=2.32.2->datasets) (3.4.3)
Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests>=2.32.2->datasets) (2.5.0)
Requirement already satisfied: aiohappyeyeballs>=2.5.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2026.2.0,>=2023.1.0->datasets) (2.6.2)
Requirement already satisfied: aiosignal>=1.4.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2026.2.0,>=2023.1.0->datasets) (1.4.0)
Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2026.2.0,>=2023.1.0->datasets) (25.4.0)
Requirement already satisfied: frozenlist>=1.1.1 in /workspace/emoji-venv/lib/python3.12/site-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2026.2.0,>=2023.1.0->datasets) (1.8.0)
Requirement already satisfied: multidict<7.0,>=4.5 in /workspace/emoji-venv/lib/python3.12/site-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2026.2.0,>=2023.1.0->datasets) (6.7.1)
Requirement already satisfied: propcache>=0.2.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2026.2.0,>=2023.1.0->datasets) (0.5.2)
Requirement already satisfied: yarl<2.0,>=1.17.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2026.2.0,>=2023.1.0->datasets) (1.24.2)
Requirement already satisfied: gitdb<5,>=4.0.1 in /workspace/emoji-venv/lib/python3.12/site-packages (from gitpython!=3.1.29,>=1.0.0->wandb) (4.0.12)
Requirement already satisfied: smmap<6,>=3.0.1 in /workspace/emoji-venv/lib/python3.12/site-packages (from gitdb<5,>=4.0.1->gitpython!=3.1.29,>=1.0.0->wandb) (5.0.3)
Requirement already satisfied: markdown-it-py>=2.2.0 in /workspace/emoji-venv/lib/python3.12/site-packages (from rich>=13.8.0->typer<0.26.0,>=0.20.0->huggingface-hub<2.0,>=0.25.0->datasets) (4.2.0)
Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.12/dist-packages (from rich>=13.8.0->typer<0.26.0,>=0.20.0->huggingface-hub<2.0,>=0.25.0->datasets) (2.19.2)
Requirement already satisfied: mdurl~=0.1 in /workspace/emoji-venv/lib/python3.12/site-packages (from markdown-it-py>=2.2.0->rich>=13.8.0->typer<0.26.0,>=0.20.0->huggingface-hub<2.0,>=0.25.0->datasets) (0.1.2)
Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy>=1.13.3->torch<3,>=2.3->bitsandbytes) (1.3.0)
Requirement already satisfied: sniffio>=1.1 in /usr/local/lib/python3.12/dist-packages (from anyio->httpx<1.0.0->datasets) (1.3.1)
Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.12/dist-packages (from jinja2->torch<3,>=2.3->bitsandbytes) (3.0.3)
Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.12/dist-packages (from pandas->datasets) (2.9.0.post0)
Requirement already satisfied: six>=1.5 in /usr/lib/python3/dist-packages (from python-dateutil>=2.8.2->pandas->datasets) (1.16.0)
Configuration already exists at /workspace/.cache/huggingface/accelerate/default_config.yaml, will not override. Run `accelerate config` manually or pass a different `save_location`.
Patched /workspace/diffusers/examples/dreambooth/train_dreambooth_lora_flux.py
05/30/2026 08:31:25 - INFO - __main__ - [RANK 0] Distributed environment: DistributedType.NO
Num processes: 1
Process index: 0
Local process index: 0
Device: cuda

Mixed precision type: bf16

05/30/2026 08:31:25 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/tokenizer/tokenizer_config.json "HTTP/1.1 200 OK"
05/30/2026 08:31:25 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev/tree/main/additional_chat_templates?recursive=false&expand=false "HTTP/1.1 404 Not Found"
05/30/2026 08:31:25 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev/tree/main?recursive=true&expand=false "HTTP/1.1 200 OK"
05/30/2026 08:31:25 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/tokenizer_2/tokenizer_config.json "HTTP/1.1 200 OK"
05/30/2026 08:31:25 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev/tree/main/additional_chat_templates?recursive=false&expand=false "HTTP/1.1 404 Not Found"
05/30/2026 08:31:25 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev/tree/main?recursive=true&expand=false "HTTP/1.1 200 OK"
05/30/2026 08:31:26 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/config.json "HTTP/1.1 200 OK"
[transformers] You are using a model of type `clip_text_model` to instantiate a model of type ``. This may be expected if you are loading a checkpoint that shares a subset of the architecture (e.g., loading a `sam2_video` checkpoint into `Sam2Model`), but is otherwise not supported and can yield errors. Please verify that the checkpoint is compatible with the model you are instantiating.
05/30/2026 08:31:26 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/config.json "HTTP/1.1 200 OK"
[transformers] You are using a model of type `t5` to instantiate a model of type ``. This may be expected if you are loading a checkpoint that shares a subset of the architecture (e.g., loading a `sam2_video` checkpoint into `Sam2Model`), but is otherwise not supported and can yield errors. Please verify that the checkpoint is compatible with the model you are instantiating.
/workspace/emoji-venv/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py:205: UserWarning: The `local_dir_use_symlinks` argument is deprecated and ignored in `hf_hub_download`. Downloading to a local directory does not use symlinks anymore.
  warnings.warn(
05/30/2026 08:31:26 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/scheduler/scheduler_config.json "HTTP/1.1 200 OK"
{'stochastic_sampling', 'use_beta_sigmas', 'invert_sigmas', 'time_shift_type', 'use_exponential_sigmas', 'shift_terminal', 'use_karras_sigmas'} was not found in config. Values will be initialized to default values.
05/30/2026 08:31:26 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/config.json "HTTP/1.1 200 OK"
05/30/2026 08:31:26 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/config.json "HTTP/1.1 200 OK"
05/30/2026 08:31:26 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/model.safetensors "HTTP/1.1 302 Found"

Loading weights:   0%|          | 0/196 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 196/196 [00:00<00:00, 6644.50it/s]
05/30/2026 08:31:27 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/config.json "HTTP/1.1 200 OK"
05/30/2026 08:31:27 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/config.json "HTTP/1.1 200 OK"
05/30/2026 08:31:27 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/model.safetensors "HTTP/1.1 404 Not Found"
05/30/2026 08:31:27 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/model.safetensors.index.json "HTTP/1.1 200 OK"
05/30/2026 08:31:27 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev/revision/main "HTTP/1.1 200 OK"

Fetching 2 files:   0%|          | 0/2 [00:00<?, ?it/s]
Fetching 2 files: 100%|██████████| 2/2 [00:00<00:00, 3748.26it/s]

Loading weights:   0%|          | 0/219 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 219/219 [00:00<00:00, 5761.77it/s]
05/30/2026 08:31:27 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/vae/config.json "HTTP/1.1 200 OK"
05/30/2026 08:31:28 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/3de623fc3c33e44ffbe2bad470d0f45bccf2eb21/vae/diffusion_pytorch_model.safetensors.index.json "HTTP/1.1 404 Not Found"
All model checkpoint weights were used when initializing AutoencoderKL.

All the weights of AutoencoderKL were initialized from the model checkpoint at black-forest-labs/FLUX.1-dev.
If your task is similar to the task the model of the checkpoint was trained on, you can already use AutoencoderKL for predictions without further training.
05/30/2026 08:31:28 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/transformer/config.json "HTTP/1.1 200 OK"
05/30/2026 08:31:28 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev "HTTP/1.1 200 OK"
05/30/2026 08:31:28 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev/revision/main "HTTP/1.1 200 OK"

Fetching 3 files:   0%|          | 0/3 [00:00<?, ?it/s]
Fetching 3 files: 100%|██████████| 3/3 [00:00<00:00, 5021.11it/s]
{'out_channels', 'axes_dims_rope'} was not found in config. Values will be initialized to default values.

Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards:  33%|███▎      | 1/3 [00:09<00:18,  9.16s/it]
Loading checkpoint shards:  67%|██████▋   | 2/3 [00:18<00:09,  9.26s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:22<00:00,  6.74s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:22<00:00,  7.41s/it]
All model checkpoint weights were used when initializing FluxTransformer2DModel.

All the weights of FluxTransformer2DModel were initialized from the model checkpoint at black-forest-labs/FLUX.1-dev.
If your task is similar to the task the model of the checkpoint was trained on, you can already use FluxTransformer2DModel for predictions without further training.

Downloading data:   0%|          | 0/220 [00:00<?, ?files/s]
Downloading data: 100%|██████████| 220/220 [00:00<00:00, 32613.96files/s]

Generating train split: 0 examples [00:00, ? examples/s]
Generating train split: 220 examples [00:00, 20030.97 examples/s]

Caching prompt embeds:   0%|          | 0/220 [00:00<?, ?it/s]
Caching prompt embeds:   0%|          | 1/220 [00:00<01:09,  3.17it/s]
Caching prompt embeds:   2%|▏         | 5/220 [00:00<00:15, 14.19it/s]
Caching prompt embeds:   4%|▍         | 9/220 [00:00<00:09, 21.39it/s]
Caching prompt embeds:   6%|▌         | 13/220 [00:00<00:08, 25.77it/s]
Caching prompt embeds:   8%|▊         | 17/220 [00:00<00:06, 29.01it/s]
Caching prompt embeds:  10%|▉         | 21/220 [00:00<00:06, 31.22it/s]
Caching prompt embeds:  11%|█▏        | 25/220 [00:00<00:05, 32.85it/s]
Caching prompt embeds:  13%|█▎        | 29/220 [00:01<00:05, 33.98it/s]
Caching prompt embeds:  15%|█▌        | 33/220 [00:01<00:05, 34.58it/s]
Caching prompt embeds:  17%|█▋        | 37/220 [00:01<00:05, 35.17it/s]
Caching prompt embeds:  19%|█▊        | 41/220 [00:01<00:05, 35.58it/s]
Caching prompt embeds:  20%|██        | 45/220 [00:01<00:04, 35.72it/s]
Caching prompt embeds:  22%|██▏       | 49/220 [00:01<00:04, 35.94it/s]
Caching prompt embeds:  24%|██▍       | 53/220 [00:01<00:04, 36.14it/s]
Caching prompt embeds:  26%|██▌       | 57/220 [00:01<00:04, 36.08it/s]
Caching prompt embeds:  28%|██▊       | 61/220 [00:01<00:04, 36.24it/s]
Caching prompt embeds:  30%|██▉       | 65/220 [00:02<00:04, 36.34it/s]
Caching prompt embeds:  31%|███▏      | 69/220 [00:02<00:04, 36.28it/s]
Caching prompt embeds:  33%|███▎      | 73/220 [00:02<00:04, 36.20it/s]
Caching prompt embeds:  35%|███▌      | 77/220 [00:02<00:03, 36.30it/s]
Caching prompt embeds:  37%|███▋      | 81/220 [00:02<00:03, 36.38it/s]
Caching prompt embeds:  39%|███▊      | 85/220 [00:02<00:03, 35.99it/s]
Caching prompt embeds:  40%|████      | 89/220 [00:02<00:03, 36.22it/s]
Caching prompt embeds:  42%|████▏     | 93/220 [00:02<00:03, 36.31it/s]
Caching prompt embeds:  44%|████▍     | 97/220 [00:02<00:03, 36.41it/s]
Caching prompt embeds:  46%|████▌     | 101/220 [00:03<00:03, 36.52it/s]
Caching prompt embeds:  48%|████▊     | 105/220 [00:03<00:03, 36.54it/s]
Caching prompt embeds:  50%|████▉     | 109/220 [00:03<00:03, 36.59it/s]
Caching prompt embeds:  51%|█████▏    | 113/220 [00:03<00:02, 36.66it/s]
Caching prompt embeds:  53%|█████▎    | 117/220 [00:03<00:02, 36.56it/s]
Caching prompt embeds:  55%|█████▌    | 121/220 [00:03<00:02, 36.63it/s]
Caching prompt embeds:  57%|█████▋    | 125/220 [00:03<00:02, 36.67it/s]
Caching prompt embeds:  59%|█████▊    | 129/220 [00:03<00:02, 36.71it/s]
Caching prompt embeds:  60%|██████    | 133/220 [00:03<00:02, 36.57it/s]
Caching prompt embeds:  62%|██████▏   | 137/220 [00:04<00:02, 36.63it/s]
Caching prompt embeds:  64%|██████▍   | 141/220 [00:04<00:02, 36.63it/s]
Caching prompt embeds:  66%|██████▌   | 145/220 [00:04<00:02, 36.67it/s]
Caching prompt embeds:  68%|██████▊   | 149/220 [00:04<00:01, 36.70it/s]
Caching prompt embeds:  70%|██████▉   | 153/220 [00:04<00:01, 36.64it/s]
Caching prompt embeds:  71%|███████▏  | 157/220 [00:04<00:01, 36.68it/s]
Caching prompt embeds:  73%|███████▎  | 161/220 [00:04<00:01, 36.54it/s]
Caching prompt embeds:  75%|███████▌  | 165/220 [00:04<00:01, 36.49it/s]
Caching prompt embeds:  77%|███████▋  | 169/220 [00:04<00:01, 36.01it/s]
Caching prompt embeds:  79%|███████▊  | 173/220 [00:05<00:01, 36.20it/s]
Caching prompt embeds:  80%|████████  | 177/220 [00:05<00:01, 36.34it/s]
Caching prompt embeds:  82%|████████▏ | 181/220 [00:05<00:01, 36.27it/s]
Caching prompt embeds:  84%|████████▍ | 185/220 [00:05<00:00, 36.40it/s]
Caching prompt embeds:  86%|████████▌ | 189/220 [00:05<00:00, 36.47it/s]
Caching prompt embeds:  88%|████████▊ | 193/220 [00:05<00:00, 36.54it/s]
Caching prompt embeds:  90%|████████▉ | 197/220 [00:05<00:00, 36.60it/s]
Caching prompt embeds:  91%|█████████▏| 201/220 [00:05<00:00, 36.65it/s]
Caching prompt embeds:  93%|█████████▎| 205/220 [00:05<00:00, 36.69it/s]
Caching prompt embeds:  95%|█████████▌| 209/220 [00:06<00:00, 36.65it/s]
Caching prompt embeds:  97%|█████████▋| 213/220 [00:06<00:00, 36.67it/s]
Caching prompt embeds:  99%|█████████▊| 217/220 [00:06<00:00, 36.70it/s]
Caching prompt embeds: 100%|██████████| 220/220 [00:06<00:00, 34.79it/s]

Caching latents:   0%|          | 0/220 [00:00<?, ?it/s]
Caching latents:   0%|          | 1/220 [00:00<00:36,  6.01it/s]
Caching latents:   5%|▍         | 10/220 [00:00<00:04, 42.98it/s]
Caching latents:   9%|▊         | 19/220 [00:00<00:03, 59.33it/s]
Caching latents:  13%|█▎        | 28/220 [00:00<00:02, 68.06it/s]
Caching latents:  17%|█▋        | 37/220 [00:00<00:02, 73.12it/s]
Caching latents:  21%|██        | 46/220 [00:00<00:02, 76.26it/s]
Caching latents:  25%|██▌       | 55/220 [00:00<00:02, 78.28it/s]
Caching latents:  29%|██▉       | 64/220 [00:00<00:01, 79.83it/s]
Caching latents:  33%|███▎      | 73/220 [00:01<00:01, 80.79it/s]
Caching latents:  37%|███▋      | 82/220 [00:01<00:01, 81.39it/s]
Caching latents:  41%|████▏     | 91/220 [00:01<00:01, 81.88it/s]
Caching latents:  45%|████▌     | 100/220 [00:01<00:01, 82.10it/s]
Caching latents:  50%|████▉     | 109/220 [00:01<00:01, 82.33it/s]
Caching latents:  54%|█████▎    | 118/220 [00:01<00:01, 82.56it/s]
Caching latents:  58%|█████▊    | 127/220 [00:01<00:01, 82.71it/s]
Caching latents:  62%|██████▏   | 136/220 [00:01<00:01, 82.69it/s]
Caching latents:  66%|██████▌   | 145/220 [00:01<00:00, 82.53it/s]
Caching latents:  70%|███████   | 154/220 [00:02<00:00, 81.93it/s]
Caching latents:  74%|███████▍  | 163/220 [00:02<00:00, 82.24it/s]
Caching latents:  78%|███████▊  | 172/220 [00:02<00:00, 82.33it/s]
Caching latents:  82%|████████▏ | 181/220 [00:02<00:00, 82.45it/s]
Caching latents:  86%|████████▋ | 190/220 [00:02<00:00, 82.64it/s]
Caching latents:  90%|█████████ | 199/220 [00:02<00:00, 82.54it/s]
Caching latents:  95%|█████████▍| 208/220 [00:02<00:00, 82.73it/s]
Caching latents:  99%|█████████▊| 217/220 [00:02<00:00, 82.77it/s]
Caching latents: 100%|██████████| 220/220 [00:02<00:00, 78.12it/s]
05/30/2026 08:32:25 - INFO - __main__ - [RANK 0] ***** Running training *****
05/30/2026 08:32:25 - INFO - __main__ - [RANK 0]   Num examples = 220
05/30/2026 08:32:25 - INFO - __main__ - [RANK 0]   Num batches each epoch = 220
05/30/2026 08:32:25 - INFO - __main__ - [RANK 0]   Num Epochs = 37
05/30/2026 08:32:25 - INFO - __main__ - [RANK 0]   Instantaneous batch size per device = 1
05/30/2026 08:32:25 - INFO - __main__ - [RANK 0]   Total train batch size (w. parallel, distributed & accumulation) = 4
05/30/2026 08:32:25 - INFO - __main__ - [RANK 0]   Gradient Accumulation steps = 4
05/30/2026 08:32:25 - INFO - __main__ - [RANK 0]   Total optimization steps = 2000

Steps:   0%|          | 0/2000 [00:00<?, ?it/s]
Steps:   0%|          | 0/2000 [00:00<?, ?it/s, loss=0.235, lr=0]
Steps:   0%|          | 0/2000 [00:00<?, ?it/s, loss=0.232, lr=0]
Steps:   0%|          | 0/2000 [00:01<?, ?it/s, loss=0.379, lr=0]
Steps:   0%|          | 1/2000 [00:01<1:02:32,  1.88s/it, loss=0.379, lr=0]
Steps:   0%|          | 1/2000 [00:01<1:02:32,  1.88s/it, loss=0.152, lr=1e-6]
Steps:   0%|          | 1/2000 [00:02<1:02:32,  1.88s/it, loss=0.286, lr=1e-6]
Steps:   0%|          | 1/2000 [00:02<1:02:32,  1.88s/it, loss=0.315, lr=1e-6]
Steps:   0%|          | 1/2000 [00:03<1:02:32,  1.88s/it, loss=0.87, lr=1e-6] 
Steps:   0%|          | 2/2000 [00:03<58:36,  1.76s/it, loss=0.87, lr=1e-6]  
Steps:   0%|          | 2/2000 [00:03<58:36,  1.76s/it, loss=0.226, lr=2e-6]
Steps:   0%|          | 2/2000 [00:03<58:36,  1.76s/it, loss=0.0772, lr=2e-6]
Steps:   0%|          | 2/2000 [00:04<58:36,  1.76s/it, loss=1.41, lr=2e-6]  
Steps:   0%|          | 2/2000 [00:04<58:36,  1.76s/it, loss=0.227, lr=2e-6]
Steps:   0%|          | 3/2000 [00:05<1:01:38,  1.85s/it, loss=0.227, lr=2e-6]
Steps:   0%|          | 3/2000 [00:05<1:01:38,  1.85s/it, loss=0.727, lr=3e-6]
Steps:   0%|          | 3/2000 [00:05<1:01:38,  1.85s/it, loss=0.441, lr=3e-6]
Steps:   0%|          | 3/2000 [00:06<1:01:38,  1.85s/it, loss=0.171, lr=3e-6]
Steps:   0%|          | 3/2000 [00:06<1:01:38,  1.85s/it, loss=0.164, lr=3e-6]
Steps:   0%|          | 4/2000 [00:07<59:11,  1.78s/it, loss=0.164, lr=3e-6]  
Steps:   0%|          | 4/2000 [00:07<59:11,  1.78s/it, loss=0.263, lr=4e-6]
Steps:   0%|          | 4/2000 [00:07<59:11,  1.78s/it, loss=0.896, lr=4e-6]
Steps:   0%|          | 4/2000 [00:07<59:11,  1.78s/it, loss=0.156, lr=4e-6]
Steps:   0%|          | 4/2000 [00:08<59:11,  1.78s/it, loss=0.197, lr=4e-6]
Steps:   0%|          | 5/2000 [00:08<57:35,  1.73s/it, loss=0.197, lr=4e-6]
Steps:   0%|          | 5/2000 [00:08<57:35,  1.73s/it, loss=0.594, lr=5e-6]
Steps:   0%|          | 5/2000 [00:09<57:35,  1.73s/it, loss=0.195, lr=5e-6]
Steps:   0%|          | 5/2000 [00:09<57:35,  1.73s/it, loss=0.735, lr=5e-6]
Steps:   0%|          | 5/2000 [00:11<57:35,  1.73s/it, loss=0.212, lr=5e-6]
Steps:   0%|          | 6/2000 [00:11<1:10:18,  2.12s/it, loss=0.212, lr=5e-6]
Steps:   0%|          | 6/2000 [00:11<1:10:18,  2.12s/it, loss=0.186, lr=6e-6]
Steps:   0%|          | 6/2000 [00:12<1:10:18,  2.12s/it, loss=0.247, lr=6e-6]
Steps:   0%|          | 6/2000 [00:12<1:10:18,  2.12s/it, loss=0.113, lr=6e-6]
Steps:   0%|          | 6/2000 [00:12<1:10:18,  2.12s/it, loss=0.321, lr=6e-6]
Steps:   0%|          | 7/2000 [00:13<1:04:58,  1.96s/it, loss=0.321, lr=6e-6]
Steps:   0%|          | 7/2000 [00:13<1:04:58,  1.96s/it, loss=0.149, lr=7e-6]
Steps:   0%|          | 7/2000 [00:13<1:04:58,  1.96s/it, loss=0.0305, lr=7e-6]
Steps:   0%|          | 7/2000 [00:14<1:04:58,  1.96s/it, loss=0.125, lr=7e-6] 
Steps:   0%|          | 7/2000 [00:14<1:04:58,  1.96s/it, loss=0.237, lr=7e-6]
Steps:   0%|          | 8/2000 [00:14<1:01:46,  1.86s/it, loss=0.237, lr=7e-6]
Steps:   0%|          | 8/2000 [00:14<1:01:46,  1.86s/it, loss=0.167, lr=8e-6]
Steps:   0%|          | 8/2000 [00:15<1:01:46,  1.86s/it, loss=0.243, lr=8e-6]
Steps:   0%|          | 8/2000 [00:15<1:01:46,  1.86s/it, loss=0.189, lr=8e-6]
Steps:   0%|          | 8/2000 [00:16<1:01:46,  1.86s/it, loss=0.223, lr=8e-6]
Steps:   0%|          | 9/2000 [00:16<1:00:12,  1.81s/it, loss=0.223, lr=8e-6]
Steps:   0%|          | 9/2000 [00:16<1:00:12,  1.81s/it, loss=0.233, lr=9e-6]
Steps:   0%|          | 9/2000 [00:17<1:00:12,  1.81s/it, loss=0.25, lr=9e-6] 
Steps:   0%|          | 9/2000 [00:17<1:00:12,  1.81s/it, loss=0.0923, lr=9e-6]
Steps:   0%|          | 9/2000 [00:18<1:00:12,  1.81s/it, loss=0.126, lr=9e-6] 
Steps:   0%|          | 10/2000 [00:18<1:01:13,  1.85s/it, loss=0.126, lr=9e-6]
Steps:   0%|          | 10/2000 [00:18<1:01:13,  1.85s/it, loss=0.0659, lr=1e-5]
Steps:   0%|          | 10/2000 [00:19<1:01:13,  1.85s/it, loss=0.203, lr=1e-5] 
Steps:   0%|          | 10/2000 [00:19<1:01:13,  1.85s/it, loss=0.151, lr=1e-5]
Steps:   0%|          | 10/2000 [00:19<1:01:13,  1.85s/it, loss=0.242, lr=1e-5]
Steps:   1%|          | 11/2000 [00:20<59:09,  1.78s/it, loss=0.242, lr=1e-5]  
Steps:   1%|          | 11/2000 [00:20<59:09,  1.78s/it, loss=0.706, lr=1.1e-5]
Steps:   1%|          | 11/2000 [00:20<59:09,  1.78s/it, loss=21.4, lr=1.1e-5] 
Steps:   1%|          | 11/2000 [00:21<59:09,  1.78s/it, loss=0.329, lr=1.1e-5]
Steps:   1%|          | 11/2000 [00:21<59:09,  1.78s/it, loss=0.162, lr=1.1e-5]
Steps:   1%|          | 12/2000 [00:21<57:51,  1.75s/it, loss=0.162, lr=1.1e-5]
Steps:   1%|          | 12/2000 [00:21<57:51,  1.75s/it, loss=0.66, lr=1.2e-5] 
Steps:   1%|          | 12/2000 [00:22<57:51,  1.75s/it, loss=0.22, lr=1.2e-5]
Steps:   1%|          | 12/2000 [00:22<57:51,  1.75s/it, loss=0.181, lr=1.2e-5]
Steps:   1%|          | 12/2000 [00:23<57:51,  1.75s/it, loss=0.703, lr=1.2e-5]
Steps:   1%|          | 13/2000 [00:23<59:30,  1.80s/it, loss=0.703, lr=1.2e-5]
Steps:   1%|          | 13/2000 [00:23<59:30,  1.80s/it, loss=0.188, lr=1.3e-5]
Steps:   1%|          | 13/2000 [00:24<59:30,  1.80s/it, loss=0.548, lr=1.3e-5]
Steps:   1%|          | 13/2000 [00:24<59:30,  1.80s/it, loss=0.227, lr=1.3e-5]
Steps:   1%|          | 13/2000 [00:25<59:30,  1.80s/it, loss=0.172, lr=1.3e-5]
Steps:   1%|          | 14/2000 [00:25<57:56,  1.75s/it, loss=0.172, lr=1.3e-5]
Steps:   1%|          | 14/2000 [00:25<57:56,  1.75s/it, loss=0.43, lr=1.4e-5] 
Steps:   1%|          | 14/2000 [00:25<57:56,  1.75s/it, loss=0.156, lr=1.4e-5]
Steps:   1%|          | 14/2000 [00:26<57:56,  1.75s/it, loss=0.179, lr=1.4e-5]
Steps:   1%|          | 14/2000 [00:26<57:56,  1.75s/it, loss=0.2, lr=1.4e-5]  
Steps:   1%|          | 15/2000 [00:27<57:06,  1.73s/it, loss=0.2, lr=1.4e-5]
Steps:   1%|          | 15/2000 [00:27<57:06,  1.73s/it, loss=0.354, lr=1.5e-5]
Steps:   1%|          | 15/2000 [00:27<57:06,  1.73s/it, loss=0.879, lr=1.5e-5]
Steps:   1%|          | 15/2000 [00:27<57:06,  1.73s/it, loss=0.101, lr=1.5e-5]
Steps:   1%|          | 15/2000 [00:28<57:06,  1.73s/it, loss=0.11, lr=1.5e-5] 
Steps:   1%|          | 16/2000 [00:29<58:51,  1.78s/it, loss=0.11, lr=1.5e-5]
Steps:   1%|          | 16/2000 [00:29<58:51,  1.78s/it, loss=1.14, lr=1.6e-5]
Steps:   1%|          | 16/2000 [00:29<58:51,  1.78s/it, loss=0.239, lr=1.6e-5]
Steps:   1%|          | 16/2000 [00:29<58:51,  1.78s/it, loss=0.176, lr=1.6e-5]
Steps:   1%|          | 16/2000 [00:30<58:51,  1.78s/it, loss=0.541, lr=1.6e-5]
Steps:   1%|          | 17/2000 [00:30<57:39,  1.74s/it, loss=0.541, lr=1.6e-5]
Steps:   1%|          | 17/2000 [00:30<57:39,  1.74s/it, loss=0.266, lr=1.7e-5]
Steps:   1%|          | 17/2000 [00:31<57:39,  1.74s/it, loss=0.254, lr=1.7e-5]
Steps:   1%|          | 17/2000 [00:31<57:39,  1.74s/it, loss=0.205, lr=1.7e-5]
Steps:   1%|          | 17/2000 [00:31<57:39,  1.74s/it, loss=0.225, lr=1.7e-5]
Steps:   1%|          | 18/2000 [00:32<57:00,  1.73s/it, loss=0.225, lr=1.7e-5]
Steps:   1%|          | 18/2000 [00:32<57:00,  1.73s/it, loss=0.176, lr=1.8e-5]
Steps:   1%|          | 18/2000 [00:32<57:00,  1.73s/it, loss=1.59, lr=1.8e-5] 
Steps:   1%|          | 18/2000 [00:33<57:00,  1.73s/it, loss=0.175, lr=1.8e-5]
Steps:   1%|          | 18/2000 [00:33<57:00,  1.73s/it, loss=0.199, lr=1.8e-5]
Steps:   1%|          | 19/2000 [00:34<59:03,  1.79s/it, loss=0.199, lr=1.8e-5]
Steps:   1%|          | 19/2000 [00:34<59:03,  1.79s/it, loss=0.267, lr=1.9e-5]
Steps:   1%|          | 19/2000 [00:34<59:03,  1.79s/it, loss=0.9, lr=1.9e-5]  
Steps:   1%|          | 19/2000 [00:35<59:03,  1.79s/it, loss=0.254, lr=1.9e-5]
Steps:   1%|          | 19/2000 [00:35<59:03,  1.79s/it, loss=0.207, lr=1.9e-5]
Steps:   1%|          | 20/2000 [00:35<57:39,  1.75s/it, loss=0.207, lr=1.9e-5]
Steps:   1%|          | 20/2000 [00:35<57:39,  1.75s/it, loss=0.587, lr=2e-5]  
Steps:   1%|          | 20/2000 [00:36<57:39,  1.75s/it, loss=0.225, lr=2e-5]
Steps:   1%|          | 20/2000 [00:36<57:39,  1.75s/it, loss=0.275, lr=2e-5]
Steps:   1%|          | 20/2000 [00:37<57:39,  1.75s/it, loss=0.608, lr=2e-5]
Steps:   1%|          | 21/2000 [00:37<57:19,  1.74s/it, loss=0.608, lr=2e-5]
Steps:   1%|          | 21/2000 [00:37<57:19,  1.74s/it, loss=0.209, lr=2.1e-5]
Steps:   1%|          | 21/2000 [00:38<57:19,  1.74s/it, loss=0.749, lr=2.1e-5]
Steps:   1%|          | 21/2000 [00:38<57:19,  1.74s/it, loss=0.605, lr=2.1e-5]
Steps:   1%|          | 21/2000 [00:39<57:19,  1.74s/it, loss=0.914, lr=2.1e-5]
Steps:   1%|          | 22/2000 [00:39<58:55,  1.79s/it, loss=0.914, lr=2.1e-5]
Steps:   1%|          | 22/2000 [00:39<58:55,  1.79s/it, loss=0.211, lr=2.2e-5]
Steps:   1%|          | 22/2000 [00:39<58:55,  1.79s/it, loss=0.202, lr=2.2e-5]
Steps:   1%|          | 22/2000 [00:40<58:55,  1.79s/it, loss=0.158, lr=2.2e-5]
Steps:   1%|          | 22/2000 [00:40<58:55,  1.79s/it, loss=0.382, lr=2.2e-5]
Steps:   1%|          | 23/2000 [00:41<57:49,  1.75s/it, loss=0.382, lr=2.2e-5]
Steps:   1%|          | 23/2000 [00:41<57:49,  1.75s/it, loss=0.153, lr=2.3e-5]
Steps:   1%|          | 23/2000 [00:41<57:49,  1.75s/it, loss=0.261, lr=2.3e-5]
Steps:   1%|          | 23/2000 [00:42<57:49,  1.75s/it, loss=0.493, lr=2.3e-5]
Steps:   1%|          | 23/2000 [00:42<57:49,  1.75s/it, loss=0.263, lr=2.3e-5]
Steps:   1%|          | 24/2000 [00:42<56:51,  1.73s/it, loss=0.263, lr=2.3e-5]
Steps:   1%|          | 24/2000 [00:42<56:51,  1.73s/it, loss=0.163, lr=2.4e-5]
Steps:   1%|          | 24/2000 [00:43<56:51,  1.73s/it, loss=0.171, lr=2.4e-5]
Steps:   1%|          | 24/2000 [00:43<56:51,  1.73s/it, loss=0.179, lr=2.4e-5]
Steps:   1%|          | 24/2000 [00:44<56:51,  1.73s/it, loss=0.296, lr=2.4e-5]
Steps:   1%|▏         | 25/2000 [00:44<58:37,  1.78s/it, loss=0.296, lr=2.4e-5]
Steps:   1%|▏         | 25/2000 [00:44<58:37,  1.78s/it, loss=0.144, lr=2.5e-5]
Steps:   1%|▏         | 25/2000 [00:45<58:37,  1.78s/it, loss=0.313, lr=2.5e-5]
Steps:   1%|▏         | 25/2000 [00:45<58:37,  1.78s/it, loss=0.186, lr=2.5e-5]
Steps:   1%|▏         | 25/2000 [00:46<58:37,  1.78s/it, loss=0.14, lr=2.5e-5] 
Steps:   1%|▏         | 26/2000 [00:46<57:17,  1.74s/it, loss=0.14, lr=2.5e-5]
Steps:   1%|▏         | 26/2000 [00:46<57:17,  1.74s/it, loss=0.597, lr=2.6e-5]
Steps:   1%|▏         | 26/2000 [00:46<57:17,  1.74s/it, loss=0.517, lr=2.6e-5]
Steps:   1%|▏         | 26/2000 [00:47<57:17,  1.74s/it, loss=0.227, lr=2.6e-5]
Steps:   1%|▏         | 26/2000 [00:47<57:17,  1.74s/it, loss=0.134, lr=2.6e-5]
Steps:   1%|▏         | 27/2000 [00:48<56:43,  1.73s/it, loss=0.134, lr=2.6e-5]
Steps:   1%|▏         | 27/2000 [00:48<56:43,  1.73s/it, loss=0.179, lr=2.7e-5]
Steps:   1%|▏         | 27/2000 [00:48<56:43,  1.73s/it, loss=0.181, lr=2.7e-5]
Steps:   1%|▏         | 27/2000 [00:48<56:43,  1.73s/it, loss=0.0965, lr=2.7e-5]
Steps:   1%|▏         | 27/2000 [00:49<56:43,  1.73s/it, loss=0.624, lr=2.7e-5] 
Steps:   1%|▏         | 28/2000 [00:50<58:25,  1.78s/it, loss=0.624, lr=2.7e-5]
Steps:   1%|▏         | 28/2000 [00:50<58:25,  1.78s/it, loss=0.539, lr=2.8e-5]
Steps:   1%|▏         | 28/2000 [00:50<58:25,  1.78s/it, loss=0.188, lr=2.8e-5]
Steps:   1%|▏         | 28/2000 [00:50<58:25,  1.78s/it, loss=0.323, lr=2.8e-5]
Steps:   1%|▏         | 28/2000 [00:51<58:25,  1.78s/it, loss=0.166, lr=2.8e-5]
Steps:   1%|▏         | 29/2000 [00:51<56:57,  1.73s/it, loss=0.166, lr=2.8e-5]
Steps:   1%|▏         | 29/2000 [00:51<56:57,  1.73s/it, loss=0.211, lr=2.9e-5]
Steps:   1%|▏         | 29/2000 [00:52<56:57,  1.73s/it, loss=0.296, lr=2.9e-5]
Steps:   1%|▏         | 29/2000 [00:52<56:57,  1.73s/it, loss=0.231, lr=2.9e-5]
Steps:   1%|▏         | 29/2000 [00:52<56:57,  1.73s/it, loss=0.222, lr=2.9e-5]
Steps:   2%|▏         | 30/2000 [00:53<56:04,  1.71s/it, loss=0.222, lr=2.9e-5]
Steps:   2%|▏         | 30/2000 [00:53<56:04,  1.71s/it, loss=0.0979, lr=3e-5] 
Steps:   2%|▏         | 30/2000 [00:53<56:04,  1.71s/it, loss=0.172, lr=3e-5] 
Steps:   2%|▏         | 30/2000 [00:54<56:04,  1.71s/it, loss=0.236, lr=3e-5]
Steps:   2%|▏         | 30/2000 [00:54<56:04,  1.71s/it, loss=0.205, lr=3e-5]
Steps:   2%|▏         | 31/2000 [00:54<55:25,  1.69s/it, loss=0.205, lr=3e-5]
Steps:   2%|▏         | 31/2000 [00:54<55:25,  1.69s/it, loss=0.204, lr=3.1e-5]
Steps:   2%|▏         | 31/2000 [00:55<55:25,  1.69s/it, loss=0.184, lr=3.1e-5]
Steps:   2%|▏         | 31/2000 [00:56<55:25,  1.69s/it, loss=0.127, lr=3.1e-5]
Steps:   2%|▏         | 31/2000 [00:56<55:25,  1.69s/it, loss=0.959, lr=3.1e-5]
Steps:   2%|▏         | 32/2000 [00:56<57:31,  1.75s/it, loss=0.959, lr=3.1e-5]
Steps:   2%|▏         | 32/2000 [00:56<57:31,  1.75s/it, loss=0.24, lr=3.2e-5] 
Steps:   2%|▏         | 32/2000 [00:57<57:31,  1.75s/it, loss=0.257, lr=3.2e-5]
Steps:   2%|▏         | 32/2000 [00:57<57:31,  1.75s/it, loss=0.175, lr=3.2e-5]
Steps:   2%|▏         | 32/2000 [00:58<57:31,  1.75s/it, loss=0.104, lr=3.2e-5]
Steps:   2%|▏         | 33/2000 [00:58<56:41,  1.73s/it, loss=0.104, lr=3.2e-5]
Steps:   2%|▏         | 33/2000 [00:58<56:41,  1.73s/it, loss=0.305, lr=3.3e-5]
Steps:   2%|▏         | 33/2000 [00:58<56:41,  1.73s/it, loss=0.441, lr=3.3e-5]
Steps:   2%|▏         | 33/2000 [00:59<56:41,  1.73s/it, loss=0.0961, lr=3.3e-5]
Steps:   2%|▏         | 33/2000 [00:59<56:41,  1.73s/it, loss=0.0975, lr=3.3e-5]
Steps:   2%|▏         | 34/2000 [01:00<56:07,  1.71s/it, loss=0.0975, lr=3.3e-5]
Steps:   2%|▏         | 34/2000 [01:00<56:07,  1.71s/it, loss=0.181, lr=3.4e-5] 
Steps:   2%|▏         | 34/2000 [01:00<56:07,  1.71s/it, loss=0.181, lr=3.4e-5]
Steps:   2%|▏         | 34/2000 [01:01<56:07,  1.71s/it, loss=0.251, lr=3.4e-5]
Steps:   2%|▏         | 34/2000 [01:01<56:07,  1.71s/it, loss=0.0804, lr=3.4e-5]
Steps:   2%|▏         | 35/2000 [01:02<57:57,  1.77s/it, loss=0.0804, lr=3.4e-5]
Steps:   2%|▏         | 35/2000 [01:02<57:57,  1.77s/it, loss=0.711, lr=3.5e-5] 
Steps:   2%|▏         | 35/2000 [01:02<57:57,  1.77s/it, loss=0.663, lr=3.5e-5]
Steps:   2%|▏         | 35/2000 [01:02<57:57,  1.77s/it, loss=0.205, lr=3.5e-5]
Steps:   2%|▏         | 35/2000 [01:03<57:57,  1.77s/it, loss=0.0997, lr=3.5e-5]
Steps:   2%|▏         | 36/2000 [01:03<56:39,  1.73s/it, loss=0.0997, lr=3.5e-5]
Steps:   2%|▏         | 36/2000 [01:03<56:39,  1.73s/it, loss=0.2, lr=3.6e-5]   
Steps:   2%|▏         | 36/2000 [01:04<56:39,  1.73s/it, loss=0.183, lr=3.6e-5]
Steps:   2%|▏         | 36/2000 [01:04<56:39,  1.73s/it, loss=0.175, lr=3.6e-5]
Steps:   2%|▏         | 36/2000 [01:05<56:39,  1.73s/it, loss=0.168, lr=3.6e-5]
Steps:   2%|▏         | 37/2000 [01:05<56:04,  1.71s/it, loss=0.168, lr=3.6e-5]
Steps:   2%|▏         | 37/2000 [01:05<56:04,  1.71s/it, loss=0.281, lr=3.7e-5]
Steps:   2%|▏         | 37/2000 [01:05<56:04,  1.71s/it, loss=1.13, lr=3.7e-5] 
Steps:   2%|▏         | 37/2000 [01:06<56:04,  1.71s/it, loss=0.171, lr=3.7e-5]
Steps:   2%|▏         | 37/2000 [01:06<56:04,  1.71s/it, loss=0.18, lr=3.7e-5] 
Steps:   2%|▏         | 38/2000 [01:07<57:12,  1.75s/it, loss=0.18, lr=3.7e-5]
Steps:   2%|▏         | 38/2000 [01:07<57:12,  1.75s/it, loss=0.164, lr=3.8e-5]
Steps:   2%|▏         | 38/2000 [01:07<57:12,  1.75s/it, loss=0.133, lr=3.8e-5]
Steps:   2%|▏         | 38/2000 [01:08<57:12,  1.75s/it, loss=0.126, lr=3.8e-5]
Steps:   2%|▏         | 38/2000 [01:08<57:12,  1.75s/it, loss=0.229, lr=3.8e-5]
Steps:   2%|▏         | 39/2000 [01:08<55:55,  1.71s/it, loss=0.229, lr=3.8e-5]
Steps:   2%|▏         | 39/2000 [01:08<55:55,  1.71s/it, loss=0.179, lr=3.9e-5]
Steps:   2%|▏         | 39/2000 [01:09<55:55,  1.71s/it, loss=0.234, lr=3.9e-5]
Steps:   2%|▏         | 39/2000 [01:09<55:55,  1.71s/it, loss=0.231, lr=3.9e-5]
Steps:   2%|▏         | 39/2000 [01:10<55:55,  1.71s/it, loss=0.337, lr=3.9e-5]
Steps:   2%|▏         | 40/2000 [01:10<55:17,  1.69s/it, loss=0.337, lr=3.9e-5]
Steps:   2%|▏         | 40/2000 [01:10<55:17,  1.69s/it, loss=0.275, lr=4e-5]  
Steps:   2%|▏         | 40/2000 [01:10<55:17,  1.69s/it, loss=0.326, lr=4e-5]
Steps:   2%|▏         | 40/2000 [01:11<55:17,  1.69s/it, loss=0.232, lr=4e-5]
Steps:   2%|▏         | 40/2000 [01:12<55:17,  1.69s/it, loss=0.268, lr=4e-5]
Steps:   2%|▏         | 41/2000 [01:12<57:23,  1.76s/it, loss=0.268, lr=4e-5]
Steps:   2%|▏         | 41/2000 [01:12<57:23,  1.76s/it, loss=0.429, lr=4.1e-5]
Steps:   2%|▏         | 41/2000 [01:12<57:23,  1.76s/it, loss=0.284, lr=4.1e-5]
Steps:   2%|▏         | 41/2000 [01:13<57:23,  1.76s/it, loss=0.124, lr=4.1e-5]
Steps:   2%|▏         | 41/2000 [01:13<57:23,  1.76s/it, loss=0.243, lr=4.1e-5]
Steps:   2%|▏         | 42/2000 [01:14<56:19,  1.73s/it, loss=0.243, lr=4.1e-5]
Steps:   2%|▏         | 42/2000 [01:14<56:19,  1.73s/it, loss=0.197, lr=4.2e-5]
Steps:   2%|▏         | 42/2000 [01:14<56:19,  1.73s/it, loss=0.349, lr=4.2e-5]
Steps:   2%|▏         | 42/2000 [01:14<56:19,  1.73s/it, loss=0.191, lr=4.2e-5]
Steps:   2%|▏         | 42/2000 [01:15<56:19,  1.73s/it, loss=0.192, lr=4.2e-5]
Steps:   2%|▏         | 43/2000 [01:15<55:30,  1.70s/it, loss=0.192, lr=4.2e-5]
Steps:   2%|▏         | 43/2000 [01:15<55:30,  1.70s/it, loss=0.117, lr=4.3e-5]
Steps:   2%|▏         | 43/2000 [01:16<55:30,  1.70s/it, loss=0.245, lr=4.3e-5]
Steps:   2%|▏         | 43/2000 [01:16<55:30,  1.70s/it, loss=0.397, lr=4.3e-5]
Steps:   2%|▏         | 43/2000 [01:17<55:30,  1.70s/it, loss=0.352, lr=4.3e-5]
Steps:   2%|▏         | 44/2000 [01:17<57:04,  1.75s/it, loss=0.352, lr=4.3e-5]
Steps:   2%|▏         | 44/2000 [01:17<57:04,  1.75s/it, loss=0.192, lr=4.4e-5]
Steps:   2%|▏         | 44/2000 [01:18<57:04,  1.75s/it, loss=0.252, lr=4.4e-5]
Steps:   2%|▏         | 44/2000 [01:18<57:04,  1.75s/it, loss=0.158, lr=4.4e-5]
Steps:   2%|▏         | 44/2000 [01:18<57:04,  1.75s/it, loss=0.114, lr=4.4e-5]
Steps:   2%|▏         | 45/2000 [01:19<56:32,  1.74s/it, loss=0.114, lr=4.4e-5]
Steps:   2%|▏         | 45/2000 [01:19<56:32,  1.74s/it, loss=0.181, lr=4.5e-5]
Steps:   2%|▏         | 45/2000 [01:19<56:32,  1.74s/it, loss=0.257, lr=4.5e-5]
Steps:   2%|▏         | 45/2000 [01:20<56:32,  1.74s/it, loss=0.0849, lr=4.5e-5]
Steps:   2%|▏         | 45/2000 [01:20<56:32,  1.74s/it, loss=0.156, lr=4.5e-5] 
Steps:   2%|▏         | 46/2000 [01:20<55:38,  1.71s/it, loss=0.156, lr=4.5e-5]
Steps:   2%|▏         | 46/2000 [01:20<55:38,  1.71s/it, loss=0.224, lr=4.6e-5]
Steps:   2%|▏         | 46/2000 [01:21<55:38,  1.71s/it, loss=0.171, lr=4.6e-5]
Steps:   2%|▏         | 46/2000 [01:21<55:38,  1.71s/it, loss=0.255, lr=4.6e-5]
Steps:   2%|▏         | 46/2000 [01:22<55:38,  1.71s/it, loss=0.678, lr=4.6e-5]
Steps:   2%|▏         | 47/2000 [01:22<57:25,  1.76s/it, loss=0.678, lr=4.6e-5]
Steps:   2%|▏         | 47/2000 [01:22<57:25,  1.76s/it, loss=0.669, lr=4.7e-5]
Steps:   2%|▏         | 47/2000 [01:23<57:25,  1.76s/it, loss=0.177, lr=4.7e-5]
Steps:   2%|▏         | 47/2000 [01:23<57:25,  1.76s/it, loss=0.205, lr=4.7e-5]
Steps:   2%|▏         | 47/2000 [01:24<57:25,  1.76s/it, loss=0.318, lr=4.7e-5]
Steps:   2%|▏         | 48/2000 [01:24<56:23,  1.73s/it, loss=0.318, lr=4.7e-5]
Steps:   2%|▏         | 48/2000 [01:24<56:23,  1.73s/it, loss=0.428, lr=4.8e-5]
Steps:   2%|▏         | 48/2000 [01:24<56:23,  1.73s/it, loss=0.163, lr=4.8e-5]
Steps:   2%|▏         | 48/2000 [01:25<56:23,  1.73s/it, loss=0.0983, lr=4.8e-5]
Steps:   2%|▏         | 48/2000 [01:25<56:23,  1.73s/it, loss=0.241, lr=4.8e-5] 
Steps:   2%|▏         | 49/2000 [01:26<55:37,  1.71s/it, loss=0.241, lr=4.8e-5]
Steps:   2%|▏         | 49/2000 [01:26<55:37,  1.71s/it, loss=0.171, lr=4.9e-5]
Steps:   2%|▏         | 49/2000 [01:26<55:37,  1.71s/it, loss=0.409, lr=4.9e-5]
Steps:   2%|▏         | 49/2000 [01:27<55:37,  1.71s/it, loss=0.255, lr=4.9e-5]
Steps:   2%|▏         | 49/2000 [01:27<55:37,  1.71s/it, loss=0.241, lr=4.9e-5]
Steps:   2%|▎         | 50/2000 [01:28<57:12,  1.76s/it, loss=0.241, lr=4.9e-5]
Steps:   2%|▎         | 50/2000 [01:28<57:12,  1.76s/it, loss=0.249, lr=5e-5]  
Steps:   2%|▎         | 50/2000 [01:28<57:12,  1.76s/it, loss=0.648, lr=5e-5]
Steps:   2%|▎         | 50/2000 [01:28<57:12,  1.76s/it, loss=0.424, lr=5e-5]
Steps:   2%|▎         | 50/2000 [01:29<57:12,  1.76s/it, loss=0.152, lr=5e-5]
Steps:   3%|▎         | 51/2000 [01:29<56:16,  1.73s/it, loss=0.152, lr=5e-5]
Steps:   3%|▎         | 51/2000 [01:29<56:16,  1.73s/it, loss=0.164, lr=5.1e-5]
Steps:   3%|▎         | 51/2000 [01:30<56:16,  1.73s/it, loss=0.689, lr=5.1e-5]
Steps:   3%|▎         | 51/2000 [01:30<56:16,  1.73s/it, loss=0.323, lr=5.1e-5]
Steps:   3%|▎         | 51/2000 [01:31<56:16,  1.73s/it, loss=0.275, lr=5.1e-5]
Steps:   3%|▎         | 52/2000 [01:31<56:02,  1.73s/it, loss=0.275, lr=5.1e-5]
Steps:   3%|▎         | 52/2000 [01:31<56:02,  1.73s/it, loss=0.248, lr=5.2e-5]
Steps:   3%|▎         | 52/2000 [01:31<56:02,  1.73s/it, loss=0.219, lr=5.2e-5]
Steps:   3%|▎         | 52/2000 [01:32<56:02,  1.73s/it, loss=0.101, lr=5.2e-5]
Steps:   3%|▎         | 52/2000 [01:32<56:02,  1.73s/it, loss=0.505, lr=5.2e-5]
Steps:   3%|▎         | 53/2000 [01:33<55:50,  1.72s/it, loss=0.505, lr=5.2e-5]
Steps:   3%|▎         | 53/2000 [01:33<55:50,  1.72s/it, loss=0.148, lr=5.3e-5]
Steps:   3%|▎         | 53/2000 [01:33<55:50,  1.72s/it, loss=0.417, lr=5.3e-5]
Steps:   3%|▎         | 53/2000 [01:34<55:50,  1.72s/it, loss=0.488, lr=5.3e-5]
Steps:   3%|▎         | 53/2000 [01:34<55:50,  1.72s/it, loss=0.0904, lr=5.3e-5]
Steps:   3%|▎         | 54/2000 [01:35<57:42,  1.78s/it, loss=0.0904, lr=5.3e-5]
Steps:   3%|▎         | 54/2000 [01:35<57:42,  1.78s/it, loss=0.197, lr=5.4e-5] 
Steps:   3%|▎         | 54/2000 [01:35<57:42,  1.78s/it, loss=0.151, lr=5.4e-5]
Steps:   3%|▎         | 54/2000 [01:35<57:42,  1.78s/it, loss=0.181, lr=5.4e-5]
Steps:   3%|▎         | 54/2000 [01:36<57:42,  1.78s/it, loss=0.2, lr=5.4e-5]  
Steps:   3%|▎         | 55/2000 [01:36<57:12,  1.76s/it, loss=0.2, lr=5.4e-5]
Steps:   3%|▎         | 55/2000 [01:36<57:12,  1.76s/it, loss=0.182, lr=5.5e-5]05/30/2026 08:34:01 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/config.json "HTTP/1.1 200 OK"
05/30/2026 08:34:02 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/config.json "HTTP/1.1 200 OK"
05/30/2026 08:34:02 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/model.safetensors "HTTP/1.1 302 Found"


Loading weights:   0%|          | 0/196 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 196/196 [00:00<00:00, 6114.65it/s]
05/30/2026 08:34:02 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/config.json "HTTP/1.1 200 OK"
05/30/2026 08:34:02 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/config.json "HTTP/1.1 200 OK"
05/30/2026 08:34:02 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/model.safetensors "HTTP/1.1 404 Not Found"
05/30/2026 08:34:02 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/model.safetensors.index.json "HTTP/1.1 200 OK"
05/30/2026 08:34:02 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev/revision/main "HTTP/1.1 200 OK"


Fetching 2 files:   0%|          | 0/2 [00:00<?, ?it/s]
Fetching 2 files: 100%|██████████| 2/2 [00:00<00:00, 8848.74it/s]


Loading weights:   0%|          | 0/219 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 219/219 [00:00<00:00, 5691.83it/s]
05/30/2026 08:34:03 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev "HTTP/1.1 200 OK"
05/30/2026 08:34:03 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/model_index.json "HTTP/1.1 200 OK"
{'feature_extractor', 'image_encoder'} was not found in config. Values will be initialized to default values.


Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]Loaded tokenizer_2 as T5TokenizerFast from `tokenizer_2` subfolder of black-forest-labs/FLUX.1-dev.


Loading pipeline components...:  43%|████▎     | 3/7 [00:00<00:00, 15.93it/s]Loaded tokenizer as CLIPTokenizer from `tokenizer` subfolder of black-forest-labs/FLUX.1-dev.
{'stochastic_sampling', 'use_beta_sigmas', 'invert_sigmas', 'time_shift_type', 'use_exponential_sigmas', 'shift_terminal', 'use_karras_sigmas'} was not found in config. Values will be initialized to default values.
Loaded scheduler as FlowMatchEulerDiscreteScheduler from `scheduler` subfolder of black-forest-labs/FLUX.1-dev.

Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 27.62it/s]
05/30/2026 08:34:03 - INFO - __main__ - [RANK 0] Running validation... 
 Generating 1 images with prompt: emj icon of a pelican with a hat, centered on a plain white background.

Steps:   3%|▎         | 55/2000 [01:49<57:12,  1.76s/it, loss=0.15, lr=5.5e-5] 
Steps:   3%|▎         | 55/2000 [01:49<57:12,  1.76s/it, loss=0.576, lr=5.5e-5]
Steps:   3%|▎         | 55/2000 [01:50<57:12,  1.76s/it, loss=0.19, lr=5.5e-5] 
Steps:   3%|▎         | 56/2000 [01:50<2:55:15,  5.41s/it, loss=0.19, lr=5.5e-5]
Steps:   3%|▎         | 56/2000 [01:50<2:55:15,  5.41s/it, loss=0.263, lr=5.6e-5]
Steps:   3%|▎         | 56/2000 [01:51<2:55:15,  5.41s/it, loss=0.427, lr=5.6e-5]
Steps:   3%|▎         | 56/2000 [01:51<2:55:15,  5.41s/it, loss=0.0852, lr=5.6e-5]
Steps:   3%|▎         | 56/2000 [01:51<2:55:15,  5.41s/it, loss=0.199, lr=5.6e-5] 
Steps:   3%|▎         | 57/2000 [01:52<2:18:36,  4.28s/it, loss=0.199, lr=5.6e-5]
Steps:   3%|▎         | 57/2000 [01:52<2:18:36,  4.28s/it, loss=0.232, lr=5.7e-5]
Steps:   3%|▎         | 57/2000 [01:52<2:18:36,  4.28s/it, loss=0.238, lr=5.7e-5]
Steps:   3%|▎         | 57/2000 [01:53<2:18:36,  4.28s/it, loss=0.108, lr=5.7e-5]
Steps:   3%|▎         | 57/2000 [01:53<2:18:36,  4.28s/it, loss=0.342, lr=5.7e-5]
Steps:   3%|▎         | 58/2000 [01:54<1:53:00,  3.49s/it, loss=0.342, lr=5.7e-5]
Steps:   3%|▎         | 58/2000 [01:54<1:53:00,  3.49s/it, loss=0.311, lr=5.8e-5]
Steps:   3%|▎         | 58/2000 [01:54<1:53:00,  3.49s/it, loss=0.1, lr=5.8e-5]  
Steps:   3%|▎         | 58/2000 [01:55<1:53:00,  3.49s/it, loss=0.156, lr=5.8e-5]
Steps:   3%|▎         | 58/2000 [01:55<1:53:00,  3.49s/it, loss=0.183, lr=5.8e-5]
Steps:   3%|▎         | 59/2000 [01:55<1:37:18,  3.01s/it, loss=0.183, lr=5.8e-5]
Steps:   3%|▎         | 59/2000 [01:55<1:37:18,  3.01s/it, loss=0.517, lr=5.9e-5]
Steps:   3%|▎         | 59/2000 [01:56<1:37:18,  3.01s/it, loss=0.243, lr=5.9e-5]
Steps:   3%|▎         | 59/2000 [01:56<1:37:18,  3.01s/it, loss=0.405, lr=5.9e-5]
Steps:   3%|▎         | 59/2000 [01:57<1:37:18,  3.01s/it, loss=0.684, lr=5.9e-5]
Steps:   3%|▎         | 60/2000 [01:57<1:23:49,  2.59s/it, loss=0.684, lr=5.9e-5]
Steps:   3%|▎         | 60/2000 [01:57<1:23:49,  2.59s/it, loss=0.186, lr=6e-5]  
Steps:   3%|▎         | 60/2000 [01:57<1:23:49,  2.59s/it, loss=0.151, lr=6e-5]
Steps:   3%|▎         | 60/2000 [01:58<1:23:49,  2.59s/it, loss=0.245, lr=6e-5]
Steps:   3%|▎         | 60/2000 [01:58<1:23:49,  2.59s/it, loss=0.145, lr=6e-5]
Steps:   3%|▎         | 61/2000 [01:59<1:15:03,  2.32s/it, loss=0.145, lr=6e-5]
Steps:   3%|▎         | 61/2000 [01:59<1:15:03,  2.32s/it, loss=0.115, lr=6.1e-5]
Steps:   3%|▎         | 61/2000 [01:59<1:15:03,  2.32s/it, loss=0.306, lr=6.1e-5]
Steps:   3%|▎         | 61/2000 [02:00<1:15:03,  2.32s/it, loss=0.45, lr=6.1e-5] 
Steps:   3%|▎         | 61/2000 [02:00<1:15:03,  2.32s/it, loss=0.0826, lr=6.1e-5]
Steps:   3%|▎         | 62/2000 [02:01<1:11:18,  2.21s/it, loss=0.0826, lr=6.1e-5]
Steps:   3%|▎         | 62/2000 [02:01<1:11:18,  2.21s/it, loss=0.228, lr=6.2e-5] 
Steps:   3%|▎         | 62/2000 [02:01<1:11:18,  2.21s/it, loss=0.123, lr=6.2e-5]
Steps:   3%|▎         | 62/2000 [02:01<1:11:18,  2.21s/it, loss=0.0537, lr=6.2e-5]
Steps:   3%|▎         | 62/2000 [02:02<1:11:18,  2.21s/it, loss=0.725, lr=6.2e-5] 
Steps:   3%|▎         | 63/2000 [02:02<1:05:38,  2.03s/it, loss=0.725, lr=6.2e-5]
Steps:   3%|▎         | 63/2000 [02:02<1:05:38,  2.03s/it, loss=0.191, lr=6.3e-5]
Steps:   3%|▎         | 63/2000 [02:03<1:05:38,  2.03s/it, loss=0.374, lr=6.3e-5]
Steps:   3%|▎         | 63/2000 [02:03<1:05:38,  2.03s/it, loss=0.109, lr=6.3e-5]
Steps:   3%|▎         | 63/2000 [02:04<1:05:38,  2.03s/it, loss=0.26, lr=6.3e-5] 
Steps:   3%|▎         | 64/2000 [02:04<1:02:05,  1.92s/it, loss=0.26, lr=6.3e-5]
Steps:   3%|▎         | 64/2000 [02:04<1:02:05,  1.92s/it, loss=0.228, lr=6.4e-5]
Steps:   3%|▎         | 64/2000 [02:04<1:02:05,  1.92s/it, loss=0.235, lr=6.4e-5]
Steps:   3%|▎         | 64/2000 [02:05<1:02:05,  1.92s/it, loss=0.244, lr=6.4e-5]
Steps:   3%|▎         | 64/2000 [02:05<1:02:05,  1.92s/it, loss=0.201, lr=6.4e-5]
Steps:   3%|▎         | 65/2000 [02:06<1:01:57,  1.92s/it, loss=0.201, lr=6.4e-5]
Steps:   3%|▎         | 65/2000 [02:06<1:01:57,  1.92s/it, loss=0.227, lr=6.5e-5]
Steps:   3%|▎         | 65/2000 [02:06<1:01:57,  1.92s/it, loss=0.157, lr=6.5e-5]
Steps:   3%|▎         | 65/2000 [02:07<1:01:57,  1.92s/it, loss=0.0999, lr=6.5e-5]
Steps:   3%|▎         | 65/2000 [02:07<1:01:57,  1.92s/it, loss=0.236, lr=6.5e-5] 
Steps:   3%|▎         | 66/2000 [02:07<58:59,  1.83s/it, loss=0.236, lr=6.5e-5]  
Steps:   3%|▎         | 66/2000 [02:07<58:59,  1.83s/it, loss=0.406, lr=6.6e-5]
Steps:   3%|▎         | 66/2000 [02:08<58:59,  1.83s/it, loss=0.244, lr=6.6e-5]
Steps:   3%|▎         | 66/2000 [02:08<58:59,  1.83s/it, loss=0.0824, lr=6.6e-5]
Steps:   3%|▎         | 66/2000 [02:09<58:59,  1.83s/it, loss=2.09, lr=6.6e-5]  
Steps:   3%|▎         | 67/2000 [02:09<57:04,  1.77s/it, loss=2.09, lr=6.6e-5]
Steps:   3%|▎         | 67/2000 [02:09<57:04,  1.77s/it, loss=0.33, lr=6.7e-5]
Steps:   3%|▎         | 67/2000 [02:10<57:04,  1.77s/it, loss=0.201, lr=6.7e-5]
Steps:   3%|▎         | 67/2000 [02:10<57:04,  1.77s/it, loss=1.15, lr=6.7e-5] 
Steps:   3%|▎         | 67/2000 [02:11<57:04,  1.77s/it, loss=0.207, lr=6.7e-5]
Steps:   3%|▎         | 68/2000 [02:11<58:16,  1.81s/it, loss=0.207, lr=6.7e-5]
Steps:   3%|▎         | 68/2000 [02:11<58:16,  1.81s/it, loss=0.169, lr=6.8e-5]
Steps:   3%|▎         | 68/2000 [02:11<58:16,  1.81s/it, loss=0.117, lr=6.8e-5]
Steps:   3%|▎         | 68/2000 [02:12<58:16,  1.81s/it, loss=0.306, lr=6.8e-5]
Steps:   3%|▎         | 68/2000 [02:12<58:16,  1.81s/it, loss=0.191, lr=6.8e-5]
Steps:   3%|▎         | 69/2000 [02:13<56:32,  1.76s/it, loss=0.191, lr=6.8e-5]
Steps:   3%|▎         | 69/2000 [02:13<56:32,  1.76s/it, loss=0.337, lr=6.9e-5]
Steps:   3%|▎         | 69/2000 [02:13<56:32,  1.76s/it, loss=0.137, lr=6.9e-5]
Steps:   3%|▎         | 69/2000 [02:13<56:32,  1.76s/it, loss=0.177, lr=6.9e-5]
Steps:   3%|▎         | 69/2000 [02:14<56:32,  1.76s/it, loss=0.233, lr=6.9e-5]
Steps:   4%|▎         | 70/2000 [02:14<55:13,  1.72s/it, loss=0.233, lr=6.9e-5]
Steps:   4%|▎         | 70/2000 [02:14<55:13,  1.72s/it, loss=0.172, lr=7e-5]  
Steps:   4%|▎         | 70/2000 [02:15<55:13,  1.72s/it, loss=0.18, lr=7e-5] 
Steps:   4%|▎         | 70/2000 [02:15<55:13,  1.72s/it, loss=0.39, lr=7e-5]
Steps:   4%|▎         | 70/2000 [02:16<55:13,  1.72s/it, loss=0.202, lr=7e-5]
Steps:   4%|▎         | 71/2000 [02:16<56:52,  1.77s/it, loss=0.202, lr=7e-5]
Steps:   4%|▎         | 71/2000 [02:16<56:52,  1.77s/it, loss=0.194, lr=7.1e-5]
Steps:   4%|▎         | 71/2000 [02:17<56:52,  1.77s/it, loss=0.174, lr=7.1e-5]
Steps:   4%|▎         | 71/2000 [02:17<56:52,  1.77s/it, loss=0.491, lr=7.1e-5]
Steps:   4%|▎         | 71/2000 [02:17<56:52,  1.77s/it, loss=0.21, lr=7.1e-5] 
Steps:   4%|▎         | 72/2000 [02:18<55:36,  1.73s/it, loss=0.21, lr=7.1e-5]
Steps:   4%|▎         | 72/2000 [02:18<55:36,  1.73s/it, loss=0.134, lr=7.2e-5]
Steps:   4%|▎         | 72/2000 [02:18<55:36,  1.73s/it, loss=0.258, lr=7.2e-5]
Steps:   4%|▎         | 72/2000 [02:19<55:36,  1.73s/it, loss=0.191, lr=7.2e-5]
Steps:   4%|▎         | 72/2000 [02:19<55:36,  1.73s/it, loss=0.146, lr=7.2e-5]
Steps:   4%|▎         | 73/2000 [02:19<54:37,  1.70s/it, loss=0.146, lr=7.2e-5]
Steps:   4%|▎         | 73/2000 [02:19<54:37,  1.70s/it, loss=0.203, lr=7.3e-5]
Steps:   4%|▎         | 73/2000 [02:20<54:37,  1.70s/it, loss=0.241, lr=7.3e-5]
Steps:   4%|▎         | 73/2000 [02:20<54:37,  1.70s/it, loss=0.16, lr=7.3e-5] 
Steps:   4%|▎         | 73/2000 [02:21<54:37,  1.70s/it, loss=0.175, lr=7.3e-5]
Steps:   4%|▎         | 74/2000 [02:21<56:43,  1.77s/it, loss=0.175, lr=7.3e-5]
Steps:   4%|▎         | 74/2000 [02:21<56:43,  1.77s/it, loss=0.152, lr=7.4e-5]
Steps:   4%|▎         | 74/2000 [02:22<56:43,  1.77s/it, loss=0.127, lr=7.4e-5]
Steps:   4%|▎         | 74/2000 [02:22<56:43,  1.77s/it, loss=0.184, lr=7.4e-5]
Steps:   4%|▎         | 74/2000 [02:23<56:43,  1.77s/it, loss=0.197, lr=7.4e-5]
Steps:   4%|▍         | 75/2000 [02:23<55:29,  1.73s/it, loss=0.197, lr=7.4e-5]
Steps:   4%|▍         | 75/2000 [02:23<55:29,  1.73s/it, loss=0.535, lr=7.5e-5]
Steps:   4%|▍         | 75/2000 [02:23<55:29,  1.73s/it, loss=0.191, lr=7.5e-5]
Steps:   4%|▍         | 75/2000 [02:24<55:29,  1.73s/it, loss=0.174, lr=7.5e-5]
Steps:   4%|▍         | 75/2000 [02:24<55:29,  1.73s/it, loss=0.502, lr=7.5e-5]
Steps:   4%|▍         | 76/2000 [02:25<54:41,  1.71s/it, loss=0.502, lr=7.5e-5]
Steps:   4%|▍         | 76/2000 [02:25<54:41,  1.71s/it, loss=0.19, lr=7.6e-5] 
Steps:   4%|▍         | 76/2000 [02:25<54:41,  1.71s/it, loss=0.648, lr=7.6e-5]
Steps:   4%|▍         | 76/2000 [02:25<54:41,  1.71s/it, loss=0.105, lr=7.6e-5]
Steps:   4%|▍         | 76/2000 [02:26<54:41,  1.71s/it, loss=0.266, lr=7.6e-5]
Steps:   4%|▍         | 77/2000 [02:27<56:33,  1.76s/it, loss=0.266, lr=7.6e-5]
Steps:   4%|▍         | 77/2000 [02:27<56:33,  1.76s/it, loss=0.166, lr=7.7e-5]
Steps:   4%|▍         | 77/2000 [02:27<56:33,  1.76s/it, loss=0.174, lr=7.7e-5]
Steps:   4%|▍         | 77/2000 [02:27<56:33,  1.76s/it, loss=0.159, lr=7.7e-5]
Steps:   4%|▍         | 77/2000 [02:28<56:33,  1.76s/it, loss=0.159, lr=7.7e-5]
Steps:   4%|▍         | 78/2000 [02:28<55:29,  1.73s/it, loss=0.159, lr=7.7e-5]
Steps:   4%|▍         | 78/2000 [02:28<55:29,  1.73s/it, loss=0.134, lr=7.8e-5]
Steps:   4%|▍         | 78/2000 [02:29<55:29,  1.73s/it, loss=0.288, lr=7.8e-5]
Steps:   4%|▍         | 78/2000 [02:29<55:29,  1.73s/it, loss=0.105, lr=7.8e-5]
Steps:   4%|▍         | 78/2000 [02:29<55:29,  1.73s/it, loss=0.224, lr=7.8e-5]
Steps:   4%|▍         | 79/2000 [02:30<54:37,  1.71s/it, loss=0.224, lr=7.8e-5]
Steps:   4%|▍         | 79/2000 [02:30<54:37,  1.71s/it, loss=0.159, lr=7.9e-5]
Steps:   4%|▍         | 79/2000 [02:30<54:37,  1.71s/it, loss=0.181, lr=7.9e-5]
Steps:   4%|▍         | 79/2000 [02:31<54:37,  1.71s/it, loss=0.185, lr=7.9e-5]
Steps:   4%|▍         | 79/2000 [02:31<54:37,  1.71s/it, loss=0.156, lr=7.9e-5]
Steps:   4%|▍         | 80/2000 [02:32<54:13,  1.69s/it, loss=0.156, lr=7.9e-5]
Steps:   4%|▍         | 80/2000 [02:32<54:13,  1.69s/it, loss=0.218, lr=8e-5]  
Steps:   4%|▍         | 80/2000 [02:32<54:13,  1.69s/it, loss=0.143, lr=8e-5]
Steps:   4%|▍         | 80/2000 [02:33<54:13,  1.69s/it, loss=0.0974, lr=8e-5]
Steps:   4%|▍         | 80/2000 [02:33<54:13,  1.69s/it, loss=0.149, lr=8e-5] 
Steps:   4%|▍         | 81/2000 [02:33<56:04,  1.75s/it, loss=0.149, lr=8e-5]
Steps:   4%|▍         | 81/2000 [02:33<56:04,  1.75s/it, loss=0.234, lr=8.1e-5]
Steps:   4%|▍         | 81/2000 [02:34<56:04,  1.75s/it, loss=0.136, lr=8.1e-5]
Steps:   4%|▍         | 81/2000 [02:34<56:04,  1.75s/it, loss=0.317, lr=8.1e-5]
Steps:   4%|▍         | 81/2000 [02:35<56:04,  1.75s/it, loss=0.231, lr=8.1e-5]
Steps:   4%|▍         | 82/2000 [02:35<55:12,  1.73s/it, loss=0.231, lr=8.1e-5]
Steps:   4%|▍         | 82/2000 [02:35<55:12,  1.73s/it, loss=0.152, lr=8.2e-5]
Steps:   4%|▍         | 82/2000 [02:35<55:12,  1.73s/it, loss=0.177, lr=8.2e-5]
Steps:   4%|▍         | 82/2000 [02:36<55:12,  1.73s/it, loss=0.132, lr=8.2e-5]
Steps:   4%|▍         | 82/2000 [02:36<55:12,  1.73s/it, loss=0.197, lr=8.2e-5]
Steps:   4%|▍         | 83/2000 [02:37<54:26,  1.70s/it, loss=0.197, lr=8.2e-5]
Steps:   4%|▍         | 83/2000 [02:37<54:26,  1.70s/it, loss=0.243, lr=8.3e-5]
Steps:   4%|▍         | 83/2000 [02:37<54:26,  1.70s/it, loss=0.277, lr=8.3e-5]
Steps:   4%|▍         | 83/2000 [02:38<54:26,  1.70s/it, loss=0.183, lr=8.3e-5]
Steps:   4%|▍         | 83/2000 [02:38<54:26,  1.70s/it, loss=0.435, lr=8.3e-5]
Steps:   4%|▍         | 84/2000 [02:39<56:04,  1.76s/it, loss=0.435, lr=8.3e-5]
Steps:   4%|▍         | 84/2000 [02:39<56:04,  1.76s/it, loss=0.178, lr=8.4e-5]
Steps:   4%|▍         | 84/2000 [02:39<56:04,  1.76s/it, loss=0.322, lr=8.4e-5]
Steps:   4%|▍         | 84/2000 [02:39<56:04,  1.76s/it, loss=0.299, lr=8.4e-5]
Steps:   4%|▍         | 84/2000 [02:40<56:04,  1.76s/it, loss=0.169, lr=8.4e-5]
Steps:   4%|▍         | 85/2000 [02:40<55:12,  1.73s/it, loss=0.169, lr=8.4e-5]
Steps:   4%|▍         | 85/2000 [02:40<55:12,  1.73s/it, loss=0.189, lr=8.5e-5]
Steps:   4%|▍         | 85/2000 [02:41<55:12,  1.73s/it, loss=0.23, lr=8.5e-5] 
Steps:   4%|▍         | 85/2000 [02:41<55:12,  1.73s/it, loss=0.206, lr=8.5e-5]
Steps:   4%|▍         | 85/2000 [02:41<55:12,  1.73s/it, loss=0.179, lr=8.5e-5]
Steps:   4%|▍         | 86/2000 [02:42<54:10,  1.70s/it, loss=0.179, lr=8.5e-5]
Steps:   4%|▍         | 86/2000 [02:42<54:10,  1.70s/it, loss=0.131, lr=8.6e-5]
Steps:   4%|▍         | 86/2000 [02:42<54:10,  1.70s/it, loss=0.115, lr=8.6e-5]
Steps:   4%|▍         | 86/2000 [02:43<54:10,  1.70s/it, loss=0.157, lr=8.6e-5]
Steps:   4%|▍         | 86/2000 [02:43<54:10,  1.70s/it, loss=0.19, lr=8.6e-5] 
Steps:   4%|▍         | 87/2000 [02:44<55:45,  1.75s/it, loss=0.19, lr=8.6e-5]
Steps:   4%|▍         | 87/2000 [02:44<55:45,  1.75s/it, loss=0.0769, lr=8.7e-5]
Steps:   4%|▍         | 87/2000 [02:44<55:45,  1.75s/it, loss=0.328, lr=8.7e-5] 
Steps:   4%|▍         | 87/2000 [02:45<55:45,  1.75s/it, loss=0.159, lr=8.7e-5]
Steps:   4%|▍         | 87/2000 [02:45<55:45,  1.75s/it, loss=0.199, lr=8.7e-5]
Steps:   4%|▍         | 88/2000 [02:45<54:31,  1.71s/it, loss=0.199, lr=8.7e-5]
Steps:   4%|▍         | 88/2000 [02:45<54:31,  1.71s/it, loss=0.105, lr=8.8e-5]
Steps:   4%|▍         | 88/2000 [02:46<54:31,  1.71s/it, loss=0.156, lr=8.8e-5]
Steps:   4%|▍         | 88/2000 [02:46<54:31,  1.71s/it, loss=0.0882, lr=8.8e-5]
Steps:   4%|▍         | 88/2000 [02:47<54:31,  1.71s/it, loss=0.138, lr=8.8e-5] 
Steps:   4%|▍         | 89/2000 [02:47<53:40,  1.69s/it, loss=0.138, lr=8.8e-5]
Steps:   4%|▍         | 89/2000 [02:47<53:40,  1.69s/it, loss=0.147, lr=8.9e-5]
Steps:   4%|▍         | 89/2000 [02:47<53:40,  1.69s/it, loss=0.183, lr=8.9e-5]
Steps:   4%|▍         | 89/2000 [02:48<53:40,  1.69s/it, loss=0.453, lr=8.9e-5]
Steps:   4%|▍         | 89/2000 [02:48<53:40,  1.69s/it, loss=0.118, lr=8.9e-5]
Steps:   4%|▍         | 90/2000 [02:49<55:37,  1.75s/it, loss=0.118, lr=8.9e-5]
Steps:   4%|▍         | 90/2000 [02:49<55:37,  1.75s/it, loss=0.0923, lr=9e-5] 
Steps:   4%|▍         | 90/2000 [02:49<55:37,  1.75s/it, loss=0.199, lr=9e-5] 
Steps:   4%|▍         | 90/2000 [02:50<55:37,  1.75s/it, loss=0.269, lr=9e-5]
Steps:   4%|▍         | 90/2000 [02:50<55:37,  1.75s/it, loss=0.193, lr=9e-5]
Steps:   5%|▍         | 91/2000 [02:51<54:25,  1.71s/it, loss=0.193, lr=9e-5]
Steps:   5%|▍         | 91/2000 [02:51<54:25,  1.71s/it, loss=0.175, lr=9.1e-5]
Steps:   5%|▍         | 91/2000 [02:51<54:25,  1.71s/it, loss=0.179, lr=9.1e-5]
Steps:   5%|▍         | 91/2000 [02:51<54:25,  1.71s/it, loss=0.119, lr=9.1e-5]
Steps:   5%|▍         | 91/2000 [02:52<54:25,  1.71s/it, loss=0.202, lr=9.1e-5]
Steps:   5%|▍         | 92/2000 [02:52<53:45,  1.69s/it, loss=0.202, lr=9.1e-5]
Steps:   5%|▍         | 92/2000 [02:52<53:45,  1.69s/it, loss=0.0641, lr=9.2e-5]
Steps:   5%|▍         | 92/2000 [02:53<53:45,  1.69s/it, loss=0.268, lr=9.2e-5] 
Steps:   5%|▍         | 92/2000 [02:53<53:45,  1.69s/it, loss=0.185, lr=9.2e-5]
Steps:   5%|▍         | 92/2000 [02:54<53:45,  1.69s/it, loss=0.209, lr=9.2e-5]
Steps:   5%|▍         | 93/2000 [02:54<55:34,  1.75s/it, loss=0.209, lr=9.2e-5]
Steps:   5%|▍         | 93/2000 [02:54<55:34,  1.75s/it, loss=0.797, lr=9.3e-5]
Steps:   5%|▍         | 93/2000 [02:54<55:34,  1.75s/it, loss=0.668, lr=9.3e-5]
Steps:   5%|▍         | 93/2000 [02:55<55:34,  1.75s/it, loss=0.148, lr=9.3e-5]
Steps:   5%|▍         | 93/2000 [02:56<55:34,  1.75s/it, loss=0.147, lr=9.3e-5]
Steps:   5%|▍         | 94/2000 [02:57<1:05:00,  2.05s/it, loss=0.147, lr=9.3e-5]
Steps:   5%|▍         | 94/2000 [02:57<1:05:00,  2.05s/it, loss=0.194, lr=9.4e-5]
Steps:   5%|▍         | 94/2000 [02:57<1:05:00,  2.05s/it, loss=0.15, lr=9.4e-5] 
Steps:   5%|▍         | 94/2000 [02:58<1:05:00,  2.05s/it, loss=0.215, lr=9.4e-5]
Steps:   5%|▍         | 94/2000 [02:58<1:05:00,  2.05s/it, loss=0.209, lr=9.4e-5]
Steps:   5%|▍         | 95/2000 [02:59<1:01:47,  1.95s/it, loss=0.209, lr=9.4e-5]
Steps:   5%|▍         | 95/2000 [02:59<1:01:47,  1.95s/it, loss=0.393, lr=9.5e-5]
Steps:   5%|▍         | 95/2000 [02:59<1:01:47,  1.95s/it, loss=0.228, lr=9.5e-5]
Steps:   5%|▍         | 95/2000 [02:59<1:01:47,  1.95s/it, loss=0.183, lr=9.5e-5]
Steps:   5%|▍         | 95/2000 [03:00<1:01:47,  1.95s/it, loss=0.17, lr=9.5e-5] 
Steps:   5%|▍         | 96/2000 [03:01<1:02:17,  1.96s/it, loss=0.17, lr=9.5e-5]
Steps:   5%|▍         | 96/2000 [03:01<1:02:17,  1.96s/it, loss=0.109, lr=9.6e-5]
Steps:   5%|▍         | 96/2000 [03:01<1:02:17,  1.96s/it, loss=0.252, lr=9.6e-5]
Steps:   5%|▍         | 96/2000 [03:01<1:02:17,  1.96s/it, loss=0.223, lr=9.6e-5]
Steps:   5%|▍         | 96/2000 [03:02<1:02:17,  1.96s/it, loss=0.144, lr=9.6e-5]
Steps:   5%|▍         | 97/2000 [03:02<59:47,  1.89s/it, loss=0.144, lr=9.6e-5]  
Steps:   5%|▍         | 97/2000 [03:02<59:47,  1.89s/it, loss=0.182, lr=9.7e-5]
Steps:   5%|▍         | 97/2000 [03:03<59:47,  1.89s/it, loss=0.297, lr=9.7e-5]
Steps:   5%|▍         | 97/2000 [03:03<59:47,  1.89s/it, loss=0.185, lr=9.7e-5]
Steps:   5%|▍         | 97/2000 [03:04<59:47,  1.89s/it, loss=0.134, lr=9.7e-5]
Steps:   5%|▍         | 98/2000 [03:04<58:30,  1.85s/it, loss=0.134, lr=9.7e-5]
Steps:   5%|▍         | 98/2000 [03:04<58:30,  1.85s/it, loss=0.272, lr=9.8e-5]
Steps:   5%|▍         | 98/2000 [03:04<58:30,  1.85s/it, loss=0.363, lr=9.8e-5]
Steps:   5%|▍         | 98/2000 [03:05<58:30,  1.85s/it, loss=0.212, lr=9.8e-5]
Steps:   5%|▍         | 98/2000 [03:05<58:30,  1.85s/it, loss=0.162, lr=9.8e-5]
Steps:   5%|▍         | 99/2000 [03:06<1:00:37,  1.91s/it, loss=0.162, lr=9.8e-5]
Steps:   5%|▍         | 99/2000 [03:06<1:00:37,  1.91s/it, loss=0.353, lr=9.9e-5]
Steps:   5%|▍         | 99/2000 [03:06<1:00:37,  1.91s/it, loss=0.258, lr=9.9e-5]
Steps:   5%|▍         | 99/2000 [03:07<1:00:37,  1.91s/it, loss=0.147, lr=9.9e-5]
Steps:   5%|▍         | 99/2000 [03:07<1:00:37,  1.91s/it, loss=0.165, lr=9.9e-5]
Steps:   5%|▌         | 100/2000 [03:08<58:35,  1.85s/it, loss=0.165, lr=9.9e-5] 
Steps:   5%|▌         | 100/2000 [03:08<58:35,  1.85s/it, loss=0.207, lr=0.0001]
Steps:   5%|▌         | 100/2000 [03:08<58:35,  1.85s/it, loss=0.213, lr=0.0001]
Steps:   5%|▌         | 100/2000 [03:09<58:35,  1.85s/it, loss=0.137, lr=0.0001]
Steps:   5%|▌         | 100/2000 [03:09<58:35,  1.85s/it, loss=0.248, lr=0.0001]
Steps:   5%|▌         | 101/2000 [03:09<57:10,  1.81s/it, loss=0.248, lr=0.0001]
Steps:   5%|▌         | 101/2000 [03:09<57:10,  1.81s/it, loss=0.163, lr=0.0001]
Steps:   5%|▌         | 101/2000 [03:10<57:10,  1.81s/it, loss=0.0833, lr=0.0001]
Steps:   5%|▌         | 101/2000 [03:10<57:10,  1.81s/it, loss=0.215, lr=0.0001] 
Steps:   5%|▌         | 101/2000 [03:11<57:10,  1.81s/it, loss=0.117, lr=0.0001]
Steps:   5%|▌         | 102/2000 [03:11<56:26,  1.78s/it, loss=0.117, lr=0.0001]
Steps:   5%|▌         | 102/2000 [03:11<56:26,  1.78s/it, loss=0.602, lr=0.0001]
Steps:   5%|▌         | 102/2000 [03:12<56:26,  1.78s/it, loss=0.33, lr=0.0001] 
Steps:   5%|▌         | 102/2000 [03:12<56:26,  1.78s/it, loss=0.0991, lr=0.0001]
Steps:   5%|▌         | 102/2000 [03:13<56:26,  1.78s/it, loss=0.312, lr=0.0001] 
Steps:   5%|▌         | 103/2000 [03:13<57:31,  1.82s/it, loss=0.312, lr=0.0001]
Steps:   5%|▌         | 103/2000 [03:13<57:31,  1.82s/it, loss=0.169, lr=0.0001]
Steps:   5%|▌         | 103/2000 [03:13<57:31,  1.82s/it, loss=0.175, lr=0.0001]
Steps:   5%|▌         | 103/2000 [03:14<57:31,  1.82s/it, loss=0.148, lr=0.0001]
Steps:   5%|▌         | 103/2000 [03:14<57:31,  1.82s/it, loss=0.122, lr=0.0001]
Steps:   5%|▌         | 104/2000 [03:15<56:01,  1.77s/it, loss=0.122, lr=0.0001]
Steps:   5%|▌         | 104/2000 [03:15<56:01,  1.77s/it, loss=0.243, lr=0.0001]
Steps:   5%|▌         | 104/2000 [03:15<56:01,  1.77s/it, loss=0.222, lr=0.0001]
Steps:   5%|▌         | 104/2000 [03:16<56:01,  1.77s/it, loss=0.203, lr=0.0001]
Steps:   5%|▌         | 104/2000 [03:16<56:01,  1.77s/it, loss=0.16, lr=0.0001] 
Steps:   5%|▌         | 105/2000 [03:16<55:09,  1.75s/it, loss=0.16, lr=0.0001]
Steps:   5%|▌         | 105/2000 [03:16<55:09,  1.75s/it, loss=0.136, lr=0.0001]
Steps:   5%|▌         | 105/2000 [03:17<55:09,  1.75s/it, loss=0.245, lr=0.0001]
Steps:   5%|▌         | 105/2000 [03:17<55:09,  1.75s/it, loss=0.325, lr=0.0001]
Steps:   5%|▌         | 105/2000 [03:18<55:09,  1.75s/it, loss=0.6, lr=0.0001]  
Steps:   5%|▌         | 106/2000 [03:18<56:24,  1.79s/it, loss=0.6, lr=0.0001]
Steps:   5%|▌         | 106/2000 [03:18<56:24,  1.79s/it, loss=0.177, lr=0.0001]
Steps:   5%|▌         | 106/2000 [03:19<56:24,  1.79s/it, loss=0.219, lr=0.0001]
Steps:   5%|▌         | 106/2000 [03:19<56:24,  1.79s/it, loss=0.305, lr=0.0001]
Steps:   5%|▌         | 106/2000 [03:20<56:24,  1.79s/it, loss=0.203, lr=0.0001]
Steps:   5%|▌         | 107/2000 [03:20<54:51,  1.74s/it, loss=0.203, lr=0.0001]
Steps:   5%|▌         | 107/2000 [03:20<54:51,  1.74s/it, loss=0.113, lr=0.0001]
Steps:   5%|▌         | 107/2000 [03:20<54:51,  1.74s/it, loss=0.126, lr=0.0001]
Steps:   5%|▌         | 107/2000 [03:21<54:51,  1.74s/it, loss=0.191, lr=0.0001]
Steps:   5%|▌         | 107/2000 [03:21<54:51,  1.74s/it, loss=0.143, lr=0.0001]
Steps:   5%|▌         | 108/2000 [03:22<54:10,  1.72s/it, loss=0.143, lr=0.0001]
Steps:   5%|▌         | 108/2000 [03:22<54:10,  1.72s/it, loss=0.367, lr=0.0001]
Steps:   5%|▌         | 108/2000 [03:22<54:10,  1.72s/it, loss=0.275, lr=0.0001]
Steps:   5%|▌         | 108/2000 [03:22<54:10,  1.72s/it, loss=0.236, lr=0.0001]
Steps:   5%|▌         | 108/2000 [03:23<54:10,  1.72s/it, loss=0.18, lr=0.0001] 
Steps:   5%|▌         | 109/2000 [03:23<55:26,  1.76s/it, loss=0.18, lr=0.0001]
Steps:   5%|▌         | 109/2000 [03:23<55:26,  1.76s/it, loss=0.194, lr=0.0001]
Steps:   5%|▌         | 109/2000 [03:24<55:26,  1.76s/it, loss=0.208, lr=0.0001]
Steps:   5%|▌         | 109/2000 [03:24<55:26,  1.76s/it, loss=0.261, lr=0.0001]
Steps:   5%|▌         | 109/2000 [03:25<55:26,  1.76s/it, loss=0.287, lr=0.0001]
Steps:   6%|▌         | 110/2000 [03:25<54:06,  1.72s/it, loss=0.287, lr=0.0001]
Steps:   6%|▌         | 110/2000 [03:25<54:06,  1.72s/it, loss=0.134, lr=0.0001]
Steps:   6%|▌         | 110/2000 [03:25<54:06,  1.72s/it, loss=0.683, lr=0.0001]
Steps:   6%|▌         | 110/2000 [03:26<54:06,  1.72s/it, loss=0.106, lr=0.0001]
Steps:   6%|▌         | 110/2000 [03:26<54:06,  1.72s/it, loss=0.164, lr=0.0001]
Steps:   6%|▌         | 111/2000 [03:27<53:12,  1.69s/it, loss=0.164, lr=0.0001]
Steps:   6%|▌         | 111/2000 [03:27<53:12,  1.69s/it, loss=0.138, lr=0.0001]
Steps:   6%|▌         | 111/2000 [03:27<53:12,  1.69s/it, loss=0.201, lr=0.0001]
Steps:   6%|▌         | 111/2000 [03:28<53:12,  1.69s/it, loss=0.0991, lr=0.0001]
Steps:   6%|▌         | 111/2000 [03:28<53:12,  1.69s/it, loss=0.149, lr=0.0001] 
Steps:   6%|▌         | 112/2000 [03:29<54:42,  1.74s/it, loss=0.149, lr=0.0001]
Steps:   6%|▌         | 112/2000 [03:29<54:42,  1.74s/it, loss=0.278, lr=0.0001]
Steps:   6%|▌         | 112/2000 [03:29<54:42,  1.74s/it, loss=0.209, lr=0.0001]
Steps:   6%|▌         | 112/2000 [03:29<54:42,  1.74s/it, loss=0.0428, lr=0.0001]
Steps:   6%|▌         | 112/2000 [03:30<54:42,  1.74s/it, loss=0.198, lr=0.0001] 
Steps:   6%|▌         | 113/2000 [03:30<53:38,  1.71s/it, loss=0.198, lr=0.0001]
Steps:   6%|▌         | 113/2000 [03:30<53:38,  1.71s/it, loss=0.22, lr=0.0001] 
Steps:   6%|▌         | 113/2000 [03:31<53:38,  1.71s/it, loss=0.179, lr=0.0001]
Steps:   6%|▌         | 113/2000 [03:31<53:38,  1.71s/it, loss=0.357, lr=0.0001]
Steps:   6%|▌         | 113/2000 [03:31<53:38,  1.71s/it, loss=0.12, lr=0.0001] 
Steps:   6%|▌         | 114/2000 [03:32<53:08,  1.69s/it, loss=0.12, lr=0.0001]
Steps:   6%|▌         | 114/2000 [03:32<53:08,  1.69s/it, loss=0.0868, lr=0.0001]
Steps:   6%|▌         | 114/2000 [03:32<53:08,  1.69s/it, loss=0.277, lr=0.0001] 
Steps:   6%|▌         | 114/2000 [03:33<53:08,  1.69s/it, loss=0.172, lr=0.0001]
Steps:   6%|▌         | 114/2000 [03:33<53:08,  1.69s/it, loss=0.218, lr=0.0001]
Steps:   6%|▌         | 115/2000 [03:34<54:55,  1.75s/it, loss=0.218, lr=0.0001]
Steps:   6%|▌         | 115/2000 [03:34<54:55,  1.75s/it, loss=0.106, lr=0.0001]
Steps:   6%|▌         | 115/2000 [03:34<54:55,  1.75s/it, loss=0.104, lr=0.0001]
Steps:   6%|▌         | 115/2000 [03:35<54:55,  1.75s/it, loss=0.371, lr=0.0001]
Steps:   6%|▌         | 115/2000 [03:35<54:55,  1.75s/it, loss=0.229, lr=0.0001]
Steps:   6%|▌         | 116/2000 [03:35<54:11,  1.73s/it, loss=0.229, lr=0.0001]
Steps:   6%|▌         | 116/2000 [03:35<54:11,  1.73s/it, loss=0.128, lr=0.0001]
Steps:   6%|▌         | 116/2000 [03:36<54:11,  1.73s/it, loss=0.208, lr=0.0001]
Steps:   6%|▌         | 116/2000 [03:36<54:11,  1.73s/it, loss=0.155, lr=0.0001]
Steps:   6%|▌         | 116/2000 [03:37<54:11,  1.73s/it, loss=0.0973, lr=0.0001]
Steps:   6%|▌         | 117/2000 [03:37<53:31,  1.71s/it, loss=0.0973, lr=0.0001]
Steps:   6%|▌         | 117/2000 [03:37<53:31,  1.71s/it, loss=0.274, lr=0.0001] 
Steps:   6%|▌         | 117/2000 [03:37<53:31,  1.71s/it, loss=0.159, lr=0.0001]
Steps:   6%|▌         | 117/2000 [03:38<53:31,  1.71s/it, loss=0.328, lr=0.0001]
Steps:   6%|▌         | 117/2000 [03:38<53:31,  1.71s/it, loss=0.869, lr=0.0001]
Steps:   6%|▌         | 118/2000 [03:39<55:08,  1.76s/it, loss=0.869, lr=0.0001]
Steps:   6%|▌         | 118/2000 [03:39<55:08,  1.76s/it, loss=0.479, lr=0.0001]
Steps:   6%|▌         | 118/2000 [03:39<55:08,  1.76s/it, loss=0.175, lr=0.0001]
Steps:   6%|▌         | 118/2000 [03:40<55:08,  1.76s/it, loss=0.164, lr=0.0001]
Steps:   6%|▌         | 118/2000 [03:40<55:08,  1.76s/it, loss=0.186, lr=0.0001]
Steps:   6%|▌         | 119/2000 [03:41<54:15,  1.73s/it, loss=0.186, lr=0.0001]
Steps:   6%|▌         | 119/2000 [03:41<54:15,  1.73s/it, loss=0.254, lr=0.0001]
Steps:   6%|▌         | 119/2000 [03:41<54:15,  1.73s/it, loss=0.43, lr=0.0001] 
Steps:   6%|▌         | 119/2000 [03:41<54:15,  1.73s/it, loss=0.0987, lr=0.0001]
Steps:   6%|▌         | 119/2000 [03:42<54:15,  1.73s/it, loss=0.238, lr=0.0001] 
Steps:   6%|▌         | 120/2000 [03:42<53:34,  1.71s/it, loss=0.238, lr=0.0001]
Steps:   6%|▌         | 120/2000 [03:42<53:34,  1.71s/it, loss=0.463, lr=0.0001]
Steps:   6%|▌         | 120/2000 [03:43<53:34,  1.71s/it, loss=0.167, lr=0.0001]
Steps:   6%|▌         | 120/2000 [03:43<53:34,  1.71s/it, loss=0.085, lr=0.0001]
Steps:   6%|▌         | 120/2000 [03:43<53:34,  1.71s/it, loss=0.521, lr=0.0001]
Steps:   6%|▌         | 121/2000 [03:44<55:19,  1.77s/it, loss=0.521, lr=0.0001]
Steps:   6%|▌         | 121/2000 [03:44<55:19,  1.77s/it, loss=1.05, lr=0.0001] 
Steps:   6%|▌         | 121/2000 [03:45<55:19,  1.77s/it, loss=0.176, lr=0.0001]
Steps:   6%|▌         | 121/2000 [03:45<55:19,  1.77s/it, loss=0.263, lr=0.0001]
Steps:   6%|▌         | 121/2000 [03:45<55:19,  1.77s/it, loss=0.655, lr=0.0001]
Steps:   6%|▌         | 122/2000 [03:46<54:21,  1.74s/it, loss=0.655, lr=0.0001]
Steps:   6%|▌         | 122/2000 [03:46<54:21,  1.74s/it, loss=0.246, lr=0.0001]
Steps:   6%|▌         | 122/2000 [03:46<54:21,  1.74s/it, loss=0.586, lr=0.0001]
Steps:   6%|▌         | 122/2000 [03:47<54:21,  1.74s/it, loss=0.259, lr=0.0001]
Steps:   6%|▌         | 122/2000 [03:47<54:21,  1.74s/it, loss=0.187, lr=0.0001]
Steps:   6%|▌         | 123/2000 [03:47<53:34,  1.71s/it, loss=0.187, lr=0.0001]
Steps:   6%|▌         | 123/2000 [03:47<53:34,  1.71s/it, loss=0.133, lr=0.0001]
Steps:   6%|▌         | 123/2000 [03:48<53:34,  1.71s/it, loss=0.184, lr=0.0001]
Steps:   6%|▌         | 123/2000 [03:48<53:34,  1.71s/it, loss=0.173, lr=0.0001]
Steps:   6%|▌         | 123/2000 [03:49<53:34,  1.71s/it, loss=0.222, lr=0.0001]
Steps:   6%|▌         | 124/2000 [03:49<53:07,  1.70s/it, loss=0.222, lr=0.0001]
Steps:   6%|▌         | 124/2000 [03:49<53:07,  1.70s/it, loss=0.17, lr=0.0001] 
Steps:   6%|▌         | 124/2000 [03:50<53:07,  1.70s/it, loss=0.342, lr=0.0001]
Steps:   6%|▌         | 124/2000 [03:50<53:07,  1.70s/it, loss=0.0757, lr=0.0001]
Steps:   6%|▌         | 124/2000 [03:51<53:07,  1.70s/it, loss=0.257, lr=0.0001] 
Steps:   6%|▋         | 125/2000 [03:51<54:42,  1.75s/it, loss=0.257, lr=0.0001]
Steps:   6%|▋         | 125/2000 [03:51<54:42,  1.75s/it, loss=0.248, lr=0.0001]
Steps:   6%|▋         | 125/2000 [03:51<54:42,  1.75s/it, loss=0.0576, lr=0.0001]
Steps:   6%|▋         | 125/2000 [03:52<54:42,  1.75s/it, loss=0.314, lr=0.0001] 
Steps:   6%|▋         | 125/2000 [03:52<54:42,  1.75s/it, loss=0.261, lr=0.0001]
Steps:   6%|▋         | 126/2000 [03:53<53:43,  1.72s/it, loss=0.261, lr=0.0001]
Steps:   6%|▋         | 126/2000 [03:53<53:43,  1.72s/it, loss=0.115, lr=0.0001]
Steps:   6%|▋         | 126/2000 [03:53<53:43,  1.72s/it, loss=0.144, lr=0.0001]
Steps:   6%|▋         | 126/2000 [03:53<53:43,  1.72s/it, loss=0.0661, lr=0.0001]
Steps:   6%|▋         | 126/2000 [03:54<53:43,  1.72s/it, loss=0.247, lr=0.0001] 
Steps:   6%|▋         | 127/2000 [03:54<53:07,  1.70s/it, loss=0.247, lr=0.0001]
Steps:   6%|▋         | 127/2000 [03:54<53:07,  1.70s/it, loss=0.148, lr=0.0001]
Steps:   6%|▋         | 127/2000 [03:55<53:07,  1.70s/it, loss=0.166, lr=0.0001]
Steps:   6%|▋         | 127/2000 [03:55<53:07,  1.70s/it, loss=0.156, lr=0.0001]
Steps:   6%|▋         | 127/2000 [03:56<53:07,  1.70s/it, loss=0.157, lr=0.0001]
Steps:   6%|▋         | 128/2000 [03:56<54:48,  1.76s/it, loss=0.157, lr=0.0001]
Steps:   6%|▋         | 128/2000 [03:56<54:48,  1.76s/it, loss=0.158, lr=0.0001]
Steps:   6%|▋         | 128/2000 [03:57<54:48,  1.76s/it, loss=0.228, lr=0.0001]
Steps:   6%|▋         | 128/2000 [03:57<54:48,  1.76s/it, loss=0.624, lr=0.0001]
Steps:   6%|▋         | 128/2000 [03:57<54:48,  1.76s/it, loss=0.996, lr=0.0001]
Steps:   6%|▋         | 129/2000 [03:58<53:44,  1.72s/it, loss=0.996, lr=0.0001]
Steps:   6%|▋         | 129/2000 [03:58<53:44,  1.72s/it, loss=2.58, lr=0.0001] 
Steps:   6%|▋         | 129/2000 [03:58<53:44,  1.72s/it, loss=0.116, lr=0.0001]
Steps:   6%|▋         | 129/2000 [03:59<53:44,  1.72s/it, loss=0.184, lr=0.0001]
Steps:   6%|▋         | 129/2000 [03:59<53:44,  1.72s/it, loss=0.258, lr=0.0001]
Steps:   6%|▋         | 130/2000 [04:00<53:02,  1.70s/it, loss=0.258, lr=0.0001]
Steps:   6%|▋         | 130/2000 [04:00<53:02,  1.70s/it, loss=0.216, lr=0.0001]
Steps:   6%|▋         | 130/2000 [04:00<53:02,  1.70s/it, loss=0.337, lr=0.0001]
Steps:   6%|▋         | 130/2000 [04:00<53:02,  1.70s/it, loss=0.156, lr=0.0001]
Steps:   6%|▋         | 130/2000 [04:01<53:02,  1.70s/it, loss=0.301, lr=0.0001]
Steps:   7%|▋         | 131/2000 [04:01<54:54,  1.76s/it, loss=0.301, lr=0.0001]
Steps:   7%|▋         | 131/2000 [04:01<54:54,  1.76s/it, loss=0.236, lr=0.0001]
Steps:   7%|▋         | 131/2000 [04:02<54:54,  1.76s/it, loss=0.294, lr=0.0001]
Steps:   7%|▋         | 131/2000 [04:02<54:54,  1.76s/it, loss=0.624, lr=0.0001]
Steps:   7%|▋         | 131/2000 [04:03<54:54,  1.76s/it, loss=0.209, lr=0.0001]
Steps:   7%|▋         | 132/2000 [04:03<53:46,  1.73s/it, loss=0.209, lr=0.0001]
Steps:   7%|▋         | 132/2000 [04:03<53:46,  1.73s/it, loss=0.213, lr=0.0001]
Steps:   7%|▋         | 132/2000 [04:03<53:46,  1.73s/it, loss=0.147, lr=0.0001]
Steps:   7%|▋         | 132/2000 [04:04<53:46,  1.73s/it, loss=0.169, lr=0.0001]
Steps:   7%|▋         | 132/2000 [04:04<53:46,  1.73s/it, loss=0.165, lr=0.0001]
Steps:   7%|▋         | 133/2000 [04:05<52:58,  1.70s/it, loss=0.165, lr=0.0001]
Steps:   7%|▋         | 133/2000 [04:05<52:58,  1.70s/it, loss=0.194, lr=0.0001]
Steps:   7%|▋         | 133/2000 [04:05<52:58,  1.70s/it, loss=0.128, lr=0.0001]
Steps:   7%|▋         | 133/2000 [04:06<52:58,  1.70s/it, loss=0.984, lr=0.0001]
Steps:   7%|▋         | 133/2000 [04:06<52:58,  1.70s/it, loss=1.13, lr=0.0001] 
Steps:   7%|▋         | 134/2000 [04:07<55:07,  1.77s/it, loss=1.13, lr=0.0001]
Steps:   7%|▋         | 134/2000 [04:07<55:07,  1.77s/it, loss=0.121, lr=0.0001]
Steps:   7%|▋         | 134/2000 [04:07<55:07,  1.77s/it, loss=0.269, lr=0.0001]
Steps:   7%|▋         | 134/2000 [04:07<55:07,  1.77s/it, loss=0.211, lr=0.0001]
Steps:   7%|▋         | 134/2000 [04:08<55:07,  1.77s/it, loss=0.225, lr=0.0001]
Steps:   7%|▋         | 135/2000 [04:08<54:10,  1.74s/it, loss=0.225, lr=0.0001]
Steps:   7%|▋         | 135/2000 [04:08<54:10,  1.74s/it, loss=0.243, lr=0.0001]
Steps:   7%|▋         | 135/2000 [04:09<54:10,  1.74s/it, loss=0.253, lr=0.0001]
Steps:   7%|▋         | 135/2000 [04:09<54:10,  1.74s/it, loss=0.17, lr=0.0001] 
Steps:   7%|▋         | 135/2000 [04:10<54:10,  1.74s/it, loss=0.121, lr=0.0001]
Steps:   7%|▋         | 136/2000 [04:10<54:30,  1.75s/it, loss=0.121, lr=0.0001]
Steps:   7%|▋         | 136/2000 [04:10<54:30,  1.75s/it, loss=0.239, lr=0.0001]
Steps:   7%|▋         | 136/2000 [04:11<54:30,  1.75s/it, loss=0.741, lr=0.0001]
Steps:   7%|▋         | 136/2000 [04:11<54:30,  1.75s/it, loss=0.191, lr=0.0001]
Steps:   7%|▋         | 136/2000 [04:12<54:30,  1.75s/it, loss=0.292, lr=0.0001]
Steps:   7%|▋         | 137/2000 [04:12<56:06,  1.81s/it, loss=0.292, lr=0.0001]
Steps:   7%|▋         | 137/2000 [04:12<56:06,  1.81s/it, loss=0.167, lr=0.0001]
Steps:   7%|▋         | 137/2000 [04:12<56:06,  1.81s/it, loss=0.257, lr=0.0001]
Steps:   7%|▋         | 137/2000 [04:13<56:06,  1.81s/it, loss=0.207, lr=0.0001]
Steps:   7%|▋         | 137/2000 [04:13<56:06,  1.81s/it, loss=0.206, lr=0.0001]
Steps:   7%|▋         | 138/2000 [04:14<55:04,  1.77s/it, loss=0.206, lr=0.0001]
Steps:   7%|▋         | 138/2000 [04:14<55:04,  1.77s/it, loss=0.183, lr=0.0001]
Steps:   7%|▋         | 138/2000 [04:14<55:04,  1.77s/it, loss=0.122, lr=0.0001]
Steps:   7%|▋         | 138/2000 [04:15<55:04,  1.77s/it, loss=0.228, lr=0.0001]
Steps:   7%|▋         | 138/2000 [04:15<55:04,  1.77s/it, loss=0.238, lr=0.0001]
Steps:   7%|▋         | 139/2000 [04:15<54:07,  1.75s/it, loss=0.238, lr=0.0001]
Steps:   7%|▋         | 139/2000 [04:15<54:07,  1.75s/it, loss=0.26, lr=0.0001] 
Steps:   7%|▋         | 139/2000 [04:16<54:07,  1.75s/it, loss=0.161, lr=0.0001]
Steps:   7%|▋         | 139/2000 [04:16<54:07,  1.75s/it, loss=0.131, lr=0.0001]
Steps:   7%|▋         | 139/2000 [04:17<54:07,  1.75s/it, loss=0.243, lr=0.0001]
Steps:   7%|▋         | 140/2000 [04:17<55:23,  1.79s/it, loss=0.243, lr=0.0001]
Steps:   7%|▋         | 140/2000 [04:17<55:23,  1.79s/it, loss=0.185, lr=0.0001]
Steps:   7%|▋         | 140/2000 [04:18<55:23,  1.79s/it, loss=0.249, lr=0.0001]
Steps:   7%|▋         | 140/2000 [04:18<55:23,  1.79s/it, loss=0.191, lr=0.0001]
Steps:   7%|▋         | 140/2000 [04:19<55:23,  1.79s/it, loss=0.45, lr=0.0001] 
Steps:   7%|▋         | 141/2000 [04:19<54:04,  1.75s/it, loss=0.45, lr=0.0001]
Steps:   7%|▋         | 141/2000 [04:19<54:04,  1.75s/it, loss=0.162, lr=0.0001]
Steps:   7%|▋         | 141/2000 [04:19<54:04,  1.75s/it, loss=0.113, lr=0.0001]
Steps:   7%|▋         | 141/2000 [04:20<54:04,  1.75s/it, loss=0.145, lr=0.0001]
Steps:   7%|▋         | 141/2000 [04:20<54:04,  1.75s/it, loss=0.267, lr=0.0001]
Steps:   7%|▋         | 142/2000 [04:21<53:25,  1.73s/it, loss=0.267, lr=0.0001]
Steps:   7%|▋         | 142/2000 [04:21<53:25,  1.73s/it, loss=0.672, lr=0.0001]
Steps:   7%|▋         | 142/2000 [04:21<53:25,  1.73s/it, loss=0.217, lr=0.0001]
Steps:   7%|▋         | 142/2000 [04:21<53:25,  1.73s/it, loss=0.242, lr=0.0001]
Steps:   7%|▋         | 142/2000 [04:22<53:25,  1.73s/it, loss=0.268, lr=0.0001]
Steps:   7%|▋         | 143/2000 [04:23<55:39,  1.80s/it, loss=0.268, lr=0.0001]
Steps:   7%|▋         | 143/2000 [04:23<55:39,  1.80s/it, loss=0.16, lr=0.0001] 
Steps:   7%|▋         | 143/2000 [04:23<55:39,  1.80s/it, loss=0.336, lr=0.0001]
Steps:   7%|▋         | 143/2000 [04:23<55:39,  1.80s/it, loss=0.123, lr=0.0001]
Steps:   7%|▋         | 143/2000 [04:24<55:39,  1.80s/it, loss=0.224, lr=0.0001]
Steps:   7%|▋         | 144/2000 [04:24<54:59,  1.78s/it, loss=0.224, lr=0.0001]
Steps:   7%|▋         | 144/2000 [04:24<54:59,  1.78s/it, loss=0.601, lr=0.0001]
Steps:   7%|▋         | 144/2000 [04:25<54:59,  1.78s/it, loss=0.155, lr=0.0001]
Steps:   7%|▋         | 144/2000 [04:25<54:59,  1.78s/it, loss=0.145, lr=0.0001]
Steps:   7%|▋         | 144/2000 [04:26<54:59,  1.78s/it, loss=0.284, lr=0.0001]
Steps:   7%|▋         | 145/2000 [04:26<54:25,  1.76s/it, loss=0.284, lr=0.0001]
Steps:   7%|▋         | 145/2000 [04:26<54:25,  1.76s/it, loss=0.126, lr=0.0001]
Steps:   7%|▋         | 145/2000 [04:26<54:25,  1.76s/it, loss=0.14, lr=0.0001] 
Steps:   7%|▋         | 145/2000 [04:27<54:25,  1.76s/it, loss=0.072, lr=0.0001]
Steps:   7%|▋         | 145/2000 [04:27<54:25,  1.76s/it, loss=0.158, lr=0.0001]
Steps:   7%|▋         | 146/2000 [04:28<53:40,  1.74s/it, loss=0.158, lr=0.0001]
Steps:   7%|▋         | 146/2000 [04:28<53:40,  1.74s/it, loss=0.0979, lr=0.0001]
Steps:   7%|▋         | 146/2000 [04:28<53:40,  1.74s/it, loss=0.14, lr=0.0001]  
Steps:   7%|▋         | 146/2000 [04:29<53:40,  1.74s/it, loss=0.0614, lr=0.0001]
Steps:   7%|▋         | 146/2000 [04:29<53:40,  1.74s/it, loss=0.27, lr=0.0001]  
Steps:   7%|▋         | 147/2000 [04:30<54:57,  1.78s/it, loss=0.27, lr=0.0001]
Steps:   7%|▋         | 147/2000 [04:30<54:57,  1.78s/it, loss=0.248, lr=0.0001]
Steps:   7%|▋         | 147/2000 [04:30<54:57,  1.78s/it, loss=0.163, lr=0.0001]
Steps:   7%|▋         | 147/2000 [04:30<54:57,  1.78s/it, loss=0.494, lr=0.0001]
Steps:   7%|▋         | 147/2000 [04:31<54:57,  1.78s/it, loss=0.225, lr=0.0001]
Steps:   7%|▋         | 148/2000 [04:31<53:48,  1.74s/it, loss=0.225, lr=0.0001]
Steps:   7%|▋         | 148/2000 [04:31<53:48,  1.74s/it, loss=0.154, lr=0.0001]
Steps:   7%|▋         | 148/2000 [04:32<53:48,  1.74s/it, loss=0.165, lr=0.0001]
Steps:   7%|▋         | 148/2000 [04:32<53:48,  1.74s/it, loss=0.188, lr=0.0001]
Steps:   7%|▋         | 148/2000 [04:32<53:48,  1.74s/it, loss=0.187, lr=0.0001]
Steps:   7%|▋         | 149/2000 [04:33<52:43,  1.71s/it, loss=0.187, lr=0.0001]
Steps:   7%|▋         | 149/2000 [04:33<52:43,  1.71s/it, loss=0.144, lr=0.0001]
Steps:   7%|▋         | 149/2000 [04:33<52:43,  1.71s/it, loss=0.141, lr=0.0001]
Steps:   7%|▋         | 149/2000 [04:34<52:43,  1.71s/it, loss=0.0687, lr=0.0001]
Steps:   7%|▋         | 149/2000 [04:34<52:43,  1.71s/it, loss=0.334, lr=0.0001] 
Steps:   8%|▊         | 150/2000 [04:35<54:07,  1.76s/it, loss=0.334, lr=0.0001]
Steps:   8%|▊         | 150/2000 [04:35<54:07,  1.76s/it, loss=0.113, lr=0.0001]
Steps:   8%|▊         | 150/2000 [04:35<54:07,  1.76s/it, loss=0.174, lr=0.0001]
Steps:   8%|▊         | 150/2000 [04:36<54:07,  1.76s/it, loss=0.416, lr=0.0001]
Steps:   8%|▊         | 150/2000 [04:36<54:07,  1.76s/it, loss=0.0842, lr=0.0001]
Steps:   8%|▊         | 151/2000 [04:36<53:18,  1.73s/it, loss=0.0842, lr=0.0001]
Steps:   8%|▊         | 151/2000 [04:36<53:18,  1.73s/it, loss=0.298, lr=0.0001] 
Steps:   8%|▊         | 151/2000 [04:37<53:18,  1.73s/it, loss=0.0792, lr=0.0001]
Steps:   8%|▊         | 151/2000 [04:37<53:18,  1.73s/it, loss=0.125, lr=0.0001] 
Steps:   8%|▊         | 151/2000 [04:38<53:18,  1.73s/it, loss=0.16, lr=0.0001] 
Steps:   8%|▊         | 152/2000 [04:38<52:35,  1.71s/it, loss=0.16, lr=0.0001]
Steps:   8%|▊         | 152/2000 [04:38<52:35,  1.71s/it, loss=0.158, lr=0.0001]
Steps:   8%|▊         | 152/2000 [04:38<52:35,  1.71s/it, loss=0.18, lr=0.0001] 
Steps:   8%|▊         | 152/2000 [04:39<52:35,  1.71s/it, loss=0.184, lr=0.0001]
Steps:   8%|▊         | 152/2000 [04:40<52:35,  1.71s/it, loss=0.156, lr=0.0001]
Steps:   8%|▊         | 153/2000 [04:40<54:09,  1.76s/it, loss=0.156, lr=0.0001]
Steps:   8%|▊         | 153/2000 [04:40<54:09,  1.76s/it, loss=0.238, lr=0.0001]
Steps:   8%|▊         | 153/2000 [04:40<54:09,  1.76s/it, loss=0.128, lr=0.0001]
Steps:   8%|▊         | 153/2000 [04:41<54:09,  1.76s/it, loss=0.299, lr=0.0001]
Steps:   8%|▊         | 153/2000 [04:41<54:09,  1.76s/it, loss=0.2, lr=0.0001]  
Steps:   8%|▊         | 154/2000 [04:42<53:24,  1.74s/it, loss=0.2, lr=0.0001]
Steps:   8%|▊         | 154/2000 [04:42<53:24,  1.74s/it, loss=0.223, lr=0.0001]
Steps:   8%|▊         | 154/2000 [04:42<53:24,  1.74s/it, loss=0.24, lr=0.0001] 
Steps:   8%|▊         | 154/2000 [04:42<53:24,  1.74s/it, loss=0.153, lr=0.0001]
Steps:   8%|▊         | 154/2000 [04:43<53:24,  1.74s/it, loss=0.191, lr=0.0001]
Steps:   8%|▊         | 155/2000 [04:43<53:45,  1.75s/it, loss=0.191, lr=0.0001]
Steps:   8%|▊         | 155/2000 [04:43<53:45,  1.75s/it, loss=0.868, lr=0.0001]
Steps:   8%|▊         | 155/2000 [04:44<53:45,  1.75s/it, loss=0.53, lr=0.0001] 
Steps:   8%|▊         | 155/2000 [04:44<53:45,  1.75s/it, loss=0.139, lr=0.0001]
Steps:   8%|▊         | 155/2000 [04:45<53:45,  1.75s/it, loss=0.808, lr=0.0001]
Steps:   8%|▊         | 156/2000 [04:45<55:16,  1.80s/it, loss=0.808, lr=0.0001]
Steps:   8%|▊         | 156/2000 [04:45<55:16,  1.80s/it, loss=0.0958, lr=0.0001]
Steps:   8%|▊         | 156/2000 [04:46<55:16,  1.80s/it, loss=0.188, lr=0.0001] 
Steps:   8%|▊         | 156/2000 [04:46<55:16,  1.80s/it, loss=0.173, lr=0.0001]
Steps:   8%|▊         | 156/2000 [04:47<55:16,  1.80s/it, loss=0.166, lr=0.0001]
Steps:   8%|▊         | 157/2000 [04:47<54:00,  1.76s/it, loss=0.166, lr=0.0001]
Steps:   8%|▊         | 157/2000 [04:47<54:00,  1.76s/it, loss=0.258, lr=0.0001]
Steps:   8%|▊         | 157/2000 [04:47<54:00,  1.76s/it, loss=0.209, lr=0.0001]
Steps:   8%|▊         | 157/2000 [04:48<54:00,  1.76s/it, loss=0.149, lr=0.0001]
Steps:   8%|▊         | 157/2000 [04:48<54:00,  1.76s/it, loss=0.245, lr=0.0001]
Steps:   8%|▊         | 158/2000 [04:49<52:54,  1.72s/it, loss=0.245, lr=0.0001]
Steps:   8%|▊         | 158/2000 [04:49<52:54,  1.72s/it, loss=0.156, lr=0.0001]
Steps:   8%|▊         | 158/2000 [04:49<52:54,  1.72s/it, loss=0.19, lr=0.0001] 
Steps:   8%|▊         | 158/2000 [04:49<52:54,  1.72s/it, loss=0.13, lr=0.0001]
Steps:   8%|▊         | 158/2000 [04:50<52:54,  1.72s/it, loss=0.347, lr=0.0001]
Steps:   8%|▊         | 159/2000 [04:51<54:53,  1.79s/it, loss=0.347, lr=0.0001]
Steps:   8%|▊         | 159/2000 [04:51<54:53,  1.79s/it, loss=0.332, lr=0.0001]
Steps:   8%|▊         | 159/2000 [04:51<54:53,  1.79s/it, loss=0.156, lr=0.0001]
Steps:   8%|▊         | 159/2000 [04:51<54:53,  1.79s/it, loss=0.556, lr=0.0001]
Steps:   8%|▊         | 159/2000 [04:52<54:53,  1.79s/it, loss=0.191, lr=0.0001]
Steps:   8%|▊         | 160/2000 [04:52<53:55,  1.76s/it, loss=0.191, lr=0.0001]
Steps:   8%|▊         | 160/2000 [04:52<53:55,  1.76s/it, loss=0.197, lr=0.0001]
Steps:   8%|▊         | 160/2000 [04:53<53:55,  1.76s/it, loss=0.184, lr=0.0001]
Steps:   8%|▊         | 160/2000 [04:53<53:55,  1.76s/it, loss=0.108, lr=0.0001]
Steps:   8%|▊         | 160/2000 [04:54<53:55,  1.76s/it, loss=0.425, lr=0.0001]
Steps:   8%|▊         | 161/2000 [04:54<53:45,  1.75s/it, loss=0.425, lr=0.0001]
Steps:   8%|▊         | 161/2000 [04:54<53:45,  1.75s/it, loss=0.149, lr=0.0001]
Steps:   8%|▊         | 161/2000 [04:54<53:45,  1.75s/it, loss=0.149, lr=0.0001]
Steps:   8%|▊         | 161/2000 [04:55<53:45,  1.75s/it, loss=0.263, lr=0.0001]
Steps:   8%|▊         | 161/2000 [04:55<53:45,  1.75s/it, loss=0.122, lr=0.0001]
Steps:   8%|▊         | 162/2000 [04:56<55:36,  1.82s/it, loss=0.122, lr=0.0001]
Steps:   8%|▊         | 162/2000 [04:56<55:36,  1.82s/it, loss=0.208, lr=0.0001]
Steps:   8%|▊         | 162/2000 [04:56<55:36,  1.82s/it, loss=0.183, lr=0.0001]
Steps:   8%|▊         | 162/2000 [04:57<55:36,  1.82s/it, loss=0.374, lr=0.0001]
Steps:   8%|▊         | 162/2000 [04:57<55:36,  1.82s/it, loss=0.164, lr=0.0001]
Steps:   8%|▊         | 163/2000 [04:58<53:55,  1.76s/it, loss=0.164, lr=0.0001]
Steps:   8%|▊         | 163/2000 [04:58<53:55,  1.76s/it, loss=0.132, lr=0.0001]
Steps:   8%|▊         | 163/2000 [04:58<53:55,  1.76s/it, loss=0.184, lr=0.0001]
Steps:   8%|▊         | 163/2000 [04:58<53:55,  1.76s/it, loss=0.246, lr=0.0001]
Steps:   8%|▊         | 163/2000 [04:59<53:55,  1.76s/it, loss=0.0909, lr=0.0001]
Steps:   8%|▊         | 164/2000 [04:59<52:56,  1.73s/it, loss=0.0909, lr=0.0001]
Steps:   8%|▊         | 164/2000 [04:59<52:56,  1.73s/it, loss=0.147, lr=0.0001] 
Steps:   8%|▊         | 164/2000 [05:00<52:56,  1.73s/it, loss=1.12, lr=0.0001] 
Steps:   8%|▊         | 164/2000 [05:00<52:56,  1.73s/it, loss=0.363, lr=0.0001]
Steps:   8%|▊         | 164/2000 [05:01<52:56,  1.73s/it, loss=0.189, lr=0.0001]
Steps:   8%|▊         | 165/2000 [05:01<55:05,  1.80s/it, loss=0.189, lr=0.0001]
Steps:   8%|▊         | 165/2000 [05:01<55:05,  1.80s/it, loss=0.688, lr=0.0001]
Steps:   8%|▊         | 165/2000 [05:02<55:05,  1.80s/it, loss=0.427, lr=0.0001]
Steps:   8%|▊         | 165/2000 [05:02<55:05,  1.80s/it, loss=0.166, lr=0.0001]
Steps:   8%|▊         | 165/2000 [05:02<55:05,  1.80s/it, loss=0.283, lr=0.0001]
Steps:   8%|▊         | 166/2000 [05:03<53:30,  1.75s/it, loss=0.283, lr=0.0001]
Steps:   8%|▊         | 166/2000 [05:03<53:30,  1.75s/it, loss=0.837, lr=0.0001]
Steps:   8%|▊         | 166/2000 [05:03<53:30,  1.75s/it, loss=0.161, lr=0.0001]
Steps:   8%|▊         | 166/2000 [05:04<53:30,  1.75s/it, loss=0.186, lr=0.0001]
Steps:   8%|▊         | 166/2000 [05:04<53:30,  1.75s/it, loss=0.0682, lr=0.0001]
Steps:   8%|▊         | 167/2000 [05:05<52:27,  1.72s/it, loss=0.0682, lr=0.0001]
Steps:   8%|▊         | 167/2000 [05:05<52:27,  1.72s/it, loss=0.0871, lr=0.0001]
Steps:   8%|▊         | 167/2000 [05:05<52:27,  1.72s/it, loss=0.232, lr=0.0001] 
Steps:   8%|▊         | 167/2000 [05:05<52:27,  1.72s/it, loss=0.176, lr=0.0001]
Steps:   8%|▊         | 167/2000 [05:06<52:27,  1.72s/it, loss=0.241, lr=0.0001]
Steps:   8%|▊         | 168/2000 [05:06<52:12,  1.71s/it, loss=0.241, lr=0.0001]
Steps:   8%|▊         | 168/2000 [05:06<52:12,  1.71s/it, loss=0.426, lr=0.0001]
Steps:   8%|▊         | 168/2000 [05:07<52:12,  1.71s/it, loss=0.277, lr=0.0001]
Steps:   8%|▊         | 168/2000 [05:07<52:12,  1.71s/it, loss=0.205, lr=0.0001]
Steps:   8%|▊         | 168/2000 [05:08<52:12,  1.71s/it, loss=0.208, lr=0.0001]
Steps:   8%|▊         | 169/2000 [05:08<54:13,  1.78s/it, loss=0.208, lr=0.0001]
Steps:   8%|▊         | 169/2000 [05:08<54:13,  1.78s/it, loss=0.234, lr=0.0001]
Steps:   8%|▊         | 169/2000 [05:09<54:13,  1.78s/it, loss=0.398, lr=0.0001]
Steps:   8%|▊         | 169/2000 [05:09<54:13,  1.78s/it, loss=0.129, lr=0.0001]
Steps:   8%|▊         | 169/2000 [05:09<54:13,  1.78s/it, loss=0.193, lr=0.0001]
Steps:   8%|▊         | 170/2000 [05:10<53:32,  1.76s/it, loss=0.193, lr=0.0001]
Steps:   8%|▊         | 170/2000 [05:10<53:32,  1.76s/it, loss=0.177, lr=0.0001]
Steps:   8%|▊         | 170/2000 [05:10<53:32,  1.76s/it, loss=0.17, lr=0.0001] 
Steps:   8%|▊         | 170/2000 [05:11<53:32,  1.76s/it, loss=1.46, lr=0.0001]
Steps:   8%|▊         | 170/2000 [05:11<53:32,  1.76s/it, loss=0.146, lr=0.0001]
Steps:   9%|▊         | 171/2000 [05:11<52:35,  1.73s/it, loss=0.146, lr=0.0001]
Steps:   9%|▊         | 171/2000 [05:11<52:35,  1.73s/it, loss=0.0815, lr=0.0001]
Steps:   9%|▊         | 171/2000 [05:12<52:35,  1.73s/it, loss=0.0835, lr=0.0001]
Steps:   9%|▊         | 171/2000 [05:13<52:35,  1.73s/it, loss=0.125, lr=0.0001] 
Steps:   9%|▊         | 171/2000 [05:13<52:35,  1.73s/it, loss=0.22, lr=0.0001] 
Steps:   9%|▊         | 172/2000 [05:13<54:34,  1.79s/it, loss=0.22, lr=0.0001]
Steps:   9%|▊         | 172/2000 [05:13<54:34,  1.79s/it, loss=0.0657, lr=0.0001]
Steps:   9%|▊         | 172/2000 [05:14<54:34,  1.79s/it, loss=0.349, lr=0.0001] 
Steps:   9%|▊         | 172/2000 [05:14<54:34,  1.79s/it, loss=0.151, lr=0.0001]
Steps:   9%|▊         | 172/2000 [05:15<54:34,  1.79s/it, loss=0.0942, lr=0.0001]
Steps:   9%|▊         | 173/2000 [05:15<53:51,  1.77s/it, loss=0.0942, lr=0.0001]
Steps:   9%|▊         | 173/2000 [05:15<53:51,  1.77s/it, loss=0.0906, lr=0.0001]
Steps:   9%|▊         | 173/2000 [05:16<53:51,  1.77s/it, loss=0.157, lr=0.0001] 
Steps:   9%|▊         | 173/2000 [05:16<53:51,  1.77s/it, loss=0.152, lr=0.0001]
Steps:   9%|▊         | 173/2000 [05:16<53:51,  1.77s/it, loss=0.145, lr=0.0001]
Steps:   9%|▊         | 174/2000 [05:17<53:00,  1.74s/it, loss=0.145, lr=0.0001]
Steps:   9%|▊         | 174/2000 [05:17<53:00,  1.74s/it, loss=0.0542, lr=0.0001]
Steps:   9%|▊         | 174/2000 [05:17<53:00,  1.74s/it, loss=0.155, lr=0.0001] 
Steps:   9%|▊         | 174/2000 [05:18<53:00,  1.74s/it, loss=0.304, lr=0.0001]
Steps:   9%|▊         | 174/2000 [05:18<53:00,  1.74s/it, loss=0.205, lr=0.0001]
Steps:   9%|▉         | 175/2000 [05:19<55:04,  1.81s/it, loss=0.205, lr=0.0001]
Steps:   9%|▉         | 175/2000 [05:19<55:04,  1.81s/it, loss=0.146, lr=0.0001]
Steps:   9%|▉         | 175/2000 [05:19<55:04,  1.81s/it, loss=0.181, lr=0.0001]
Steps:   9%|▉         | 175/2000 [05:20<55:04,  1.81s/it, loss=0.188, lr=0.0001]
Steps:   9%|▉         | 175/2000 [05:20<55:04,  1.81s/it, loss=0.102, lr=0.0001]
Steps:   9%|▉         | 176/2000 [05:20<53:57,  1.77s/it, loss=0.102, lr=0.0001]
Steps:   9%|▉         | 176/2000 [05:20<53:57,  1.77s/it, loss=0.182, lr=0.0001]
Steps:   9%|▉         | 176/2000 [05:21<53:57,  1.77s/it, loss=0.158, lr=0.0001]
Steps:   9%|▉         | 176/2000 [05:21<53:57,  1.77s/it, loss=0.269, lr=0.0001]
Steps:   9%|▉         | 176/2000 [05:22<53:57,  1.77s/it, loss=0.118, lr=0.0001]
Steps:   9%|▉         | 177/2000 [05:22<53:16,  1.75s/it, loss=0.118, lr=0.0001]
Steps:   9%|▉         | 177/2000 [05:22<53:16,  1.75s/it, loss=0.264, lr=0.0001]
Steps:   9%|▉         | 177/2000 [05:23<53:16,  1.75s/it, loss=0.291, lr=0.0001]
Steps:   9%|▉         | 177/2000 [05:23<53:16,  1.75s/it, loss=0.218, lr=0.0001]
Steps:   9%|▉         | 177/2000 [05:24<53:16,  1.75s/it, loss=0.154, lr=0.0001]
Steps:   9%|▉         | 178/2000 [05:24<55:50,  1.84s/it, loss=0.154, lr=0.0001]
Steps:   9%|▉         | 178/2000 [05:24<55:50,  1.84s/it, loss=0.301, lr=0.0001]
Steps:   9%|▉         | 178/2000 [05:25<55:50,  1.84s/it, loss=0.145, lr=0.0001]
Steps:   9%|▉         | 178/2000 [05:25<55:50,  1.84s/it, loss=0.142, lr=0.0001]
Steps:   9%|▉         | 178/2000 [05:26<55:50,  1.84s/it, loss=0.22, lr=0.0001] 
Steps:   9%|▉         | 179/2000 [05:26<55:01,  1.81s/it, loss=0.22, lr=0.0001]
Steps:   9%|▉         | 179/2000 [05:26<55:01,  1.81s/it, loss=0.141, lr=0.0001]
Steps:   9%|▉         | 179/2000 [05:26<55:01,  1.81s/it, loss=0.23, lr=0.0001] 
Steps:   9%|▉         | 179/2000 [05:27<55:01,  1.81s/it, loss=0.615, lr=0.0001]
Steps:   9%|▉         | 179/2000 [05:27<55:01,  1.81s/it, loss=0.181, lr=0.0001]
Steps:   9%|▉         | 180/2000 [05:28<54:54,  1.81s/it, loss=0.181, lr=0.0001]
Steps:   9%|▉         | 180/2000 [05:28<54:54,  1.81s/it, loss=0.241, lr=0.0001]
Steps:   9%|▉         | 180/2000 [05:28<54:54,  1.81s/it, loss=0.174, lr=0.0001]
Steps:   9%|▉         | 180/2000 [05:29<54:54,  1.81s/it, loss=0.222, lr=0.0001]
Steps:   9%|▉         | 180/2000 [05:29<54:54,  1.81s/it, loss=1.06, lr=0.0001] 
Steps:   9%|▉         | 181/2000 [05:30<56:51,  1.88s/it, loss=1.06, lr=0.0001]
Steps:   9%|▉         | 181/2000 [05:30<56:51,  1.88s/it, loss=0.183, lr=0.0001]
Steps:   9%|▉         | 181/2000 [05:30<56:51,  1.88s/it, loss=0.173, lr=0.0001]
Steps:   9%|▉         | 181/2000 [05:31<56:51,  1.88s/it, loss=0.143, lr=0.0001]
Steps:   9%|▉         | 181/2000 [05:31<56:51,  1.88s/it, loss=0.154, lr=0.0001]
Steps:   9%|▉         | 182/2000 [05:32<55:42,  1.84s/it, loss=0.154, lr=0.0001]
Steps:   9%|▉         | 182/2000 [05:32<55:42,  1.84s/it, loss=0.081, lr=0.0001]
Steps:   9%|▉         | 182/2000 [05:32<55:42,  1.84s/it, loss=0.241, lr=0.0001]
Steps:   9%|▉         | 182/2000 [05:32<55:42,  1.84s/it, loss=0.133, lr=0.0001]
Steps:   9%|▉         | 182/2000 [05:33<55:42,  1.84s/it, loss=0.253, lr=0.0001]
Steps:   9%|▉         | 183/2000 [05:33<55:01,  1.82s/it, loss=0.253, lr=0.0001]
Steps:   9%|▉         | 183/2000 [05:33<55:01,  1.82s/it, loss=0.258, lr=0.0001]
Steps:   9%|▉         | 183/2000 [05:34<55:01,  1.82s/it, loss=0.203, lr=0.0001]
Steps:   9%|▉         | 183/2000 [05:34<55:01,  1.82s/it, loss=0.166, lr=0.0001]
Steps:   9%|▉         | 183/2000 [05:35<55:01,  1.82s/it, loss=0.354, lr=0.0001]
Steps:   9%|▉         | 184/2000 [05:35<56:30,  1.87s/it, loss=0.354, lr=0.0001]
Steps:   9%|▉         | 184/2000 [05:35<56:30,  1.87s/it, loss=0.151, lr=0.0001]
Steps:   9%|▉         | 184/2000 [05:36<56:30,  1.87s/it, loss=0.229, lr=0.0001]
Steps:   9%|▉         | 184/2000 [05:36<56:30,  1.87s/it, loss=0.248, lr=0.0001]
Steps:   9%|▉         | 184/2000 [05:37<56:30,  1.87s/it, loss=0.0834, lr=0.0001]
Steps:   9%|▉         | 185/2000 [05:37<54:34,  1.80s/it, loss=0.0834, lr=0.0001]
Steps:   9%|▉         | 185/2000 [05:37<54:34,  1.80s/it, loss=0.203, lr=0.0001] 
Steps:   9%|▉         | 185/2000 [05:37<54:34,  1.80s/it, loss=0.36, lr=0.0001] 
Steps:   9%|▉         | 185/2000 [05:38<54:34,  1.80s/it, loss=0.811, lr=0.0001]
Steps:   9%|▉         | 185/2000 [05:38<54:34,  1.80s/it, loss=0.151, lr=0.0001]
Steps:   9%|▉         | 186/2000 [05:39<53:24,  1.77s/it, loss=0.151, lr=0.0001]
Steps:   9%|▉         | 186/2000 [05:39<53:24,  1.77s/it, loss=0.0297, lr=0.0001]
Steps:   9%|▉         | 186/2000 [05:39<53:24,  1.77s/it, loss=0.15, lr=0.0001]  
Steps:   9%|▉         | 186/2000 [05:39<53:24,  1.77s/it, loss=0.257, lr=0.0001]
Steps:   9%|▉         | 186/2000 [05:40<53:24,  1.77s/it, loss=0.183, lr=0.0001]
Steps:   9%|▉         | 187/2000 [05:41<54:43,  1.81s/it, loss=0.183, lr=0.0001]
Steps:   9%|▉         | 187/2000 [05:41<54:43,  1.81s/it, loss=0.556, lr=0.0001]
Steps:   9%|▉         | 187/2000 [05:41<54:43,  1.81s/it, loss=0.16, lr=0.0001] 
Steps:   9%|▉         | 187/2000 [05:41<54:43,  1.81s/it, loss=0.174, lr=0.0001]
Steps:   9%|▉         | 187/2000 [05:42<54:43,  1.81s/it, loss=0.213, lr=0.0001]
Steps:   9%|▉         | 188/2000 [05:42<53:28,  1.77s/it, loss=0.213, lr=0.0001]
Steps:   9%|▉         | 188/2000 [05:42<53:28,  1.77s/it, loss=0.161, lr=0.0001]
Steps:   9%|▉         | 188/2000 [05:43<53:28,  1.77s/it, loss=0.147, lr=0.0001]
Steps:   9%|▉         | 188/2000 [05:43<53:28,  1.77s/it, loss=0.211, lr=0.0001]
Steps:   9%|▉         | 188/2000 [05:43<53:28,  1.77s/it, loss=0.295, lr=0.0001]
Steps:   9%|▉         | 189/2000 [05:44<52:36,  1.74s/it, loss=0.295, lr=0.0001]
Steps:   9%|▉         | 189/2000 [05:44<52:36,  1.74s/it, loss=0.155, lr=0.0001]
Steps:   9%|▉         | 189/2000 [05:44<52:36,  1.74s/it, loss=0.0884, lr=0.0001]
Steps:   9%|▉         | 189/2000 [05:45<52:36,  1.74s/it, loss=0.136, lr=0.0001] 
Steps:   9%|▉         | 189/2000 [05:45<52:36,  1.74s/it, loss=0.161, lr=0.0001]
Steps:  10%|▉         | 190/2000 [05:46<51:44,  1.71s/it, loss=0.161, lr=0.0001]
Steps:  10%|▉         | 190/2000 [05:46<51:44,  1.71s/it, loss=0.113, lr=0.0001]
Steps:  10%|▉         | 190/2000 [05:46<51:44,  1.71s/it, loss=0.158, lr=0.0001]
Steps:  10%|▉         | 190/2000 [05:47<51:44,  1.71s/it, loss=0.0942, lr=0.0001]
Steps:  10%|▉         | 190/2000 [05:47<51:44,  1.71s/it, loss=0.159, lr=0.0001] 
Steps:  10%|▉         | 191/2000 [05:47<53:17,  1.77s/it, loss=0.159, lr=0.0001]
Steps:  10%|▉         | 191/2000 [05:47<53:17,  1.77s/it, loss=0.143, lr=0.0001]
Steps:  10%|▉         | 191/2000 [05:48<53:17,  1.77s/it, loss=0.214, lr=0.0001]
Steps:  10%|▉         | 191/2000 [05:48<53:17,  1.77s/it, loss=0.221, lr=0.0001]
Steps:  10%|▉         | 191/2000 [05:49<53:17,  1.77s/it, loss=0.235, lr=0.0001]
Steps:  10%|▉         | 192/2000 [05:49<52:45,  1.75s/it, loss=0.235, lr=0.0001]
Steps:  10%|▉         | 192/2000 [05:49<52:45,  1.75s/it, loss=0.136, lr=0.0001]
Steps:  10%|▉         | 192/2000 [05:50<52:45,  1.75s/it, loss=0.183, lr=0.0001]
Steps:  10%|▉         | 192/2000 [05:50<52:45,  1.75s/it, loss=0.152, lr=0.0001]
Steps:  10%|▉         | 192/2000 [05:50<52:45,  1.75s/it, loss=0.131, lr=0.0001]
Steps:  10%|▉         | 193/2000 [05:51<51:52,  1.72s/it, loss=0.131, lr=0.0001]
Steps:  10%|▉         | 193/2000 [05:51<51:52,  1.72s/it, loss=0.15, lr=0.0001] 
Steps:  10%|▉         | 193/2000 [05:51<51:52,  1.72s/it, loss=0.231, lr=0.0001]
Steps:  10%|▉         | 193/2000 [05:52<51:52,  1.72s/it, loss=0.116, lr=0.0001]
Steps:  10%|▉         | 193/2000 [05:52<51:52,  1.72s/it, loss=0.158, lr=0.0001]
Steps:  10%|▉         | 194/2000 [05:53<53:27,  1.78s/it, loss=0.158, lr=0.0001]
Steps:  10%|▉         | 194/2000 [05:53<53:27,  1.78s/it, loss=0.122, lr=0.0001]
Steps:  10%|▉         | 194/2000 [05:53<53:27,  1.78s/it, loss=0.467, lr=0.0001]
Steps:  10%|▉         | 194/2000 [05:54<53:27,  1.78s/it, loss=0.184, lr=0.0001]
Steps:  10%|▉         | 194/2000 [05:54<53:27,  1.78s/it, loss=0.0918, lr=0.0001]
Steps:  10%|▉         | 195/2000 [05:54<52:19,  1.74s/it, loss=0.0918, lr=0.0001]
Steps:  10%|▉         | 195/2000 [05:54<52:19,  1.74s/it, loss=0.2, lr=0.0001]   
Steps:  10%|▉         | 195/2000 [05:55<52:19,  1.74s/it, loss=0.138, lr=0.0001]
Steps:  10%|▉         | 195/2000 [05:55<52:19,  1.74s/it, loss=0.0997, lr=0.0001]
Steps:  10%|▉         | 195/2000 [05:56<52:19,  1.74s/it, loss=0.165, lr=0.0001] 
Steps:  10%|▉         | 196/2000 [05:56<51:39,  1.72s/it, loss=0.165, lr=0.0001]
Steps:  10%|▉         | 196/2000 [05:56<51:39,  1.72s/it, loss=0.12, lr=0.0001] 
Steps:  10%|▉         | 196/2000 [05:56<51:39,  1.72s/it, loss=0.151, lr=0.0001]
Steps:  10%|▉         | 196/2000 [05:57<51:39,  1.72s/it, loss=0.135, lr=0.0001]
Steps:  10%|▉         | 196/2000 [05:57<51:39,  1.72s/it, loss=0.206, lr=0.0001]
Steps:  10%|▉         | 197/2000 [05:58<53:02,  1.77s/it, loss=0.206, lr=0.0001]
Steps:  10%|▉         | 197/2000 [05:58<53:02,  1.77s/it, loss=0.207, lr=0.0001]
Steps:  10%|▉         | 197/2000 [05:58<53:02,  1.77s/it, loss=0.208, lr=0.0001]
Steps:  10%|▉         | 197/2000 [05:59<53:02,  1.77s/it, loss=0.137, lr=0.0001]
Steps:  10%|▉         | 197/2000 [05:59<53:02,  1.77s/it, loss=0.131, lr=0.0001]
Steps:  10%|▉         | 198/2000 [06:00<51:58,  1.73s/it, loss=0.131, lr=0.0001]
Steps:  10%|▉         | 198/2000 [06:00<51:58,  1.73s/it, loss=0.265, lr=0.0001]
Steps:  10%|▉         | 198/2000 [06:00<51:58,  1.73s/it, loss=0.357, lr=0.0001]
Steps:  10%|▉         | 198/2000 [06:00<51:58,  1.73s/it, loss=0.233, lr=0.0001]
Steps:  10%|▉         | 198/2000 [06:01<51:58,  1.73s/it, loss=0.158, lr=0.0001]
Steps:  10%|▉         | 199/2000 [06:01<51:26,  1.71s/it, loss=0.158, lr=0.0001]
Steps:  10%|▉         | 199/2000 [06:01<51:26,  1.71s/it, loss=0.135, lr=0.0001]
Steps:  10%|▉         | 199/2000 [06:02<51:26,  1.71s/it, loss=0.2, lr=0.0001]  
Steps:  10%|▉         | 199/2000 [06:02<51:26,  1.71s/it, loss=0.122, lr=0.0001]
Steps:  10%|▉         | 199/2000 [06:03<51:26,  1.71s/it, loss=0.177, lr=0.0001]
Steps:  10%|█         | 200/2000 [06:03<53:14,  1.77s/it, loss=0.177, lr=0.0001]
Steps:  10%|█         | 200/2000 [06:03<53:14,  1.77s/it, loss=0.132, lr=0.0001]
Steps:  10%|█         | 200/2000 [06:04<53:14,  1.77s/it, loss=0.129, lr=0.0001]
Steps:  10%|█         | 200/2000 [06:04<53:14,  1.77s/it, loss=0.298, lr=0.0001]
Steps:  10%|█         | 200/2000 [06:04<53:14,  1.77s/it, loss=0.182, lr=0.0001]
Steps:  10%|█         | 201/2000 [06:05<52:08,  1.74s/it, loss=0.182, lr=0.0001]
Steps:  10%|█         | 201/2000 [06:05<52:08,  1.74s/it, loss=0.191, lr=0.0001]
Steps:  10%|█         | 201/2000 [06:05<52:08,  1.74s/it, loss=0.129, lr=0.0001]
Steps:  10%|█         | 201/2000 [06:06<52:08,  1.74s/it, loss=0.208, lr=0.0001]
Steps:  10%|█         | 201/2000 [06:06<52:08,  1.74s/it, loss=0.128, lr=0.0001]
Steps:  10%|█         | 202/2000 [06:06<51:19,  1.71s/it, loss=0.128, lr=0.0001]
Steps:  10%|█         | 202/2000 [06:06<51:19,  1.71s/it, loss=0.224, lr=0.0001]
Steps:  10%|█         | 202/2000 [06:07<51:19,  1.71s/it, loss=0.147, lr=0.0001]
Steps:  10%|█         | 202/2000 [06:07<51:19,  1.71s/it, loss=0.459, lr=0.0001]
Steps:  10%|█         | 202/2000 [06:08<51:19,  1.71s/it, loss=0.513, lr=0.0001]
Steps:  10%|█         | 203/2000 [06:08<52:56,  1.77s/it, loss=0.513, lr=0.0001]
Steps:  10%|█         | 203/2000 [06:08<52:56,  1.77s/it, loss=0.18, lr=0.0001] 
Steps:  10%|█         | 203/2000 [06:09<52:56,  1.77s/it, loss=0.0787, lr=0.0001]
Steps:  10%|█         | 203/2000 [06:09<52:56,  1.77s/it, loss=0.262, lr=0.0001] 
Steps:  10%|█         | 203/2000 [06:10<52:56,  1.77s/it, loss=0.169, lr=0.0001]
Steps:  10%|█         | 204/2000 [06:10<51:39,  1.73s/it, loss=0.169, lr=0.0001]
Steps:  10%|█         | 204/2000 [06:10<51:39,  1.73s/it, loss=0.146, lr=0.0001]
Steps:  10%|█         | 204/2000 [06:10<51:39,  1.73s/it, loss=0.187, lr=0.0001]
Steps:  10%|█         | 204/2000 [06:11<51:39,  1.73s/it, loss=0.174, lr=0.0001]
Steps:  10%|█         | 204/2000 [06:11<51:39,  1.73s/it, loss=0.264, lr=0.0001]
Steps:  10%|█         | 205/2000 [06:12<51:02,  1.71s/it, loss=0.264, lr=0.0001]
Steps:  10%|█         | 205/2000 [06:12<51:02,  1.71s/it, loss=0.262, lr=0.0001]
Steps:  10%|█         | 205/2000 [06:12<51:02,  1.71s/it, loss=0.295, lr=0.0001]
Steps:  10%|█         | 205/2000 [06:12<51:02,  1.71s/it, loss=0.163, lr=0.0001]
Steps:  10%|█         | 205/2000 [06:13<51:02,  1.71s/it, loss=0.128, lr=0.0001]
Steps:  10%|█         | 206/2000 [06:14<52:42,  1.76s/it, loss=0.128, lr=0.0001]
Steps:  10%|█         | 206/2000 [06:14<52:42,  1.76s/it, loss=0.49, lr=0.0001] 
Steps:  10%|█         | 206/2000 [06:14<52:42,  1.76s/it, loss=0.116, lr=0.0001]
Steps:  10%|█         | 206/2000 [06:14<52:42,  1.76s/it, loss=0.178, lr=0.0001]
Steps:  10%|█         | 206/2000 [06:15<52:42,  1.76s/it, loss=0.331, lr=0.0001]
Steps:  10%|█         | 207/2000 [06:15<51:33,  1.73s/it, loss=0.331, lr=0.0001]
Steps:  10%|█         | 207/2000 [06:15<51:33,  1.73s/it, loss=0.0762, lr=0.0001]
Steps:  10%|█         | 207/2000 [06:16<51:33,  1.73s/it, loss=0.188, lr=0.0001] 
Steps:  10%|█         | 207/2000 [06:16<51:33,  1.73s/it, loss=0.181, lr=0.0001]
Steps:  10%|█         | 207/2000 [06:16<51:33,  1.73s/it, loss=0.156, lr=0.0001]
Steps:  10%|█         | 208/2000 [06:17<50:53,  1.70s/it, loss=0.156, lr=0.0001]
Steps:  10%|█         | 208/2000 [06:17<50:53,  1.70s/it, loss=0.0899, lr=0.0001]
Steps:  10%|█         | 208/2000 [06:17<50:53,  1.70s/it, loss=0.227, lr=0.0001] 
Steps:  10%|█         | 208/2000 [06:18<50:53,  1.70s/it, loss=0.252, lr=0.0001]
Steps:  10%|█         | 208/2000 [06:18<50:53,  1.70s/it, loss=0.0515, lr=0.0001]
Steps:  10%|█         | 209/2000 [06:19<52:14,  1.75s/it, loss=0.0515, lr=0.0001]
Steps:  10%|█         | 209/2000 [06:19<52:14,  1.75s/it, loss=0.17, lr=0.0001]  
Steps:  10%|█         | 209/2000 [06:19<52:14,  1.75s/it, loss=0.199, lr=0.0001]
Steps:  10%|█         | 209/2000 [06:20<52:14,  1.75s/it, loss=0.197, lr=0.0001]
Steps:  10%|█         | 209/2000 [06:20<52:14,  1.75s/it, loss=0.224, lr=0.0001]
Steps:  10%|█         | 210/2000 [06:20<51:09,  1.72s/it, loss=0.224, lr=0.0001]
Steps:  10%|█         | 210/2000 [06:20<51:09,  1.72s/it, loss=0.274, lr=0.0001]
Steps:  10%|█         | 210/2000 [06:21<51:09,  1.72s/it, loss=0.169, lr=0.0001]
Steps:  10%|█         | 210/2000 [06:21<51:09,  1.72s/it, loss=0.199, lr=0.0001]
Steps:  10%|█         | 210/2000 [06:22<51:09,  1.72s/it, loss=0.225, lr=0.0001]
Steps:  11%|█         | 211/2000 [06:22<50:57,  1.71s/it, loss=0.225, lr=0.0001]
Steps:  11%|█         | 211/2000 [06:22<50:57,  1.71s/it, loss=0.145, lr=0.0001]
Steps:  11%|█         | 211/2000 [06:22<50:57,  1.71s/it, loss=0.172, lr=0.0001]
Steps:  11%|█         | 211/2000 [06:23<50:57,  1.71s/it, loss=0.152, lr=0.0001]
Steps:  11%|█         | 211/2000 [06:23<50:57,  1.71s/it, loss=0.247, lr=0.0001]
Steps:  11%|█         | 212/2000 [06:24<50:49,  1.71s/it, loss=0.247, lr=0.0001]
Steps:  11%|█         | 212/2000 [06:24<50:49,  1.71s/it, loss=0.178, lr=0.0001]
Steps:  11%|█         | 212/2000 [06:24<50:49,  1.71s/it, loss=0.146, lr=0.0001]
Steps:  11%|█         | 212/2000 [06:25<50:49,  1.71s/it, loss=0.109, lr=0.0001]
Steps:  11%|█         | 212/2000 [06:25<50:49,  1.71s/it, loss=0.526, lr=0.0001]
Steps:  11%|█         | 213/2000 [06:26<52:25,  1.76s/it, loss=0.526, lr=0.0001]
Steps:  11%|█         | 213/2000 [06:26<52:25,  1.76s/it, loss=0.166, lr=0.0001]
Steps:  11%|█         | 213/2000 [06:26<52:25,  1.76s/it, loss=0.208, lr=0.0001]
Steps:  11%|█         | 213/2000 [06:26<52:25,  1.76s/it, loss=0.0982, lr=0.0001]
Steps:  11%|█         | 213/2000 [06:27<52:25,  1.76s/it, loss=0.231, lr=0.0001] 
Steps:  11%|█         | 214/2000 [06:27<51:49,  1.74s/it, loss=0.231, lr=0.0001]
Steps:  11%|█         | 214/2000 [06:27<51:49,  1.74s/it, loss=0.174, lr=0.0001]
Steps:  11%|█         | 214/2000 [06:28<51:49,  1.74s/it, loss=0.125, lr=0.0001]
Steps:  11%|█         | 214/2000 [06:28<51:49,  1.74s/it, loss=0.513, lr=0.0001]
Steps:  11%|█         | 214/2000 [06:29<51:49,  1.74s/it, loss=0.204, lr=0.0001]
Steps:  11%|█         | 215/2000 [06:29<51:20,  1.73s/it, loss=0.204, lr=0.0001]
Steps:  11%|█         | 215/2000 [06:29<51:20,  1.73s/it, loss=0.213, lr=0.0001]
Steps:  11%|█         | 215/2000 [06:29<51:20,  1.73s/it, loss=0.107, lr=0.0001]
Steps:  11%|█         | 215/2000 [06:30<51:20,  1.73s/it, loss=0.201, lr=0.0001]
Steps:  11%|█         | 215/2000 [06:30<51:20,  1.73s/it, loss=0.133, lr=0.0001]
Steps:  11%|█         | 216/2000 [06:31<53:19,  1.79s/it, loss=0.133, lr=0.0001]
Steps:  11%|█         | 216/2000 [06:31<53:19,  1.79s/it, loss=0.565, lr=0.0001]
Steps:  11%|█         | 216/2000 [06:31<53:19,  1.79s/it, loss=0.173, lr=0.0001]
Steps:  11%|█         | 216/2000 [06:32<53:19,  1.79s/it, loss=0.161, lr=0.0001]
Steps:  11%|█         | 216/2000 [06:32<53:19,  1.79s/it, loss=0.146, lr=0.0001]
Steps:  11%|█         | 217/2000 [06:33<52:39,  1.77s/it, loss=0.146, lr=0.0001]
Steps:  11%|█         | 217/2000 [06:33<52:39,  1.77s/it, loss=0.172, lr=0.0001]
Steps:  11%|█         | 217/2000 [06:33<52:39,  1.77s/it, loss=0.769, lr=0.0001]
Steps:  11%|█         | 217/2000 [06:33<52:39,  1.77s/it, loss=0.346, lr=0.0001]
Steps:  11%|█         | 217/2000 [06:34<52:39,  1.77s/it, loss=0.539, lr=0.0001]
Steps:  11%|█         | 218/2000 [06:34<51:33,  1.74s/it, loss=0.539, lr=0.0001]
Steps:  11%|█         | 218/2000 [06:34<51:33,  1.74s/it, loss=0.21, lr=0.0001] 
Steps:  11%|█         | 218/2000 [06:35<51:33,  1.74s/it, loss=0.173, lr=0.0001]
Steps:  11%|█         | 218/2000 [06:35<51:33,  1.74s/it, loss=0.236, lr=0.0001]
Steps:  11%|█         | 218/2000 [06:36<51:33,  1.74s/it, loss=0.188, lr=0.0001]
Steps:  11%|█         | 219/2000 [06:36<52:58,  1.78s/it, loss=0.188, lr=0.0001]
Steps:  11%|█         | 219/2000 [06:36<52:58,  1.78s/it, loss=0.174, lr=0.0001]
Steps:  11%|█         | 219/2000 [06:37<52:58,  1.78s/it, loss=0.0813, lr=0.0001]
Steps:  11%|█         | 219/2000 [06:37<52:58,  1.78s/it, loss=0.18, lr=0.0001]  
Steps:  11%|█         | 219/2000 [06:37<52:58,  1.78s/it, loss=0.151, lr=0.0001]
Steps:  11%|█         | 220/2000 [06:38<51:52,  1.75s/it, loss=0.151, lr=0.0001]
Steps:  11%|█         | 220/2000 [06:38<51:52,  1.75s/it, loss=0.149, lr=0.0001]
Steps:  11%|█         | 220/2000 [06:38<51:52,  1.75s/it, loss=0.122, lr=0.0001]
Steps:  11%|█         | 220/2000 [06:39<51:52,  1.75s/it, loss=0.234, lr=0.0001]
Steps:  11%|█         | 220/2000 [06:39<51:52,  1.75s/it, loss=0.299, lr=0.0001]
Steps:  11%|█         | 221/2000 [06:40<51:08,  1.72s/it, loss=0.299, lr=0.0001]
Steps:  11%|█         | 221/2000 [06:40<51:08,  1.72s/it, loss=0.176, lr=0.0001]
Steps:  11%|█         | 221/2000 [06:40<51:08,  1.72s/it, loss=0.0686, lr=0.0001]
Steps:  11%|█         | 221/2000 [06:40<51:08,  1.72s/it, loss=0.237, lr=0.0001] 
Steps:  11%|█         | 221/2000 [06:41<51:08,  1.72s/it, loss=0.189, lr=0.0001]
Steps:  11%|█         | 222/2000 [06:41<52:08,  1.76s/it, loss=0.189, lr=0.0001]
Steps:  11%|█         | 222/2000 [06:41<52:08,  1.76s/it, loss=0.149, lr=0.0001]
Steps:  11%|█         | 222/2000 [06:42<52:08,  1.76s/it, loss=0.232, lr=0.0001]
Steps:  11%|█         | 222/2000 [06:42<52:08,  1.76s/it, loss=0.106, lr=0.0001]
Steps:  11%|█         | 222/2000 [06:43<52:08,  1.76s/it, loss=0.124, lr=0.0001]
Steps:  11%|█         | 223/2000 [06:43<50:55,  1.72s/it, loss=0.124, lr=0.0001]
Steps:  11%|█         | 223/2000 [06:43<50:55,  1.72s/it, loss=0.119, lr=0.0001]
Steps:  11%|█         | 223/2000 [06:43<50:55,  1.72s/it, loss=0.351, lr=0.0001]
Steps:  11%|█         | 223/2000 [06:44<50:55,  1.72s/it, loss=1.08, lr=0.0001] 
Steps:  11%|█         | 223/2000 [06:44<50:55,  1.72s/it, loss=0.686, lr=0.0001]
Steps:  11%|█         | 224/2000 [06:45<50:35,  1.71s/it, loss=0.686, lr=0.0001]
Steps:  11%|█         | 224/2000 [06:45<50:35,  1.71s/it, loss=0.263, lr=0.0001]
Steps:  11%|█         | 224/2000 [06:45<50:35,  1.71s/it, loss=0.248, lr=0.0001]
Steps:  11%|█         | 224/2000 [06:46<50:35,  1.71s/it, loss=0.0395, lr=0.0001]
Steps:  11%|█         | 224/2000 [06:46<50:35,  1.71s/it, loss=0.147, lr=0.0001] 
Steps:  11%|█▏        | 225/2000 [06:47<52:01,  1.76s/it, loss=0.147, lr=0.0001]
Steps:  11%|█▏        | 225/2000 [06:47<52:01,  1.76s/it, loss=0.265, lr=0.0001]
Steps:  11%|█▏        | 225/2000 [06:47<52:01,  1.76s/it, loss=0.22, lr=0.0001] 
Steps:  11%|█▏        | 225/2000 [06:47<52:01,  1.76s/it, loss=0.163, lr=0.0001]
Steps:  11%|█▏        | 225/2000 [06:48<52:01,  1.76s/it, loss=0.369, lr=0.0001]
Steps:  11%|█▏        | 226/2000 [06:48<50:53,  1.72s/it, loss=0.369, lr=0.0001]
Steps:  11%|█▏        | 226/2000 [06:48<50:53,  1.72s/it, loss=0.256, lr=0.0001]
Steps:  11%|█▏        | 226/2000 [06:49<50:53,  1.72s/it, loss=0.213, lr=0.0001]
Steps:  11%|█▏        | 226/2000 [06:49<50:53,  1.72s/it, loss=0.108, lr=0.0001]
Steps:  11%|█▏        | 226/2000 [06:49<50:53,  1.72s/it, loss=0.369, lr=0.0001]
Steps:  11%|█▏        | 227/2000 [06:50<50:08,  1.70s/it, loss=0.369, lr=0.0001]
Steps:  11%|█▏        | 227/2000 [06:50<50:08,  1.70s/it, loss=0.135, lr=0.0001]
Steps:  11%|█▏        | 227/2000 [06:50<50:08,  1.70s/it, loss=0.173, lr=0.0001]
Steps:  11%|█▏        | 227/2000 [06:51<50:08,  1.70s/it, loss=0.0706, lr=0.0001]
Steps:  11%|█▏        | 227/2000 [06:51<50:08,  1.70s/it, loss=0.989, lr=0.0001] 
Steps:  11%|█▏        | 228/2000 [06:52<51:45,  1.75s/it, loss=0.989, lr=0.0001]
Steps:  11%|█▏        | 228/2000 [06:52<51:45,  1.75s/it, loss=0.0341, lr=0.0001]
Steps:  11%|█▏        | 228/2000 [06:52<51:45,  1.75s/it, loss=0.18, lr=0.0001]  
Steps:  11%|█▏        | 228/2000 [06:53<51:45,  1.75s/it, loss=0.206, lr=0.0001]
Steps:  11%|█▏        | 228/2000 [06:53<51:45,  1.75s/it, loss=0.381, lr=0.0001]
Steps:  11%|█▏        | 229/2000 [06:53<50:47,  1.72s/it, loss=0.381, lr=0.0001]
Steps:  11%|█▏        | 229/2000 [06:53<50:47,  1.72s/it, loss=0.186, lr=0.0001]
Steps:  11%|█▏        | 229/2000 [06:54<50:47,  1.72s/it, loss=0.138, lr=0.0001]
Steps:  11%|█▏        | 229/2000 [06:54<50:47,  1.72s/it, loss=0.188, lr=0.0001]
Steps:  11%|█▏        | 229/2000 [06:55<50:47,  1.72s/it, loss=0.615, lr=0.0001]
Steps:  12%|█▏        | 230/2000 [06:55<50:07,  1.70s/it, loss=0.615, lr=0.0001]
Steps:  12%|█▏        | 230/2000 [06:55<50:07,  1.70s/it, loss=0.414, lr=0.0001]
Steps:  12%|█▏        | 230/2000 [06:55<50:07,  1.70s/it, loss=0.219, lr=0.0001]
Steps:  12%|█▏        | 230/2000 [06:56<50:07,  1.70s/it, loss=0.148, lr=0.0001]
Steps:  12%|█▏        | 230/2000 [06:56<50:07,  1.70s/it, loss=0.145, lr=0.0001]
Steps:  12%|█▏        | 231/2000 [06:57<51:39,  1.75s/it, loss=0.145, lr=0.0001]
Steps:  12%|█▏        | 231/2000 [06:57<51:39,  1.75s/it, loss=0.127, lr=0.0001]
Steps:  12%|█▏        | 231/2000 [06:57<51:39,  1.75s/it, loss=0.18, lr=0.0001] 
Steps:  12%|█▏        | 231/2000 [06:58<51:39,  1.75s/it, loss=0.229, lr=0.0001]
Steps:  12%|█▏        | 231/2000 [06:58<51:39,  1.75s/it, loss=0.125, lr=0.0001]
Steps:  12%|█▏        | 232/2000 [06:59<50:56,  1.73s/it, loss=0.125, lr=0.0001]
Steps:  12%|█▏        | 232/2000 [06:59<50:56,  1.73s/it, loss=0.154, lr=0.0001]
Steps:  12%|█▏        | 232/2000 [06:59<50:56,  1.73s/it, loss=0.194, lr=0.0001]
Steps:  12%|█▏        | 232/2000 [06:59<50:56,  1.73s/it, loss=0.171, lr=0.0001]
Steps:  12%|█▏        | 232/2000 [07:00<50:56,  1.73s/it, loss=0.12, lr=0.0001] 
Steps:  12%|█▏        | 233/2000 [07:00<50:41,  1.72s/it, loss=0.12, lr=0.0001]
Steps:  12%|█▏        | 233/2000 [07:00<50:41,  1.72s/it, loss=0.174, lr=0.0001]
Steps:  12%|█▏        | 233/2000 [07:01<50:41,  1.72s/it, loss=0.0716, lr=0.0001]
Steps:  12%|█▏        | 233/2000 [07:01<50:41,  1.72s/it, loss=0.178, lr=0.0001] 
Steps:  12%|█▏        | 233/2000 [07:02<50:41,  1.72s/it, loss=0.156, lr=0.0001]
Steps:  12%|█▏        | 234/2000 [07:02<50:11,  1.71s/it, loss=0.156, lr=0.0001]
Steps:  12%|█▏        | 234/2000 [07:02<50:11,  1.71s/it, loss=0.33, lr=0.0001] 
Steps:  12%|█▏        | 234/2000 [07:03<50:11,  1.71s/it, loss=0.179, lr=0.0001]
Steps:  12%|█▏        | 234/2000 [07:03<50:11,  1.71s/it, loss=0.237, lr=0.0001]
Steps:  12%|█▏        | 234/2000 [07:03<50:11,  1.71s/it, loss=0.117, lr=0.0001]
Steps:  12%|█▏        | 235/2000 [07:04<51:54,  1.76s/it, loss=0.117, lr=0.0001]
Steps:  12%|█▏        | 235/2000 [07:04<51:54,  1.76s/it, loss=0.349, lr=0.0001]
Steps:  12%|█▏        | 235/2000 [07:04<51:54,  1.76s/it, loss=0.338, lr=0.0001]
Steps:  12%|█▏        | 235/2000 [07:05<51:54,  1.76s/it, loss=0.231, lr=0.0001]
Steps:  12%|█▏        | 235/2000 [07:05<51:54,  1.76s/it, loss=0.179, lr=0.0001]
Steps:  12%|█▏        | 236/2000 [07:06<50:56,  1.73s/it, loss=0.179, lr=0.0001]
Steps:  12%|█▏        | 236/2000 [07:06<50:56,  1.73s/it, loss=0.235, lr=0.0001]
Steps:  12%|█▏        | 236/2000 [07:06<50:56,  1.73s/it, loss=0.924, lr=0.0001]
Steps:  12%|█▏        | 236/2000 [07:06<50:56,  1.73s/it, loss=0.134, lr=0.0001]
Steps:  12%|█▏        | 236/2000 [07:07<50:56,  1.73s/it, loss=0.249, lr=0.0001]
Steps:  12%|█▏        | 237/2000 [07:07<50:07,  1.71s/it, loss=0.249, lr=0.0001]
Steps:  12%|█▏        | 237/2000 [07:07<50:07,  1.71s/it, loss=0.341, lr=0.0001]
Steps:  12%|█▏        | 237/2000 [07:08<50:07,  1.71s/it, loss=0.187, lr=0.0001]
Steps:  12%|█▏        | 237/2000 [07:08<50:07,  1.71s/it, loss=0.21, lr=0.0001] 
Steps:  12%|█▏        | 237/2000 [07:09<50:07,  1.71s/it, loss=0.126, lr=0.0001]
Steps:  12%|█▏        | 238/2000 [07:09<51:35,  1.76s/it, loss=0.126, lr=0.0001]
Steps:  12%|█▏        | 238/2000 [07:09<51:35,  1.76s/it, loss=0.134, lr=0.0001]
Steps:  12%|█▏        | 238/2000 [07:09<51:35,  1.76s/it, loss=0.108, lr=0.0001]
Steps:  12%|█▏        | 238/2000 [07:10<51:35,  1.76s/it, loss=0.161, lr=0.0001]
Steps:  12%|█▏        | 238/2000 [07:10<51:35,  1.76s/it, loss=0.0854, lr=0.0001]
Steps:  12%|█▏        | 239/2000 [07:11<50:30,  1.72s/it, loss=0.0854, lr=0.0001]
Steps:  12%|█▏        | 239/2000 [07:11<50:30,  1.72s/it, loss=0.152, lr=0.0001] 
Steps:  12%|█▏        | 239/2000 [07:11<50:30,  1.72s/it, loss=0.482, lr=0.0001]
Steps:  12%|█▏        | 239/2000 [07:11<50:30,  1.72s/it, loss=0.304, lr=0.0001]
Steps:  12%|█▏        | 239/2000 [07:12<50:30,  1.72s/it, loss=0.128, lr=0.0001]
Steps:  12%|█▏        | 240/2000 [07:12<49:47,  1.70s/it, loss=0.128, lr=0.0001]
Steps:  12%|█▏        | 240/2000 [07:12<49:47,  1.70s/it, loss=0.0801, lr=0.0001]
Steps:  12%|█▏        | 240/2000 [07:13<49:47,  1.70s/it, loss=0.13, lr=0.0001]  
Steps:  12%|█▏        | 240/2000 [07:13<49:47,  1.70s/it, loss=0.222, lr=0.0001]
Steps:  12%|█▏        | 240/2000 [07:14<49:47,  1.70s/it, loss=0.347, lr=0.0001]
Steps:  12%|█▏        | 241/2000 [07:14<51:18,  1.75s/it, loss=0.347, lr=0.0001]
Steps:  12%|█▏        | 241/2000 [07:14<51:18,  1.75s/it, loss=0.114, lr=0.0001]
Steps:  12%|█▏        | 241/2000 [07:15<51:18,  1.75s/it, loss=0.176, lr=0.0001]
Steps:  12%|█▏        | 241/2000 [07:15<51:18,  1.75s/it, loss=0.139, lr=0.0001]
Steps:  12%|█▏        | 241/2000 [07:15<51:18,  1.75s/it, loss=0.156, lr=0.0001]
Steps:  12%|█▏        | 242/2000 [07:16<50:28,  1.72s/it, loss=0.156, lr=0.0001]
Steps:  12%|█▏        | 242/2000 [07:16<50:28,  1.72s/it, loss=0.218, lr=0.0001]
Steps:  12%|█▏        | 242/2000 [07:16<50:28,  1.72s/it, loss=1.11, lr=0.0001] 
Steps:  12%|█▏        | 242/2000 [07:17<50:28,  1.72s/it, loss=0.321, lr=0.0001]
Steps:  12%|█▏        | 242/2000 [07:17<50:28,  1.72s/it, loss=0.155, lr=0.0001]
Steps:  12%|█▏        | 243/2000 [07:17<49:43,  1.70s/it, loss=0.155, lr=0.0001]
Steps:  12%|█▏        | 243/2000 [07:17<49:43,  1.70s/it, loss=0.136, lr=0.0001]
Steps:  12%|█▏        | 243/2000 [07:18<49:43,  1.70s/it, loss=0.163, lr=0.0001]
Steps:  12%|█▏        | 243/2000 [07:18<49:43,  1.70s/it, loss=0.218, lr=0.0001]
Steps:  12%|█▏        | 243/2000 [07:19<49:43,  1.70s/it, loss=0.158, lr=0.0001]
Steps:  12%|█▏        | 244/2000 [07:19<51:13,  1.75s/it, loss=0.158, lr=0.0001]
Steps:  12%|█▏        | 244/2000 [07:19<51:13,  1.75s/it, loss=0.0976, lr=0.0001]
Steps:  12%|█▏        | 244/2000 [07:20<51:13,  1.75s/it, loss=0.256, lr=0.0001] 
Steps:  12%|█▏        | 244/2000 [07:20<51:13,  1.75s/it, loss=0.147, lr=0.0001]
Steps:  12%|█▏        | 244/2000 [07:21<51:13,  1.75s/it, loss=0.145, lr=0.0001]
Steps:  12%|█▏        | 245/2000 [07:21<50:11,  1.72s/it, loss=0.145, lr=0.0001]
Steps:  12%|█▏        | 245/2000 [07:21<50:11,  1.72s/it, loss=0.109, lr=0.0001]
Steps:  12%|█▏        | 245/2000 [07:21<50:11,  1.72s/it, loss=0.231, lr=0.0001]
Steps:  12%|█▏        | 245/2000 [07:22<50:11,  1.72s/it, loss=0.666, lr=0.0001]
Steps:  12%|█▏        | 245/2000 [07:22<50:11,  1.72s/it, loss=0.208, lr=0.0001]
Steps:  12%|█▏        | 246/2000 [07:23<49:34,  1.70s/it, loss=0.208, lr=0.0001]
Steps:  12%|█▏        | 246/2000 [07:23<49:34,  1.70s/it, loss=0.253, lr=0.0001]
Steps:  12%|█▏        | 246/2000 [07:23<49:34,  1.70s/it, loss=0.205, lr=0.0001]
Steps:  12%|█▏        | 246/2000 [07:23<49:34,  1.70s/it, loss=0.192, lr=0.0001]
Steps:  12%|█▏        | 246/2000 [07:24<49:34,  1.70s/it, loss=0.105, lr=0.0001]
Steps:  12%|█▏        | 247/2000 [07:25<51:01,  1.75s/it, loss=0.105, lr=0.0001]
Steps:  12%|█▏        | 247/2000 [07:25<51:01,  1.75s/it, loss=0.166, lr=0.0001]
Steps:  12%|█▏        | 247/2000 [07:25<51:01,  1.75s/it, loss=0.263, lr=0.0001]
Steps:  12%|█▏        | 247/2000 [07:25<51:01,  1.75s/it, loss=0.0603, lr=0.0001]
Steps:  12%|█▏        | 247/2000 [07:26<51:01,  1.75s/it, loss=0.213, lr=0.0001] 
Steps:  12%|█▏        | 248/2000 [07:26<50:04,  1.71s/it, loss=0.213, lr=0.0001]
Steps:  12%|█▏        | 248/2000 [07:26<50:04,  1.71s/it, loss=0.203, lr=0.0001]
Steps:  12%|█▏        | 248/2000 [07:27<50:04,  1.71s/it, loss=0.278, lr=0.0001]
Steps:  12%|█▏        | 248/2000 [07:27<50:04,  1.71s/it, loss=0.224, lr=0.0001]
Steps:  12%|█▏        | 248/2000 [07:27<50:04,  1.71s/it, loss=0.0754, lr=0.0001]
Steps:  12%|█▏        | 249/2000 [07:28<49:18,  1.69s/it, loss=0.0754, lr=0.0001]
Steps:  12%|█▏        | 249/2000 [07:28<49:18,  1.69s/it, loss=0.177, lr=0.0001] 
Steps:  12%|█▏        | 249/2000 [07:28<49:18,  1.69s/it, loss=0.106, lr=0.0001]
Steps:  12%|█▏        | 249/2000 [07:29<49:18,  1.69s/it, loss=0.237, lr=0.0001]
Steps:  12%|█▏        | 249/2000 [07:29<49:18,  1.69s/it, loss=1.22, lr=0.0001] 
Steps:  12%|█▎        | 250/2000 [07:30<50:54,  1.75s/it, loss=1.22, lr=0.0001]05/30/2026 08:39:55 - INFO - accelerate.accelerator - [RANK 0] Saving current state to /workspace/output/flux-dev-apple-emoji-lora/checkpoint-250
Model weights saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-250/pytorch_lora_weights.safetensors
05/30/2026 08:39:55 - INFO - accelerate.checkpointing - [RANK 0] Optimizer state saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-250/optimizer.bin
05/30/2026 08:39:55 - INFO - accelerate.checkpointing - [RANK 0] Scheduler state saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-250/scheduler.bin
05/30/2026 08:39:55 - INFO - accelerate.checkpointing - [RANK 0] Sampler state for dataloader 0 saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-250/sampler.bin
05/30/2026 08:39:55 - INFO - accelerate.checkpointing - [RANK 0] Random states saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-250/random_states_0.pkl
05/30/2026 08:39:55 - INFO - __main__ - [RANK 0] Saved state to /workspace/output/flux-dev-apple-emoji-lora/checkpoint-250

Steps:  12%|█▎        | 250/2000 [07:30<50:54,  1.75s/it, loss=0.24, lr=0.0001]
Steps:  12%|█▎        | 250/2000 [07:31<50:54,  1.75s/it, loss=0.198, lr=0.0001]
Steps:  12%|█▎        | 250/2000 [07:31<50:54,  1.75s/it, loss=0.145, lr=0.0001]
Steps:  12%|█▎        | 250/2000 [07:32<50:54,  1.75s/it, loss=0.0944, lr=0.0001]
Steps:  13%|█▎        | 251/2000 [07:32<56:51,  1.95s/it, loss=0.0944, lr=0.0001]
Steps:  13%|█▎        | 251/2000 [07:32<56:51,  1.95s/it, loss=0.149, lr=0.0001] 
Steps:  13%|█▎        | 251/2000 [07:32<56:51,  1.95s/it, loss=0.426, lr=0.0001]
Steps:  13%|█▎        | 251/2000 [07:33<56:51,  1.95s/it, loss=0.183, lr=0.0001]
Steps:  13%|█▎        | 251/2000 [07:33<56:51,  1.95s/it, loss=0.343, lr=0.0001]
Steps:  13%|█▎        | 252/2000 [07:34<54:12,  1.86s/it, loss=0.343, lr=0.0001]
Steps:  13%|█▎        | 252/2000 [07:34<54:12,  1.86s/it, loss=1.14, lr=0.0001] 
Steps:  13%|█▎        | 252/2000 [07:34<54:12,  1.86s/it, loss=0.33, lr=0.0001]
Steps:  13%|█▎        | 252/2000 [07:35<54:12,  1.86s/it, loss=0.0553, lr=0.0001]
Steps:  13%|█▎        | 252/2000 [07:35<54:12,  1.86s/it, loss=0.135, lr=0.0001] 
Steps:  13%|█▎        | 253/2000 [07:36<54:27,  1.87s/it, loss=0.135, lr=0.0001]
Steps:  13%|█▎        | 253/2000 [07:36<54:27,  1.87s/it, loss=0.201, lr=0.0001]
Steps:  13%|█▎        | 253/2000 [07:36<54:27,  1.87s/it, loss=0.953, lr=0.0001]
Steps:  13%|█▎        | 253/2000 [07:36<54:27,  1.87s/it, loss=0.205, lr=0.0001]
Steps:  13%|█▎        | 253/2000 [07:37<54:27,  1.87s/it, loss=0.153, lr=0.0001]
Steps:  13%|█▎        | 254/2000 [07:37<52:34,  1.81s/it, loss=0.153, lr=0.0001]
Steps:  13%|█▎        | 254/2000 [07:37<52:34,  1.81s/it, loss=0.169, lr=0.0001]
Steps:  13%|█▎        | 254/2000 [07:38<52:34,  1.81s/it, loss=0.251, lr=0.0001]
Steps:  13%|█▎        | 254/2000 [07:38<52:34,  1.81s/it, loss=0.151, lr=0.0001]
Steps:  13%|█▎        | 254/2000 [07:39<52:34,  1.81s/it, loss=0.201, lr=0.0001]
Steps:  13%|█▎        | 255/2000 [07:39<51:39,  1.78s/it, loss=0.201, lr=0.0001]
Steps:  13%|█▎        | 255/2000 [07:39<51:39,  1.78s/it, loss=0.283, lr=0.0001]
Steps:  13%|█▎        | 255/2000 [07:39<51:39,  1.78s/it, loss=0.148, lr=0.0001]
Steps:  13%|█▎        | 255/2000 [07:40<51:39,  1.78s/it, loss=0.171, lr=0.0001]
Steps:  13%|█▎        | 255/2000 [07:40<51:39,  1.78s/it, loss=0.25, lr=0.0001] 
Steps:  13%|█▎        | 256/2000 [07:41<52:33,  1.81s/it, loss=0.25, lr=0.0001]
Steps:  13%|█▎        | 256/2000 [07:41<52:33,  1.81s/it, loss=0.161, lr=0.0001]
Steps:  13%|█▎        | 256/2000 [07:41<52:33,  1.81s/it, loss=1.02, lr=0.0001] 
Steps:  13%|█▎        | 256/2000 [07:42<52:33,  1.81s/it, loss=0.0771, lr=0.0001]
Steps:  13%|█▎        | 256/2000 [07:42<52:33,  1.81s/it, loss=0.14, lr=0.0001]  
Steps:  13%|█▎        | 257/2000 [07:43<51:18,  1.77s/it, loss=0.14, lr=0.0001]
Steps:  13%|█▎        | 257/2000 [07:43<51:18,  1.77s/it, loss=0.169, lr=0.0001]
Steps:  13%|█▎        | 257/2000 [07:43<51:18,  1.77s/it, loss=0.267, lr=0.0001]
Steps:  13%|█▎        | 257/2000 [07:43<51:18,  1.77s/it, loss=0.129, lr=0.0001]
Steps:  13%|█▎        | 257/2000 [07:44<51:18,  1.77s/it, loss=0.164, lr=0.0001]
Steps:  13%|█▎        | 258/2000 [07:44<50:36,  1.74s/it, loss=0.164, lr=0.0001]
Steps:  13%|█▎        | 258/2000 [07:44<50:36,  1.74s/it, loss=0.169, lr=0.0001]
Steps:  13%|█▎        | 258/2000 [07:45<50:36,  1.74s/it, loss=0.088, lr=0.0001]
Steps:  13%|█▎        | 258/2000 [07:45<50:36,  1.74s/it, loss=0.125, lr=0.0001]
Steps:  13%|█▎        | 258/2000 [07:45<50:36,  1.74s/it, loss=0.258, lr=0.0001]
Steps:  13%|█▎        | 259/2000 [07:46<51:55,  1.79s/it, loss=0.258, lr=0.0001]
Steps:  13%|█▎        | 259/2000 [07:46<51:55,  1.79s/it, loss=0.728, lr=0.0001]
Steps:  13%|█▎        | 259/2000 [07:47<51:55,  1.79s/it, loss=0.165, lr=0.0001]
Steps:  13%|█▎        | 259/2000 [07:47<51:55,  1.79s/it, loss=0.155, lr=0.0001]
Steps:  13%|█▎        | 259/2000 [07:47<51:55,  1.79s/it, loss=0.231, lr=0.0001]
Steps:  13%|█▎        | 260/2000 [07:48<50:32,  1.74s/it, loss=0.231, lr=0.0001]
Steps:  13%|█▎        | 260/2000 [07:48<50:32,  1.74s/it, loss=0.109, lr=0.0001]
Steps:  13%|█▎        | 260/2000 [07:48<50:32,  1.74s/it, loss=0.21, lr=0.0001] 
Steps:  13%|█▎        | 260/2000 [07:49<50:32,  1.74s/it, loss=0.187, lr=0.0001]
Steps:  13%|█▎        | 260/2000 [07:49<50:32,  1.74s/it, loss=0.265, lr=0.0001]
Steps:  13%|█▎        | 261/2000 [07:49<49:55,  1.72s/it, loss=0.265, lr=0.0001]
Steps:  13%|█▎        | 261/2000 [07:49<49:55,  1.72s/it, loss=0.131, lr=0.0001]
Steps:  13%|█▎        | 261/2000 [07:50<49:55,  1.72s/it, loss=0.237, lr=0.0001]
Steps:  13%|█▎        | 261/2000 [07:50<49:55,  1.72s/it, loss=0.201, lr=0.0001]
Steps:  13%|█▎        | 261/2000 [07:51<49:55,  1.72s/it, loss=0.17, lr=0.0001] 
Steps:  13%|█▎        | 262/2000 [07:51<49:11,  1.70s/it, loss=0.17, lr=0.0001]
Steps:  13%|█▎        | 262/2000 [07:51<49:11,  1.70s/it, loss=0.234, lr=0.0001]
Steps:  13%|█▎        | 262/2000 [07:52<49:11,  1.70s/it, loss=0.139, lr=0.0001]
Steps:  13%|█▎        | 262/2000 [07:52<49:11,  1.70s/it, loss=0.145, lr=0.0001]
Steps:  13%|█▎        | 262/2000 [07:53<49:11,  1.70s/it, loss=0.136, lr=0.0001]
Steps:  13%|█▎        | 263/2000 [07:53<50:36,  1.75s/it, loss=0.136, lr=0.0001]
Steps:  13%|█▎        | 263/2000 [07:53<50:36,  1.75s/it, loss=0.154, lr=0.0001]
Steps:  13%|█▎        | 263/2000 [07:53<50:36,  1.75s/it, loss=0.148, lr=0.0001]
Steps:  13%|█▎        | 263/2000 [07:54<50:36,  1.75s/it, loss=0.0872, lr=0.0001]
Steps:  13%|█▎        | 263/2000 [07:54<50:36,  1.75s/it, loss=0.219, lr=0.0001] 
Steps:  13%|█▎        | 264/2000 [07:55<49:44,  1.72s/it, loss=0.219, lr=0.0001]
Steps:  13%|█▎        | 264/2000 [07:55<49:44,  1.72s/it, loss=0.29, lr=0.0001] 
Steps:  13%|█▎        | 264/2000 [07:55<49:44,  1.72s/it, loss=0.253, lr=0.0001]
Steps:  13%|█▎        | 264/2000 [07:55<49:44,  1.72s/it, loss=0.13, lr=0.0001] 
Steps:  13%|█▎        | 264/2000 [07:56<49:44,  1.72s/it, loss=0.0971, lr=0.0001]
Steps:  13%|█▎        | 265/2000 [07:56<49:01,  1.70s/it, loss=0.0971, lr=0.0001]
Steps:  13%|█▎        | 265/2000 [07:56<49:01,  1.70s/it, loss=0.112, lr=0.0001] 
Steps:  13%|█▎        | 265/2000 [07:57<49:01,  1.70s/it, loss=0.12, lr=0.0001] 
Steps:  13%|█▎        | 265/2000 [07:57<49:01,  1.70s/it, loss=0.093, lr=0.0001]
Steps:  13%|█▎        | 265/2000 [07:58<49:01,  1.70s/it, loss=0.24, lr=0.0001] 
Steps:  13%|█▎        | 266/2000 [07:58<50:44,  1.76s/it, loss=0.24, lr=0.0001]
Steps:  13%|█▎        | 266/2000 [07:58<50:44,  1.76s/it, loss=0.109, lr=0.0001]
Steps:  13%|█▎        | 266/2000 [07:59<50:44,  1.76s/it, loss=0.114, lr=0.0001]
Steps:  13%|█▎        | 266/2000 [07:59<50:44,  1.76s/it, loss=0.234, lr=0.0001]
Steps:  13%|█▎        | 266/2000 [07:59<50:44,  1.76s/it, loss=1.06, lr=0.0001] 
Steps:  13%|█▎        | 267/2000 [08:00<49:50,  1.73s/it, loss=1.06, lr=0.0001]
Steps:  13%|█▎        | 267/2000 [08:00<49:50,  1.73s/it, loss=0.198, lr=0.0001]
Steps:  13%|█▎        | 267/2000 [08:00<49:50,  1.73s/it, loss=1.12, lr=0.0001] 
Steps:  13%|█▎        | 267/2000 [08:01<49:50,  1.73s/it, loss=0.379, lr=0.0001]
Steps:  13%|█▎        | 267/2000 [08:01<49:50,  1.73s/it, loss=0.471, lr=0.0001]
Steps:  13%|█▎        | 268/2000 [08:01<49:30,  1.71s/it, loss=0.471, lr=0.0001]
Steps:  13%|█▎        | 268/2000 [08:01<49:30,  1.71s/it, loss=0.251, lr=0.0001]
Steps:  13%|█▎        | 268/2000 [08:02<49:30,  1.71s/it, loss=0.215, lr=0.0001]
Steps:  13%|█▎        | 268/2000 [08:02<49:30,  1.71s/it, loss=0.101, lr=0.0001]
Steps:  13%|█▎        | 268/2000 [08:03<49:30,  1.71s/it, loss=0.146, lr=0.0001]
Steps:  13%|█▎        | 269/2000 [08:03<51:04,  1.77s/it, loss=0.146, lr=0.0001]
Steps:  13%|█▎        | 269/2000 [08:03<51:04,  1.77s/it, loss=0.12, lr=0.0001] 
Steps:  13%|█▎        | 269/2000 [08:04<51:04,  1.77s/it, loss=0.27, lr=0.0001]
Steps:  13%|█▎        | 269/2000 [08:04<51:04,  1.77s/it, loss=0.128, lr=0.0001]
Steps:  13%|█▎        | 269/2000 [08:05<51:04,  1.77s/it, loss=0.238, lr=0.0001]
Steps:  14%|█▎        | 270/2000 [08:05<50:10,  1.74s/it, loss=0.238, lr=0.0001]
Steps:  14%|█▎        | 270/2000 [08:05<50:10,  1.74s/it, loss=0.187, lr=0.0001]
Steps:  14%|█▎        | 270/2000 [08:05<50:10,  1.74s/it, loss=0.526, lr=0.0001]
Steps:  14%|█▎        | 270/2000 [08:06<50:10,  1.74s/it, loss=0.23, lr=0.0001] 
Steps:  14%|█▎        | 270/2000 [08:06<50:10,  1.74s/it, loss=0.139, lr=0.0001]
Steps:  14%|█▎        | 271/2000 [08:07<49:31,  1.72s/it, loss=0.139, lr=0.0001]
Steps:  14%|█▎        | 271/2000 [08:07<49:31,  1.72s/it, loss=0.298, lr=0.0001]
Steps:  14%|█▎        | 271/2000 [08:07<49:31,  1.72s/it, loss=0.225, lr=0.0001]
Steps:  14%|█▎        | 271/2000 [08:08<49:31,  1.72s/it, loss=0.141, lr=0.0001]
Steps:  14%|█▎        | 271/2000 [08:08<49:31,  1.72s/it, loss=0.223, lr=0.0001]
Steps:  14%|█▎        | 272/2000 [08:09<51:18,  1.78s/it, loss=0.223, lr=0.0001]
Steps:  14%|█▎        | 272/2000 [08:09<51:18,  1.78s/it, loss=0.152, lr=0.0001]
Steps:  14%|█▎        | 272/2000 [08:09<51:18,  1.78s/it, loss=0.247, lr=0.0001]
Steps:  14%|█▎        | 272/2000 [08:09<51:18,  1.78s/it, loss=0.29, lr=0.0001] 
Steps:  14%|█▎        | 272/2000 [08:10<51:18,  1.78s/it, loss=0.241, lr=0.0001]
Steps:  14%|█▎        | 273/2000 [08:10<50:10,  1.74s/it, loss=0.241, lr=0.0001]
Steps:  14%|█▎        | 273/2000 [08:10<50:10,  1.74s/it, loss=0.118, lr=0.0001]
Steps:  14%|█▎        | 273/2000 [08:11<50:10,  1.74s/it, loss=0.129, lr=0.0001]
Steps:  14%|█▎        | 273/2000 [08:11<50:10,  1.74s/it, loss=0.337, lr=0.0001]
Steps:  14%|█▎        | 273/2000 [08:12<50:10,  1.74s/it, loss=0.235, lr=0.0001]
Steps:  14%|█▎        | 274/2000 [08:12<49:31,  1.72s/it, loss=0.235, lr=0.0001]
Steps:  14%|█▎        | 274/2000 [08:12<49:31,  1.72s/it, loss=0.229, lr=0.0001]
Steps:  14%|█▎        | 274/2000 [08:12<49:31,  1.72s/it, loss=0.177, lr=0.0001]
Steps:  14%|█▎        | 274/2000 [08:13<49:31,  1.72s/it, loss=0.169, lr=0.0001]
Steps:  14%|█▎        | 274/2000 [08:13<49:31,  1.72s/it, loss=0.165, lr=0.0001]
Steps:  14%|█▍        | 275/2000 [08:14<51:04,  1.78s/it, loss=0.165, lr=0.0001]
Steps:  14%|█▍        | 275/2000 [08:14<51:04,  1.78s/it, loss=0.237, lr=0.0001]
Steps:  14%|█▍        | 275/2000 [08:14<51:04,  1.78s/it, loss=0.238, lr=0.0001]
Steps:  14%|█▍        | 275/2000 [08:15<51:04,  1.78s/it, loss=0.573, lr=0.0001]
Steps:  14%|█▍        | 275/2000 [08:15<51:04,  1.78s/it, loss=0.267, lr=0.0001]
Steps:  14%|█▍        | 276/2000 [08:16<50:11,  1.75s/it, loss=0.267, lr=0.0001]
Steps:  14%|█▍        | 276/2000 [08:16<50:11,  1.75s/it, loss=0.248, lr=0.0001]
Steps:  14%|█▍        | 276/2000 [08:16<50:11,  1.75s/it, loss=0.134, lr=0.0001]
Steps:  14%|█▍        | 276/2000 [08:16<50:11,  1.75s/it, loss=0.215, lr=0.0001]
Steps:  14%|█▍        | 276/2000 [08:17<50:11,  1.75s/it, loss=0.118, lr=0.0001]
Steps:  14%|█▍        | 277/2000 [08:17<49:20,  1.72s/it, loss=0.118, lr=0.0001]
Steps:  14%|█▍        | 277/2000 [08:17<49:20,  1.72s/it, loss=0.0993, lr=0.0001]
Steps:  14%|█▍        | 277/2000 [08:18<49:20,  1.72s/it, loss=0.103, lr=0.0001] 
Steps:  14%|█▍        | 277/2000 [08:18<49:20,  1.72s/it, loss=0.111, lr=0.0001]
Steps:  14%|█▍        | 277/2000 [08:18<49:20,  1.72s/it, loss=0.143, lr=0.0001]
Steps:  14%|█▍        | 278/2000 [08:19<50:58,  1.78s/it, loss=0.143, lr=0.0001]
Steps:  14%|█▍        | 278/2000 [08:19<50:58,  1.78s/it, loss=0.101, lr=0.0001]
Steps:  14%|█▍        | 278/2000 [08:20<50:58,  1.78s/it, loss=0.233, lr=0.0001]
Steps:  14%|█▍        | 278/2000 [08:20<50:58,  1.78s/it, loss=0.217, lr=0.0001]
Steps:  14%|█▍        | 278/2000 [08:20<50:58,  1.78s/it, loss=0.0961, lr=0.0001]
Steps:  14%|█▍        | 279/2000 [08:21<49:54,  1.74s/it, loss=0.0961, lr=0.0001]
Steps:  14%|█▍        | 279/2000 [08:21<49:54,  1.74s/it, loss=0.101, lr=0.0001] 
Steps:  14%|█▍        | 279/2000 [08:21<49:54,  1.74s/it, loss=0.233, lr=0.0001]
Steps:  14%|█▍        | 279/2000 [08:22<49:54,  1.74s/it, loss=0.332, lr=0.0001]
Steps:  14%|█▍        | 279/2000 [08:22<49:54,  1.74s/it, loss=0.159, lr=0.0001]
Steps:  14%|█▍        | 280/2000 [08:22<49:13,  1.72s/it, loss=0.159, lr=0.0001]
Steps:  14%|█▍        | 280/2000 [08:22<49:13,  1.72s/it, loss=0.137, lr=0.0001]
Steps:  14%|█▍        | 280/2000 [08:23<49:13,  1.72s/it, loss=0.225, lr=0.0001]
Steps:  14%|█▍        | 280/2000 [08:23<49:13,  1.72s/it, loss=0.087, lr=0.0001]
Steps:  14%|█▍        | 280/2000 [08:24<49:13,  1.72s/it, loss=0.476, lr=0.0001]
Steps:  14%|█▍        | 281/2000 [08:24<49:02,  1.71s/it, loss=0.476, lr=0.0001]
Steps:  14%|█▍        | 281/2000 [08:24<49:02,  1.71s/it, loss=0.21, lr=0.0001] 
Steps:  14%|█▍        | 281/2000 [08:25<49:02,  1.71s/it, loss=0.331, lr=0.0001]
Steps:  14%|█▍        | 281/2000 [08:25<49:02,  1.71s/it, loss=0.195, lr=0.0001]
Steps:  14%|█▍        | 281/2000 [08:26<49:02,  1.71s/it, loss=0.152, lr=0.0001]
Steps:  14%|█▍        | 282/2000 [08:26<50:33,  1.77s/it, loss=0.152, lr=0.0001]
Steps:  14%|█▍        | 282/2000 [08:26<50:33,  1.77s/it, loss=0.298, lr=0.0001]
Steps:  14%|█▍        | 282/2000 [08:26<50:33,  1.77s/it, loss=0.585, lr=0.0001]
Steps:  14%|█▍        | 282/2000 [08:27<50:33,  1.77s/it, loss=1.13, lr=0.0001] 
Steps:  14%|█▍        | 282/2000 [08:27<50:33,  1.77s/it, loss=0.143, lr=0.0001]
Steps:  14%|█▍        | 283/2000 [08:28<49:29,  1.73s/it, loss=0.143, lr=0.0001]
Steps:  14%|█▍        | 283/2000 [08:28<49:29,  1.73s/it, loss=0.15, lr=0.0001] 
Steps:  14%|█▍        | 283/2000 [08:28<49:29,  1.73s/it, loss=0.309, lr=0.0001]
Steps:  14%|█▍        | 283/2000 [08:28<49:29,  1.73s/it, loss=1.38, lr=0.0001] 
Steps:  14%|█▍        | 283/2000 [08:29<49:29,  1.73s/it, loss=0.201, lr=0.0001]
Steps:  14%|█▍        | 284/2000 [08:29<48:50,  1.71s/it, loss=0.201, lr=0.0001]
Steps:  14%|█▍        | 284/2000 [08:29<48:50,  1.71s/it, loss=0.0928, lr=0.0001]
Steps:  14%|█▍        | 284/2000 [08:30<48:50,  1.71s/it, loss=0.192, lr=0.0001] 
Steps:  14%|█▍        | 284/2000 [08:30<48:50,  1.71s/it, loss=0.352, lr=0.0001]
Steps:  14%|█▍        | 284/2000 [08:31<48:50,  1.71s/it, loss=0.0393, lr=0.0001]
Steps:  14%|█▍        | 285/2000 [08:31<50:15,  1.76s/it, loss=0.0393, lr=0.0001]
Steps:  14%|█▍        | 285/2000 [08:31<50:15,  1.76s/it, loss=0.214, lr=0.0001] 
Steps:  14%|█▍        | 285/2000 [08:32<50:15,  1.76s/it, loss=0.173, lr=0.0001]
Steps:  14%|█▍        | 285/2000 [08:32<50:15,  1.76s/it, loss=0.0696, lr=0.0001]
Steps:  14%|█▍        | 285/2000 [08:32<50:15,  1.76s/it, loss=0.27, lr=0.0001]  
Steps:  14%|█▍        | 286/2000 [08:33<49:31,  1.73s/it, loss=0.27, lr=0.0001]
Steps:  14%|█▍        | 286/2000 [08:33<49:31,  1.73s/it, loss=0.18, lr=0.0001]
Steps:  14%|█▍        | 286/2000 [08:33<49:31,  1.73s/it, loss=0.183, lr=0.0001]
Steps:  14%|█▍        | 286/2000 [08:34<49:31,  1.73s/it, loss=0.298, lr=0.0001]
Steps:  14%|█▍        | 286/2000 [08:34<49:31,  1.73s/it, loss=0.152, lr=0.0001]
Steps:  14%|█▍        | 287/2000 [08:35<48:53,  1.71s/it, loss=0.152, lr=0.0001]
Steps:  14%|█▍        | 287/2000 [08:35<48:53,  1.71s/it, loss=0.203, lr=0.0001]
Steps:  14%|█▍        | 287/2000 [08:35<48:53,  1.71s/it, loss=0.193, lr=0.0001]
Steps:  14%|█▍        | 287/2000 [08:36<48:53,  1.71s/it, loss=0.204, lr=0.0001]
Steps:  14%|█▍        | 287/2000 [08:36<48:53,  1.71s/it, loss=0.148, lr=0.0001]
Steps:  14%|█▍        | 288/2000 [08:36<50:37,  1.77s/it, loss=0.148, lr=0.0001]
Steps:  14%|█▍        | 288/2000 [08:36<50:37,  1.77s/it, loss=0.136, lr=0.0001]
Steps:  14%|█▍        | 288/2000 [08:37<50:37,  1.77s/it, loss=0.117, lr=0.0001]
Steps:  14%|█▍        | 288/2000 [08:37<50:37,  1.77s/it, loss=0.244, lr=0.0001]
Steps:  14%|█▍        | 288/2000 [08:38<50:37,  1.77s/it, loss=0.191, lr=0.0001]
Steps:  14%|█▍        | 289/2000 [08:38<49:28,  1.74s/it, loss=0.191, lr=0.0001]
Steps:  14%|█▍        | 289/2000 [08:38<49:28,  1.74s/it, loss=0.162, lr=0.0001]
Steps:  14%|█▍        | 289/2000 [08:39<49:28,  1.74s/it, loss=0.154, lr=0.0001]
Steps:  14%|█▍        | 289/2000 [08:39<49:28,  1.74s/it, loss=0.101, lr=0.0001]
Steps:  14%|█▍        | 289/2000 [08:39<49:28,  1.74s/it, loss=0.115, lr=0.0001]
Steps:  14%|█▍        | 290/2000 [08:40<48:49,  1.71s/it, loss=0.115, lr=0.0001]
Steps:  14%|█▍        | 290/2000 [08:40<48:49,  1.71s/it, loss=0.175, lr=0.0001]
Steps:  14%|█▍        | 290/2000 [08:40<48:49,  1.71s/it, loss=0.162, lr=0.0001]
Steps:  14%|█▍        | 290/2000 [08:41<48:49,  1.71s/it, loss=0.19, lr=0.0001] 
Steps:  14%|█▍        | 290/2000 [08:41<48:49,  1.71s/it, loss=0.173, lr=0.0001]
Steps:  15%|█▍        | 291/2000 [08:42<50:18,  1.77s/it, loss=0.173, lr=0.0001]
Steps:  15%|█▍        | 291/2000 [08:42<50:18,  1.77s/it, loss=0.165, lr=0.0001]
Steps:  15%|█▍        | 291/2000 [08:42<50:18,  1.77s/it, loss=0.164, lr=0.0001]
Steps:  15%|█▍        | 291/2000 [08:42<50:18,  1.77s/it, loss=0.118, lr=0.0001]
Steps:  15%|█▍        | 291/2000 [08:43<50:18,  1.77s/it, loss=0.156, lr=0.0001]
Steps:  15%|█▍        | 292/2000 [08:43<49:19,  1.73s/it, loss=0.156, lr=0.0001]
Steps:  15%|█▍        | 292/2000 [08:43<49:19,  1.73s/it, loss=0.137, lr=0.0001]
Steps:  15%|█▍        | 292/2000 [08:44<49:19,  1.73s/it, loss=0.156, lr=0.0001]
Steps:  15%|█▍        | 292/2000 [08:44<49:19,  1.73s/it, loss=0.145, lr=0.0001]
Steps:  15%|█▍        | 292/2000 [08:45<49:19,  1.73s/it, loss=0.0748, lr=0.0001]
Steps:  15%|█▍        | 293/2000 [08:45<48:42,  1.71s/it, loss=0.0748, lr=0.0001]
Steps:  15%|█▍        | 293/2000 [08:45<48:42,  1.71s/it, loss=0.16, lr=0.0001]  
Steps:  15%|█▍        | 293/2000 [08:45<48:42,  1.71s/it, loss=0.221, lr=0.0001]
Steps:  15%|█▍        | 293/2000 [08:46<48:42,  1.71s/it, loss=0.239, lr=0.0001]
Steps:  15%|█▍        | 293/2000 [08:46<48:42,  1.71s/it, loss=0.215, lr=0.0001]
Steps:  15%|█▍        | 294/2000 [08:47<50:13,  1.77s/it, loss=0.215, lr=0.0001]
Steps:  15%|█▍        | 294/2000 [08:47<50:13,  1.77s/it, loss=0.125, lr=0.0001]
Steps:  15%|█▍        | 294/2000 [08:47<50:13,  1.77s/it, loss=0.225, lr=0.0001]
Steps:  15%|█▍        | 294/2000 [08:48<50:13,  1.77s/it, loss=0.874, lr=0.0001]
Steps:  15%|█▍        | 294/2000 [08:48<50:13,  1.77s/it, loss=0.192, lr=0.0001]
Steps:  15%|█▍        | 295/2000 [08:49<49:29,  1.74s/it, loss=0.192, lr=0.0001]
Steps:  15%|█▍        | 295/2000 [08:49<49:29,  1.74s/it, loss=0.501, lr=0.0001]
Steps:  15%|█▍        | 295/2000 [08:49<49:29,  1.74s/it, loss=0.145, lr=0.0001]
Steps:  15%|█▍        | 295/2000 [08:49<49:29,  1.74s/it, loss=0.528, lr=0.0001]
Steps:  15%|█▍        | 295/2000 [08:50<49:29,  1.74s/it, loss=0.173, lr=0.0001]
Steps:  15%|█▍        | 296/2000 [08:50<48:46,  1.72s/it, loss=0.173, lr=0.0001]
Steps:  15%|█▍        | 296/2000 [08:50<48:46,  1.72s/it, loss=0.188, lr=0.0001]
Steps:  15%|█▍        | 296/2000 [08:51<48:46,  1.72s/it, loss=0.196, lr=0.0001]
Steps:  15%|█▍        | 296/2000 [08:51<48:46,  1.72s/it, loss=0.194, lr=0.0001]
Steps:  15%|█▍        | 296/2000 [08:51<48:46,  1.72s/it, loss=0.185, lr=0.0001]
Steps:  15%|█▍        | 297/2000 [08:52<50:18,  1.77s/it, loss=0.185, lr=0.0001]
Steps:  15%|█▍        | 297/2000 [08:52<50:18,  1.77s/it, loss=0.347, lr=0.0001]
Steps:  15%|█▍        | 297/2000 [08:53<50:18,  1.77s/it, loss=0.142, lr=0.0001]
Steps:  15%|█▍        | 297/2000 [08:53<50:18,  1.77s/it, loss=0.227, lr=0.0001]
Steps:  15%|█▍        | 297/2000 [08:53<50:18,  1.77s/it, loss=1.72, lr=0.0001] 
Steps:  15%|█▍        | 298/2000 [08:54<49:13,  1.74s/it, loss=1.72, lr=0.0001]
Steps:  15%|█▍        | 298/2000 [08:54<49:13,  1.74s/it, loss=0.109, lr=0.0001]
Steps:  15%|█▍        | 298/2000 [08:54<49:13,  1.74s/it, loss=0.339, lr=0.0001]
Steps:  15%|█▍        | 298/2000 [08:55<49:13,  1.74s/it, loss=0.131, lr=0.0001]
Steps:  15%|█▍        | 298/2000 [08:55<49:13,  1.74s/it, loss=0.182, lr=0.0001]
Steps:  15%|█▍        | 299/2000 [08:55<48:29,  1.71s/it, loss=0.182, lr=0.0001]
Steps:  15%|█▍        | 299/2000 [08:55<48:29,  1.71s/it, loss=0.144, lr=0.0001]
Steps:  15%|█▍        | 299/2000 [08:56<48:29,  1.71s/it, loss=0.119, lr=0.0001]
Steps:  15%|█▍        | 299/2000 [08:56<48:29,  1.71s/it, loss=0.426, lr=0.0001]
Steps:  15%|█▍        | 299/2000 [08:57<48:29,  1.71s/it, loss=0.236, lr=0.0001]
Steps:  15%|█▌        | 300/2000 [08:57<48:11,  1.70s/it, loss=0.236, lr=0.0001]
Steps:  15%|█▌        | 300/2000 [08:57<48:11,  1.70s/it, loss=0.169, lr=0.0001]
Steps:  15%|█▌        | 300/2000 [08:58<48:11,  1.70s/it, loss=0.134, lr=0.0001]
Steps:  15%|█▌        | 300/2000 [08:58<48:11,  1.70s/it, loss=0.145, lr=0.0001]
Steps:  15%|█▌        | 300/2000 [08:59<48:11,  1.70s/it, loss=0.0887, lr=0.0001]
Steps:  15%|█▌        | 301/2000 [08:59<49:56,  1.76s/it, loss=0.0887, lr=0.0001]
Steps:  15%|█▌        | 301/2000 [08:59<49:56,  1.76s/it, loss=0.101, lr=0.0001] 
Steps:  15%|█▌        | 301/2000 [08:59<49:56,  1.76s/it, loss=0.0559, lr=0.0001]
Steps:  15%|█▌        | 301/2000 [09:00<49:56,  1.76s/it, loss=0.173, lr=0.0001] 
Steps:  15%|█▌        | 301/2000 [09:00<49:56,  1.76s/it, loss=0.226, lr=0.0001]
Steps:  15%|█▌        | 302/2000 [09:01<48:56,  1.73s/it, loss=0.226, lr=0.0001]
Steps:  15%|█▌        | 302/2000 [09:01<48:56,  1.73s/it, loss=0.286, lr=0.0001]
Steps:  15%|█▌        | 302/2000 [09:01<48:56,  1.73s/it, loss=0.214, lr=0.0001]
Steps:  15%|█▌        | 302/2000 [09:01<48:56,  1.73s/it, loss=2, lr=0.0001]    
Steps:  15%|█▌        | 302/2000 [09:02<48:56,  1.73s/it, loss=0.228, lr=0.0001]
Steps:  15%|█▌        | 303/2000 [09:02<48:37,  1.72s/it, loss=0.228, lr=0.0001]
Steps:  15%|█▌        | 303/2000 [09:02<48:37,  1.72s/it, loss=0.09, lr=0.0001] 
Steps:  15%|█▌        | 303/2000 [09:03<48:37,  1.72s/it, loss=0.139, lr=0.0001]
Steps:  15%|█▌        | 303/2000 [09:03<48:37,  1.72s/it, loss=0.146, lr=0.0001]
Steps:  15%|█▌        | 303/2000 [09:04<48:37,  1.72s/it, loss=0.135, lr=0.0001]
Steps:  15%|█▌        | 304/2000 [09:04<49:59,  1.77s/it, loss=0.135, lr=0.0001]
Steps:  15%|█▌        | 304/2000 [09:04<49:59,  1.77s/it, loss=0.124, lr=0.0001]
Steps:  15%|█▌        | 304/2000 [09:05<49:59,  1.77s/it, loss=0.0637, lr=0.0001]
Steps:  15%|█▌        | 304/2000 [09:05<49:59,  1.77s/it, loss=0.147, lr=0.0001] 
Steps:  15%|█▌        | 304/2000 [09:05<49:59,  1.77s/it, loss=0.358, lr=0.0001]
Steps:  15%|█▌        | 305/2000 [09:06<48:55,  1.73s/it, loss=0.358, lr=0.0001]
Steps:  15%|█▌        | 305/2000 [09:06<48:55,  1.73s/it, loss=0.267, lr=0.0001]
Steps:  15%|█▌        | 305/2000 [09:06<48:55,  1.73s/it, loss=0.159, lr=0.0001]
Steps:  15%|█▌        | 305/2000 [09:07<48:55,  1.73s/it, loss=0.126, lr=0.0001]
Steps:  15%|█▌        | 305/2000 [09:07<48:55,  1.73s/it, loss=0.233, lr=0.0001]
Steps:  15%|█▌        | 306/2000 [09:08<48:27,  1.72s/it, loss=0.233, lr=0.0001]
Steps:  15%|█▌        | 306/2000 [09:08<48:27,  1.72s/it, loss=0.234, lr=0.0001]
Steps:  15%|█▌        | 306/2000 [09:08<48:27,  1.72s/it, loss=0.0874, lr=0.0001]
Steps:  15%|█▌        | 306/2000 [09:09<48:27,  1.72s/it, loss=0.184, lr=0.0001] 
Steps:  15%|█▌        | 306/2000 [09:09<48:27,  1.72s/it, loss=0.449, lr=0.0001]
Steps:  15%|█▌        | 307/2000 [09:09<49:51,  1.77s/it, loss=0.449, lr=0.0001]
Steps:  15%|█▌        | 307/2000 [09:09<49:51,  1.77s/it, loss=0.247, lr=0.0001]
Steps:  15%|█▌        | 307/2000 [09:10<49:51,  1.77s/it, loss=0.221, lr=0.0001]
Steps:  15%|█▌        | 307/2000 [09:10<49:51,  1.77s/it, loss=0.0305, lr=0.0001]
Steps:  15%|█▌        | 307/2000 [09:11<49:51,  1.77s/it, loss=0.166, lr=0.0001] 
Steps:  15%|█▌        | 308/2000 [09:11<48:52,  1.73s/it, loss=0.166, lr=0.0001]
Steps:  15%|█▌        | 308/2000 [09:11<48:52,  1.73s/it, loss=0.183, lr=0.0001]
Steps:  15%|█▌        | 308/2000 [09:12<48:52,  1.73s/it, loss=0.131, lr=0.0001]
Steps:  15%|█▌        | 308/2000 [09:12<48:52,  1.73s/it, loss=0.169, lr=0.0001]
Steps:  15%|█▌        | 308/2000 [09:12<48:52,  1.73s/it, loss=0.136, lr=0.0001]
Steps:  15%|█▌        | 309/2000 [09:13<48:08,  1.71s/it, loss=0.136, lr=0.0001]
Steps:  15%|█▌        | 309/2000 [09:13<48:08,  1.71s/it, loss=0.141, lr=0.0001]
Steps:  15%|█▌        | 309/2000 [09:13<48:08,  1.71s/it, loss=0.162, lr=0.0001]
Steps:  15%|█▌        | 309/2000 [09:14<48:08,  1.71s/it, loss=0.18, lr=0.0001] 
Steps:  15%|█▌        | 309/2000 [09:14<48:08,  1.71s/it, loss=0.242, lr=0.0001]
Steps:  16%|█▌        | 310/2000 [09:15<50:10,  1.78s/it, loss=0.242, lr=0.0001]
Steps:  16%|█▌        | 310/2000 [09:15<50:10,  1.78s/it, loss=0.0865, lr=0.0001]
Steps:  16%|█▌        | 310/2000 [09:15<50:10,  1.78s/it, loss=0.238, lr=0.0001] 
Steps:  16%|█▌        | 310/2000 [09:16<50:10,  1.78s/it, loss=0.0966, lr=0.0001]
Steps:  16%|█▌        | 310/2000 [09:16<50:10,  1.78s/it, loss=0.614, lr=0.0001] 
Steps:  16%|█▌        | 311/2000 [09:16<49:41,  1.77s/it, loss=0.614, lr=0.0001]
Steps:  16%|█▌        | 311/2000 [09:16<49:41,  1.77s/it, loss=0.107, lr=0.0001]
Steps:  16%|█▌        | 311/2000 [09:17<49:41,  1.77s/it, loss=0.162, lr=0.0001]
Steps:  16%|█▌        | 311/2000 [09:17<49:41,  1.77s/it, loss=0.345, lr=0.0001]
Steps:  16%|█▌        | 311/2000 [09:18<49:41,  1.77s/it, loss=0.237, lr=0.0001]
Steps:  16%|█▌        | 312/2000 [09:18<48:54,  1.74s/it, loss=0.237, lr=0.0001]
Steps:  16%|█▌        | 312/2000 [09:18<48:54,  1.74s/it, loss=0.268, lr=0.0001]
Steps:  16%|█▌        | 312/2000 [09:19<48:54,  1.74s/it, loss=0.144, lr=0.0001]
Steps:  16%|█▌        | 312/2000 [09:19<48:54,  1.74s/it, loss=0.199, lr=0.0001]
Steps:  16%|█▌        | 312/2000 [09:20<48:54,  1.74s/it, loss=0.206, lr=0.0001]
Steps:  16%|█▌        | 313/2000 [09:20<50:09,  1.78s/it, loss=0.206, lr=0.0001]
Steps:  16%|█▌        | 313/2000 [09:20<50:09,  1.78s/it, loss=0.23, lr=0.0001] 
Steps:  16%|█▌        | 313/2000 [09:20<50:09,  1.78s/it, loss=0.156, lr=0.0001]
Steps:  16%|█▌        | 313/2000 [09:21<50:09,  1.78s/it, loss=0.132, lr=0.0001]
Steps:  16%|█▌        | 313/2000 [09:21<50:09,  1.78s/it, loss=0.177, lr=0.0001]
Steps:  16%|█▌        | 314/2000 [09:22<49:01,  1.74s/it, loss=0.177, lr=0.0001]
Steps:  16%|█▌        | 314/2000 [09:22<49:01,  1.74s/it, loss=0.153, lr=0.0001]
Steps:  16%|█▌        | 314/2000 [09:22<49:01,  1.74s/it, loss=0.298, lr=0.0001]
Steps:  16%|█▌        | 314/2000 [09:22<49:01,  1.74s/it, loss=0.11, lr=0.0001] 
Steps:  16%|█▌        | 314/2000 [09:23<49:01,  1.74s/it, loss=0.124, lr=0.0001]
Steps:  16%|█▌        | 315/2000 [09:23<48:18,  1.72s/it, loss=0.124, lr=0.0001]
Steps:  16%|█▌        | 315/2000 [09:23<48:18,  1.72s/it, loss=0.224, lr=0.0001]
Steps:  16%|█▌        | 315/2000 [09:24<48:18,  1.72s/it, loss=0.219, lr=0.0001]
Steps:  16%|█▌        | 315/2000 [09:24<48:18,  1.72s/it, loss=0.198, lr=0.0001]
Steps:  16%|█▌        | 315/2000 [09:25<48:18,  1.72s/it, loss=0.0795, lr=0.0001]
Steps:  16%|█▌        | 316/2000 [09:25<50:07,  1.79s/it, loss=0.0795, lr=0.0001]
Steps:  16%|█▌        | 316/2000 [09:25<50:07,  1.79s/it, loss=0.123, lr=0.0001] 
Steps:  16%|█▌        | 316/2000 [09:26<50:07,  1.79s/it, loss=0.0716, lr=0.0001]
Steps:  16%|█▌        | 316/2000 [09:26<50:07,  1.79s/it, loss=0.426, lr=0.0001] 
Steps:  16%|█▌        | 316/2000 [09:26<50:07,  1.79s/it, loss=0.22, lr=0.0001] 
Steps:  16%|█▌        | 317/2000 [09:27<49:16,  1.76s/it, loss=0.22, lr=0.0001]
Steps:  16%|█▌        | 317/2000 [09:27<49:16,  1.76s/it, loss=0.998, lr=0.0001]
Steps:  16%|█▌        | 317/2000 [09:27<49:16,  1.76s/it, loss=0.133, lr=0.0001]
Steps:  16%|█▌        | 317/2000 [09:28<49:16,  1.76s/it, loss=0.236, lr=0.0001]
Steps:  16%|█▌        | 317/2000 [09:28<49:16,  1.76s/it, loss=0.15, lr=0.0001] 
Steps:  16%|█▌        | 318/2000 [09:29<48:29,  1.73s/it, loss=0.15, lr=0.0001]
Steps:  16%|█▌        | 318/2000 [09:29<48:29,  1.73s/it, loss=0.227, lr=0.0001]
Steps:  16%|█▌        | 318/2000 [09:29<48:29,  1.73s/it, loss=0.109, lr=0.0001]
Steps:  16%|█▌        | 318/2000 [09:29<48:29,  1.73s/it, loss=0.178, lr=0.0001]
Steps:  16%|█▌        | 318/2000 [09:30<48:29,  1.73s/it, loss=0.175, lr=0.0001]
Steps:  16%|█▌        | 319/2000 [09:30<49:38,  1.77s/it, loss=0.175, lr=0.0001]
Steps:  16%|█▌        | 319/2000 [09:30<49:38,  1.77s/it, loss=0.133, lr=0.0001]
Steps:  16%|█▌        | 319/2000 [09:31<49:38,  1.77s/it, loss=0.141, lr=0.0001]
Steps:  16%|█▌        | 319/2000 [09:31<49:38,  1.77s/it, loss=0.176, lr=0.0001]
Steps:  16%|█▌        | 319/2000 [09:32<49:38,  1.77s/it, loss=0.193, lr=0.0001]
Steps:  16%|█▌        | 320/2000 [09:32<48:46,  1.74s/it, loss=0.193, lr=0.0001]
Steps:  16%|█▌        | 320/2000 [09:32<48:46,  1.74s/it, loss=0.188, lr=0.0001]
Steps:  16%|█▌        | 320/2000 [09:33<48:46,  1.74s/it, loss=0.226, lr=0.0001]
Steps:  16%|█▌        | 320/2000 [09:33<48:46,  1.74s/it, loss=0.196, lr=0.0001]
Steps:  16%|█▌        | 320/2000 [09:33<48:46,  1.74s/it, loss=0.204, lr=0.0001]
Steps:  16%|█▌        | 321/2000 [09:34<47:56,  1.71s/it, loss=0.204, lr=0.0001]
Steps:  16%|█▌        | 321/2000 [09:34<47:56,  1.71s/it, loss=0.259, lr=0.0001]
Steps:  16%|█▌        | 321/2000 [09:34<47:56,  1.71s/it, loss=0.226, lr=0.0001]
Steps:  16%|█▌        | 321/2000 [09:35<47:56,  1.71s/it, loss=0.117, lr=0.0001]
Steps:  16%|█▌        | 321/2000 [09:35<47:56,  1.71s/it, loss=0.311, lr=0.0001]
Steps:  16%|█▌        | 322/2000 [09:35<47:19,  1.69s/it, loss=0.311, lr=0.0001]
Steps:  16%|█▌        | 322/2000 [09:35<47:19,  1.69s/it, loss=0.146, lr=0.0001]
Steps:  16%|█▌        | 322/2000 [09:36<47:19,  1.69s/it, loss=0.156, lr=0.0001]
Steps:  16%|█▌        | 322/2000 [09:36<47:19,  1.69s/it, loss=0.0942, lr=0.0001]
Steps:  16%|█▌        | 322/2000 [09:37<47:19,  1.69s/it, loss=0.182, lr=0.0001] 
Steps:  16%|█▌        | 323/2000 [09:37<48:48,  1.75s/it, loss=0.182, lr=0.0001]
Steps:  16%|█▌        | 323/2000 [09:37<48:48,  1.75s/it, loss=0.147, lr=0.0001]
Steps:  16%|█▌        | 323/2000 [09:38<48:48,  1.75s/it, loss=0.236, lr=0.0001]
Steps:  16%|█▌        | 323/2000 [09:38<48:48,  1.75s/it, loss=0.225, lr=0.0001]
Steps:  16%|█▌        | 323/2000 [09:39<48:48,  1.75s/it, loss=0.15, lr=0.0001] 
Steps:  16%|█▌        | 324/2000 [09:39<47:59,  1.72s/it, loss=0.15, lr=0.0001]
Steps:  16%|█▌        | 324/2000 [09:39<47:59,  1.72s/it, loss=0.181, lr=0.0001]
Steps:  16%|█▌        | 324/2000 [09:39<47:59,  1.72s/it, loss=0.275, lr=0.0001]
Steps:  16%|█▌        | 324/2000 [09:40<47:59,  1.72s/it, loss=0.25, lr=0.0001] 
Steps:  16%|█▌        | 324/2000 [09:40<47:59,  1.72s/it, loss=0.439, lr=0.0001]
Steps:  16%|█▋        | 325/2000 [09:41<47:23,  1.70s/it, loss=0.439, lr=0.0001]
Steps:  16%|█▋        | 325/2000 [09:41<47:23,  1.70s/it, loss=0.349, lr=0.0001]
Steps:  16%|█▋        | 325/2000 [09:41<47:23,  1.70s/it, loss=0.226, lr=0.0001]
Steps:  16%|█▋        | 325/2000 [09:42<47:23,  1.70s/it, loss=0.272, lr=0.0001]
Steps:  16%|█▋        | 325/2000 [09:42<47:23,  1.70s/it, loss=0.156, lr=0.0001]
Steps:  16%|█▋        | 326/2000 [09:42<48:41,  1.75s/it, loss=0.156, lr=0.0001]
Steps:  16%|█▋        | 326/2000 [09:42<48:41,  1.75s/it, loss=0.242, lr=0.0001]
Steps:  16%|█▋        | 326/2000 [09:43<48:41,  1.75s/it, loss=0.229, lr=0.0001]
Steps:  16%|█▋        | 326/2000 [09:43<48:41,  1.75s/it, loss=0.16, lr=0.0001] 
Steps:  16%|█▋        | 326/2000 [09:44<48:41,  1.75s/it, loss=0.156, lr=0.0001]
Steps:  16%|█▋        | 327/2000 [09:44<47:38,  1.71s/it, loss=0.156, lr=0.0001]
Steps:  16%|█▋        | 327/2000 [09:44<47:38,  1.71s/it, loss=0.254, lr=0.0001]
Steps:  16%|█▋        | 327/2000 [09:44<47:38,  1.71s/it, loss=0.173, lr=0.0001]
Steps:  16%|█▋        | 327/2000 [09:45<47:38,  1.71s/it, loss=0.0947, lr=0.0001]
Steps:  16%|█▋        | 327/2000 [09:45<47:38,  1.71s/it, loss=0.101, lr=0.0001] 
Steps:  16%|█▋        | 328/2000 [09:46<46:57,  1.69s/it, loss=0.101, lr=0.0001]
Steps:  16%|█▋        | 328/2000 [09:46<46:57,  1.69s/it, loss=0.183, lr=0.0001]
Steps:  16%|█▋        | 328/2000 [09:46<46:57,  1.69s/it, loss=0.455, lr=0.0001]
Steps:  16%|█▋        | 328/2000 [09:47<46:57,  1.69s/it, loss=0.23, lr=0.0001] 
Steps:  16%|█▋        | 328/2000 [09:47<46:57,  1.69s/it, loss=0.148, lr=0.0001]
Steps:  16%|█▋        | 329/2000 [09:48<48:20,  1.74s/it, loss=0.148, lr=0.0001]
Steps:  16%|█▋        | 329/2000 [09:48<48:20,  1.74s/it, loss=0.207, lr=0.0001]
Steps:  16%|█▋        | 329/2000 [09:48<48:20,  1.74s/it, loss=0.947, lr=0.0001]
Steps:  16%|█▋        | 329/2000 [09:48<48:20,  1.74s/it, loss=0.17, lr=0.0001] 
Steps:  16%|█▋        | 329/2000 [09:49<48:20,  1.74s/it, loss=0.198, lr=0.0001]
Steps:  16%|█▋        | 330/2000 [09:49<47:29,  1.71s/it, loss=0.198, lr=0.0001]
Steps:  16%|█▋        | 330/2000 [09:49<47:29,  1.71s/it, loss=0.129, lr=0.0001]05/30/2026 08:42:14 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/config.json "HTTP/1.1 200 OK"
05/30/2026 08:42:15 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/config.json "HTTP/1.1 200 OK"
05/30/2026 08:42:15 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/model.safetensors "HTTP/1.1 302 Found"


Loading weights:   0%|          | 0/196 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 196/196 [00:00<00:00, 9042.53it/s]
05/30/2026 08:42:15 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/config.json "HTTP/1.1 200 OK"
05/30/2026 08:42:15 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/config.json "HTTP/1.1 200 OK"
05/30/2026 08:42:15 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/model.safetensors "HTTP/1.1 404 Not Found"
05/30/2026 08:42:15 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/model.safetensors.index.json "HTTP/1.1 200 OK"
05/30/2026 08:42:15 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev/revision/main "HTTP/1.1 200 OK"


Fetching 2 files:   0%|          | 0/2 [00:00<?, ?it/s]
Fetching 2 files: 100%|██████████| 2/2 [00:00<00:00, 3751.61it/s]


Loading weights:   0%|          | 0/219 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 219/219 [00:00<00:00, 7330.94it/s]
05/30/2026 08:42:16 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev "HTTP/1.1 200 OK"
05/30/2026 08:42:16 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/model_index.json "HTTP/1.1 200 OK"
{'feature_extractor', 'image_encoder'} was not found in config. Values will be initialized to default values.


Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]Loaded tokenizer_2 as T5TokenizerFast from `tokenizer_2` subfolder of black-forest-labs/FLUX.1-dev.


Loading pipeline components...:  43%|████▎     | 3/7 [00:00<00:00, 17.55it/s]Loaded tokenizer as CLIPTokenizer from `tokenizer` subfolder of black-forest-labs/FLUX.1-dev.
{'stochastic_sampling', 'use_beta_sigmas', 'invert_sigmas', 'time_shift_type', 'use_exponential_sigmas', 'shift_terminal', 'use_karras_sigmas'} was not found in config. Values will be initialized to default values.
Loaded scheduler as FlowMatchEulerDiscreteScheduler from `scheduler` subfolder of black-forest-labs/FLUX.1-dev.

Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 31.35it/s]
05/30/2026 08:42:16 - INFO - __main__ - [RANK 0] Running validation... 
 Generating 1 images with prompt: emj icon of a pelican with a hat, centered on a plain white background.

Steps:  16%|█▋        | 330/2000 [10:02<47:29,  1.71s/it, loss=0.157, lr=0.0001]
Steps:  16%|█▋        | 330/2000 [10:02<47:29,  1.71s/it, loss=0.164, lr=0.0001]
Steps:  16%|█▋        | 330/2000 [10:02<47:29,  1.71s/it, loss=0.145, lr=0.0001]
Steps:  17%|█▋        | 331/2000 [10:03<2:27:03,  5.29s/it, loss=0.145, lr=0.0001]
Steps:  17%|█▋        | 331/2000 [10:03<2:27:03,  5.29s/it, loss=0.511, lr=0.0001]
Steps:  17%|█▋        | 331/2000 [10:03<2:27:03,  5.29s/it, loss=0.168, lr=0.0001]
Steps:  17%|█▋        | 331/2000 [10:04<2:27:03,  5.29s/it, loss=0.156, lr=0.0001]
Steps:  17%|█▋        | 331/2000 [10:04<2:27:03,  5.29s/it, loss=0.187, lr=0.0001]
Steps:  17%|█▋        | 332/2000 [10:05<1:57:14,  4.22s/it, loss=0.187, lr=0.0001]
Steps:  17%|█▋        | 332/2000 [10:05<1:57:14,  4.22s/it, loss=1.05, lr=0.0001] 
Steps:  17%|█▋        | 332/2000 [10:05<1:57:14,  4.22s/it, loss=0.0533, lr=0.0001]
Steps:  17%|█▋        | 332/2000 [10:05<1:57:14,  4.22s/it, loss=0.212, lr=0.0001] 
Steps:  17%|█▋        | 332/2000 [10:06<1:57:14,  4.22s/it, loss=0.124, lr=0.0001]
Steps:  17%|█▋        | 333/2000 [10:06<1:36:26,  3.47s/it, loss=0.124, lr=0.0001]
Steps:  17%|█▋        | 333/2000 [10:06<1:36:26,  3.47s/it, loss=1.26, lr=0.0001] 
Steps:  17%|█▋        | 333/2000 [10:07<1:36:26,  3.47s/it, loss=0.223, lr=0.0001]
Steps:  17%|█▋        | 333/2000 [10:07<1:36:26,  3.47s/it, loss=0.107, lr=0.0001]
Steps:  17%|█▋        | 333/2000 [10:08<1:36:26,  3.47s/it, loss=0.174, lr=0.0001]
Steps:  17%|█▋        | 334/2000 [10:08<1:24:09,  3.03s/it, loss=0.174, lr=0.0001]
Steps:  17%|█▋        | 334/2000 [10:08<1:24:09,  3.03s/it, loss=0.198, lr=0.0001]
Steps:  17%|█▋        | 334/2000 [10:09<1:24:09,  3.03s/it, loss=0.215, lr=0.0001]
Steps:  17%|█▋        | 334/2000 [10:09<1:24:09,  3.03s/it, loss=0.152, lr=0.0001]
Steps:  17%|█▋        | 334/2000 [10:10<1:24:09,  3.03s/it, loss=0.22, lr=0.0001] 
Steps:  17%|█▋        | 335/2000 [10:10<1:13:43,  2.66s/it, loss=0.22, lr=0.0001]
Steps:  17%|█▋        | 335/2000 [10:10<1:13:43,  2.66s/it, loss=0.218, lr=0.0001]
Steps:  17%|█▋        | 335/2000 [10:11<1:13:43,  2.66s/it, loss=0.123, lr=0.0001]
Steps:  17%|█▋        | 335/2000 [10:11<1:13:43,  2.66s/it, loss=0.229, lr=0.0001]
Steps:  17%|█▋        | 335/2000 [10:11<1:13:43,  2.66s/it, loss=0.384, lr=0.0001]
Steps:  17%|█▋        | 336/2000 [10:12<1:05:49,  2.37s/it, loss=0.384, lr=0.0001]
Steps:  17%|█▋        | 336/2000 [10:12<1:05:49,  2.37s/it, loss=0.255, lr=0.0001]
Steps:  17%|█▋        | 336/2000 [10:12<1:05:49,  2.37s/it, loss=0.269, lr=0.0001]
Steps:  17%|█▋        | 336/2000 [10:13<1:05:49,  2.37s/it, loss=0.324, lr=0.0001]
Steps:  17%|█▋        | 336/2000 [10:13<1:05:49,  2.37s/it, loss=0.479, lr=0.0001]
Steps:  17%|█▋        | 337/2000 [10:14<1:02:33,  2.26s/it, loss=0.479, lr=0.0001]
Steps:  17%|█▋        | 337/2000 [10:14<1:02:33,  2.26s/it, loss=0.214, lr=0.0001]
Steps:  17%|█▋        | 337/2000 [10:14<1:02:33,  2.26s/it, loss=0.245, lr=0.0001]
Steps:  17%|█▋        | 337/2000 [10:15<1:02:33,  2.26s/it, loss=0.087, lr=0.0001]
Steps:  17%|█▋        | 337/2000 [10:15<1:02:33,  2.26s/it, loss=0.22, lr=0.0001] 
Steps:  17%|█▋        | 338/2000 [10:16<58:04,  2.10s/it, loss=0.22, lr=0.0001]  
Steps:  17%|█▋        | 338/2000 [10:16<58:04,  2.10s/it, loss=0.155, lr=0.0001]
Steps:  17%|█▋        | 338/2000 [10:16<58:04,  2.10s/it, loss=0.157, lr=0.0001]
Steps:  17%|█▋        | 338/2000 [10:16<58:04,  2.10s/it, loss=0.323, lr=0.0001]
Steps:  17%|█▋        | 338/2000 [10:17<58:04,  2.10s/it, loss=0.229, lr=0.0001]
Steps:  17%|█▋        | 339/2000 [10:17<54:40,  1.97s/it, loss=0.229, lr=0.0001]
Steps:  17%|█▋        | 339/2000 [10:17<54:40,  1.97s/it, loss=0.188, lr=0.0001]
Steps:  17%|█▋        | 339/2000 [10:18<54:40,  1.97s/it, loss=0.0736, lr=0.0001]
Steps:  17%|█▋        | 339/2000 [10:18<54:40,  1.97s/it, loss=0.15, lr=0.0001]  
Steps:  17%|█▋        | 339/2000 [10:19<54:40,  1.97s/it, loss=0.184, lr=0.0001]
Steps:  17%|█▋        | 340/2000 [10:19<54:39,  1.98s/it, loss=0.184, lr=0.0001]
Steps:  17%|█▋        | 340/2000 [10:19<54:39,  1.98s/it, loss=0.356, lr=0.0001]
Steps:  17%|█▋        | 340/2000 [10:20<54:39,  1.98s/it, loss=0.608, lr=0.0001]
Steps:  17%|█▋        | 340/2000 [10:20<54:39,  1.98s/it, loss=0.195, lr=0.0001]
Steps:  17%|█▋        | 340/2000 [10:20<54:39,  1.98s/it, loss=0.209, lr=0.0001]
Steps:  17%|█▋        | 341/2000 [10:21<52:11,  1.89s/it, loss=0.209, lr=0.0001]
Steps:  17%|█▋        | 341/2000 [10:21<52:11,  1.89s/it, loss=0.11, lr=0.0001] 
Steps:  17%|█▋        | 341/2000 [10:21<52:11,  1.89s/it, loss=0.167, lr=0.0001]
Steps:  17%|█▋        | 341/2000 [10:22<52:11,  1.89s/it, loss=0.133, lr=0.0001]
Steps:  17%|█▋        | 341/2000 [10:22<52:11,  1.89s/it, loss=0.0848, lr=0.0001]
Steps:  17%|█▋        | 342/2000 [10:23<50:38,  1.83s/it, loss=0.0848, lr=0.0001]
Steps:  17%|█▋        | 342/2000 [10:23<50:38,  1.83s/it, loss=0.563, lr=0.0001] 
Steps:  17%|█▋        | 342/2000 [10:23<50:38,  1.83s/it, loss=0.349, lr=0.0001]
Steps:  17%|█▋        | 342/2000 [10:23<50:38,  1.83s/it, loss=0.227, lr=0.0001]
Steps:  17%|█▋        | 342/2000 [10:24<50:38,  1.83s/it, loss=0.0665, lr=0.0001]
Steps:  17%|█▋        | 343/2000 [10:24<50:58,  1.85s/it, loss=0.0665, lr=0.0001]
Steps:  17%|█▋        | 343/2000 [10:24<50:58,  1.85s/it, loss=0.162, lr=0.0001] 
Steps:  17%|█▋        | 343/2000 [10:25<50:58,  1.85s/it, loss=0.224, lr=0.0001]
Steps:  17%|█▋        | 343/2000 [10:25<50:58,  1.85s/it, loss=1.25, lr=0.0001] 
Steps:  17%|█▋        | 343/2000 [10:26<50:58,  1.85s/it, loss=0.182, lr=0.0001]
Steps:  17%|█▋        | 344/2000 [10:26<49:25,  1.79s/it, loss=0.182, lr=0.0001]
Steps:  17%|█▋        | 344/2000 [10:26<49:25,  1.79s/it, loss=0.281, lr=0.0001]
Steps:  17%|█▋        | 344/2000 [10:27<49:25,  1.79s/it, loss=0.149, lr=0.0001]
Steps:  17%|█▋        | 344/2000 [10:27<49:25,  1.79s/it, loss=0.209, lr=0.0001]
Steps:  17%|█▋        | 344/2000 [10:27<49:25,  1.79s/it, loss=0.348, lr=0.0001]
Steps:  17%|█▋        | 345/2000 [10:28<48:38,  1.76s/it, loss=0.348, lr=0.0001]
Steps:  17%|█▋        | 345/2000 [10:28<48:38,  1.76s/it, loss=0.192, lr=0.0001]
Steps:  17%|█▋        | 345/2000 [10:28<48:38,  1.76s/it, loss=0.613, lr=0.0001]
Steps:  17%|█▋        | 345/2000 [10:29<48:38,  1.76s/it, loss=0.262, lr=0.0001]
Steps:  17%|█▋        | 345/2000 [10:29<48:38,  1.76s/it, loss=0.259, lr=0.0001]
Steps:  17%|█▋        | 346/2000 [10:30<49:57,  1.81s/it, loss=0.259, lr=0.0001]
Steps:  17%|█▋        | 346/2000 [10:30<49:57,  1.81s/it, loss=0.287, lr=0.0001]
Steps:  17%|█▋        | 346/2000 [10:30<49:57,  1.81s/it, loss=0.152, lr=0.0001]
Steps:  17%|█▋        | 346/2000 [10:31<49:57,  1.81s/it, loss=0.146, lr=0.0001]
Steps:  17%|█▋        | 346/2000 [10:31<49:57,  1.81s/it, loss=0.175, lr=0.0001]
Steps:  17%|█▋        | 347/2000 [10:31<48:42,  1.77s/it, loss=0.175, lr=0.0001]
Steps:  17%|█▋        | 347/2000 [10:31<48:42,  1.77s/it, loss=0.136, lr=0.0001]
Steps:  17%|█▋        | 347/2000 [10:32<48:42,  1.77s/it, loss=0.358, lr=0.0001]
Steps:  17%|█▋        | 347/2000 [10:32<48:42,  1.77s/it, loss=0.196, lr=0.0001]
Steps:  17%|█▋        | 347/2000 [10:33<48:42,  1.77s/it, loss=0.0912, lr=0.0001]
Steps:  17%|█▋        | 348/2000 [10:33<48:07,  1.75s/it, loss=0.0912, lr=0.0001]
Steps:  17%|█▋        | 348/2000 [10:33<48:07,  1.75s/it, loss=0.234, lr=0.0001] 
Steps:  17%|█▋        | 348/2000 [10:34<48:07,  1.75s/it, loss=0.193, lr=0.0001]
Steps:  17%|█▋        | 348/2000 [10:34<48:07,  1.75s/it, loss=0.84, lr=0.0001] 
Steps:  17%|█▋        | 348/2000 [10:34<48:07,  1.75s/it, loss=0.173, lr=0.0001]
Steps:  17%|█▋        | 349/2000 [10:35<49:14,  1.79s/it, loss=0.173, lr=0.0001]
Steps:  17%|█▋        | 349/2000 [10:35<49:14,  1.79s/it, loss=0.184, lr=0.0001]
Steps:  17%|█▋        | 349/2000 [10:35<49:14,  1.79s/it, loss=0.224, lr=0.0001]
Steps:  17%|█▋        | 349/2000 [10:36<49:14,  1.79s/it, loss=0.197, lr=0.0001]
Steps:  17%|█▋        | 349/2000 [10:36<49:14,  1.79s/it, loss=0.426, lr=0.0001]
Steps:  18%|█▊        | 350/2000 [10:37<48:06,  1.75s/it, loss=0.426, lr=0.0001]
Steps:  18%|█▊        | 350/2000 [10:37<48:06,  1.75s/it, loss=0.276, lr=0.0001]
Steps:  18%|█▊        | 350/2000 [10:37<48:06,  1.75s/it, loss=0.321, lr=0.0001]
Steps:  18%|█▊        | 350/2000 [10:37<48:06,  1.75s/it, loss=0.205, lr=0.0001]
Steps:  18%|█▊        | 350/2000 [10:38<48:06,  1.75s/it, loss=0.0262, lr=0.0001]
Steps:  18%|█▊        | 351/2000 [10:38<47:15,  1.72s/it, loss=0.0262, lr=0.0001]
Steps:  18%|█▊        | 351/2000 [10:38<47:15,  1.72s/it, loss=0.164, lr=0.0001] 
Steps:  18%|█▊        | 351/2000 [10:39<47:15,  1.72s/it, loss=0.329, lr=0.0001]
Steps:  18%|█▊        | 351/2000 [10:39<47:15,  1.72s/it, loss=0.178, lr=0.0001]
Steps:  18%|█▊        | 351/2000 [10:40<47:15,  1.72s/it, loss=0.178, lr=0.0001]
Steps:  18%|█▊        | 352/2000 [10:40<46:41,  1.70s/it, loss=0.178, lr=0.0001]
Steps:  18%|█▊        | 352/2000 [10:40<46:41,  1.70s/it, loss=0.256, lr=0.0001]
Steps:  18%|█▊        | 352/2000 [10:41<46:41,  1.70s/it, loss=0.133, lr=0.0001]
Steps:  18%|█▊        | 352/2000 [10:41<46:41,  1.70s/it, loss=0.239, lr=0.0001]
Steps:  18%|█▊        | 352/2000 [10:41<46:41,  1.70s/it, loss=0.263, lr=0.0001]
Steps:  18%|█▊        | 353/2000 [10:42<48:08,  1.75s/it, loss=0.263, lr=0.0001]
Steps:  18%|█▊        | 353/2000 [10:42<48:08,  1.75s/it, loss=0.265, lr=0.0001]
Steps:  18%|█▊        | 353/2000 [10:42<48:08,  1.75s/it, loss=0.113, lr=0.0001]
Steps:  18%|█▊        | 353/2000 [10:43<48:08,  1.75s/it, loss=0.701, lr=0.0001]
Steps:  18%|█▊        | 353/2000 [10:43<48:08,  1.75s/it, loss=0.254, lr=0.0001]
Steps:  18%|█▊        | 354/2000 [10:43<47:23,  1.73s/it, loss=0.254, lr=0.0001]
Steps:  18%|█▊        | 354/2000 [10:43<47:23,  1.73s/it, loss=1.03, lr=0.0001] 
Steps:  18%|█▊        | 354/2000 [10:44<47:23,  1.73s/it, loss=0.215, lr=0.0001]
Steps:  18%|█▊        | 354/2000 [10:44<47:23,  1.73s/it, loss=0.224, lr=0.0001]
Steps:  18%|█▊        | 354/2000 [10:45<47:23,  1.73s/it, loss=0.0562, lr=0.0001]
Steps:  18%|█▊        | 355/2000 [10:45<46:46,  1.71s/it, loss=0.0562, lr=0.0001]
Steps:  18%|█▊        | 355/2000 [10:45<46:46,  1.71s/it, loss=0.196, lr=0.0001] 
Steps:  18%|█▊        | 355/2000 [10:46<46:46,  1.71s/it, loss=0.0785, lr=0.0001]
Steps:  18%|█▊        | 355/2000 [10:46<46:46,  1.71s/it, loss=0.584, lr=0.0001] 
Steps:  18%|█▊        | 355/2000 [10:47<46:46,  1.71s/it, loss=0.197, lr=0.0001]
Steps:  18%|█▊        | 356/2000 [10:47<48:12,  1.76s/it, loss=0.197, lr=0.0001]
Steps:  18%|█▊        | 356/2000 [10:47<48:12,  1.76s/it, loss=0.345, lr=0.0001]
Steps:  18%|█▊        | 356/2000 [10:47<48:12,  1.76s/it, loss=0.217, lr=0.0001]
Steps:  18%|█▊        | 356/2000 [10:48<48:12,  1.76s/it, loss=0.211, lr=0.0001]
Steps:  18%|█▊        | 356/2000 [10:48<48:12,  1.76s/it, loss=0.244, lr=0.0001]
Steps:  18%|█▊        | 357/2000 [10:49<47:18,  1.73s/it, loss=0.244, lr=0.0001]
Steps:  18%|█▊        | 357/2000 [10:49<47:18,  1.73s/it, loss=0.256, lr=0.0001]
Steps:  18%|█▊        | 357/2000 [10:49<47:18,  1.73s/it, loss=0.128, lr=0.0001]
Steps:  18%|█▊        | 357/2000 [10:50<47:18,  1.73s/it, loss=0.142, lr=0.0001]
Steps:  18%|█▊        | 357/2000 [10:50<47:18,  1.73s/it, loss=0.823, lr=0.0001]
Steps:  18%|█▊        | 358/2000 [10:50<46:49,  1.71s/it, loss=0.823, lr=0.0001]
Steps:  18%|█▊        | 358/2000 [10:50<46:49,  1.71s/it, loss=0.564, lr=0.0001]
Steps:  18%|█▊        | 358/2000 [10:51<46:49,  1.71s/it, loss=0.494, lr=0.0001]
Steps:  18%|█▊        | 358/2000 [10:51<46:49,  1.71s/it, loss=0.152, lr=0.0001]
Steps:  18%|█▊        | 358/2000 [10:52<46:49,  1.71s/it, loss=0.168, lr=0.0001]
Steps:  18%|█▊        | 359/2000 [10:52<48:07,  1.76s/it, loss=0.168, lr=0.0001]
Steps:  18%|█▊        | 359/2000 [10:52<48:07,  1.76s/it, loss=0.446, lr=0.0001]
Steps:  18%|█▊        | 359/2000 [10:53<48:07,  1.76s/it, loss=0.051, lr=0.0001]
Steps:  18%|█▊        | 359/2000 [10:53<48:07,  1.76s/it, loss=1.21, lr=0.0001] 
Steps:  18%|█▊        | 359/2000 [10:53<48:07,  1.76s/it, loss=0.174, lr=0.0001]
Steps:  18%|█▊        | 360/2000 [10:54<47:12,  1.73s/it, loss=0.174, lr=0.0001]
Steps:  18%|█▊        | 360/2000 [10:54<47:12,  1.73s/it, loss=0.0835, lr=0.0001]
Steps:  18%|█▊        | 360/2000 [10:54<47:12,  1.73s/it, loss=0.739, lr=0.0001] 
Steps:  18%|█▊        | 360/2000 [10:55<47:12,  1.73s/it, loss=0.482, lr=0.0001]
Steps:  18%|█▊        | 360/2000 [10:55<47:12,  1.73s/it, loss=0.18, lr=0.0001] 
Steps:  18%|█▊        | 361/2000 [10:56<46:51,  1.72s/it, loss=0.18, lr=0.0001]
Steps:  18%|█▊        | 361/2000 [10:56<46:51,  1.72s/it, loss=0.237, lr=0.0001]
Steps:  18%|█▊        | 361/2000 [10:56<46:51,  1.72s/it, loss=0.183, lr=0.0001]
Steps:  18%|█▊        | 361/2000 [10:57<46:51,  1.72s/it, loss=0.185, lr=0.0001]
Steps:  18%|█▊        | 361/2000 [10:57<46:51,  1.72s/it, loss=0.165, lr=0.0001]
Steps:  18%|█▊        | 362/2000 [10:57<48:11,  1.77s/it, loss=0.165, lr=0.0001]
Steps:  18%|█▊        | 362/2000 [10:57<48:11,  1.77s/it, loss=0.19, lr=0.0001] 
Steps:  18%|█▊        | 362/2000 [10:58<48:11,  1.77s/it, loss=0.482, lr=0.0001]
Steps:  18%|█▊        | 362/2000 [10:58<48:11,  1.77s/it, loss=0.162, lr=0.0001]
Steps:  18%|█▊        | 362/2000 [10:59<48:11,  1.77s/it, loss=0.159, lr=0.0001]
Steps:  18%|█▊        | 363/2000 [10:59<47:32,  1.74s/it, loss=0.159, lr=0.0001]
Steps:  18%|█▊        | 363/2000 [10:59<47:32,  1.74s/it, loss=0.183, lr=0.0001]
Steps:  18%|█▊        | 363/2000 [11:00<47:32,  1.74s/it, loss=0.231, lr=0.0001]
Steps:  18%|█▊        | 363/2000 [11:00<47:32,  1.74s/it, loss=0.164, lr=0.0001]
Steps:  18%|█▊        | 363/2000 [11:00<47:32,  1.74s/it, loss=0.118, lr=0.0001]
Steps:  18%|█▊        | 364/2000 [11:01<46:39,  1.71s/it, loss=0.118, lr=0.0001]
Steps:  18%|█▊        | 364/2000 [11:01<46:39,  1.71s/it, loss=0.167, lr=0.0001]
Steps:  18%|█▊        | 364/2000 [11:01<46:39,  1.71s/it, loss=0.175, lr=0.0001]
Steps:  18%|█▊        | 364/2000 [11:02<46:39,  1.71s/it, loss=0.131, lr=0.0001]
Steps:  18%|█▊        | 364/2000 [11:02<46:39,  1.71s/it, loss=0.319, lr=0.0001]
Steps:  18%|█▊        | 365/2000 [11:03<48:19,  1.77s/it, loss=0.319, lr=0.0001]
Steps:  18%|█▊        | 365/2000 [11:03<48:19,  1.77s/it, loss=0.171, lr=0.0001]
Steps:  18%|█▊        | 365/2000 [11:03<48:19,  1.77s/it, loss=0.123, lr=0.0001]
Steps:  18%|█▊        | 365/2000 [11:04<48:19,  1.77s/it, loss=0.0838, lr=0.0001]
Steps:  18%|█▊        | 365/2000 [11:04<48:19,  1.77s/it, loss=0.19, lr=0.0001]  
Steps:  18%|█▊        | 366/2000 [11:04<47:30,  1.74s/it, loss=0.19, lr=0.0001]
Steps:  18%|█▊        | 366/2000 [11:04<47:30,  1.74s/it, loss=0.12, lr=0.0001]
Steps:  18%|█▊        | 366/2000 [11:05<47:30,  1.74s/it, loss=0.17, lr=0.0001]
Steps:  18%|█▊        | 366/2000 [11:05<47:30,  1.74s/it, loss=0.137, lr=0.0001]
Steps:  18%|█▊        | 366/2000 [11:06<47:30,  1.74s/it, loss=0.348, lr=0.0001]
Steps:  18%|█▊        | 367/2000 [11:06<46:54,  1.72s/it, loss=0.348, lr=0.0001]
Steps:  18%|█▊        | 367/2000 [11:06<46:54,  1.72s/it, loss=0.115, lr=0.0001]
Steps:  18%|█▊        | 367/2000 [11:06<46:54,  1.72s/it, loss=0.225, lr=0.0001]
Steps:  18%|█▊        | 367/2000 [11:07<46:54,  1.72s/it, loss=0.16, lr=0.0001] 
Steps:  18%|█▊        | 367/2000 [11:07<46:54,  1.72s/it, loss=0.194, lr=0.0001]
Steps:  18%|█▊        | 368/2000 [11:08<48:16,  1.77s/it, loss=0.194, lr=0.0001]
Steps:  18%|█▊        | 368/2000 [11:08<48:16,  1.77s/it, loss=0.0762, lr=0.0001]
Steps:  18%|█▊        | 368/2000 [11:08<48:16,  1.77s/it, loss=0.146, lr=0.0001] 
Steps:  18%|█▊        | 368/2000 [11:09<48:16,  1.77s/it, loss=0.0743, lr=0.0001]
Steps:  18%|█▊        | 368/2000 [11:09<48:16,  1.77s/it, loss=0.182, lr=0.0001] 
Steps:  18%|█▊        | 369/2000 [11:10<47:28,  1.75s/it, loss=0.182, lr=0.0001]
Steps:  18%|█▊        | 369/2000 [11:10<47:28,  1.75s/it, loss=0.253, lr=0.0001]
Steps:  18%|█▊        | 369/2000 [11:10<47:28,  1.75s/it, loss=0.156, lr=0.0001]
Steps:  18%|█▊        | 369/2000 [11:10<47:28,  1.75s/it, loss=0.195, lr=0.0001]
Steps:  18%|█▊        | 369/2000 [11:11<47:28,  1.75s/it, loss=0.151, lr=0.0001]
Steps:  18%|█▊        | 370/2000 [11:11<46:30,  1.71s/it, loss=0.151, lr=0.0001]
Steps:  18%|█▊        | 370/2000 [11:11<46:30,  1.71s/it, loss=0.319, lr=0.0001]
Steps:  18%|█▊        | 370/2000 [11:12<46:30,  1.71s/it, loss=0.144, lr=0.0001]
Steps:  18%|█▊        | 370/2000 [11:12<46:30,  1.71s/it, loss=0.279, lr=0.0001]
Steps:  18%|█▊        | 370/2000 [11:12<46:30,  1.71s/it, loss=0.343, lr=0.0001]
Steps:  19%|█▊        | 371/2000 [11:13<46:04,  1.70s/it, loss=0.343, lr=0.0001]
Steps:  19%|█▊        | 371/2000 [11:13<46:04,  1.70s/it, loss=0.134, lr=0.0001]
Steps:  19%|█▊        | 371/2000 [11:14<46:04,  1.70s/it, loss=0.103, lr=0.0001]
Steps:  19%|█▊        | 371/2000 [11:14<46:04,  1.70s/it, loss=0.141, lr=0.0001]
Steps:  19%|█▊        | 371/2000 [11:14<46:04,  1.70s/it, loss=0.216, lr=0.0001]
Steps:  19%|█▊        | 372/2000 [11:15<47:45,  1.76s/it, loss=0.216, lr=0.0001]
Steps:  19%|█▊        | 372/2000 [11:15<47:45,  1.76s/it, loss=0.148, lr=0.0001]
Steps:  19%|█▊        | 372/2000 [11:16<47:45,  1.76s/it, loss=0.196, lr=0.0001]
Steps:  19%|█▊        | 372/2000 [11:17<47:45,  1.76s/it, loss=0.147, lr=0.0001]
Steps:  19%|█▊        | 372/2000 [11:17<47:45,  1.76s/it, loss=0.162, lr=0.0001]
Steps:  19%|█▊        | 373/2000 [11:18<56:15,  2.07s/it, loss=0.162, lr=0.0001]
Steps:  19%|█▊        | 373/2000 [11:18<56:15,  2.07s/it, loss=0.118, lr=0.0001]
Steps:  19%|█▊        | 373/2000 [11:18<56:15,  2.07s/it, loss=0.183, lr=0.0001]
Steps:  19%|█▊        | 373/2000 [11:18<56:15,  2.07s/it, loss=1.04, lr=0.0001] 
Steps:  19%|█▊        | 373/2000 [11:19<56:15,  2.07s/it, loss=0.241, lr=0.0001]
Steps:  19%|█▊        | 374/2000 [11:19<52:37,  1.94s/it, loss=0.241, lr=0.0001]
Steps:  19%|█▊        | 374/2000 [11:19<52:37,  1.94s/it, loss=0.286, lr=0.0001]
Steps:  19%|█▊        | 374/2000 [11:20<52:37,  1.94s/it, loss=0.139, lr=0.0001]
Steps:  19%|█▊        | 374/2000 [11:20<52:37,  1.94s/it, loss=0.21, lr=0.0001] 
Steps:  19%|█▊        | 374/2000 [11:21<52:37,  1.94s/it, loss=0.183, lr=0.0001]
Steps:  19%|█▉        | 375/2000 [11:21<52:06,  1.92s/it, loss=0.183, lr=0.0001]
Steps:  19%|█▉        | 375/2000 [11:21<52:06,  1.92s/it, loss=0.0836, lr=0.0001]
Steps:  19%|█▉        | 375/2000 [11:22<52:06,  1.92s/it, loss=0.174, lr=0.0001] 
Steps:  19%|█▉        | 375/2000 [11:22<52:06,  1.92s/it, loss=0.282, lr=0.0001]
Steps:  19%|█▉        | 375/2000 [11:22<52:06,  1.92s/it, loss=0.19, lr=0.0001] 
Steps:  19%|█▉        | 376/2000 [11:23<50:04,  1.85s/it, loss=0.19, lr=0.0001]
Steps:  19%|█▉        | 376/2000 [11:23<50:04,  1.85s/it, loss=0.192, lr=0.0001]
Steps:  19%|█▉        | 376/2000 [11:23<50:04,  1.85s/it, loss=0.106, lr=0.0001]
Steps:  19%|█▉        | 376/2000 [11:24<50:04,  1.85s/it, loss=0.29, lr=0.0001] 
Steps:  19%|█▉        | 376/2000 [11:24<50:04,  1.85s/it, loss=0.527, lr=0.0001]
Steps:  19%|█▉        | 377/2000 [11:25<48:54,  1.81s/it, loss=0.527, lr=0.0001]
Steps:  19%|█▉        | 377/2000 [11:25<48:54,  1.81s/it, loss=0.283, lr=0.0001]
Steps:  19%|█▉        | 377/2000 [11:25<48:54,  1.81s/it, loss=0.17, lr=0.0001] 
Steps:  19%|█▉        | 377/2000 [11:26<48:54,  1.81s/it, loss=0.257, lr=0.0001]
Steps:  19%|█▉        | 377/2000 [11:26<48:54,  1.81s/it, loss=0.249, lr=0.0001]
Steps:  19%|█▉        | 378/2000 [11:26<49:54,  1.85s/it, loss=0.249, lr=0.0001]
Steps:  19%|█▉        | 378/2000 [11:26<49:54,  1.85s/it, loss=0.136, lr=0.0001]
Steps:  19%|█▉        | 378/2000 [11:27<49:54,  1.85s/it, loss=0.0879, lr=0.0001]
Steps:  19%|█▉        | 378/2000 [11:27<49:54,  1.85s/it, loss=0.131, lr=0.0001] 
Steps:  19%|█▉        | 378/2000 [11:28<49:54,  1.85s/it, loss=0.235, lr=0.0001]
Steps:  19%|█▉        | 379/2000 [11:28<48:50,  1.81s/it, loss=0.235, lr=0.0001]
Steps:  19%|█▉        | 379/2000 [11:28<48:50,  1.81s/it, loss=0.256, lr=0.0001]
Steps:  19%|█▉        | 379/2000 [11:29<48:50,  1.81s/it, loss=0.0763, lr=0.0001]
Steps:  19%|█▉        | 379/2000 [11:29<48:50,  1.81s/it, loss=0.165, lr=0.0001] 
Steps:  19%|█▉        | 379/2000 [11:29<48:50,  1.81s/it, loss=0.178, lr=0.0001]
Steps:  19%|█▉        | 380/2000 [11:30<47:21,  1.75s/it, loss=0.178, lr=0.0001]
Steps:  19%|█▉        | 380/2000 [11:30<47:21,  1.75s/it, loss=0.564, lr=0.0001]
Steps:  19%|█▉        | 380/2000 [11:30<47:21,  1.75s/it, loss=0.12, lr=0.0001] 
Steps:  19%|█▉        | 380/2000 [11:31<47:21,  1.75s/it, loss=0.115, lr=0.0001]
Steps:  19%|█▉        | 380/2000 [11:31<47:21,  1.75s/it, loss=0.66, lr=0.0001] 
Steps:  19%|█▉        | 381/2000 [11:32<48:24,  1.79s/it, loss=0.66, lr=0.0001]
Steps:  19%|█▉        | 381/2000 [11:32<48:24,  1.79s/it, loss=0.101, lr=0.0001]
Steps:  19%|█▉        | 381/2000 [11:32<48:24,  1.79s/it, loss=0.185, lr=0.0001]
Steps:  19%|█▉        | 381/2000 [11:33<48:24,  1.79s/it, loss=0.32, lr=0.0001] 
Steps:  19%|█▉        | 381/2000 [11:33<48:24,  1.79s/it, loss=0.143, lr=0.0001]
Steps:  19%|█▉        | 382/2000 [11:33<47:26,  1.76s/it, loss=0.143, lr=0.0001]
Steps:  19%|█▉        | 382/2000 [11:33<47:26,  1.76s/it, loss=0.143, lr=0.0001]
Steps:  19%|█▉        | 382/2000 [11:34<47:26,  1.76s/it, loss=0.264, lr=0.0001]
Steps:  19%|█▉        | 382/2000 [11:34<47:26,  1.76s/it, loss=0.218, lr=0.0001]
Steps:  19%|█▉        | 382/2000 [11:35<47:26,  1.76s/it, loss=0.0767, lr=0.0001]
Steps:  19%|█▉        | 383/2000 [11:35<46:25,  1.72s/it, loss=0.0767, lr=0.0001]
Steps:  19%|█▉        | 383/2000 [11:35<46:25,  1.72s/it, loss=0.139, lr=0.0001] 
Steps:  19%|█▉        | 383/2000 [11:35<46:25,  1.72s/it, loss=0.187, lr=0.0001]
Steps:  19%|█▉        | 383/2000 [11:36<46:25,  1.72s/it, loss=0.577, lr=0.0001]
Steps:  19%|█▉        | 383/2000 [11:36<46:25,  1.72s/it, loss=0.125, lr=0.0001]
Steps:  19%|█▉        | 384/2000 [11:37<47:35,  1.77s/it, loss=0.125, lr=0.0001]
Steps:  19%|█▉        | 384/2000 [11:37<47:35,  1.77s/it, loss=0.0727, lr=0.0001]
Steps:  19%|█▉        | 384/2000 [11:37<47:35,  1.77s/it, loss=0.184, lr=0.0001] 
Steps:  19%|█▉        | 384/2000 [11:38<47:35,  1.77s/it, loss=0.0469, lr=0.0001]
Steps:  19%|█▉        | 384/2000 [11:38<47:35,  1.77s/it, loss=0.188, lr=0.0001] 
Steps:  19%|█▉        | 385/2000 [11:39<46:30,  1.73s/it, loss=0.188, lr=0.0001]
Steps:  19%|█▉        | 385/2000 [11:39<46:30,  1.73s/it, loss=0.212, lr=0.0001]
Steps:  19%|█▉        | 385/2000 [11:39<46:30,  1.73s/it, loss=0.178, lr=0.0001]
Steps:  19%|█▉        | 385/2000 [11:39<46:30,  1.73s/it, loss=0.158, lr=0.0001]
Steps:  19%|█▉        | 385/2000 [11:40<46:30,  1.73s/it, loss=0.127, lr=0.0001]
Steps:  19%|█▉        | 386/2000 [11:40<45:47,  1.70s/it, loss=0.127, lr=0.0001]
Steps:  19%|█▉        | 386/2000 [11:40<45:47,  1.70s/it, loss=0.108, lr=0.0001]
Steps:  19%|█▉        | 386/2000 [11:41<45:47,  1.70s/it, loss=0.214, lr=0.0001]
Steps:  19%|█▉        | 386/2000 [11:41<45:47,  1.70s/it, loss=0.138, lr=0.0001]
Steps:  19%|█▉        | 386/2000 [11:42<45:47,  1.70s/it, loss=0.133, lr=0.0001]
Steps:  19%|█▉        | 387/2000 [11:42<47:11,  1.76s/it, loss=0.133, lr=0.0001]
Steps:  19%|█▉        | 387/2000 [11:42<47:11,  1.76s/it, loss=0.43, lr=0.0001] 
Steps:  19%|█▉        | 387/2000 [11:42<47:11,  1.76s/it, loss=0.204, lr=0.0001]
Steps:  19%|█▉        | 387/2000 [11:43<47:11,  1.76s/it, loss=0.0985, lr=0.0001]
Steps:  19%|█▉        | 387/2000 [11:43<47:11,  1.76s/it, loss=0.295, lr=0.0001] 
Steps:  19%|█▉        | 388/2000 [11:44<46:07,  1.72s/it, loss=0.295, lr=0.0001]
Steps:  19%|█▉        | 388/2000 [11:44<46:07,  1.72s/it, loss=0.203, lr=0.0001]
Steps:  19%|█▉        | 388/2000 [11:44<46:07,  1.72s/it, loss=0.19, lr=0.0001] 
Steps:  19%|█▉        | 388/2000 [11:44<46:07,  1.72s/it, loss=0.289, lr=0.0001]
Steps:  19%|█▉        | 388/2000 [11:45<46:07,  1.72s/it, loss=0.782, lr=0.0001]
Steps:  19%|█▉        | 389/2000 [11:45<45:38,  1.70s/it, loss=0.782, lr=0.0001]
Steps:  19%|█▉        | 389/2000 [11:45<45:38,  1.70s/it, loss=0.223, lr=0.0001]
Steps:  19%|█▉        | 389/2000 [11:46<45:38,  1.70s/it, loss=0.3, lr=0.0001]  
Steps:  19%|█▉        | 389/2000 [11:46<45:38,  1.70s/it, loss=0.161, lr=0.0001]
Steps:  19%|█▉        | 389/2000 [11:47<45:38,  1.70s/it, loss=0.216, lr=0.0001]
Steps:  20%|█▉        | 390/2000 [11:47<46:59,  1.75s/it, loss=0.216, lr=0.0001]
Steps:  20%|█▉        | 390/2000 [11:47<46:59,  1.75s/it, loss=0.152, lr=0.0001]
Steps:  20%|█▉        | 390/2000 [11:48<46:59,  1.75s/it, loss=0.247, lr=0.0001]
Steps:  20%|█▉        | 390/2000 [11:48<46:59,  1.75s/it, loss=0.354, lr=0.0001]
Steps:  20%|█▉        | 390/2000 [11:48<46:59,  1.75s/it, loss=0.299, lr=0.0001]
Steps:  20%|█▉        | 391/2000 [11:49<46:08,  1.72s/it, loss=0.299, lr=0.0001]
Steps:  20%|█▉        | 391/2000 [11:49<46:08,  1.72s/it, loss=0.344, lr=0.0001]
Steps:  20%|█▉        | 391/2000 [11:49<46:08,  1.72s/it, loss=0.131, lr=0.0001]
Steps:  20%|█▉        | 391/2000 [11:50<46:08,  1.72s/it, loss=0.172, lr=0.0001]
Steps:  20%|█▉        | 391/2000 [11:50<46:08,  1.72s/it, loss=0.0997, lr=0.0001]
Steps:  20%|█▉        | 392/2000 [11:50<45:23,  1.69s/it, loss=0.0997, lr=0.0001]
Steps:  20%|█▉        | 392/2000 [11:50<45:23,  1.69s/it, loss=0.0883, lr=0.0001]
Steps:  20%|█▉        | 392/2000 [11:51<45:23,  1.69s/it, loss=0.243, lr=0.0001] 
Steps:  20%|█▉        | 392/2000 [11:51<45:23,  1.69s/it, loss=0.189, lr=0.0001]
Steps:  20%|█▉        | 392/2000 [11:52<45:23,  1.69s/it, loss=0.112, lr=0.0001]
Steps:  20%|█▉        | 393/2000 [11:52<45:05,  1.68s/it, loss=0.112, lr=0.0001]
Steps:  20%|█▉        | 393/2000 [11:52<45:05,  1.68s/it, loss=0.166, lr=0.0001]
Steps:  20%|█▉        | 393/2000 [11:53<45:05,  1.68s/it, loss=0.191, lr=0.0001]
Steps:  20%|█▉        | 393/2000 [11:53<45:05,  1.68s/it, loss=0.16, lr=0.0001] 
Steps:  20%|█▉        | 393/2000 [11:54<45:05,  1.68s/it, loss=0.273, lr=0.0001]
Steps:  20%|█▉        | 394/2000 [11:54<46:29,  1.74s/it, loss=0.273, lr=0.0001]
Steps:  20%|█▉        | 394/2000 [11:54<46:29,  1.74s/it, loss=0.197, lr=0.0001]
Steps:  20%|█▉        | 394/2000 [11:54<46:29,  1.74s/it, loss=0.14, lr=0.0001] 
Steps:  20%|█▉        | 394/2000 [11:55<46:29,  1.74s/it, loss=0.169, lr=0.0001]
Steps:  20%|█▉        | 394/2000 [11:55<46:29,  1.74s/it, loss=0.101, lr=0.0001]
Steps:  20%|█▉        | 395/2000 [11:56<45:47,  1.71s/it, loss=0.101, lr=0.0001]
Steps:  20%|█▉        | 395/2000 [11:56<45:47,  1.71s/it, loss=0.2, lr=0.0001]  
Steps:  20%|█▉        | 395/2000 [11:56<45:47,  1.71s/it, loss=0.146, lr=0.0001]
Steps:  20%|█▉        | 395/2000 [11:56<45:47,  1.71s/it, loss=0.165, lr=0.0001]
Steps:  20%|█▉        | 395/2000 [11:57<45:47,  1.71s/it, loss=0.166, lr=0.0001]
Steps:  20%|█▉        | 396/2000 [11:57<45:15,  1.69s/it, loss=0.166, lr=0.0001]
Steps:  20%|█▉        | 396/2000 [11:57<45:15,  1.69s/it, loss=0.32, lr=0.0001] 
Steps:  20%|█▉        | 396/2000 [11:58<45:15,  1.69s/it, loss=0.22, lr=0.0001]
Steps:  20%|█▉        | 396/2000 [11:58<45:15,  1.69s/it, loss=0.199, lr=0.0001]
Steps:  20%|█▉        | 396/2000 [11:59<45:15,  1.69s/it, loss=0.147, lr=0.0001]
Steps:  20%|█▉        | 397/2000 [11:59<46:55,  1.76s/it, loss=0.147, lr=0.0001]
Steps:  20%|█▉        | 397/2000 [11:59<46:55,  1.76s/it, loss=0.156, lr=0.0001]
Steps:  20%|█▉        | 397/2000 [12:00<46:55,  1.76s/it, loss=0.144, lr=0.0001]
Steps:  20%|█▉        | 397/2000 [12:00<46:55,  1.76s/it, loss=0.146, lr=0.0001]
Steps:  20%|█▉        | 397/2000 [12:00<46:55,  1.76s/it, loss=0.203, lr=0.0001]
Steps:  20%|█▉        | 398/2000 [12:01<46:32,  1.74s/it, loss=0.203, lr=0.0001]
Steps:  20%|█▉        | 398/2000 [12:01<46:32,  1.74s/it, loss=0.166, lr=0.0001]
Steps:  20%|█▉        | 398/2000 [12:01<46:32,  1.74s/it, loss=0.088, lr=0.0001]
Steps:  20%|█▉        | 398/2000 [12:02<46:32,  1.74s/it, loss=0.207, lr=0.0001]
Steps:  20%|█▉        | 398/2000 [12:02<46:32,  1.74s/it, loss=0.142, lr=0.0001]
Steps:  20%|█▉        | 399/2000 [12:03<46:15,  1.73s/it, loss=0.142, lr=0.0001]
Steps:  20%|█▉        | 399/2000 [12:03<46:15,  1.73s/it, loss=0.0706, lr=0.0001]
Steps:  20%|█▉        | 399/2000 [12:03<46:15,  1.73s/it, loss=0.241, lr=0.0001] 
Steps:  20%|█▉        | 399/2000 [12:04<46:15,  1.73s/it, loss=0.424, lr=0.0001]
Steps:  20%|█▉        | 399/2000 [12:04<46:15,  1.73s/it, loss=0.243, lr=0.0001]
Steps:  20%|██        | 400/2000 [12:05<47:39,  1.79s/it, loss=0.243, lr=0.0001]
Steps:  20%|██        | 400/2000 [12:05<47:39,  1.79s/it, loss=0.119, lr=0.0001]
Steps:  20%|██        | 400/2000 [12:05<47:39,  1.79s/it, loss=0.319, lr=0.0001]
Steps:  20%|██        | 400/2000 [12:05<47:39,  1.79s/it, loss=0.455, lr=0.0001]
Steps:  20%|██        | 400/2000 [12:06<47:39,  1.79s/it, loss=0.206, lr=0.0001]
Steps:  20%|██        | 401/2000 [12:06<46:40,  1.75s/it, loss=0.206, lr=0.0001]
Steps:  20%|██        | 401/2000 [12:06<46:40,  1.75s/it, loss=0.147, lr=0.0001]
Steps:  20%|██        | 401/2000 [12:07<46:40,  1.75s/it, loss=0.148, lr=0.0001]
Steps:  20%|██        | 401/2000 [12:07<46:40,  1.75s/it, loss=0.498, lr=0.0001]
Steps:  20%|██        | 401/2000 [12:07<46:40,  1.75s/it, loss=0.16, lr=0.0001] 
Steps:  20%|██        | 402/2000 [12:08<45:58,  1.73s/it, loss=0.16, lr=0.0001]
Steps:  20%|██        | 402/2000 [12:08<45:58,  1.73s/it, loss=1.39, lr=0.0001]
Steps:  20%|██        | 402/2000 [12:08<45:58,  1.73s/it, loss=0.175, lr=0.0001]
Steps:  20%|██        | 402/2000 [12:09<45:58,  1.73s/it, loss=0.181, lr=0.0001]
Steps:  20%|██        | 402/2000 [12:09<45:58,  1.73s/it, loss=0.306, lr=0.0001]
Steps:  20%|██        | 403/2000 [12:10<47:29,  1.78s/it, loss=0.306, lr=0.0001]
Steps:  20%|██        | 403/2000 [12:10<47:29,  1.78s/it, loss=0.198, lr=0.0001]
Steps:  20%|██        | 403/2000 [12:10<47:29,  1.78s/it, loss=0.145, lr=0.0001]
Steps:  20%|██        | 403/2000 [12:11<47:29,  1.78s/it, loss=0.364, lr=0.0001]
Steps:  20%|██        | 403/2000 [12:11<47:29,  1.78s/it, loss=0.167, lr=0.0001]
Steps:  20%|██        | 404/2000 [12:11<46:17,  1.74s/it, loss=0.167, lr=0.0001]
Steps:  20%|██        | 404/2000 [12:11<46:17,  1.74s/it, loss=0.392, lr=0.0001]
Steps:  20%|██        | 404/2000 [12:12<46:17,  1.74s/it, loss=0.178, lr=0.0001]
Steps:  20%|██        | 404/2000 [12:12<46:17,  1.74s/it, loss=1.17, lr=0.0001] 
Steps:  20%|██        | 404/2000 [12:13<46:17,  1.74s/it, loss=0.195, lr=0.0001]
Steps:  20%|██        | 405/2000 [12:13<45:37,  1.72s/it, loss=0.195, lr=0.0001]
Steps:  20%|██        | 405/2000 [12:13<45:37,  1.72s/it, loss=0.255, lr=0.0001]
Steps:  20%|██        | 405/2000 [12:14<45:37,  1.72s/it, loss=0.192, lr=0.0001]
Steps:  20%|██        | 405/2000 [12:14<45:37,  1.72s/it, loss=0.109, lr=0.0001]
Steps:  20%|██        | 405/2000 [12:15<45:37,  1.72s/it, loss=0.178, lr=0.0001]
Steps:  20%|██        | 406/2000 [12:15<48:31,  1.83s/it, loss=0.178, lr=0.0001]
Steps:  20%|██        | 406/2000 [12:15<48:31,  1.83s/it, loss=0.163, lr=0.0001]
Steps:  20%|██        | 406/2000 [12:16<48:31,  1.83s/it, loss=0.186, lr=0.0001]
Steps:  20%|██        | 406/2000 [12:16<48:31,  1.83s/it, loss=0.116, lr=0.0001]
Steps:  20%|██        | 406/2000 [12:16<48:31,  1.83s/it, loss=0.186, lr=0.0001]
Steps:  20%|██        | 407/2000 [12:17<47:12,  1.78s/it, loss=0.186, lr=0.0001]
Steps:  20%|██        | 407/2000 [12:17<47:12,  1.78s/it, loss=0.194, lr=0.0001]
Steps:  20%|██        | 407/2000 [12:17<47:12,  1.78s/it, loss=0.161, lr=0.0001]
Steps:  20%|██        | 407/2000 [12:18<47:12,  1.78s/it, loss=0.0889, lr=0.0001]
Steps:  20%|██        | 407/2000 [12:18<47:12,  1.78s/it, loss=0.0617, lr=0.0001]
Steps:  20%|██        | 408/2000 [12:19<46:21,  1.75s/it, loss=0.0617, lr=0.0001]
Steps:  20%|██        | 408/2000 [12:19<46:21,  1.75s/it, loss=0.131, lr=0.0001] 
Steps:  20%|██        | 408/2000 [12:19<46:21,  1.75s/it, loss=0.156, lr=0.0001]
Steps:  20%|██        | 408/2000 [12:19<46:21,  1.75s/it, loss=0.101, lr=0.0001]
Steps:  20%|██        | 408/2000 [12:20<46:21,  1.75s/it, loss=0.102, lr=0.0001]
Steps:  20%|██        | 409/2000 [12:20<47:24,  1.79s/it, loss=0.102, lr=0.0001]
Steps:  20%|██        | 409/2000 [12:20<47:24,  1.79s/it, loss=0.113, lr=0.0001]
Steps:  20%|██        | 409/2000 [12:21<47:24,  1.79s/it, loss=0.967, lr=0.0001]
Steps:  20%|██        | 409/2000 [12:21<47:24,  1.79s/it, loss=0.192, lr=0.0001]
Steps:  20%|██        | 409/2000 [12:22<47:24,  1.79s/it, loss=0.177, lr=0.0001]
Steps:  20%|██        | 410/2000 [12:22<47:29,  1.79s/it, loss=0.177, lr=0.0001]
Steps:  20%|██        | 410/2000 [12:22<47:29,  1.79s/it, loss=0.15, lr=0.0001] 
Steps:  20%|██        | 410/2000 [12:23<47:29,  1.79s/it, loss=0.183, lr=0.0001]
Steps:  20%|██        | 410/2000 [12:23<47:29,  1.79s/it, loss=0.807, lr=0.0001]
Steps:  20%|██        | 410/2000 [12:23<47:29,  1.79s/it, loss=0.233, lr=0.0001]
Steps:  21%|██        | 411/2000 [12:24<47:25,  1.79s/it, loss=0.233, lr=0.0001]
Steps:  21%|██        | 411/2000 [12:24<47:25,  1.79s/it, loss=0.162, lr=0.0001]
Steps:  21%|██        | 411/2000 [12:24<47:25,  1.79s/it, loss=0.168, lr=0.0001]
Steps:  21%|██        | 411/2000 [12:25<47:25,  1.79s/it, loss=0.198, lr=0.0001]
Steps:  21%|██        | 411/2000 [12:25<47:25,  1.79s/it, loss=0.226, lr=0.0001]
Steps:  21%|██        | 412/2000 [12:26<49:41,  1.88s/it, loss=0.226, lr=0.0001]
Steps:  21%|██        | 412/2000 [12:26<49:41,  1.88s/it, loss=0.385, lr=0.0001]
Steps:  21%|██        | 412/2000 [12:26<49:41,  1.88s/it, loss=0.184, lr=0.0001]
Steps:  21%|██        | 412/2000 [12:27<49:41,  1.88s/it, loss=0.188, lr=0.0001]
Steps:  21%|██        | 412/2000 [12:27<49:41,  1.88s/it, loss=1.05, lr=0.0001] 
Steps:  21%|██        | 413/2000 [12:28<48:17,  1.83s/it, loss=1.05, lr=0.0001]
Steps:  21%|██        | 413/2000 [12:28<48:17,  1.83s/it, loss=0.117, lr=0.0001]
Steps:  21%|██        | 413/2000 [12:28<48:17,  1.83s/it, loss=0.294, lr=0.0001]
Steps:  21%|██        | 413/2000 [12:29<48:17,  1.83s/it, loss=0.128, lr=0.0001]
Steps:  21%|██        | 413/2000 [12:29<48:17,  1.83s/it, loss=0.0469, lr=0.0001]
Steps:  21%|██        | 414/2000 [12:30<47:30,  1.80s/it, loss=0.0469, lr=0.0001]
Steps:  21%|██        | 414/2000 [12:30<47:30,  1.80s/it, loss=0.111, lr=0.0001] 
Steps:  21%|██        | 414/2000 [12:30<47:30,  1.80s/it, loss=0.212, lr=0.0001]
Steps:  21%|██        | 414/2000 [12:30<47:30,  1.80s/it, loss=0.233, lr=0.0001]
Steps:  21%|██        | 414/2000 [12:31<47:30,  1.80s/it, loss=0.465, lr=0.0001]
Steps:  21%|██        | 415/2000 [12:31<46:18,  1.75s/it, loss=0.465, lr=0.0001]
Steps:  21%|██        | 415/2000 [12:31<46:18,  1.75s/it, loss=0.279, lr=0.0001]
Steps:  21%|██        | 415/2000 [12:32<46:18,  1.75s/it, loss=0.148, lr=0.0001]
Steps:  21%|██        | 415/2000 [12:32<46:18,  1.75s/it, loss=0.183, lr=0.0001]
Steps:  21%|██        | 415/2000 [12:33<46:18,  1.75s/it, loss=0.159, lr=0.0001]
Steps:  21%|██        | 416/2000 [12:33<47:46,  1.81s/it, loss=0.159, lr=0.0001]
Steps:  21%|██        | 416/2000 [12:33<47:46,  1.81s/it, loss=0.19, lr=0.0001] 
Steps:  21%|██        | 416/2000 [12:34<47:46,  1.81s/it, loss=0.642, lr=0.0001]
Steps:  21%|██        | 416/2000 [12:34<47:46,  1.81s/it, loss=0.189, lr=0.0001]
Steps:  21%|██        | 416/2000 [12:34<47:46,  1.81s/it, loss=0.314, lr=0.0001]
Steps:  21%|██        | 417/2000 [12:35<46:37,  1.77s/it, loss=0.314, lr=0.0001]
Steps:  21%|██        | 417/2000 [12:35<46:37,  1.77s/it, loss=0.503, lr=0.0001]
Steps:  21%|██        | 417/2000 [12:35<46:37,  1.77s/it, loss=0.249, lr=0.0001]
Steps:  21%|██        | 417/2000 [12:36<46:37,  1.77s/it, loss=0.223, lr=0.0001]
Steps:  21%|██        | 417/2000 [12:36<46:37,  1.77s/it, loss=0.212, lr=0.0001]
Steps:  21%|██        | 418/2000 [12:36<45:47,  1.74s/it, loss=0.212, lr=0.0001]
Steps:  21%|██        | 418/2000 [12:36<45:47,  1.74s/it, loss=0.152, lr=0.0001]
Steps:  21%|██        | 418/2000 [12:37<45:47,  1.74s/it, loss=0.18, lr=0.0001] 
Steps:  21%|██        | 418/2000 [12:37<45:47,  1.74s/it, loss=0.157, lr=0.0001]
Steps:  21%|██        | 418/2000 [12:38<45:47,  1.74s/it, loss=0.207, lr=0.0001]
Steps:  21%|██        | 419/2000 [12:38<46:54,  1.78s/it, loss=0.207, lr=0.0001]
Steps:  21%|██        | 419/2000 [12:38<46:54,  1.78s/it, loss=0.14, lr=0.0001] 
Steps:  21%|██        | 419/2000 [12:39<46:54,  1.78s/it, loss=0.139, lr=0.0001]
Steps:  21%|██        | 419/2000 [12:39<46:54,  1.78s/it, loss=0.196, lr=0.0001]
Steps:  21%|██        | 419/2000 [12:40<46:54,  1.78s/it, loss=0.197, lr=0.0001]
Steps:  21%|██        | 420/2000 [12:40<46:02,  1.75s/it, loss=0.197, lr=0.0001]
Steps:  21%|██        | 420/2000 [12:40<46:02,  1.75s/it, loss=0.0972, lr=0.0001]
Steps:  21%|██        | 420/2000 [12:40<46:02,  1.75s/it, loss=0.24, lr=0.0001]  
Steps:  21%|██        | 420/2000 [12:41<46:02,  1.75s/it, loss=0.115, lr=0.0001]
Steps:  21%|██        | 420/2000 [12:41<46:02,  1.75s/it, loss=0.217, lr=0.0001]
Steps:  21%|██        | 421/2000 [12:42<45:24,  1.73s/it, loss=0.217, lr=0.0001]
Steps:  21%|██        | 421/2000 [12:42<45:24,  1.73s/it, loss=0.134, lr=0.0001]
Steps:  21%|██        | 421/2000 [12:42<45:24,  1.73s/it, loss=0.269, lr=0.0001]
Steps:  21%|██        | 421/2000 [12:43<45:24,  1.73s/it, loss=1.07, lr=0.0001] 
Steps:  21%|██        | 421/2000 [12:43<45:24,  1.73s/it, loss=0.0991, lr=0.0001]
Steps:  21%|██        | 422/2000 [12:44<46:50,  1.78s/it, loss=0.0991, lr=0.0001]
Steps:  21%|██        | 422/2000 [12:44<46:50,  1.78s/it, loss=0.58, lr=0.0001]  
Steps:  21%|██        | 422/2000 [12:44<46:50,  1.78s/it, loss=0.212, lr=0.0001]
Steps:  21%|██        | 422/2000 [12:44<46:50,  1.78s/it, loss=0.112, lr=0.0001]
Steps:  21%|██        | 422/2000 [12:45<46:50,  1.78s/it, loss=0.574, lr=0.0001]
Steps:  21%|██        | 423/2000 [12:45<46:03,  1.75s/it, loss=0.574, lr=0.0001]
Steps:  21%|██        | 423/2000 [12:45<46:03,  1.75s/it, loss=0.101, lr=0.0001]
Steps:  21%|██        | 423/2000 [12:46<46:03,  1.75s/it, loss=0.124, lr=0.0001]
Steps:  21%|██        | 423/2000 [12:46<46:03,  1.75s/it, loss=0.151, lr=0.0001]
Steps:  21%|██        | 423/2000 [12:46<46:03,  1.75s/it, loss=0.0844, lr=0.0001]
Steps:  21%|██        | 424/2000 [12:47<45:17,  1.72s/it, loss=0.0844, lr=0.0001]
Steps:  21%|██        | 424/2000 [12:47<45:17,  1.72s/it, loss=0.374, lr=0.0001] 
Steps:  21%|██        | 424/2000 [12:47<45:17,  1.72s/it, loss=0.283, lr=0.0001]
Steps:  21%|██        | 424/2000 [12:48<45:17,  1.72s/it, loss=0.313, lr=0.0001]
Steps:  21%|██        | 424/2000 [12:48<45:17,  1.72s/it, loss=0.0954, lr=0.0001]
Steps:  21%|██▏       | 425/2000 [12:49<46:47,  1.78s/it, loss=0.0954, lr=0.0001]
Steps:  21%|██▏       | 425/2000 [12:49<46:47,  1.78s/it, loss=0.214, lr=0.0001] 
Steps:  21%|██▏       | 425/2000 [12:49<46:47,  1.78s/it, loss=0.138, lr=0.0001]
Steps:  21%|██▏       | 425/2000 [12:50<46:47,  1.78s/it, loss=0.141, lr=0.0001]
Steps:  21%|██▏       | 425/2000 [12:50<46:47,  1.78s/it, loss=0.221, lr=0.0001]
Steps:  21%|██▏       | 426/2000 [12:51<46:08,  1.76s/it, loss=0.221, lr=0.0001]
Steps:  21%|██▏       | 426/2000 [12:51<46:08,  1.76s/it, loss=0.0682, lr=0.0001]
Steps:  21%|██▏       | 426/2000 [12:51<46:08,  1.76s/it, loss=0.124, lr=0.0001] 
Steps:  21%|██▏       | 426/2000 [12:51<46:08,  1.76s/it, loss=0.42, lr=0.0001] 
Steps:  21%|██▏       | 426/2000 [12:52<46:08,  1.76s/it, loss=0.087, lr=0.0001]
Steps:  21%|██▏       | 427/2000 [12:52<45:38,  1.74s/it, loss=0.087, lr=0.0001]
Steps:  21%|██▏       | 427/2000 [12:52<45:38,  1.74s/it, loss=0.216, lr=0.0001]
Steps:  21%|██▏       | 427/2000 [12:53<45:38,  1.74s/it, loss=0.199, lr=0.0001]
Steps:  21%|██▏       | 427/2000 [12:53<45:38,  1.74s/it, loss=0.21, lr=0.0001] 
Steps:  21%|██▏       | 427/2000 [12:54<45:38,  1.74s/it, loss=0.217, lr=0.0001]
Steps:  21%|██▏       | 428/2000 [12:54<47:02,  1.80s/it, loss=0.217, lr=0.0001]
Steps:  21%|██▏       | 428/2000 [12:54<47:02,  1.80s/it, loss=0.213, lr=0.0001]
Steps:  21%|██▏       | 428/2000 [12:55<47:02,  1.80s/it, loss=0.154, lr=0.0001]
Steps:  21%|██▏       | 428/2000 [12:55<47:02,  1.80s/it, loss=0.23, lr=0.0001] 
Steps:  21%|██▏       | 428/2000 [12:55<47:02,  1.80s/it, loss=0.167, lr=0.0001]
Steps:  21%|██▏       | 429/2000 [12:56<46:04,  1.76s/it, loss=0.167, lr=0.0001]
Steps:  21%|██▏       | 429/2000 [12:56<46:04,  1.76s/it, loss=0.0999, lr=0.0001]
Steps:  21%|██▏       | 429/2000 [12:56<46:04,  1.76s/it, loss=0.122, lr=0.0001] 
Steps:  21%|██▏       | 429/2000 [12:57<46:04,  1.76s/it, loss=0.264, lr=0.0001]
Steps:  21%|██▏       | 429/2000 [12:57<46:04,  1.76s/it, loss=0.505, lr=0.0001]
Steps:  22%|██▏       | 430/2000 [12:58<45:13,  1.73s/it, loss=0.505, lr=0.0001]
Steps:  22%|██▏       | 430/2000 [12:58<45:13,  1.73s/it, loss=0.236, lr=0.0001]
Steps:  22%|██▏       | 430/2000 [12:58<45:13,  1.73s/it, loss=0.201, lr=0.0001]
Steps:  22%|██▏       | 430/2000 [12:58<45:13,  1.73s/it, loss=0.0849, lr=0.0001]
Steps:  22%|██▏       | 430/2000 [12:59<45:13,  1.73s/it, loss=0.182, lr=0.0001] 
Steps:  22%|██▏       | 431/2000 [12:59<46:36,  1.78s/it, loss=0.182, lr=0.0001]
Steps:  22%|██▏       | 431/2000 [12:59<46:36,  1.78s/it, loss=0.151, lr=0.0001]
Steps:  22%|██▏       | 431/2000 [13:00<46:36,  1.78s/it, loss=0.203, lr=0.0001]
Steps:  22%|██▏       | 431/2000 [13:00<46:36,  1.78s/it, loss=0.145, lr=0.0001]
Steps:  22%|██▏       | 431/2000 [13:01<46:36,  1.78s/it, loss=0.0722, lr=0.0001]
Steps:  22%|██▏       | 432/2000 [13:01<45:45,  1.75s/it, loss=0.0722, lr=0.0001]
Steps:  22%|██▏       | 432/2000 [13:01<45:45,  1.75s/it, loss=0.186, lr=0.0001] 
Steps:  22%|██▏       | 432/2000 [13:01<45:45,  1.75s/it, loss=0.167, lr=0.0001]
Steps:  22%|██▏       | 432/2000 [13:02<45:45,  1.75s/it, loss=0.234, lr=0.0001]
Steps:  22%|██▏       | 432/2000 [13:02<45:45,  1.75s/it, loss=0.138, lr=0.0001]
Steps:  22%|██▏       | 433/2000 [13:03<45:06,  1.73s/it, loss=0.138, lr=0.0001]
Steps:  22%|██▏       | 433/2000 [13:03<45:06,  1.73s/it, loss=0.139, lr=0.0001]
Steps:  22%|██▏       | 433/2000 [13:03<45:06,  1.73s/it, loss=0.0803, lr=0.0001]
Steps:  22%|██▏       | 433/2000 [13:04<45:06,  1.73s/it, loss=0.278, lr=0.0001] 
Steps:  22%|██▏       | 433/2000 [13:04<45:06,  1.73s/it, loss=0.0895, lr=0.0001]
Steps:  22%|██▏       | 434/2000 [13:05<46:36,  1.79s/it, loss=0.0895, lr=0.0001]
Steps:  22%|██▏       | 434/2000 [13:05<46:36,  1.79s/it, loss=0.0284, lr=0.0001]
Steps:  22%|██▏       | 434/2000 [13:05<46:36,  1.79s/it, loss=0.168, lr=0.0001] 
Steps:  22%|██▏       | 434/2000 [13:05<46:36,  1.79s/it, loss=0.156, lr=0.0001]
Steps:  22%|██▏       | 434/2000 [13:06<46:36,  1.79s/it, loss=0.226, lr=0.0001]
Steps:  22%|██▏       | 435/2000 [13:06<45:47,  1.76s/it, loss=0.226, lr=0.0001]
Steps:  22%|██▏       | 435/2000 [13:06<45:47,  1.76s/it, loss=0.22, lr=0.0001] 
Steps:  22%|██▏       | 435/2000 [13:07<45:47,  1.76s/it, loss=0.339, lr=0.0001]
Steps:  22%|██▏       | 435/2000 [13:07<45:47,  1.76s/it, loss=0.242, lr=0.0001]
Steps:  22%|██▏       | 435/2000 [13:08<45:47,  1.76s/it, loss=0.329, lr=0.0001]
Steps:  22%|██▏       | 436/2000 [13:08<45:14,  1.74s/it, loss=0.329, lr=0.0001]
Steps:  22%|██▏       | 436/2000 [13:08<45:14,  1.74s/it, loss=0.393, lr=0.0001]
Steps:  22%|██▏       | 436/2000 [13:08<45:14,  1.74s/it, loss=0.091, lr=0.0001]
Steps:  22%|██▏       | 436/2000 [13:09<45:14,  1.74s/it, loss=0.319, lr=0.0001]
Steps:  22%|██▏       | 436/2000 [13:09<45:14,  1.74s/it, loss=0.167, lr=0.0001]
Steps:  22%|██▏       | 437/2000 [13:10<44:46,  1.72s/it, loss=0.167, lr=0.0001]
Steps:  22%|██▏       | 437/2000 [13:10<44:46,  1.72s/it, loss=0.256, lr=0.0001]
Steps:  22%|██▏       | 437/2000 [13:10<44:46,  1.72s/it, loss=0.588, lr=0.0001]
Steps:  22%|██▏       | 437/2000 [13:11<44:46,  1.72s/it, loss=0.163, lr=0.0001]
Steps:  22%|██▏       | 437/2000 [13:11<44:46,  1.72s/it, loss=0.0525, lr=0.0001]
Steps:  22%|██▏       | 438/2000 [13:12<46:02,  1.77s/it, loss=0.0525, lr=0.0001]
Steps:  22%|██▏       | 438/2000 [13:12<46:02,  1.77s/it, loss=0.164, lr=0.0001] 
Steps:  22%|██▏       | 438/2000 [13:12<46:02,  1.77s/it, loss=0.313, lr=0.0001]
Steps:  22%|██▏       | 438/2000 [13:12<46:02,  1.77s/it, loss=0.123, lr=0.0001]
Steps:  22%|██▏       | 438/2000 [13:13<46:02,  1.77s/it, loss=0.156, lr=0.0001]
Steps:  22%|██▏       | 439/2000 [13:13<45:10,  1.74s/it, loss=0.156, lr=0.0001]
Steps:  22%|██▏       | 439/2000 [13:13<45:10,  1.74s/it, loss=0.307, lr=0.0001]
Steps:  22%|██▏       | 439/2000 [13:14<45:10,  1.74s/it, loss=0.36, lr=0.0001] 
Steps:  22%|██▏       | 439/2000 [13:14<45:10,  1.74s/it, loss=0.429, lr=0.0001]
Steps:  22%|██▏       | 439/2000 [13:15<45:10,  1.74s/it, loss=0.21, lr=0.0001] 
Steps:  22%|██▏       | 440/2000 [13:15<44:33,  1.71s/it, loss=0.21, lr=0.0001]
Steps:  22%|██▏       | 440/2000 [13:15<44:33,  1.71s/it, loss=0.214, lr=0.0001]
Steps:  22%|██▏       | 440/2000 [13:15<44:33,  1.71s/it, loss=0.192, lr=0.0001]
Steps:  22%|██▏       | 440/2000 [13:16<44:33,  1.71s/it, loss=0.454, lr=0.0001]
Steps:  22%|██▏       | 440/2000 [13:16<44:33,  1.71s/it, loss=0.194, lr=0.0001]
Steps:  22%|██▏       | 441/2000 [13:17<46:19,  1.78s/it, loss=0.194, lr=0.0001]
Steps:  22%|██▏       | 441/2000 [13:17<46:19,  1.78s/it, loss=1.78, lr=0.0001] 
Steps:  22%|██▏       | 441/2000 [13:17<46:19,  1.78s/it, loss=0.247, lr=0.0001]
Steps:  22%|██▏       | 441/2000 [13:18<46:19,  1.78s/it, loss=0.234, lr=0.0001]
Steps:  22%|██▏       | 441/2000 [13:18<46:19,  1.78s/it, loss=1.04, lr=0.0001] 
Steps:  22%|██▏       | 442/2000 [13:19<45:25,  1.75s/it, loss=1.04, lr=0.0001]
Steps:  22%|██▏       | 442/2000 [13:19<45:25,  1.75s/it, loss=0.153, lr=0.0001]
Steps:  22%|██▏       | 442/2000 [13:19<45:25,  1.75s/it, loss=0.201, lr=0.0001]
Steps:  22%|██▏       | 442/2000 [13:19<45:25,  1.75s/it, loss=0.296, lr=0.0001]
Steps:  22%|██▏       | 442/2000 [13:20<45:25,  1.75s/it, loss=0.305, lr=0.0001]
Steps:  22%|██▏       | 443/2000 [13:20<44:47,  1.73s/it, loss=0.305, lr=0.0001]
Steps:  22%|██▏       | 443/2000 [13:20<44:47,  1.73s/it, loss=0.242, lr=0.0001]
Steps:  22%|██▏       | 443/2000 [13:21<44:47,  1.73s/it, loss=0.263, lr=0.0001]
Steps:  22%|██▏       | 443/2000 [13:21<44:47,  1.73s/it, loss=0.232, lr=0.0001]
Steps:  22%|██▏       | 443/2000 [13:22<44:47,  1.73s/it, loss=0.0551, lr=0.0001]
Steps:  22%|██▏       | 444/2000 [13:22<46:08,  1.78s/it, loss=0.0551, lr=0.0001]
Steps:  22%|██▏       | 444/2000 [13:22<46:08,  1.78s/it, loss=0.286, lr=0.0001] 
Steps:  22%|██▏       | 444/2000 [13:23<46:08,  1.78s/it, loss=0.242, lr=0.0001]
Steps:  22%|██▏       | 444/2000 [13:23<46:08,  1.78s/it, loss=0.856, lr=0.0001]
Steps:  22%|██▏       | 444/2000 [13:23<46:08,  1.78s/it, loss=0.151, lr=0.0001]
Steps:  22%|██▏       | 445/2000 [13:24<45:22,  1.75s/it, loss=0.151, lr=0.0001]
Steps:  22%|██▏       | 445/2000 [13:24<45:22,  1.75s/it, loss=0.22, lr=0.0001] 
Steps:  22%|██▏       | 445/2000 [13:24<45:22,  1.75s/it, loss=0.289, lr=0.0001]
Steps:  22%|██▏       | 445/2000 [13:25<45:22,  1.75s/it, loss=0.181, lr=0.0001]
Steps:  22%|██▏       | 445/2000 [13:25<45:22,  1.75s/it, loss=0.196, lr=0.0001]
Steps:  22%|██▏       | 446/2000 [13:26<44:50,  1.73s/it, loss=0.196, lr=0.0001]
Steps:  22%|██▏       | 446/2000 [13:26<44:50,  1.73s/it, loss=0.192, lr=0.0001]
Steps:  22%|██▏       | 446/2000 [13:26<44:50,  1.73s/it, loss=0.447, lr=0.0001]
Steps:  22%|██▏       | 446/2000 [13:26<44:50,  1.73s/it, loss=0.113, lr=0.0001]
Steps:  22%|██▏       | 446/2000 [13:27<44:50,  1.73s/it, loss=0.12, lr=0.0001] 
Steps:  22%|██▏       | 447/2000 [13:27<46:11,  1.78s/it, loss=0.12, lr=0.0001]
Steps:  22%|██▏       | 447/2000 [13:27<46:11,  1.78s/it, loss=0.323, lr=0.0001]
Steps:  22%|██▏       | 447/2000 [13:28<46:11,  1.78s/it, loss=0.521, lr=0.0001]
Steps:  22%|██▏       | 447/2000 [13:28<46:11,  1.78s/it, loss=0.237, lr=0.0001]
Steps:  22%|██▏       | 447/2000 [13:29<46:11,  1.78s/it, loss=0.141, lr=0.0001]
Steps:  22%|██▏       | 448/2000 [13:29<45:37,  1.76s/it, loss=0.141, lr=0.0001]
Steps:  22%|██▏       | 448/2000 [13:29<45:37,  1.76s/it, loss=0.191, lr=0.0001]
Steps:  22%|██▏       | 448/2000 [13:30<45:37,  1.76s/it, loss=0.154, lr=0.0001]
Steps:  22%|██▏       | 448/2000 [13:30<45:37,  1.76s/it, loss=0.173, lr=0.0001]
Steps:  22%|██▏       | 448/2000 [13:30<45:37,  1.76s/it, loss=0.219, lr=0.0001]
Steps:  22%|██▏       | 449/2000 [13:31<44:56,  1.74s/it, loss=0.219, lr=0.0001]
Steps:  22%|██▏       | 449/2000 [13:31<44:56,  1.74s/it, loss=0.906, lr=0.0001]
Steps:  22%|██▏       | 449/2000 [13:31<44:56,  1.74s/it, loss=0.106, lr=0.0001]
Steps:  22%|██▏       | 449/2000 [13:32<44:56,  1.74s/it, loss=0.713, lr=0.0001]
Steps:  22%|██▏       | 449/2000 [13:32<44:56,  1.74s/it, loss=0.0977, lr=0.0001]
Steps:  22%|██▎       | 450/2000 [13:33<46:39,  1.81s/it, loss=0.0977, lr=0.0001]
Steps:  22%|██▎       | 450/2000 [13:33<46:39,  1.81s/it, loss=0.146, lr=0.0001] 
Steps:  22%|██▎       | 450/2000 [13:33<46:39,  1.81s/it, loss=0.263, lr=0.0001]
Steps:  22%|██▎       | 450/2000 [13:34<46:39,  1.81s/it, loss=0.19, lr=0.0001] 
Steps:  22%|██▎       | 450/2000 [13:34<46:39,  1.81s/it, loss=0.19, lr=0.0001]
Steps:  23%|██▎       | 451/2000 [13:34<45:58,  1.78s/it, loss=0.19, lr=0.0001]
Steps:  23%|██▎       | 451/2000 [13:34<45:58,  1.78s/it, loss=0.329, lr=0.0001]
Steps:  23%|██▎       | 451/2000 [13:35<45:58,  1.78s/it, loss=0.23, lr=0.0001] 
Steps:  23%|██▎       | 451/2000 [13:35<45:58,  1.78s/it, loss=0.154, lr=0.0001]
Steps:  23%|██▎       | 451/2000 [13:36<45:58,  1.78s/it, loss=0.179, lr=0.0001]
Steps:  23%|██▎       | 452/2000 [13:36<45:35,  1.77s/it, loss=0.179, lr=0.0001]
Steps:  23%|██▎       | 452/2000 [13:36<45:35,  1.77s/it, loss=0.962, lr=0.0001]
Steps:  23%|██▎       | 452/2000 [13:37<45:35,  1.77s/it, loss=0.295, lr=0.0001]
Steps:  23%|██▎       | 452/2000 [13:37<45:35,  1.77s/it, loss=0.142, lr=0.0001]
Steps:  23%|██▎       | 452/2000 [13:38<45:35,  1.77s/it, loss=0.235, lr=0.0001]
Steps:  23%|██▎       | 453/2000 [13:38<47:14,  1.83s/it, loss=0.235, lr=0.0001]
Steps:  23%|██▎       | 453/2000 [13:38<47:14,  1.83s/it, loss=0.256, lr=0.0001]
Steps:  23%|██▎       | 453/2000 [13:39<47:14,  1.83s/it, loss=0.149, lr=0.0001]
Steps:  23%|██▎       | 453/2000 [13:39<47:14,  1.83s/it, loss=0.195, lr=0.0001]
Steps:  23%|██▎       | 453/2000 [13:39<47:14,  1.83s/it, loss=0.131, lr=0.0001]
Steps:  23%|██▎       | 454/2000 [13:40<46:07,  1.79s/it, loss=0.131, lr=0.0001]
Steps:  23%|██▎       | 454/2000 [13:40<46:07,  1.79s/it, loss=0.138, lr=0.0001]
Steps:  23%|██▎       | 454/2000 [13:40<46:07,  1.79s/it, loss=0.186, lr=0.0001]
Steps:  23%|██▎       | 454/2000 [13:41<46:07,  1.79s/it, loss=0.15, lr=0.0001] 
Steps:  23%|██▎       | 454/2000 [13:41<46:07,  1.79s/it, loss=0.256, lr=0.0001]
Steps:  23%|██▎       | 455/2000 [13:42<45:05,  1.75s/it, loss=0.256, lr=0.0001]
Steps:  23%|██▎       | 455/2000 [13:42<45:05,  1.75s/it, loss=0.0852, lr=0.0001]
Steps:  23%|██▎       | 455/2000 [13:42<45:05,  1.75s/it, loss=0.15, lr=0.0001]  
Steps:  23%|██▎       | 455/2000 [13:42<45:05,  1.75s/it, loss=0.146, lr=0.0001]
Steps:  23%|██▎       | 455/2000 [13:43<45:05,  1.75s/it, loss=0.258, lr=0.0001]
Steps:  23%|██▎       | 456/2000 [13:43<44:23,  1.73s/it, loss=0.258, lr=0.0001]
Steps:  23%|██▎       | 456/2000 [13:43<44:23,  1.73s/it, loss=0.124, lr=0.0001]
Steps:  23%|██▎       | 456/2000 [13:44<44:23,  1.73s/it, loss=0.205, lr=0.0001]
Steps:  23%|██▎       | 456/2000 [13:44<44:23,  1.73s/it, loss=0.165, lr=0.0001]
Steps:  23%|██▎       | 456/2000 [13:45<44:23,  1.73s/it, loss=0.261, lr=0.0001]
Steps:  23%|██▎       | 457/2000 [13:45<45:54,  1.78s/it, loss=0.261, lr=0.0001]
Steps:  23%|██▎       | 457/2000 [13:45<45:54,  1.78s/it, loss=0.28, lr=0.0001] 
Steps:  23%|██▎       | 457/2000 [13:46<45:54,  1.78s/it, loss=0.121, lr=0.0001]
Steps:  23%|██▎       | 457/2000 [13:46<45:54,  1.78s/it, loss=0.272, lr=0.0001]
Steps:  23%|██▎       | 457/2000 [13:46<45:54,  1.78s/it, loss=0.178, lr=0.0001]
Steps:  23%|██▎       | 458/2000 [13:47<45:12,  1.76s/it, loss=0.178, lr=0.0001]
Steps:  23%|██▎       | 458/2000 [13:47<45:12,  1.76s/it, loss=0.385, lr=0.0001]
Steps:  23%|██▎       | 458/2000 [13:47<45:12,  1.76s/it, loss=0.698, lr=0.0001]
Steps:  23%|██▎       | 458/2000 [13:48<45:12,  1.76s/it, loss=0.0731, lr=0.0001]
Steps:  23%|██▎       | 458/2000 [13:48<45:12,  1.76s/it, loss=0.464, lr=0.0001] 
Steps:  23%|██▎       | 459/2000 [13:49<44:26,  1.73s/it, loss=0.464, lr=0.0001]
Steps:  23%|██▎       | 459/2000 [13:49<44:26,  1.73s/it, loss=0.189, lr=0.0001]
Steps:  23%|██▎       | 459/2000 [13:49<44:26,  1.73s/it, loss=0.164, lr=0.0001]
Steps:  23%|██▎       | 459/2000 [13:50<44:26,  1.73s/it, loss=0.186, lr=0.0001]
Steps:  23%|██▎       | 459/2000 [13:50<44:26,  1.73s/it, loss=0.264, lr=0.0001]
Steps:  23%|██▎       | 460/2000 [13:50<45:41,  1.78s/it, loss=0.264, lr=0.0001]
Steps:  23%|██▎       | 460/2000 [13:50<45:41,  1.78s/it, loss=0.15, lr=0.0001] 
Steps:  23%|██▎       | 460/2000 [13:51<45:41,  1.78s/it, loss=0.158, lr=0.0001]
Steps:  23%|██▎       | 460/2000 [13:51<45:41,  1.78s/it, loss=0.43, lr=0.0001] 
Steps:  23%|██▎       | 460/2000 [13:52<45:41,  1.78s/it, loss=0.213, lr=0.0001]
Steps:  23%|██▎       | 461/2000 [13:52<44:49,  1.75s/it, loss=0.213, lr=0.0001]
Steps:  23%|██▎       | 461/2000 [13:52<44:49,  1.75s/it, loss=0.272, lr=0.0001]
Steps:  23%|██▎       | 461/2000 [13:52<44:49,  1.75s/it, loss=0.114, lr=0.0001]
Steps:  23%|██▎       | 461/2000 [13:53<44:49,  1.75s/it, loss=0.239, lr=0.0001]
Steps:  23%|██▎       | 461/2000 [13:53<44:49,  1.75s/it, loss=0.199, lr=0.0001]
Steps:  23%|██▎       | 462/2000 [13:54<44:01,  1.72s/it, loss=0.199, lr=0.0001]
Steps:  23%|██▎       | 462/2000 [13:54<44:01,  1.72s/it, loss=0.138, lr=0.0001]
Steps:  23%|██▎       | 462/2000 [13:54<44:01,  1.72s/it, loss=0.251, lr=0.0001]
Steps:  23%|██▎       | 462/2000 [13:55<44:01,  1.72s/it, loss=0.0742, lr=0.0001]
Steps:  23%|██▎       | 462/2000 [13:55<44:01,  1.72s/it, loss=0.245, lr=0.0001] 
Steps:  23%|██▎       | 463/2000 [13:56<45:15,  1.77s/it, loss=0.245, lr=0.0001]
Steps:  23%|██▎       | 463/2000 [13:56<45:15,  1.77s/it, loss=0.0678, lr=0.0001]
Steps:  23%|██▎       | 463/2000 [13:56<45:15,  1.77s/it, loss=0.21, lr=0.0001]  
Steps:  23%|██▎       | 463/2000 [13:56<45:15,  1.77s/it, loss=0.164, lr=0.0001]
Steps:  23%|██▎       | 463/2000 [13:57<45:15,  1.77s/it, loss=0.047, lr=0.0001]
Steps:  23%|██▎       | 464/2000 [13:57<44:12,  1.73s/it, loss=0.047, lr=0.0001]
Steps:  23%|██▎       | 464/2000 [13:57<44:12,  1.73s/it, loss=0.14, lr=0.0001] 
Steps:  23%|██▎       | 464/2000 [13:58<44:12,  1.73s/it, loss=0.113, lr=0.0001]
Steps:  23%|██▎       | 464/2000 [13:58<44:12,  1.73s/it, loss=0.2, lr=0.0001]  
Steps:  23%|██▎       | 464/2000 [13:58<44:12,  1.73s/it, loss=0.0692, lr=0.0001]
Steps:  23%|██▎       | 465/2000 [13:59<43:38,  1.71s/it, loss=0.0692, lr=0.0001]
Steps:  23%|██▎       | 465/2000 [13:59<43:38,  1.71s/it, loss=1.01, lr=0.0001]  
Steps:  23%|██▎       | 465/2000 [13:59<43:38,  1.71s/it, loss=0.0987, lr=0.0001]
Steps:  23%|██▎       | 465/2000 [14:00<43:38,  1.71s/it, loss=0.159, lr=0.0001] 
Steps:  23%|██▎       | 465/2000 [14:00<43:38,  1.71s/it, loss=0.163, lr=0.0001]
Steps:  23%|██▎       | 466/2000 [14:01<44:51,  1.75s/it, loss=0.163, lr=0.0001]
Steps:  23%|██▎       | 466/2000 [14:01<44:51,  1.75s/it, loss=0.197, lr=0.0001]
Steps:  23%|██▎       | 466/2000 [14:01<44:51,  1.75s/it, loss=0.208, lr=0.0001]
Steps:  23%|██▎       | 466/2000 [14:02<44:51,  1.75s/it, loss=0.232, lr=0.0001]
Steps:  23%|██▎       | 466/2000 [14:02<44:51,  1.75s/it, loss=0.196, lr=0.0001]
Steps:  23%|██▎       | 467/2000 [14:02<44:11,  1.73s/it, loss=0.196, lr=0.0001]
Steps:  23%|██▎       | 467/2000 [14:02<44:11,  1.73s/it, loss=1.03, lr=0.0001] 
Steps:  23%|██▎       | 467/2000 [14:03<44:11,  1.73s/it, loss=0.322, lr=0.0001]
Steps:  23%|██▎       | 467/2000 [14:03<44:11,  1.73s/it, loss=0.0946, lr=0.0001]
Steps:  23%|██▎       | 467/2000 [14:04<44:11,  1.73s/it, loss=0.0675, lr=0.0001]
Steps:  23%|██▎       | 468/2000 [14:04<43:41,  1.71s/it, loss=0.0675, lr=0.0001]
Steps:  23%|██▎       | 468/2000 [14:04<43:41,  1.71s/it, loss=0.153, lr=0.0001] 
Steps:  23%|██▎       | 468/2000 [14:05<43:41,  1.71s/it, loss=0.201, lr=0.0001]
Steps:  23%|██▎       | 468/2000 [14:05<43:41,  1.71s/it, loss=0.128, lr=0.0001]
Steps:  23%|██▎       | 468/2000 [14:05<43:41,  1.71s/it, loss=0.149, lr=0.0001]
Steps:  23%|██▎       | 469/2000 [14:06<45:17,  1.78s/it, loss=0.149, lr=0.0001]
Steps:  23%|██▎       | 469/2000 [14:06<45:17,  1.78s/it, loss=0.144, lr=0.0001]
Steps:  23%|██▎       | 469/2000 [14:06<45:17,  1.78s/it, loss=0.254, lr=0.0001]
Steps:  23%|██▎       | 469/2000 [14:07<45:17,  1.78s/it, loss=0.13, lr=0.0001] 
Steps:  23%|██▎       | 469/2000 [14:07<45:17,  1.78s/it, loss=0.563, lr=0.0001]
Steps:  24%|██▎       | 470/2000 [14:08<44:31,  1.75s/it, loss=0.563, lr=0.0001]
Steps:  24%|██▎       | 470/2000 [14:08<44:31,  1.75s/it, loss=0.0819, lr=0.0001]
Steps:  24%|██▎       | 470/2000 [14:08<44:31,  1.75s/it, loss=0.169, lr=0.0001] 
Steps:  24%|██▎       | 470/2000 [14:09<44:31,  1.75s/it, loss=0.14, lr=0.0001] 
Steps:  24%|██▎       | 470/2000 [14:09<44:31,  1.75s/it, loss=0.222, lr=0.0001]
Steps:  24%|██▎       | 471/2000 [14:09<44:19,  1.74s/it, loss=0.222, lr=0.0001]
Steps:  24%|██▎       | 471/2000 [14:09<44:19,  1.74s/it, loss=0.215, lr=0.0001]
Steps:  24%|██▎       | 471/2000 [14:10<44:19,  1.74s/it, loss=1.94, lr=0.0001] 
Steps:  24%|██▎       | 471/2000 [14:10<44:19,  1.74s/it, loss=0.17, lr=0.0001]
Steps:  24%|██▎       | 471/2000 [14:11<44:19,  1.74s/it, loss=0.429, lr=0.0001]
Steps:  24%|██▎       | 472/2000 [14:11<45:36,  1.79s/it, loss=0.429, lr=0.0001]
Steps:  24%|██▎       | 472/2000 [14:11<45:36,  1.79s/it, loss=0.099, lr=0.0001]
Steps:  24%|██▎       | 472/2000 [14:12<45:36,  1.79s/it, loss=0.108, lr=0.0001]
Steps:  24%|██▎       | 472/2000 [14:12<45:36,  1.79s/it, loss=0.329, lr=0.0001]
Steps:  24%|██▎       | 472/2000 [14:13<45:36,  1.79s/it, loss=0.234, lr=0.0001]
Steps:  24%|██▎       | 473/2000 [14:13<44:41,  1.76s/it, loss=0.234, lr=0.0001]
Steps:  24%|██▎       | 473/2000 [14:13<44:41,  1.76s/it, loss=0.151, lr=0.0001]
Steps:  24%|██▎       | 473/2000 [14:13<44:41,  1.76s/it, loss=0.146, lr=0.0001]
Steps:  24%|██▎       | 473/2000 [14:14<44:41,  1.76s/it, loss=0.088, lr=0.0001]
Steps:  24%|██▎       | 473/2000 [14:14<44:41,  1.76s/it, loss=0.141, lr=0.0001]
Steps:  24%|██▎       | 474/2000 [14:15<44:03,  1.73s/it, loss=0.141, lr=0.0001]
Steps:  24%|██▎       | 474/2000 [14:15<44:03,  1.73s/it, loss=0.0328, lr=0.0001]
Steps:  24%|██▎       | 474/2000 [14:15<44:03,  1.73s/it, loss=0.464, lr=0.0001] 
Steps:  24%|██▎       | 474/2000 [14:16<44:03,  1.73s/it, loss=0.18, lr=0.0001] 
Steps:  24%|██▎       | 474/2000 [14:16<44:03,  1.73s/it, loss=0.218, lr=0.0001]
Steps:  24%|██▍       | 475/2000 [14:16<43:54,  1.73s/it, loss=0.218, lr=0.0001]
Steps:  24%|██▍       | 475/2000 [14:16<43:54,  1.73s/it, loss=0.22, lr=0.0001] 
Steps:  24%|██▍       | 475/2000 [14:17<43:54,  1.73s/it, loss=1.23, lr=0.0001]
Steps:  24%|██▍       | 475/2000 [14:18<43:54,  1.73s/it, loss=0.146, lr=0.0001]
Steps:  24%|██▍       | 475/2000 [14:18<43:54,  1.73s/it, loss=0.242, lr=0.0001]
Steps:  24%|██▍       | 476/2000 [14:18<45:36,  1.80s/it, loss=0.242, lr=0.0001]
Steps:  24%|██▍       | 476/2000 [14:18<45:36,  1.80s/it, loss=0.489, lr=0.0001]
Steps:  24%|██▍       | 476/2000 [14:19<45:36,  1.80s/it, loss=0.228, lr=0.0001]
Steps:  24%|██▍       | 476/2000 [14:19<45:36,  1.80s/it, loss=0.15, lr=0.0001] 
Steps:  24%|██▍       | 476/2000 [14:20<45:36,  1.80s/it, loss=0.238, lr=0.0001]
Steps:  24%|██▍       | 477/2000 [14:20<44:41,  1.76s/it, loss=0.238, lr=0.0001]
Steps:  24%|██▍       | 477/2000 [14:20<44:41,  1.76s/it, loss=0.201, lr=0.0001]
Steps:  24%|██▍       | 477/2000 [14:20<44:41,  1.76s/it, loss=0.108, lr=0.0001]
Steps:  24%|██▍       | 477/2000 [14:21<44:41,  1.76s/it, loss=0.207, lr=0.0001]
Steps:  24%|██▍       | 477/2000 [14:21<44:41,  1.76s/it, loss=0.587, lr=0.0001]
Steps:  24%|██▍       | 478/2000 [14:22<43:42,  1.72s/it, loss=0.587, lr=0.0001]
Steps:  24%|██▍       | 478/2000 [14:22<43:42,  1.72s/it, loss=0.136, lr=0.0001]
Steps:  24%|██▍       | 478/2000 [14:22<43:42,  1.72s/it, loss=0.0846, lr=0.0001]
Steps:  24%|██▍       | 478/2000 [14:23<43:42,  1.72s/it, loss=0.235, lr=0.0001] 
Steps:  24%|██▍       | 478/2000 [14:23<43:42,  1.72s/it, loss=0.226, lr=0.0001]
Steps:  24%|██▍       | 479/2000 [14:24<44:39,  1.76s/it, loss=0.226, lr=0.0001]
Steps:  24%|██▍       | 479/2000 [14:24<44:39,  1.76s/it, loss=0.176, lr=0.0001]
Steps:  24%|██▍       | 479/2000 [14:24<44:39,  1.76s/it, loss=0.204, lr=0.0001]
Steps:  24%|██▍       | 479/2000 [14:24<44:39,  1.76s/it, loss=0.346, lr=0.0001]
Steps:  24%|██▍       | 479/2000 [14:25<44:39,  1.76s/it, loss=0.157, lr=0.0001]
Steps:  24%|██▍       | 480/2000 [14:25<43:35,  1.72s/it, loss=0.157, lr=0.0001]
Steps:  24%|██▍       | 480/2000 [14:25<43:35,  1.72s/it, loss=0.183, lr=0.0001]
Steps:  24%|██▍       | 480/2000 [14:26<43:35,  1.72s/it, loss=0.378, lr=0.0001]
Steps:  24%|██▍       | 480/2000 [14:26<43:35,  1.72s/it, loss=0.172, lr=0.0001]
Steps:  24%|██▍       | 480/2000 [14:26<43:35,  1.72s/it, loss=0.219, lr=0.0001]
Steps:  24%|██▍       | 481/2000 [14:27<43:01,  1.70s/it, loss=0.219, lr=0.0001]
Steps:  24%|██▍       | 481/2000 [14:27<43:01,  1.70s/it, loss=0.268, lr=0.0001]
Steps:  24%|██▍       | 481/2000 [14:27<43:01,  1.70s/it, loss=0.162, lr=0.0001]
Steps:  24%|██▍       | 481/2000 [14:28<43:01,  1.70s/it, loss=0.158, lr=0.0001]
Steps:  24%|██▍       | 481/2000 [14:28<43:01,  1.70s/it, loss=0.0968, lr=0.0001]
Steps:  24%|██▍       | 482/2000 [14:29<44:20,  1.75s/it, loss=0.0968, lr=0.0001]
Steps:  24%|██▍       | 482/2000 [14:29<44:20,  1.75s/it, loss=0.0845, lr=0.0001]
Steps:  24%|██▍       | 482/2000 [14:29<44:20,  1.75s/it, loss=0.134, lr=0.0001] 
Steps:  24%|██▍       | 482/2000 [14:29<44:20,  1.75s/it, loss=0.162, lr=0.0001]
Steps:  24%|██▍       | 482/2000 [14:30<44:20,  1.75s/it, loss=0.207, lr=0.0001]
Steps:  24%|██▍       | 483/2000 [14:30<43:31,  1.72s/it, loss=0.207, lr=0.0001]
Steps:  24%|██▍       | 483/2000 [14:30<43:31,  1.72s/it, loss=0.189, lr=0.0001]
Steps:  24%|██▍       | 483/2000 [14:31<43:31,  1.72s/it, loss=0.195, lr=0.0001]
Steps:  24%|██▍       | 483/2000 [14:31<43:31,  1.72s/it, loss=0.116, lr=0.0001]
Steps:  24%|██▍       | 483/2000 [14:32<43:31,  1.72s/it, loss=0.342, lr=0.0001]
Steps:  24%|██▍       | 484/2000 [14:32<43:24,  1.72s/it, loss=0.342, lr=0.0001]
Steps:  24%|██▍       | 484/2000 [14:32<43:24,  1.72s/it, loss=0.535, lr=0.0001]
Steps:  24%|██▍       | 484/2000 [14:32<43:24,  1.72s/it, loss=0.142, lr=0.0001]
Steps:  24%|██▍       | 484/2000 [14:33<43:24,  1.72s/it, loss=0.141, lr=0.0001]
Steps:  24%|██▍       | 484/2000 [14:33<43:24,  1.72s/it, loss=0.24, lr=0.0001] 
Steps:  24%|██▍       | 485/2000 [14:34<45:37,  1.81s/it, loss=0.24, lr=0.0001]
Steps:  24%|██▍       | 485/2000 [14:34<45:37,  1.81s/it, loss=0.2, lr=0.0001] 
Steps:  24%|██▍       | 485/2000 [14:34<45:37,  1.81s/it, loss=0.186, lr=0.0001]
Steps:  24%|██▍       | 485/2000 [14:35<45:37,  1.81s/it, loss=0.184, lr=0.0001]
Steps:  24%|██▍       | 485/2000 [14:35<45:37,  1.81s/it, loss=0.12, lr=0.0001] 
Steps:  24%|██▍       | 486/2000 [14:36<45:18,  1.80s/it, loss=0.12, lr=0.0001]
Steps:  24%|██▍       | 486/2000 [14:36<45:18,  1.80s/it, loss=0.111, lr=0.0001]
Steps:  24%|██▍       | 486/2000 [14:36<45:18,  1.80s/it, loss=0.364, lr=0.0001]
Steps:  24%|██▍       | 486/2000 [14:37<45:18,  1.80s/it, loss=0.167, lr=0.0001]
Steps:  24%|██▍       | 486/2000 [14:37<45:18,  1.80s/it, loss=0.239, lr=0.0001]
Steps:  24%|██▍       | 487/2000 [14:38<44:56,  1.78s/it, loss=0.239, lr=0.0001]
Steps:  24%|██▍       | 487/2000 [14:38<44:56,  1.78s/it, loss=0.886, lr=0.0001]
Steps:  24%|██▍       | 487/2000 [14:38<44:56,  1.78s/it, loss=0.103, lr=0.0001]
Steps:  24%|██▍       | 487/2000 [14:38<44:56,  1.78s/it, loss=0.186, lr=0.0001]
Steps:  24%|██▍       | 487/2000 [14:39<44:56,  1.78s/it, loss=0.184, lr=0.0001]
Steps:  24%|██▍       | 488/2000 [14:40<46:47,  1.86s/it, loss=0.184, lr=0.0001]
Steps:  24%|██▍       | 488/2000 [14:40<46:47,  1.86s/it, loss=0.4, lr=0.0001]  
Steps:  24%|██▍       | 488/2000 [14:40<46:47,  1.86s/it, loss=0.203, lr=0.0001]
Steps:  24%|██▍       | 488/2000 [14:40<46:47,  1.86s/it, loss=0.125, lr=0.0001]
Steps:  24%|██▍       | 488/2000 [14:41<46:47,  1.86s/it, loss=0.121, lr=0.0001]
Steps:  24%|██▍       | 489/2000 [14:41<45:52,  1.82s/it, loss=0.121, lr=0.0001]
Steps:  24%|██▍       | 489/2000 [14:41<45:52,  1.82s/it, loss=0.234, lr=0.0001]
Steps:  24%|██▍       | 489/2000 [14:42<45:52,  1.82s/it, loss=0.194, lr=0.0001]
Steps:  24%|██▍       | 489/2000 [14:42<45:52,  1.82s/it, loss=0.665, lr=0.0001]
Steps:  24%|██▍       | 489/2000 [14:43<45:52,  1.82s/it, loss=0.111, lr=0.0001]
Steps:  24%|██▍       | 490/2000 [14:43<45:31,  1.81s/it, loss=0.111, lr=0.0001]
Steps:  24%|██▍       | 490/2000 [14:43<45:31,  1.81s/it, loss=0.183, lr=0.0001]
Steps:  24%|██▍       | 490/2000 [14:44<45:31,  1.81s/it, loss=0.367, lr=0.0001]
Steps:  24%|██▍       | 490/2000 [14:44<45:31,  1.81s/it, loss=0.234, lr=0.0001]
Steps:  24%|██▍       | 490/2000 [14:44<45:31,  1.81s/it, loss=0.236, lr=0.0001]
Steps:  25%|██▍       | 491/2000 [14:45<45:13,  1.80s/it, loss=0.236, lr=0.0001]
Steps:  25%|██▍       | 491/2000 [14:45<45:13,  1.80s/it, loss=0.155, lr=0.0001]
Steps:  25%|██▍       | 491/2000 [14:46<45:13,  1.80s/it, loss=0.189, lr=0.0001]
Steps:  25%|██▍       | 491/2000 [14:46<45:13,  1.80s/it, loss=1.02, lr=0.0001] 
Steps:  25%|██▍       | 491/2000 [14:46<45:13,  1.80s/it, loss=0.844, lr=0.0001]
Steps:  25%|██▍       | 492/2000 [14:47<46:14,  1.84s/it, loss=0.844, lr=0.0001]
Steps:  25%|██▍       | 492/2000 [14:47<46:14,  1.84s/it, loss=0.367, lr=0.0001]
Steps:  25%|██▍       | 492/2000 [14:47<46:14,  1.84s/it, loss=0.113, lr=0.0001]
Steps:  25%|██▍       | 492/2000 [14:48<46:14,  1.84s/it, loss=0.0658, lr=0.0001]
Steps:  25%|██▍       | 492/2000 [14:48<46:14,  1.84s/it, loss=0.131, lr=0.0001] 
Steps:  25%|██▍       | 493/2000 [14:49<44:50,  1.79s/it, loss=0.131, lr=0.0001]
Steps:  25%|██▍       | 493/2000 [14:49<44:50,  1.79s/it, loss=0.159, lr=0.0001]
Steps:  25%|██▍       | 493/2000 [14:49<44:50,  1.79s/it, loss=0.231, lr=0.0001]
Steps:  25%|██▍       | 493/2000 [14:49<44:50,  1.79s/it, loss=0.313, lr=0.0001]
Steps:  25%|██▍       | 493/2000 [14:50<44:50,  1.79s/it, loss=0.194, lr=0.0001]
Steps:  25%|██▍       | 494/2000 [14:50<43:51,  1.75s/it, loss=0.194, lr=0.0001]
Steps:  25%|██▍       | 494/2000 [14:50<43:51,  1.75s/it, loss=0.085, lr=0.0001]
Steps:  25%|██▍       | 494/2000 [14:51<43:51,  1.75s/it, loss=0.119, lr=0.0001]
Steps:  25%|██▍       | 494/2000 [14:51<43:51,  1.75s/it, loss=0.164, lr=0.0001]
Steps:  25%|██▍       | 494/2000 [14:52<43:51,  1.75s/it, loss=0.169, lr=0.0001]
Steps:  25%|██▍       | 495/2000 [14:52<45:00,  1.79s/it, loss=0.169, lr=0.0001]
Steps:  25%|██▍       | 495/2000 [14:52<45:00,  1.79s/it, loss=0.137, lr=0.0001]
Steps:  25%|██▍       | 495/2000 [14:52<45:00,  1.79s/it, loss=0.0587, lr=0.0001]
Steps:  25%|██▍       | 495/2000 [14:53<45:00,  1.79s/it, loss=0.128, lr=0.0001] 
Steps:  25%|██▍       | 495/2000 [14:53<45:00,  1.79s/it, loss=0.161, lr=0.0001]
Steps:  25%|██▍       | 496/2000 [14:54<44:02,  1.76s/it, loss=0.161, lr=0.0001]
Steps:  25%|██▍       | 496/2000 [14:54<44:02,  1.76s/it, loss=0.165, lr=0.0001]
Steps:  25%|██▍       | 496/2000 [14:54<44:02,  1.76s/it, loss=0.165, lr=0.0001]
Steps:  25%|██▍       | 496/2000 [14:55<44:02,  1.76s/it, loss=0.567, lr=0.0001]
Steps:  25%|██▍       | 496/2000 [14:55<44:02,  1.76s/it, loss=0.365, lr=0.0001]
Steps:  25%|██▍       | 497/2000 [14:55<43:17,  1.73s/it, loss=0.365, lr=0.0001]
Steps:  25%|██▍       | 497/2000 [14:55<43:17,  1.73s/it, loss=0.177, lr=0.0001]
Steps:  25%|██▍       | 497/2000 [14:56<43:17,  1.73s/it, loss=0.483, lr=0.0001]
Steps:  25%|██▍       | 497/2000 [14:56<43:17,  1.73s/it, loss=0.145, lr=0.0001]
Steps:  25%|██▍       | 497/2000 [14:57<43:17,  1.73s/it, loss=0.163, lr=0.0001]
Steps:  25%|██▍       | 498/2000 [14:57<44:30,  1.78s/it, loss=0.163, lr=0.0001]
Steps:  25%|██▍       | 498/2000 [14:57<44:30,  1.78s/it, loss=0.498, lr=0.0001]
Steps:  25%|██▍       | 498/2000 [14:58<44:30,  1.78s/it, loss=0.157, lr=0.0001]
Steps:  25%|██▍       | 498/2000 [14:58<44:30,  1.78s/it, loss=0.114, lr=0.0001]
Steps:  25%|██▍       | 498/2000 [14:58<44:30,  1.78s/it, loss=0.331, lr=0.0001]
Steps:  25%|██▍       | 499/2000 [14:59<43:41,  1.75s/it, loss=0.331, lr=0.0001]
Steps:  25%|██▍       | 499/2000 [14:59<43:41,  1.75s/it, loss=0.145, lr=0.0001]
Steps:  25%|██▍       | 499/2000 [14:59<43:41,  1.75s/it, loss=0.202, lr=0.0001]
Steps:  25%|██▍       | 499/2000 [15:00<43:41,  1.75s/it, loss=0.149, lr=0.0001]
Steps:  25%|██▍       | 499/2000 [15:00<43:41,  1.75s/it, loss=0.156, lr=0.0001]
Steps:  25%|██▌       | 500/2000 [15:01<42:53,  1.72s/it, loss=0.156, lr=0.0001]05/30/2026 08:47:26 - INFO - accelerate.accelerator - [RANK 0] Saving current state to /workspace/output/flux-dev-apple-emoji-lora/checkpoint-500
Model weights saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-500/pytorch_lora_weights.safetensors
05/30/2026 08:47:26 - INFO - accelerate.checkpointing - [RANK 0] Optimizer state saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-500/optimizer.bin
05/30/2026 08:47:26 - INFO - accelerate.checkpointing - [RANK 0] Scheduler state saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-500/scheduler.bin
05/30/2026 08:47:26 - INFO - accelerate.checkpointing - [RANK 0] Sampler state for dataloader 0 saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-500/sampler.bin
05/30/2026 08:47:26 - INFO - accelerate.checkpointing - [RANK 0] Random states saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-500/random_states_0.pkl
05/30/2026 08:47:26 - INFO - __main__ - [RANK 0] Saved state to /workspace/output/flux-dev-apple-emoji-lora/checkpoint-500

Steps:  25%|██▌       | 500/2000 [15:01<42:53,  1.72s/it, loss=0.186, lr=0.0001]
Steps:  25%|██▌       | 500/2000 [15:02<42:53,  1.72s/it, loss=0.241, lr=0.0001]
Steps:  25%|██▌       | 500/2000 [15:02<42:53,  1.72s/it, loss=0.223, lr=0.0001]
Steps:  25%|██▌       | 500/2000 [15:03<42:53,  1.72s/it, loss=0.183, lr=0.0001]
Steps:  25%|██▌       | 501/2000 [15:03<49:44,  1.99s/it, loss=0.183, lr=0.0001]
Steps:  25%|██▌       | 501/2000 [15:03<49:44,  1.99s/it, loss=0.124, lr=0.0001]
Steps:  25%|██▌       | 501/2000 [15:04<49:44,  1.99s/it, loss=0.509, lr=0.0001]
Steps:  25%|██▌       | 501/2000 [15:04<49:44,  1.99s/it, loss=0.248, lr=0.0001]
Steps:  25%|██▌       | 501/2000 [15:04<49:44,  1.99s/it, loss=0.185, lr=0.0001]
Steps:  25%|██▌       | 502/2000 [15:05<47:15,  1.89s/it, loss=0.185, lr=0.0001]
Steps:  25%|██▌       | 502/2000 [15:05<47:15,  1.89s/it, loss=0.237, lr=0.0001]
Steps:  25%|██▌       | 502/2000 [15:05<47:15,  1.89s/it, loss=0.189, lr=0.0001]
Steps:  25%|██▌       | 502/2000 [15:06<47:15,  1.89s/it, loss=0.125, lr=0.0001]
Steps:  25%|██▌       | 502/2000 [15:06<47:15,  1.89s/it, loss=0.266, lr=0.0001]
Steps:  25%|██▌       | 503/2000 [15:07<45:27,  1.82s/it, loss=0.266, lr=0.0001]
Steps:  25%|██▌       | 503/2000 [15:07<45:27,  1.82s/it, loss=0.323, lr=0.0001]
Steps:  25%|██▌       | 503/2000 [15:07<45:27,  1.82s/it, loss=0.282, lr=0.0001]
Steps:  25%|██▌       | 503/2000 [15:08<45:27,  1.82s/it, loss=0.0814, lr=0.0001]
Steps:  25%|██▌       | 503/2000 [15:08<45:27,  1.82s/it, loss=0.208, lr=0.0001] 
Steps:  25%|██▌       | 504/2000 [15:08<45:49,  1.84s/it, loss=0.208, lr=0.0001]
Steps:  25%|██▌       | 504/2000 [15:08<45:49,  1.84s/it, loss=0.175, lr=0.0001]
Steps:  25%|██▌       | 504/2000 [15:09<45:49,  1.84s/it, loss=0.23, lr=0.0001] 
Steps:  25%|██▌       | 504/2000 [15:09<45:49,  1.84s/it, loss=0.13, lr=0.0001]
Steps:  25%|██▌       | 504/2000 [15:10<45:49,  1.84s/it, loss=1.07, lr=0.0001]
Steps:  25%|██▌       | 505/2000 [15:10<44:33,  1.79s/it, loss=1.07, lr=0.0001]
Steps:  25%|██▌       | 505/2000 [15:10<44:33,  1.79s/it, loss=0.108, lr=0.0001]
Steps:  25%|██▌       | 505/2000 [15:11<44:33,  1.79s/it, loss=0.146, lr=0.0001]
Steps:  25%|██▌       | 505/2000 [15:11<44:33,  1.79s/it, loss=0.198, lr=0.0001]
Steps:  25%|██▌       | 505/2000 [15:11<44:33,  1.79s/it, loss=0.154, lr=0.0001]
Steps:  25%|██▌       | 506/2000 [15:12<43:23,  1.74s/it, loss=0.154, lr=0.0001]
Steps:  25%|██▌       | 506/2000 [15:12<43:23,  1.74s/it, loss=0.174, lr=0.0001]
Steps:  25%|██▌       | 506/2000 [15:12<43:23,  1.74s/it, loss=0.215, lr=0.0001]
Steps:  25%|██▌       | 506/2000 [15:13<43:23,  1.74s/it, loss=0.965, lr=0.0001]
Steps:  25%|██▌       | 506/2000 [15:13<43:23,  1.74s/it, loss=0.27, lr=0.0001] 
Steps:  25%|██▌       | 507/2000 [15:14<44:21,  1.78s/it, loss=0.27, lr=0.0001]
Steps:  25%|██▌       | 507/2000 [15:14<44:21,  1.78s/it, loss=0.205, lr=0.0001]
Steps:  25%|██▌       | 507/2000 [15:14<44:21,  1.78s/it, loss=0.105, lr=0.0001]
Steps:  25%|██▌       | 507/2000 [15:14<44:21,  1.78s/it, loss=0.277, lr=0.0001]
Steps:  25%|██▌       | 507/2000 [15:15<44:21,  1.78s/it, loss=0.0543, lr=0.0001]
Steps:  25%|██▌       | 508/2000 [15:15<43:51,  1.76s/it, loss=0.0543, lr=0.0001]
Steps:  25%|██▌       | 508/2000 [15:15<43:51,  1.76s/it, loss=0.0539, lr=0.0001]
Steps:  25%|██▌       | 508/2000 [15:16<43:51,  1.76s/it, loss=0.111, lr=0.0001] 
Steps:  25%|██▌       | 508/2000 [15:16<43:51,  1.76s/it, loss=0.334, lr=0.0001]
Steps:  25%|██▌       | 508/2000 [15:17<43:51,  1.76s/it, loss=0.149, lr=0.0001]
Steps:  25%|██▌       | 509/2000 [15:17<43:57,  1.77s/it, loss=0.149, lr=0.0001]
Steps:  25%|██▌       | 509/2000 [15:17<43:57,  1.77s/it, loss=0.0736, lr=0.0001]
Steps:  25%|██▌       | 509/2000 [15:18<43:57,  1.77s/it, loss=0.155, lr=0.0001] 
Steps:  25%|██▌       | 509/2000 [15:18<43:57,  1.77s/it, loss=0.254, lr=0.0001]
Steps:  25%|██▌       | 509/2000 [15:18<43:57,  1.77s/it, loss=0.165, lr=0.0001]
Steps:  26%|██▌       | 510/2000 [15:19<45:14,  1.82s/it, loss=0.165, lr=0.0001]
Steps:  26%|██▌       | 510/2000 [15:19<45:14,  1.82s/it, loss=0.105, lr=0.0001]
Steps:  26%|██▌       | 510/2000 [15:19<45:14,  1.82s/it, loss=0.152, lr=0.0001]
Steps:  26%|██▌       | 510/2000 [15:20<45:14,  1.82s/it, loss=0.461, lr=0.0001]
Steps:  26%|██▌       | 510/2000 [15:20<45:14,  1.82s/it, loss=0.248, lr=0.0001]
Steps:  26%|██▌       | 511/2000 [15:21<44:25,  1.79s/it, loss=0.248, lr=0.0001]
Steps:  26%|██▌       | 511/2000 [15:21<44:25,  1.79s/it, loss=0.0356, lr=0.0001]
Steps:  26%|██▌       | 511/2000 [15:21<44:25,  1.79s/it, loss=0.307, lr=0.0001] 
Steps:  26%|██▌       | 511/2000 [15:22<44:25,  1.79s/it, loss=0.0698, lr=0.0001]
Steps:  26%|██▌       | 511/2000 [15:22<44:25,  1.79s/it, loss=0.126, lr=0.0001] 
Steps:  26%|██▌       | 512/2000 [15:23<44:33,  1.80s/it, loss=0.126, lr=0.0001]
Steps:  26%|██▌       | 512/2000 [15:23<44:33,  1.80s/it, loss=0.149, lr=0.0001]
Steps:  26%|██▌       | 512/2000 [15:23<44:33,  1.80s/it, loss=0.153, lr=0.0001]
Steps:  26%|██▌       | 512/2000 [15:23<44:33,  1.80s/it, loss=0.143, lr=0.0001]
Steps:  26%|██▌       | 512/2000 [15:24<44:33,  1.80s/it, loss=0.226, lr=0.0001]
Steps:  26%|██▌       | 513/2000 [15:24<45:15,  1.83s/it, loss=0.226, lr=0.0001]
Steps:  26%|██▌       | 513/2000 [15:24<45:15,  1.83s/it, loss=0.165, lr=0.0001]
Steps:  26%|██▌       | 513/2000 [15:25<45:15,  1.83s/it, loss=0.203, lr=0.0001]
Steps:  26%|██▌       | 513/2000 [15:25<45:15,  1.83s/it, loss=0.257, lr=0.0001]
Steps:  26%|██▌       | 513/2000 [15:26<45:15,  1.83s/it, loss=0.156, lr=0.0001]
Steps:  26%|██▌       | 514/2000 [15:26<43:54,  1.77s/it, loss=0.156, lr=0.0001]
Steps:  26%|██▌       | 514/2000 [15:26<43:54,  1.77s/it, loss=0.216, lr=0.0001]
Steps:  26%|██▌       | 514/2000 [15:27<43:54,  1.77s/it, loss=0.189, lr=0.0001]
Steps:  26%|██▌       | 514/2000 [15:27<43:54,  1.77s/it, loss=0.146, lr=0.0001]
Steps:  26%|██▌       | 514/2000 [15:27<43:54,  1.77s/it, loss=0.157, lr=0.0001]
Steps:  26%|██▌       | 515/2000 [15:28<43:03,  1.74s/it, loss=0.157, lr=0.0001]
Steps:  26%|██▌       | 515/2000 [15:28<43:03,  1.74s/it, loss=0.147, lr=0.0001]
Steps:  26%|██▌       | 515/2000 [15:28<43:03,  1.74s/it, loss=0.192, lr=0.0001]
Steps:  26%|██▌       | 515/2000 [15:29<43:03,  1.74s/it, loss=0.0754, lr=0.0001]
Steps:  26%|██▌       | 515/2000 [15:29<43:03,  1.74s/it, loss=0.117, lr=0.0001] 
Steps:  26%|██▌       | 516/2000 [15:29<42:13,  1.71s/it, loss=0.117, lr=0.0001]
Steps:  26%|██▌       | 516/2000 [15:29<42:13,  1.71s/it, loss=0.198, lr=0.0001]
Steps:  26%|██▌       | 516/2000 [15:30<42:13,  1.71s/it, loss=0.149, lr=0.0001]
Steps:  26%|██▌       | 516/2000 [15:30<42:13,  1.71s/it, loss=0.175, lr=0.0001]
Steps:  26%|██▌       | 516/2000 [15:31<42:13,  1.71s/it, loss=0.0959, lr=0.0001]
Steps:  26%|██▌       | 517/2000 [15:31<43:25,  1.76s/it, loss=0.0959, lr=0.0001]
Steps:  26%|██▌       | 517/2000 [15:31<43:25,  1.76s/it, loss=0.158, lr=0.0001] 
Steps:  26%|██▌       | 517/2000 [15:32<43:25,  1.76s/it, loss=0.134, lr=0.0001]
Steps:  26%|██▌       | 517/2000 [15:32<43:25,  1.76s/it, loss=0.0764, lr=0.0001]
Steps:  26%|██▌       | 517/2000 [15:33<43:25,  1.76s/it, loss=0.141, lr=0.0001] 
Steps:  26%|██▌       | 518/2000 [15:33<42:31,  1.72s/it, loss=0.141, lr=0.0001]
Steps:  26%|██▌       | 518/2000 [15:33<42:31,  1.72s/it, loss=0.178, lr=0.0001]
Steps:  26%|██▌       | 518/2000 [15:33<42:31,  1.72s/it, loss=1, lr=0.0001]    
Steps:  26%|██▌       | 518/2000 [15:34<42:31,  1.72s/it, loss=0.744, lr=0.0001]
Steps:  26%|██▌       | 518/2000 [15:34<42:31,  1.72s/it, loss=0.261, lr=0.0001]
Steps:  26%|██▌       | 519/2000 [15:35<41:52,  1.70s/it, loss=0.261, lr=0.0001]
Steps:  26%|██▌       | 519/2000 [15:35<41:52,  1.70s/it, loss=0.183, lr=0.0001]
Steps:  26%|██▌       | 519/2000 [15:35<41:52,  1.70s/it, loss=0.436, lr=0.0001]
Steps:  26%|██▌       | 519/2000 [15:36<41:52,  1.70s/it, loss=0.24, lr=0.0001] 
Steps:  26%|██▌       | 519/2000 [15:36<41:52,  1.70s/it, loss=0.149, lr=0.0001]
Steps:  26%|██▌       | 520/2000 [15:36<43:05,  1.75s/it, loss=0.149, lr=0.0001]
Steps:  26%|██▌       | 520/2000 [15:36<43:05,  1.75s/it, loss=0.145, lr=0.0001]
Steps:  26%|██▌       | 520/2000 [15:37<43:05,  1.75s/it, loss=0.346, lr=0.0001]
Steps:  26%|██▌       | 520/2000 [15:37<43:05,  1.75s/it, loss=0.137, lr=0.0001]
Steps:  26%|██▌       | 520/2000 [15:38<43:05,  1.75s/it, loss=0.238, lr=0.0001]
Steps:  26%|██▌       | 521/2000 [15:38<42:13,  1.71s/it, loss=0.238, lr=0.0001]
Steps:  26%|██▌       | 521/2000 [15:38<42:13,  1.71s/it, loss=0.184, lr=0.0001]
Steps:  26%|██▌       | 521/2000 [15:38<42:13,  1.71s/it, loss=0.128, lr=0.0001]
Steps:  26%|██▌       | 521/2000 [15:39<42:13,  1.71s/it, loss=0.14, lr=0.0001] 
Steps:  26%|██▌       | 521/2000 [15:39<42:13,  1.71s/it, loss=0.18, lr=0.0001]
Steps:  26%|██▌       | 522/2000 [15:40<41:34,  1.69s/it, loss=0.18, lr=0.0001]
Steps:  26%|██▌       | 522/2000 [15:40<41:34,  1.69s/it, loss=0.35, lr=0.0001]
Steps:  26%|██▌       | 522/2000 [15:40<41:34,  1.69s/it, loss=0.186, lr=0.0001]
Steps:  26%|██▌       | 522/2000 [15:41<41:34,  1.69s/it, loss=0.131, lr=0.0001]
Steps:  26%|██▌       | 522/2000 [15:41<41:34,  1.69s/it, loss=0.188, lr=0.0001]
Steps:  26%|██▌       | 523/2000 [15:42<42:54,  1.74s/it, loss=0.188, lr=0.0001]
Steps:  26%|██▌       | 523/2000 [15:42<42:54,  1.74s/it, loss=0.0877, lr=0.0001]
Steps:  26%|██▌       | 523/2000 [15:42<42:54,  1.74s/it, loss=0.117, lr=0.0001] 
Steps:  26%|██▌       | 523/2000 [15:42<42:54,  1.74s/it, loss=0.212, lr=0.0001]
Steps:  26%|██▌       | 523/2000 [15:43<42:54,  1.74s/it, loss=0.154, lr=0.0001]
Steps:  26%|██▌       | 524/2000 [15:43<42:02,  1.71s/it, loss=0.154, lr=0.0001]
Steps:  26%|██▌       | 524/2000 [15:43<42:02,  1.71s/it, loss=0.292, lr=0.0001]
Steps:  26%|██▌       | 524/2000 [15:44<42:02,  1.71s/it, loss=0.0893, lr=0.0001]
Steps:  26%|██▌       | 524/2000 [15:44<42:02,  1.71s/it, loss=0.787, lr=0.0001] 
Steps:  26%|██▌       | 524/2000 [15:44<42:02,  1.71s/it, loss=0.13, lr=0.0001] 
Steps:  26%|██▋       | 525/2000 [15:45<41:26,  1.69s/it, loss=0.13, lr=0.0001]
Steps:  26%|██▋       | 525/2000 [15:45<41:26,  1.69s/it, loss=0.168, lr=0.0001]
Steps:  26%|██▋       | 525/2000 [15:45<41:26,  1.69s/it, loss=0.235, lr=0.0001]
Steps:  26%|██▋       | 525/2000 [15:46<41:26,  1.69s/it, loss=0.177, lr=0.0001]
Steps:  26%|██▋       | 525/2000 [15:46<41:26,  1.69s/it, loss=0.232, lr=0.0001]
Steps:  26%|██▋       | 526/2000 [15:47<42:43,  1.74s/it, loss=0.232, lr=0.0001]
Steps:  26%|██▋       | 526/2000 [15:47<42:43,  1.74s/it, loss=0.151, lr=0.0001]
Steps:  26%|██▋       | 526/2000 [15:47<42:43,  1.74s/it, loss=0.186, lr=0.0001]
Steps:  26%|██▋       | 526/2000 [15:48<42:43,  1.74s/it, loss=0.129, lr=0.0001]
Steps:  26%|██▋       | 526/2000 [15:48<42:43,  1.74s/it, loss=0.103, lr=0.0001]
Steps:  26%|██▋       | 527/2000 [15:48<41:54,  1.71s/it, loss=0.103, lr=0.0001]
Steps:  26%|██▋       | 527/2000 [15:48<41:54,  1.71s/it, loss=0.599, lr=0.0001]
Steps:  26%|██▋       | 527/2000 [15:49<41:54,  1.71s/it, loss=0.164, lr=0.0001]
Steps:  26%|██▋       | 527/2000 [15:49<41:54,  1.71s/it, loss=0.189, lr=0.0001]
Steps:  26%|██▋       | 527/2000 [15:50<41:54,  1.71s/it, loss=0.404, lr=0.0001]
Steps:  26%|██▋       | 528/2000 [15:50<41:23,  1.69s/it, loss=0.404, lr=0.0001]
Steps:  26%|██▋       | 528/2000 [15:50<41:23,  1.69s/it, loss=0.12, lr=0.0001] 
Steps:  26%|██▋       | 528/2000 [15:50<41:23,  1.69s/it, loss=0.323, lr=0.0001]
Steps:  26%|██▋       | 528/2000 [15:51<41:23,  1.69s/it, loss=0.158, lr=0.0001]
Steps:  26%|██▋       | 528/2000 [15:51<41:23,  1.69s/it, loss=0.445, lr=0.0001]
Steps:  26%|██▋       | 529/2000 [15:52<42:41,  1.74s/it, loss=0.445, lr=0.0001]
Steps:  26%|██▋       | 529/2000 [15:52<42:41,  1.74s/it, loss=0.189, lr=0.0001]
Steps:  26%|██▋       | 529/2000 [15:52<42:41,  1.74s/it, loss=0.0229, lr=0.0001]
Steps:  26%|██▋       | 529/2000 [15:53<42:41,  1.74s/it, loss=0.182, lr=0.0001] 
Steps:  26%|██▋       | 529/2000 [15:53<42:41,  1.74s/it, loss=0.274, lr=0.0001]
Steps:  26%|██▋       | 530/2000 [15:54<42:05,  1.72s/it, loss=0.274, lr=0.0001]
Steps:  26%|██▋       | 530/2000 [15:54<42:05,  1.72s/it, loss=0.162, lr=0.0001]
Steps:  26%|██▋       | 530/2000 [15:54<42:05,  1.72s/it, loss=0.128, lr=0.0001]
Steps:  26%|██▋       | 530/2000 [15:54<42:05,  1.72s/it, loss=0.657, lr=0.0001]
Steps:  26%|██▋       | 530/2000 [15:55<42:05,  1.72s/it, loss=0.237, lr=0.0001]
Steps:  27%|██▋       | 531/2000 [15:55<41:25,  1.69s/it, loss=0.237, lr=0.0001]
Steps:  27%|██▋       | 531/2000 [15:55<41:25,  1.69s/it, loss=0.215, lr=0.0001]
Steps:  27%|██▋       | 531/2000 [15:56<41:25,  1.69s/it, loss=0.248, lr=0.0001]
Steps:  27%|██▋       | 531/2000 [15:56<41:25,  1.69s/it, loss=0.112, lr=0.0001]
Steps:  27%|██▋       | 531/2000 [15:56<41:25,  1.69s/it, loss=0.245, lr=0.0001]
Steps:  27%|██▋       | 532/2000 [15:57<42:47,  1.75s/it, loss=0.245, lr=0.0001]
Steps:  27%|██▋       | 532/2000 [15:57<42:47,  1.75s/it, loss=0.194, lr=0.0001]
Steps:  27%|██▋       | 532/2000 [15:57<42:47,  1.75s/it, loss=0.19, lr=0.0001] 
Steps:  27%|██▋       | 532/2000 [15:58<42:47,  1.75s/it, loss=0.134, lr=0.0001]
Steps:  27%|██▋       | 532/2000 [15:58<42:47,  1.75s/it, loss=0.219, lr=0.0001]
Steps:  27%|██▋       | 533/2000 [15:59<41:51,  1.71s/it, loss=0.219, lr=0.0001]
Steps:  27%|██▋       | 533/2000 [15:59<41:51,  1.71s/it, loss=0.193, lr=0.0001]
Steps:  27%|██▋       | 533/2000 [15:59<41:51,  1.71s/it, loss=0.0863, lr=0.0001]
Steps:  27%|██▋       | 533/2000 [15:59<41:51,  1.71s/it, loss=0.132, lr=0.0001] 
Steps:  27%|██▋       | 533/2000 [16:00<41:51,  1.71s/it, loss=0.182, lr=0.0001]
Steps:  27%|██▋       | 534/2000 [16:00<41:12,  1.69s/it, loss=0.182, lr=0.0001]
Steps:  27%|██▋       | 534/2000 [16:00<41:12,  1.69s/it, loss=0.236, lr=0.0001]
Steps:  27%|██▋       | 534/2000 [16:01<41:12,  1.69s/it, loss=0.193, lr=0.0001]
Steps:  27%|██▋       | 534/2000 [16:01<41:12,  1.69s/it, loss=0.292, lr=0.0001]
Steps:  27%|██▋       | 534/2000 [16:01<41:12,  1.69s/it, loss=0.845, lr=0.0001]
Steps:  27%|██▋       | 535/2000 [16:02<41:00,  1.68s/it, loss=0.845, lr=0.0001]
Steps:  27%|██▋       | 535/2000 [16:02<41:00,  1.68s/it, loss=0.985, lr=0.0001]
Steps:  27%|██▋       | 535/2000 [16:03<41:00,  1.68s/it, loss=0.334, lr=0.0001]
Steps:  27%|██▋       | 535/2000 [16:03<41:00,  1.68s/it, loss=0.379, lr=0.0001]
Steps:  27%|██▋       | 535/2000 [16:03<41:00,  1.68s/it, loss=0.388, lr=0.0001]
Steps:  27%|██▋       | 536/2000 [16:04<42:26,  1.74s/it, loss=0.388, lr=0.0001]
Steps:  27%|██▋       | 536/2000 [16:04<42:26,  1.74s/it, loss=0.209, lr=0.0001]
Steps:  27%|██▋       | 536/2000 [16:04<42:26,  1.74s/it, loss=0.439, lr=0.0001]
Steps:  27%|██▋       | 536/2000 [16:05<42:26,  1.74s/it, loss=0.824, lr=0.0001]
Steps:  27%|██▋       | 536/2000 [16:05<42:26,  1.74s/it, loss=0.371, lr=0.0001]
Steps:  27%|██▋       | 537/2000 [16:05<41:37,  1.71s/it, loss=0.371, lr=0.0001]
Steps:  27%|██▋       | 537/2000 [16:05<41:37,  1.71s/it, loss=0.118, lr=0.0001]
Steps:  27%|██▋       | 537/2000 [16:06<41:37,  1.71s/it, loss=0.15, lr=0.0001] 
Steps:  27%|██▋       | 537/2000 [16:06<41:37,  1.71s/it, loss=0.218, lr=0.0001]
Steps:  27%|██▋       | 537/2000 [16:07<41:37,  1.71s/it, loss=0.191, lr=0.0001]
Steps:  27%|██▋       | 538/2000 [16:07<41:26,  1.70s/it, loss=0.191, lr=0.0001]
Steps:  27%|██▋       | 538/2000 [16:07<41:26,  1.70s/it, loss=0.263, lr=0.0001]
Steps:  27%|██▋       | 538/2000 [16:08<41:26,  1.70s/it, loss=0.102, lr=0.0001]
Steps:  27%|██▋       | 538/2000 [16:08<41:26,  1.70s/it, loss=0.741, lr=0.0001]
Steps:  27%|██▋       | 538/2000 [16:09<41:26,  1.70s/it, loss=0.663, lr=0.0001]
Steps:  27%|██▋       | 539/2000 [16:09<42:51,  1.76s/it, loss=0.663, lr=0.0001]
Steps:  27%|██▋       | 539/2000 [16:09<42:51,  1.76s/it, loss=0.128, lr=0.0001]
Steps:  27%|██▋       | 539/2000 [16:09<42:51,  1.76s/it, loss=0.237, lr=0.0001]
Steps:  27%|██▋       | 539/2000 [16:10<42:51,  1.76s/it, loss=0.157, lr=0.0001]
Steps:  27%|██▋       | 539/2000 [16:10<42:51,  1.76s/it, loss=0.613, lr=0.0001]
Steps:  27%|██▋       | 540/2000 [16:11<41:51,  1.72s/it, loss=0.613, lr=0.0001]
Steps:  27%|██▋       | 540/2000 [16:11<41:51,  1.72s/it, loss=0.155, lr=0.0001]
Steps:  27%|██▋       | 540/2000 [16:11<41:51,  1.72s/it, loss=0.286, lr=0.0001]
Steps:  27%|██▋       | 540/2000 [16:11<41:51,  1.72s/it, loss=0.186, lr=0.0001]
Steps:  27%|██▋       | 540/2000 [16:12<41:51,  1.72s/it, loss=0.209, lr=0.0001]
Steps:  27%|██▋       | 541/2000 [16:12<41:07,  1.69s/it, loss=0.209, lr=0.0001]
Steps:  27%|██▋       | 541/2000 [16:12<41:07,  1.69s/it, loss=0.16, lr=0.0001] 
Steps:  27%|██▋       | 541/2000 [16:13<41:07,  1.69s/it, loss=0.179, lr=0.0001]
Steps:  27%|██▋       | 541/2000 [16:13<41:07,  1.69s/it, loss=0.232, lr=0.0001]
Steps:  27%|██▋       | 541/2000 [16:14<41:07,  1.69s/it, loss=0.114, lr=0.0001]
Steps:  27%|██▋       | 542/2000 [16:14<42:20,  1.74s/it, loss=0.114, lr=0.0001]
Steps:  27%|██▋       | 542/2000 [16:14<42:20,  1.74s/it, loss=0.27, lr=0.0001] 
Steps:  27%|██▋       | 542/2000 [16:15<42:20,  1.74s/it, loss=0.121, lr=0.0001]
Steps:  27%|██▋       | 542/2000 [16:15<42:20,  1.74s/it, loss=2.29, lr=0.0001] 
Steps:  27%|██▋       | 542/2000 [16:15<42:20,  1.74s/it, loss=0.177, lr=0.0001]
Steps:  27%|██▋       | 543/2000 [16:16<41:39,  1.72s/it, loss=0.177, lr=0.0001]
Steps:  27%|██▋       | 543/2000 [16:16<41:39,  1.72s/it, loss=0.0995, lr=0.0001]
Steps:  27%|██▋       | 543/2000 [16:16<41:39,  1.72s/it, loss=0.0742, lr=0.0001]
Steps:  27%|██▋       | 543/2000 [16:17<41:39,  1.72s/it, loss=0.968, lr=0.0001] 
Steps:  27%|██▋       | 543/2000 [16:17<41:39,  1.72s/it, loss=0.18, lr=0.0001] 
Steps:  27%|██▋       | 544/2000 [16:17<41:20,  1.70s/it, loss=0.18, lr=0.0001]
Steps:  27%|██▋       | 544/2000 [16:17<41:20,  1.70s/it, loss=0.165, lr=0.0001]
Steps:  27%|██▋       | 544/2000 [16:18<41:20,  1.70s/it, loss=0.361, lr=0.0001]
Steps:  27%|██▋       | 544/2000 [16:18<41:20,  1.70s/it, loss=0.408, lr=0.0001]
Steps:  27%|██▋       | 544/2000 [16:19<41:20,  1.70s/it, loss=0.578, lr=0.0001]
Steps:  27%|██▋       | 545/2000 [16:19<42:38,  1.76s/it, loss=0.578, lr=0.0001]
Steps:  27%|██▋       | 545/2000 [16:19<42:38,  1.76s/it, loss=0.134, lr=0.0001]
Steps:  27%|██▋       | 545/2000 [16:20<42:38,  1.76s/it, loss=0.281, lr=0.0001]
Steps:  27%|██▋       | 545/2000 [16:20<42:38,  1.76s/it, loss=0.14, lr=0.0001] 
Steps:  27%|██▋       | 545/2000 [16:21<42:38,  1.76s/it, loss=0.158, lr=0.0001]
Steps:  27%|██▋       | 546/2000 [16:21<42:10,  1.74s/it, loss=0.158, lr=0.0001]
Steps:  27%|██▋       | 546/2000 [16:21<42:10,  1.74s/it, loss=0.165, lr=0.0001]
Steps:  27%|██▋       | 546/2000 [16:21<42:10,  1.74s/it, loss=0.128, lr=0.0001]
Steps:  27%|██▋       | 546/2000 [16:22<42:10,  1.74s/it, loss=0.108, lr=0.0001]
Steps:  27%|██▋       | 546/2000 [16:22<42:10,  1.74s/it, loss=0.337, lr=0.0001]
Steps:  27%|██▋       | 547/2000 [16:23<41:39,  1.72s/it, loss=0.337, lr=0.0001]
Steps:  27%|██▋       | 547/2000 [16:23<41:39,  1.72s/it, loss=0.0994, lr=0.0001]
Steps:  27%|██▋       | 547/2000 [16:23<41:39,  1.72s/it, loss=0.161, lr=0.0001] 
Steps:  27%|██▋       | 547/2000 [16:24<41:39,  1.72s/it, loss=0.641, lr=0.0001]
Steps:  27%|██▋       | 547/2000 [16:24<41:39,  1.72s/it, loss=0.187, lr=0.0001]
Steps:  27%|██▋       | 548/2000 [16:25<42:53,  1.77s/it, loss=0.187, lr=0.0001]
Steps:  27%|██▋       | 548/2000 [16:25<42:53,  1.77s/it, loss=0.279, lr=0.0001]
Steps:  27%|██▋       | 548/2000 [16:25<42:53,  1.77s/it, loss=0.198, lr=0.0001]
Steps:  27%|██▋       | 548/2000 [16:25<42:53,  1.77s/it, loss=0.461, lr=0.0001]
Steps:  27%|██▋       | 548/2000 [16:26<42:53,  1.77s/it, loss=0.215, lr=0.0001]
Steps:  27%|██▋       | 549/2000 [16:26<41:57,  1.74s/it, loss=0.215, lr=0.0001]
Steps:  27%|██▋       | 549/2000 [16:26<41:57,  1.74s/it, loss=0.173, lr=0.0001]
Steps:  27%|██▋       | 549/2000 [16:27<41:57,  1.74s/it, loss=0.324, lr=0.0001]
Steps:  27%|██▋       | 549/2000 [16:27<41:57,  1.74s/it, loss=0.131, lr=0.0001]
Steps:  27%|██▋       | 549/2000 [16:27<41:57,  1.74s/it, loss=0.101, lr=0.0001]
Steps:  28%|██▊       | 550/2000 [16:28<41:15,  1.71s/it, loss=0.101, lr=0.0001]
Steps:  28%|██▊       | 550/2000 [16:28<41:15,  1.71s/it, loss=0.247, lr=0.0001]
Steps:  28%|██▊       | 550/2000 [16:28<41:15,  1.71s/it, loss=0.152, lr=0.0001]
Steps:  28%|██▊       | 550/2000 [16:29<41:15,  1.71s/it, loss=0.0781, lr=0.0001]
Steps:  28%|██▊       | 550/2000 [16:29<41:15,  1.71s/it, loss=0.19, lr=0.0001]  
Steps:  28%|██▊       | 551/2000 [16:30<40:49,  1.69s/it, loss=0.19, lr=0.0001]
Steps:  28%|██▊       | 551/2000 [16:30<40:49,  1.69s/it, loss=0.184, lr=0.0001]
Steps:  28%|██▊       | 551/2000 [16:30<40:49,  1.69s/it, loss=0.139, lr=0.0001]
Steps:  28%|██▊       | 551/2000 [16:31<40:49,  1.69s/it, loss=0.22, lr=0.0001] 
Steps:  28%|██▊       | 551/2000 [16:31<40:49,  1.69s/it, loss=0.374, lr=0.0001]
Steps:  28%|██▊       | 552/2000 [16:31<42:02,  1.74s/it, loss=0.374, lr=0.0001]
Steps:  28%|██▊       | 552/2000 [16:31<42:02,  1.74s/it, loss=0.104, lr=0.0001]
Steps:  28%|██▊       | 552/2000 [16:32<42:02,  1.74s/it, loss=0.188, lr=0.0001]
Steps:  28%|██▊       | 552/2000 [16:32<42:02,  1.74s/it, loss=0.168, lr=0.0001]
Steps:  28%|██▊       | 552/2000 [16:33<42:02,  1.74s/it, loss=0.424, lr=0.0001]
Steps:  28%|██▊       | 553/2000 [16:33<41:17,  1.71s/it, loss=0.424, lr=0.0001]
Steps:  28%|██▊       | 553/2000 [16:33<41:17,  1.71s/it, loss=0.0629, lr=0.0001]
Steps:  28%|██▊       | 553/2000 [16:33<41:17,  1.71s/it, loss=0.0854, lr=0.0001]
Steps:  28%|██▊       | 553/2000 [16:34<41:17,  1.71s/it, loss=0.157, lr=0.0001] 
Steps:  28%|██▊       | 553/2000 [16:34<41:17,  1.71s/it, loss=0.209, lr=0.0001]
Steps:  28%|██▊       | 554/2000 [16:35<40:48,  1.69s/it, loss=0.209, lr=0.0001]
Steps:  28%|██▊       | 554/2000 [16:35<40:48,  1.69s/it, loss=0.148, lr=0.0001]
Steps:  28%|██▊       | 554/2000 [16:35<40:48,  1.69s/it, loss=0.0875, lr=0.0001]
Steps:  28%|██▊       | 554/2000 [16:36<40:48,  1.69s/it, loss=0.218, lr=0.0001] 
Steps:  28%|██▊       | 554/2000 [16:36<40:48,  1.69s/it, loss=0.183, lr=0.0001]
Steps:  28%|██▊       | 555/2000 [16:37<42:01,  1.75s/it, loss=0.183, lr=0.0001]
Steps:  28%|██▊       | 555/2000 [16:37<42:01,  1.75s/it, loss=0.0672, lr=0.0001]
Steps:  28%|██▊       | 555/2000 [16:37<42:01,  1.75s/it, loss=0.243, lr=0.0001] 
Steps:  28%|██▊       | 555/2000 [16:37<42:01,  1.75s/it, loss=0.289, lr=0.0001]
Steps:  28%|██▊       | 555/2000 [16:38<42:01,  1.75s/it, loss=0.0631, lr=0.0001]
Steps:  28%|██▊       | 556/2000 [16:38<41:53,  1.74s/it, loss=0.0631, lr=0.0001]
Steps:  28%|██▊       | 556/2000 [16:38<41:53,  1.74s/it, loss=0.15, lr=0.0001]  
Steps:  28%|██▊       | 556/2000 [16:39<41:53,  1.74s/it, loss=0.189, lr=0.0001]
Steps:  28%|██▊       | 556/2000 [16:39<41:53,  1.74s/it, loss=0.264, lr=0.0001]
Steps:  28%|██▊       | 556/2000 [16:40<41:53,  1.74s/it, loss=0.22, lr=0.0001] 
Steps:  28%|██▊       | 557/2000 [16:40<41:06,  1.71s/it, loss=0.22, lr=0.0001]
Steps:  28%|██▊       | 557/2000 [16:40<41:06,  1.71s/it, loss=0.313, lr=0.0001]
Steps:  28%|██▊       | 557/2000 [16:40<41:06,  1.71s/it, loss=0.151, lr=0.0001]
Steps:  28%|██▊       | 557/2000 [16:41<41:06,  1.71s/it, loss=0.252, lr=0.0001]
Steps:  28%|██▊       | 557/2000 [16:41<41:06,  1.71s/it, loss=0.0716, lr=0.0001]
Steps:  28%|██▊       | 558/2000 [16:42<42:11,  1.76s/it, loss=0.0716, lr=0.0001]
Steps:  28%|██▊       | 558/2000 [16:42<42:11,  1.76s/it, loss=0.249, lr=0.0001] 
Steps:  28%|██▊       | 558/2000 [16:42<42:11,  1.76s/it, loss=0.112, lr=0.0001]
Steps:  28%|██▊       | 558/2000 [16:43<42:11,  1.76s/it, loss=0.0739, lr=0.0001]
Steps:  28%|██▊       | 558/2000 [16:43<42:11,  1.76s/it, loss=0.167, lr=0.0001] 
Steps:  28%|██▊       | 559/2000 [16:43<41:22,  1.72s/it, loss=0.167, lr=0.0001]
Steps:  28%|██▊       | 559/2000 [16:43<41:22,  1.72s/it, loss=0.16, lr=0.0001] 
Steps:  28%|██▊       | 559/2000 [16:44<41:22,  1.72s/it, loss=0.234, lr=0.0001]
Steps:  28%|██▊       | 559/2000 [16:44<41:22,  1.72s/it, loss=0.245, lr=0.0001]
Steps:  28%|██▊       | 559/2000 [16:45<41:22,  1.72s/it, loss=0.15, lr=0.0001] 
Steps:  28%|██▊       | 560/2000 [16:45<41:05,  1.71s/it, loss=0.15, lr=0.0001]
Steps:  28%|██▊       | 560/2000 [16:45<41:05,  1.71s/it, loss=0.18, lr=0.0001]
Steps:  28%|██▊       | 560/2000 [16:46<41:05,  1.71s/it, loss=0.447, lr=0.0001]
Steps:  28%|██▊       | 560/2000 [16:46<41:05,  1.71s/it, loss=0.219, lr=0.0001]
Steps:  28%|██▊       | 560/2000 [16:47<41:05,  1.71s/it, loss=0.271, lr=0.0001]
Steps:  28%|██▊       | 561/2000 [16:47<42:50,  1.79s/it, loss=0.271, lr=0.0001]
Steps:  28%|██▊       | 561/2000 [16:47<42:50,  1.79s/it, loss=0.22, lr=0.0001] 
Steps:  28%|██▊       | 561/2000 [16:48<42:50,  1.79s/it, loss=0.228, lr=0.0001]
Steps:  28%|██▊       | 561/2000 [16:48<42:50,  1.79s/it, loss=0.372, lr=0.0001]
Steps:  28%|██▊       | 561/2000 [16:48<42:50,  1.79s/it, loss=0.295, lr=0.0001]
Steps:  28%|██▊       | 562/2000 [16:49<42:21,  1.77s/it, loss=0.295, lr=0.0001]
Steps:  28%|██▊       | 562/2000 [16:49<42:21,  1.77s/it, loss=0.0858, lr=0.0001]
Steps:  28%|██▊       | 562/2000 [16:49<42:21,  1.77s/it, loss=0.0829, lr=0.0001]
Steps:  28%|██▊       | 562/2000 [16:50<42:21,  1.77s/it, loss=0.141, lr=0.0001] 
Steps:  28%|██▊       | 562/2000 [16:50<42:21,  1.77s/it, loss=0.0693, lr=0.0001]
Steps:  28%|██▊       | 563/2000 [16:51<41:53,  1.75s/it, loss=0.0693, lr=0.0001]
Steps:  28%|██▊       | 563/2000 [16:51<41:53,  1.75s/it, loss=0.172, lr=0.0001] 
Steps:  28%|██▊       | 563/2000 [16:51<41:53,  1.75s/it, loss=0.241, lr=0.0001]
Steps:  28%|██▊       | 563/2000 [16:51<41:53,  1.75s/it, loss=0.573, lr=0.0001]
Steps:  28%|██▊       | 563/2000 [16:52<41:53,  1.75s/it, loss=0.153, lr=0.0001]
Steps:  28%|██▊       | 564/2000 [16:52<42:51,  1.79s/it, loss=0.153, lr=0.0001]
Steps:  28%|██▊       | 564/2000 [16:52<42:51,  1.79s/it, loss=0.132, lr=0.0001]
Steps:  28%|██▊       | 564/2000 [16:53<42:51,  1.79s/it, loss=0.124, lr=0.0001]
Steps:  28%|██▊       | 564/2000 [16:53<42:51,  1.79s/it, loss=0.128, lr=0.0001]
Steps:  28%|██▊       | 564/2000 [16:54<42:51,  1.79s/it, loss=0.362, lr=0.0001]
Steps:  28%|██▊       | 565/2000 [16:54<42:19,  1.77s/it, loss=0.362, lr=0.0001]
Steps:  28%|██▊       | 565/2000 [16:54<42:19,  1.77s/it, loss=0.143, lr=0.0001]
Steps:  28%|██▊       | 565/2000 [16:55<42:19,  1.77s/it, loss=0.209, lr=0.0001]
Steps:  28%|██▊       | 565/2000 [16:55<42:19,  1.77s/it, loss=0.188, lr=0.0001]
Steps:  28%|██▊       | 565/2000 [16:55<42:19,  1.77s/it, loss=0.301, lr=0.0001]
Steps:  28%|██▊       | 566/2000 [16:56<42:06,  1.76s/it, loss=0.301, lr=0.0001]
Steps:  28%|██▊       | 566/2000 [16:56<42:06,  1.76s/it, loss=0.358, lr=0.0001]
Steps:  28%|██▊       | 566/2000 [16:56<42:06,  1.76s/it, loss=0.165, lr=0.0001]
Steps:  28%|██▊       | 566/2000 [16:57<42:06,  1.76s/it, loss=0.134, lr=0.0001]
Steps:  28%|██▊       | 566/2000 [16:57<42:06,  1.76s/it, loss=1.09, lr=0.0001] 
Steps:  28%|██▊       | 567/2000 [16:58<43:34,  1.82s/it, loss=1.09, lr=0.0001]
Steps:  28%|██▊       | 567/2000 [16:58<43:34,  1.82s/it, loss=0.194, lr=0.0001]
Steps:  28%|██▊       | 567/2000 [16:58<43:34,  1.82s/it, loss=0.0876, lr=0.0001]
Steps:  28%|██▊       | 567/2000 [16:59<43:34,  1.82s/it, loss=0.214, lr=0.0001] 
Steps:  28%|██▊       | 567/2000 [16:59<43:34,  1.82s/it, loss=0.126, lr=0.0001]
Steps:  28%|██▊       | 568/2000 [17:00<43:05,  1.81s/it, loss=0.126, lr=0.0001]
Steps:  28%|██▊       | 568/2000 [17:00<43:05,  1.81s/it, loss=0.166, lr=0.0001]
Steps:  28%|██▊       | 568/2000 [17:00<43:05,  1.81s/it, loss=0.164, lr=0.0001]
Steps:  28%|██▊       | 568/2000 [17:00<43:05,  1.81s/it, loss=0.142, lr=0.0001]
Steps:  28%|██▊       | 568/2000 [17:01<43:05,  1.81s/it, loss=0.255, lr=0.0001]
Steps:  28%|██▊       | 569/2000 [17:01<42:28,  1.78s/it, loss=0.255, lr=0.0001]
Steps:  28%|██▊       | 569/2000 [17:01<42:28,  1.78s/it, loss=0.214, lr=0.0001]
Steps:  28%|██▊       | 569/2000 [17:02<42:28,  1.78s/it, loss=0.21, lr=0.0001] 
Steps:  28%|██▊       | 569/2000 [17:02<42:28,  1.78s/it, loss=0.14, lr=0.0001]
Steps:  28%|██▊       | 569/2000 [17:03<42:28,  1.78s/it, loss=0.313, lr=0.0001]
Steps:  28%|██▊       | 570/2000 [17:03<41:46,  1.75s/it, loss=0.313, lr=0.0001]
Steps:  28%|██▊       | 570/2000 [17:03<41:46,  1.75s/it, loss=0.0778, lr=0.0001]
Steps:  28%|██▊       | 570/2000 [17:04<41:46,  1.75s/it, loss=0.236, lr=0.0001] 
Steps:  28%|██▊       | 570/2000 [17:04<41:46,  1.75s/it, loss=0.19, lr=0.0001] 
Steps:  28%|██▊       | 570/2000 [17:05<41:46,  1.75s/it, loss=0.172, lr=0.0001]
Steps:  29%|██▊       | 571/2000 [17:05<43:04,  1.81s/it, loss=0.172, lr=0.0001]
Steps:  29%|██▊       | 571/2000 [17:05<43:04,  1.81s/it, loss=0.23, lr=0.0001] 
Steps:  29%|██▊       | 571/2000 [17:05<43:04,  1.81s/it, loss=0.247, lr=0.0001]
Steps:  29%|██▊       | 571/2000 [17:06<43:04,  1.81s/it, loss=0.197, lr=0.0001]
Steps:  29%|██▊       | 571/2000 [17:06<43:04,  1.81s/it, loss=0.0671, lr=0.0001]
Steps:  29%|██▊       | 572/2000 [17:07<42:05,  1.77s/it, loss=0.0671, lr=0.0001]
Steps:  29%|██▊       | 572/2000 [17:07<42:05,  1.77s/it, loss=0.198, lr=0.0001] 
Steps:  29%|██▊       | 572/2000 [17:07<42:05,  1.77s/it, loss=0.181, lr=0.0001]
Steps:  29%|██▊       | 572/2000 [17:07<42:05,  1.77s/it, loss=0.258, lr=0.0001]
Steps:  29%|██▊       | 572/2000 [17:08<42:05,  1.77s/it, loss=0.173, lr=0.0001]
Steps:  29%|██▊       | 573/2000 [17:08<41:29,  1.74s/it, loss=0.173, lr=0.0001]
Steps:  29%|██▊       | 573/2000 [17:08<41:29,  1.74s/it, loss=0.173, lr=0.0001]
Steps:  29%|██▊       | 573/2000 [17:09<41:29,  1.74s/it, loss=0.175, lr=0.0001]
Steps:  29%|██▊       | 573/2000 [17:09<41:29,  1.74s/it, loss=0.325, lr=0.0001]
Steps:  29%|██▊       | 573/2000 [17:10<41:29,  1.74s/it, loss=0.181, lr=0.0001]
Steps:  29%|██▊       | 574/2000 [17:10<42:33,  1.79s/it, loss=0.181, lr=0.0001]
Steps:  29%|██▊       | 574/2000 [17:10<42:33,  1.79s/it, loss=0.17, lr=0.0001] 
Steps:  29%|██▊       | 574/2000 [17:11<42:33,  1.79s/it, loss=0.177, lr=0.0001]
Steps:  29%|██▊       | 574/2000 [17:11<42:33,  1.79s/it, loss=0.282, lr=0.0001]
Steps:  29%|██▊       | 574/2000 [17:11<42:33,  1.79s/it, loss=0.135, lr=0.0001]
Steps:  29%|██▉       | 575/2000 [17:12<41:40,  1.76s/it, loss=0.135, lr=0.0001]
Steps:  29%|██▉       | 575/2000 [17:12<41:40,  1.76s/it, loss=0.101, lr=0.0001]
Steps:  29%|██▉       | 575/2000 [17:12<41:40,  1.76s/it, loss=0.174, lr=0.0001]
Steps:  29%|██▉       | 575/2000 [17:13<41:40,  1.76s/it, loss=0.187, lr=0.0001]
Steps:  29%|██▉       | 575/2000 [17:13<41:40,  1.76s/it, loss=0.154, lr=0.0001]
Steps:  29%|██▉       | 576/2000 [17:14<40:58,  1.73s/it, loss=0.154, lr=0.0001]
Steps:  29%|██▉       | 576/2000 [17:14<40:58,  1.73s/it, loss=0.174, lr=0.0001]
Steps:  29%|██▉       | 576/2000 [17:14<40:58,  1.73s/it, loss=0.202, lr=0.0001]
Steps:  29%|██▉       | 576/2000 [17:15<40:58,  1.73s/it, loss=0.473, lr=0.0001]
Steps:  29%|██▉       | 576/2000 [17:15<40:58,  1.73s/it, loss=0.356, lr=0.0001]
Steps:  29%|██▉       | 577/2000 [17:15<42:08,  1.78s/it, loss=0.356, lr=0.0001]
Steps:  29%|██▉       | 577/2000 [17:15<42:08,  1.78s/it, loss=0.409, lr=0.0001]
Steps:  29%|██▉       | 577/2000 [17:16<42:08,  1.78s/it, loss=0.156, lr=0.0001]
Steps:  29%|██▉       | 577/2000 [17:16<42:08,  1.78s/it, loss=0.133, lr=0.0001]
Steps:  29%|██▉       | 577/2000 [17:17<42:08,  1.78s/it, loss=0.228, lr=0.0001]
Steps:  29%|██▉       | 578/2000 [17:17<41:29,  1.75s/it, loss=0.228, lr=0.0001]
Steps:  29%|██▉       | 578/2000 [17:17<41:29,  1.75s/it, loss=0.114, lr=0.0001]
Steps:  29%|██▉       | 578/2000 [17:18<41:29,  1.75s/it, loss=0.733, lr=0.0001]
Steps:  29%|██▉       | 578/2000 [17:18<41:29,  1.75s/it, loss=0.145, lr=0.0001]
Steps:  29%|██▉       | 578/2000 [17:18<41:29,  1.75s/it, loss=0.221, lr=0.0001]
Steps:  29%|██▉       | 579/2000 [17:19<40:44,  1.72s/it, loss=0.221, lr=0.0001]
Steps:  29%|██▉       | 579/2000 [17:19<40:44,  1.72s/it, loss=0.164, lr=0.0001]
Steps:  29%|██▉       | 579/2000 [17:19<40:44,  1.72s/it, loss=0.188, lr=0.0001]
Steps:  29%|██▉       | 579/2000 [17:20<40:44,  1.72s/it, loss=0.259, lr=0.0001]
Steps:  29%|██▉       | 579/2000 [17:20<40:44,  1.72s/it, loss=0.21, lr=0.0001] 
Steps:  29%|██▉       | 580/2000 [17:21<41:41,  1.76s/it, loss=0.21, lr=0.0001]
Steps:  29%|██▉       | 580/2000 [17:21<41:41,  1.76s/it, loss=0.148, lr=0.0001]
Steps:  29%|██▉       | 580/2000 [17:21<41:41,  1.76s/it, loss=0.222, lr=0.0001]
Steps:  29%|██▉       | 580/2000 [17:21<41:41,  1.76s/it, loss=0.0917, lr=0.0001]
Steps:  29%|██▉       | 580/2000 [17:22<41:41,  1.76s/it, loss=0.163, lr=0.0001] 
Steps:  29%|██▉       | 581/2000 [17:22<40:44,  1.72s/it, loss=0.163, lr=0.0001]
Steps:  29%|██▉       | 581/2000 [17:22<40:44,  1.72s/it, loss=0.143, lr=0.0001]
Steps:  29%|██▉       | 581/2000 [17:23<40:44,  1.72s/it, loss=0.344, lr=0.0001]
Steps:  29%|██▉       | 581/2000 [17:23<40:44,  1.72s/it, loss=0.149, lr=0.0001]
Steps:  29%|██▉       | 581/2000 [17:23<40:44,  1.72s/it, loss=0.191, lr=0.0001]
Steps:  29%|██▉       | 582/2000 [17:24<40:03,  1.69s/it, loss=0.191, lr=0.0001]
Steps:  29%|██▉       | 582/2000 [17:24<40:03,  1.69s/it, loss=0.195, lr=0.0001]
Steps:  29%|██▉       | 582/2000 [17:24<40:03,  1.69s/it, loss=0.244, lr=0.0001]
Steps:  29%|██▉       | 582/2000 [17:25<40:03,  1.69s/it, loss=0.111, lr=0.0001]
Steps:  29%|██▉       | 582/2000 [17:25<40:03,  1.69s/it, loss=0.191, lr=0.0001]
Steps:  29%|██▉       | 583/2000 [17:26<41:11,  1.74s/it, loss=0.191, lr=0.0001]
Steps:  29%|██▉       | 583/2000 [17:26<41:11,  1.74s/it, loss=0.0931, lr=0.0001]
Steps:  29%|██▉       | 583/2000 [17:26<41:11,  1.74s/it, loss=0.141, lr=0.0001] 
Steps:  29%|██▉       | 583/2000 [17:27<41:11,  1.74s/it, loss=0.252, lr=0.0001]
Steps:  29%|██▉       | 583/2000 [17:27<41:11,  1.74s/it, loss=0.19, lr=0.0001] 
Steps:  29%|██▉       | 584/2000 [17:27<40:21,  1.71s/it, loss=0.19, lr=0.0001]
Steps:  29%|██▉       | 584/2000 [17:27<40:21,  1.71s/it, loss=0.109, lr=0.0001]
Steps:  29%|██▉       | 584/2000 [17:28<40:21,  1.71s/it, loss=0.165, lr=0.0001]
Steps:  29%|██▉       | 584/2000 [17:28<40:21,  1.71s/it, loss=0.161, lr=0.0001]
Steps:  29%|██▉       | 584/2000 [17:29<40:21,  1.71s/it, loss=0.13, lr=0.0001] 
Steps:  29%|██▉       | 585/2000 [17:29<40:04,  1.70s/it, loss=0.13, lr=0.0001]
Steps:  29%|██▉       | 585/2000 [17:29<40:04,  1.70s/it, loss=0.203, lr=0.0001]
Steps:  29%|██▉       | 585/2000 [17:29<40:04,  1.70s/it, loss=0.158, lr=0.0001]
Steps:  29%|██▉       | 585/2000 [17:30<40:04,  1.70s/it, loss=0.201, lr=0.0001]
Steps:  29%|██▉       | 585/2000 [17:31<40:04,  1.70s/it, loss=0.156, lr=0.0001]
Steps:  29%|██▉       | 586/2000 [17:31<41:14,  1.75s/it, loss=0.156, lr=0.0001]
Steps:  29%|██▉       | 586/2000 [17:31<41:14,  1.75s/it, loss=0.139, lr=0.0001]
Steps:  29%|██▉       | 586/2000 [17:31<41:14,  1.75s/it, loss=0.236, lr=0.0001]
Steps:  29%|██▉       | 586/2000 [17:32<41:14,  1.75s/it, loss=0.162, lr=0.0001]
Steps:  29%|██▉       | 586/2000 [17:32<41:14,  1.75s/it, loss=0.241, lr=0.0001]
Steps:  29%|██▉       | 587/2000 [17:33<40:22,  1.71s/it, loss=0.241, lr=0.0001]
Steps:  29%|██▉       | 587/2000 [17:33<40:22,  1.71s/it, loss=0.135, lr=0.0001]
Steps:  29%|██▉       | 587/2000 [17:33<40:22,  1.71s/it, loss=0.0753, lr=0.0001]
Steps:  29%|██▉       | 587/2000 [17:34<40:22,  1.71s/it, loss=0.138, lr=0.0001] 
Steps:  29%|██▉       | 587/2000 [17:35<40:22,  1.71s/it, loss=0.216, lr=0.0001]
Steps:  29%|██▉       | 588/2000 [17:36<51:24,  2.18s/it, loss=0.216, lr=0.0001]
Steps:  29%|██▉       | 588/2000 [17:36<51:24,  2.18s/it, loss=0.534, lr=0.0001]
Steps:  29%|██▉       | 588/2000 [17:36<51:24,  2.18s/it, loss=0.241, lr=0.0001]
Steps:  29%|██▉       | 588/2000 [17:37<51:24,  2.18s/it, loss=0.141, lr=0.0001]
Steps:  29%|██▉       | 588/2000 [17:37<51:24,  2.18s/it, loss=0.109, lr=0.0001]
Steps:  29%|██▉       | 589/2000 [17:38<49:13,  2.09s/it, loss=0.109, lr=0.0001]
Steps:  29%|██▉       | 589/2000 [17:38<49:13,  2.09s/it, loss=0.176, lr=0.0001]
Steps:  29%|██▉       | 589/2000 [17:38<49:13,  2.09s/it, loss=0.125, lr=0.0001]
Steps:  29%|██▉       | 589/2000 [17:39<49:13,  2.09s/it, loss=0.084, lr=0.0001]
Steps:  29%|██▉       | 589/2000 [17:39<49:13,  2.09s/it, loss=0.135, lr=0.0001]
Steps:  30%|██▉       | 590/2000 [17:39<45:55,  1.95s/it, loss=0.135, lr=0.0001]
Steps:  30%|██▉       | 590/2000 [17:39<45:55,  1.95s/it, loss=0.0993, lr=0.0001]
Steps:  30%|██▉       | 590/2000 [17:40<45:55,  1.95s/it, loss=0.287, lr=0.0001] 
Steps:  30%|██▉       | 590/2000 [17:40<45:55,  1.95s/it, loss=0.152, lr=0.0001]
Steps:  30%|██▉       | 590/2000 [17:41<45:55,  1.95s/it, loss=0.0981, lr=0.0001]
Steps:  30%|██▉       | 591/2000 [17:41<43:42,  1.86s/it, loss=0.0981, lr=0.0001]
Steps:  30%|██▉       | 591/2000 [17:41<43:42,  1.86s/it, loss=0.188, lr=0.0001] 
Steps:  30%|██▉       | 591/2000 [17:41<43:42,  1.86s/it, loss=0.21, lr=0.0001] 
Steps:  30%|██▉       | 591/2000 [17:42<43:42,  1.86s/it, loss=0.206, lr=0.0001]
Steps:  30%|██▉       | 591/2000 [17:42<43:42,  1.86s/it, loss=0.425, lr=0.0001]
Steps:  30%|██▉       | 592/2000 [17:43<42:05,  1.79s/it, loss=0.425, lr=0.0001]
Steps:  30%|██▉       | 592/2000 [17:43<42:05,  1.79s/it, loss=0.0729, lr=0.0001]
Steps:  30%|██▉       | 592/2000 [17:43<42:05,  1.79s/it, loss=0.165, lr=0.0001] 
Steps:  30%|██▉       | 592/2000 [17:44<42:05,  1.79s/it, loss=0.169, lr=0.0001]
Steps:  30%|██▉       | 592/2000 [17:44<42:05,  1.79s/it, loss=0.153, lr=0.0001]
Steps:  30%|██▉       | 593/2000 [17:45<42:41,  1.82s/it, loss=0.153, lr=0.0001]
Steps:  30%|██▉       | 593/2000 [17:45<42:41,  1.82s/it, loss=0.25, lr=0.0001] 
Steps:  30%|██▉       | 593/2000 [17:45<42:41,  1.82s/it, loss=0.27, lr=0.0001]
Steps:  30%|██▉       | 593/2000 [17:45<42:41,  1.82s/it, loss=0.152, lr=0.0001]
Steps:  30%|██▉       | 593/2000 [17:46<42:41,  1.82s/it, loss=0.156, lr=0.0001]
Steps:  30%|██▉       | 594/2000 [17:46<41:22,  1.77s/it, loss=0.156, lr=0.0001]
Steps:  30%|██▉       | 594/2000 [17:46<41:22,  1.77s/it, loss=0.14, lr=0.0001] 
Steps:  30%|██▉       | 594/2000 [17:47<41:22,  1.77s/it, loss=0.219, lr=0.0001]
Steps:  30%|██▉       | 594/2000 [17:47<41:22,  1.77s/it, loss=0.143, lr=0.0001]
Steps:  30%|██▉       | 594/2000 [17:47<41:22,  1.77s/it, loss=0.117, lr=0.0001]
Steps:  30%|██▉       | 595/2000 [17:48<40:30,  1.73s/it, loss=0.117, lr=0.0001]
Steps:  30%|██▉       | 595/2000 [17:48<40:30,  1.73s/it, loss=0.0585, lr=0.0001]
Steps:  30%|██▉       | 595/2000 [17:48<40:30,  1.73s/it, loss=0.277, lr=0.0001] 
Steps:  30%|██▉       | 595/2000 [17:49<40:30,  1.73s/it, loss=0.272, lr=0.0001]
Steps:  30%|██▉       | 595/2000 [17:49<40:30,  1.73s/it, loss=0.02, lr=0.0001] 
Steps:  30%|██▉       | 596/2000 [17:50<41:32,  1.78s/it, loss=0.02, lr=0.0001]
Steps:  30%|██▉       | 596/2000 [17:50<41:32,  1.78s/it, loss=0.188, lr=0.0001]
Steps:  30%|██▉       | 596/2000 [17:50<41:32,  1.78s/it, loss=0.327, lr=0.0001]
Steps:  30%|██▉       | 596/2000 [17:51<41:32,  1.78s/it, loss=0.196, lr=0.0001]
Steps:  30%|██▉       | 596/2000 [17:51<41:32,  1.78s/it, loss=0.167, lr=0.0001]
Steps:  30%|██▉       | 597/2000 [17:51<40:32,  1.73s/it, loss=0.167, lr=0.0001]
Steps:  30%|██▉       | 597/2000 [17:51<40:32,  1.73s/it, loss=0.171, lr=0.0001]
Steps:  30%|██▉       | 597/2000 [17:52<40:32,  1.73s/it, loss=0.0937, lr=0.0001]
Steps:  30%|██▉       | 597/2000 [17:52<40:32,  1.73s/it, loss=0.131, lr=0.0001] 
Steps:  30%|██▉       | 597/2000 [17:53<40:32,  1.73s/it, loss=0.169, lr=0.0001]
Steps:  30%|██▉       | 598/2000 [17:53<40:00,  1.71s/it, loss=0.169, lr=0.0001]
Steps:  30%|██▉       | 598/2000 [17:53<40:00,  1.71s/it, loss=0.578, lr=0.0001]
Steps:  30%|██▉       | 598/2000 [17:53<40:00,  1.71s/it, loss=0.135, lr=0.0001]
Steps:  30%|██▉       | 598/2000 [17:54<40:00,  1.71s/it, loss=0.311, lr=0.0001]
Steps:  30%|██▉       | 598/2000 [17:55<40:00,  1.71s/it, loss=0.34, lr=0.0001] 
Steps:  30%|██▉       | 599/2000 [17:55<41:36,  1.78s/it, loss=0.34, lr=0.0001]
Steps:  30%|██▉       | 599/2000 [17:55<41:36,  1.78s/it, loss=0.164, lr=0.0001]
Steps:  30%|██▉       | 599/2000 [17:55<41:36,  1.78s/it, loss=0.292, lr=0.0001]
Steps:  30%|██▉       | 599/2000 [17:56<41:36,  1.78s/it, loss=0.297, lr=0.0001]
Steps:  30%|██▉       | 599/2000 [17:56<41:36,  1.78s/it, loss=0.28, lr=0.0001] 
Steps:  30%|███       | 600/2000 [17:57<40:37,  1.74s/it, loss=0.28, lr=0.0001]
Steps:  30%|███       | 600/2000 [17:57<40:37,  1.74s/it, loss=0.413, lr=0.0001]
Steps:  30%|███       | 600/2000 [17:57<40:37,  1.74s/it, loss=0.163, lr=0.0001]
Steps:  30%|███       | 600/2000 [17:57<40:37,  1.74s/it, loss=0.132, lr=0.0001]
Steps:  30%|███       | 600/2000 [17:58<40:37,  1.74s/it, loss=0.147, lr=0.0001]
Steps:  30%|███       | 601/2000 [17:58<39:57,  1.71s/it, loss=0.147, lr=0.0001]
Steps:  30%|███       | 601/2000 [17:58<39:57,  1.71s/it, loss=0.132, lr=0.0001]
Steps:  30%|███       | 601/2000 [17:59<39:57,  1.71s/it, loss=0.185, lr=0.0001]
Steps:  30%|███       | 601/2000 [17:59<39:57,  1.71s/it, loss=0.141, lr=0.0001]
Steps:  30%|███       | 601/2000 [18:00<39:57,  1.71s/it, loss=0.176, lr=0.0001]
Steps:  30%|███       | 602/2000 [18:00<41:27,  1.78s/it, loss=0.176, lr=0.0001]
Steps:  30%|███       | 602/2000 [18:00<41:27,  1.78s/it, loss=0.224, lr=0.0001]
Steps:  30%|███       | 602/2000 [18:01<41:27,  1.78s/it, loss=0.902, lr=0.0001]
Steps:  30%|███       | 602/2000 [18:01<41:27,  1.78s/it, loss=0.155, lr=0.0001]
Steps:  30%|███       | 602/2000 [18:01<41:27,  1.78s/it, loss=0.174, lr=0.0001]
Steps:  30%|███       | 603/2000 [18:02<40:46,  1.75s/it, loss=0.174, lr=0.0001]
Steps:  30%|███       | 603/2000 [18:02<40:46,  1.75s/it, loss=0.148, lr=0.0001]
Steps:  30%|███       | 603/2000 [18:02<40:46,  1.75s/it, loss=0.308, lr=0.0001]
Steps:  30%|███       | 603/2000 [18:03<40:46,  1.75s/it, loss=0.158, lr=0.0001]
Steps:  30%|███       | 603/2000 [18:03<40:46,  1.75s/it, loss=0.279, lr=0.0001]
Steps:  30%|███       | 604/2000 [18:03<39:55,  1.72s/it, loss=0.279, lr=0.0001]
Steps:  30%|███       | 604/2000 [18:03<39:55,  1.72s/it, loss=0.196, lr=0.0001]
Steps:  30%|███       | 604/2000 [18:04<39:55,  1.72s/it, loss=0.191, lr=0.0001]
Steps:  30%|███       | 604/2000 [18:04<39:55,  1.72s/it, loss=0.224, lr=0.0001]
Steps:  30%|███       | 604/2000 [18:05<39:55,  1.72s/it, loss=0.172, lr=0.0001]
Steps:  30%|███       | 605/2000 [18:05<41:05,  1.77s/it, loss=0.172, lr=0.0001]
Steps:  30%|███       | 605/2000 [18:05<41:05,  1.77s/it, loss=0.0868, lr=0.0001]05/30/2026 08:50:31 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/config.json "HTTP/1.1 200 OK"
05/30/2026 08:50:31 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/config.json "HTTP/1.1 200 OK"
05/30/2026 08:50:31 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/model.safetensors "HTTP/1.1 302 Found"


Loading weights:   0%|          | 0/196 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 196/196 [00:00<00:00, 7271.99it/s]
05/30/2026 08:50:31 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/config.json "HTTP/1.1 200 OK"
05/30/2026 08:50:31 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/config.json "HTTP/1.1 200 OK"
05/30/2026 08:50:31 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/model.safetensors "HTTP/1.1 404 Not Found"
05/30/2026 08:50:31 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/model.safetensors.index.json "HTTP/1.1 200 OK"
05/30/2026 08:50:31 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev/revision/main "HTTP/1.1 200 OK"


Fetching 2 files:   0%|          | 0/2 [00:00<?, ?it/s]
Fetching 2 files: 100%|██████████| 2/2 [00:00<00:00, 2471.60it/s]


Loading weights:   0%|          | 0/219 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 219/219 [00:00<00:00, 7078.58it/s]
05/30/2026 08:50:32 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev "HTTP/1.1 200 OK"
05/30/2026 08:50:32 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/model_index.json "HTTP/1.1 200 OK"
{'feature_extractor', 'image_encoder'} was not found in config. Values will be initialized to default values.


Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]Loaded tokenizer_2 as T5TokenizerFast from `tokenizer_2` subfolder of black-forest-labs/FLUX.1-dev.


Loading pipeline components...:  43%|████▎     | 3/7 [00:00<00:00, 18.76it/s]Loaded tokenizer as CLIPTokenizer from `tokenizer` subfolder of black-forest-labs/FLUX.1-dev.
{'stochastic_sampling', 'use_beta_sigmas', 'invert_sigmas', 'time_shift_type', 'use_exponential_sigmas', 'shift_terminal', 'use_karras_sigmas'} was not found in config. Values will be initialized to default values.
Loaded scheduler as FlowMatchEulerDiscreteScheduler from `scheduler` subfolder of black-forest-labs/FLUX.1-dev.

Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 33.18it/s]
05/30/2026 08:50:32 - INFO - __main__ - [RANK 0] Running validation... 
 Generating 1 images with prompt: emj icon of a pelican with a hat, centered on a plain white background.

Steps:  30%|███       | 605/2000 [18:18<41:05,  1.77s/it, loss=0.555, lr=0.0001] 
Steps:  30%|███       | 605/2000 [18:18<41:05,  1.77s/it, loss=0.171, lr=0.0001]
Steps:  30%|███       | 605/2000 [18:19<41:05,  1.77s/it, loss=0.147, lr=0.0001]
Steps:  30%|███       | 606/2000 [18:19<2:03:17,  5.31s/it, loss=0.147, lr=0.0001]
Steps:  30%|███       | 606/2000 [18:19<2:03:17,  5.31s/it, loss=0.0929, lr=0.0001]
Steps:  30%|███       | 606/2000 [18:19<2:03:17,  5.31s/it, loss=0.1, lr=0.0001]   
Steps:  30%|███       | 606/2000 [18:20<2:03:17,  5.31s/it, loss=0.155, lr=0.0001]
Steps:  30%|███       | 606/2000 [18:20<2:03:17,  5.31s/it, loss=0.113, lr=0.0001]
Steps:  30%|███       | 607/2000 [18:21<1:37:53,  4.22s/it, loss=0.113, lr=0.0001]
Steps:  30%|███       | 607/2000 [18:21<1:37:53,  4.22s/it, loss=0.226, lr=0.0001]
Steps:  30%|███       | 607/2000 [18:21<1:37:53,  4.22s/it, loss=0.14, lr=0.0001] 
Steps:  30%|███       | 607/2000 [18:21<1:37:53,  4.22s/it, loss=0.208, lr=0.0001]
Steps:  30%|███       | 607/2000 [18:22<1:37:53,  4.22s/it, loss=0.143, lr=0.0001]
Steps:  30%|███       | 608/2000 [18:22<1:19:56,  3.45s/it, loss=0.143, lr=0.0001]
Steps:  30%|███       | 608/2000 [18:22<1:19:56,  3.45s/it, loss=0.194, lr=0.0001]
Steps:  30%|███       | 608/2000 [18:23<1:19:56,  3.45s/it, loss=0.143, lr=0.0001]
Steps:  30%|███       | 608/2000 [18:23<1:19:56,  3.45s/it, loss=0.198, lr=0.0001]
Steps:  30%|███       | 608/2000 [18:24<1:19:56,  3.45s/it, loss=0.109, lr=0.0001]
Steps:  30%|███       | 609/2000 [18:24<1:08:57,  2.97s/it, loss=0.109, lr=0.0001]
Steps:  30%|███       | 609/2000 [18:24<1:08:57,  2.97s/it, loss=0.368, lr=0.0001]
Steps:  30%|███       | 609/2000 [18:25<1:08:57,  2.97s/it, loss=0.128, lr=0.0001]
Steps:  30%|███       | 609/2000 [18:25<1:08:57,  2.97s/it, loss=1.09, lr=0.0001] 
Steps:  30%|███       | 609/2000 [18:25<1:08:57,  2.97s/it, loss=1.07, lr=0.0001]
Steps:  30%|███       | 610/2000 [18:26<59:47,  2.58s/it, loss=1.07, lr=0.0001]  
Steps:  30%|███       | 610/2000 [18:26<59:47,  2.58s/it, loss=0.113, lr=0.0001]
Steps:  30%|███       | 610/2000 [18:26<59:47,  2.58s/it, loss=0.0786, lr=0.0001]
Steps:  30%|███       | 610/2000 [18:27<59:47,  2.58s/it, loss=0.205, lr=0.0001] 
Steps:  30%|███       | 610/2000 [18:27<59:47,  2.58s/it, loss=0.39, lr=0.0001] 
Steps:  31%|███       | 611/2000 [18:27<53:13,  2.30s/it, loss=0.39, lr=0.0001]
Steps:  31%|███       | 611/2000 [18:27<53:13,  2.30s/it, loss=0.141, lr=0.0001]
Steps:  31%|███       | 611/2000 [18:28<53:13,  2.30s/it, loss=0.172, lr=0.0001]
Steps:  31%|███       | 611/2000 [18:28<53:13,  2.30s/it, loss=0.186, lr=0.0001]
Steps:  31%|███       | 611/2000 [18:29<53:13,  2.30s/it, loss=0.133, lr=0.0001]
Steps:  31%|███       | 612/2000 [18:29<50:20,  2.18s/it, loss=0.133, lr=0.0001]
Steps:  31%|███       | 612/2000 [18:29<50:20,  2.18s/it, loss=0.164, lr=0.0001]
Steps:  31%|███       | 612/2000 [18:30<50:20,  2.18s/it, loss=0.135, lr=0.0001]
Steps:  31%|███       | 612/2000 [18:30<50:20,  2.18s/it, loss=0.225, lr=0.0001]
Steps:  31%|███       | 612/2000 [18:31<50:20,  2.18s/it, loss=0.141, lr=0.0001]
Steps:  31%|███       | 613/2000 [18:31<46:38,  2.02s/it, loss=0.141, lr=0.0001]
Steps:  31%|███       | 613/2000 [18:31<46:38,  2.02s/it, loss=0.329, lr=0.0001]
Steps:  31%|███       | 613/2000 [18:31<46:38,  2.02s/it, loss=0.333, lr=0.0001]
Steps:  31%|███       | 613/2000 [18:32<46:38,  2.02s/it, loss=0.176, lr=0.0001]
Steps:  31%|███       | 613/2000 [18:32<46:38,  2.02s/it, loss=0.238, lr=0.0001]
Steps:  31%|███       | 614/2000 [18:33<44:03,  1.91s/it, loss=0.238, lr=0.0001]
Steps:  31%|███       | 614/2000 [18:33<44:03,  1.91s/it, loss=0.127, lr=0.0001]
Steps:  31%|███       | 614/2000 [18:33<44:03,  1.91s/it, loss=0.157, lr=0.0001]
Steps:  31%|███       | 614/2000 [18:33<44:03,  1.91s/it, loss=0.116, lr=0.0001]
Steps:  31%|███       | 614/2000 [18:34<44:03,  1.91s/it, loss=0.219, lr=0.0001]
Steps:  31%|███       | 615/2000 [18:35<44:05,  1.91s/it, loss=0.219, lr=0.0001]
Steps:  31%|███       | 615/2000 [18:35<44:05,  1.91s/it, loss=0.0528, lr=0.0001]
Steps:  31%|███       | 615/2000 [18:35<44:05,  1.91s/it, loss=0.129, lr=0.0001] 
Steps:  31%|███       | 615/2000 [18:35<44:05,  1.91s/it, loss=0.0466, lr=0.0001]
Steps:  31%|███       | 615/2000 [18:36<44:05,  1.91s/it, loss=0.117, lr=0.0001] 
Steps:  31%|███       | 616/2000 [18:36<42:12,  1.83s/it, loss=0.117, lr=0.0001]
Steps:  31%|███       | 616/2000 [18:36<42:12,  1.83s/it, loss=0.176, lr=0.0001]
Steps:  31%|███       | 616/2000 [18:37<42:12,  1.83s/it, loss=0.262, lr=0.0001]
Steps:  31%|███       | 616/2000 [18:37<42:12,  1.83s/it, loss=0.0902, lr=0.0001]
Steps:  31%|███       | 616/2000 [18:37<42:12,  1.83s/it, loss=0.107, lr=0.0001] 
Steps:  31%|███       | 617/2000 [18:38<40:48,  1.77s/it, loss=0.107, lr=0.0001]
Steps:  31%|███       | 617/2000 [18:38<40:48,  1.77s/it, loss=0.27, lr=0.0001] 
Steps:  31%|███       | 617/2000 [18:38<40:48,  1.77s/it, loss=0.307, lr=0.0001]
Steps:  31%|███       | 617/2000 [18:39<40:48,  1.77s/it, loss=0.192, lr=0.0001]
Steps:  31%|███       | 617/2000 [18:39<40:48,  1.77s/it, loss=0.0949, lr=0.0001]
Steps:  31%|███       | 618/2000 [18:40<41:25,  1.80s/it, loss=0.0949, lr=0.0001]
Steps:  31%|███       | 618/2000 [18:40<41:25,  1.80s/it, loss=0.162, lr=0.0001] 
Steps:  31%|███       | 618/2000 [18:40<41:25,  1.80s/it, loss=0.338, lr=0.0001]
Steps:  31%|███       | 618/2000 [18:40<41:25,  1.80s/it, loss=0.301, lr=0.0001]
Steps:  31%|███       | 618/2000 [18:41<41:25,  1.80s/it, loss=0.27, lr=0.0001] 
Steps:  31%|███       | 619/2000 [18:41<40:22,  1.75s/it, loss=0.27, lr=0.0001]
Steps:  31%|███       | 619/2000 [18:41<40:22,  1.75s/it, loss=0.1, lr=0.0001] 
Steps:  31%|███       | 619/2000 [18:42<40:22,  1.75s/it, loss=0.114, lr=0.0001]
Steps:  31%|███       | 619/2000 [18:42<40:22,  1.75s/it, loss=0.167, lr=0.0001]
Steps:  31%|███       | 619/2000 [18:43<40:22,  1.75s/it, loss=0.181, lr=0.0001]
Steps:  31%|███       | 620/2000 [18:43<39:42,  1.73s/it, loss=0.181, lr=0.0001]
Steps:  31%|███       | 620/2000 [18:43<39:42,  1.73s/it, loss=0.175, lr=0.0001]
Steps:  31%|███       | 620/2000 [18:43<39:42,  1.73s/it, loss=0.97, lr=0.0001] 
Steps:  31%|███       | 620/2000 [18:44<39:42,  1.73s/it, loss=0.135, lr=0.0001]
Steps:  31%|███       | 620/2000 [18:44<39:42,  1.73s/it, loss=0.173, lr=0.0001]
Steps:  31%|███       | 621/2000 [18:45<40:51,  1.78s/it, loss=0.173, lr=0.0001]
Steps:  31%|███       | 621/2000 [18:45<40:51,  1.78s/it, loss=0.161, lr=0.0001]
Steps:  31%|███       | 621/2000 [18:45<40:51,  1.78s/it, loss=0.124, lr=0.0001]
Steps:  31%|███       | 621/2000 [18:46<40:51,  1.78s/it, loss=0.274, lr=0.0001]
Steps:  31%|███       | 621/2000 [18:46<40:51,  1.78s/it, loss=0.288, lr=0.0001]
Steps:  31%|███       | 622/2000 [18:47<40:13,  1.75s/it, loss=0.288, lr=0.0001]
Steps:  31%|███       | 622/2000 [18:47<40:13,  1.75s/it, loss=0.0786, lr=0.0001]
Steps:  31%|███       | 622/2000 [18:47<40:13,  1.75s/it, loss=0.157, lr=0.0001] 
Steps:  31%|███       | 622/2000 [18:47<40:13,  1.75s/it, loss=0.134, lr=0.0001]
Steps:  31%|███       | 622/2000 [18:48<40:13,  1.75s/it, loss=0.211, lr=0.0001]
Steps:  31%|███       | 623/2000 [18:48<39:36,  1.73s/it, loss=0.211, lr=0.0001]
Steps:  31%|███       | 623/2000 [18:48<39:36,  1.73s/it, loss=0.166, lr=0.0001]
Steps:  31%|███       | 623/2000 [18:49<39:36,  1.73s/it, loss=0.142, lr=0.0001]
Steps:  31%|███       | 623/2000 [18:49<39:36,  1.73s/it, loss=0.195, lr=0.0001]
Steps:  31%|███       | 623/2000 [18:50<39:36,  1.73s/it, loss=0.235, lr=0.0001]
Steps:  31%|███       | 624/2000 [18:50<41:04,  1.79s/it, loss=0.235, lr=0.0001]
Steps:  31%|███       | 624/2000 [18:50<41:04,  1.79s/it, loss=0.134, lr=0.0001]
Steps:  31%|███       | 624/2000 [18:51<41:04,  1.79s/it, loss=0.191, lr=0.0001]
Steps:  31%|███       | 624/2000 [18:51<41:04,  1.79s/it, loss=1.03, lr=0.0001] 
Steps:  31%|███       | 624/2000 [18:52<41:04,  1.79s/it, loss=0.112, lr=0.0001]
Steps:  31%|███▏      | 625/2000 [18:52<41:10,  1.80s/it, loss=0.112, lr=0.0001]
Steps:  31%|███▏      | 625/2000 [18:52<41:10,  1.80s/it, loss=0.204, lr=0.0001]
Steps:  31%|███▏      | 625/2000 [18:52<41:10,  1.80s/it, loss=0.122, lr=0.0001]
Steps:  31%|███▏      | 625/2000 [18:53<41:10,  1.80s/it, loss=0.234, lr=0.0001]
Steps:  31%|███▏      | 625/2000 [18:53<41:10,  1.80s/it, loss=0.0617, lr=0.0001]
Steps:  31%|███▏      | 626/2000 [18:54<40:56,  1.79s/it, loss=0.0617, lr=0.0001]
Steps:  31%|███▏      | 626/2000 [18:54<40:56,  1.79s/it, loss=0.167, lr=0.0001] 
Steps:  31%|███▏      | 626/2000 [18:54<40:56,  1.79s/it, loss=0.139, lr=0.0001]
Steps:  31%|███▏      | 626/2000 [18:55<40:56,  1.79s/it, loss=0.104, lr=0.0001]
Steps:  31%|███▏      | 626/2000 [18:55<40:56,  1.79s/it, loss=0.64, lr=0.0001] 
Steps:  31%|███▏      | 627/2000 [18:56<40:46,  1.78s/it, loss=0.64, lr=0.0001]
Steps:  31%|███▏      | 627/2000 [18:56<40:46,  1.78s/it, loss=0.139, lr=0.0001]
Steps:  31%|███▏      | 627/2000 [18:56<40:46,  1.78s/it, loss=0.161, lr=0.0001]
Steps:  31%|███▏      | 627/2000 [18:57<40:46,  1.78s/it, loss=0.224, lr=0.0001]
Steps:  31%|███▏      | 627/2000 [18:57<40:46,  1.78s/it, loss=0.16, lr=0.0001] 
Steps:  31%|███▏      | 628/2000 [18:58<42:10,  1.84s/it, loss=0.16, lr=0.0001]
Steps:  31%|███▏      | 628/2000 [18:58<42:10,  1.84s/it, loss=0.162, lr=0.0001]
Steps:  31%|███▏      | 628/2000 [18:58<42:10,  1.84s/it, loss=0.287, lr=0.0001]
Steps:  31%|███▏      | 628/2000 [18:58<42:10,  1.84s/it, loss=0.134, lr=0.0001]
Steps:  31%|███▏      | 628/2000 [18:59<42:10,  1.84s/it, loss=0.258, lr=0.0001]
Steps:  31%|███▏      | 629/2000 [18:59<41:41,  1.82s/it, loss=0.258, lr=0.0001]
Steps:  31%|███▏      | 629/2000 [18:59<41:41,  1.82s/it, loss=0.152, lr=0.0001]
Steps:  31%|███▏      | 629/2000 [19:00<41:41,  1.82s/it, loss=0.132, lr=0.0001]
Steps:  31%|███▏      | 629/2000 [19:00<41:41,  1.82s/it, loss=0.133, lr=0.0001]
Steps:  31%|███▏      | 629/2000 [19:01<41:41,  1.82s/it, loss=0.0553, lr=0.0001]
Steps:  32%|███▏      | 630/2000 [19:01<41:03,  1.80s/it, loss=0.0553, lr=0.0001]
Steps:  32%|███▏      | 630/2000 [19:01<41:03,  1.80s/it, loss=0.184, lr=0.0001] 
Steps:  32%|███▏      | 630/2000 [19:01<41:03,  1.80s/it, loss=0.132, lr=0.0001]
Steps:  32%|███▏      | 630/2000 [19:02<41:03,  1.80s/it, loss=0.13, lr=0.0001] 
Steps:  32%|███▏      | 630/2000 [19:03<41:03,  1.80s/it, loss=0.284, lr=0.0001]
Steps:  32%|███▏      | 631/2000 [19:03<42:16,  1.85s/it, loss=0.284, lr=0.0001]
Steps:  32%|███▏      | 631/2000 [19:03<42:16,  1.85s/it, loss=0.688, lr=0.0001]
Steps:  32%|███▏      | 631/2000 [19:03<42:16,  1.85s/it, loss=0.148, lr=0.0001]
Steps:  32%|███▏      | 631/2000 [19:04<42:16,  1.85s/it, loss=0.154, lr=0.0001]
Steps:  32%|███▏      | 631/2000 [19:04<42:16,  1.85s/it, loss=0.117, lr=0.0001]
Steps:  32%|███▏      | 632/2000 [19:05<41:24,  1.82s/it, loss=0.117, lr=0.0001]
Steps:  32%|███▏      | 632/2000 [19:05<41:24,  1.82s/it, loss=0.363, lr=0.0001]
Steps:  32%|███▏      | 632/2000 [19:05<41:24,  1.82s/it, loss=0.12, lr=0.0001] 
Steps:  32%|███▏      | 632/2000 [19:06<41:24,  1.82s/it, loss=0.344, lr=0.0001]
Steps:  32%|███▏      | 632/2000 [19:06<41:24,  1.82s/it, loss=0.21, lr=0.0001] 
Steps:  32%|███▏      | 633/2000 [19:07<41:13,  1.81s/it, loss=0.21, lr=0.0001]
Steps:  32%|███▏      | 633/2000 [19:07<41:13,  1.81s/it, loss=0.138, lr=0.0001]
Steps:  32%|███▏      | 633/2000 [19:07<41:13,  1.81s/it, loss=0.635, lr=0.0001]
Steps:  32%|███▏      | 633/2000 [19:08<41:13,  1.81s/it, loss=0.15, lr=0.0001] 
Steps:  32%|███▏      | 633/2000 [19:08<41:13,  1.81s/it, loss=0.218, lr=0.0001]
Steps:  32%|███▏      | 634/2000 [19:09<42:27,  1.86s/it, loss=0.218, lr=0.0001]
Steps:  32%|███▏      | 634/2000 [19:09<42:27,  1.86s/it, loss=0.178, lr=0.0001]
Steps:  32%|███▏      | 634/2000 [19:09<42:27,  1.86s/it, loss=0.351, lr=0.0001]
Steps:  32%|███▏      | 634/2000 [19:09<42:27,  1.86s/it, loss=0.129, lr=0.0001]
Steps:  32%|███▏      | 634/2000 [19:10<42:27,  1.86s/it, loss=0.182, lr=0.0001]
Steps:  32%|███▏      | 635/2000 [19:10<41:39,  1.83s/it, loss=0.182, lr=0.0001]
Steps:  32%|███▏      | 635/2000 [19:10<41:39,  1.83s/it, loss=0.124, lr=0.0001]
Steps:  32%|███▏      | 635/2000 [19:11<41:39,  1.83s/it, loss=0.182, lr=0.0001]
Steps:  32%|███▏      | 635/2000 [19:11<41:39,  1.83s/it, loss=0.284, lr=0.0001]
Steps:  32%|███▏      | 635/2000 [19:12<41:39,  1.83s/it, loss=0.181, lr=0.0001]
Steps:  32%|███▏      | 636/2000 [19:12<40:52,  1.80s/it, loss=0.181, lr=0.0001]
Steps:  32%|███▏      | 636/2000 [19:12<40:52,  1.80s/it, loss=0.252, lr=0.0001]
Steps:  32%|███▏      | 636/2000 [19:12<40:52,  1.80s/it, loss=0.0877, lr=0.0001]
Steps:  32%|███▏      | 636/2000 [19:13<40:52,  1.80s/it, loss=0.231, lr=0.0001] 
Steps:  32%|███▏      | 636/2000 [19:14<40:52,  1.80s/it, loss=0.233, lr=0.0001]
Steps:  32%|███▏      | 637/2000 [19:14<42:00,  1.85s/it, loss=0.233, lr=0.0001]
Steps:  32%|███▏      | 637/2000 [19:14<42:00,  1.85s/it, loss=0.109, lr=0.0001]
Steps:  32%|███▏      | 637/2000 [19:14<42:00,  1.85s/it, loss=0.123, lr=0.0001]
Steps:  32%|███▏      | 637/2000 [19:15<42:00,  1.85s/it, loss=0.136, lr=0.0001]
Steps:  32%|███▏      | 637/2000 [19:15<42:00,  1.85s/it, loss=1.24, lr=0.0001] 
Steps:  32%|███▏      | 638/2000 [19:16<41:16,  1.82s/it, loss=1.24, lr=0.0001]
Steps:  32%|███▏      | 638/2000 [19:16<41:16,  1.82s/it, loss=0.657, lr=0.0001]
Steps:  32%|███▏      | 638/2000 [19:16<41:16,  1.82s/it, loss=0.329, lr=0.0001]
Steps:  32%|███▏      | 638/2000 [19:17<41:16,  1.82s/it, loss=0.177, lr=0.0001]
Steps:  32%|███▏      | 638/2000 [19:17<41:16,  1.82s/it, loss=0.125, lr=0.0001]
Steps:  32%|███▏      | 639/2000 [19:17<40:43,  1.80s/it, loss=0.125, lr=0.0001]
Steps:  32%|███▏      | 639/2000 [19:17<40:43,  1.80s/it, loss=0.181, lr=0.0001]
Steps:  32%|███▏      | 639/2000 [19:18<40:43,  1.80s/it, loss=0.204, lr=0.0001]
Steps:  32%|███▏      | 639/2000 [19:18<40:43,  1.80s/it, loss=0.197, lr=0.0001]
Steps:  32%|███▏      | 639/2000 [19:19<40:43,  1.80s/it, loss=0.197, lr=0.0001]
Steps:  32%|███▏      | 640/2000 [19:19<41:46,  1.84s/it, loss=0.197, lr=0.0001]
Steps:  32%|███▏      | 640/2000 [19:19<41:46,  1.84s/it, loss=0.101, lr=0.0001]
Steps:  32%|███▏      | 640/2000 [19:20<41:46,  1.84s/it, loss=0.165, lr=0.0001]
Steps:  32%|███▏      | 640/2000 [19:20<41:46,  1.84s/it, loss=0.242, lr=0.0001]
Steps:  32%|███▏      | 640/2000 [19:21<41:46,  1.84s/it, loss=0.243, lr=0.0001]
Steps:  32%|███▏      | 641/2000 [19:21<40:49,  1.80s/it, loss=0.243, lr=0.0001]
Steps:  32%|███▏      | 641/2000 [19:21<40:49,  1.80s/it, loss=0.135, lr=0.0001]
Steps:  32%|███▏      | 641/2000 [19:22<40:49,  1.80s/it, loss=0.125, lr=0.0001]
Steps:  32%|███▏      | 641/2000 [19:22<40:49,  1.80s/it, loss=0.196, lr=0.0001]
Steps:  32%|███▏      | 641/2000 [19:22<40:49,  1.80s/it, loss=0.242, lr=0.0001]
Steps:  32%|███▏      | 642/2000 [19:23<40:02,  1.77s/it, loss=0.242, lr=0.0001]
Steps:  32%|███▏      | 642/2000 [19:23<40:02,  1.77s/it, loss=0.165, lr=0.0001]
Steps:  32%|███▏      | 642/2000 [19:23<40:02,  1.77s/it, loss=0.138, lr=0.0001]
Steps:  32%|███▏      | 642/2000 [19:24<40:02,  1.77s/it, loss=0.268, lr=0.0001]
Steps:  32%|███▏      | 642/2000 [19:24<40:02,  1.77s/it, loss=0.182, lr=0.0001]
Steps:  32%|███▏      | 643/2000 [19:25<41:05,  1.82s/it, loss=0.182, lr=0.0001]
Steps:  32%|███▏      | 643/2000 [19:25<41:05,  1.82s/it, loss=0.205, lr=0.0001]
Steps:  32%|███▏      | 643/2000 [19:25<41:05,  1.82s/it, loss=0.183, lr=0.0001]
Steps:  32%|███▏      | 643/2000 [19:26<41:05,  1.82s/it, loss=0.327, lr=0.0001]
Steps:  32%|███▏      | 643/2000 [19:26<41:05,  1.82s/it, loss=0.241, lr=0.0001]
Steps:  32%|███▏      | 644/2000 [19:26<40:19,  1.78s/it, loss=0.241, lr=0.0001]
Steps:  32%|███▏      | 644/2000 [19:26<40:19,  1.78s/it, loss=0.0711, lr=0.0001]
Steps:  32%|███▏      | 644/2000 [19:27<40:19,  1.78s/it, loss=0.0839, lr=0.0001]
Steps:  32%|███▏      | 644/2000 [19:27<40:19,  1.78s/it, loss=0.186, lr=0.0001] 
Steps:  32%|███▏      | 644/2000 [19:28<40:19,  1.78s/it, loss=0.201, lr=0.0001]
Steps:  32%|███▏      | 645/2000 [19:28<39:47,  1.76s/it, loss=0.201, lr=0.0001]
Steps:  32%|███▏      | 645/2000 [19:28<39:47,  1.76s/it, loss=0.158, lr=0.0001]
Steps:  32%|███▏      | 645/2000 [19:29<39:47,  1.76s/it, loss=0.14, lr=0.0001] 
Steps:  32%|███▏      | 645/2000 [19:29<39:47,  1.76s/it, loss=0.0956, lr=0.0001]
Steps:  32%|███▏      | 645/2000 [19:29<39:47,  1.76s/it, loss=0.244, lr=0.0001] 
Steps:  32%|███▏      | 646/2000 [19:30<39:37,  1.76s/it, loss=0.244, lr=0.0001]
Steps:  32%|███▏      | 646/2000 [19:30<39:37,  1.76s/it, loss=0.0815, lr=0.0001]
Steps:  32%|███▏      | 646/2000 [19:31<39:37,  1.76s/it, loss=0.0881, lr=0.0001]
Steps:  32%|███▏      | 646/2000 [19:31<39:37,  1.76s/it, loss=0.0938, lr=0.0001]
Steps:  32%|███▏      | 646/2000 [19:31<39:37,  1.76s/it, loss=0.227, lr=0.0001] 
Steps:  32%|███▏      | 647/2000 [19:32<40:49,  1.81s/it, loss=0.227, lr=0.0001]
Steps:  32%|███▏      | 647/2000 [19:32<40:49,  1.81s/it, loss=0.263, lr=0.0001]
Steps:  32%|███▏      | 647/2000 [19:32<40:49,  1.81s/it, loss=0.283, lr=0.0001]
Steps:  32%|███▏      | 647/2000 [19:33<40:49,  1.81s/it, loss=0.208, lr=0.0001]
Steps:  32%|███▏      | 647/2000 [19:33<40:49,  1.81s/it, loss=0.146, lr=0.0001]
Steps:  32%|███▏      | 648/2000 [19:34<40:12,  1.78s/it, loss=0.146, lr=0.0001]
Steps:  32%|███▏      | 648/2000 [19:34<40:12,  1.78s/it, loss=0.263, lr=0.0001]
Steps:  32%|███▏      | 648/2000 [19:34<40:12,  1.78s/it, loss=0.167, lr=0.0001]
Steps:  32%|███▏      | 648/2000 [19:34<40:12,  1.78s/it, loss=0.155, lr=0.0001]
Steps:  32%|███▏      | 648/2000 [19:35<40:12,  1.78s/it, loss=0.14, lr=0.0001] 
Steps:  32%|███▏      | 649/2000 [19:35<39:41,  1.76s/it, loss=0.14, lr=0.0001]
Steps:  32%|███▏      | 649/2000 [19:35<39:41,  1.76s/it, loss=0.265, lr=0.0001]
Steps:  32%|███▏      | 649/2000 [19:36<39:41,  1.76s/it, loss=0.198, lr=0.0001]
Steps:  32%|███▏      | 649/2000 [19:36<39:41,  1.76s/it, loss=0.422, lr=0.0001]
Steps:  32%|███▏      | 649/2000 [19:37<39:41,  1.76s/it, loss=0.167, lr=0.0001]
Steps:  32%|███▎      | 650/2000 [19:37<41:00,  1.82s/it, loss=0.167, lr=0.0001]
Steps:  32%|███▎      | 650/2000 [19:37<41:00,  1.82s/it, loss=0.217, lr=0.0001]
Steps:  32%|███▎      | 650/2000 [19:38<41:00,  1.82s/it, loss=0.149, lr=0.0001]
Steps:  32%|███▎      | 650/2000 [19:38<41:00,  1.82s/it, loss=0.218, lr=0.0001]
Steps:  32%|███▎      | 650/2000 [19:39<41:00,  1.82s/it, loss=0.24, lr=0.0001] 
Steps:  33%|███▎      | 651/2000 [19:39<40:13,  1.79s/it, loss=0.24, lr=0.0001]
Steps:  33%|███▎      | 651/2000 [19:39<40:13,  1.79s/it, loss=0.127, lr=0.0001]
Steps:  33%|███▎      | 651/2000 [19:39<40:13,  1.79s/it, loss=0.136, lr=0.0001]
Steps:  33%|███▎      | 651/2000 [19:40<40:13,  1.79s/it, loss=0.273, lr=0.0001]
Steps:  33%|███▎      | 651/2000 [19:40<40:13,  1.79s/it, loss=0.168, lr=0.0001]
Steps:  33%|███▎      | 652/2000 [19:41<39:53,  1.78s/it, loss=0.168, lr=0.0001]
Steps:  33%|███▎      | 652/2000 [19:41<39:53,  1.78s/it, loss=0.134, lr=0.0001]
Steps:  33%|███▎      | 652/2000 [19:41<39:53,  1.78s/it, loss=0.218, lr=0.0001]
Steps:  33%|███▎      | 652/2000 [19:42<39:53,  1.78s/it, loss=0.0978, lr=0.0001]
Steps:  33%|███▎      | 652/2000 [19:42<39:53,  1.78s/it, loss=0.251, lr=0.0001] 
Steps:  33%|███▎      | 653/2000 [19:43<40:59,  1.83s/it, loss=0.251, lr=0.0001]
Steps:  33%|███▎      | 653/2000 [19:43<40:59,  1.83s/it, loss=0.501, lr=0.0001]
Steps:  33%|███▎      | 653/2000 [19:43<40:59,  1.83s/it, loss=0.117, lr=0.0001]
Steps:  33%|███▎      | 653/2000 [19:43<40:59,  1.83s/it, loss=0.321, lr=0.0001]
Steps:  33%|███▎      | 653/2000 [19:44<40:59,  1.83s/it, loss=0.146, lr=0.0001]
Steps:  33%|███▎      | 654/2000 [19:44<40:19,  1.80s/it, loss=0.146, lr=0.0001]
Steps:  33%|███▎      | 654/2000 [19:44<40:19,  1.80s/it, loss=0.136, lr=0.0001]
Steps:  33%|███▎      | 654/2000 [19:45<40:19,  1.80s/it, loss=0.176, lr=0.0001]
Steps:  33%|███▎      | 654/2000 [19:45<40:19,  1.80s/it, loss=0.073, lr=0.0001]
Steps:  33%|███▎      | 654/2000 [19:46<40:19,  1.80s/it, loss=0.144, lr=0.0001]
Steps:  33%|███▎      | 655/2000 [19:46<39:46,  1.77s/it, loss=0.144, lr=0.0001]
Steps:  33%|███▎      | 655/2000 [19:46<39:46,  1.77s/it, loss=0.126, lr=0.0001]
Steps:  33%|███▎      | 655/2000 [19:47<39:46,  1.77s/it, loss=0.0841, lr=0.0001]
Steps:  33%|███▎      | 655/2000 [19:47<39:46,  1.77s/it, loss=0.242, lr=0.0001] 
Steps:  33%|███▎      | 655/2000 [19:48<39:46,  1.77s/it, loss=0.178, lr=0.0001]
Steps:  33%|███▎      | 656/2000 [19:48<41:06,  1.83s/it, loss=0.178, lr=0.0001]
Steps:  33%|███▎      | 656/2000 [19:48<41:06,  1.83s/it, loss=0.206, lr=0.0001]
Steps:  33%|███▎      | 656/2000 [19:49<41:06,  1.83s/it, loss=0.235, lr=0.0001]
Steps:  33%|███▎      | 656/2000 [19:49<41:06,  1.83s/it, loss=0.236, lr=0.0001]
Steps:  33%|███▎      | 656/2000 [19:49<41:06,  1.83s/it, loss=0.178, lr=0.0001]
Steps:  33%|███▎      | 657/2000 [19:50<40:28,  1.81s/it, loss=0.178, lr=0.0001]
Steps:  33%|███▎      | 657/2000 [19:50<40:28,  1.81s/it, loss=0.29, lr=0.0001] 
Steps:  33%|███▎      | 657/2000 [19:50<40:28,  1.81s/it, loss=0.217, lr=0.0001]
Steps:  33%|███▎      | 657/2000 [19:51<40:28,  1.81s/it, loss=0.161, lr=0.0001]
Steps:  33%|███▎      | 657/2000 [19:51<40:28,  1.81s/it, loss=0.306, lr=0.0001]
Steps:  33%|███▎      | 658/2000 [19:51<39:29,  1.77s/it, loss=0.306, lr=0.0001]
Steps:  33%|███▎      | 658/2000 [19:51<39:29,  1.77s/it, loss=0.244, lr=0.0001]
Steps:  33%|███▎      | 658/2000 [19:52<39:29,  1.77s/it, loss=0.171, lr=0.0001]
Steps:  33%|███▎      | 658/2000 [19:52<39:29,  1.77s/it, loss=0.181, lr=0.0001]
Steps:  33%|███▎      | 658/2000 [19:53<39:29,  1.77s/it, loss=0.272, lr=0.0001]
Steps:  33%|███▎      | 659/2000 [19:53<40:24,  1.81s/it, loss=0.272, lr=0.0001]
Steps:  33%|███▎      | 659/2000 [19:53<40:24,  1.81s/it, loss=0.153, lr=0.0001]
Steps:  33%|███▎      | 659/2000 [19:54<40:24,  1.81s/it, loss=0.162, lr=0.0001]
Steps:  33%|███▎      | 659/2000 [19:54<40:24,  1.81s/it, loss=0.127, lr=0.0001]
Steps:  33%|███▎      | 659/2000 [19:55<40:24,  1.81s/it, loss=0.142, lr=0.0001]
Steps:  33%|███▎      | 660/2000 [19:55<39:39,  1.78s/it, loss=0.142, lr=0.0001]
Steps:  33%|███▎      | 660/2000 [19:55<39:39,  1.78s/it, loss=0.145, lr=0.0001]
Steps:  33%|███▎      | 660/2000 [19:56<39:39,  1.78s/it, loss=0.0911, lr=0.0001]
Steps:  33%|███▎      | 660/2000 [19:56<39:39,  1.78s/it, loss=0.441, lr=0.0001] 
Steps:  33%|███▎      | 660/2000 [19:56<39:39,  1.78s/it, loss=0.245, lr=0.0001]
Steps:  33%|███▎      | 661/2000 [19:57<39:21,  1.76s/it, loss=0.245, lr=0.0001]
Steps:  33%|███▎      | 661/2000 [19:57<39:21,  1.76s/it, loss=0.276, lr=0.0001]
Steps:  33%|███▎      | 661/2000 [19:57<39:21,  1.76s/it, loss=0.163, lr=0.0001]
Steps:  33%|███▎      | 661/2000 [19:58<39:21,  1.76s/it, loss=0.17, lr=0.0001] 
Steps:  33%|███▎      | 661/2000 [19:58<39:21,  1.76s/it, loss=0.108, lr=0.0001]
Steps:  33%|███▎      | 662/2000 [19:59<40:08,  1.80s/it, loss=0.108, lr=0.0001]
Steps:  33%|███▎      | 662/2000 [19:59<40:08,  1.80s/it, loss=0.0828, lr=0.0001]
Steps:  33%|███▎      | 662/2000 [19:59<40:08,  1.80s/it, loss=0.138, lr=0.0001] 
Steps:  33%|███▎      | 662/2000 [20:00<40:08,  1.80s/it, loss=0.126, lr=0.0001]
Steps:  33%|███▎      | 662/2000 [20:00<40:08,  1.80s/it, loss=0.173, lr=0.0001]
Steps:  33%|███▎      | 663/2000 [20:00<39:02,  1.75s/it, loss=0.173, lr=0.0001]
Steps:  33%|███▎      | 663/2000 [20:00<39:02,  1.75s/it, loss=0.195, lr=0.0001]
Steps:  33%|███▎      | 663/2000 [20:01<39:02,  1.75s/it, loss=0.223, lr=0.0001]
Steps:  33%|███▎      | 663/2000 [20:01<39:02,  1.75s/it, loss=0.172, lr=0.0001]
Steps:  33%|███▎      | 663/2000 [20:02<39:02,  1.75s/it, loss=0.111, lr=0.0001]
Steps:  33%|███▎      | 664/2000 [20:02<38:46,  1.74s/it, loss=0.111, lr=0.0001]
Steps:  33%|███▎      | 664/2000 [20:02<38:46,  1.74s/it, loss=0.323, lr=0.0001]
Steps:  33%|███▎      | 664/2000 [20:02<38:46,  1.74s/it, loss=0.232, lr=0.0001]
Steps:  33%|███▎      | 664/2000 [20:03<38:46,  1.74s/it, loss=0.0703, lr=0.0001]
Steps:  33%|███▎      | 664/2000 [20:03<38:46,  1.74s/it, loss=0.926, lr=0.0001] 
Steps:  33%|███▎      | 665/2000 [20:04<40:11,  1.81s/it, loss=0.926, lr=0.0001]
Steps:  33%|███▎      | 665/2000 [20:04<40:11,  1.81s/it, loss=0.202, lr=0.0001]
Steps:  33%|███▎      | 665/2000 [20:04<40:11,  1.81s/it, loss=0.0755, lr=0.0001]
Steps:  33%|███▎      | 665/2000 [20:05<40:11,  1.81s/it, loss=0.395, lr=0.0001] 
Steps:  33%|███▎      | 665/2000 [20:05<40:11,  1.81s/it, loss=0.155, lr=0.0001]
Steps:  33%|███▎      | 666/2000 [20:06<39:25,  1.77s/it, loss=0.155, lr=0.0001]
Steps:  33%|███▎      | 666/2000 [20:06<39:25,  1.77s/it, loss=1.1, lr=0.0001]  
Steps:  33%|███▎      | 666/2000 [20:06<39:25,  1.77s/it, loss=0.425, lr=0.0001]
Steps:  33%|███▎      | 666/2000 [20:07<39:25,  1.77s/it, loss=0.202, lr=0.0001]
Steps:  33%|███▎      | 666/2000 [20:07<39:25,  1.77s/it, loss=0.158, lr=0.0001]
Steps:  33%|███▎      | 667/2000 [20:07<38:44,  1.74s/it, loss=0.158, lr=0.0001]
Steps:  33%|███▎      | 667/2000 [20:07<38:44,  1.74s/it, loss=0.133, lr=0.0001]
Steps:  33%|███▎      | 667/2000 [20:08<38:44,  1.74s/it, loss=0.162, lr=0.0001]
Steps:  33%|███▎      | 667/2000 [20:08<38:44,  1.74s/it, loss=0.189, lr=0.0001]
Steps:  33%|███▎      | 667/2000 [20:09<38:44,  1.74s/it, loss=0.0203, lr=0.0001]
Steps:  33%|███▎      | 668/2000 [20:09<38:16,  1.72s/it, loss=0.0203, lr=0.0001]
Steps:  33%|███▎      | 668/2000 [20:09<38:16,  1.72s/it, loss=0.171, lr=0.0001] 
Steps:  33%|███▎      | 668/2000 [20:10<38:16,  1.72s/it, loss=0.117, lr=0.0001]
Steps:  33%|███▎      | 668/2000 [20:10<38:16,  1.72s/it, loss=0.144, lr=0.0001]
Steps:  33%|███▎      | 668/2000 [20:11<38:16,  1.72s/it, loss=0.304, lr=0.0001]
Steps:  33%|███▎      | 669/2000 [20:11<39:35,  1.78s/it, loss=0.304, lr=0.0001]
Steps:  33%|███▎      | 669/2000 [20:11<39:35,  1.78s/it, loss=0.148, lr=0.0001]
Steps:  33%|███▎      | 669/2000 [20:11<39:35,  1.78s/it, loss=0.228, lr=0.0001]
Steps:  33%|███▎      | 669/2000 [20:12<39:35,  1.78s/it, loss=0.0818, lr=0.0001]
Steps:  33%|███▎      | 669/2000 [20:12<39:35,  1.78s/it, loss=0.147, lr=0.0001] 
Steps:  34%|███▎      | 670/2000 [20:13<39:20,  1.77s/it, loss=0.147, lr=0.0001]
Steps:  34%|███▎      | 670/2000 [20:13<39:20,  1.77s/it, loss=0.0896, lr=0.0001]
Steps:  34%|███▎      | 670/2000 [20:13<39:20,  1.77s/it, loss=0.203, lr=0.0001] 
Steps:  34%|███▎      | 670/2000 [20:14<39:20,  1.77s/it, loss=0.174, lr=0.0001]
Steps:  34%|███▎      | 670/2000 [20:14<39:20,  1.77s/it, loss=0.148, lr=0.0001]
Steps:  34%|███▎      | 671/2000 [20:14<38:56,  1.76s/it, loss=0.148, lr=0.0001]
Steps:  34%|███▎      | 671/2000 [20:14<38:56,  1.76s/it, loss=0.2, lr=0.0001]  
Steps:  34%|███▎      | 671/2000 [20:15<38:56,  1.76s/it, loss=0.901, lr=0.0001]
Steps:  34%|███▎      | 671/2000 [20:16<38:56,  1.76s/it, loss=0.101, lr=0.0001]
Steps:  34%|███▎      | 671/2000 [20:16<38:56,  1.76s/it, loss=0.0682, lr=0.0001]
Steps:  34%|███▎      | 672/2000 [20:17<40:43,  1.84s/it, loss=0.0682, lr=0.0001]
Steps:  34%|███▎      | 672/2000 [20:17<40:43,  1.84s/it, loss=0.23, lr=0.0001]  
Steps:  34%|███▎      | 672/2000 [20:17<40:43,  1.84s/it, loss=0.284, lr=0.0001]
Steps:  34%|███▎      | 672/2000 [20:17<40:43,  1.84s/it, loss=0.579, lr=0.0001]
Steps:  34%|███▎      | 672/2000 [20:18<40:43,  1.84s/it, loss=0.152, lr=0.0001]
Steps:  34%|███▎      | 673/2000 [20:18<39:34,  1.79s/it, loss=0.152, lr=0.0001]
Steps:  34%|███▎      | 673/2000 [20:18<39:34,  1.79s/it, loss=0.323, lr=0.0001]
Steps:  34%|███▎      | 673/2000 [20:19<39:34,  1.79s/it, loss=0.14, lr=0.0001] 
Steps:  34%|███▎      | 673/2000 [20:19<39:34,  1.79s/it, loss=0.234, lr=0.0001]
Steps:  34%|███▎      | 673/2000 [20:19<39:34,  1.79s/it, loss=0.194, lr=0.0001]
Steps:  34%|███▎      | 674/2000 [20:20<38:36,  1.75s/it, loss=0.194, lr=0.0001]
Steps:  34%|███▎      | 674/2000 [20:20<38:36,  1.75s/it, loss=0.162, lr=0.0001]
Steps:  34%|███▎      | 674/2000 [20:20<38:36,  1.75s/it, loss=0.148, lr=0.0001]
Steps:  34%|███▎      | 674/2000 [20:21<38:36,  1.75s/it, loss=0.108, lr=0.0001]
Steps:  34%|███▎      | 674/2000 [20:21<38:36,  1.75s/it, loss=0.289, lr=0.0001]
Steps:  34%|███▍      | 675/2000 [20:22<39:38,  1.80s/it, loss=0.289, lr=0.0001]
Steps:  34%|███▍      | 675/2000 [20:22<39:38,  1.80s/it, loss=0.186, lr=0.0001]
Steps:  34%|███▍      | 675/2000 [20:22<39:38,  1.80s/it, loss=0.123, lr=0.0001]
Steps:  34%|███▍      | 675/2000 [20:23<39:38,  1.80s/it, loss=0.237, lr=0.0001]
Steps:  34%|███▍      | 675/2000 [20:23<39:38,  1.80s/it, loss=0.182, lr=0.0001]
Steps:  34%|███▍      | 676/2000 [20:23<39:03,  1.77s/it, loss=0.182, lr=0.0001]
Steps:  34%|███▍      | 676/2000 [20:23<39:03,  1.77s/it, loss=0.117, lr=0.0001]
Steps:  34%|███▍      | 676/2000 [20:24<39:03,  1.77s/it, loss=0.138, lr=0.0001]
Steps:  34%|███▍      | 676/2000 [20:24<39:03,  1.77s/it, loss=0.211, lr=0.0001]
Steps:  34%|███▍      | 676/2000 [20:25<39:03,  1.77s/it, loss=0.208, lr=0.0001]
Steps:  34%|███▍      | 677/2000 [20:25<38:31,  1.75s/it, loss=0.208, lr=0.0001]
Steps:  34%|███▍      | 677/2000 [20:25<38:31,  1.75s/it, loss=0.201, lr=0.0001]
Steps:  34%|███▍      | 677/2000 [20:26<38:31,  1.75s/it, loss=0.326, lr=0.0001]
Steps:  34%|███▍      | 677/2000 [20:26<38:31,  1.75s/it, loss=0.171, lr=0.0001]
Steps:  34%|███▍      | 677/2000 [20:27<38:31,  1.75s/it, loss=0.215, lr=0.0001]
Steps:  34%|███▍      | 678/2000 [20:27<39:36,  1.80s/it, loss=0.215, lr=0.0001]
Steps:  34%|███▍      | 678/2000 [20:27<39:36,  1.80s/it, loss=0.129, lr=0.0001]
Steps:  34%|███▍      | 678/2000 [20:27<39:36,  1.80s/it, loss=0.176, lr=0.0001]
Steps:  34%|███▍      | 678/2000 [20:28<39:36,  1.80s/it, loss=0.193, lr=0.0001]
Steps:  34%|███▍      | 678/2000 [20:28<39:36,  1.80s/it, loss=0.142, lr=0.0001]
Steps:  34%|███▍      | 679/2000 [20:29<39:12,  1.78s/it, loss=0.142, lr=0.0001]
Steps:  34%|███▍      | 679/2000 [20:29<39:12,  1.78s/it, loss=0.201, lr=0.0001]
Steps:  34%|███▍      | 679/2000 [20:29<39:12,  1.78s/it, loss=0.214, lr=0.0001]
Steps:  34%|███▍      | 679/2000 [20:30<39:12,  1.78s/it, loss=0.189, lr=0.0001]
Steps:  34%|███▍      | 679/2000 [20:30<39:12,  1.78s/it, loss=0.176, lr=0.0001]
Steps:  34%|███▍      | 680/2000 [20:30<38:26,  1.75s/it, loss=0.176, lr=0.0001]
Steps:  34%|███▍      | 680/2000 [20:30<38:26,  1.75s/it, loss=0.388, lr=0.0001]
Steps:  34%|███▍      | 680/2000 [20:31<38:26,  1.75s/it, loss=0.318, lr=0.0001]
Steps:  34%|███▍      | 680/2000 [20:31<38:26,  1.75s/it, loss=0.199, lr=0.0001]
Steps:  34%|███▍      | 680/2000 [20:32<38:26,  1.75s/it, loss=0.791, lr=0.0001]
Steps:  34%|███▍      | 681/2000 [20:32<39:19,  1.79s/it, loss=0.791, lr=0.0001]
Steps:  34%|███▍      | 681/2000 [20:32<39:19,  1.79s/it, loss=0.202, lr=0.0001]
Steps:  34%|███▍      | 681/2000 [20:33<39:19,  1.79s/it, loss=0.12, lr=0.0001] 
Steps:  34%|███▍      | 681/2000 [20:33<39:19,  1.79s/it, loss=0.223, lr=0.0001]
Steps:  34%|███▍      | 681/2000 [20:34<39:19,  1.79s/it, loss=0.13, lr=0.0001] 
Steps:  34%|███▍      | 682/2000 [20:34<38:20,  1.75s/it, loss=0.13, lr=0.0001]
Steps:  34%|███▍      | 682/2000 [20:34<38:20,  1.75s/it, loss=0.663, lr=0.0001]
Steps:  34%|███▍      | 682/2000 [20:34<38:20,  1.75s/it, loss=0.991, lr=0.0001]
Steps:  34%|███▍      | 682/2000 [20:35<38:20,  1.75s/it, loss=0.174, lr=0.0001]
Steps:  34%|███▍      | 682/2000 [20:35<38:20,  1.75s/it, loss=0.0993, lr=0.0001]
Steps:  34%|███▍      | 683/2000 [20:36<37:42,  1.72s/it, loss=0.0993, lr=0.0001]
Steps:  34%|███▍      | 683/2000 [20:36<37:42,  1.72s/it, loss=0.0844, lr=0.0001]
Steps:  34%|███▍      | 683/2000 [20:36<37:42,  1.72s/it, loss=0.619, lr=0.0001] 
Steps:  34%|███▍      | 683/2000 [20:36<37:42,  1.72s/it, loss=0.24, lr=0.0001] 
Steps:  34%|███▍      | 683/2000 [20:37<37:42,  1.72s/it, loss=0.128, lr=0.0001]
Steps:  34%|███▍      | 684/2000 [20:38<38:41,  1.76s/it, loss=0.128, lr=0.0001]
Steps:  34%|███▍      | 684/2000 [20:38<38:41,  1.76s/it, loss=0.159, lr=0.0001]
Steps:  34%|███▍      | 684/2000 [20:38<38:41,  1.76s/it, loss=0.203, lr=0.0001]
Steps:  34%|███▍      | 684/2000 [20:38<38:41,  1.76s/it, loss=0.139, lr=0.0001]
Steps:  34%|███▍      | 684/2000 [20:39<38:41,  1.76s/it, loss=0.389, lr=0.0001]
Steps:  34%|███▍      | 685/2000 [20:39<38:06,  1.74s/it, loss=0.389, lr=0.0001]
Steps:  34%|███▍      | 685/2000 [20:39<38:06,  1.74s/it, loss=0.183, lr=0.0001]
Steps:  34%|███▍      | 685/2000 [20:40<38:06,  1.74s/it, loss=0.286, lr=0.0001]
Steps:  34%|███▍      | 685/2000 [20:40<38:06,  1.74s/it, loss=0.199, lr=0.0001]
Steps:  34%|███▍      | 685/2000 [20:40<38:06,  1.74s/it, loss=0.405, lr=0.0001]
Steps:  34%|███▍      | 686/2000 [20:41<37:24,  1.71s/it, loss=0.405, lr=0.0001]
Steps:  34%|███▍      | 686/2000 [20:41<37:24,  1.71s/it, loss=0.235, lr=0.0001]
Steps:  34%|███▍      | 686/2000 [20:41<37:24,  1.71s/it, loss=0.169, lr=0.0001]
Steps:  34%|███▍      | 686/2000 [20:42<37:24,  1.71s/it, loss=0.264, lr=0.0001]
Steps:  34%|███▍      | 686/2000 [20:42<37:24,  1.71s/it, loss=0.173, lr=0.0001]
Steps:  34%|███▍      | 687/2000 [20:43<38:58,  1.78s/it, loss=0.173, lr=0.0001]
Steps:  34%|███▍      | 687/2000 [20:43<38:58,  1.78s/it, loss=0.291, lr=0.0001]
Steps:  34%|███▍      | 687/2000 [20:43<38:58,  1.78s/it, loss=0.188, lr=0.0001]
Steps:  34%|███▍      | 687/2000 [20:44<38:58,  1.78s/it, loss=0.213, lr=0.0001]
Steps:  34%|███▍      | 687/2000 [20:44<38:58,  1.78s/it, loss=0.0687, lr=0.0001]
Steps:  34%|███▍      | 688/2000 [20:45<38:43,  1.77s/it, loss=0.0687, lr=0.0001]
Steps:  34%|███▍      | 688/2000 [20:45<38:43,  1.77s/it, loss=0.213, lr=0.0001] 
Steps:  34%|███▍      | 688/2000 [20:45<38:43,  1.77s/it, loss=0.083, lr=0.0001]
Steps:  34%|███▍      | 688/2000 [20:45<38:43,  1.77s/it, loss=0.155, lr=0.0001]
Steps:  34%|███▍      | 688/2000 [20:46<38:43,  1.77s/it, loss=1.56, lr=0.0001] 
Steps:  34%|███▍      | 689/2000 [20:46<38:28,  1.76s/it, loss=1.56, lr=0.0001]
Steps:  34%|███▍      | 689/2000 [20:46<38:28,  1.76s/it, loss=0.514, lr=0.0001]
Steps:  34%|███▍      | 689/2000 [20:47<38:28,  1.76s/it, loss=0.155, lr=0.0001]
Steps:  34%|███▍      | 689/2000 [20:47<38:28,  1.76s/it, loss=0.26, lr=0.0001] 
Steps:  34%|███▍      | 689/2000 [20:48<38:28,  1.76s/it, loss=0.826, lr=0.0001]
Steps:  34%|███▍      | 690/2000 [20:48<38:02,  1.74s/it, loss=0.826, lr=0.0001]
Steps:  34%|███▍      | 690/2000 [20:48<38:02,  1.74s/it, loss=0.841, lr=0.0001]
Steps:  34%|███▍      | 690/2000 [20:49<38:02,  1.74s/it, loss=0.153, lr=0.0001]
Steps:  34%|███▍      | 690/2000 [20:49<38:02,  1.74s/it, loss=0.212, lr=0.0001]
Steps:  34%|███▍      | 690/2000 [20:49<38:02,  1.74s/it, loss=0.243, lr=0.0001]
Steps:  35%|███▍      | 691/2000 [20:50<39:12,  1.80s/it, loss=0.243, lr=0.0001]
Steps:  35%|███▍      | 691/2000 [20:50<39:12,  1.80s/it, loss=0.101, lr=0.0001]
Steps:  35%|███▍      | 691/2000 [20:50<39:12,  1.80s/it, loss=0.229, lr=0.0001]
Steps:  35%|███▍      | 691/2000 [20:51<39:12,  1.80s/it, loss=0.227, lr=0.0001]
Steps:  35%|███▍      | 691/2000 [20:51<39:12,  1.80s/it, loss=0.0771, lr=0.0001]
Steps:  35%|███▍      | 692/2000 [20:52<38:28,  1.77s/it, loss=0.0771, lr=0.0001]
Steps:  35%|███▍      | 692/2000 [20:52<38:28,  1.77s/it, loss=0.129, lr=0.0001] 
Steps:  35%|███▍      | 692/2000 [20:52<38:28,  1.77s/it, loss=0.203, lr=0.0001]
Steps:  35%|███▍      | 692/2000 [20:52<38:28,  1.77s/it, loss=0.684, lr=0.0001]
Steps:  35%|███▍      | 692/2000 [20:53<38:28,  1.77s/it, loss=0.0947, lr=0.0001]
Steps:  35%|███▍      | 693/2000 [20:53<37:59,  1.74s/it, loss=0.0947, lr=0.0001]
Steps:  35%|███▍      | 693/2000 [20:53<37:59,  1.74s/it, loss=0.462, lr=0.0001] 
Steps:  35%|███▍      | 693/2000 [20:54<37:59,  1.74s/it, loss=0.183, lr=0.0001]
Steps:  35%|███▍      | 693/2000 [20:54<37:59,  1.74s/it, loss=0.493, lr=0.0001]
Steps:  35%|███▍      | 693/2000 [20:55<37:59,  1.74s/it, loss=0.159, lr=0.0001]
Steps:  35%|███▍      | 694/2000 [20:55<39:05,  1.80s/it, loss=0.159, lr=0.0001]
Steps:  35%|███▍      | 694/2000 [20:55<39:05,  1.80s/it, loss=0.164, lr=0.0001]
Steps:  35%|███▍      | 694/2000 [20:56<39:05,  1.80s/it, loss=0.18, lr=0.0001] 
Steps:  35%|███▍      | 694/2000 [20:56<39:05,  1.80s/it, loss=0.138, lr=0.0001]
Steps:  35%|███▍      | 694/2000 [20:56<39:05,  1.80s/it, loss=0.476, lr=0.0001]
Steps:  35%|███▍      | 695/2000 [20:57<38:08,  1.75s/it, loss=0.476, lr=0.0001]
Steps:  35%|███▍      | 695/2000 [20:57<38:08,  1.75s/it, loss=0.0735, lr=0.0001]
Steps:  35%|███▍      | 695/2000 [20:57<38:08,  1.75s/it, loss=0.123, lr=0.0001] 
Steps:  35%|███▍      | 695/2000 [20:58<38:08,  1.75s/it, loss=0.304, lr=0.0001]
Steps:  35%|███▍      | 695/2000 [20:58<38:08,  1.75s/it, loss=0.166, lr=0.0001]
Steps:  35%|███▍      | 696/2000 [20:59<37:27,  1.72s/it, loss=0.166, lr=0.0001]
Steps:  35%|███▍      | 696/2000 [20:59<37:27,  1.72s/it, loss=0.537, lr=0.0001]
Steps:  35%|███▍      | 696/2000 [20:59<37:27,  1.72s/it, loss=0.0632, lr=0.0001]
Steps:  35%|███▍      | 696/2000 [21:00<37:27,  1.72s/it, loss=0.275, lr=0.0001] 
Steps:  35%|███▍      | 696/2000 [21:00<37:27,  1.72s/it, loss=0.159, lr=0.0001]
Steps:  35%|███▍      | 697/2000 [21:00<38:33,  1.78s/it, loss=0.159, lr=0.0001]
Steps:  35%|███▍      | 697/2000 [21:00<38:33,  1.78s/it, loss=0.325, lr=0.0001]
Steps:  35%|███▍      | 697/2000 [21:01<38:33,  1.78s/it, loss=0.199, lr=0.0001]
Steps:  35%|███▍      | 697/2000 [21:01<38:33,  1.78s/it, loss=0.0767, lr=0.0001]
Steps:  35%|███▍      | 697/2000 [21:02<38:33,  1.78s/it, loss=0.152, lr=0.0001] 
Steps:  35%|███▍      | 698/2000 [21:02<37:54,  1.75s/it, loss=0.152, lr=0.0001]
Steps:  35%|███▍      | 698/2000 [21:02<37:54,  1.75s/it, loss=0.137, lr=0.0001]
Steps:  35%|███▍      | 698/2000 [21:02<37:54,  1.75s/it, loss=0.12, lr=0.0001] 
Steps:  35%|███▍      | 698/2000 [21:03<37:54,  1.75s/it, loss=0.117, lr=0.0001]
Steps:  35%|███▍      | 698/2000 [21:03<37:54,  1.75s/it, loss=0.189, lr=0.0001]
Steps:  35%|███▍      | 699/2000 [21:04<37:24,  1.73s/it, loss=0.189, lr=0.0001]
Steps:  35%|███▍      | 699/2000 [21:04<37:24,  1.73s/it, loss=0.163, lr=0.0001]
Steps:  35%|███▍      | 699/2000 [21:04<37:24,  1.73s/it, loss=0.209, lr=0.0001]
Steps:  35%|███▍      | 699/2000 [21:05<37:24,  1.73s/it, loss=0.218, lr=0.0001]
Steps:  35%|███▍      | 699/2000 [21:05<37:24,  1.73s/it, loss=0.926, lr=0.0001]
Steps:  35%|███▌      | 700/2000 [21:06<39:09,  1.81s/it, loss=0.926, lr=0.0001]
Steps:  35%|███▌      | 700/2000 [21:06<39:09,  1.81s/it, loss=0.131, lr=0.0001]
Steps:  35%|███▌      | 700/2000 [21:06<39:09,  1.81s/it, loss=0.121, lr=0.0001]
Steps:  35%|███▌      | 700/2000 [21:07<39:09,  1.81s/it, loss=0.146, lr=0.0001]
Steps:  35%|███▌      | 700/2000 [21:07<39:09,  1.81s/it, loss=0.141, lr=0.0001]
Steps:  35%|███▌      | 701/2000 [21:07<38:20,  1.77s/it, loss=0.141, lr=0.0001]
Steps:  35%|███▌      | 701/2000 [21:07<38:20,  1.77s/it, loss=0.161, lr=0.0001]
Steps:  35%|███▌      | 701/2000 [21:08<38:20,  1.77s/it, loss=0.0655, lr=0.0001]
Steps:  35%|███▌      | 701/2000 [21:08<38:20,  1.77s/it, loss=0.198, lr=0.0001] 
Steps:  35%|███▌      | 701/2000 [21:09<38:20,  1.77s/it, loss=0.141, lr=0.0001]
Steps:  35%|███▌      | 702/2000 [21:09<37:55,  1.75s/it, loss=0.141, lr=0.0001]
Steps:  35%|███▌      | 702/2000 [21:09<37:55,  1.75s/it, loss=0.111, lr=0.0001]
Steps:  35%|███▌      | 702/2000 [21:10<37:55,  1.75s/it, loss=0.134, lr=0.0001]
Steps:  35%|███▌      | 702/2000 [21:10<37:55,  1.75s/it, loss=0.113, lr=0.0001]
Steps:  35%|███▌      | 702/2000 [21:11<37:55,  1.75s/it, loss=0.197, lr=0.0001]
Steps:  35%|███▌      | 703/2000 [21:11<39:00,  1.80s/it, loss=0.197, lr=0.0001]
Steps:  35%|███▌      | 703/2000 [21:11<39:00,  1.80s/it, loss=0.183, lr=0.0001]
Steps:  35%|███▌      | 703/2000 [21:11<39:00,  1.80s/it, loss=0.201, lr=0.0001]
Steps:  35%|███▌      | 703/2000 [21:12<39:00,  1.80s/it, loss=0.118, lr=0.0001]
Steps:  35%|███▌      | 703/2000 [21:12<39:00,  1.80s/it, loss=0.184, lr=0.0001]
Steps:  35%|███▌      | 704/2000 [21:13<38:17,  1.77s/it, loss=0.184, lr=0.0001]
Steps:  35%|███▌      | 704/2000 [21:13<38:17,  1.77s/it, loss=0.218, lr=0.0001]
Steps:  35%|███▌      | 704/2000 [21:13<38:17,  1.77s/it, loss=1.28, lr=0.0001] 
Steps:  35%|███▌      | 704/2000 [21:14<38:17,  1.77s/it, loss=0.37, lr=0.0001]
Steps:  35%|███▌      | 704/2000 [21:14<38:17,  1.77s/it, loss=0.142, lr=0.0001]
Steps:  35%|███▌      | 705/2000 [21:14<37:45,  1.75s/it, loss=0.142, lr=0.0001]
Steps:  35%|███▌      | 705/2000 [21:14<37:45,  1.75s/it, loss=0.211, lr=0.0001]
Steps:  35%|███▌      | 705/2000 [21:15<37:45,  1.75s/it, loss=0.164, lr=0.0001]
Steps:  35%|███▌      | 705/2000 [21:15<37:45,  1.75s/it, loss=0.165, lr=0.0001]
Steps:  35%|███▌      | 705/2000 [21:16<37:45,  1.75s/it, loss=0.132, lr=0.0001]
Steps:  35%|███▌      | 706/2000 [21:16<39:23,  1.83s/it, loss=0.132, lr=0.0001]
Steps:  35%|███▌      | 706/2000 [21:16<39:23,  1.83s/it, loss=0.209, lr=0.0001]
Steps:  35%|███▌      | 706/2000 [21:17<39:23,  1.83s/it, loss=0.232, lr=0.0001]
Steps:  35%|███▌      | 706/2000 [21:17<39:23,  1.83s/it, loss=0.207, lr=0.0001]
Steps:  35%|███▌      | 706/2000 [21:18<39:23,  1.83s/it, loss=0.276, lr=0.0001]
Steps:  35%|███▌      | 707/2000 [21:18<38:53,  1.80s/it, loss=0.276, lr=0.0001]
Steps:  35%|███▌      | 707/2000 [21:18<38:53,  1.80s/it, loss=0.196, lr=0.0001]
Steps:  35%|███▌      | 707/2000 [21:19<38:53,  1.80s/it, loss=0.0945, lr=0.0001]
Steps:  35%|███▌      | 707/2000 [21:19<38:53,  1.80s/it, loss=0.149, lr=0.0001] 
Steps:  35%|███▌      | 707/2000 [21:20<38:53,  1.80s/it, loss=0.263, lr=0.0001]
Steps:  35%|███▌      | 708/2000 [21:20<38:13,  1.77s/it, loss=0.263, lr=0.0001]
Steps:  35%|███▌      | 708/2000 [21:20<38:13,  1.77s/it, loss=0.0996, lr=0.0001]
Steps:  35%|███▌      | 708/2000 [21:20<38:13,  1.77s/it, loss=0.0814, lr=0.0001]
Steps:  35%|███▌      | 708/2000 [21:21<38:13,  1.77s/it, loss=0.143, lr=0.0001] 
Steps:  35%|███▌      | 708/2000 [21:21<38:13,  1.77s/it, loss=0.146, lr=0.0001]
Steps:  35%|███▌      | 709/2000 [21:22<39:04,  1.82s/it, loss=0.146, lr=0.0001]
Steps:  35%|███▌      | 709/2000 [21:22<39:04,  1.82s/it, loss=0.154, lr=0.0001]
Steps:  35%|███▌      | 709/2000 [21:22<39:04,  1.82s/it, loss=0.151, lr=0.0001]
Steps:  35%|███▌      | 709/2000 [21:23<39:04,  1.82s/it, loss=0.375, lr=0.0001]
Steps:  35%|███▌      | 709/2000 [21:23<39:04,  1.82s/it, loss=0.431, lr=0.0001]
Steps:  36%|███▌      | 710/2000 [21:24<38:09,  1.77s/it, loss=0.431, lr=0.0001]
Steps:  36%|███▌      | 710/2000 [21:24<38:09,  1.77s/it, loss=0.228, lr=0.0001]
Steps:  36%|███▌      | 710/2000 [21:24<38:09,  1.77s/it, loss=0.12, lr=0.0001] 
Steps:  36%|███▌      | 710/2000 [21:24<38:09,  1.77s/it, loss=0.155, lr=0.0001]
Steps:  36%|███▌      | 710/2000 [21:25<38:09,  1.77s/it, loss=0.108, lr=0.0001]
Steps:  36%|███▌      | 711/2000 [21:25<37:28,  1.74s/it, loss=0.108, lr=0.0001]
Steps:  36%|███▌      | 711/2000 [21:25<37:28,  1.74s/it, loss=0.249, lr=0.0001]
Steps:  36%|███▌      | 711/2000 [21:26<37:28,  1.74s/it, loss=0.183, lr=0.0001]
Steps:  36%|███▌      | 711/2000 [21:26<37:28,  1.74s/it, loss=0.236, lr=0.0001]
Steps:  36%|███▌      | 711/2000 [21:26<37:28,  1.74s/it, loss=0.0965, lr=0.0001]
Steps:  36%|███▌      | 712/2000 [21:27<36:59,  1.72s/it, loss=0.0965, lr=0.0001]
Steps:  36%|███▌      | 712/2000 [21:27<36:59,  1.72s/it, loss=0.0598, lr=0.0001]
Steps:  36%|███▌      | 712/2000 [21:28<36:59,  1.72s/it, loss=0.191, lr=0.0001] 
Steps:  36%|███▌      | 712/2000 [21:28<36:59,  1.72s/it, loss=0.184, lr=0.0001]
Steps:  36%|███▌      | 712/2000 [21:28<36:59,  1.72s/it, loss=0.152, lr=0.0001]
Steps:  36%|███▌      | 713/2000 [21:29<38:08,  1.78s/it, loss=0.152, lr=0.0001]
Steps:  36%|███▌      | 713/2000 [21:29<38:08,  1.78s/it, loss=0.254, lr=0.0001]
Steps:  36%|███▌      | 713/2000 [21:29<38:08,  1.78s/it, loss=0.254, lr=0.0001]
Steps:  36%|███▌      | 713/2000 [21:30<38:08,  1.78s/it, loss=0.416, lr=0.0001]
Steps:  36%|███▌      | 713/2000 [21:30<38:08,  1.78s/it, loss=0.212, lr=0.0001]
Steps:  36%|███▌      | 714/2000 [21:30<37:29,  1.75s/it, loss=0.212, lr=0.0001]
Steps:  36%|███▌      | 714/2000 [21:30<37:29,  1.75s/it, loss=0.23, lr=0.0001] 
Steps:  36%|███▌      | 714/2000 [21:31<37:29,  1.75s/it, loss=0.337, lr=0.0001]
Steps:  36%|███▌      | 714/2000 [21:31<37:29,  1.75s/it, loss=0.122, lr=0.0001]
Steps:  36%|███▌      | 714/2000 [21:32<37:29,  1.75s/it, loss=0.125, lr=0.0001]
Steps:  36%|███▌      | 715/2000 [21:32<37:08,  1.73s/it, loss=0.125, lr=0.0001]
Steps:  36%|███▌      | 715/2000 [21:32<37:08,  1.73s/it, loss=0.22, lr=0.0001] 
Steps:  36%|███▌      | 715/2000 [21:33<37:08,  1.73s/it, loss=0.12, lr=0.0001]
Steps:  36%|███▌      | 715/2000 [21:33<37:08,  1.73s/it, loss=0.0726, lr=0.0001]
Steps:  36%|███▌      | 715/2000 [21:34<37:08,  1.73s/it, loss=0.822, lr=0.0001] 
Steps:  36%|███▌      | 716/2000 [21:34<38:07,  1.78s/it, loss=0.822, lr=0.0001]
Steps:  36%|███▌      | 716/2000 [21:34<38:07,  1.78s/it, loss=0.0775, lr=0.0001]
Steps:  36%|███▌      | 716/2000 [21:34<38:07,  1.78s/it, loss=0.156, lr=0.0001] 
Steps:  36%|███▌      | 716/2000 [21:35<38:07,  1.78s/it, loss=0.107, lr=0.0001]
Steps:  36%|███▌      | 716/2000 [21:35<38:07,  1.78s/it, loss=0.13, lr=0.0001] 
Steps:  36%|███▌      | 717/2000 [21:36<37:19,  1.75s/it, loss=0.13, lr=0.0001]
Steps:  36%|███▌      | 717/2000 [21:36<37:19,  1.75s/it, loss=0.244, lr=0.0001]
Steps:  36%|███▌      | 717/2000 [21:36<37:19,  1.75s/it, loss=0.124, lr=0.0001]
Steps:  36%|███▌      | 717/2000 [21:37<37:19,  1.75s/it, loss=0.115, lr=0.0001]
Steps:  36%|███▌      | 717/2000 [21:37<37:19,  1.75s/it, loss=0.285, lr=0.0001]
Steps:  36%|███▌      | 718/2000 [21:37<36:41,  1.72s/it, loss=0.285, lr=0.0001]
Steps:  36%|███▌      | 718/2000 [21:37<36:41,  1.72s/it, loss=0.135, lr=0.0001]
Steps:  36%|███▌      | 718/2000 [21:38<36:41,  1.72s/it, loss=0.229, lr=0.0001]
Steps:  36%|███▌      | 718/2000 [21:38<36:41,  1.72s/it, loss=0.0849, lr=0.0001]
Steps:  36%|███▌      | 718/2000 [21:39<36:41,  1.72s/it, loss=0.147, lr=0.0001] 
Steps:  36%|███▌      | 719/2000 [21:39<37:48,  1.77s/it, loss=0.147, lr=0.0001]
Steps:  36%|███▌      | 719/2000 [21:39<37:48,  1.77s/it, loss=0.0664, lr=0.0001]
Steps:  36%|███▌      | 719/2000 [21:40<37:48,  1.77s/it, loss=0.975, lr=0.0001] 
Steps:  36%|███▌      | 719/2000 [21:40<37:48,  1.77s/it, loss=0.125, lr=0.0001]
Steps:  36%|███▌      | 719/2000 [21:41<37:48,  1.77s/it, loss=0.104, lr=0.0001]
Steps:  36%|███▌      | 720/2000 [21:41<37:12,  1.74s/it, loss=0.104, lr=0.0001]
Steps:  36%|███▌      | 720/2000 [21:41<37:12,  1.74s/it, loss=0.268, lr=0.0001]
Steps:  36%|███▌      | 720/2000 [21:41<37:12,  1.74s/it, loss=0.153, lr=0.0001]
Steps:  36%|███▌      | 720/2000 [21:42<37:12,  1.74s/it, loss=0.119, lr=0.0001]
Steps:  36%|███▌      | 720/2000 [21:42<37:12,  1.74s/it, loss=0.236, lr=0.0001]
Steps:  36%|███▌      | 721/2000 [21:43<36:40,  1.72s/it, loss=0.236, lr=0.0001]
Steps:  36%|███▌      | 721/2000 [21:43<36:40,  1.72s/it, loss=0.187, lr=0.0001]
Steps:  36%|███▌      | 721/2000 [21:43<36:40,  1.72s/it, loss=0.237, lr=0.0001]
Steps:  36%|███▌      | 721/2000 [21:43<36:40,  1.72s/it, loss=0.271, lr=0.0001]
Steps:  36%|███▌      | 721/2000 [21:44<36:40,  1.72s/it, loss=0.214, lr=0.0001]
Steps:  36%|███▌      | 722/2000 [21:45<37:43,  1.77s/it, loss=0.214, lr=0.0001]
Steps:  36%|███▌      | 722/2000 [21:45<37:43,  1.77s/it, loss=0.0871, lr=0.0001]
Steps:  36%|███▌      | 722/2000 [21:45<37:43,  1.77s/it, loss=0.1, lr=0.0001]   
Steps:  36%|███▌      | 722/2000 [21:45<37:43,  1.77s/it, loss=0.181, lr=0.0001]
Steps:  36%|███▌      | 722/2000 [21:46<37:43,  1.77s/it, loss=0.232, lr=0.0001]
Steps:  36%|███▌      | 723/2000 [21:46<37:04,  1.74s/it, loss=0.232, lr=0.0001]
Steps:  36%|███▌      | 723/2000 [21:46<37:04,  1.74s/it, loss=0.145, lr=0.0001]
Steps:  36%|███▌      | 723/2000 [21:47<37:04,  1.74s/it, loss=0.105, lr=0.0001]
Steps:  36%|███▌      | 723/2000 [21:47<37:04,  1.74s/it, loss=0.185, lr=0.0001]
Steps:  36%|███▌      | 723/2000 [21:47<37:04,  1.74s/it, loss=0.174, lr=0.0001]
Steps:  36%|███▌      | 724/2000 [21:48<36:31,  1.72s/it, loss=0.174, lr=0.0001]
Steps:  36%|███▌      | 724/2000 [21:48<36:31,  1.72s/it, loss=0.177, lr=0.0001]
Steps:  36%|███▌      | 724/2000 [21:48<36:31,  1.72s/it, loss=0.174, lr=0.0001]
Steps:  36%|███▌      | 724/2000 [21:49<36:31,  1.72s/it, loss=0.16, lr=0.0001] 
Steps:  36%|███▌      | 724/2000 [21:49<36:31,  1.72s/it, loss=0.118, lr=0.0001]
Steps:  36%|███▋      | 725/2000 [21:50<37:45,  1.78s/it, loss=0.118, lr=0.0001]
Steps:  36%|███▋      | 725/2000 [21:50<37:45,  1.78s/it, loss=0.216, lr=0.0001]
Steps:  36%|███▋      | 725/2000 [21:50<37:45,  1.78s/it, loss=0.344, lr=0.0001]
Steps:  36%|███▋      | 725/2000 [21:51<37:45,  1.78s/it, loss=0.166, lr=0.0001]
Steps:  36%|███▋      | 725/2000 [21:51<37:45,  1.78s/it, loss=0.509, lr=0.0001]
Steps:  36%|███▋      | 726/2000 [21:52<37:31,  1.77s/it, loss=0.509, lr=0.0001]
Steps:  36%|███▋      | 726/2000 [21:52<37:31,  1.77s/it, loss=0.191, lr=0.0001]
Steps:  36%|███▋      | 726/2000 [21:52<37:31,  1.77s/it, loss=0.26, lr=0.0001] 
Steps:  36%|███▋      | 726/2000 [21:52<37:31,  1.77s/it, loss=0.905, lr=0.0001]
Steps:  36%|███▋      | 726/2000 [21:53<37:31,  1.77s/it, loss=0.256, lr=0.0001]
Steps:  36%|███▋      | 727/2000 [21:53<36:48,  1.74s/it, loss=0.256, lr=0.0001]
Steps:  36%|███▋      | 727/2000 [21:53<36:48,  1.74s/it, loss=0.339, lr=0.0001]
Steps:  36%|███▋      | 727/2000 [21:54<36:48,  1.74s/it, loss=0.782, lr=0.0001]
Steps:  36%|███▋      | 727/2000 [21:54<36:48,  1.74s/it, loss=0.175, lr=0.0001]
Steps:  36%|███▋      | 727/2000 [21:54<36:48,  1.74s/it, loss=0.308, lr=0.0001]
Steps:  36%|███▋      | 728/2000 [21:55<37:50,  1.78s/it, loss=0.308, lr=0.0001]
Steps:  36%|███▋      | 728/2000 [21:55<37:50,  1.78s/it, loss=0.131, lr=0.0001]
Steps:  36%|███▋      | 728/2000 [21:55<37:50,  1.78s/it, loss=0.115, lr=0.0001]
Steps:  36%|███▋      | 728/2000 [21:56<37:50,  1.78s/it, loss=0.215, lr=0.0001]
Steps:  36%|███▋      | 728/2000 [21:56<37:50,  1.78s/it, loss=0.915, lr=0.0001]
Steps:  36%|███▋      | 729/2000 [21:57<36:55,  1.74s/it, loss=0.915, lr=0.0001]
Steps:  36%|███▋      | 729/2000 [21:57<36:55,  1.74s/it, loss=0.279, lr=0.0001]
Steps:  36%|███▋      | 729/2000 [21:57<36:55,  1.74s/it, loss=0.636, lr=0.0001]
Steps:  36%|███▋      | 729/2000 [21:58<36:55,  1.74s/it, loss=0.124, lr=0.0001]
Steps:  36%|███▋      | 729/2000 [21:58<36:55,  1.74s/it, loss=0.186, lr=0.0001]
Steps:  36%|███▋      | 730/2000 [21:58<36:20,  1.72s/it, loss=0.186, lr=0.0001]
Steps:  36%|███▋      | 730/2000 [21:58<36:20,  1.72s/it, loss=0.257, lr=0.0001]
Steps:  36%|███▋      | 730/2000 [21:59<36:20,  1.72s/it, loss=0.18, lr=0.0001] 
Steps:  36%|███▋      | 730/2000 [21:59<36:20,  1.72s/it, loss=0.277, lr=0.0001]
Steps:  36%|███▋      | 730/2000 [22:00<36:20,  1.72s/it, loss=0.363, lr=0.0001]
Steps:  37%|███▋      | 731/2000 [22:00<35:58,  1.70s/it, loss=0.363, lr=0.0001]
Steps:  37%|███▋      | 731/2000 [22:00<35:58,  1.70s/it, loss=0.21, lr=0.0001] 
Steps:  37%|███▋      | 731/2000 [22:01<35:58,  1.70s/it, loss=0.241, lr=0.0001]
Steps:  37%|███▋      | 731/2000 [22:01<35:58,  1.70s/it, loss=0.32, lr=0.0001] 
Steps:  37%|███▋      | 731/2000 [22:01<35:58,  1.70s/it, loss=0.722, lr=0.0001]
Steps:  37%|███▋      | 732/2000 [22:02<37:17,  1.76s/it, loss=0.722, lr=0.0001]
Steps:  37%|███▋      | 732/2000 [22:02<37:17,  1.76s/it, loss=0.179, lr=0.0001]
Steps:  37%|███▋      | 732/2000 [22:02<37:17,  1.76s/it, loss=0.137, lr=0.0001]
Steps:  37%|███▋      | 732/2000 [22:03<37:17,  1.76s/it, loss=0.168, lr=0.0001]
Steps:  37%|███▋      | 732/2000 [22:03<37:17,  1.76s/it, loss=0.196, lr=0.0001]
Steps:  37%|███▋      | 733/2000 [22:04<36:39,  1.74s/it, loss=0.196, lr=0.0001]
Steps:  37%|███▋      | 733/2000 [22:04<36:39,  1.74s/it, loss=0.131, lr=0.0001]
Steps:  37%|███▋      | 733/2000 [22:04<36:39,  1.74s/it, loss=0.383, lr=0.0001]
Steps:  37%|███▋      | 733/2000 [22:04<36:39,  1.74s/it, loss=0.163, lr=0.0001]
Steps:  37%|███▋      | 733/2000 [22:05<36:39,  1.74s/it, loss=0.135, lr=0.0001]
Steps:  37%|███▋      | 734/2000 [22:05<36:26,  1.73s/it, loss=0.135, lr=0.0001]
Steps:  37%|███▋      | 734/2000 [22:05<36:26,  1.73s/it, loss=0.24, lr=0.0001] 
Steps:  37%|███▋      | 734/2000 [22:06<36:26,  1.73s/it, loss=0.152, lr=0.0001]
Steps:  37%|███▋      | 734/2000 [22:06<36:26,  1.73s/it, loss=0.115, lr=0.0001]
Steps:  37%|███▋      | 734/2000 [22:07<36:26,  1.73s/it, loss=0.252, lr=0.0001]
Steps:  37%|███▋      | 735/2000 [22:07<37:29,  1.78s/it, loss=0.252, lr=0.0001]
Steps:  37%|███▋      | 735/2000 [22:07<37:29,  1.78s/it, loss=0.191, lr=0.0001]
Steps:  37%|███▋      | 735/2000 [22:08<37:29,  1.78s/it, loss=0.14, lr=0.0001] 
Steps:  37%|███▋      | 735/2000 [22:08<37:29,  1.78s/it, loss=0.159, lr=0.0001]
Steps:  37%|███▋      | 735/2000 [22:08<37:29,  1.78s/it, loss=0.223, lr=0.0001]
Steps:  37%|███▋      | 736/2000 [22:09<36:43,  1.74s/it, loss=0.223, lr=0.0001]
Steps:  37%|███▋      | 736/2000 [22:09<36:43,  1.74s/it, loss=0.186, lr=0.0001]
Steps:  37%|███▋      | 736/2000 [22:09<36:43,  1.74s/it, loss=0.412, lr=0.0001]
Steps:  37%|███▋      | 736/2000 [22:10<36:43,  1.74s/it, loss=0.304, lr=0.0001]
Steps:  37%|███▋      | 736/2000 [22:10<36:43,  1.74s/it, loss=0.156, lr=0.0001]
Steps:  37%|███▋      | 737/2000 [22:11<36:05,  1.71s/it, loss=0.156, lr=0.0001]
Steps:  37%|███▋      | 737/2000 [22:11<36:05,  1.71s/it, loss=0.148, lr=0.0001]
Steps:  37%|███▋      | 737/2000 [22:11<36:05,  1.71s/it, loss=0.105, lr=0.0001]
Steps:  37%|███▋      | 737/2000 [22:12<36:05,  1.71s/it, loss=0.0997, lr=0.0001]
Steps:  37%|███▋      | 737/2000 [22:12<36:05,  1.71s/it, loss=0.195, lr=0.0001] 
Steps:  37%|███▋      | 738/2000 [22:12<37:26,  1.78s/it, loss=0.195, lr=0.0001]
Steps:  37%|███▋      | 738/2000 [22:12<37:26,  1.78s/it, loss=0.1, lr=0.0001]  
Steps:  37%|███▋      | 738/2000 [22:13<37:26,  1.78s/it, loss=0.212, lr=0.0001]
Steps:  37%|███▋      | 738/2000 [22:13<37:26,  1.78s/it, loss=0.107, lr=0.0001]
Steps:  37%|███▋      | 738/2000 [22:14<37:26,  1.78s/it, loss=0.247, lr=0.0001]
Steps:  37%|███▋      | 739/2000 [22:14<36:55,  1.76s/it, loss=0.247, lr=0.0001]
Steps:  37%|███▋      | 739/2000 [22:14<36:55,  1.76s/it, loss=0.182, lr=0.0001]
Steps:  37%|███▋      | 739/2000 [22:15<36:55,  1.76s/it, loss=0.15, lr=0.0001] 
Steps:  37%|███▋      | 739/2000 [22:15<36:55,  1.76s/it, loss=0.144, lr=0.0001]
Steps:  37%|███▋      | 739/2000 [22:15<36:55,  1.76s/it, loss=0.198, lr=0.0001]
Steps:  37%|███▋      | 740/2000 [22:16<36:20,  1.73s/it, loss=0.198, lr=0.0001]
Steps:  37%|███▋      | 740/2000 [22:16<36:20,  1.73s/it, loss=0.152, lr=0.0001]
Steps:  37%|███▋      | 740/2000 [22:16<36:20,  1.73s/it, loss=0.258, lr=0.0001]
Steps:  37%|███▋      | 740/2000 [22:17<36:20,  1.73s/it, loss=0.221, lr=0.0001]
Steps:  37%|███▋      | 740/2000 [22:17<36:20,  1.73s/it, loss=0.421, lr=0.0001]
Steps:  37%|███▋      | 741/2000 [22:18<37:28,  1.79s/it, loss=0.421, lr=0.0001]
Steps:  37%|███▋      | 741/2000 [22:18<37:28,  1.79s/it, loss=0.235, lr=0.0001]
Steps:  37%|███▋      | 741/2000 [22:18<37:28,  1.79s/it, loss=0.199, lr=0.0001]
Steps:  37%|███▋      | 741/2000 [22:19<37:28,  1.79s/it, loss=0.194, lr=0.0001]
Steps:  37%|███▋      | 741/2000 [22:19<37:28,  1.79s/it, loss=1.41, lr=0.0001] 
Steps:  37%|███▋      | 742/2000 [22:19<36:53,  1.76s/it, loss=1.41, lr=0.0001]
Steps:  37%|███▋      | 742/2000 [22:19<36:53,  1.76s/it, loss=0.237, lr=0.0001]
Steps:  37%|███▋      | 742/2000 [22:20<36:53,  1.76s/it, loss=0.161, lr=0.0001]
Steps:  37%|███▋      | 742/2000 [22:20<36:53,  1.76s/it, loss=0.1, lr=0.0001]  
Steps:  37%|███▋      | 742/2000 [22:21<36:53,  1.76s/it, loss=0.165, lr=0.0001]
Steps:  37%|███▋      | 743/2000 [22:21<36:32,  1.74s/it, loss=0.165, lr=0.0001]
Steps:  37%|███▋      | 743/2000 [22:21<36:32,  1.74s/it, loss=0.188, lr=0.0001]
Steps:  37%|███▋      | 743/2000 [22:22<36:32,  1.74s/it, loss=0.264, lr=0.0001]
Steps:  37%|███▋      | 743/2000 [22:22<36:32,  1.74s/it, loss=0.181, lr=0.0001]
Steps:  37%|███▋      | 743/2000 [22:22<36:32,  1.74s/it, loss=0.213, lr=0.0001]
Steps:  37%|███▋      | 744/2000 [22:23<37:26,  1.79s/it, loss=0.213, lr=0.0001]
Steps:  37%|███▋      | 744/2000 [22:23<37:26,  1.79s/it, loss=0.133, lr=0.0001]
Steps:  37%|███▋      | 744/2000 [22:23<37:26,  1.79s/it, loss=0.192, lr=0.0001]
Steps:  37%|███▋      | 744/2000 [22:24<37:26,  1.79s/it, loss=0.169, lr=0.0001]
Steps:  37%|███▋      | 744/2000 [22:24<37:26,  1.79s/it, loss=0.209, lr=0.0001]
Steps:  37%|███▋      | 745/2000 [22:25<36:44,  1.76s/it, loss=0.209, lr=0.0001]
Steps:  37%|███▋      | 745/2000 [22:25<36:44,  1.76s/it, loss=0.0974, lr=0.0001]
Steps:  37%|███▋      | 745/2000 [22:25<36:44,  1.76s/it, loss=0.141, lr=0.0001] 
Steps:  37%|███▋      | 745/2000 [22:26<36:44,  1.76s/it, loss=0.412, lr=0.0001]
Steps:  37%|███▋      | 745/2000 [22:26<36:44,  1.76s/it, loss=0.222, lr=0.0001]
Steps:  37%|███▋      | 746/2000 [22:26<36:15,  1.73s/it, loss=0.222, lr=0.0001]
Steps:  37%|███▋      | 746/2000 [22:26<36:15,  1.73s/it, loss=1.01, lr=0.0001] 
Steps:  37%|███▋      | 746/2000 [22:27<36:15,  1.73s/it, loss=0.189, lr=0.0001]
Steps:  37%|███▋      | 746/2000 [22:27<36:15,  1.73s/it, loss=0.2, lr=0.0001]  
Steps:  37%|███▋      | 746/2000 [22:28<36:15,  1.73s/it, loss=0.316, lr=0.0001]
Steps:  37%|███▋      | 747/2000 [22:28<37:44,  1.81s/it, loss=0.316, lr=0.0001]
Steps:  37%|███▋      | 747/2000 [22:28<37:44,  1.81s/it, loss=0.136, lr=0.0001]
Steps:  37%|███▋      | 747/2000 [22:29<37:44,  1.81s/it, loss=0.145, lr=0.0001]
Steps:  37%|███▋      | 747/2000 [22:29<37:44,  1.81s/it, loss=0.0839, lr=0.0001]
Steps:  37%|███▋      | 747/2000 [22:30<37:44,  1.81s/it, loss=0.231, lr=0.0001] 
Steps:  37%|███▋      | 748/2000 [22:30<37:22,  1.79s/it, loss=0.231, lr=0.0001]
Steps:  37%|███▋      | 748/2000 [22:30<37:22,  1.79s/it, loss=0.55, lr=0.0001] 
Steps:  37%|███▋      | 748/2000 [22:31<37:22,  1.79s/it, loss=0.875, lr=0.0001]
Steps:  37%|███▋      | 748/2000 [22:31<37:22,  1.79s/it, loss=0.149, lr=0.0001]
Steps:  37%|███▋      | 748/2000 [22:31<37:22,  1.79s/it, loss=0.946, lr=0.0001]
Steps:  37%|███▋      | 749/2000 [22:32<37:07,  1.78s/it, loss=0.946, lr=0.0001]
Steps:  37%|███▋      | 749/2000 [22:32<37:07,  1.78s/it, loss=0.16, lr=0.0001] 
Steps:  37%|███▋      | 749/2000 [22:32<37:07,  1.78s/it, loss=0.298, lr=0.0001]
Steps:  37%|███▋      | 749/2000 [22:33<37:07,  1.78s/it, loss=0.261, lr=0.0001]
Steps:  37%|███▋      | 749/2000 [22:33<37:07,  1.78s/it, loss=0.0766, lr=0.0001]
Steps:  38%|███▊      | 750/2000 [22:34<36:30,  1.75s/it, loss=0.0766, lr=0.0001]05/30/2026 08:54:59 - INFO - accelerate.accelerator - [RANK 0] Saving current state to /workspace/output/flux-dev-apple-emoji-lora/checkpoint-750
Model weights saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-750/pytorch_lora_weights.safetensors
05/30/2026 08:55:00 - INFO - accelerate.checkpointing - [RANK 0] Optimizer state saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-750/optimizer.bin
05/30/2026 08:55:00 - INFO - accelerate.checkpointing - [RANK 0] Scheduler state saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-750/scheduler.bin
05/30/2026 08:55:00 - INFO - accelerate.checkpointing - [RANK 0] Sampler state for dataloader 0 saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-750/sampler.bin
05/30/2026 08:55:00 - INFO - accelerate.checkpointing - [RANK 0] Random states saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-750/random_states_0.pkl
05/30/2026 08:55:00 - INFO - __main__ - [RANK 0] Saved state to /workspace/output/flux-dev-apple-emoji-lora/checkpoint-750

Steps:  38%|███▊      | 750/2000 [22:35<36:30,  1.75s/it, loss=0.134, lr=0.0001] 
Steps:  38%|███▊      | 750/2000 [22:35<36:30,  1.75s/it, loss=0.22, lr=0.0001] 
Steps:  38%|███▊      | 750/2000 [22:36<36:30,  1.75s/it, loss=0.155, lr=0.0001]
Steps:  38%|███▊      | 750/2000 [22:36<36:30,  1.75s/it, loss=0.167, lr=0.0001]
Steps:  38%|███▊      | 751/2000 [22:36<42:52,  2.06s/it, loss=0.167, lr=0.0001]
Steps:  38%|███▊      | 751/2000 [22:36<42:52,  2.06s/it, loss=0.116, lr=0.0001]
Steps:  38%|███▊      | 751/2000 [22:37<42:52,  2.06s/it, loss=0.239, lr=0.0001]
Steps:  38%|███▊      | 751/2000 [22:37<42:52,  2.06s/it, loss=0.137, lr=0.0001]
Steps:  38%|███▊      | 751/2000 [22:38<42:52,  2.06s/it, loss=0.073, lr=0.0001]
Steps:  38%|███▊      | 752/2000 [22:38<40:27,  1.95s/it, loss=0.073, lr=0.0001]
Steps:  38%|███▊      | 752/2000 [22:38<40:27,  1.95s/it, loss=0.249, lr=0.0001]
Steps:  38%|███▊      | 752/2000 [22:38<40:27,  1.95s/it, loss=0.321, lr=0.0001]
Steps:  38%|███▊      | 752/2000 [22:39<40:27,  1.95s/it, loss=0.169, lr=0.0001]
Steps:  38%|███▊      | 752/2000 [22:39<40:27,  1.95s/it, loss=0.0952, lr=0.0001]
Steps:  38%|███▊      | 753/2000 [22:40<38:43,  1.86s/it, loss=0.0952, lr=0.0001]
Steps:  38%|███▊      | 753/2000 [22:40<38:43,  1.86s/it, loss=0.13, lr=0.0001]  
Steps:  38%|███▊      | 753/2000 [22:40<38:43,  1.86s/it, loss=0.13, lr=0.0001]
Steps:  38%|███▊      | 753/2000 [22:41<38:43,  1.86s/it, loss=0.119, lr=0.0001]
Steps:  38%|███▊      | 753/2000 [22:41<38:43,  1.86s/it, loss=0.152, lr=0.0001]
Steps:  38%|███▊      | 754/2000 [22:42<38:56,  1.87s/it, loss=0.152, lr=0.0001]
Steps:  38%|███▊      | 754/2000 [22:42<38:56,  1.87s/it, loss=0.204, lr=0.0001]
Steps:  38%|███▊      | 754/2000 [22:42<38:56,  1.87s/it, loss=0.255, lr=0.0001]
Steps:  38%|███▊      | 754/2000 [22:42<38:56,  1.87s/it, loss=0.0633, lr=0.0001]
Steps:  38%|███▊      | 754/2000 [22:43<38:56,  1.87s/it, loss=0.179, lr=0.0001] 
Steps:  38%|███▊      | 755/2000 [22:43<37:36,  1.81s/it, loss=0.179, lr=0.0001]
Steps:  38%|███▊      | 755/2000 [22:43<37:36,  1.81s/it, loss=0.167, lr=0.0001]
Steps:  38%|███▊      | 755/2000 [22:44<37:36,  1.81s/it, loss=0.309, lr=0.0001]
Steps:  38%|███▊      | 755/2000 [22:44<37:36,  1.81s/it, loss=0.144, lr=0.0001]
Steps:  38%|███▊      | 755/2000 [22:45<37:36,  1.81s/it, loss=0.138, lr=0.0001]
Steps:  38%|███▊      | 756/2000 [22:45<36:52,  1.78s/it, loss=0.138, lr=0.0001]
Steps:  38%|███▊      | 756/2000 [22:45<36:52,  1.78s/it, loss=0.164, lr=0.0001]
Steps:  38%|███▊      | 756/2000 [22:45<36:52,  1.78s/it, loss=0.0589, lr=0.0001]
Steps:  38%|███▊      | 756/2000 [22:46<36:52,  1.78s/it, loss=0.262, lr=0.0001] 
Steps:  38%|███▊      | 756/2000 [22:46<36:52,  1.78s/it, loss=0.207, lr=0.0001]
Steps:  38%|███▊      | 757/2000 [22:47<37:46,  1.82s/it, loss=0.207, lr=0.0001]
Steps:  38%|███▊      | 757/2000 [22:47<37:46,  1.82s/it, loss=0.0687, lr=0.0001]
Steps:  38%|███▊      | 757/2000 [22:47<37:46,  1.82s/it, loss=0.119, lr=0.0001] 
Steps:  38%|███▊      | 757/2000 [22:48<37:46,  1.82s/it, loss=0.189, lr=0.0001]
Steps:  38%|███▊      | 757/2000 [22:48<37:46,  1.82s/it, loss=0.113, lr=0.0001]
Steps:  38%|███▊      | 758/2000 [22:49<36:43,  1.77s/it, loss=0.113, lr=0.0001]
Steps:  38%|███▊      | 758/2000 [22:49<36:43,  1.77s/it, loss=0.147, lr=0.0001]
Steps:  38%|███▊      | 758/2000 [22:49<36:43,  1.77s/it, loss=0.188, lr=0.0001]
Steps:  38%|███▊      | 758/2000 [22:49<36:43,  1.77s/it, loss=0.372, lr=0.0001]
Steps:  38%|███▊      | 758/2000 [22:50<36:43,  1.77s/it, loss=0.349, lr=0.0001]
Steps:  38%|███▊      | 759/2000 [22:50<37:00,  1.79s/it, loss=0.349, lr=0.0001]
Steps:  38%|███▊      | 759/2000 [22:50<37:00,  1.79s/it, loss=0.328, lr=0.0001]
Steps:  38%|███▊      | 759/2000 [22:51<37:00,  1.79s/it, loss=0.0931, lr=0.0001]
Steps:  38%|███▊      | 759/2000 [22:52<37:00,  1.79s/it, loss=0.159, lr=0.0001] 
Steps:  38%|███▊      | 759/2000 [22:52<37:00,  1.79s/it, loss=0.0513, lr=0.0001]
Steps:  38%|███▊      | 760/2000 [22:52<38:44,  1.87s/it, loss=0.0513, lr=0.0001]
Steps:  38%|███▊      | 760/2000 [22:52<38:44,  1.87s/it, loss=0.122, lr=0.0001] 
Steps:  38%|███▊      | 760/2000 [22:53<38:44,  1.87s/it, loss=0.131, lr=0.0001]
Steps:  38%|███▊      | 760/2000 [22:53<38:44,  1.87s/it, loss=0.157, lr=0.0001]
Steps:  38%|███▊      | 760/2000 [22:54<38:44,  1.87s/it, loss=0.113, lr=0.0001]
Steps:  38%|███▊      | 761/2000 [22:54<38:22,  1.86s/it, loss=0.113, lr=0.0001]
Steps:  38%|███▊      | 761/2000 [22:54<38:22,  1.86s/it, loss=0.226, lr=0.0001]
Steps:  38%|███▊      | 761/2000 [22:55<38:22,  1.86s/it, loss=0.215, lr=0.0001]
Steps:  38%|███▊      | 761/2000 [22:55<38:22,  1.86s/it, loss=0.218, lr=0.0001]
Steps:  38%|███▊      | 761/2000 [22:56<38:22,  1.86s/it, loss=0.223, lr=0.0001]
Steps:  38%|███▊      | 762/2000 [22:56<38:09,  1.85s/it, loss=0.223, lr=0.0001]
Steps:  38%|███▊      | 762/2000 [22:56<38:09,  1.85s/it, loss=0.199, lr=0.0001]
Steps:  38%|███▊      | 762/2000 [22:57<38:09,  1.85s/it, loss=0.23, lr=0.0001] 
Steps:  38%|███▊      | 762/2000 [22:57<38:09,  1.85s/it, loss=0.322, lr=0.0001]
Steps:  38%|███▊      | 762/2000 [22:58<38:09,  1.85s/it, loss=0.0886, lr=0.0001]
Steps:  38%|███▊      | 763/2000 [22:58<40:32,  1.97s/it, loss=0.0886, lr=0.0001]
Steps:  38%|███▊      | 763/2000 [22:58<40:32,  1.97s/it, loss=0.113, lr=0.0001] 
Steps:  38%|███▊      | 763/2000 [22:59<40:32,  1.97s/it, loss=0.649, lr=0.0001]
Steps:  38%|███▊      | 763/2000 [22:59<40:32,  1.97s/it, loss=0.363, lr=0.0001]
Steps:  38%|███▊      | 763/2000 [23:00<40:32,  1.97s/it, loss=0.0848, lr=0.0001]
Steps:  38%|███▊      | 764/2000 [23:00<39:31,  1.92s/it, loss=0.0848, lr=0.0001]
Steps:  38%|███▊      | 764/2000 [23:00<39:31,  1.92s/it, loss=0.167, lr=0.0001] 
Steps:  38%|███▊      | 764/2000 [23:01<39:31,  1.92s/it, loss=0.299, lr=0.0001]
Steps:  38%|███▊      | 764/2000 [23:01<39:31,  1.92s/it, loss=0.374, lr=0.0001]
Steps:  38%|███▊      | 764/2000 [23:02<39:31,  1.92s/it, loss=0.188, lr=0.0001]
Steps:  38%|███▊      | 765/2000 [23:02<38:54,  1.89s/it, loss=0.188, lr=0.0001]
Steps:  38%|███▊      | 765/2000 [23:02<38:54,  1.89s/it, loss=0.184, lr=0.0001]
Steps:  38%|███▊      | 765/2000 [23:02<38:54,  1.89s/it, loss=0.278, lr=0.0001]
Steps:  38%|███▊      | 765/2000 [23:03<38:54,  1.89s/it, loss=0.414, lr=0.0001]
Steps:  38%|███▊      | 765/2000 [23:03<38:54,  1.89s/it, loss=0.223, lr=0.0001]
Steps:  38%|███▊      | 766/2000 [23:04<39:16,  1.91s/it, loss=0.223, lr=0.0001]
Steps:  38%|███▊      | 766/2000 [23:04<39:16,  1.91s/it, loss=0.359, lr=0.0001]
Steps:  38%|███▊      | 766/2000 [23:04<39:16,  1.91s/it, loss=0.524, lr=0.0001]
Steps:  38%|███▊      | 766/2000 [23:05<39:16,  1.91s/it, loss=0.16, lr=0.0001] 
Steps:  38%|███▊      | 766/2000 [23:05<39:16,  1.91s/it, loss=0.146, lr=0.0001]
Steps:  38%|███▊      | 767/2000 [23:06<37:59,  1.85s/it, loss=0.146, lr=0.0001]
Steps:  38%|███▊      | 767/2000 [23:06<37:59,  1.85s/it, loss=0.2, lr=0.0001]  
Steps:  38%|███▊      | 767/2000 [23:06<37:59,  1.85s/it, loss=0.202, lr=0.0001]
Steps:  38%|███▊      | 767/2000 [23:06<37:59,  1.85s/it, loss=0.151, lr=0.0001]
Steps:  38%|███▊      | 767/2000 [23:07<37:59,  1.85s/it, loss=0.0359, lr=0.0001]
Steps:  38%|███▊      | 768/2000 [23:07<37:08,  1.81s/it, loss=0.0359, lr=0.0001]
Steps:  38%|███▊      | 768/2000 [23:07<37:08,  1.81s/it, loss=0.167, lr=0.0001] 
Steps:  38%|███▊      | 768/2000 [23:08<37:08,  1.81s/it, loss=0.114, lr=0.0001]
Steps:  38%|███▊      | 768/2000 [23:08<37:08,  1.81s/it, loss=0.124, lr=0.0001]
Steps:  38%|███▊      | 768/2000 [23:09<37:08,  1.81s/it, loss=0.211, lr=0.0001]
Steps:  38%|███▊      | 769/2000 [23:09<37:43,  1.84s/it, loss=0.211, lr=0.0001]
Steps:  38%|███▊      | 769/2000 [23:09<37:43,  1.84s/it, loss=0.206, lr=0.0001]
Steps:  38%|███▊      | 769/2000 [23:10<37:43,  1.84s/it, loss=0.17, lr=0.0001] 
Steps:  38%|███▊      | 769/2000 [23:10<37:43,  1.84s/it, loss=0.304, lr=0.0001]
Steps:  38%|███▊      | 769/2000 [23:10<37:43,  1.84s/it, loss=0.355, lr=0.0001]
Steps:  38%|███▊      | 770/2000 [23:11<36:39,  1.79s/it, loss=0.355, lr=0.0001]
Steps:  38%|███▊      | 770/2000 [23:11<36:39,  1.79s/it, loss=0.143, lr=0.0001]
Steps:  38%|███▊      | 770/2000 [23:11<36:39,  1.79s/it, loss=0.151, lr=0.0001]
Steps:  38%|███▊      | 770/2000 [23:12<36:39,  1.79s/it, loss=0.181, lr=0.0001]
Steps:  38%|███▊      | 770/2000 [23:12<36:39,  1.79s/it, loss=0.0811, lr=0.0001]
Steps:  39%|███▊      | 771/2000 [23:13<36:06,  1.76s/it, loss=0.0811, lr=0.0001]
Steps:  39%|███▊      | 771/2000 [23:13<36:06,  1.76s/it, loss=0.123, lr=0.0001] 
Steps:  39%|███▊      | 771/2000 [23:13<36:06,  1.76s/it, loss=0.473, lr=0.0001]
Steps:  39%|███▊      | 771/2000 [23:13<36:06,  1.76s/it, loss=0.0999, lr=0.0001]
Steps:  39%|███▊      | 771/2000 [23:14<36:06,  1.76s/it, loss=0.0758, lr=0.0001]
Steps:  39%|███▊      | 772/2000 [23:15<37:00,  1.81s/it, loss=0.0758, lr=0.0001]
Steps:  39%|███▊      | 772/2000 [23:15<37:00,  1.81s/it, loss=0.24, lr=0.0001]  
Steps:  39%|███▊      | 772/2000 [23:15<37:00,  1.81s/it, loss=0.388, lr=0.0001]
Steps:  39%|███▊      | 772/2000 [23:15<37:00,  1.81s/it, loss=0.109, lr=0.0001]
Steps:  39%|███▊      | 772/2000 [23:16<37:00,  1.81s/it, loss=0.192, lr=0.0001]
Steps:  39%|███▊      | 773/2000 [23:16<36:15,  1.77s/it, loss=0.192, lr=0.0001]
Steps:  39%|███▊      | 773/2000 [23:16<36:15,  1.77s/it, loss=0.327, lr=0.0001]
Steps:  39%|███▊      | 773/2000 [23:17<36:15,  1.77s/it, loss=0.0892, lr=0.0001]
Steps:  39%|███▊      | 773/2000 [23:17<36:15,  1.77s/it, loss=0.235, lr=0.0001] 
Steps:  39%|███▊      | 773/2000 [23:17<36:15,  1.77s/it, loss=0.158, lr=0.0001]
Steps:  39%|███▊      | 774/2000 [23:18<35:34,  1.74s/it, loss=0.158, lr=0.0001]
Steps:  39%|███▊      | 774/2000 [23:18<35:34,  1.74s/it, loss=0.237, lr=0.0001]
Steps:  39%|███▊      | 774/2000 [23:18<35:34,  1.74s/it, loss=0.346, lr=0.0001]
Steps:  39%|███▊      | 774/2000 [23:19<35:34,  1.74s/it, loss=0.243, lr=0.0001]
Steps:  39%|███▊      | 774/2000 [23:19<35:34,  1.74s/it, loss=0.224, lr=0.0001]
Steps:  39%|███▉      | 775/2000 [23:20<35:04,  1.72s/it, loss=0.224, lr=0.0001]
Steps:  39%|███▉      | 775/2000 [23:20<35:04,  1.72s/it, loss=0.107, lr=0.0001]
Steps:  39%|███▉      | 775/2000 [23:20<35:04,  1.72s/it, loss=0.206, lr=0.0001]
Steps:  39%|███▉      | 775/2000 [23:21<35:04,  1.72s/it, loss=0.143, lr=0.0001]
Steps:  39%|███▉      | 775/2000 [23:21<35:04,  1.72s/it, loss=0.528, lr=0.0001]
Steps:  39%|███▉      | 776/2000 [23:21<36:13,  1.78s/it, loss=0.528, lr=0.0001]
Steps:  39%|███▉      | 776/2000 [23:21<36:13,  1.78s/it, loss=0.153, lr=0.0001]
Steps:  39%|███▉      | 776/2000 [23:22<36:13,  1.78s/it, loss=0.163, lr=0.0001]
Steps:  39%|███▉      | 776/2000 [23:22<36:13,  1.78s/it, loss=0.0783, lr=0.0001]
Steps:  39%|███▉      | 776/2000 [23:23<36:13,  1.78s/it, loss=0.152, lr=0.0001] 
Steps:  39%|███▉      | 777/2000 [23:23<35:30,  1.74s/it, loss=0.152, lr=0.0001]
Steps:  39%|███▉      | 777/2000 [23:23<35:30,  1.74s/it, loss=0.112, lr=0.0001]
Steps:  39%|███▉      | 777/2000 [23:24<35:30,  1.74s/it, loss=0.202, lr=0.0001]
Steps:  39%|███▉      | 777/2000 [23:24<35:30,  1.74s/it, loss=0.164, lr=0.0001]
Steps:  39%|███▉      | 777/2000 [23:24<35:30,  1.74s/it, loss=0.145, lr=0.0001]
Steps:  39%|███▉      | 778/2000 [23:25<35:07,  1.72s/it, loss=0.145, lr=0.0001]
Steps:  39%|███▉      | 778/2000 [23:25<35:07,  1.72s/it, loss=0.191, lr=0.0001]
Steps:  39%|███▉      | 778/2000 [23:25<35:07,  1.72s/it, loss=0.221, lr=0.0001]
Steps:  39%|███▉      | 778/2000 [23:26<35:07,  1.72s/it, loss=0.208, lr=0.0001]
Steps:  39%|███▉      | 778/2000 [23:26<35:07,  1.72s/it, loss=0.209, lr=0.0001]
Steps:  39%|███▉      | 779/2000 [23:27<36:22,  1.79s/it, loss=0.209, lr=0.0001]
Steps:  39%|███▉      | 779/2000 [23:27<36:22,  1.79s/it, loss=0.146, lr=0.0001]
Steps:  39%|███▉      | 779/2000 [23:27<36:22,  1.79s/it, loss=2.55, lr=0.0001] 
Steps:  39%|███▉      | 779/2000 [23:28<36:22,  1.79s/it, loss=0.11, lr=0.0001]
Steps:  39%|███▉      | 779/2000 [23:28<36:22,  1.79s/it, loss=0.155, lr=0.0001]
Steps:  39%|███▉      | 780/2000 [23:28<35:36,  1.75s/it, loss=0.155, lr=0.0001]
Steps:  39%|███▉      | 780/2000 [23:28<35:36,  1.75s/it, loss=0.608, lr=0.0001]
Steps:  39%|███▉      | 780/2000 [23:29<35:36,  1.75s/it, loss=0.199, lr=0.0001]
Steps:  39%|███▉      | 780/2000 [23:29<35:36,  1.75s/it, loss=0.182, lr=0.0001]
Steps:  39%|███▉      | 780/2000 [23:30<35:36,  1.75s/it, loss=0.259, lr=0.0001]
Steps:  39%|███▉      | 781/2000 [23:30<35:07,  1.73s/it, loss=0.259, lr=0.0001]
Steps:  39%|███▉      | 781/2000 [23:30<35:07,  1.73s/it, loss=0.65, lr=0.0001] 
Steps:  39%|███▉      | 781/2000 [23:31<35:07,  1.73s/it, loss=0.15, lr=0.0001]
Steps:  39%|███▉      | 781/2000 [23:31<35:07,  1.73s/it, loss=0.192, lr=0.0001]
Steps:  39%|███▉      | 781/2000 [23:32<35:07,  1.73s/it, loss=0.0669, lr=0.0001]
Steps:  39%|███▉      | 782/2000 [23:32<36:18,  1.79s/it, loss=0.0669, lr=0.0001]
Steps:  39%|███▉      | 782/2000 [23:32<36:18,  1.79s/it, loss=0.155, lr=0.0001] 
Steps:  39%|███▉      | 782/2000 [23:32<36:18,  1.79s/it, loss=0.146, lr=0.0001]
Steps:  39%|███▉      | 782/2000 [23:33<36:18,  1.79s/it, loss=0.924, lr=0.0001]
Steps:  39%|███▉      | 782/2000 [23:33<36:18,  1.79s/it, loss=0.391, lr=0.0001]
Steps:  39%|███▉      | 783/2000 [23:34<35:35,  1.75s/it, loss=0.391, lr=0.0001]
Steps:  39%|███▉      | 783/2000 [23:34<35:35,  1.75s/it, loss=0.221, lr=0.0001]
Steps:  39%|███▉      | 783/2000 [23:34<35:35,  1.75s/it, loss=0.151, lr=0.0001]
Steps:  39%|███▉      | 783/2000 [23:35<35:35,  1.75s/it, loss=0.295, lr=0.0001]
Steps:  39%|███▉      | 783/2000 [23:35<35:35,  1.75s/it, loss=0.193, lr=0.0001]
Steps:  39%|███▉      | 784/2000 [23:35<35:13,  1.74s/it, loss=0.193, lr=0.0001]
Steps:  39%|███▉      | 784/2000 [23:35<35:13,  1.74s/it, loss=0.0737, lr=0.0001]
Steps:  39%|███▉      | 784/2000 [23:36<35:13,  1.74s/it, loss=0.158, lr=0.0001] 
Steps:  39%|███▉      | 784/2000 [23:36<35:13,  1.74s/it, loss=0.346, lr=0.0001]
Steps:  39%|███▉      | 784/2000 [23:37<35:13,  1.74s/it, loss=0.14, lr=0.0001] 
Steps:  39%|███▉      | 785/2000 [23:37<36:14,  1.79s/it, loss=0.14, lr=0.0001]
Steps:  39%|███▉      | 785/2000 [23:37<36:14,  1.79s/it, loss=0.196, lr=0.0001]
Steps:  39%|███▉      | 785/2000 [23:38<36:14,  1.79s/it, loss=0.0583, lr=0.0001]
Steps:  39%|███▉      | 785/2000 [23:38<36:14,  1.79s/it, loss=0.198, lr=0.0001] 
Steps:  39%|███▉      | 785/2000 [23:39<36:14,  1.79s/it, loss=0.153, lr=0.0001]
Steps:  39%|███▉      | 786/2000 [23:39<35:34,  1.76s/it, loss=0.153, lr=0.0001]
Steps:  39%|███▉      | 786/2000 [23:39<35:34,  1.76s/it, loss=0.187, lr=0.0001]
Steps:  39%|███▉      | 786/2000 [23:39<35:34,  1.76s/it, loss=0.532, lr=0.0001]
Steps:  39%|███▉      | 786/2000 [23:40<35:34,  1.76s/it, loss=0.158, lr=0.0001]
Steps:  39%|███▉      | 786/2000 [23:40<35:34,  1.76s/it, loss=0.189, lr=0.0001]
Steps:  39%|███▉      | 787/2000 [23:41<35:49,  1.77s/it, loss=0.189, lr=0.0001]
Steps:  39%|███▉      | 787/2000 [23:41<35:49,  1.77s/it, loss=0.276, lr=0.0001]
Steps:  39%|███▉      | 787/2000 [23:41<35:49,  1.77s/it, loss=1.34, lr=0.0001] 
Steps:  39%|███▉      | 787/2000 [23:42<35:49,  1.77s/it, loss=0.148, lr=0.0001]
Steps:  39%|███▉      | 787/2000 [23:42<35:49,  1.77s/it, loss=0.32, lr=0.0001] 
Steps:  39%|███▉      | 788/2000 [23:43<36:39,  1.81s/it, loss=0.32, lr=0.0001]
Steps:  39%|███▉      | 788/2000 [23:43<36:39,  1.81s/it, loss=0.605, lr=0.0001]
Steps:  39%|███▉      | 788/2000 [23:43<36:39,  1.81s/it, loss=0.227, lr=0.0001]
Steps:  39%|███▉      | 788/2000 [23:44<36:39,  1.81s/it, loss=0.274, lr=0.0001]
Steps:  39%|███▉      | 788/2000 [23:44<36:39,  1.81s/it, loss=0.026, lr=0.0001]
Steps:  39%|███▉      | 789/2000 [23:44<35:53,  1.78s/it, loss=0.026, lr=0.0001]
Steps:  39%|███▉      | 789/2000 [23:44<35:53,  1.78s/it, loss=0.216, lr=0.0001]
Steps:  39%|███▉      | 789/2000 [23:45<35:53,  1.78s/it, loss=0.123, lr=0.0001]
Steps:  39%|███▉      | 789/2000 [23:45<35:53,  1.78s/it, loss=0.379, lr=0.0001]
Steps:  39%|███▉      | 789/2000 [23:46<35:53,  1.78s/it, loss=0.184, lr=0.0001]
Steps:  40%|███▉      | 790/2000 [23:46<35:27,  1.76s/it, loss=0.184, lr=0.0001]
Steps:  40%|███▉      | 790/2000 [23:46<35:27,  1.76s/it, loss=0.109, lr=0.0001]
Steps:  40%|███▉      | 790/2000 [23:47<35:27,  1.76s/it, loss=0.163, lr=0.0001]
Steps:  40%|███▉      | 790/2000 [23:47<35:27,  1.76s/it, loss=0.12, lr=0.0001] 
Steps:  40%|███▉      | 790/2000 [23:47<35:27,  1.76s/it, loss=0.192, lr=0.0001]
Steps:  40%|███▉      | 791/2000 [23:48<36:31,  1.81s/it, loss=0.192, lr=0.0001]
Steps:  40%|███▉      | 791/2000 [23:48<36:31,  1.81s/it, loss=0.589, lr=0.0001]
Steps:  40%|███▉      | 791/2000 [23:48<36:31,  1.81s/it, loss=0.15, lr=0.0001] 
Steps:  40%|███▉      | 791/2000 [23:49<36:31,  1.81s/it, loss=0.603, lr=0.0001]
Steps:  40%|███▉      | 791/2000 [23:49<36:31,  1.81s/it, loss=0.255, lr=0.0001]
Steps:  40%|███▉      | 792/2000 [23:50<35:43,  1.77s/it, loss=0.255, lr=0.0001]
Steps:  40%|███▉      | 792/2000 [23:50<35:43,  1.77s/it, loss=0.156, lr=0.0001]
Steps:  40%|███▉      | 792/2000 [23:50<35:43,  1.77s/it, loss=0.121, lr=0.0001]
Steps:  40%|███▉      | 792/2000 [23:51<35:43,  1.77s/it, loss=0.0715, lr=0.0001]
Steps:  40%|███▉      | 792/2000 [23:51<35:43,  1.77s/it, loss=0.186, lr=0.0001] 
Steps:  40%|███▉      | 793/2000 [23:51<35:12,  1.75s/it, loss=0.186, lr=0.0001]
Steps:  40%|███▉      | 793/2000 [23:51<35:12,  1.75s/it, loss=0.0865, lr=0.0001]
Steps:  40%|███▉      | 793/2000 [23:52<35:12,  1.75s/it, loss=0.113, lr=0.0001] 
Steps:  40%|███▉      | 793/2000 [23:52<35:12,  1.75s/it, loss=0.137, lr=0.0001]
Steps:  40%|███▉      | 793/2000 [23:53<35:12,  1.75s/it, loss=0.158, lr=0.0001]
Steps:  40%|███▉      | 794/2000 [23:53<36:25,  1.81s/it, loss=0.158, lr=0.0001]
Steps:  40%|███▉      | 794/2000 [23:53<36:25,  1.81s/it, loss=0.111, lr=0.0001]
Steps:  40%|███▉      | 794/2000 [23:54<36:25,  1.81s/it, loss=0.142, lr=0.0001]
Steps:  40%|███▉      | 794/2000 [23:54<36:25,  1.81s/it, loss=0.191, lr=0.0001]
Steps:  40%|███▉      | 794/2000 [23:55<36:25,  1.81s/it, loss=0.24, lr=0.0001] 
Steps:  40%|███▉      | 795/2000 [23:55<35:51,  1.79s/it, loss=0.24, lr=0.0001]
Steps:  40%|███▉      | 795/2000 [23:55<35:51,  1.79s/it, loss=0.813, lr=0.0001]
Steps:  40%|███▉      | 795/2000 [23:56<35:51,  1.79s/it, loss=0.799, lr=0.0001]
Steps:  40%|███▉      | 795/2000 [23:56<35:51,  1.79s/it, loss=0.143, lr=0.0001]
Steps:  40%|███▉      | 795/2000 [23:56<35:51,  1.79s/it, loss=0.523, lr=0.0001]
Steps:  40%|███▉      | 796/2000 [23:57<35:22,  1.76s/it, loss=0.523, lr=0.0001]
Steps:  40%|███▉      | 796/2000 [23:57<35:22,  1.76s/it, loss=0.164, lr=0.0001]
Steps:  40%|███▉      | 796/2000 [23:57<35:22,  1.76s/it, loss=0.148, lr=0.0001]
Steps:  40%|███▉      | 796/2000 [23:58<35:22,  1.76s/it, loss=0.279, lr=0.0001]
Steps:  40%|███▉      | 796/2000 [23:58<35:22,  1.76s/it, loss=0.191, lr=0.0001]
Steps:  40%|███▉      | 797/2000 [23:59<35:10,  1.75s/it, loss=0.191, lr=0.0001]
Steps:  40%|███▉      | 797/2000 [23:59<35:10,  1.75s/it, loss=0.0874, lr=0.0001]
Steps:  40%|███▉      | 797/2000 [23:59<35:10,  1.75s/it, loss=0.243, lr=0.0001] 
Steps:  40%|███▉      | 797/2000 [24:00<35:10,  1.75s/it, loss=0.107, lr=0.0001]
Steps:  40%|███▉      | 797/2000 [24:00<35:10,  1.75s/it, loss=0.0854, lr=0.0001]
Steps:  40%|███▉      | 798/2000 [24:01<36:30,  1.82s/it, loss=0.0854, lr=0.0001]
Steps:  40%|███▉      | 798/2000 [24:01<36:30,  1.82s/it, loss=0.126, lr=0.0001] 
Steps:  40%|███▉      | 798/2000 [24:01<36:30,  1.82s/it, loss=0.662, lr=0.0001]
Steps:  40%|███▉      | 798/2000 [24:01<36:30,  1.82s/it, loss=0.166, lr=0.0001]
Steps:  40%|███▉      | 798/2000 [24:02<36:30,  1.82s/it, loss=0.215, lr=0.0001]
Steps:  40%|███▉      | 799/2000 [24:02<35:37,  1.78s/it, loss=0.215, lr=0.0001]
Steps:  40%|███▉      | 799/2000 [24:02<35:37,  1.78s/it, loss=0.157, lr=0.0001]
Steps:  40%|███▉      | 799/2000 [24:03<35:37,  1.78s/it, loss=0.126, lr=0.0001]
Steps:  40%|███▉      | 799/2000 [24:03<35:37,  1.78s/it, loss=0.172, lr=0.0001]
Steps:  40%|███▉      | 799/2000 [24:04<35:37,  1.78s/it, loss=0.112, lr=0.0001]
Steps:  40%|████      | 800/2000 [24:04<35:10,  1.76s/it, loss=0.112, lr=0.0001]
Steps:  40%|████      | 800/2000 [24:04<35:10,  1.76s/it, loss=0.248, lr=0.0001]
Steps:  40%|████      | 800/2000 [24:04<35:10,  1.76s/it, loss=0.194, lr=0.0001]
Steps:  40%|████      | 800/2000 [24:05<35:10,  1.76s/it, loss=0.185, lr=0.0001]
Steps:  40%|████      | 800/2000 [24:05<35:10,  1.76s/it, loss=0.166, lr=0.0001]
Steps:  40%|████      | 801/2000 [24:06<36:10,  1.81s/it, loss=0.166, lr=0.0001]
Steps:  40%|████      | 801/2000 [24:06<36:10,  1.81s/it, loss=0.0328, lr=0.0001]
Steps:  40%|████      | 801/2000 [24:06<36:10,  1.81s/it, loss=0.0928, lr=0.0001]
Steps:  40%|████      | 801/2000 [24:07<36:10,  1.81s/it, loss=0.127, lr=0.0001] 
Steps:  40%|████      | 801/2000 [24:07<36:10,  1.81s/it, loss=0.173, lr=0.0001]
Steps:  40%|████      | 802/2000 [24:08<35:30,  1.78s/it, loss=0.173, lr=0.0001]
Steps:  40%|████      | 802/2000 [24:08<35:30,  1.78s/it, loss=0.19, lr=0.0001] 
Steps:  40%|████      | 802/2000 [24:08<35:30,  1.78s/it, loss=0.138, lr=0.0001]
Steps:  40%|████      | 802/2000 [24:08<35:30,  1.78s/it, loss=0.157, lr=0.0001]
Steps:  40%|████      | 802/2000 [24:09<35:30,  1.78s/it, loss=0.291, lr=0.0001]
Steps:  40%|████      | 803/2000 [24:09<35:04,  1.76s/it, loss=0.291, lr=0.0001]
Steps:  40%|████      | 803/2000 [24:09<35:04,  1.76s/it, loss=0.171, lr=0.0001]
Steps:  40%|████      | 803/2000 [24:10<35:04,  1.76s/it, loss=0.16, lr=0.0001] 
Steps:  40%|████      | 803/2000 [24:10<35:04,  1.76s/it, loss=0.748, lr=0.0001]
Steps:  40%|████      | 803/2000 [24:11<35:04,  1.76s/it, loss=0.144, lr=0.0001]
Steps:  40%|████      | 804/2000 [24:11<36:07,  1.81s/it, loss=0.144, lr=0.0001]
Steps:  40%|████      | 804/2000 [24:11<36:07,  1.81s/it, loss=0.177, lr=0.0001]
Steps:  40%|████      | 804/2000 [24:12<36:07,  1.81s/it, loss=0.137, lr=0.0001]
Steps:  40%|████      | 804/2000 [24:12<36:07,  1.81s/it, loss=0.148, lr=0.0001]
Steps:  40%|████      | 804/2000 [24:12<36:07,  1.81s/it, loss=0.416, lr=0.0001]
Steps:  40%|████      | 805/2000 [24:13<35:16,  1.77s/it, loss=0.416, lr=0.0001]
Steps:  40%|████      | 805/2000 [24:13<35:16,  1.77s/it, loss=0.164, lr=0.0001]
Steps:  40%|████      | 805/2000 [24:13<35:16,  1.77s/it, loss=0.0495, lr=0.0001]
Steps:  40%|████      | 805/2000 [24:14<35:16,  1.77s/it, loss=0.187, lr=0.0001] 
Steps:  40%|████      | 805/2000 [24:14<35:16,  1.77s/it, loss=0.359, lr=0.0001]
Steps:  40%|████      | 806/2000 [24:15<34:33,  1.74s/it, loss=0.359, lr=0.0001]
Steps:  40%|████      | 806/2000 [24:15<34:33,  1.74s/it, loss=0.127, lr=0.0001]
Steps:  40%|████      | 806/2000 [24:15<34:33,  1.74s/it, loss=0.196, lr=0.0001]
Steps:  40%|████      | 806/2000 [24:15<34:33,  1.74s/it, loss=0.457, lr=0.0001]
Steps:  40%|████      | 806/2000 [24:16<34:33,  1.74s/it, loss=0.154, lr=0.0001]
Steps:  40%|████      | 807/2000 [24:16<35:31,  1.79s/it, loss=0.154, lr=0.0001]
Steps:  40%|████      | 807/2000 [24:16<35:31,  1.79s/it, loss=0.146, lr=0.0001]
Steps:  40%|████      | 807/2000 [24:17<35:31,  1.79s/it, loss=0.244, lr=0.0001]
Steps:  40%|████      | 807/2000 [24:17<35:31,  1.79s/it, loss=0.278, lr=0.0001]
Steps:  40%|████      | 807/2000 [24:18<35:31,  1.79s/it, loss=0.174, lr=0.0001]
Steps:  40%|████      | 808/2000 [24:18<34:42,  1.75s/it, loss=0.174, lr=0.0001]
Steps:  40%|████      | 808/2000 [24:18<34:42,  1.75s/it, loss=0.221, lr=0.0001]
Steps:  40%|████      | 808/2000 [24:19<34:42,  1.75s/it, loss=0.147, lr=0.0001]
Steps:  40%|████      | 808/2000 [24:19<34:42,  1.75s/it, loss=0.247, lr=0.0001]
Steps:  40%|████      | 808/2000 [24:19<34:42,  1.75s/it, loss=0.142, lr=0.0001]
Steps:  40%|████      | 809/2000 [24:20<34:08,  1.72s/it, loss=0.142, lr=0.0001]
Steps:  40%|████      | 809/2000 [24:20<34:08,  1.72s/it, loss=0.0724, lr=0.0001]
Steps:  40%|████      | 809/2000 [24:20<34:08,  1.72s/it, loss=0.918, lr=0.0001] 
Steps:  40%|████      | 809/2000 [24:21<34:08,  1.72s/it, loss=0.0729, lr=0.0001]
Steps:  40%|████      | 809/2000 [24:21<34:08,  1.72s/it, loss=0.231, lr=0.0001] 
Steps:  40%|████      | 810/2000 [24:22<35:13,  1.78s/it, loss=0.231, lr=0.0001]
Steps:  40%|████      | 810/2000 [24:22<35:13,  1.78s/it, loss=0.176, lr=0.0001]
Steps:  40%|████      | 810/2000 [24:22<35:13,  1.78s/it, loss=0.164, lr=0.0001]
Steps:  40%|████      | 810/2000 [24:22<35:13,  1.78s/it, loss=0.351, lr=0.0001]
Steps:  40%|████      | 810/2000 [24:23<35:13,  1.78s/it, loss=0.117, lr=0.0001]
Steps:  41%|████      | 811/2000 [24:23<34:32,  1.74s/it, loss=0.117, lr=0.0001]
Steps:  41%|████      | 811/2000 [24:23<34:32,  1.74s/it, loss=0.164, lr=0.0001]
Steps:  41%|████      | 811/2000 [24:24<34:32,  1.74s/it, loss=0.196, lr=0.0001]
Steps:  41%|████      | 811/2000 [24:24<34:32,  1.74s/it, loss=0.207, lr=0.0001]
Steps:  41%|████      | 811/2000 [24:25<34:32,  1.74s/it, loss=0.0952, lr=0.0001]
Steps:  41%|████      | 812/2000 [24:25<33:54,  1.71s/it, loss=0.0952, lr=0.0001]
Steps:  41%|████      | 812/2000 [24:25<33:54,  1.71s/it, loss=0.34, lr=0.0001]  
Steps:  41%|████      | 812/2000 [24:25<33:54,  1.71s/it, loss=0.181, lr=0.0001]
Steps:  41%|████      | 812/2000 [24:26<33:54,  1.71s/it, loss=0.188, lr=0.0001]
Steps:  41%|████      | 812/2000 [24:26<33:54,  1.71s/it, loss=0.225, lr=0.0001]
Steps:  41%|████      | 813/2000 [24:27<34:52,  1.76s/it, loss=0.225, lr=0.0001]
Steps:  41%|████      | 813/2000 [24:27<34:52,  1.76s/it, loss=0.134, lr=0.0001]
Steps:  41%|████      | 813/2000 [24:27<34:52,  1.76s/it, loss=0.705, lr=0.0001]
Steps:  41%|████      | 813/2000 [24:28<34:52,  1.76s/it, loss=0.145, lr=0.0001]
Steps:  41%|████      | 813/2000 [24:28<34:52,  1.76s/it, loss=0.122, lr=0.0001]
Steps:  41%|████      | 814/2000 [24:29<34:09,  1.73s/it, loss=0.122, lr=0.0001]
Steps:  41%|████      | 814/2000 [24:29<34:09,  1.73s/it, loss=0.14, lr=0.0001] 
Steps:  41%|████      | 814/2000 [24:29<34:09,  1.73s/it, loss=0.141, lr=0.0001]
Steps:  41%|████      | 814/2000 [24:29<34:09,  1.73s/it, loss=0.189, lr=0.0001]
Steps:  41%|████      | 814/2000 [24:30<34:09,  1.73s/it, loss=0.257, lr=0.0001]
Steps:  41%|████      | 815/2000 [24:30<33:41,  1.71s/it, loss=0.257, lr=0.0001]
Steps:  41%|████      | 815/2000 [24:30<33:41,  1.71s/it, loss=0.159, lr=0.0001]
Steps:  41%|████      | 815/2000 [24:31<33:41,  1.71s/it, loss=0.239, lr=0.0001]
Steps:  41%|████      | 815/2000 [24:31<33:41,  1.71s/it, loss=0.234, lr=0.0001]
Steps:  41%|████      | 815/2000 [24:31<33:41,  1.71s/it, loss=0.104, lr=0.0001]
Steps:  41%|████      | 816/2000 [24:32<33:19,  1.69s/it, loss=0.104, lr=0.0001]
Steps:  41%|████      | 816/2000 [24:32<33:19,  1.69s/it, loss=0.395, lr=0.0001]
Steps:  41%|████      | 816/2000 [24:32<33:19,  1.69s/it, loss=0.144, lr=0.0001]
Steps:  41%|████      | 816/2000 [24:33<33:19,  1.69s/it, loss=0.28, lr=0.0001] 
Steps:  41%|████      | 816/2000 [24:33<33:19,  1.69s/it, loss=0.315, lr=0.0001]
Steps:  41%|████      | 817/2000 [24:34<34:39,  1.76s/it, loss=0.315, lr=0.0001]
Steps:  41%|████      | 817/2000 [24:34<34:39,  1.76s/it, loss=0.62, lr=0.0001] 
Steps:  41%|████      | 817/2000 [24:34<34:39,  1.76s/it, loss=0.132, lr=0.0001]
Steps:  41%|████      | 817/2000 [24:35<34:39,  1.76s/it, loss=0.156, lr=0.0001]
Steps:  41%|████      | 817/2000 [24:35<34:39,  1.76s/it, loss=0.14, lr=0.0001] 
Steps:  41%|████      | 818/2000 [24:35<34:05,  1.73s/it, loss=0.14, lr=0.0001]
Steps:  41%|████      | 818/2000 [24:35<34:05,  1.73s/it, loss=0.301, lr=0.0001]
Steps:  41%|████      | 818/2000 [24:36<34:05,  1.73s/it, loss=0.0776, lr=0.0001]
Steps:  41%|████      | 818/2000 [24:36<34:05,  1.73s/it, loss=0.0865, lr=0.0001]
Steps:  41%|████      | 818/2000 [24:37<34:05,  1.73s/it, loss=0.147, lr=0.0001] 
Steps:  41%|████      | 819/2000 [24:37<34:24,  1.75s/it, loss=0.147, lr=0.0001]
Steps:  41%|████      | 819/2000 [24:37<34:24,  1.75s/it, loss=0.104, lr=0.0001]
Steps:  41%|████      | 819/2000 [24:38<34:24,  1.75s/it, loss=0.32, lr=0.0001] 
Steps:  41%|████      | 819/2000 [24:38<34:24,  1.75s/it, loss=0.154, lr=0.0001]
Steps:  41%|████      | 819/2000 [24:39<34:24,  1.75s/it, loss=0.153, lr=0.0001]
Steps:  41%|████      | 820/2000 [24:39<36:12,  1.84s/it, loss=0.153, lr=0.0001]
Steps:  41%|████      | 820/2000 [24:39<36:12,  1.84s/it, loss=0.168, lr=0.0001]
Steps:  41%|████      | 820/2000 [24:40<36:12,  1.84s/it, loss=0.291, lr=0.0001]
Steps:  41%|████      | 820/2000 [24:40<36:12,  1.84s/it, loss=0.215, lr=0.0001]
Steps:  41%|████      | 820/2000 [24:40<36:12,  1.84s/it, loss=0.155, lr=0.0001]
Steps:  41%|████      | 821/2000 [24:41<35:10,  1.79s/it, loss=0.155, lr=0.0001]
Steps:  41%|████      | 821/2000 [24:41<35:10,  1.79s/it, loss=0.13, lr=0.0001] 
Steps:  41%|████      | 821/2000 [24:41<35:10,  1.79s/it, loss=0.133, lr=0.0001]
Steps:  41%|████      | 821/2000 [24:42<35:10,  1.79s/it, loss=0.13, lr=0.0001] 
Steps:  41%|████      | 821/2000 [24:42<35:10,  1.79s/it, loss=0.113, lr=0.0001]
Steps:  41%|████      | 822/2000 [24:43<34:27,  1.76s/it, loss=0.113, lr=0.0001]
Steps:  41%|████      | 822/2000 [24:43<34:27,  1.76s/it, loss=0.201, lr=0.0001]
Steps:  41%|████      | 822/2000 [24:43<34:27,  1.76s/it, loss=0.125, lr=0.0001]
Steps:  41%|████      | 822/2000 [24:44<34:27,  1.76s/it, loss=0.223, lr=0.0001]
Steps:  41%|████      | 822/2000 [24:44<34:27,  1.76s/it, loss=0.216, lr=0.0001]
Steps:  41%|████      | 823/2000 [24:45<35:36,  1.81s/it, loss=0.216, lr=0.0001]
Steps:  41%|████      | 823/2000 [24:45<35:36,  1.81s/it, loss=0.357, lr=0.0001]
Steps:  41%|████      | 823/2000 [24:45<35:36,  1.81s/it, loss=0.141, lr=0.0001]
Steps:  41%|████      | 823/2000 [24:45<35:36,  1.81s/it, loss=0.207, lr=0.0001]
Steps:  41%|████      | 823/2000 [24:46<35:36,  1.81s/it, loss=0.149, lr=0.0001]
Steps:  41%|████      | 824/2000 [24:46<34:49,  1.78s/it, loss=0.149, lr=0.0001]
Steps:  41%|████      | 824/2000 [24:46<34:49,  1.78s/it, loss=0.307, lr=0.0001]
Steps:  41%|████      | 824/2000 [24:47<34:49,  1.78s/it, loss=0.294, lr=0.0001]
Steps:  41%|████      | 824/2000 [24:47<34:49,  1.78s/it, loss=0.117, lr=0.0001]
Steps:  41%|████      | 824/2000 [24:47<34:49,  1.78s/it, loss=0.173, lr=0.0001]
Steps:  41%|████▏     | 825/2000 [24:48<34:06,  1.74s/it, loss=0.173, lr=0.0001]
Steps:  41%|████▏     | 825/2000 [24:48<34:06,  1.74s/it, loss=0.481, lr=0.0001]
Steps:  41%|████▏     | 825/2000 [24:48<34:06,  1.74s/it, loss=0.502, lr=0.0001]
Steps:  41%|████▏     | 825/2000 [24:49<34:06,  1.74s/it, loss=0.206, lr=0.0001]
Steps:  41%|████▏     | 825/2000 [24:49<34:06,  1.74s/it, loss=0.15, lr=0.0001] 
Steps:  41%|████▏     | 826/2000 [24:50<35:12,  1.80s/it, loss=0.15, lr=0.0001]
Steps:  41%|████▏     | 826/2000 [24:50<35:12,  1.80s/it, loss=0.175, lr=0.0001]
Steps:  41%|████▏     | 826/2000 [24:50<35:12,  1.80s/it, loss=0.185, lr=0.0001]
Steps:  41%|████▏     | 826/2000 [24:51<35:12,  1.80s/it, loss=0.0732, lr=0.0001]
Steps:  41%|████▏     | 826/2000 [24:51<35:12,  1.80s/it, loss=0.0871, lr=0.0001]
Steps:  41%|████▏     | 827/2000 [24:52<34:33,  1.77s/it, loss=0.0871, lr=0.0001]
Steps:  41%|████▏     | 827/2000 [24:52<34:33,  1.77s/it, loss=0.152, lr=0.0001] 
Steps:  41%|████▏     | 827/2000 [24:52<34:33,  1.77s/it, loss=0.219, lr=0.0001]
Steps:  41%|████▏     | 827/2000 [24:52<34:33,  1.77s/it, loss=0.263, lr=0.0001]
Steps:  41%|████▏     | 827/2000 [24:53<34:33,  1.77s/it, loss=0.129, lr=0.0001]
Steps:  41%|████▏     | 828/2000 [24:53<33:49,  1.73s/it, loss=0.129, lr=0.0001]
Steps:  41%|████▏     | 828/2000 [24:53<33:49,  1.73s/it, loss=0.182, lr=0.0001]
Steps:  41%|████▏     | 828/2000 [24:54<33:49,  1.73s/it, loss=0.252, lr=0.0001]
Steps:  41%|████▏     | 828/2000 [24:54<33:49,  1.73s/it, loss=0.218, lr=0.0001]
Steps:  41%|████▏     | 828/2000 [24:54<33:49,  1.73s/it, loss=0.274, lr=0.0001]
Steps:  41%|████▏     | 829/2000 [24:55<34:41,  1.78s/it, loss=0.274, lr=0.0001]
Steps:  41%|████▏     | 829/2000 [24:55<34:41,  1.78s/it, loss=0.182, lr=0.0001]
Steps:  41%|████▏     | 829/2000 [24:55<34:41,  1.78s/it, loss=0.279, lr=0.0001]
Steps:  41%|████▏     | 829/2000 [24:56<34:41,  1.78s/it, loss=0.297, lr=0.0001]
Steps:  41%|████▏     | 829/2000 [24:56<34:41,  1.78s/it, loss=0.131, lr=0.0001]
Steps:  42%|████▏     | 830/2000 [24:57<33:46,  1.73s/it, loss=0.131, lr=0.0001]
Steps:  42%|████▏     | 830/2000 [24:57<33:46,  1.73s/it, loss=0.344, lr=0.0001]
Steps:  42%|████▏     | 830/2000 [24:57<33:46,  1.73s/it, loss=0.339, lr=0.0001]
Steps:  42%|████▏     | 830/2000 [24:57<33:46,  1.73s/it, loss=0.119, lr=0.0001]
Steps:  42%|████▏     | 830/2000 [24:58<33:46,  1.73s/it, loss=0.147, lr=0.0001]
Steps:  42%|████▏     | 831/2000 [24:58<33:20,  1.71s/it, loss=0.147, lr=0.0001]
Steps:  42%|████▏     | 831/2000 [24:58<33:20,  1.71s/it, loss=0.093, lr=0.0001]
Steps:  42%|████▏     | 831/2000 [24:59<33:20,  1.71s/it, loss=0.103, lr=0.0001]
Steps:  42%|████▏     | 831/2000 [24:59<33:20,  1.71s/it, loss=0.219, lr=0.0001]
Steps:  42%|████▏     | 831/2000 [25:00<33:20,  1.71s/it, loss=0.166, lr=0.0001]
Steps:  42%|████▏     | 832/2000 [25:00<34:20,  1.76s/it, loss=0.166, lr=0.0001]
Steps:  42%|████▏     | 832/2000 [25:00<34:20,  1.76s/it, loss=0.184, lr=0.0001]
Steps:  42%|████▏     | 832/2000 [25:01<34:20,  1.76s/it, loss=0.201, lr=0.0001]
Steps:  42%|████▏     | 832/2000 [25:01<34:20,  1.76s/it, loss=0.319, lr=0.0001]
Steps:  42%|████▏     | 832/2000 [25:01<34:20,  1.76s/it, loss=0.191, lr=0.0001]
Steps:  42%|████▏     | 833/2000 [25:02<33:37,  1.73s/it, loss=0.191, lr=0.0001]
Steps:  42%|████▏     | 833/2000 [25:02<33:37,  1.73s/it, loss=0.203, lr=0.0001]
Steps:  42%|████▏     | 833/2000 [25:02<33:37,  1.73s/it, loss=0.144, lr=0.0001]
Steps:  42%|████▏     | 833/2000 [25:03<33:37,  1.73s/it, loss=0.255, lr=0.0001]
Steps:  42%|████▏     | 833/2000 [25:03<33:37,  1.73s/it, loss=0.131, lr=0.0001]
Steps:  42%|████▏     | 834/2000 [25:04<33:11,  1.71s/it, loss=0.131, lr=0.0001]
Steps:  42%|████▏     | 834/2000 [25:04<33:11,  1.71s/it, loss=0.114, lr=0.0001]
Steps:  42%|████▏     | 834/2000 [25:04<33:11,  1.71s/it, loss=0.0774, lr=0.0001]
Steps:  42%|████▏     | 834/2000 [25:04<33:11,  1.71s/it, loss=0.12, lr=0.0001]  
Steps:  42%|████▏     | 834/2000 [25:05<33:11,  1.71s/it, loss=0.397, lr=0.0001]
Steps:  42%|████▏     | 835/2000 [25:05<33:01,  1.70s/it, loss=0.397, lr=0.0001]
Steps:  42%|████▏     | 835/2000 [25:05<33:01,  1.70s/it, loss=0.119, lr=0.0001]
Steps:  42%|████▏     | 835/2000 [25:06<33:01,  1.70s/it, loss=0.198, lr=0.0001]
Steps:  42%|████▏     | 835/2000 [25:06<33:01,  1.70s/it, loss=0.269, lr=0.0001]
Steps:  42%|████▏     | 835/2000 [25:07<33:01,  1.70s/it, loss=0.192, lr=0.0001]
Steps:  42%|████▏     | 836/2000 [25:07<34:37,  1.78s/it, loss=0.192, lr=0.0001]
Steps:  42%|████▏     | 836/2000 [25:07<34:37,  1.78s/it, loss=0.172, lr=0.0001]
Steps:  42%|████▏     | 836/2000 [25:08<34:37,  1.78s/it, loss=0.131, lr=0.0001]
Steps:  42%|████▏     | 836/2000 [25:08<34:37,  1.78s/it, loss=0.134, lr=0.0001]
Steps:  42%|████▏     | 836/2000 [25:08<34:37,  1.78s/it, loss=0.205, lr=0.0001]
Steps:  42%|████▏     | 837/2000 [25:09<33:53,  1.75s/it, loss=0.205, lr=0.0001]
Steps:  42%|████▏     | 837/2000 [25:09<33:53,  1.75s/it, loss=0.171, lr=0.0001]
Steps:  42%|████▏     | 837/2000 [25:09<33:53,  1.75s/it, loss=0.273, lr=0.0001]
Steps:  42%|████▏     | 837/2000 [25:10<33:53,  1.75s/it, loss=0.111, lr=0.0001]
Steps:  42%|████▏     | 837/2000 [25:10<33:53,  1.75s/it, loss=0.073, lr=0.0001]
Steps:  42%|████▏     | 838/2000 [25:11<33:22,  1.72s/it, loss=0.073, lr=0.0001]
Steps:  42%|████▏     | 838/2000 [25:11<33:22,  1.72s/it, loss=0.299, lr=0.0001]
Steps:  42%|████▏     | 838/2000 [25:11<33:22,  1.72s/it, loss=0.177, lr=0.0001]
Steps:  42%|████▏     | 838/2000 [25:12<33:22,  1.72s/it, loss=0.0645, lr=0.0001]
Steps:  42%|████▏     | 838/2000 [25:12<33:22,  1.72s/it, loss=0.23, lr=0.0001]  
Steps:  42%|████▏     | 839/2000 [25:12<34:24,  1.78s/it, loss=0.23, lr=0.0001]
Steps:  42%|████▏     | 839/2000 [25:12<34:24,  1.78s/it, loss=0.491, lr=0.0001]
Steps:  42%|████▏     | 839/2000 [25:13<34:24,  1.78s/it, loss=0.163, lr=0.0001]
Steps:  42%|████▏     | 839/2000 [25:13<34:24,  1.78s/it, loss=0.152, lr=0.0001]
Steps:  42%|████▏     | 839/2000 [25:14<34:24,  1.78s/it, loss=0.0465, lr=0.0001]
Steps:  42%|████▏     | 840/2000 [25:14<34:07,  1.77s/it, loss=0.0465, lr=0.0001]
Steps:  42%|████▏     | 840/2000 [25:14<34:07,  1.77s/it, loss=0.125, lr=0.0001] 
Steps:  42%|████▏     | 840/2000 [25:15<34:07,  1.77s/it, loss=0.165, lr=0.0001]
Steps:  42%|████▏     | 840/2000 [25:15<34:07,  1.77s/it, loss=0.074, lr=0.0001]
Steps:  42%|████▏     | 840/2000 [25:15<34:07,  1.77s/it, loss=0.0948, lr=0.0001]
Steps:  42%|████▏     | 841/2000 [25:16<33:49,  1.75s/it, loss=0.0948, lr=0.0001]
Steps:  42%|████▏     | 841/2000 [25:16<33:49,  1.75s/it, loss=0.157, lr=0.0001] 
Steps:  42%|████▏     | 841/2000 [25:16<33:49,  1.75s/it, loss=0.425, lr=0.0001]
Steps:  42%|████▏     | 841/2000 [25:17<33:49,  1.75s/it, loss=0.13, lr=0.0001] 
Steps:  42%|████▏     | 841/2000 [25:17<33:49,  1.75s/it, loss=0.213, lr=0.0001]
Steps:  42%|████▏     | 842/2000 [25:18<35:17,  1.83s/it, loss=0.213, lr=0.0001]
Steps:  42%|████▏     | 842/2000 [25:18<35:17,  1.83s/it, loss=0.119, lr=0.0001]
Steps:  42%|████▏     | 842/2000 [25:18<35:17,  1.83s/it, loss=0.229, lr=0.0001]
Steps:  42%|████▏     | 842/2000 [25:19<35:17,  1.83s/it, loss=0.149, lr=0.0001]
Steps:  42%|████▏     | 842/2000 [25:19<35:17,  1.83s/it, loss=0.136, lr=0.0001]
Steps:  42%|████▏     | 843/2000 [25:20<34:41,  1.80s/it, loss=0.136, lr=0.0001]
Steps:  42%|████▏     | 843/2000 [25:20<34:41,  1.80s/it, loss=0.182, lr=0.0001]
Steps:  42%|████▏     | 843/2000 [25:20<34:41,  1.80s/it, loss=0.186, lr=0.0001]
Steps:  42%|████▏     | 843/2000 [25:20<34:41,  1.80s/it, loss=0.711, lr=0.0001]
Steps:  42%|████▏     | 843/2000 [25:21<34:41,  1.80s/it, loss=0.0813, lr=0.0001]
Steps:  42%|████▏     | 844/2000 [25:21<34:24,  1.79s/it, loss=0.0813, lr=0.0001]
Steps:  42%|████▏     | 844/2000 [25:21<34:24,  1.79s/it, loss=0.199, lr=0.0001] 
Steps:  42%|████▏     | 844/2000 [25:22<34:24,  1.79s/it, loss=0.227, lr=0.0001]
Steps:  42%|████▏     | 844/2000 [25:22<34:24,  1.79s/it, loss=0.221, lr=0.0001]
Steps:  42%|████▏     | 844/2000 [25:23<34:24,  1.79s/it, loss=0.598, lr=0.0001]
Steps:  42%|████▏     | 845/2000 [25:23<35:14,  1.83s/it, loss=0.598, lr=0.0001]
Steps:  42%|████▏     | 845/2000 [25:23<35:14,  1.83s/it, loss=0.164, lr=0.0001]
Steps:  42%|████▏     | 845/2000 [25:24<35:14,  1.83s/it, loss=0.22, lr=0.0001] 
Steps:  42%|████▏     | 845/2000 [25:24<35:14,  1.83s/it, loss=0.52, lr=0.0001]
Steps:  42%|████▏     | 845/2000 [25:25<35:14,  1.83s/it, loss=0.144, lr=0.0001]
Steps:  42%|████▏     | 846/2000 [25:25<34:14,  1.78s/it, loss=0.144, lr=0.0001]
Steps:  42%|████▏     | 846/2000 [25:25<34:14,  1.78s/it, loss=0.153, lr=0.0001]
Steps:  42%|████▏     | 846/2000 [25:25<34:14,  1.78s/it, loss=0.124, lr=0.0001]
Steps:  42%|████▏     | 846/2000 [25:26<34:14,  1.78s/it, loss=0.232, lr=0.0001]
Steps:  42%|████▏     | 846/2000 [25:26<34:14,  1.78s/it, loss=0.159, lr=0.0001]
Steps:  42%|████▏     | 847/2000 [25:27<33:43,  1.75s/it, loss=0.159, lr=0.0001]
Steps:  42%|████▏     | 847/2000 [25:27<33:43,  1.75s/it, loss=0.164, lr=0.0001]
Steps:  42%|████▏     | 847/2000 [25:27<33:43,  1.75s/it, loss=0.217, lr=0.0001]
Steps:  42%|████▏     | 847/2000 [25:28<33:43,  1.75s/it, loss=0.438, lr=0.0001]
Steps:  42%|████▏     | 847/2000 [25:28<33:43,  1.75s/it, loss=0.688, lr=0.0001]
Steps:  42%|████▏     | 848/2000 [25:29<34:38,  1.80s/it, loss=0.688, lr=0.0001]
Steps:  42%|████▏     | 848/2000 [25:29<34:38,  1.80s/it, loss=0.149, lr=0.0001]
Steps:  42%|████▏     | 848/2000 [25:29<34:38,  1.80s/it, loss=0.285, lr=0.0001]
Steps:  42%|████▏     | 848/2000 [25:29<34:38,  1.80s/it, loss=0.258, lr=0.0001]
Steps:  42%|████▏     | 848/2000 [25:30<34:38,  1.80s/it, loss=0.204, lr=0.0001]
Steps:  42%|████▏     | 849/2000 [25:30<33:51,  1.77s/it, loss=0.204, lr=0.0001]
Steps:  42%|████▏     | 849/2000 [25:30<33:51,  1.77s/it, loss=0.144, lr=0.0001]
Steps:  42%|████▏     | 849/2000 [25:31<33:51,  1.77s/it, loss=0.197, lr=0.0001]
Steps:  42%|████▏     | 849/2000 [25:31<33:51,  1.77s/it, loss=0.145, lr=0.0001]
Steps:  42%|████▏     | 849/2000 [25:32<33:51,  1.77s/it, loss=0.201, lr=0.0001]
Steps:  42%|████▎     | 850/2000 [25:32<33:19,  1.74s/it, loss=0.201, lr=0.0001]
Steps:  42%|████▎     | 850/2000 [25:32<33:19,  1.74s/it, loss=0.805, lr=0.0001]
Steps:  42%|████▎     | 850/2000 [25:32<33:19,  1.74s/it, loss=0.298, lr=0.0001]
Steps:  42%|████▎     | 850/2000 [25:33<33:19,  1.74s/it, loss=0.0817, lr=0.0001]
Steps:  42%|████▎     | 850/2000 [25:33<33:19,  1.74s/it, loss=0.609, lr=0.0001] 
Steps:  43%|████▎     | 851/2000 [25:34<32:57,  1.72s/it, loss=0.609, lr=0.0001]
Steps:  43%|████▎     | 851/2000 [25:34<32:57,  1.72s/it, loss=0.242, lr=0.0001]
Steps:  43%|████▎     | 851/2000 [25:34<32:57,  1.72s/it, loss=0.168, lr=0.0001]
Steps:  43%|████▎     | 851/2000 [25:35<32:57,  1.72s/it, loss=0.147, lr=0.0001]
Steps:  43%|████▎     | 851/2000 [25:35<32:57,  1.72s/it, loss=0.23, lr=0.0001] 
Steps:  43%|████▎     | 852/2000 [25:36<34:10,  1.79s/it, loss=0.23, lr=0.0001]
Steps:  43%|████▎     | 852/2000 [25:36<34:10,  1.79s/it, loss=0.182, lr=0.0001]
Steps:  43%|████▎     | 852/2000 [25:36<34:10,  1.79s/it, loss=0.069, lr=0.0001]
Steps:  43%|████▎     | 852/2000 [25:36<34:10,  1.79s/it, loss=0.173, lr=0.0001]
Steps:  43%|████▎     | 852/2000 [25:37<34:10,  1.79s/it, loss=0.185, lr=0.0001]
Steps:  43%|████▎     | 853/2000 [25:37<33:40,  1.76s/it, loss=0.185, lr=0.0001]
Steps:  43%|████▎     | 853/2000 [25:37<33:40,  1.76s/it, loss=0.176, lr=0.0001]
Steps:  43%|████▎     | 853/2000 [25:38<33:40,  1.76s/it, loss=0.251, lr=0.0001]
Steps:  43%|████▎     | 853/2000 [25:38<33:40,  1.76s/it, loss=0.314, lr=0.0001]
Steps:  43%|████▎     | 853/2000 [25:39<33:40,  1.76s/it, loss=0.24, lr=0.0001] 
Steps:  43%|████▎     | 854/2000 [25:39<33:26,  1.75s/it, loss=0.24, lr=0.0001]
Steps:  43%|████▎     | 854/2000 [25:39<33:26,  1.75s/it, loss=0.148, lr=0.0001]
Steps:  43%|████▎     | 854/2000 [25:39<33:26,  1.75s/it, loss=0.164, lr=0.0001]
Steps:  43%|████▎     | 854/2000 [25:40<33:26,  1.75s/it, loss=0.0949, lr=0.0001]
Steps:  43%|████▎     | 854/2000 [25:40<33:26,  1.75s/it, loss=0.274, lr=0.0001] 
Steps:  43%|████▎     | 855/2000 [25:41<34:18,  1.80s/it, loss=0.274, lr=0.0001]
Steps:  43%|████▎     | 855/2000 [25:41<34:18,  1.80s/it, loss=0.248, lr=0.0001]
Steps:  43%|████▎     | 855/2000 [25:41<34:18,  1.80s/it, loss=0.324, lr=0.0001]
Steps:  43%|████▎     | 855/2000 [25:42<34:18,  1.80s/it, loss=0.213, lr=0.0001]
Steps:  43%|████▎     | 855/2000 [25:42<34:18,  1.80s/it, loss=0.107, lr=0.0001]
Steps:  43%|████▎     | 856/2000 [25:43<33:32,  1.76s/it, loss=0.107, lr=0.0001]
Steps:  43%|████▎     | 856/2000 [25:43<33:32,  1.76s/it, loss=0.267, lr=0.0001]
Steps:  43%|████▎     | 856/2000 [25:43<33:32,  1.76s/it, loss=0.155, lr=0.0001]
Steps:  43%|████▎     | 856/2000 [25:43<33:32,  1.76s/it, loss=0.265, lr=0.0001]
Steps:  43%|████▎     | 856/2000 [25:44<33:32,  1.76s/it, loss=0.0861, lr=0.0001]
Steps:  43%|████▎     | 857/2000 [25:44<32:57,  1.73s/it, loss=0.0861, lr=0.0001]
Steps:  43%|████▎     | 857/2000 [25:44<32:57,  1.73s/it, loss=0.283, lr=0.0001] 
Steps:  43%|████▎     | 857/2000 [25:45<32:57,  1.73s/it, loss=0.249, lr=0.0001]
Steps:  43%|████▎     | 857/2000 [25:45<32:57,  1.73s/it, loss=0.139, lr=0.0001]
Steps:  43%|████▎     | 857/2000 [25:46<32:57,  1.73s/it, loss=0.221, lr=0.0001]
Steps:  43%|████▎     | 858/2000 [25:46<33:52,  1.78s/it, loss=0.221, lr=0.0001]
Steps:  43%|████▎     | 858/2000 [25:46<33:52,  1.78s/it, loss=0.262, lr=0.0001]
Steps:  43%|████▎     | 858/2000 [25:47<33:52,  1.78s/it, loss=0.254, lr=0.0001]
Steps:  43%|████▎     | 858/2000 [25:47<33:52,  1.78s/it, loss=0.144, lr=0.0001]
Steps:  43%|████▎     | 858/2000 [25:47<33:52,  1.78s/it, loss=0.121, lr=0.0001]
Steps:  43%|████▎     | 859/2000 [25:48<33:11,  1.75s/it, loss=0.121, lr=0.0001]
Steps:  43%|████▎     | 859/2000 [25:48<33:11,  1.75s/it, loss=0.177, lr=0.0001]
Steps:  43%|████▎     | 859/2000 [25:48<33:11,  1.75s/it, loss=0.0831, lr=0.0001]
Steps:  43%|████▎     | 859/2000 [25:49<33:11,  1.75s/it, loss=0.0944, lr=0.0001]
Steps:  43%|████▎     | 859/2000 [25:49<33:11,  1.75s/it, loss=0.15, lr=0.0001]  
Steps:  43%|████▎     | 860/2000 [25:49<32:49,  1.73s/it, loss=0.15, lr=0.0001]
Steps:  43%|████▎     | 860/2000 [25:49<32:49,  1.73s/it, loss=0.158, lr=0.0001]
Steps:  43%|████▎     | 860/2000 [25:50<32:49,  1.73s/it, loss=0.487, lr=0.0001]
Steps:  43%|████▎     | 860/2000 [25:51<32:49,  1.73s/it, loss=0.17, lr=0.0001] 
Steps:  43%|████▎     | 860/2000 [25:51<32:49,  1.73s/it, loss=0.298, lr=0.0001]
Steps:  43%|████▎     | 861/2000 [25:51<33:45,  1.78s/it, loss=0.298, lr=0.0001]
Steps:  43%|████▎     | 861/2000 [25:51<33:45,  1.78s/it, loss=0.154, lr=0.0001]
Steps:  43%|████▎     | 861/2000 [25:52<33:45,  1.78s/it, loss=0.191, lr=0.0001]
Steps:  43%|████▎     | 861/2000 [25:52<33:45,  1.78s/it, loss=0.185, lr=0.0001]
Steps:  43%|████▎     | 861/2000 [25:53<33:45,  1.78s/it, loss=0.273, lr=0.0001]
Steps:  43%|████▎     | 862/2000 [25:53<33:14,  1.75s/it, loss=0.273, lr=0.0001]
Steps:  43%|████▎     | 862/2000 [25:53<33:14,  1.75s/it, loss=0.0893, lr=0.0001]
Steps:  43%|████▎     | 862/2000 [25:53<33:14,  1.75s/it, loss=0.166, lr=0.0001] 
Steps:  43%|████▎     | 862/2000 [25:54<33:14,  1.75s/it, loss=0.605, lr=0.0001]
Steps:  43%|████▎     | 862/2000 [25:54<33:14,  1.75s/it, loss=0.142, lr=0.0001]
Steps:  43%|████▎     | 863/2000 [25:55<32:41,  1.73s/it, loss=0.142, lr=0.0001]
Steps:  43%|████▎     | 863/2000 [25:55<32:41,  1.73s/it, loss=0.164, lr=0.0001]
Steps:  43%|████▎     | 863/2000 [25:55<32:41,  1.73s/it, loss=0.134, lr=0.0001]
Steps:  43%|████▎     | 863/2000 [25:56<32:41,  1.73s/it, loss=0.185, lr=0.0001]
Steps:  43%|████▎     | 863/2000 [25:56<32:41,  1.73s/it, loss=1.58, lr=0.0001] 
Steps:  43%|████▎     | 864/2000 [25:57<33:39,  1.78s/it, loss=1.58, lr=0.0001]
Steps:  43%|████▎     | 864/2000 [25:57<33:39,  1.78s/it, loss=0.116, lr=0.0001]
Steps:  43%|████▎     | 864/2000 [25:57<33:39,  1.78s/it, loss=0.153, lr=0.0001]
Steps:  43%|████▎     | 864/2000 [25:57<33:39,  1.78s/it, loss=0.15, lr=0.0001] 
Steps:  43%|████▎     | 864/2000 [25:58<33:39,  1.78s/it, loss=0.277, lr=0.0001]
Steps:  43%|████▎     | 865/2000 [25:58<33:09,  1.75s/it, loss=0.277, lr=0.0001]
Steps:  43%|████▎     | 865/2000 [25:58<33:09,  1.75s/it, loss=0.111, lr=0.0001]
Steps:  43%|████▎     | 865/2000 [25:59<33:09,  1.75s/it, loss=0.42, lr=0.0001] 
Steps:  43%|████▎     | 865/2000 [25:59<33:09,  1.75s/it, loss=0.144, lr=0.0001]
Steps:  43%|████▎     | 865/2000 [26:00<33:09,  1.75s/it, loss=0.139, lr=0.0001]
Steps:  43%|████▎     | 866/2000 [26:00<32:53,  1.74s/it, loss=0.139, lr=0.0001]
Steps:  43%|████▎     | 866/2000 [26:00<32:53,  1.74s/it, loss=0.214, lr=0.0001]
Steps:  43%|████▎     | 866/2000 [26:00<32:53,  1.74s/it, loss=0.234, lr=0.0001]
Steps:  43%|████▎     | 866/2000 [26:01<32:53,  1.74s/it, loss=0.165, lr=0.0001]
Steps:  43%|████▎     | 866/2000 [26:01<32:53,  1.74s/it, loss=0.137, lr=0.0001]
Steps:  43%|████▎     | 867/2000 [26:02<34:08,  1.81s/it, loss=0.137, lr=0.0001]
Steps:  43%|████▎     | 867/2000 [26:02<34:08,  1.81s/it, loss=0.773, lr=0.0001]
Steps:  43%|████▎     | 867/2000 [26:02<34:08,  1.81s/it, loss=0.178, lr=0.0001]
Steps:  43%|████▎     | 867/2000 [26:03<34:08,  1.81s/it, loss=0.251, lr=0.0001]
Steps:  43%|████▎     | 867/2000 [26:03<34:08,  1.81s/it, loss=0.189, lr=0.0001]
Steps:  43%|████▎     | 868/2000 [26:04<33:43,  1.79s/it, loss=0.189, lr=0.0001]
Steps:  43%|████▎     | 868/2000 [26:04<33:43,  1.79s/it, loss=0.252, lr=0.0001]
Steps:  43%|████▎     | 868/2000 [26:04<33:43,  1.79s/it, loss=0.483, lr=0.0001]
Steps:  43%|████▎     | 868/2000 [26:05<33:43,  1.79s/it, loss=0.189, lr=0.0001]
Steps:  43%|████▎     | 868/2000 [26:05<33:43,  1.79s/it, loss=0.0913, lr=0.0001]
Steps:  43%|████▎     | 869/2000 [26:05<33:04,  1.75s/it, loss=0.0913, lr=0.0001]
Steps:  43%|████▎     | 869/2000 [26:05<33:04,  1.75s/it, loss=0.154, lr=0.0001] 
Steps:  43%|████▎     | 869/2000 [26:06<33:04,  1.75s/it, loss=0.219, lr=0.0001]
Steps:  43%|████▎     | 869/2000 [26:06<33:04,  1.75s/it, loss=0.486, lr=0.0001]
Steps:  43%|████▎     | 869/2000 [26:07<33:04,  1.75s/it, loss=0.216, lr=0.0001]
Steps:  44%|████▎     | 870/2000 [26:07<32:44,  1.74s/it, loss=0.216, lr=0.0001]
Steps:  44%|████▎     | 870/2000 [26:07<32:44,  1.74s/it, loss=0.142, lr=0.0001]
Steps:  44%|████▎     | 870/2000 [26:08<32:44,  1.74s/it, loss=0.234, lr=0.0001]
Steps:  44%|████▎     | 870/2000 [26:08<32:44,  1.74s/it, loss=0.193, lr=0.0001]
Steps:  44%|████▎     | 870/2000 [26:09<32:44,  1.74s/it, loss=0.238, lr=0.0001]
Steps:  44%|████▎     | 871/2000 [26:09<34:01,  1.81s/it, loss=0.238, lr=0.0001]
Steps:  44%|████▎     | 871/2000 [26:09<34:01,  1.81s/it, loss=0.132, lr=0.0001]
Steps:  44%|████▎     | 871/2000 [26:10<34:01,  1.81s/it, loss=0.181, lr=0.0001]
Steps:  44%|████▎     | 871/2000 [26:10<34:01,  1.81s/it, loss=0.138, lr=0.0001]
Steps:  44%|████▎     | 871/2000 [26:10<34:01,  1.81s/it, loss=0.163, lr=0.0001]
Steps:  44%|████▎     | 872/2000 [26:11<33:13,  1.77s/it, loss=0.163, lr=0.0001]
Steps:  44%|████▎     | 872/2000 [26:11<33:13,  1.77s/it, loss=0.129, lr=0.0001]
Steps:  44%|████▎     | 872/2000 [26:11<33:13,  1.77s/it, loss=0.405, lr=0.0001]
Steps:  44%|████▎     | 872/2000 [26:12<33:13,  1.77s/it, loss=0.2, lr=0.0001]  
Steps:  44%|████▎     | 872/2000 [26:12<33:13,  1.77s/it, loss=0.265, lr=0.0001]
Steps:  44%|████▎     | 873/2000 [26:13<33:06,  1.76s/it, loss=0.265, lr=0.0001]
Steps:  44%|████▎     | 873/2000 [26:13<33:06,  1.76s/it, loss=0.206, lr=0.0001]
Steps:  44%|████▎     | 873/2000 [26:13<33:06,  1.76s/it, loss=0.115, lr=0.0001]
Steps:  44%|████▎     | 873/2000 [26:14<33:06,  1.76s/it, loss=0.0907, lr=0.0001]
Steps:  44%|████▎     | 873/2000 [26:14<33:06,  1.76s/it, loss=0.16, lr=0.0001]  
Steps:  44%|████▎     | 874/2000 [26:14<34:02,  1.81s/it, loss=0.16, lr=0.0001]
Steps:  44%|████▎     | 874/2000 [26:14<34:02,  1.81s/it, loss=0.427, lr=0.0001]
Steps:  44%|████▎     | 874/2000 [26:15<34:02,  1.81s/it, loss=0.079, lr=0.0001]
Steps:  44%|████▎     | 874/2000 [26:15<34:02,  1.81s/it, loss=0.222, lr=0.0001]
Steps:  44%|████▎     | 874/2000 [26:16<34:02,  1.81s/it, loss=3.23, lr=0.0001] 
Steps:  44%|████▍     | 875/2000 [26:16<33:13,  1.77s/it, loss=3.23, lr=0.0001]
Steps:  44%|████▍     | 875/2000 [26:16<33:13,  1.77s/it, loss=0.152, lr=0.0001]
Steps:  44%|████▍     | 875/2000 [26:17<33:13,  1.77s/it, loss=0.262, lr=0.0001]
Steps:  44%|████▍     | 875/2000 [26:17<33:13,  1.77s/it, loss=0.0794, lr=0.0001]
Steps:  44%|████▍     | 875/2000 [26:17<33:13,  1.77s/it, loss=0.186, lr=0.0001] 
Steps:  44%|████▍     | 876/2000 [26:18<32:35,  1.74s/it, loss=0.186, lr=0.0001]
Steps:  44%|████▍     | 876/2000 [26:18<32:35,  1.74s/it, loss=0.264, lr=0.0001]
Steps:  44%|████▍     | 876/2000 [26:18<32:35,  1.74s/it, loss=0.238, lr=0.0001]
Steps:  44%|████▍     | 876/2000 [26:19<32:35,  1.74s/it, loss=0.259, lr=0.0001]
Steps:  44%|████▍     | 876/2000 [26:19<32:35,  1.74s/it, loss=0.578, lr=0.0001]
Steps:  44%|████▍     | 877/2000 [26:20<33:23,  1.78s/it, loss=0.578, lr=0.0001]
Steps:  44%|████▍     | 877/2000 [26:20<33:23,  1.78s/it, loss=0.274, lr=0.0001]
Steps:  44%|████▍     | 877/2000 [26:20<33:23,  1.78s/it, loss=0.411, lr=0.0001]
Steps:  44%|████▍     | 877/2000 [26:20<33:23,  1.78s/it, loss=0.118, lr=0.0001]
Steps:  44%|████▍     | 877/2000 [26:21<33:23,  1.78s/it, loss=0.14, lr=0.0001] 
Steps:  44%|████▍     | 878/2000 [26:21<32:54,  1.76s/it, loss=0.14, lr=0.0001]
Steps:  44%|████▍     | 878/2000 [26:21<32:54,  1.76s/it, loss=0.0202, lr=0.0001]
Steps:  44%|████▍     | 878/2000 [26:22<32:54,  1.76s/it, loss=0.204, lr=0.0001] 
Steps:  44%|████▍     | 878/2000 [26:22<32:54,  1.76s/it, loss=0.242, lr=0.0001]
Steps:  44%|████▍     | 878/2000 [26:23<32:54,  1.76s/it, loss=0.161, lr=0.0001]
Steps:  44%|████▍     | 879/2000 [26:23<32:17,  1.73s/it, loss=0.161, lr=0.0001]
Steps:  44%|████▍     | 879/2000 [26:23<32:17,  1.73s/it, loss=0.26, lr=0.0001] 
Steps:  44%|████▍     | 879/2000 [26:23<32:17,  1.73s/it, loss=0.257, lr=0.0001]
Steps:  44%|████▍     | 879/2000 [26:24<32:17,  1.73s/it, loss=0.142, lr=0.0001]
Steps:  44%|████▍     | 879/2000 [26:25<32:17,  1.73s/it, loss=0.278, lr=0.0001]
Steps:  44%|████▍     | 880/2000 [26:25<33:14,  1.78s/it, loss=0.278, lr=0.0001]
Steps:  44%|████▍     | 880/2000 [26:25<33:14,  1.78s/it, loss=0.127, lr=0.0001]05/30/2026 08:58:50 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/config.json "HTTP/1.1 200 OK"
05/30/2026 08:58:51 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/config.json "HTTP/1.1 200 OK"
05/30/2026 08:58:51 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/model.safetensors "HTTP/1.1 302 Found"


Loading weights:   0%|          | 0/196 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 196/196 [00:00<00:00, 8701.88it/s]
05/30/2026 08:58:51 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/config.json "HTTP/1.1 200 OK"
05/30/2026 08:58:51 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/config.json "HTTP/1.1 200 OK"
05/30/2026 08:58:51 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/model.safetensors "HTTP/1.1 404 Not Found"
05/30/2026 08:58:52 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/model.safetensors.index.json "HTTP/1.1 200 OK"
05/30/2026 08:58:52 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev/revision/main "HTTP/1.1 200 OK"


Fetching 2 files:   0%|          | 0/2 [00:00<?, ?it/s]
Fetching 2 files: 100%|██████████| 2/2 [00:00<00:00, 5890.88it/s]


Loading weights:   0%|          | 0/219 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 219/219 [00:00<00:00, 9175.25it/s]
05/30/2026 08:58:52 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev "HTTP/1.1 200 OK"
05/30/2026 08:58:52 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/model_index.json "HTTP/1.1 200 OK"
{'feature_extractor', 'image_encoder'} was not found in config. Values will be initialized to default values.


Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]Loaded tokenizer_2 as T5TokenizerFast from `tokenizer_2` subfolder of black-forest-labs/FLUX.1-dev.


Loading pipeline components...:  43%|████▎     | 3/7 [00:00<00:00, 18.57it/s]Loaded tokenizer as CLIPTokenizer from `tokenizer` subfolder of black-forest-labs/FLUX.1-dev.
{'stochastic_sampling', 'use_beta_sigmas', 'invert_sigmas', 'time_shift_type', 'use_exponential_sigmas', 'shift_terminal', 'use_karras_sigmas'} was not found in config. Values will be initialized to default values.
Loaded scheduler as FlowMatchEulerDiscreteScheduler from `scheduler` subfolder of black-forest-labs/FLUX.1-dev.

Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 32.89it/s]
05/30/2026 08:58:52 - INFO - __main__ - [RANK 0] Running validation... 
 Generating 1 images with prompt: emj icon of a pelican with a hat, centered on a plain white background.

Steps:  44%|████▍     | 880/2000 [26:38<33:14,  1.78s/it, loss=0.224, lr=0.0001]
Steps:  44%|████▍     | 880/2000 [26:39<33:14,  1.78s/it, loss=0.0876, lr=0.0001]
Steps:  44%|████▍     | 880/2000 [26:39<33:14,  1.78s/it, loss=0.138, lr=0.0001] 
Steps:  44%|████▍     | 881/2000 [26:40<1:44:50,  5.62s/it, loss=0.138, lr=0.0001]
Steps:  44%|████▍     | 881/2000 [26:40<1:44:50,  5.62s/it, loss=0.185, lr=0.0001]
Steps:  44%|████▍     | 881/2000 [26:40<1:44:50,  5.62s/it, loss=0.199, lr=0.0001]
Steps:  44%|████▍     | 881/2000 [26:40<1:44:50,  5.62s/it, loss=0.743, lr=0.0001]
Steps:  44%|████▍     | 881/2000 [26:41<1:44:50,  5.62s/it, loss=0.377, lr=0.0001]
Steps:  44%|████▍     | 882/2000 [26:41<1:22:40,  4.44s/it, loss=0.377, lr=0.0001]
Steps:  44%|████▍     | 882/2000 [26:41<1:22:40,  4.44s/it, loss=0.297, lr=0.0001]
Steps:  44%|████▍     | 882/2000 [26:42<1:22:40,  4.44s/it, loss=0.314, lr=0.0001]
Steps:  44%|████▍     | 882/2000 [26:42<1:22:40,  4.44s/it, loss=0.198, lr=0.0001]
Steps:  44%|████▍     | 882/2000 [26:42<1:22:40,  4.44s/it, loss=0.191, lr=0.0001]
Steps:  44%|████▍     | 883/2000 [26:43<1:06:55,  3.60s/it, loss=0.191, lr=0.0001]
Steps:  44%|████▍     | 883/2000 [26:43<1:06:55,  3.60s/it, loss=0.149, lr=0.0001]
Steps:  44%|████▍     | 883/2000 [26:43<1:06:55,  3.60s/it, loss=0.21, lr=0.0001] 
Steps:  44%|████▍     | 883/2000 [26:44<1:06:55,  3.60s/it, loss=0.186, lr=0.0001]
Steps:  44%|████▍     | 883/2000 [26:44<1:06:55,  3.60s/it, loss=0.234, lr=0.0001]
Steps:  44%|████▍     | 884/2000 [26:45<57:12,  3.08s/it, loss=0.234, lr=0.0001]  
Steps:  44%|████▍     | 884/2000 [26:45<57:12,  3.08s/it, loss=0.426, lr=0.0001]
Steps:  44%|████▍     | 884/2000 [26:45<57:12,  3.08s/it, loss=0.195, lr=0.0001]
Steps:  44%|████▍     | 884/2000 [26:46<57:12,  3.08s/it, loss=0.612, lr=0.0001]
Steps:  44%|████▍     | 884/2000 [26:46<57:12,  3.08s/it, loss=0.435, lr=0.0001]
Steps:  44%|████▍     | 885/2000 [26:46<49:10,  2.65s/it, loss=0.435, lr=0.0001]
Steps:  44%|████▍     | 885/2000 [26:46<49:10,  2.65s/it, loss=0.111, lr=0.0001]
Steps:  44%|████▍     | 885/2000 [26:47<49:10,  2.65s/it, loss=0.0604, lr=0.0001]
Steps:  44%|████▍     | 885/2000 [26:47<49:10,  2.65s/it, loss=0.052, lr=0.0001] 
Steps:  44%|████▍     | 885/2000 [26:48<49:10,  2.65s/it, loss=0.375, lr=0.0001]
Steps:  44%|████▍     | 886/2000 [26:48<43:44,  2.36s/it, loss=0.375, lr=0.0001]
Steps:  44%|████▍     | 886/2000 [26:48<43:44,  2.36s/it, loss=0.132, lr=0.0001]
Steps:  44%|████▍     | 886/2000 [26:48<43:44,  2.36s/it, loss=0.221, lr=0.0001]
Steps:  44%|████▍     | 886/2000 [26:49<43:44,  2.36s/it, loss=0.172, lr=0.0001]
Steps:  44%|████▍     | 886/2000 [26:49<43:44,  2.36s/it, loss=1.1, lr=0.0001]  
Steps:  44%|████▍     | 887/2000 [26:50<41:02,  2.21s/it, loss=1.1, lr=0.0001]
Steps:  44%|████▍     | 887/2000 [26:50<41:02,  2.21s/it, loss=0.317, lr=0.0001]
Steps:  44%|████▍     | 887/2000 [26:50<41:02,  2.21s/it, loss=0.199, lr=0.0001]
Steps:  44%|████▍     | 887/2000 [26:51<41:02,  2.21s/it, loss=0.186, lr=0.0001]
Steps:  44%|████▍     | 887/2000 [26:51<41:02,  2.21s/it, loss=0.157, lr=0.0001]
Steps:  44%|████▍     | 888/2000 [26:52<38:25,  2.07s/it, loss=0.157, lr=0.0001]
Steps:  44%|████▍     | 888/2000 [26:52<38:25,  2.07s/it, loss=0.319, lr=0.0001]
Steps:  44%|████▍     | 888/2000 [26:52<38:25,  2.07s/it, loss=0.182, lr=0.0001]
Steps:  44%|████▍     | 888/2000 [26:52<38:25,  2.07s/it, loss=0.101, lr=0.0001]
Steps:  44%|████▍     | 888/2000 [26:53<38:25,  2.07s/it, loss=0.207, lr=0.0001]
Steps:  44%|████▍     | 889/2000 [26:53<36:17,  1.96s/it, loss=0.207, lr=0.0001]
Steps:  44%|████▍     | 889/2000 [26:53<36:17,  1.96s/it, loss=1.04, lr=0.0001] 
Steps:  44%|████▍     | 889/2000 [26:54<36:17,  1.96s/it, loss=0.249, lr=0.0001]
Steps:  44%|████▍     | 889/2000 [26:54<36:17,  1.96s/it, loss=0.121, lr=0.0001]
Steps:  44%|████▍     | 889/2000 [26:55<36:17,  1.96s/it, loss=0.792, lr=0.0001]
Steps:  44%|████▍     | 890/2000 [26:55<35:51,  1.94s/it, loss=0.792, lr=0.0001]
Steps:  44%|████▍     | 890/2000 [26:55<35:51,  1.94s/it, loss=0.311, lr=0.0001]
Steps:  44%|████▍     | 890/2000 [26:56<35:51,  1.94s/it, loss=0.126, lr=0.0001]
Steps:  44%|████▍     | 890/2000 [26:56<35:51,  1.94s/it, loss=0.143, lr=0.0001]
Steps:  44%|████▍     | 890/2000 [26:56<35:51,  1.94s/it, loss=0.173, lr=0.0001]
Steps:  45%|████▍     | 891/2000 [26:57<34:13,  1.85s/it, loss=0.173, lr=0.0001]
Steps:  45%|████▍     | 891/2000 [26:57<34:13,  1.85s/it, loss=1.39, lr=0.0001] 
Steps:  45%|████▍     | 891/2000 [26:57<34:13,  1.85s/it, loss=0.0632, lr=0.0001]
Steps:  45%|████▍     | 891/2000 [26:58<34:13,  1.85s/it, loss=0.168, lr=0.0001] 
Steps:  45%|████▍     | 891/2000 [26:58<34:13,  1.85s/it, loss=0.348, lr=0.0001]
Steps:  45%|████▍     | 892/2000 [26:59<32:59,  1.79s/it, loss=0.348, lr=0.0001]
Steps:  45%|████▍     | 892/2000 [26:59<32:59,  1.79s/it, loss=0.186, lr=0.0001]
Steps:  45%|████▍     | 892/2000 [26:59<32:59,  1.79s/it, loss=0.237, lr=0.0001]
Steps:  45%|████▍     | 892/2000 [26:59<32:59,  1.79s/it, loss=0.214, lr=0.0001]
Steps:  45%|████▍     | 892/2000 [27:00<32:59,  1.79s/it, loss=0.0636, lr=0.0001]
Steps:  45%|████▍     | 893/2000 [27:00<33:55,  1.84s/it, loss=0.0636, lr=0.0001]
Steps:  45%|████▍     | 893/2000 [27:00<33:55,  1.84s/it, loss=0.201, lr=0.0001] 
Steps:  45%|████▍     | 893/2000 [27:01<33:55,  1.84s/it, loss=0.165, lr=0.0001]
Steps:  45%|████▍     | 893/2000 [27:01<33:55,  1.84s/it, loss=0.165, lr=0.0001]
Steps:  45%|████▍     | 893/2000 [27:02<33:55,  1.84s/it, loss=0.973, lr=0.0001]
Steps:  45%|████▍     | 894/2000 [27:02<32:48,  1.78s/it, loss=0.973, lr=0.0001]
Steps:  45%|████▍     | 894/2000 [27:02<32:48,  1.78s/it, loss=0.179, lr=0.0001]
Steps:  45%|████▍     | 894/2000 [27:03<32:48,  1.78s/it, loss=0.306, lr=0.0001]
Steps:  45%|████▍     | 894/2000 [27:03<32:48,  1.78s/it, loss=0.238, lr=0.0001]
Steps:  45%|████▍     | 894/2000 [27:03<32:48,  1.78s/it, loss=0.85, lr=0.0001] 
Steps:  45%|████▍     | 895/2000 [27:04<32:07,  1.74s/it, loss=0.85, lr=0.0001]
Steps:  45%|████▍     | 895/2000 [27:04<32:07,  1.74s/it, loss=0.104, lr=0.0001]
Steps:  45%|████▍     | 895/2000 [27:04<32:07,  1.74s/it, loss=0.0855, lr=0.0001]
Steps:  45%|████▍     | 895/2000 [27:05<32:07,  1.74s/it, loss=0.108, lr=0.0001] 
Steps:  45%|████▍     | 895/2000 [27:05<32:07,  1.74s/it, loss=0.143, lr=0.0001]
Steps:  45%|████▍     | 896/2000 [27:06<33:17,  1.81s/it, loss=0.143, lr=0.0001]
Steps:  45%|████▍     | 896/2000 [27:06<33:17,  1.81s/it, loss=0.226, lr=0.0001]
Steps:  45%|████▍     | 896/2000 [27:06<33:17,  1.81s/it, loss=0.15, lr=0.0001] 
Steps:  45%|████▍     | 896/2000 [27:07<33:17,  1.81s/it, loss=0.0983, lr=0.0001]
Steps:  45%|████▍     | 896/2000 [27:07<33:17,  1.81s/it, loss=0.375, lr=0.0001] 
Steps:  45%|████▍     | 897/2000 [27:07<32:53,  1.79s/it, loss=0.375, lr=0.0001]
Steps:  45%|████▍     | 897/2000 [27:07<32:53,  1.79s/it, loss=0.516, lr=0.0001]
Steps:  45%|████▍     | 897/2000 [27:08<32:53,  1.79s/it, loss=0.0725, lr=0.0001]
Steps:  45%|████▍     | 897/2000 [27:08<32:53,  1.79s/it, loss=0.156, lr=0.0001] 
Steps:  45%|████▍     | 897/2000 [27:09<32:53,  1.79s/it, loss=0.48, lr=0.0001] 
Steps:  45%|████▍     | 898/2000 [27:09<32:06,  1.75s/it, loss=0.48, lr=0.0001]
Steps:  45%|████▍     | 898/2000 [27:09<32:06,  1.75s/it, loss=0.225, lr=0.0001]
Steps:  45%|████▍     | 898/2000 [27:10<32:06,  1.75s/it, loss=1.06, lr=0.0001] 
Steps:  45%|████▍     | 898/2000 [27:10<32:06,  1.75s/it, loss=0.164, lr=0.0001]
Steps:  45%|████▍     | 898/2000 [27:10<32:06,  1.75s/it, loss=0.24, lr=0.0001] 
Steps:  45%|████▍     | 899/2000 [27:11<32:45,  1.79s/it, loss=0.24, lr=0.0001]
Steps:  45%|████▍     | 899/2000 [27:11<32:45,  1.79s/it, loss=0.209, lr=0.0001]
Steps:  45%|████▍     | 899/2000 [27:11<32:45,  1.79s/it, loss=0.217, lr=0.0001]
Steps:  45%|████▍     | 899/2000 [27:12<32:45,  1.79s/it, loss=0.243, lr=0.0001]
Steps:  45%|████▍     | 899/2000 [27:12<32:45,  1.79s/it, loss=0.155, lr=0.0001]
Steps:  45%|████▌     | 900/2000 [27:13<31:55,  1.74s/it, loss=0.155, lr=0.0001]
Steps:  45%|████▌     | 900/2000 [27:13<31:55,  1.74s/it, loss=0.21, lr=0.0001] 
Steps:  45%|████▌     | 900/2000 [27:13<31:55,  1.74s/it, loss=0.183, lr=0.0001]
Steps:  45%|████▌     | 900/2000 [27:13<31:55,  1.74s/it, loss=0.874, lr=0.0001]
Steps:  45%|████▌     | 900/2000 [27:14<31:55,  1.74s/it, loss=0.329, lr=0.0001]
Steps:  45%|████▌     | 901/2000 [27:14<31:17,  1.71s/it, loss=0.329, lr=0.0001]
Steps:  45%|████▌     | 901/2000 [27:14<31:17,  1.71s/it, loss=0.15, lr=0.0001] 
Steps:  45%|████▌     | 901/2000 [27:15<31:17,  1.71s/it, loss=0.267, lr=0.0001]
Steps:  45%|████▌     | 901/2000 [27:15<31:17,  1.71s/it, loss=0.188, lr=0.0001]
Steps:  45%|████▌     | 901/2000 [27:15<31:17,  1.71s/it, loss=0.253, lr=0.0001]
Steps:  45%|████▌     | 902/2000 [27:16<30:51,  1.69s/it, loss=0.253, lr=0.0001]
Steps:  45%|████▌     | 902/2000 [27:16<30:51,  1.69s/it, loss=0.121, lr=0.0001]
Steps:  45%|████▌     | 902/2000 [27:17<30:51,  1.69s/it, loss=0.197, lr=0.0001]
Steps:  45%|████▌     | 902/2000 [27:17<30:51,  1.69s/it, loss=0.123, lr=0.0001]
Steps:  45%|████▌     | 902/2000 [27:17<30:51,  1.69s/it, loss=0.137, lr=0.0001]
Steps:  45%|████▌     | 903/2000 [27:18<31:50,  1.74s/it, loss=0.137, lr=0.0001]
Steps:  45%|████▌     | 903/2000 [27:18<31:50,  1.74s/it, loss=0.152, lr=0.0001]
Steps:  45%|████▌     | 903/2000 [27:18<31:50,  1.74s/it, loss=0.257, lr=0.0001]
Steps:  45%|████▌     | 903/2000 [27:19<31:50,  1.74s/it, loss=0.167, lr=0.0001]
Steps:  45%|████▌     | 903/2000 [27:19<31:50,  1.74s/it, loss=0.189, lr=0.0001]
Steps:  45%|████▌     | 904/2000 [27:19<31:13,  1.71s/it, loss=0.189, lr=0.0001]
Steps:  45%|████▌     | 904/2000 [27:19<31:13,  1.71s/it, loss=0.143, lr=0.0001]
Steps:  45%|████▌     | 904/2000 [27:20<31:13,  1.71s/it, loss=0.164, lr=0.0001]
Steps:  45%|████▌     | 904/2000 [27:20<31:13,  1.71s/it, loss=0.158, lr=0.0001]
Steps:  45%|████▌     | 904/2000 [27:21<31:13,  1.71s/it, loss=0.134, lr=0.0001]
Steps:  45%|████▌     | 905/2000 [27:21<30:50,  1.69s/it, loss=0.134, lr=0.0001]
Steps:  45%|████▌     | 905/2000 [27:21<30:50,  1.69s/it, loss=0.116, lr=0.0001]
Steps:  45%|████▌     | 905/2000 [27:21<30:50,  1.69s/it, loss=0.129, lr=0.0001]
Steps:  45%|████▌     | 905/2000 [27:22<30:50,  1.69s/it, loss=0.24, lr=0.0001] 
Steps:  45%|████▌     | 905/2000 [27:22<30:50,  1.69s/it, loss=0.0983, lr=0.0001]
Steps:  45%|████▌     | 906/2000 [27:23<31:46,  1.74s/it, loss=0.0983, lr=0.0001]
Steps:  45%|████▌     | 906/2000 [27:23<31:46,  1.74s/it, loss=0.14, lr=0.0001]  
Steps:  45%|████▌     | 906/2000 [27:23<31:46,  1.74s/it, loss=0.0769, lr=0.0001]
Steps:  45%|████▌     | 906/2000 [27:24<31:46,  1.74s/it, loss=0.208, lr=0.0001] 
Steps:  45%|████▌     | 906/2000 [27:24<31:46,  1.74s/it, loss=0.12, lr=0.0001] 
Steps:  45%|████▌     | 907/2000 [27:25<31:08,  1.71s/it, loss=0.12, lr=0.0001]
Steps:  45%|████▌     | 907/2000 [27:25<31:08,  1.71s/it, loss=0.203, lr=0.0001]
Steps:  45%|████▌     | 907/2000 [27:25<31:08,  1.71s/it, loss=0.115, lr=0.0001]
Steps:  45%|████▌     | 907/2000 [27:25<31:08,  1.71s/it, loss=0.157, lr=0.0001]
Steps:  45%|████▌     | 907/2000 [27:26<31:08,  1.71s/it, loss=0.0923, lr=0.0001]
Steps:  45%|████▌     | 908/2000 [27:26<30:42,  1.69s/it, loss=0.0923, lr=0.0001]
Steps:  45%|████▌     | 908/2000 [27:26<30:42,  1.69s/it, loss=0.107, lr=0.0001] 
Steps:  45%|████▌     | 908/2000 [27:27<30:42,  1.69s/it, loss=0.23, lr=0.0001] 
Steps:  45%|████▌     | 908/2000 [27:27<30:42,  1.69s/it, loss=0.175, lr=0.0001]
Steps:  45%|████▌     | 908/2000 [27:28<30:42,  1.69s/it, loss=0.138, lr=0.0001]
Steps:  45%|████▌     | 909/2000 [27:28<31:45,  1.75s/it, loss=0.138, lr=0.0001]
Steps:  45%|████▌     | 909/2000 [27:28<31:45,  1.75s/it, loss=0.263, lr=0.0001]
Steps:  45%|████▌     | 909/2000 [27:28<31:45,  1.75s/it, loss=0.135, lr=0.0001]
Steps:  45%|████▌     | 909/2000 [27:29<31:45,  1.75s/it, loss=0.189, lr=0.0001]
Steps:  45%|████▌     | 909/2000 [27:29<31:45,  1.75s/it, loss=0.204, lr=0.0001]
Steps:  46%|████▌     | 910/2000 [27:30<31:10,  1.72s/it, loss=0.204, lr=0.0001]
Steps:  46%|████▌     | 910/2000 [27:30<31:10,  1.72s/it, loss=0.113, lr=0.0001]
Steps:  46%|████▌     | 910/2000 [27:30<31:10,  1.72s/it, loss=0.707, lr=0.0001]
Steps:  46%|████▌     | 910/2000 [27:31<31:10,  1.72s/it, loss=0.476, lr=0.0001]
Steps:  46%|████▌     | 910/2000 [27:31<31:10,  1.72s/it, loss=0.281, lr=0.0001]
Steps:  46%|████▌     | 911/2000 [27:31<30:49,  1.70s/it, loss=0.281, lr=0.0001]
Steps:  46%|████▌     | 911/2000 [27:31<30:49,  1.70s/it, loss=0.0947, lr=0.0001]
Steps:  46%|████▌     | 911/2000 [27:32<30:49,  1.70s/it, loss=0.0219, lr=0.0001]
Steps:  46%|████▌     | 911/2000 [27:32<30:49,  1.70s/it, loss=0.179, lr=0.0001] 
Steps:  46%|████▌     | 911/2000 [27:33<30:49,  1.70s/it, loss=0.657, lr=0.0001]
Steps:  46%|████▌     | 912/2000 [27:33<31:58,  1.76s/it, loss=0.657, lr=0.0001]
Steps:  46%|████▌     | 912/2000 [27:33<31:58,  1.76s/it, loss=0.127, lr=0.0001]
Steps:  46%|████▌     | 912/2000 [27:34<31:58,  1.76s/it, loss=0.151, lr=0.0001]
Steps:  46%|████▌     | 912/2000 [27:34<31:58,  1.76s/it, loss=1.48, lr=0.0001] 
Steps:  46%|████▌     | 912/2000 [27:35<31:58,  1.76s/it, loss=0.227, lr=0.0001]
Steps:  46%|████▌     | 913/2000 [27:35<31:16,  1.73s/it, loss=0.227, lr=0.0001]
Steps:  46%|████▌     | 913/2000 [27:35<31:16,  1.73s/it, loss=0.108, lr=0.0001]
Steps:  46%|████▌     | 913/2000 [27:35<31:16,  1.73s/it, loss=0.156, lr=0.0001]
Steps:  46%|████▌     | 913/2000 [27:36<31:16,  1.73s/it, loss=0.0994, lr=0.0001]
Steps:  46%|████▌     | 913/2000 [27:36<31:16,  1.73s/it, loss=0.123, lr=0.0001] 
Steps:  46%|████▌     | 914/2000 [27:37<30:48,  1.70s/it, loss=0.123, lr=0.0001]
Steps:  46%|████▌     | 914/2000 [27:37<30:48,  1.70s/it, loss=0.228, lr=0.0001]
Steps:  46%|████▌     | 914/2000 [27:37<30:48,  1.70s/it, loss=0.0939, lr=0.0001]
Steps:  46%|████▌     | 914/2000 [27:37<30:48,  1.70s/it, loss=0.481, lr=0.0001] 
Steps:  46%|████▌     | 914/2000 [27:38<30:48,  1.70s/it, loss=0.285, lr=0.0001]
Steps:  46%|████▌     | 915/2000 [27:38<31:43,  1.75s/it, loss=0.285, lr=0.0001]
Steps:  46%|████▌     | 915/2000 [27:38<31:43,  1.75s/it, loss=0.0663, lr=0.0001]
Steps:  46%|████▌     | 915/2000 [27:39<31:43,  1.75s/it, loss=0.175, lr=0.0001] 
Steps:  46%|████▌     | 915/2000 [27:39<31:43,  1.75s/it, loss=0.217, lr=0.0001]
Steps:  46%|████▌     | 915/2000 [27:40<31:43,  1.75s/it, loss=0.132, lr=0.0001]
Steps:  46%|████▌     | 916/2000 [27:40<31:06,  1.72s/it, loss=0.132, lr=0.0001]
Steps:  46%|████▌     | 916/2000 [27:40<31:06,  1.72s/it, loss=0.162, lr=0.0001]
Steps:  46%|████▌     | 916/2000 [27:41<31:06,  1.72s/it, loss=0.13, lr=0.0001] 
Steps:  46%|████▌     | 916/2000 [27:41<31:06,  1.72s/it, loss=0.24, lr=0.0001]
Steps:  46%|████▌     | 916/2000 [27:41<31:06,  1.72s/it, loss=0.138, lr=0.0001]
Steps:  46%|████▌     | 917/2000 [27:42<30:42,  1.70s/it, loss=0.138, lr=0.0001]
Steps:  46%|████▌     | 917/2000 [27:42<30:42,  1.70s/it, loss=0.297, lr=0.0001]
Steps:  46%|████▌     | 917/2000 [27:42<30:42,  1.70s/it, loss=1.32, lr=0.0001] 
Steps:  46%|████▌     | 917/2000 [27:43<30:42,  1.70s/it, loss=0.169, lr=0.0001]
Steps:  46%|████▌     | 917/2000 [27:43<30:42,  1.70s/it, loss=0.167, lr=0.0001]
Steps:  46%|████▌     | 918/2000 [27:44<31:53,  1.77s/it, loss=0.167, lr=0.0001]
Steps:  46%|████▌     | 918/2000 [27:44<31:53,  1.77s/it, loss=1.65, lr=0.0001] 
Steps:  46%|████▌     | 918/2000 [27:44<31:53,  1.77s/it, loss=0.207, lr=0.0001]
Steps:  46%|████▌     | 918/2000 [27:45<31:53,  1.77s/it, loss=0.328, lr=0.0001]
Steps:  46%|████▌     | 918/2000 [27:45<31:53,  1.77s/it, loss=0.188, lr=0.0001]
Steps:  46%|████▌     | 919/2000 [27:45<31:23,  1.74s/it, loss=0.188, lr=0.0001]
Steps:  46%|████▌     | 919/2000 [27:45<31:23,  1.74s/it, loss=0.11, lr=0.0001] 
Steps:  46%|████▌     | 919/2000 [27:46<31:23,  1.74s/it, loss=0.0817, lr=0.0001]
Steps:  46%|████▌     | 919/2000 [27:46<31:23,  1.74s/it, loss=0.644, lr=0.0001] 
Steps:  46%|████▌     | 919/2000 [27:47<31:23,  1.74s/it, loss=0.161, lr=0.0001]
Steps:  46%|████▌     | 920/2000 [27:47<31:02,  1.72s/it, loss=0.161, lr=0.0001]
Steps:  46%|████▌     | 920/2000 [27:47<31:02,  1.72s/it, loss=0.126, lr=0.0001]
Steps:  46%|████▌     | 920/2000 [27:47<31:02,  1.72s/it, loss=0.275, lr=0.0001]
Steps:  46%|████▌     | 920/2000 [27:48<31:02,  1.72s/it, loss=0.221, lr=0.0001]
Steps:  46%|████▌     | 920/2000 [27:48<31:02,  1.72s/it, loss=0.146, lr=0.0001]
Steps:  46%|████▌     | 921/2000 [27:49<30:46,  1.71s/it, loss=0.146, lr=0.0001]
Steps:  46%|████▌     | 921/2000 [27:49<30:46,  1.71s/it, loss=0.147, lr=0.0001]
Steps:  46%|████▌     | 921/2000 [27:49<30:46,  1.71s/it, loss=0.219, lr=0.0001]
Steps:  46%|████▌     | 921/2000 [27:50<30:46,  1.71s/it, loss=0.199, lr=0.0001]
Steps:  46%|████▌     | 921/2000 [27:50<30:46,  1.71s/it, loss=0.266, lr=0.0001]
Steps:  46%|████▌     | 922/2000 [27:51<31:44,  1.77s/it, loss=0.266, lr=0.0001]
Steps:  46%|████▌     | 922/2000 [27:51<31:44,  1.77s/it, loss=0.177, lr=0.0001]
Steps:  46%|████▌     | 922/2000 [27:51<31:44,  1.77s/it, loss=0.174, lr=0.0001]
Steps:  46%|████▌     | 922/2000 [27:51<31:44,  1.77s/it, loss=0.179, lr=0.0001]
Steps:  46%|████▌     | 922/2000 [27:52<31:44,  1.77s/it, loss=0.15, lr=0.0001] 
Steps:  46%|████▌     | 923/2000 [27:52<31:10,  1.74s/it, loss=0.15, lr=0.0001]
Steps:  46%|████▌     | 923/2000 [27:52<31:10,  1.74s/it, loss=0.1, lr=0.0001] 
Steps:  46%|████▌     | 923/2000 [27:53<31:10,  1.74s/it, loss=0.0972, lr=0.0001]
Steps:  46%|████▌     | 923/2000 [27:53<31:10,  1.74s/it, loss=0.192, lr=0.0001] 
Steps:  46%|████▌     | 923/2000 [27:54<31:10,  1.74s/it, loss=0.149, lr=0.0001]
Steps:  46%|████▌     | 924/2000 [27:54<31:04,  1.73s/it, loss=0.149, lr=0.0001]
Steps:  46%|████▌     | 924/2000 [27:54<31:04,  1.73s/it, loss=0.148, lr=0.0001]
Steps:  46%|████▌     | 924/2000 [27:55<31:04,  1.73s/it, loss=0.226, lr=0.0001]
Steps:  46%|████▌     | 924/2000 [27:55<31:04,  1.73s/it, loss=0.175, lr=0.0001]
Steps:  46%|████▌     | 924/2000 [27:55<31:04,  1.73s/it, loss=0.393, lr=0.0001]
Steps:  46%|████▋     | 925/2000 [27:56<31:54,  1.78s/it, loss=0.393, lr=0.0001]
Steps:  46%|████▋     | 925/2000 [27:56<31:54,  1.78s/it, loss=1.77, lr=0.0001] 
Steps:  46%|████▋     | 925/2000 [27:56<31:54,  1.78s/it, loss=0.522, lr=0.0001]
Steps:  46%|████▋     | 925/2000 [27:57<31:54,  1.78s/it, loss=0.112, lr=0.0001]
Steps:  46%|████▋     | 925/2000 [27:57<31:54,  1.78s/it, loss=0.0658, lr=0.0001]
Steps:  46%|████▋     | 926/2000 [27:58<31:21,  1.75s/it, loss=0.0658, lr=0.0001]
Steps:  46%|████▋     | 926/2000 [27:58<31:21,  1.75s/it, loss=0.312, lr=0.0001] 
Steps:  46%|████▋     | 926/2000 [27:58<31:21,  1.75s/it, loss=0.15, lr=0.0001] 
Steps:  46%|████▋     | 926/2000 [27:58<31:21,  1.75s/it, loss=0.197, lr=0.0001]
Steps:  46%|████▋     | 926/2000 [27:59<31:21,  1.75s/it, loss=0.169, lr=0.0001]
Steps:  46%|████▋     | 927/2000 [27:59<30:59,  1.73s/it, loss=0.169, lr=0.0001]
Steps:  46%|████▋     | 927/2000 [27:59<30:59,  1.73s/it, loss=0.122, lr=0.0001]
Steps:  46%|████▋     | 927/2000 [28:00<30:59,  1.73s/it, loss=0.169, lr=0.0001]
Steps:  46%|████▋     | 927/2000 [28:00<30:59,  1.73s/it, loss=0.254, lr=0.0001]
Steps:  46%|████▋     | 927/2000 [28:01<30:59,  1.73s/it, loss=0.228, lr=0.0001]
Steps:  46%|████▋     | 928/2000 [28:01<31:59,  1.79s/it, loss=0.228, lr=0.0001]
Steps:  46%|████▋     | 928/2000 [28:01<31:59,  1.79s/it, loss=0.301, lr=0.0001]
Steps:  46%|████▋     | 928/2000 [28:02<31:59,  1.79s/it, loss=0.182, lr=0.0001]
Steps:  46%|████▋     | 928/2000 [28:02<31:59,  1.79s/it, loss=0.0599, lr=0.0001]
Steps:  46%|████▋     | 928/2000 [28:02<31:59,  1.79s/it, loss=0.124, lr=0.0001] 
Steps:  46%|████▋     | 929/2000 [28:03<31:19,  1.75s/it, loss=0.124, lr=0.0001]
Steps:  46%|████▋     | 929/2000 [28:03<31:19,  1.75s/it, loss=0.278, lr=0.0001]
Steps:  46%|████▋     | 929/2000 [28:03<31:19,  1.75s/it, loss=0.119, lr=0.0001]
Steps:  46%|████▋     | 929/2000 [28:04<31:19,  1.75s/it, loss=0.117, lr=0.0001]
Steps:  46%|████▋     | 929/2000 [28:04<31:19,  1.75s/it, loss=0.124, lr=0.0001]
Steps:  46%|████▋     | 930/2000 [28:05<31:06,  1.74s/it, loss=0.124, lr=0.0001]
Steps:  46%|████▋     | 930/2000 [28:05<31:06,  1.74s/it, loss=0.219, lr=0.0001]
Steps:  46%|████▋     | 930/2000 [28:05<31:06,  1.74s/it, loss=0.186, lr=0.0001]
Steps:  46%|████▋     | 930/2000 [28:06<31:06,  1.74s/it, loss=0.233, lr=0.0001]
Steps:  46%|████▋     | 930/2000 [28:06<31:06,  1.74s/it, loss=0.193, lr=0.0001]
Steps:  47%|████▋     | 931/2000 [28:07<32:03,  1.80s/it, loss=0.193, lr=0.0001]
Steps:  47%|████▋     | 931/2000 [28:07<32:03,  1.80s/it, loss=0.143, lr=0.0001]
Steps:  47%|████▋     | 931/2000 [28:07<32:03,  1.80s/it, loss=0.17, lr=0.0001] 
Steps:  47%|████▋     | 931/2000 [28:07<32:03,  1.80s/it, loss=0.176, lr=0.0001]
Steps:  47%|████▋     | 931/2000 [28:08<32:03,  1.80s/it, loss=0.18, lr=0.0001] 
Steps:  47%|████▋     | 932/2000 [28:08<31:17,  1.76s/it, loss=0.18, lr=0.0001]
Steps:  47%|████▋     | 932/2000 [28:08<31:17,  1.76s/it, loss=0.174, lr=0.0001]
Steps:  47%|████▋     | 932/2000 [28:09<31:17,  1.76s/it, loss=0.661, lr=0.0001]
Steps:  47%|████▋     | 932/2000 [28:09<31:17,  1.76s/it, loss=0.994, lr=0.0001]
Steps:  47%|████▋     | 932/2000 [28:09<31:17,  1.76s/it, loss=0.235, lr=0.0001]
Steps:  47%|████▋     | 933/2000 [28:10<30:58,  1.74s/it, loss=0.235, lr=0.0001]
Steps:  47%|████▋     | 933/2000 [28:10<30:58,  1.74s/it, loss=0.209, lr=0.0001]
Steps:  47%|████▋     | 933/2000 [28:10<30:58,  1.74s/it, loss=0.144, lr=0.0001]
Steps:  47%|████▋     | 933/2000 [28:11<30:58,  1.74s/it, loss=0.104, lr=0.0001]
Steps:  47%|████▋     | 933/2000 [28:11<30:58,  1.74s/it, loss=0.194, lr=0.0001]
Steps:  47%|████▋     | 934/2000 [28:12<31:58,  1.80s/it, loss=0.194, lr=0.0001]
Steps:  47%|████▋     | 934/2000 [28:12<31:58,  1.80s/it, loss=0.233, lr=0.0001]
Steps:  47%|████▋     | 934/2000 [28:12<31:58,  1.80s/it, loss=0.582, lr=0.0001]
Steps:  47%|████▋     | 934/2000 [28:13<31:58,  1.80s/it, loss=0.157, lr=0.0001]
Steps:  47%|████▋     | 934/2000 [28:13<31:58,  1.80s/it, loss=0.232, lr=0.0001]
Steps:  47%|████▋     | 935/2000 [28:14<31:28,  1.77s/it, loss=0.232, lr=0.0001]
Steps:  47%|████▋     | 935/2000 [28:14<31:28,  1.77s/it, loss=0.169, lr=0.0001]
Steps:  47%|████▋     | 935/2000 [28:14<31:28,  1.77s/it, loss=0.149, lr=0.0001]
Steps:  47%|████▋     | 935/2000 [28:14<31:28,  1.77s/it, loss=0.109, lr=0.0001]
Steps:  47%|████▋     | 935/2000 [28:15<31:28,  1.77s/it, loss=0.138, lr=0.0001]
Steps:  47%|████▋     | 936/2000 [28:15<31:18,  1.77s/it, loss=0.138, lr=0.0001]
Steps:  47%|████▋     | 936/2000 [28:15<31:18,  1.77s/it, loss=0.204, lr=0.0001]
Steps:  47%|████▋     | 936/2000 [28:16<31:18,  1.77s/it, loss=0.168, lr=0.0001]
Steps:  47%|████▋     | 936/2000 [28:16<31:18,  1.77s/it, loss=0.187, lr=0.0001]
Steps:  47%|████▋     | 936/2000 [28:17<31:18,  1.77s/it, loss=0.119, lr=0.0001]
Steps:  47%|████▋     | 937/2000 [28:17<32:34,  1.84s/it, loss=0.119, lr=0.0001]
Steps:  47%|████▋     | 937/2000 [28:17<32:34,  1.84s/it, loss=0.278, lr=0.0001]
Steps:  47%|████▋     | 937/2000 [28:18<32:34,  1.84s/it, loss=0.245, lr=0.0001]
Steps:  47%|████▋     | 937/2000 [28:18<32:34,  1.84s/it, loss=0.0823, lr=0.0001]
Steps:  47%|████▋     | 937/2000 [28:19<32:34,  1.84s/it, loss=0.252, lr=0.0001] 
Steps:  47%|████▋     | 938/2000 [28:19<31:52,  1.80s/it, loss=0.252, lr=0.0001]
Steps:  47%|████▋     | 938/2000 [28:19<31:52,  1.80s/it, loss=0.144, lr=0.0001]
Steps:  47%|████▋     | 938/2000 [28:19<31:52,  1.80s/it, loss=0.133, lr=0.0001]
Steps:  47%|████▋     | 938/2000 [28:20<31:52,  1.80s/it, loss=0.144, lr=0.0001]
Steps:  47%|████▋     | 938/2000 [28:20<31:52,  1.80s/it, loss=0.386, lr=0.0001]
Steps:  47%|████▋     | 939/2000 [28:21<31:09,  1.76s/it, loss=0.386, lr=0.0001]
Steps:  47%|████▋     | 939/2000 [28:21<31:09,  1.76s/it, loss=0.0925, lr=0.0001]
Steps:  47%|████▋     | 939/2000 [28:21<31:09,  1.76s/it, loss=0.284, lr=0.0001] 
Steps:  47%|████▋     | 939/2000 [28:22<31:09,  1.76s/it, loss=0.222, lr=0.0001]
Steps:  47%|████▋     | 939/2000 [28:22<31:09,  1.76s/it, loss=0.145, lr=0.0001]
Steps:  47%|████▋     | 940/2000 [28:23<31:59,  1.81s/it, loss=0.145, lr=0.0001]
Steps:  47%|████▋     | 940/2000 [28:23<31:59,  1.81s/it, loss=0.126, lr=0.0001]
Steps:  47%|████▋     | 940/2000 [28:23<31:59,  1.81s/it, loss=0.0667, lr=0.0001]
Steps:  47%|████▋     | 940/2000 [28:23<31:59,  1.81s/it, loss=0.125, lr=0.0001] 
Steps:  47%|████▋     | 940/2000 [28:24<31:59,  1.81s/it, loss=0.239, lr=0.0001]
Steps:  47%|████▋     | 941/2000 [28:24<31:13,  1.77s/it, loss=0.239, lr=0.0001]
Steps:  47%|████▋     | 941/2000 [28:24<31:13,  1.77s/it, loss=0.214, lr=0.0001]
Steps:  47%|████▋     | 941/2000 [28:25<31:13,  1.77s/it, loss=0.144, lr=0.0001]
Steps:  47%|████▋     | 941/2000 [28:25<31:13,  1.77s/it, loss=0.263, lr=0.0001]
Steps:  47%|████▋     | 941/2000 [28:25<31:13,  1.77s/it, loss=0.142, lr=0.0001]
Steps:  47%|████▋     | 942/2000 [28:26<30:35,  1.74s/it, loss=0.142, lr=0.0001]
Steps:  47%|████▋     | 942/2000 [28:26<30:35,  1.74s/it, loss=0.844, lr=0.0001]
Steps:  47%|████▋     | 942/2000 [28:26<30:35,  1.74s/it, loss=0.284, lr=0.0001]
Steps:  47%|████▋     | 942/2000 [28:27<30:35,  1.74s/it, loss=0.23, lr=0.0001] 
Steps:  47%|████▋     | 942/2000 [28:27<30:35,  1.74s/it, loss=0.168, lr=0.0001]
Steps:  47%|████▋     | 943/2000 [28:28<30:08,  1.71s/it, loss=0.168, lr=0.0001]
Steps:  47%|████▋     | 943/2000 [28:28<30:08,  1.71s/it, loss=0.172, lr=0.0001]
Steps:  47%|████▋     | 943/2000 [28:28<30:08,  1.71s/it, loss=0.127, lr=0.0001]
Steps:  47%|████▋     | 943/2000 [28:29<30:08,  1.71s/it, loss=0.169, lr=0.0001]
Steps:  47%|████▋     | 943/2000 [28:29<30:08,  1.71s/it, loss=0.713, lr=0.0001]
Steps:  47%|████▋     | 944/2000 [28:29<30:59,  1.76s/it, loss=0.713, lr=0.0001]
Steps:  47%|████▋     | 944/2000 [28:29<30:59,  1.76s/it, loss=0.0492, lr=0.0001]
Steps:  47%|████▋     | 944/2000 [28:30<30:59,  1.76s/it, loss=0.171, lr=0.0001] 
Steps:  47%|████▋     | 944/2000 [28:30<30:59,  1.76s/it, loss=0.243, lr=0.0001]
Steps:  47%|████▋     | 944/2000 [28:31<30:59,  1.76s/it, loss=0.433, lr=0.0001]
Steps:  47%|████▋     | 945/2000 [28:31<30:26,  1.73s/it, loss=0.433, lr=0.0001]
Steps:  47%|████▋     | 945/2000 [28:31<30:26,  1.73s/it, loss=0.172, lr=0.0001]
Steps:  47%|████▋     | 945/2000 [28:32<30:26,  1.73s/it, loss=0.108, lr=0.0001]
Steps:  47%|████▋     | 945/2000 [28:32<30:26,  1.73s/it, loss=0.2, lr=0.0001]  
Steps:  47%|████▋     | 945/2000 [28:32<30:26,  1.73s/it, loss=0.185, lr=0.0001]
Steps:  47%|████▋     | 946/2000 [28:33<30:01,  1.71s/it, loss=0.185, lr=0.0001]
Steps:  47%|████▋     | 946/2000 [28:33<30:01,  1.71s/it, loss=0.247, lr=0.0001]
Steps:  47%|████▋     | 946/2000 [28:33<30:01,  1.71s/it, loss=0.219, lr=0.0001]
Steps:  47%|████▋     | 946/2000 [28:34<30:01,  1.71s/it, loss=0.13, lr=0.0001] 
Steps:  47%|████▋     | 946/2000 [28:34<30:01,  1.71s/it, loss=0.203, lr=0.0001]
Steps:  47%|████▋     | 947/2000 [28:35<30:58,  1.77s/it, loss=0.203, lr=0.0001]
Steps:  47%|████▋     | 947/2000 [28:35<30:58,  1.77s/it, loss=0.163, lr=0.0001]
Steps:  47%|████▋     | 947/2000 [28:35<30:58,  1.77s/it, loss=1.03, lr=0.0001] 
Steps:  47%|████▋     | 947/2000 [28:35<30:58,  1.77s/it, loss=0.134, lr=0.0001]
Steps:  47%|████▋     | 947/2000 [28:36<30:58,  1.77s/it, loss=0.189, lr=0.0001]
Steps:  47%|████▋     | 948/2000 [28:36<30:20,  1.73s/it, loss=0.189, lr=0.0001]
Steps:  47%|████▋     | 948/2000 [28:36<30:20,  1.73s/it, loss=0.343, lr=0.0001]
Steps:  47%|████▋     | 948/2000 [28:37<30:20,  1.73s/it, loss=0.11, lr=0.0001] 
Steps:  47%|████▋     | 948/2000 [28:37<30:20,  1.73s/it, loss=0.157, lr=0.0001]
Steps:  47%|████▋     | 948/2000 [28:38<30:20,  1.73s/it, loss=0.128, lr=0.0001]
Steps:  47%|████▋     | 949/2000 [28:38<29:55,  1.71s/it, loss=0.128, lr=0.0001]
Steps:  47%|████▋     | 949/2000 [28:38<29:55,  1.71s/it, loss=0.178, lr=0.0001]
Steps:  47%|████▋     | 949/2000 [28:38<29:55,  1.71s/it, loss=0.0709, lr=0.0001]
Steps:  47%|████▋     | 949/2000 [28:39<29:55,  1.71s/it, loss=0.167, lr=0.0001] 
Steps:  47%|████▋     | 949/2000 [28:39<29:55,  1.71s/it, loss=0.331, lr=0.0001]
Steps:  48%|████▊     | 950/2000 [28:40<30:51,  1.76s/it, loss=0.331, lr=0.0001]
Steps:  48%|████▊     | 950/2000 [28:40<30:51,  1.76s/it, loss=0.0719, lr=0.0001]
Steps:  48%|████▊     | 950/2000 [28:40<30:51,  1.76s/it, loss=0.278, lr=0.0001] 
Steps:  48%|████▊     | 950/2000 [28:41<30:51,  1.76s/it, loss=0.13, lr=0.0001] 
Steps:  48%|████▊     | 950/2000 [28:41<30:51,  1.76s/it, loss=0.242, lr=0.0001]
Steps:  48%|████▊     | 951/2000 [28:42<30:14,  1.73s/it, loss=0.242, lr=0.0001]
Steps:  48%|████▊     | 951/2000 [28:42<30:14,  1.73s/it, loss=0.249, lr=0.0001]
Steps:  48%|████▊     | 951/2000 [28:42<30:14,  1.73s/it, loss=0.119, lr=0.0001]
Steps:  48%|████▊     | 951/2000 [28:42<30:14,  1.73s/it, loss=0.156, lr=0.0001]
Steps:  48%|████▊     | 951/2000 [28:43<30:14,  1.73s/it, loss=1.06, lr=0.0001] 
Steps:  48%|████▊     | 952/2000 [28:43<29:53,  1.71s/it, loss=1.06, lr=0.0001]
Steps:  48%|████▊     | 952/2000 [28:43<29:53,  1.71s/it, loss=0.112, lr=0.0001]
Steps:  48%|████▊     | 952/2000 [28:44<29:53,  1.71s/it, loss=0.256, lr=0.0001]
Steps:  48%|████▊     | 952/2000 [28:44<29:53,  1.71s/it, loss=0.292, lr=0.0001]
Steps:  48%|████▊     | 952/2000 [28:45<29:53,  1.71s/it, loss=0.157, lr=0.0001]
Steps:  48%|████▊     | 953/2000 [28:45<31:17,  1.79s/it, loss=0.157, lr=0.0001]
Steps:  48%|████▊     | 953/2000 [28:45<31:17,  1.79s/it, loss=0.164, lr=0.0001]
Steps:  48%|████▊     | 953/2000 [28:46<31:17,  1.79s/it, loss=0.196, lr=0.0001]
Steps:  48%|████▊     | 953/2000 [28:46<31:17,  1.79s/it, loss=0.285, lr=0.0001]
Steps:  48%|████▊     | 953/2000 [28:46<31:17,  1.79s/it, loss=0.106, lr=0.0001]
Steps:  48%|████▊     | 954/2000 [28:47<30:34,  1.75s/it, loss=0.106, lr=0.0001]
Steps:  48%|████▊     | 954/2000 [28:47<30:34,  1.75s/it, loss=0.0642, lr=0.0001]
Steps:  48%|████▊     | 954/2000 [28:47<30:34,  1.75s/it, loss=0.279, lr=0.0001] 
Steps:  48%|████▊     | 954/2000 [28:48<30:34,  1.75s/it, loss=0.328, lr=0.0001]
Steps:  48%|████▊     | 954/2000 [28:48<30:34,  1.75s/it, loss=0.18, lr=0.0001] 
Steps:  48%|████▊     | 955/2000 [28:49<30:04,  1.73s/it, loss=0.18, lr=0.0001]
Steps:  48%|████▊     | 955/2000 [28:49<30:04,  1.73s/it, loss=0.167, lr=0.0001]
Steps:  48%|████▊     | 955/2000 [28:49<30:04,  1.73s/it, loss=0.443, lr=0.0001]
Steps:  48%|████▊     | 955/2000 [28:49<30:04,  1.73s/it, loss=0.278, lr=0.0001]
Steps:  48%|████▊     | 955/2000 [28:50<30:04,  1.73s/it, loss=0.17, lr=0.0001] 
Steps:  48%|████▊     | 956/2000 [28:50<30:56,  1.78s/it, loss=0.17, lr=0.0001]
Steps:  48%|████▊     | 956/2000 [28:50<30:56,  1.78s/it, loss=0.131, lr=0.0001]
Steps:  48%|████▊     | 956/2000 [28:51<30:56,  1.78s/it, loss=0.244, lr=0.0001]
Steps:  48%|████▊     | 956/2000 [28:51<30:56,  1.78s/it, loss=0.246, lr=0.0001]
Steps:  48%|████▊     | 956/2000 [28:52<30:56,  1.78s/it, loss=0.143, lr=0.0001]
Steps:  48%|████▊     | 957/2000 [28:52<30:16,  1.74s/it, loss=0.143, lr=0.0001]
Steps:  48%|████▊     | 957/2000 [28:52<30:16,  1.74s/it, loss=0.392, lr=0.0001]
Steps:  48%|████▊     | 957/2000 [28:52<30:16,  1.74s/it, loss=0.173, lr=0.0001]
Steps:  48%|████▊     | 957/2000 [28:53<30:16,  1.74s/it, loss=0.955, lr=0.0001]
Steps:  48%|████▊     | 957/2000 [28:53<30:16,  1.74s/it, loss=0.0987, lr=0.0001]
Steps:  48%|████▊     | 958/2000 [28:54<29:49,  1.72s/it, loss=0.0987, lr=0.0001]
Steps:  48%|████▊     | 958/2000 [28:54<29:49,  1.72s/it, loss=0.58, lr=0.0001]  
Steps:  48%|████▊     | 958/2000 [28:54<29:49,  1.72s/it, loss=0.119, lr=0.0001]
Steps:  48%|████▊     | 958/2000 [28:55<29:49,  1.72s/it, loss=0.247, lr=0.0001]
Steps:  48%|████▊     | 958/2000 [28:55<29:49,  1.72s/it, loss=0.129, lr=0.0001]
Steps:  48%|████▊     | 959/2000 [28:56<30:44,  1.77s/it, loss=0.129, lr=0.0001]
Steps:  48%|████▊     | 959/2000 [28:56<30:44,  1.77s/it, loss=0.222, lr=0.0001]
Steps:  48%|████▊     | 959/2000 [28:56<30:44,  1.77s/it, loss=0.171, lr=0.0001]
Steps:  48%|████▊     | 959/2000 [28:56<30:44,  1.77s/it, loss=0.104, lr=0.0001]
Steps:  48%|████▊     | 959/2000 [28:57<30:44,  1.77s/it, loss=0.111, lr=0.0001]
Steps:  48%|████▊     | 960/2000 [28:57<30:05,  1.74s/it, loss=0.111, lr=0.0001]
Steps:  48%|████▊     | 960/2000 [28:57<30:05,  1.74s/it, loss=0.154, lr=0.0001]
Steps:  48%|████▊     | 960/2000 [28:58<30:05,  1.74s/it, loss=0.18, lr=0.0001] 
Steps:  48%|████▊     | 960/2000 [28:58<30:05,  1.74s/it, loss=0.395, lr=0.0001]
Steps:  48%|████▊     | 960/2000 [28:59<30:05,  1.74s/it, loss=0.216, lr=0.0001]
Steps:  48%|████▊     | 961/2000 [28:59<29:54,  1.73s/it, loss=0.216, lr=0.0001]
Steps:  48%|████▊     | 961/2000 [28:59<29:54,  1.73s/it, loss=0.159, lr=0.0001]
Steps:  48%|████▊     | 961/2000 [28:59<29:54,  1.73s/it, loss=0.24, lr=0.0001] 
Steps:  48%|████▊     | 961/2000 [29:00<29:54,  1.73s/it, loss=0.27, lr=0.0001]
Steps:  48%|████▊     | 961/2000 [29:00<29:54,  1.73s/it, loss=0.197, lr=0.0001]
Steps:  48%|████▊     | 962/2000 [29:01<30:38,  1.77s/it, loss=0.197, lr=0.0001]
Steps:  48%|████▊     | 962/2000 [29:01<30:38,  1.77s/it, loss=0.215, lr=0.0001]
Steps:  48%|████▊     | 962/2000 [29:01<30:38,  1.77s/it, loss=0.0846, lr=0.0001]
Steps:  48%|████▊     | 962/2000 [29:02<30:38,  1.77s/it, loss=0.0333, lr=0.0001]
Steps:  48%|████▊     | 962/2000 [29:02<30:38,  1.77s/it, loss=0.208, lr=0.0001] 
Steps:  48%|████▊     | 963/2000 [29:03<30:37,  1.77s/it, loss=0.208, lr=0.0001]
Steps:  48%|████▊     | 963/2000 [29:03<30:37,  1.77s/it, loss=0.151, lr=0.0001]
Steps:  48%|████▊     | 963/2000 [29:03<30:37,  1.77s/it, loss=0.176, lr=0.0001]
Steps:  48%|████▊     | 963/2000 [29:03<30:37,  1.77s/it, loss=0.136, lr=0.0001]
Steps:  48%|████▊     | 963/2000 [29:04<30:37,  1.77s/it, loss=0.257, lr=0.0001]
Steps:  48%|████▊     | 964/2000 [29:04<29:58,  1.74s/it, loss=0.257, lr=0.0001]
Steps:  48%|████▊     | 964/2000 [29:04<29:58,  1.74s/it, loss=0.232, lr=0.0001]
Steps:  48%|████▊     | 964/2000 [29:05<29:58,  1.74s/it, loss=0.15, lr=0.0001] 
Steps:  48%|████▊     | 964/2000 [29:05<29:58,  1.74s/it, loss=0.12, lr=0.0001]
Steps:  48%|████▊     | 964/2000 [29:05<29:58,  1.74s/it, loss=0.17, lr=0.0001]
Steps:  48%|████▊     | 965/2000 [29:06<29:39,  1.72s/it, loss=0.17, lr=0.0001]
Steps:  48%|████▊     | 965/2000 [29:06<29:39,  1.72s/it, loss=0.0892, lr=0.0001]
Steps:  48%|████▊     | 965/2000 [29:07<29:39,  1.72s/it, loss=0.128, lr=0.0001] 
Steps:  48%|████▊     | 965/2000 [29:07<29:39,  1.72s/it, loss=0.126, lr=0.0001]
Steps:  48%|████▊     | 965/2000 [29:07<29:39,  1.72s/it, loss=0.77, lr=0.0001] 
Steps:  48%|████▊     | 966/2000 [29:08<30:37,  1.78s/it, loss=0.77, lr=0.0001]
Steps:  48%|████▊     | 966/2000 [29:08<30:37,  1.78s/it, loss=0.179, lr=0.0001]
Steps:  48%|████▊     | 966/2000 [29:08<30:37,  1.78s/it, loss=0.131, lr=0.0001]
Steps:  48%|████▊     | 966/2000 [29:09<30:37,  1.78s/it, loss=0.172, lr=0.0001]
Steps:  48%|████▊     | 966/2000 [29:09<30:37,  1.78s/it, loss=0.145, lr=0.0001]
Steps:  48%|████▊     | 967/2000 [29:10<29:58,  1.74s/it, loss=0.145, lr=0.0001]
Steps:  48%|████▊     | 967/2000 [29:10<29:58,  1.74s/it, loss=0.287, lr=0.0001]
Steps:  48%|████▊     | 967/2000 [29:10<29:58,  1.74s/it, loss=0.17, lr=0.0001] 
Steps:  48%|████▊     | 967/2000 [29:10<29:58,  1.74s/it, loss=0.137, lr=0.0001]
Steps:  48%|████▊     | 967/2000 [29:11<29:58,  1.74s/it, loss=0.21, lr=0.0001] 
Steps:  48%|████▊     | 968/2000 [29:11<29:37,  1.72s/it, loss=0.21, lr=0.0001]
Steps:  48%|████▊     | 968/2000 [29:11<29:37,  1.72s/it, loss=0.239, lr=0.0001]
Steps:  48%|████▊     | 968/2000 [29:12<29:37,  1.72s/it, loss=0.122, lr=0.0001]
Steps:  48%|████▊     | 968/2000 [29:12<29:37,  1.72s/it, loss=0.175, lr=0.0001]
Steps:  48%|████▊     | 968/2000 [29:13<29:37,  1.72s/it, loss=0.224, lr=0.0001]
Steps:  48%|████▊     | 969/2000 [29:13<30:36,  1.78s/it, loss=0.224, lr=0.0001]
Steps:  48%|████▊     | 969/2000 [29:13<30:36,  1.78s/it, loss=0.0954, lr=0.0001]
Steps:  48%|████▊     | 969/2000 [29:14<30:36,  1.78s/it, loss=0.0908, lr=0.0001]
Steps:  48%|████▊     | 969/2000 [29:14<30:36,  1.78s/it, loss=0.132, lr=0.0001] 
Steps:  48%|████▊     | 969/2000 [29:14<30:36,  1.78s/it, loss=0.187, lr=0.0001]
Steps:  48%|████▊     | 970/2000 [29:15<30:13,  1.76s/it, loss=0.187, lr=0.0001]
Steps:  48%|████▊     | 970/2000 [29:15<30:13,  1.76s/it, loss=0.173, lr=0.0001]
Steps:  48%|████▊     | 970/2000 [29:15<30:13,  1.76s/it, loss=0.113, lr=0.0001]
Steps:  48%|████▊     | 970/2000 [29:16<30:13,  1.76s/it, loss=0.868, lr=0.0001]
Steps:  48%|████▊     | 970/2000 [29:16<30:13,  1.76s/it, loss=0.123, lr=0.0001]
Steps:  49%|████▊     | 971/2000 [29:16<29:40,  1.73s/it, loss=0.123, lr=0.0001]
Steps:  49%|████▊     | 971/2000 [29:16<29:40,  1.73s/it, loss=0.143, lr=0.0001]
Steps:  49%|████▊     | 971/2000 [29:17<29:40,  1.73s/it, loss=0.178, lr=0.0001]
Steps:  49%|████▊     | 971/2000 [29:18<29:40,  1.73s/it, loss=0.0885, lr=0.0001]
Steps:  49%|████▊     | 971/2000 [29:18<29:40,  1.73s/it, loss=0.188, lr=0.0001] 
Steps:  49%|████▊     | 972/2000 [29:18<30:27,  1.78s/it, loss=0.188, lr=0.0001]
Steps:  49%|████▊     | 972/2000 [29:18<30:27,  1.78s/it, loss=0.209, lr=0.0001]
Steps:  49%|████▊     | 972/2000 [29:19<30:27,  1.78s/it, loss=0.186, lr=0.0001]
Steps:  49%|████▊     | 972/2000 [29:19<30:27,  1.78s/it, loss=0.158, lr=0.0001]
Steps:  49%|████▊     | 972/2000 [29:20<30:27,  1.78s/it, loss=0.576, lr=0.0001]
Steps:  49%|████▊     | 973/2000 [29:20<29:43,  1.74s/it, loss=0.576, lr=0.0001]
Steps:  49%|████▊     | 973/2000 [29:20<29:43,  1.74s/it, loss=0.136, lr=0.0001]
Steps:  49%|████▊     | 973/2000 [29:20<29:43,  1.74s/it, loss=0.0863, lr=0.0001]
Steps:  49%|████▊     | 973/2000 [29:21<29:43,  1.74s/it, loss=0.135, lr=0.0001] 
Steps:  49%|████▊     | 973/2000 [29:21<29:43,  1.74s/it, loss=0.178, lr=0.0001]
Steps:  49%|████▊     | 974/2000 [29:22<29:12,  1.71s/it, loss=0.178, lr=0.0001]
Steps:  49%|████▊     | 974/2000 [29:22<29:12,  1.71s/it, loss=0.135, lr=0.0001]
Steps:  49%|████▊     | 974/2000 [29:22<29:12,  1.71s/it, loss=0.0513, lr=0.0001]
Steps:  49%|████▊     | 974/2000 [29:22<29:12,  1.71s/it, loss=0.13, lr=0.0001]  
Steps:  49%|████▊     | 974/2000 [29:23<29:12,  1.71s/it, loss=0.166, lr=0.0001]
Steps:  49%|████▉     | 975/2000 [29:24<30:06,  1.76s/it, loss=0.166, lr=0.0001]
Steps:  49%|████▉     | 975/2000 [29:24<30:06,  1.76s/it, loss=0.196, lr=0.0001]
Steps:  49%|████▉     | 975/2000 [29:24<30:06,  1.76s/it, loss=0.308, lr=0.0001]
Steps:  49%|████▉     | 975/2000 [29:24<30:06,  1.76s/it, loss=0.134, lr=0.0001]
Steps:  49%|████▉     | 975/2000 [29:25<30:06,  1.76s/it, loss=0.0836, lr=0.0001]
Steps:  49%|████▉     | 976/2000 [29:25<29:44,  1.74s/it, loss=0.0836, lr=0.0001]
Steps:  49%|████▉     | 976/2000 [29:25<29:44,  1.74s/it, loss=0.169, lr=0.0001] 
Steps:  49%|████▉     | 976/2000 [29:26<29:44,  1.74s/it, loss=0.328, lr=0.0001]
Steps:  49%|████▉     | 976/2000 [29:26<29:44,  1.74s/it, loss=0.859, lr=0.0001]
Steps:  49%|████▉     | 976/2000 [29:26<29:44,  1.74s/it, loss=0.151, lr=0.0001]
Steps:  49%|████▉     | 977/2000 [29:27<29:31,  1.73s/it, loss=0.151, lr=0.0001]
Steps:  49%|████▉     | 977/2000 [29:27<29:31,  1.73s/it, loss=0.0789, lr=0.0001]
Steps:  49%|████▉     | 977/2000 [29:27<29:31,  1.73s/it, loss=0.0902, lr=0.0001]
Steps:  49%|████▉     | 977/2000 [29:28<29:31,  1.73s/it, loss=0.116, lr=0.0001] 
Steps:  49%|████▉     | 977/2000 [29:28<29:31,  1.73s/it, loss=0.137, lr=0.0001]
Steps:  49%|████▉     | 978/2000 [29:29<30:21,  1.78s/it, loss=0.137, lr=0.0001]
Steps:  49%|████▉     | 978/2000 [29:29<30:21,  1.78s/it, loss=0.435, lr=0.0001]
Steps:  49%|████▉     | 978/2000 [29:29<30:21,  1.78s/it, loss=0.549, lr=0.0001]
Steps:  49%|████▉     | 978/2000 [29:30<30:21,  1.78s/it, loss=0.277, lr=0.0001]
Steps:  49%|████▉     | 978/2000 [29:30<30:21,  1.78s/it, loss=0.348, lr=0.0001]
Steps:  49%|████▉     | 979/2000 [29:31<29:44,  1.75s/it, loss=0.348, lr=0.0001]
Steps:  49%|████▉     | 979/2000 [29:31<29:44,  1.75s/it, loss=0.11, lr=0.0001] 
Steps:  49%|████▉     | 979/2000 [29:31<29:44,  1.75s/it, loss=0.146, lr=0.0001]
Steps:  49%|████▉     | 979/2000 [29:31<29:44,  1.75s/it, loss=0.202, lr=0.0001]
Steps:  49%|████▉     | 979/2000 [29:32<29:44,  1.75s/it, loss=0.236, lr=0.0001]
Steps:  49%|████▉     | 980/2000 [29:32<29:17,  1.72s/it, loss=0.236, lr=0.0001]
Steps:  49%|████▉     | 980/2000 [29:32<29:17,  1.72s/it, loss=0.162, lr=0.0001]
Steps:  49%|████▉     | 980/2000 [29:33<29:17,  1.72s/it, loss=0.211, lr=0.0001]
Steps:  49%|████▉     | 980/2000 [29:33<29:17,  1.72s/it, loss=0.168, lr=0.0001]
Steps:  49%|████▉     | 980/2000 [29:33<29:17,  1.72s/it, loss=0.216, lr=0.0001]
Steps:  49%|████▉     | 981/2000 [29:34<30:11,  1.78s/it, loss=0.216, lr=0.0001]
Steps:  49%|████▉     | 981/2000 [29:34<30:11,  1.78s/it, loss=0.215, lr=0.0001]
Steps:  49%|████▉     | 981/2000 [29:35<30:11,  1.78s/it, loss=0.149, lr=0.0001]
Steps:  49%|████▉     | 981/2000 [29:35<30:11,  1.78s/it, loss=0.218, lr=0.0001]
Steps:  49%|████▉     | 981/2000 [29:35<30:11,  1.78s/it, loss=0.224, lr=0.0001]
Steps:  49%|████▉     | 982/2000 [29:36<29:35,  1.74s/it, loss=0.224, lr=0.0001]
Steps:  49%|████▉     | 982/2000 [29:36<29:35,  1.74s/it, loss=0.31, lr=0.0001] 
Steps:  49%|████▉     | 982/2000 [29:36<29:35,  1.74s/it, loss=0.114, lr=0.0001]
Steps:  49%|████▉     | 982/2000 [29:37<29:35,  1.74s/it, loss=0.0945, lr=0.0001]
Steps:  49%|████▉     | 982/2000 [29:37<29:35,  1.74s/it, loss=0.186, lr=0.0001] 
Steps:  49%|████▉     | 983/2000 [29:37<29:15,  1.73s/it, loss=0.186, lr=0.0001]
Steps:  49%|████▉     | 983/2000 [29:37<29:15,  1.73s/it, loss=0.178, lr=0.0001]
Steps:  49%|████▉     | 983/2000 [29:38<29:15,  1.73s/it, loss=0.261, lr=0.0001]
Steps:  49%|████▉     | 983/2000 [29:38<29:15,  1.73s/it, loss=0.185, lr=0.0001]
Steps:  49%|████▉     | 983/2000 [29:39<29:15,  1.73s/it, loss=0.151, lr=0.0001]
Steps:  49%|████▉     | 984/2000 [29:39<30:14,  1.79s/it, loss=0.151, lr=0.0001]
Steps:  49%|████▉     | 984/2000 [29:39<30:14,  1.79s/it, loss=0.198, lr=0.0001]
Steps:  49%|████▉     | 984/2000 [29:40<30:14,  1.79s/it, loss=0.239, lr=0.0001]
Steps:  49%|████▉     | 984/2000 [29:40<30:14,  1.79s/it, loss=0.224, lr=0.0001]
Steps:  49%|████▉     | 984/2000 [29:41<30:14,  1.79s/it, loss=0.266, lr=0.0001]
Steps:  49%|████▉     | 985/2000 [29:41<29:35,  1.75s/it, loss=0.266, lr=0.0001]
Steps:  49%|████▉     | 985/2000 [29:41<29:35,  1.75s/it, loss=0.0666, lr=0.0001]
Steps:  49%|████▉     | 985/2000 [29:41<29:35,  1.75s/it, loss=0.14, lr=0.0001]  
Steps:  49%|████▉     | 985/2000 [29:42<29:35,  1.75s/it, loss=0.0961, lr=0.0001]
Steps:  49%|████▉     | 985/2000 [29:42<29:35,  1.75s/it, loss=0.207, lr=0.0001] 
Steps:  49%|████▉     | 986/2000 [29:43<29:21,  1.74s/it, loss=0.207, lr=0.0001]
Steps:  49%|████▉     | 986/2000 [29:43<29:21,  1.74s/it, loss=0.181, lr=0.0001]
Steps:  49%|████▉     | 986/2000 [29:43<29:21,  1.74s/it, loss=0.143, lr=0.0001]
Steps:  49%|████▉     | 986/2000 [29:44<29:21,  1.74s/it, loss=0.21, lr=0.0001] 
Steps:  49%|████▉     | 986/2000 [29:44<29:21,  1.74s/it, loss=0.174, lr=0.0001]
Steps:  49%|████▉     | 987/2000 [29:44<28:57,  1.71s/it, loss=0.174, lr=0.0001]
Steps:  49%|████▉     | 987/2000 [29:44<28:57,  1.71s/it, loss=0.121, lr=0.0001]
Steps:  49%|████▉     | 987/2000 [29:45<28:57,  1.71s/it, loss=0.121, lr=0.0001]
Steps:  49%|████▉     | 987/2000 [29:45<28:57,  1.71s/it, loss=0.13, lr=0.0001] 
Steps:  49%|████▉     | 987/2000 [29:46<28:57,  1.71s/it, loss=0.0692, lr=0.0001]
Steps:  49%|████▉     | 988/2000 [29:46<30:00,  1.78s/it, loss=0.0692, lr=0.0001]
Steps:  49%|████▉     | 988/2000 [29:46<30:00,  1.78s/it, loss=0.32, lr=0.0001]  
Steps:  49%|████▉     | 988/2000 [29:47<30:00,  1.78s/it, loss=0.0922, lr=0.0001]
Steps:  49%|████▉     | 988/2000 [29:47<30:00,  1.78s/it, loss=0.138, lr=0.0001] 
Steps:  49%|████▉     | 988/2000 [29:48<30:00,  1.78s/it, loss=0.288, lr=0.0001]
Steps:  49%|████▉     | 989/2000 [29:48<29:26,  1.75s/it, loss=0.288, lr=0.0001]
Steps:  49%|████▉     | 989/2000 [29:48<29:26,  1.75s/it, loss=0.225, lr=0.0001]
Steps:  49%|████▉     | 989/2000 [29:48<29:26,  1.75s/it, loss=0.199, lr=0.0001]
Steps:  49%|████▉     | 989/2000 [29:49<29:26,  1.75s/it, loss=1.3, lr=0.0001]  
Steps:  49%|████▉     | 989/2000 [29:49<29:26,  1.75s/it, loss=0.138, lr=0.0001]
Steps:  50%|████▉     | 990/2000 [29:50<28:59,  1.72s/it, loss=0.138, lr=0.0001]
Steps:  50%|████▉     | 990/2000 [29:50<28:59,  1.72s/it, loss=0.126, lr=0.0001]
Steps:  50%|████▉     | 990/2000 [29:50<28:59,  1.72s/it, loss=0.154, lr=0.0001]
Steps:  50%|████▉     | 990/2000 [29:51<28:59,  1.72s/it, loss=0.075, lr=0.0001]
Steps:  50%|████▉     | 990/2000 [29:51<28:59,  1.72s/it, loss=0.181, lr=0.0001]
Steps:  50%|████▉     | 991/2000 [29:52<30:07,  1.79s/it, loss=0.181, lr=0.0001]
Steps:  50%|████▉     | 991/2000 [29:52<30:07,  1.79s/it, loss=0.204, lr=0.0001]
Steps:  50%|████▉     | 991/2000 [29:52<30:07,  1.79s/it, loss=0.263, lr=0.0001]
Steps:  50%|████▉     | 991/2000 [29:52<30:07,  1.79s/it, loss=0.211, lr=0.0001]
Steps:  50%|████▉     | 991/2000 [29:53<30:07,  1.79s/it, loss=0.557, lr=0.0001]
Steps:  50%|████▉     | 992/2000 [29:53<29:28,  1.75s/it, loss=0.557, lr=0.0001]
Steps:  50%|████▉     | 992/2000 [29:53<29:28,  1.75s/it, loss=0.162, lr=0.0001]
Steps:  50%|████▉     | 992/2000 [29:54<29:28,  1.75s/it, loss=0.219, lr=0.0001]
Steps:  50%|████▉     | 992/2000 [29:54<29:28,  1.75s/it, loss=0.22, lr=0.0001] 
Steps:  50%|████▉     | 992/2000 [29:55<29:28,  1.75s/it, loss=0.295, lr=0.0001]
Steps:  50%|████▉     | 993/2000 [29:55<29:11,  1.74s/it, loss=0.295, lr=0.0001]
Steps:  50%|████▉     | 993/2000 [29:55<29:11,  1.74s/it, loss=0.181, lr=0.0001]
Steps:  50%|████▉     | 993/2000 [29:55<29:11,  1.74s/it, loss=0.164, lr=0.0001]
Steps:  50%|████▉     | 993/2000 [29:56<29:11,  1.74s/it, loss=0.146, lr=0.0001]
Steps:  50%|████▉     | 993/2000 [29:56<29:11,  1.74s/it, loss=0.139, lr=0.0001]
Steps:  50%|████▉     | 994/2000 [29:57<29:59,  1.79s/it, loss=0.139, lr=0.0001]
Steps:  50%|████▉     | 994/2000 [29:57<29:59,  1.79s/it, loss=0.726, lr=0.0001]
Steps:  50%|████▉     | 994/2000 [29:57<29:59,  1.79s/it, loss=0.178, lr=0.0001]
Steps:  50%|████▉     | 994/2000 [29:58<29:59,  1.79s/it, loss=0.177, lr=0.0001]
Steps:  50%|████▉     | 994/2000 [29:58<29:59,  1.79s/it, loss=0.259, lr=0.0001]
Steps:  50%|████▉     | 995/2000 [29:59<29:31,  1.76s/it, loss=0.259, lr=0.0001]
Steps:  50%|████▉     | 995/2000 [29:59<29:31,  1.76s/it, loss=0.124, lr=0.0001]
Steps:  50%|████▉     | 995/2000 [29:59<29:31,  1.76s/it, loss=0.165, lr=0.0001]
Steps:  50%|████▉     | 995/2000 [29:59<29:31,  1.76s/it, loss=0.227, lr=0.0001]
Steps:  50%|████▉     | 995/2000 [30:00<29:31,  1.76s/it, loss=0.168, lr=0.0001]
Steps:  50%|████▉     | 996/2000 [30:00<28:54,  1.73s/it, loss=0.168, lr=0.0001]
Steps:  50%|████▉     | 996/2000 [30:00<28:54,  1.73s/it, loss=0.49, lr=0.0001] 
Steps:  50%|████▉     | 996/2000 [30:01<28:54,  1.73s/it, loss=0.231, lr=0.0001]
Steps:  50%|████▉     | 996/2000 [30:01<28:54,  1.73s/it, loss=0.116, lr=0.0001]
Steps:  50%|████▉     | 996/2000 [30:02<28:54,  1.73s/it, loss=0.113, lr=0.0001]
Steps:  50%|████▉     | 997/2000 [30:02<30:05,  1.80s/it, loss=0.113, lr=0.0001]
Steps:  50%|████▉     | 997/2000 [30:02<30:05,  1.80s/it, loss=0.141, lr=0.0001]
Steps:  50%|████▉     | 997/2000 [30:03<30:05,  1.80s/it, loss=0.149, lr=0.0001]
Steps:  50%|████▉     | 997/2000 [30:03<30:05,  1.80s/it, loss=0.265, lr=0.0001]
Steps:  50%|████▉     | 997/2000 [30:03<30:05,  1.80s/it, loss=0.42, lr=0.0001] 
Steps:  50%|████▉     | 998/2000 [30:04<29:22,  1.76s/it, loss=0.42, lr=0.0001]
Steps:  50%|████▉     | 998/2000 [30:04<29:22,  1.76s/it, loss=0.348, lr=0.0001]
Steps:  50%|████▉     | 998/2000 [30:04<29:22,  1.76s/it, loss=0.273, lr=0.0001]
Steps:  50%|████▉     | 998/2000 [30:05<29:22,  1.76s/it, loss=0.141, lr=0.0001]
Steps:  50%|████▉     | 998/2000 [30:05<29:22,  1.76s/it, loss=0.14, lr=0.0001] 
Steps:  50%|████▉     | 999/2000 [30:06<28:49,  1.73s/it, loss=0.14, lr=0.0001]
Steps:  50%|████▉     | 999/2000 [30:06<28:49,  1.73s/it, loss=0.166, lr=0.0001]
Steps:  50%|████▉     | 999/2000 [30:06<28:49,  1.73s/it, loss=0.187, lr=0.0001]
Steps:  50%|████▉     | 999/2000 [30:06<28:49,  1.73s/it, loss=0.25, lr=0.0001] 
Steps:  50%|████▉     | 999/2000 [30:07<28:49,  1.73s/it, loss=0.0862, lr=0.0001]
Steps:  50%|█████     | 1000/2000 [30:07<29:42,  1.78s/it, loss=0.0862, lr=0.0001]05/30/2026 09:02:32 - INFO - accelerate.accelerator - [RANK 0] Saving current state to /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1000
Model weights saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1000/pytorch_lora_weights.safetensors
05/30/2026 09:02:33 - INFO - accelerate.checkpointing - [RANK 0] Optimizer state saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1000/optimizer.bin
05/30/2026 09:02:33 - INFO - accelerate.checkpointing - [RANK 0] Scheduler state saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1000/scheduler.bin
05/30/2026 09:02:33 - INFO - accelerate.checkpointing - [RANK 0] Sampler state for dataloader 0 saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1000/sampler.bin
05/30/2026 09:02:33 - INFO - accelerate.checkpointing - [RANK 0] Random states saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1000/random_states_0.pkl
05/30/2026 09:02:33 - INFO - __main__ - [RANK 0] Saved state to /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1000

Steps:  50%|█████     | 1000/2000 [30:08<29:42,  1.78s/it, loss=0.363, lr=0.0001] 
Steps:  50%|█████     | 1000/2000 [30:09<29:42,  1.78s/it, loss=0.161, lr=0.0001]
Steps:  50%|█████     | 1000/2000 [30:09<29:42,  1.78s/it, loss=0.219, lr=0.0001]
Steps:  50%|█████     | 1000/2000 [30:09<29:42,  1.78s/it, loss=0.071, lr=0.0001]
Steps:  50%|█████     | 1001/2000 [30:10<32:58,  1.98s/it, loss=0.071, lr=0.0001]
Steps:  50%|█████     | 1001/2000 [30:10<32:58,  1.98s/it, loss=0.177, lr=0.0001]
Steps:  50%|█████     | 1001/2000 [30:10<32:58,  1.98s/it, loss=0.139, lr=0.0001]
Steps:  50%|█████     | 1001/2000 [30:11<32:58,  1.98s/it, loss=0.122, lr=0.0001]
Steps:  50%|█████     | 1001/2000 [30:11<32:58,  1.98s/it, loss=0.191, lr=0.0001]
Steps:  50%|█████     | 1002/2000 [30:12<31:25,  1.89s/it, loss=0.191, lr=0.0001]
Steps:  50%|█████     | 1002/2000 [30:12<31:25,  1.89s/it, loss=0.176, lr=0.0001]
Steps:  50%|█████     | 1002/2000 [30:12<31:25,  1.89s/it, loss=0.0922, lr=0.0001]
Steps:  50%|█████     | 1002/2000 [30:12<31:25,  1.89s/it, loss=0.0512, lr=0.0001]
Steps:  50%|█████     | 1002/2000 [30:13<31:25,  1.89s/it, loss=0.288, lr=0.0001] 
Steps:  50%|█████     | 1003/2000 [30:14<31:41,  1.91s/it, loss=0.288, lr=0.0001]
Steps:  50%|█████     | 1003/2000 [30:14<31:41,  1.91s/it, loss=0.634, lr=0.0001]
Steps:  50%|█████     | 1003/2000 [30:14<31:41,  1.91s/it, loss=0.174, lr=0.0001]
Steps:  50%|█████     | 1003/2000 [30:14<31:41,  1.91s/it, loss=0.223, lr=0.0001]
Steps:  50%|█████     | 1003/2000 [30:15<31:41,  1.91s/it, loss=0.183, lr=0.0001]
Steps:  50%|█████     | 1004/2000 [30:15<30:30,  1.84s/it, loss=0.183, lr=0.0001]
Steps:  50%|█████     | 1004/2000 [30:15<30:30,  1.84s/it, loss=0.192, lr=0.0001]
Steps:  50%|█████     | 1004/2000 [30:16<30:30,  1.84s/it, loss=0.316, lr=0.0001]
Steps:  50%|█████     | 1004/2000 [30:16<30:30,  1.84s/it, loss=0.0901, lr=0.0001]
Steps:  50%|█████     | 1004/2000 [30:16<30:30,  1.84s/it, loss=0.14, lr=0.0001]  
Steps:  50%|█████     | 1005/2000 [30:17<29:43,  1.79s/it, loss=0.14, lr=0.0001]
Steps:  50%|█████     | 1005/2000 [30:17<29:43,  1.79s/it, loss=0.183, lr=0.0001]
Steps:  50%|█████     | 1005/2000 [30:17<29:43,  1.79s/it, loss=0.269, lr=0.0001]
Steps:  50%|█████     | 1005/2000 [30:18<29:43,  1.79s/it, loss=0.295, lr=0.0001]
Steps:  50%|█████     | 1005/2000 [30:18<29:43,  1.79s/it, loss=0.147, lr=0.0001]
Steps:  50%|█████     | 1006/2000 [30:19<30:30,  1.84s/it, loss=0.147, lr=0.0001]
Steps:  50%|█████     | 1006/2000 [30:19<30:30,  1.84s/it, loss=0.273, lr=0.0001]
Steps:  50%|█████     | 1006/2000 [30:19<30:30,  1.84s/it, loss=0.09, lr=0.0001] 
Steps:  50%|█████     | 1006/2000 [30:20<30:30,  1.84s/it, loss=0.0917, lr=0.0001]
Steps:  50%|█████     | 1006/2000 [30:20<30:30,  1.84s/it, loss=0.191, lr=0.0001] 
Steps:  50%|█████     | 1007/2000 [30:21<30:01,  1.81s/it, loss=0.191, lr=0.0001]
Steps:  50%|█████     | 1007/2000 [30:21<30:01,  1.81s/it, loss=0.156, lr=0.0001]
Steps:  50%|█████     | 1007/2000 [30:21<30:01,  1.81s/it, loss=0.102, lr=0.0001]
Steps:  50%|█████     | 1007/2000 [30:21<30:01,  1.81s/it, loss=0.148, lr=0.0001]
Steps:  50%|█████     | 1007/2000 [30:22<30:01,  1.81s/it, loss=0.172, lr=0.0001]
Steps:  50%|█████     | 1008/2000 [30:22<29:20,  1.77s/it, loss=0.172, lr=0.0001]
Steps:  50%|█████     | 1008/2000 [30:22<29:20,  1.77s/it, loss=0.214, lr=0.0001]
Steps:  50%|█████     | 1008/2000 [30:23<29:20,  1.77s/it, loss=0.143, lr=0.0001]
Steps:  50%|█████     | 1008/2000 [30:23<29:20,  1.77s/it, loss=0.0681, lr=0.0001]
Steps:  50%|█████     | 1008/2000 [30:24<29:20,  1.77s/it, loss=0.289, lr=0.0001] 
Steps:  50%|█████     | 1009/2000 [30:24<30:06,  1.82s/it, loss=0.289, lr=0.0001]
Steps:  50%|█████     | 1009/2000 [30:24<30:06,  1.82s/it, loss=0.32, lr=0.0001] 
Steps:  50%|█████     | 1009/2000 [30:25<30:06,  1.82s/it, loss=0.0766, lr=0.0001]
Steps:  50%|█████     | 1009/2000 [30:25<30:06,  1.82s/it, loss=0.689, lr=0.0001] 
Steps:  50%|█████     | 1009/2000 [30:25<30:06,  1.82s/it, loss=0.167, lr=0.0001]
Steps:  50%|█████     | 1010/2000 [30:26<29:22,  1.78s/it, loss=0.167, lr=0.0001]
Steps:  50%|█████     | 1010/2000 [30:26<29:22,  1.78s/it, loss=0.27, lr=0.0001] 
Steps:  50%|█████     | 1010/2000 [30:26<29:22,  1.78s/it, loss=1.04, lr=0.0001]
Steps:  50%|█████     | 1010/2000 [30:27<29:22,  1.78s/it, loss=0.182, lr=0.0001]
Steps:  50%|█████     | 1010/2000 [30:27<29:22,  1.78s/it, loss=0.278, lr=0.0001]
Steps:  51%|█████     | 1011/2000 [30:28<28:48,  1.75s/it, loss=0.278, lr=0.0001]
Steps:  51%|█████     | 1011/2000 [30:28<28:48,  1.75s/it, loss=0.168, lr=0.0001]
Steps:  51%|█████     | 1011/2000 [30:28<28:48,  1.75s/it, loss=0.0999, lr=0.0001]
Steps:  51%|█████     | 1011/2000 [30:28<28:48,  1.75s/it, loss=0.112, lr=0.0001] 
Steps:  51%|█████     | 1011/2000 [30:29<28:48,  1.75s/it, loss=0.128, lr=0.0001]
Steps:  51%|█████     | 1012/2000 [30:29<28:27,  1.73s/it, loss=0.128, lr=0.0001]
Steps:  51%|█████     | 1012/2000 [30:29<28:27,  1.73s/it, loss=0.193, lr=0.0001]
Steps:  51%|█████     | 1012/2000 [30:30<28:27,  1.73s/it, loss=0.17, lr=0.0001] 
Steps:  51%|█████     | 1012/2000 [30:30<28:27,  1.73s/it, loss=0.146, lr=0.0001]
Steps:  51%|█████     | 1012/2000 [30:31<28:27,  1.73s/it, loss=0.199, lr=0.0001]
Steps:  51%|█████     | 1013/2000 [30:31<29:29,  1.79s/it, loss=0.199, lr=0.0001]
Steps:  51%|█████     | 1013/2000 [30:31<29:29,  1.79s/it, loss=0.288, lr=0.0001]
Steps:  51%|█████     | 1013/2000 [30:32<29:29,  1.79s/it, loss=0.412, lr=0.0001]
Steps:  51%|█████     | 1013/2000 [30:32<29:29,  1.79s/it, loss=0.226, lr=0.0001]
Steps:  51%|█████     | 1013/2000 [30:32<29:29,  1.79s/it, loss=0.139, lr=0.0001]
Steps:  51%|█████     | 1014/2000 [30:33<29:01,  1.77s/it, loss=0.139, lr=0.0001]
Steps:  51%|█████     | 1014/2000 [30:33<29:01,  1.77s/it, loss=0.139, lr=0.0001]
Steps:  51%|█████     | 1014/2000 [30:33<29:01,  1.77s/it, loss=0.178, lr=0.0001]
Steps:  51%|█████     | 1014/2000 [30:34<29:01,  1.77s/it, loss=0.0908, lr=0.0001]
Steps:  51%|█████     | 1014/2000 [30:34<29:01,  1.77s/it, loss=0.116, lr=0.0001] 
Steps:  51%|█████     | 1015/2000 [30:35<28:34,  1.74s/it, loss=0.116, lr=0.0001]
Steps:  51%|█████     | 1015/2000 [30:35<28:34,  1.74s/it, loss=0.21, lr=0.0001] 
Steps:  51%|█████     | 1015/2000 [30:35<28:34,  1.74s/it, loss=0.268, lr=0.0001]
Steps:  51%|█████     | 1015/2000 [30:36<28:34,  1.74s/it, loss=0.141, lr=0.0001]
Steps:  51%|█████     | 1015/2000 [30:36<28:34,  1.74s/it, loss=0.218, lr=0.0001]
Steps:  51%|█████     | 1016/2000 [30:37<29:51,  1.82s/it, loss=0.218, lr=0.0001]
Steps:  51%|█████     | 1016/2000 [30:37<29:51,  1.82s/it, loss=0.0915, lr=0.0001]
Steps:  51%|█████     | 1016/2000 [30:37<29:51,  1.82s/it, loss=0.101, lr=0.0001] 
Steps:  51%|█████     | 1016/2000 [30:37<29:51,  1.82s/it, loss=0.192, lr=0.0001]
Steps:  51%|█████     | 1016/2000 [30:38<29:51,  1.82s/it, loss=0.126, lr=0.0001]
Steps:  51%|█████     | 1017/2000 [30:38<29:04,  1.77s/it, loss=0.126, lr=0.0001]
Steps:  51%|█████     | 1017/2000 [30:38<29:04,  1.77s/it, loss=0.241, lr=0.0001]
Steps:  51%|█████     | 1017/2000 [30:39<29:04,  1.77s/it, loss=0.256, lr=0.0001]
Steps:  51%|█████     | 1017/2000 [30:39<29:04,  1.77s/it, loss=0.0531, lr=0.0001]
Steps:  51%|█████     | 1017/2000 [30:39<29:04,  1.77s/it, loss=0.493, lr=0.0001] 
Steps:  51%|█████     | 1018/2000 [30:40<28:34,  1.75s/it, loss=0.493, lr=0.0001]
Steps:  51%|█████     | 1018/2000 [30:40<28:34,  1.75s/it, loss=0.194, lr=0.0001]
Steps:  51%|█████     | 1018/2000 [30:40<28:34,  1.75s/it, loss=0.191, lr=0.0001]
Steps:  51%|█████     | 1018/2000 [30:41<28:34,  1.75s/it, loss=0.188, lr=0.0001]
Steps:  51%|█████     | 1018/2000 [30:41<28:34,  1.75s/it, loss=0.16, lr=0.0001] 
Steps:  51%|█████     | 1019/2000 [30:42<29:23,  1.80s/it, loss=0.16, lr=0.0001]
Steps:  51%|█████     | 1019/2000 [30:42<29:23,  1.80s/it, loss=0.162, lr=0.0001]
Steps:  51%|█████     | 1019/2000 [30:42<29:23,  1.80s/it, loss=0.201, lr=0.0001]
Steps:  51%|█████     | 1019/2000 [30:43<29:23,  1.80s/it, loss=0.141, lr=0.0001]
Steps:  51%|█████     | 1019/2000 [30:43<29:23,  1.80s/it, loss=0.137, lr=0.0001]
Steps:  51%|█████     | 1020/2000 [30:44<28:51,  1.77s/it, loss=0.137, lr=0.0001]
Steps:  51%|█████     | 1020/2000 [30:44<28:51,  1.77s/it, loss=0.157, lr=0.0001]
Steps:  51%|█████     | 1020/2000 [30:44<28:51,  1.77s/it, loss=1.06, lr=0.0001] 
Steps:  51%|█████     | 1020/2000 [30:44<28:51,  1.77s/it, loss=0.231, lr=0.0001]
Steps:  51%|█████     | 1020/2000 [30:45<28:51,  1.77s/it, loss=0.198, lr=0.0001]
Steps:  51%|█████     | 1021/2000 [30:45<28:21,  1.74s/it, loss=0.198, lr=0.0001]
Steps:  51%|█████     | 1021/2000 [30:45<28:21,  1.74s/it, loss=0.026, lr=0.0001]
Steps:  51%|█████     | 1021/2000 [30:46<28:21,  1.74s/it, loss=0.12, lr=0.0001] 
Steps:  51%|█████     | 1021/2000 [30:46<28:21,  1.74s/it, loss=0.172, lr=0.0001]
Steps:  51%|█████     | 1021/2000 [30:47<28:21,  1.74s/it, loss=0.213, lr=0.0001]
Steps:  51%|█████     | 1022/2000 [30:47<29:17,  1.80s/it, loss=0.213, lr=0.0001]
Steps:  51%|█████     | 1022/2000 [30:47<29:17,  1.80s/it, loss=0.133, lr=0.0001]
Steps:  51%|█████     | 1022/2000 [30:48<29:17,  1.80s/it, loss=0.157, lr=0.0001]
Steps:  51%|█████     | 1022/2000 [30:48<29:17,  1.80s/it, loss=0.165, lr=0.0001]
Steps:  51%|█████     | 1022/2000 [30:48<29:17,  1.80s/it, loss=0.192, lr=0.0001]
Steps:  51%|█████     | 1023/2000 [30:49<28:38,  1.76s/it, loss=0.192, lr=0.0001]
Steps:  51%|█████     | 1023/2000 [30:49<28:38,  1.76s/it, loss=0.298, lr=0.0001]
Steps:  51%|█████     | 1023/2000 [30:49<28:38,  1.76s/it, loss=0.214, lr=0.0001]
Steps:  51%|█████     | 1023/2000 [30:50<28:38,  1.76s/it, loss=0.157, lr=0.0001]
Steps:  51%|█████     | 1023/2000 [30:50<28:38,  1.76s/it, loss=0.174, lr=0.0001]
Steps:  51%|█████     | 1024/2000 [30:51<28:24,  1.75s/it, loss=0.174, lr=0.0001]
Steps:  51%|█████     | 1024/2000 [30:51<28:24,  1.75s/it, loss=0.163, lr=0.0001]
Steps:  51%|█████     | 1024/2000 [30:51<28:24,  1.75s/it, loss=0.0697, lr=0.0001]
Steps:  51%|█████     | 1024/2000 [30:51<28:24,  1.75s/it, loss=0.176, lr=0.0001] 
Steps:  51%|█████     | 1024/2000 [30:52<28:24,  1.75s/it, loss=0.211, lr=0.0001]
Steps:  51%|█████▏    | 1025/2000 [30:52<29:21,  1.81s/it, loss=0.211, lr=0.0001]
Steps:  51%|█████▏    | 1025/2000 [30:52<29:21,  1.81s/it, loss=0.268, lr=0.0001]
Steps:  51%|█████▏    | 1025/2000 [30:53<29:21,  1.81s/it, loss=0.186, lr=0.0001]
Steps:  51%|█████▏    | 1025/2000 [30:53<29:21,  1.81s/it, loss=0.105, lr=0.0001]
Steps:  51%|█████▏    | 1025/2000 [30:54<29:21,  1.81s/it, loss=0.214, lr=0.0001]
Steps:  51%|█████▏    | 1026/2000 [30:54<29:00,  1.79s/it, loss=0.214, lr=0.0001]
Steps:  51%|█████▏    | 1026/2000 [30:54<29:00,  1.79s/it, loss=0.289, lr=0.0001]
Steps:  51%|█████▏    | 1026/2000 [30:55<29:00,  1.79s/it, loss=0.222, lr=0.0001]
Steps:  51%|█████▏    | 1026/2000 [30:55<29:00,  1.79s/it, loss=0.772, lr=0.0001]
Steps:  51%|█████▏    | 1026/2000 [30:55<29:00,  1.79s/it, loss=0.148, lr=0.0001]
Steps:  51%|█████▏    | 1027/2000 [30:56<28:37,  1.77s/it, loss=0.148, lr=0.0001]
Steps:  51%|█████▏    | 1027/2000 [30:56<28:37,  1.77s/it, loss=0.129, lr=0.0001]
Steps:  51%|█████▏    | 1027/2000 [30:56<28:37,  1.77s/it, loss=0.274, lr=0.0001]
Steps:  51%|█████▏    | 1027/2000 [30:57<28:37,  1.77s/it, loss=0.571, lr=0.0001]
Steps:  51%|█████▏    | 1027/2000 [30:57<28:37,  1.77s/it, loss=0.178, lr=0.0001]
Steps:  51%|█████▏    | 1028/2000 [30:58<29:21,  1.81s/it, loss=0.178, lr=0.0001]
Steps:  51%|█████▏    | 1028/2000 [30:58<29:21,  1.81s/it, loss=0.183, lr=0.0001]
Steps:  51%|█████▏    | 1028/2000 [30:58<29:21,  1.81s/it, loss=0.249, lr=0.0001]
Steps:  51%|█████▏    | 1028/2000 [30:59<29:21,  1.81s/it, loss=0.314, lr=0.0001]
Steps:  51%|█████▏    | 1028/2000 [30:59<29:21,  1.81s/it, loss=0.196, lr=0.0001]
Steps:  51%|█████▏    | 1029/2000 [31:00<28:48,  1.78s/it, loss=0.196, lr=0.0001]
Steps:  51%|█████▏    | 1029/2000 [31:00<28:48,  1.78s/it, loss=0.156, lr=0.0001]
Steps:  51%|█████▏    | 1029/2000 [31:00<28:48,  1.78s/it, loss=1.04, lr=0.0001] 
Steps:  51%|█████▏    | 1029/2000 [31:00<28:48,  1.78s/it, loss=0.106, lr=0.0001]
Steps:  51%|█████▏    | 1029/2000 [31:01<28:48,  1.78s/it, loss=0.3, lr=0.0001]  
Steps:  52%|█████▏    | 1030/2000 [31:01<28:26,  1.76s/it, loss=0.3, lr=0.0001]
Steps:  52%|█████▏    | 1030/2000 [31:01<28:26,  1.76s/it, loss=0.11, lr=0.0001]
Steps:  52%|█████▏    | 1030/2000 [31:02<28:26,  1.76s/it, loss=0.097, lr=0.0001]
Steps:  52%|█████▏    | 1030/2000 [31:02<28:26,  1.76s/it, loss=0.131, lr=0.0001]
Steps:  52%|█████▏    | 1030/2000 [31:03<28:26,  1.76s/it, loss=0.418, lr=0.0001]
Steps:  52%|█████▏    | 1031/2000 [31:03<28:00,  1.73s/it, loss=0.418, lr=0.0001]
Steps:  52%|█████▏    | 1031/2000 [31:03<28:00,  1.73s/it, loss=0.119, lr=0.0001]
Steps:  52%|█████▏    | 1031/2000 [31:04<28:00,  1.73s/it, loss=0.732, lr=0.0001]
Steps:  52%|█████▏    | 1031/2000 [31:04<28:00,  1.73s/it, loss=0.128, lr=0.0001]
Steps:  52%|█████▏    | 1031/2000 [31:04<28:00,  1.73s/it, loss=0.219, lr=0.0001]
Steps:  52%|█████▏    | 1032/2000 [31:05<28:48,  1.79s/it, loss=0.219, lr=0.0001]
Steps:  52%|█████▏    | 1032/2000 [31:05<28:48,  1.79s/it, loss=0.107, lr=0.0001]
Steps:  52%|█████▏    | 1032/2000 [31:05<28:48,  1.79s/it, loss=0.397, lr=0.0001]
Steps:  52%|█████▏    | 1032/2000 [31:06<28:48,  1.79s/it, loss=0.464, lr=0.0001]
Steps:  52%|█████▏    | 1032/2000 [31:06<28:48,  1.79s/it, loss=1.15, lr=0.0001] 
Steps:  52%|█████▏    | 1033/2000 [31:07<28:19,  1.76s/it, loss=1.15, lr=0.0001]
Steps:  52%|█████▏    | 1033/2000 [31:07<28:19,  1.76s/it, loss=0.092, lr=0.0001]
Steps:  52%|█████▏    | 1033/2000 [31:07<28:19,  1.76s/it, loss=0.104, lr=0.0001]
Steps:  52%|█████▏    | 1033/2000 [31:07<28:19,  1.76s/it, loss=0.475, lr=0.0001]
Steps:  52%|█████▏    | 1033/2000 [31:08<28:19,  1.76s/it, loss=0.265, lr=0.0001]
Steps:  52%|█████▏    | 1034/2000 [31:08<27:58,  1.74s/it, loss=0.265, lr=0.0001]
Steps:  52%|█████▏    | 1034/2000 [31:08<27:58,  1.74s/it, loss=1.04, lr=0.0001] 
Steps:  52%|█████▏    | 1034/2000 [31:09<27:58,  1.74s/it, loss=0.188, lr=0.0001]
Steps:  52%|█████▏    | 1034/2000 [31:09<27:58,  1.74s/it, loss=0.131, lr=0.0001]
Steps:  52%|█████▏    | 1034/2000 [31:10<27:58,  1.74s/it, loss=0.224, lr=0.0001]
Steps:  52%|█████▏    | 1035/2000 [31:10<28:42,  1.79s/it, loss=0.224, lr=0.0001]
Steps:  52%|█████▏    | 1035/2000 [31:10<28:42,  1.79s/it, loss=0.174, lr=0.0001]
Steps:  52%|█████▏    | 1035/2000 [31:11<28:42,  1.79s/it, loss=0.297, lr=0.0001]
Steps:  52%|█████▏    | 1035/2000 [31:11<28:42,  1.79s/it, loss=0.155, lr=0.0001]
Steps:  52%|█████▏    | 1035/2000 [31:11<28:42,  1.79s/it, loss=0.062, lr=0.0001]
Steps:  52%|█████▏    | 1036/2000 [31:12<28:12,  1.76s/it, loss=0.062, lr=0.0001]
Steps:  52%|█████▏    | 1036/2000 [31:12<28:12,  1.76s/it, loss=0.0955, lr=0.0001]
Steps:  52%|█████▏    | 1036/2000 [31:12<28:12,  1.76s/it, loss=0.171, lr=0.0001] 
Steps:  52%|█████▏    | 1036/2000 [31:13<28:12,  1.76s/it, loss=0.113, lr=0.0001]
Steps:  52%|█████▏    | 1036/2000 [31:13<28:12,  1.76s/it, loss=0.232, lr=0.0001]
Steps:  52%|█████▏    | 1037/2000 [31:14<27:57,  1.74s/it, loss=0.232, lr=0.0001]
Steps:  52%|█████▏    | 1037/2000 [31:14<27:57,  1.74s/it, loss=0.0701, lr=0.0001]
Steps:  52%|█████▏    | 1037/2000 [31:14<27:57,  1.74s/it, loss=0.432, lr=0.0001] 
Steps:  52%|█████▏    | 1037/2000 [31:15<27:57,  1.74s/it, loss=0.134, lr=0.0001]
Steps:  52%|█████▏    | 1037/2000 [31:15<27:57,  1.74s/it, loss=0.169, lr=0.0001]
Steps:  52%|█████▏    | 1038/2000 [31:16<29:09,  1.82s/it, loss=0.169, lr=0.0001]
Steps:  52%|█████▏    | 1038/2000 [31:16<29:09,  1.82s/it, loss=0.168, lr=0.0001]
Steps:  52%|█████▏    | 1038/2000 [31:16<29:09,  1.82s/it, loss=0.242, lr=0.0001]
Steps:  52%|█████▏    | 1038/2000 [31:16<29:09,  1.82s/it, loss=0.141, lr=0.0001]
Steps:  52%|█████▏    | 1038/2000 [31:17<29:09,  1.82s/it, loss=0.15, lr=0.0001] 
Steps:  52%|█████▏    | 1039/2000 [31:17<28:23,  1.77s/it, loss=0.15, lr=0.0001]
Steps:  52%|█████▏    | 1039/2000 [31:17<28:23,  1.77s/it, loss=0.226, lr=0.0001]
Steps:  52%|█████▏    | 1039/2000 [31:18<28:23,  1.77s/it, loss=0.125, lr=0.0001]
Steps:  52%|█████▏    | 1039/2000 [31:18<28:23,  1.77s/it, loss=0.113, lr=0.0001]
Steps:  52%|█████▏    | 1039/2000 [31:18<28:23,  1.77s/it, loss=0.135, lr=0.0001]
Steps:  52%|█████▏    | 1040/2000 [31:19<27:47,  1.74s/it, loss=0.135, lr=0.0001]
Steps:  52%|█████▏    | 1040/2000 [31:19<27:47,  1.74s/it, loss=0.221, lr=0.0001]
Steps:  52%|█████▏    | 1040/2000 [31:19<27:47,  1.74s/it, loss=0.0649, lr=0.0001]
Steps:  52%|█████▏    | 1040/2000 [31:20<27:47,  1.74s/it, loss=0.166, lr=0.0001] 
Steps:  52%|█████▏    | 1040/2000 [31:20<27:47,  1.74s/it, loss=0.283, lr=0.0001]
Steps:  52%|█████▏    | 1041/2000 [31:21<28:25,  1.78s/it, loss=0.283, lr=0.0001]
Steps:  52%|█████▏    | 1041/2000 [31:21<28:25,  1.78s/it, loss=0.125, lr=0.0001]
Steps:  52%|█████▏    | 1041/2000 [31:21<28:25,  1.78s/it, loss=0.14, lr=0.0001] 
Steps:  52%|█████▏    | 1041/2000 [31:22<28:25,  1.78s/it, loss=0.233, lr=0.0001]
Steps:  52%|█████▏    | 1041/2000 [31:22<28:25,  1.78s/it, loss=0.138, lr=0.0001]
Steps:  52%|█████▏    | 1042/2000 [31:23<32:29,  2.03s/it, loss=0.138, lr=0.0001]
Steps:  52%|█████▏    | 1042/2000 [31:23<32:29,  2.03s/it, loss=0.273, lr=0.0001]
Steps:  52%|█████▏    | 1042/2000 [31:24<32:29,  2.03s/it, loss=0.137, lr=0.0001]
Steps:  52%|█████▏    | 1042/2000 [31:24<32:29,  2.03s/it, loss=0.149, lr=0.0001]
Steps:  52%|█████▏    | 1042/2000 [31:25<32:29,  2.03s/it, loss=0.158, lr=0.0001]
Steps:  52%|█████▏    | 1043/2000 [31:25<30:58,  1.94s/it, loss=0.158, lr=0.0001]
Steps:  52%|█████▏    | 1043/2000 [31:25<30:58,  1.94s/it, loss=0.0663, lr=0.0001]
Steps:  52%|█████▏    | 1043/2000 [31:25<30:58,  1.94s/it, loss=0.223, lr=0.0001] 
Steps:  52%|█████▏    | 1043/2000 [31:26<30:58,  1.94s/it, loss=0.126, lr=0.0001]
Steps:  52%|█████▏    | 1043/2000 [31:27<30:58,  1.94s/it, loss=0.296, lr=0.0001]
Steps:  52%|█████▏    | 1044/2000 [31:27<30:46,  1.93s/it, loss=0.296, lr=0.0001]
Steps:  52%|█████▏    | 1044/2000 [31:27<30:46,  1.93s/it, loss=0.343, lr=0.0001]
Steps:  52%|█████▏    | 1044/2000 [31:27<30:46,  1.93s/it, loss=0.195, lr=0.0001]
Steps:  52%|█████▏    | 1044/2000 [31:28<30:46,  1.93s/it, loss=0.222, lr=0.0001]
Steps:  52%|█████▏    | 1044/2000 [31:28<30:46,  1.93s/it, loss=0.417, lr=0.0001]
Steps:  52%|█████▏    | 1045/2000 [31:29<29:27,  1.85s/it, loss=0.417, lr=0.0001]
Steps:  52%|█████▏    | 1045/2000 [31:29<29:27,  1.85s/it, loss=0.24, lr=0.0001] 
Steps:  52%|█████▏    | 1045/2000 [31:29<29:27,  1.85s/it, loss=0.263, lr=0.0001]
Steps:  52%|█████▏    | 1045/2000 [31:29<29:27,  1.85s/it, loss=0.128, lr=0.0001]
Steps:  52%|█████▏    | 1045/2000 [31:30<29:27,  1.85s/it, loss=0.191, lr=0.0001]
Steps:  52%|█████▏    | 1046/2000 [31:30<28:32,  1.80s/it, loss=0.191, lr=0.0001]
Steps:  52%|█████▏    | 1046/2000 [31:30<28:32,  1.80s/it, loss=0.263, lr=0.0001]
Steps:  52%|█████▏    | 1046/2000 [31:31<28:32,  1.80s/it, loss=0.121, lr=0.0001]
Steps:  52%|█████▏    | 1046/2000 [31:31<28:32,  1.80s/it, loss=0.219, lr=0.0001]
Steps:  52%|█████▏    | 1046/2000 [31:32<28:32,  1.80s/it, loss=0.14, lr=0.0001] 
Steps:  52%|█████▏    | 1047/2000 [31:32<29:08,  1.83s/it, loss=0.14, lr=0.0001]
Steps:  52%|█████▏    | 1047/2000 [31:32<29:08,  1.83s/it, loss=0.121, lr=0.0001]
Steps:  52%|█████▏    | 1047/2000 [31:33<29:08,  1.83s/it, loss=0.12, lr=0.0001] 
Steps:  52%|█████▏    | 1047/2000 [31:33<29:08,  1.83s/it, loss=0.16, lr=0.0001]
Steps:  52%|█████▏    | 1047/2000 [31:33<29:08,  1.83s/it, loss=0.374, lr=0.0001]
Steps:  52%|█████▏    | 1048/2000 [31:34<28:13,  1.78s/it, loss=0.374, lr=0.0001]
Steps:  52%|█████▏    | 1048/2000 [31:34<28:13,  1.78s/it, loss=0.184, lr=0.0001]
Steps:  52%|█████▏    | 1048/2000 [31:34<28:13,  1.78s/it, loss=0.231, lr=0.0001]
Steps:  52%|█████▏    | 1048/2000 [31:35<28:13,  1.78s/it, loss=0.149, lr=0.0001]
Steps:  52%|█████▏    | 1048/2000 [31:35<28:13,  1.78s/it, loss=0.113, lr=0.0001]
Steps:  52%|█████▏    | 1049/2000 [31:36<27:38,  1.74s/it, loss=0.113, lr=0.0001]
Steps:  52%|█████▏    | 1049/2000 [31:36<27:38,  1.74s/it, loss=0.126, lr=0.0001]
Steps:  52%|█████▏    | 1049/2000 [31:36<27:38,  1.74s/it, loss=0.0676, lr=0.0001]
Steps:  52%|█████▏    | 1049/2000 [31:36<27:38,  1.74s/it, loss=0.237, lr=0.0001] 
Steps:  52%|█████▏    | 1049/2000 [31:37<27:38,  1.74s/it, loss=0.189, lr=0.0001]
Steps:  52%|█████▎    | 1050/2000 [31:37<28:29,  1.80s/it, loss=0.189, lr=0.0001]
Steps:  52%|█████▎    | 1050/2000 [31:37<28:29,  1.80s/it, loss=0.376, lr=0.0001]
Steps:  52%|█████▎    | 1050/2000 [31:38<28:29,  1.80s/it, loss=0.335, lr=0.0001]
Steps:  52%|█████▎    | 1050/2000 [31:38<28:29,  1.80s/it, loss=0.208, lr=0.0001]
Steps:  52%|█████▎    | 1050/2000 [31:39<28:29,  1.80s/it, loss=0.15, lr=0.0001] 
Steps:  53%|█████▎    | 1051/2000 [31:39<27:46,  1.76s/it, loss=0.15, lr=0.0001]
Steps:  53%|█████▎    | 1051/2000 [31:39<27:46,  1.76s/it, loss=0.122, lr=0.0001]
Steps:  53%|█████▎    | 1051/2000 [31:40<27:46,  1.76s/it, loss=0.0884, lr=0.0001]
Steps:  53%|█████▎    | 1051/2000 [31:40<27:46,  1.76s/it, loss=0.0784, lr=0.0001]
Steps:  53%|█████▎    | 1051/2000 [31:40<27:46,  1.76s/it, loss=0.202, lr=0.0001] 
Steps:  53%|█████▎    | 1052/2000 [31:41<27:17,  1.73s/it, loss=0.202, lr=0.0001]
Steps:  53%|█████▎    | 1052/2000 [31:41<27:17,  1.73s/it, loss=1.07, lr=0.0001] 
Steps:  53%|█████▎    | 1052/2000 [31:41<27:17,  1.73s/it, loss=0.246, lr=0.0001]
Steps:  53%|█████▎    | 1052/2000 [31:42<27:17,  1.73s/it, loss=0.497, lr=0.0001]
Steps:  53%|█████▎    | 1052/2000 [31:42<27:17,  1.73s/it, loss=0.159, lr=0.0001]
Steps:  53%|█████▎    | 1053/2000 [31:42<26:47,  1.70s/it, loss=0.159, lr=0.0001]
Steps:  53%|█████▎    | 1053/2000 [31:42<26:47,  1.70s/it, loss=0.204, lr=0.0001]
Steps:  53%|█████▎    | 1053/2000 [31:43<26:47,  1.70s/it, loss=0.246, lr=0.0001]
Steps:  53%|█████▎    | 1053/2000 [31:43<26:47,  1.70s/it, loss=0.207, lr=0.0001]
Steps:  53%|█████▎    | 1053/2000 [31:44<26:47,  1.70s/it, loss=0.151, lr=0.0001]
Steps:  53%|█████▎    | 1054/2000 [31:44<27:36,  1.75s/it, loss=0.151, lr=0.0001]
Steps:  53%|█████▎    | 1054/2000 [31:44<27:36,  1.75s/it, loss=0.198, lr=0.0001]
Steps:  53%|█████▎    | 1054/2000 [31:45<27:36,  1.75s/it, loss=0.301, lr=0.0001]
Steps:  53%|█████▎    | 1054/2000 [31:45<27:36,  1.75s/it, loss=0.233, lr=0.0001]
Steps:  53%|█████▎    | 1054/2000 [31:46<27:36,  1.75s/it, loss=0.241, lr=0.0001]
Steps:  53%|█████▎    | 1055/2000 [31:46<27:10,  1.73s/it, loss=0.241, lr=0.0001]
Steps:  53%|█████▎    | 1055/2000 [31:46<27:10,  1.73s/it, loss=0.184, lr=0.0001]
Steps:  53%|█████▎    | 1055/2000 [31:46<27:10,  1.73s/it, loss=0.219, lr=0.0001]
Steps:  53%|█████▎    | 1055/2000 [31:47<27:10,  1.73s/it, loss=0.155, lr=0.0001]
Steps:  53%|█████▎    | 1055/2000 [31:47<27:10,  1.73s/it, loss=0.227, lr=0.0001]
Steps:  53%|█████▎    | 1056/2000 [31:48<26:48,  1.70s/it, loss=0.227, lr=0.0001]
Steps:  53%|█████▎    | 1056/2000 [31:48<26:48,  1.70s/it, loss=0.188, lr=0.0001]
Steps:  53%|█████▎    | 1056/2000 [31:48<26:48,  1.70s/it, loss=0.154, lr=0.0001]
Steps:  53%|█████▎    | 1056/2000 [31:49<26:48,  1.70s/it, loss=0.214, lr=0.0001]
Steps:  53%|█████▎    | 1056/2000 [31:49<26:48,  1.70s/it, loss=0.203, lr=0.0001]
Steps:  53%|█████▎    | 1057/2000 [31:50<28:01,  1.78s/it, loss=0.203, lr=0.0001]
Steps:  53%|█████▎    | 1057/2000 [31:50<28:01,  1.78s/it, loss=0.143, lr=0.0001]
Steps:  53%|█████▎    | 1057/2000 [31:50<28:01,  1.78s/it, loss=0.583, lr=0.0001]
Steps:  53%|█████▎    | 1057/2000 [31:50<28:01,  1.78s/it, loss=0.198, lr=0.0001]
Steps:  53%|█████▎    | 1057/2000 [31:51<28:01,  1.78s/it, loss=0.242, lr=0.0001]
Steps:  53%|█████▎    | 1058/2000 [31:51<27:23,  1.74s/it, loss=0.242, lr=0.0001]
Steps:  53%|█████▎    | 1058/2000 [31:51<27:23,  1.74s/it, loss=0.193, lr=0.0001]
Steps:  53%|█████▎    | 1058/2000 [31:52<27:23,  1.74s/it, loss=0.0818, lr=0.0001]
Steps:  53%|█████▎    | 1058/2000 [31:52<27:23,  1.74s/it, loss=0.227, lr=0.0001] 
Steps:  53%|█████▎    | 1058/2000 [31:52<27:23,  1.74s/it, loss=0.214, lr=0.0001]
Steps:  53%|█████▎    | 1059/2000 [31:53<27:02,  1.72s/it, loss=0.214, lr=0.0001]
Steps:  53%|█████▎    | 1059/2000 [31:53<27:02,  1.72s/it, loss=0.117, lr=0.0001]
Steps:  53%|█████▎    | 1059/2000 [31:53<27:02,  1.72s/it, loss=0.209, lr=0.0001]
Steps:  53%|█████▎    | 1059/2000 [31:54<27:02,  1.72s/it, loss=0.149, lr=0.0001]
Steps:  53%|█████▎    | 1059/2000 [31:54<27:02,  1.72s/it, loss=0.298, lr=0.0001]
Steps:  53%|█████▎    | 1060/2000 [31:55<28:09,  1.80s/it, loss=0.298, lr=0.0001]
Steps:  53%|█████▎    | 1060/2000 [31:55<28:09,  1.80s/it, loss=0.522, lr=0.0001]
Steps:  53%|█████▎    | 1060/2000 [31:55<28:09,  1.80s/it, loss=0.241, lr=0.0001]
Steps:  53%|█████▎    | 1060/2000 [31:56<28:09,  1.80s/it, loss=0.214, lr=0.0001]
Steps:  53%|█████▎    | 1060/2000 [31:56<28:09,  1.80s/it, loss=0.15, lr=0.0001] 
Steps:  53%|█████▎    | 1061/2000 [31:57<27:36,  1.76s/it, loss=0.15, lr=0.0001]
Steps:  53%|█████▎    | 1061/2000 [31:57<27:36,  1.76s/it, loss=0.182, lr=0.0001]
Steps:  53%|█████▎    | 1061/2000 [31:57<27:36,  1.76s/it, loss=0.158, lr=0.0001]
Steps:  53%|█████▎    | 1061/2000 [31:57<27:36,  1.76s/it, loss=0.49, lr=0.0001] 
Steps:  53%|█████▎    | 1061/2000 [31:58<27:36,  1.76s/it, loss=0.0669, lr=0.0001]
Steps:  53%|█████▎    | 1062/2000 [31:58<27:15,  1.74s/it, loss=0.0669, lr=0.0001]
Steps:  53%|█████▎    | 1062/2000 [31:58<27:15,  1.74s/it, loss=0.144, lr=0.0001] 
Steps:  53%|█████▎    | 1062/2000 [31:59<27:15,  1.74s/it, loss=0.291, lr=0.0001]
Steps:  53%|█████▎    | 1062/2000 [31:59<27:15,  1.74s/it, loss=0.16, lr=0.0001] 
Steps:  53%|█████▎    | 1062/2000 [32:00<27:15,  1.74s/it, loss=0.152, lr=0.0001]
Steps:  53%|█████▎    | 1063/2000 [32:00<28:09,  1.80s/it, loss=0.152, lr=0.0001]
Steps:  53%|█████▎    | 1063/2000 [32:00<28:09,  1.80s/it, loss=0.143, lr=0.0001]
Steps:  53%|█████▎    | 1063/2000 [32:01<28:09,  1.80s/it, loss=0.292, lr=0.0001]
Steps:  53%|█████▎    | 1063/2000 [32:01<28:09,  1.80s/it, loss=0.135, lr=0.0001]
Steps:  53%|█████▎    | 1063/2000 [32:01<28:09,  1.80s/it, loss=0.24, lr=0.0001] 
Steps:  53%|█████▎    | 1064/2000 [32:02<27:33,  1.77s/it, loss=0.24, lr=0.0001]
Steps:  53%|█████▎    | 1064/2000 [32:02<27:33,  1.77s/it, loss=0.174, lr=0.0001]
Steps:  53%|█████▎    | 1064/2000 [32:02<27:33,  1.77s/it, loss=0.072, lr=0.0001]
Steps:  53%|█████▎    | 1064/2000 [32:03<27:33,  1.77s/it, loss=0.161, lr=0.0001]
Steps:  53%|█████▎    | 1064/2000 [32:03<27:33,  1.77s/it, loss=0.172, lr=0.0001]
Steps:  53%|█████▎    | 1065/2000 [32:04<27:20,  1.75s/it, loss=0.172, lr=0.0001]
Steps:  53%|█████▎    | 1065/2000 [32:04<27:20,  1.75s/it, loss=0.0686, lr=0.0001]
Steps:  53%|█████▎    | 1065/2000 [32:04<27:20,  1.75s/it, loss=0.173, lr=0.0001] 
Steps:  53%|█████▎    | 1065/2000 [32:04<27:20,  1.75s/it, loss=0.333, lr=0.0001]
Steps:  53%|█████▎    | 1065/2000 [32:05<27:20,  1.75s/it, loss=0.17, lr=0.0001] 
Steps:  53%|█████▎    | 1066/2000 [32:06<28:29,  1.83s/it, loss=0.17, lr=0.0001]
Steps:  53%|█████▎    | 1066/2000 [32:06<28:29,  1.83s/it, loss=0.0756, lr=0.0001]
Steps:  53%|█████▎    | 1066/2000 [32:06<28:29,  1.83s/it, loss=0.333, lr=0.0001] 
Steps:  53%|█████▎    | 1066/2000 [32:06<28:29,  1.83s/it, loss=0.193, lr=0.0001]
Steps:  53%|█████▎    | 1066/2000 [32:07<28:29,  1.83s/it, loss=0.0896, lr=0.0001]
Steps:  53%|█████▎    | 1067/2000 [32:07<27:45,  1.78s/it, loss=0.0896, lr=0.0001]
Steps:  53%|█████▎    | 1067/2000 [32:07<27:45,  1.78s/it, loss=0.184, lr=0.0001] 
Steps:  53%|█████▎    | 1067/2000 [32:08<27:45,  1.78s/it, loss=0.589, lr=0.0001]
Steps:  53%|█████▎    | 1067/2000 [32:08<27:45,  1.78s/it, loss=0.234, lr=0.0001]
Steps:  53%|█████▎    | 1067/2000 [32:09<27:45,  1.78s/it, loss=0.308, lr=0.0001]
Steps:  53%|█████▎    | 1068/2000 [32:09<27:42,  1.78s/it, loss=0.308, lr=0.0001]
Steps:  53%|█████▎    | 1068/2000 [32:09<27:42,  1.78s/it, loss=0.14, lr=0.0001] 
Steps:  53%|█████▎    | 1068/2000 [32:09<27:42,  1.78s/it, loss=0.24, lr=0.0001]
Steps:  53%|█████▎    | 1068/2000 [32:10<27:42,  1.78s/it, loss=0.179, lr=0.0001]
Steps:  53%|█████▎    | 1068/2000 [32:11<27:42,  1.78s/it, loss=0.368, lr=0.0001]
Steps:  53%|█████▎    | 1069/2000 [32:11<28:17,  1.82s/it, loss=0.368, lr=0.0001]
Steps:  53%|█████▎    | 1069/2000 [32:11<28:17,  1.82s/it, loss=0.139, lr=0.0001]
Steps:  53%|█████▎    | 1069/2000 [32:11<28:17,  1.82s/it, loss=0.0873, lr=0.0001]
Steps:  53%|█████▎    | 1069/2000 [32:12<28:17,  1.82s/it, loss=0.259, lr=0.0001] 
Steps:  53%|█████▎    | 1069/2000 [32:12<28:17,  1.82s/it, loss=0.101, lr=0.0001]
Steps:  54%|█████▎    | 1070/2000 [32:13<27:29,  1.77s/it, loss=0.101, lr=0.0001]
Steps:  54%|█████▎    | 1070/2000 [32:13<27:29,  1.77s/it, loss=0.2, lr=0.0001]  
Steps:  54%|█████▎    | 1070/2000 [32:13<27:29,  1.77s/it, loss=0.169, lr=0.0001]
Steps:  54%|█████▎    | 1070/2000 [32:13<27:29,  1.77s/it, loss=0.219, lr=0.0001]
Steps:  54%|█████▎    | 1070/2000 [32:14<27:29,  1.77s/it, loss=0.625, lr=0.0001]
Steps:  54%|█████▎    | 1071/2000 [32:14<27:00,  1.74s/it, loss=0.625, lr=0.0001]
Steps:  54%|█████▎    | 1071/2000 [32:14<27:00,  1.74s/it, loss=0.151, lr=0.0001]
Steps:  54%|█████▎    | 1071/2000 [32:15<27:00,  1.74s/it, loss=0.314, lr=0.0001]
Steps:  54%|█████▎    | 1071/2000 [32:15<27:00,  1.74s/it, loss=0.159, lr=0.0001]
Steps:  54%|█████▎    | 1071/2000 [32:16<27:00,  1.74s/it, loss=0.107, lr=0.0001]
Steps:  54%|█████▎    | 1072/2000 [32:16<27:55,  1.81s/it, loss=0.107, lr=0.0001]
Steps:  54%|█████▎    | 1072/2000 [32:16<27:55,  1.81s/it, loss=0.136, lr=0.0001]
Steps:  54%|█████▎    | 1072/2000 [32:17<27:55,  1.81s/it, loss=0.299, lr=0.0001]
Steps:  54%|█████▎    | 1072/2000 [32:17<27:55,  1.81s/it, loss=0.18, lr=0.0001] 
Steps:  54%|█████▎    | 1072/2000 [32:17<27:55,  1.81s/it, loss=0.177, lr=0.0001]
Steps:  54%|█████▎    | 1073/2000 [32:18<27:15,  1.76s/it, loss=0.177, lr=0.0001]
Steps:  54%|█████▎    | 1073/2000 [32:18<27:15,  1.76s/it, loss=0.205, lr=0.0001]
Steps:  54%|█████▎    | 1073/2000 [32:18<27:15,  1.76s/it, loss=0.145, lr=0.0001]
Steps:  54%|█████▎    | 1073/2000 [32:19<27:15,  1.76s/it, loss=0.397, lr=0.0001]
Steps:  54%|█████▎    | 1073/2000 [32:19<27:15,  1.76s/it, loss=0.728, lr=0.0001]
Steps:  54%|█████▎    | 1074/2000 [32:20<26:50,  1.74s/it, loss=0.728, lr=0.0001]
Steps:  54%|█████▎    | 1074/2000 [32:20<26:50,  1.74s/it, loss=0.19, lr=0.0001] 
Steps:  54%|█████▎    | 1074/2000 [32:20<26:50,  1.74s/it, loss=0.625, lr=0.0001]
Steps:  54%|█████▎    | 1074/2000 [32:21<26:50,  1.74s/it, loss=0.123, lr=0.0001]
Steps:  54%|█████▎    | 1074/2000 [32:21<26:50,  1.74s/it, loss=0.161, lr=0.0001]
Steps:  54%|█████▍    | 1075/2000 [32:21<27:06,  1.76s/it, loss=0.161, lr=0.0001]
Steps:  54%|█████▍    | 1075/2000 [32:21<27:06,  1.76s/it, loss=0.319, lr=0.0001]
Steps:  54%|█████▍    | 1075/2000 [32:22<27:06,  1.76s/it, loss=0.147, lr=0.0001]
Steps:  54%|█████▍    | 1075/2000 [32:22<27:06,  1.76s/it, loss=0.157, lr=0.0001]
Steps:  54%|█████▍    | 1075/2000 [32:23<27:06,  1.76s/it, loss=0.176, lr=0.0001]
Steps:  54%|█████▍    | 1076/2000 [32:23<27:43,  1.80s/it, loss=0.176, lr=0.0001]
Steps:  54%|█████▍    | 1076/2000 [32:23<27:43,  1.80s/it, loss=0.194, lr=0.0001]
Steps:  54%|█████▍    | 1076/2000 [32:24<27:43,  1.80s/it, loss=0.279, lr=0.0001]
Steps:  54%|█████▍    | 1076/2000 [32:24<27:43,  1.80s/it, loss=0.0754, lr=0.0001]
Steps:  54%|█████▍    | 1076/2000 [32:25<27:43,  1.80s/it, loss=0.0909, lr=0.0001]
Steps:  54%|█████▍    | 1077/2000 [32:25<26:58,  1.75s/it, loss=0.0909, lr=0.0001]
Steps:  54%|█████▍    | 1077/2000 [32:25<26:58,  1.75s/it, loss=0.162, lr=0.0001] 
Steps:  54%|█████▍    | 1077/2000 [32:25<26:58,  1.75s/it, loss=0.203, lr=0.0001]
Steps:  54%|█████▍    | 1077/2000 [32:26<26:58,  1.75s/it, loss=0.164, lr=0.0001]
Steps:  54%|█████▍    | 1077/2000 [32:26<26:58,  1.75s/it, loss=0.206, lr=0.0001]
Steps:  54%|█████▍    | 1078/2000 [32:27<26:25,  1.72s/it, loss=0.206, lr=0.0001]
Steps:  54%|█████▍    | 1078/2000 [32:27<26:25,  1.72s/it, loss=0.15, lr=0.0001] 
Steps:  54%|█████▍    | 1078/2000 [32:27<26:25,  1.72s/it, loss=0.426, lr=0.0001]
Steps:  54%|█████▍    | 1078/2000 [32:28<26:25,  1.72s/it, loss=0.123, lr=0.0001]
Steps:  54%|█████▍    | 1078/2000 [32:28<26:25,  1.72s/it, loss=0.175, lr=0.0001]
Steps:  54%|█████▍    | 1079/2000 [32:28<27:05,  1.76s/it, loss=0.175, lr=0.0001]
Steps:  54%|█████▍    | 1079/2000 [32:28<27:05,  1.76s/it, loss=0.137, lr=0.0001]
Steps:  54%|█████▍    | 1079/2000 [32:29<27:05,  1.76s/it, loss=0.12, lr=0.0001] 
Steps:  54%|█████▍    | 1079/2000 [32:29<27:05,  1.76s/it, loss=0.126, lr=0.0001]
Steps:  54%|█████▍    | 1079/2000 [32:30<27:05,  1.76s/it, loss=0.368, lr=0.0001]
Steps:  54%|█████▍    | 1080/2000 [32:30<26:31,  1.73s/it, loss=0.368, lr=0.0001]
Steps:  54%|█████▍    | 1080/2000 [32:30<26:31,  1.73s/it, loss=0.161, lr=0.0001]
Steps:  54%|█████▍    | 1080/2000 [32:31<26:31,  1.73s/it, loss=0.368, lr=0.0001]
Steps:  54%|█████▍    | 1080/2000 [32:31<26:31,  1.73s/it, loss=0.174, lr=0.0001]
Steps:  54%|█████▍    | 1080/2000 [32:31<26:31,  1.73s/it, loss=0.231, lr=0.0001]
Steps:  54%|█████▍    | 1081/2000 [32:32<26:07,  1.71s/it, loss=0.231, lr=0.0001]
Steps:  54%|█████▍    | 1081/2000 [32:32<26:07,  1.71s/it, loss=0.169, lr=0.0001]
Steps:  54%|█████▍    | 1081/2000 [32:32<26:07,  1.71s/it, loss=0.215, lr=0.0001]
Steps:  54%|█████▍    | 1081/2000 [32:33<26:07,  1.71s/it, loss=0.222, lr=0.0001]
Steps:  54%|█████▍    | 1081/2000 [32:33<26:07,  1.71s/it, loss=0.145, lr=0.0001]
Steps:  54%|█████▍    | 1082/2000 [32:34<26:52,  1.76s/it, loss=0.145, lr=0.0001]
Steps:  54%|█████▍    | 1082/2000 [32:34<26:52,  1.76s/it, loss=0.253, lr=0.0001]
Steps:  54%|█████▍    | 1082/2000 [32:34<26:52,  1.76s/it, loss=0.142, lr=0.0001]
Steps:  54%|█████▍    | 1082/2000 [32:34<26:52,  1.76s/it, loss=0.146, lr=0.0001]
Steps:  54%|█████▍    | 1082/2000 [32:35<26:52,  1.76s/it, loss=0.108, lr=0.0001]
Steps:  54%|█████▍    | 1083/2000 [32:35<26:18,  1.72s/it, loss=0.108, lr=0.0001]
Steps:  54%|█████▍    | 1083/2000 [32:35<26:18,  1.72s/it, loss=0.165, lr=0.0001]
Steps:  54%|█████▍    | 1083/2000 [32:36<26:18,  1.72s/it, loss=0.0844, lr=0.0001]
Steps:  54%|█████▍    | 1083/2000 [32:36<26:18,  1.72s/it, loss=0.172, lr=0.0001] 
Steps:  54%|█████▍    | 1083/2000 [32:37<26:18,  1.72s/it, loss=0.146, lr=0.0001]
Steps:  54%|█████▍    | 1084/2000 [32:37<25:55,  1.70s/it, loss=0.146, lr=0.0001]
Steps:  54%|█████▍    | 1084/2000 [32:37<25:55,  1.70s/it, loss=0.124, lr=0.0001]
Steps:  54%|█████▍    | 1084/2000 [32:37<25:55,  1.70s/it, loss=0.232, lr=0.0001]
Steps:  54%|█████▍    | 1084/2000 [32:38<25:55,  1.70s/it, loss=0.438, lr=0.0001]
Steps:  54%|█████▍    | 1084/2000 [32:38<25:55,  1.70s/it, loss=0.164, lr=0.0001]
Steps:  54%|█████▍    | 1085/2000 [32:39<26:45,  1.75s/it, loss=0.164, lr=0.0001]
Steps:  54%|█████▍    | 1085/2000 [32:39<26:45,  1.75s/it, loss=0.214, lr=0.0001]
Steps:  54%|█████▍    | 1085/2000 [32:39<26:45,  1.75s/it, loss=0.141, lr=0.0001]
Steps:  54%|█████▍    | 1085/2000 [32:40<26:45,  1.75s/it, loss=0.231, lr=0.0001]
Steps:  54%|█████▍    | 1085/2000 [32:40<26:45,  1.75s/it, loss=0.258, lr=0.0001]
Steps:  54%|█████▍    | 1086/2000 [32:40<26:14,  1.72s/it, loss=0.258, lr=0.0001]
Steps:  54%|█████▍    | 1086/2000 [32:40<26:14,  1.72s/it, loss=0.193, lr=0.0001]
Steps:  54%|█████▍    | 1086/2000 [32:41<26:14,  1.72s/it, loss=0.113, lr=0.0001]
Steps:  54%|█████▍    | 1086/2000 [32:41<26:14,  1.72s/it, loss=0.17, lr=0.0001] 
Steps:  54%|█████▍    | 1086/2000 [32:42<26:14,  1.72s/it, loss=0.122, lr=0.0001]
Steps:  54%|█████▍    | 1087/2000 [32:42<26:02,  1.71s/it, loss=0.122, lr=0.0001]
Steps:  54%|█████▍    | 1087/2000 [32:42<26:02,  1.71s/it, loss=0.126, lr=0.0001]
Steps:  54%|█████▍    | 1087/2000 [32:43<26:02,  1.71s/it, loss=0.123, lr=0.0001]
Steps:  54%|█████▍    | 1087/2000 [32:43<26:02,  1.71s/it, loss=0.185, lr=0.0001]
Steps:  54%|█████▍    | 1087/2000 [32:44<26:02,  1.71s/it, loss=0.23, lr=0.0001] 
Steps:  54%|█████▍    | 1088/2000 [32:44<27:07,  1.78s/it, loss=0.23, lr=0.0001]
Steps:  54%|█████▍    | 1088/2000 [32:44<27:07,  1.78s/it, loss=0.135, lr=0.0001]
Steps:  54%|█████▍    | 1088/2000 [32:45<27:07,  1.78s/it, loss=0.161, lr=0.0001]
Steps:  54%|█████▍    | 1088/2000 [32:45<27:07,  1.78s/it, loss=0.0524, lr=0.0001]
Steps:  54%|█████▍    | 1088/2000 [32:45<27:07,  1.78s/it, loss=0.231, lr=0.0001] 
Steps:  54%|█████▍    | 1089/2000 [32:46<26:36,  1.75s/it, loss=0.231, lr=0.0001]
Steps:  54%|█████▍    | 1089/2000 [32:46<26:36,  1.75s/it, loss=0.707, lr=0.0001]
Steps:  54%|█████▍    | 1089/2000 [32:46<26:36,  1.75s/it, loss=0.823, lr=0.0001]
Steps:  54%|█████▍    | 1089/2000 [32:47<26:36,  1.75s/it, loss=0.0818, lr=0.0001]
Steps:  54%|█████▍    | 1089/2000 [32:47<26:36,  1.75s/it, loss=0.152, lr=0.0001] 
Steps:  55%|█████▍    | 1090/2000 [32:47<26:12,  1.73s/it, loss=0.152, lr=0.0001]
Steps:  55%|█████▍    | 1090/2000 [32:47<26:12,  1.73s/it, loss=0.126, lr=0.0001]
Steps:  55%|█████▍    | 1090/2000 [32:48<26:12,  1.73s/it, loss=0.275, lr=0.0001]
Steps:  55%|█████▍    | 1090/2000 [32:48<26:12,  1.73s/it, loss=0.188, lr=0.0001]
Steps:  55%|█████▍    | 1090/2000 [32:49<26:12,  1.73s/it, loss=0.175, lr=0.0001]
Steps:  55%|█████▍    | 1091/2000 [32:49<26:55,  1.78s/it, loss=0.175, lr=0.0001]
Steps:  55%|█████▍    | 1091/2000 [32:49<26:55,  1.78s/it, loss=1.01, lr=0.0001] 
Steps:  55%|█████▍    | 1091/2000 [32:50<26:55,  1.78s/it, loss=0.193, lr=0.0001]
Steps:  55%|█████▍    | 1091/2000 [32:50<26:55,  1.78s/it, loss=0.181, lr=0.0001]
Steps:  55%|█████▍    | 1091/2000 [32:51<26:55,  1.78s/it, loss=0.589, lr=0.0001]
Steps:  55%|█████▍    | 1092/2000 [32:51<26:43,  1.77s/it, loss=0.589, lr=0.0001]
Steps:  55%|█████▍    | 1092/2000 [32:51<26:43,  1.77s/it, loss=0.0621, lr=0.0001]
Steps:  55%|█████▍    | 1092/2000 [32:51<26:43,  1.77s/it, loss=0.238, lr=0.0001] 
Steps:  55%|█████▍    | 1092/2000 [32:52<26:43,  1.77s/it, loss=0.278, lr=0.0001]
Steps:  55%|█████▍    | 1092/2000 [32:52<26:43,  1.77s/it, loss=0.187, lr=0.0001]
Steps:  55%|█████▍    | 1093/2000 [32:53<26:08,  1.73s/it, loss=0.187, lr=0.0001]
Steps:  55%|█████▍    | 1093/2000 [32:53<26:08,  1.73s/it, loss=0.296, lr=0.0001]
Steps:  55%|█████▍    | 1093/2000 [32:53<26:08,  1.73s/it, loss=0.159, lr=0.0001]
Steps:  55%|█████▍    | 1093/2000 [32:54<26:08,  1.73s/it, loss=0.19, lr=0.0001] 
Steps:  55%|█████▍    | 1093/2000 [32:54<26:08,  1.73s/it, loss=0.17, lr=0.0001]
Steps:  55%|█████▍    | 1094/2000 [32:55<26:49,  1.78s/it, loss=0.17, lr=0.0001]
Steps:  55%|█████▍    | 1094/2000 [32:55<26:49,  1.78s/it, loss=0.26, lr=0.0001]
Steps:  55%|█████▍    | 1094/2000 [32:55<26:49,  1.78s/it, loss=0.122, lr=0.0001]
Steps:  55%|█████▍    | 1094/2000 [32:55<26:49,  1.78s/it, loss=0.125, lr=0.0001]
Steps:  55%|█████▍    | 1094/2000 [32:56<26:49,  1.78s/it, loss=0.296, lr=0.0001]
Steps:  55%|█████▍    | 1095/2000 [32:56<26:10,  1.73s/it, loss=0.296, lr=0.0001]
Steps:  55%|█████▍    | 1095/2000 [32:56<26:10,  1.73s/it, loss=0.181, lr=0.0001]
Steps:  55%|█████▍    | 1095/2000 [32:57<26:10,  1.73s/it, loss=0.201, lr=0.0001]
Steps:  55%|█████▍    | 1095/2000 [32:57<26:10,  1.73s/it, loss=0.233, lr=0.0001]
Steps:  55%|█████▍    | 1095/2000 [32:58<26:10,  1.73s/it, loss=0.0766, lr=0.0001]
Steps:  55%|█████▍    | 1096/2000 [32:58<25:56,  1.72s/it, loss=0.0766, lr=0.0001]
Steps:  55%|█████▍    | 1096/2000 [32:58<25:56,  1.72s/it, loss=0.168, lr=0.0001] 
Steps:  55%|█████▍    | 1096/2000 [32:58<25:56,  1.72s/it, loss=0.598, lr=0.0001]
Steps:  55%|█████▍    | 1096/2000 [32:59<25:56,  1.72s/it, loss=0.185, lr=0.0001]
Steps:  55%|█████▍    | 1096/2000 [32:59<25:56,  1.72s/it, loss=0.0517, lr=0.0001]
Steps:  55%|█████▍    | 1097/2000 [33:00<25:34,  1.70s/it, loss=0.0517, lr=0.0001]
Steps:  55%|█████▍    | 1097/2000 [33:00<25:34,  1.70s/it, loss=0.344, lr=0.0001] 
Steps:  55%|█████▍    | 1097/2000 [33:00<25:34,  1.70s/it, loss=0.256, lr=0.0001]
Steps:  55%|█████▍    | 1097/2000 [33:01<25:34,  1.70s/it, loss=0.177, lr=0.0001]
Steps:  55%|█████▍    | 1097/2000 [33:01<25:34,  1.70s/it, loss=0.145, lr=0.0001]
Steps:  55%|█████▍    | 1098/2000 [33:01<26:19,  1.75s/it, loss=0.145, lr=0.0001]
Steps:  55%|█████▍    | 1098/2000 [33:01<26:19,  1.75s/it, loss=0.183, lr=0.0001]
Steps:  55%|█████▍    | 1098/2000 [33:02<26:19,  1.75s/it, loss=0.437, lr=0.0001]
Steps:  55%|█████▍    | 1098/2000 [33:02<26:19,  1.75s/it, loss=0.127, lr=0.0001]
Steps:  55%|█████▍    | 1098/2000 [33:03<26:19,  1.75s/it, loss=0.151, lr=0.0001]
Steps:  55%|█████▍    | 1099/2000 [33:03<25:49,  1.72s/it, loss=0.151, lr=0.0001]
Steps:  55%|█████▍    | 1099/2000 [33:03<25:49,  1.72s/it, loss=0.191, lr=0.0001]
Steps:  55%|█████▍    | 1099/2000 [33:04<25:49,  1.72s/it, loss=0.158, lr=0.0001]
Steps:  55%|█████▍    | 1099/2000 [33:04<25:49,  1.72s/it, loss=0.213, lr=0.0001]
Steps:  55%|█████▍    | 1099/2000 [33:04<25:49,  1.72s/it, loss=0.114, lr=0.0001]
Steps:  55%|█████▌    | 1100/2000 [33:05<25:23,  1.69s/it, loss=0.114, lr=0.0001]
Steps:  55%|█████▌    | 1100/2000 [33:05<25:23,  1.69s/it, loss=0.181, lr=0.0001]
Steps:  55%|█████▌    | 1100/2000 [33:05<25:23,  1.69s/it, loss=0.42, lr=0.0001] 
Steps:  55%|█████▌    | 1100/2000 [33:06<25:23,  1.69s/it, loss=0.0837, lr=0.0001]
Steps:  55%|█████▌    | 1100/2000 [33:06<25:23,  1.69s/it, loss=0.174, lr=0.0001] 
Steps:  55%|█████▌    | 1101/2000 [33:07<26:09,  1.75s/it, loss=0.174, lr=0.0001]
Steps:  55%|█████▌    | 1101/2000 [33:07<26:09,  1.75s/it, loss=0.232, lr=0.0001]
Steps:  55%|█████▌    | 1101/2000 [33:07<26:09,  1.75s/it, loss=0.206, lr=0.0001]
Steps:  55%|█████▌    | 1101/2000 [33:07<26:09,  1.75s/it, loss=0.238, lr=0.0001]
Steps:  55%|█████▌    | 1101/2000 [33:08<26:09,  1.75s/it, loss=0.229, lr=0.0001]
Steps:  55%|█████▌    | 1102/2000 [33:08<25:55,  1.73s/it, loss=0.229, lr=0.0001]
Steps:  55%|█████▌    | 1102/2000 [33:08<25:55,  1.73s/it, loss=0.25, lr=0.0001] 
Steps:  55%|█████▌    | 1102/2000 [33:09<25:55,  1.73s/it, loss=0.144, lr=0.0001]
Steps:  55%|█████▌    | 1102/2000 [33:09<25:55,  1.73s/it, loss=0.208, lr=0.0001]
Steps:  55%|█████▌    | 1102/2000 [33:10<25:55,  1.73s/it, loss=0.244, lr=0.0001]
Steps:  55%|█████▌    | 1103/2000 [33:10<25:37,  1.71s/it, loss=0.244, lr=0.0001]
Steps:  55%|█████▌    | 1103/2000 [33:10<25:37,  1.71s/it, loss=0.194, lr=0.0001]
Steps:  55%|█████▌    | 1103/2000 [33:10<25:37,  1.71s/it, loss=0.13, lr=0.0001] 
Steps:  55%|█████▌    | 1103/2000 [33:11<25:37,  1.71s/it, loss=0.239, lr=0.0001]
Steps:  55%|█████▌    | 1103/2000 [33:11<25:37,  1.71s/it, loss=0.0221, lr=0.0001]
Steps:  55%|█████▌    | 1104/2000 [33:12<26:26,  1.77s/it, loss=0.0221, lr=0.0001]
Steps:  55%|█████▌    | 1104/2000 [33:12<26:26,  1.77s/it, loss=0.222, lr=0.0001] 
Steps:  55%|█████▌    | 1104/2000 [33:12<26:26,  1.77s/it, loss=0.143, lr=0.0001]
Steps:  55%|█████▌    | 1104/2000 [33:13<26:26,  1.77s/it, loss=0.287, lr=0.0001]
Steps:  55%|█████▌    | 1104/2000 [33:13<26:26,  1.77s/it, loss=0.164, lr=0.0001]
Steps:  55%|█████▌    | 1105/2000 [33:14<25:58,  1.74s/it, loss=0.164, lr=0.0001]
Steps:  55%|█████▌    | 1105/2000 [33:14<25:58,  1.74s/it, loss=0.213, lr=0.0001]
Steps:  55%|█████▌    | 1105/2000 [33:14<25:58,  1.74s/it, loss=0.0816, lr=0.0001]
Steps:  55%|█████▌    | 1105/2000 [33:14<25:58,  1.74s/it, loss=0.196, lr=0.0001] 
Steps:  55%|█████▌    | 1105/2000 [33:15<25:58,  1.74s/it, loss=0.109, lr=0.0001]
Steps:  55%|█████▌    | 1106/2000 [33:15<25:28,  1.71s/it, loss=0.109, lr=0.0001]
Steps:  55%|█████▌    | 1106/2000 [33:15<25:28,  1.71s/it, loss=0.155, lr=0.0001]
Steps:  55%|█████▌    | 1106/2000 [33:16<25:28,  1.71s/it, loss=0.232, lr=0.0001]
Steps:  55%|█████▌    | 1106/2000 [33:16<25:28,  1.71s/it, loss=0.157, lr=0.0001]
Steps:  55%|█████▌    | 1106/2000 [33:17<25:28,  1.71s/it, loss=0.136, lr=0.0001]
Steps:  55%|█████▌    | 1107/2000 [33:17<26:08,  1.76s/it, loss=0.136, lr=0.0001]
Steps:  55%|█████▌    | 1107/2000 [33:17<26:08,  1.76s/it, loss=0.182, lr=0.0001]
Steps:  55%|█████▌    | 1107/2000 [33:17<26:08,  1.76s/it, loss=0.211, lr=0.0001]
Steps:  55%|█████▌    | 1107/2000 [33:18<26:08,  1.76s/it, loss=0.157, lr=0.0001]
Steps:  55%|█████▌    | 1107/2000 [33:18<26:08,  1.76s/it, loss=0.216, lr=0.0001]
Steps:  55%|█████▌    | 1108/2000 [33:19<25:33,  1.72s/it, loss=0.216, lr=0.0001]
Steps:  55%|█████▌    | 1108/2000 [33:19<25:33,  1.72s/it, loss=0.347, lr=0.0001]
Steps:  55%|█████▌    | 1108/2000 [33:19<25:33,  1.72s/it, loss=0.468, lr=0.0001]
Steps:  55%|█████▌    | 1108/2000 [33:19<25:33,  1.72s/it, loss=0.111, lr=0.0001]
Steps:  55%|█████▌    | 1108/2000 [33:20<25:33,  1.72s/it, loss=0.182, lr=0.0001]
Steps:  55%|█████▌    | 1109/2000 [33:20<25:07,  1.69s/it, loss=0.182, lr=0.0001]
Steps:  55%|█████▌    | 1109/2000 [33:20<25:07,  1.69s/it, loss=0.307, lr=0.0001]
Steps:  55%|█████▌    | 1109/2000 [33:21<25:07,  1.69s/it, loss=0.145, lr=0.0001]
Steps:  55%|█████▌    | 1109/2000 [33:21<25:07,  1.69s/it, loss=0.807, lr=0.0001]
Steps:  55%|█████▌    | 1109/2000 [33:22<25:07,  1.69s/it, loss=0.114, lr=0.0001]
Steps:  56%|█████▌    | 1110/2000 [33:22<25:52,  1.74s/it, loss=0.114, lr=0.0001]
Steps:  56%|█████▌    | 1110/2000 [33:22<25:52,  1.74s/it, loss=0.65, lr=0.0001] 
Steps:  56%|█████▌    | 1110/2000 [33:23<25:52,  1.74s/it, loss=0.143, lr=0.0001]
Steps:  56%|█████▌    | 1110/2000 [33:23<25:52,  1.74s/it, loss=0.101, lr=0.0001]
Steps:  56%|█████▌    | 1110/2000 [33:23<25:52,  1.74s/it, loss=0.161, lr=0.0001]
Steps:  56%|█████▌    | 1111/2000 [33:24<25:29,  1.72s/it, loss=0.161, lr=0.0001]
Steps:  56%|█████▌    | 1111/2000 [33:24<25:29,  1.72s/it, loss=0.231, lr=0.0001]
Steps:  56%|█████▌    | 1111/2000 [33:24<25:29,  1.72s/it, loss=0.134, lr=0.0001]
Steps:  56%|█████▌    | 1111/2000 [33:25<25:29,  1.72s/it, loss=0.146, lr=0.0001]
Steps:  56%|█████▌    | 1111/2000 [33:25<25:29,  1.72s/it, loss=0.196, lr=0.0001]
Steps:  56%|█████▌    | 1112/2000 [33:26<25:09,  1.70s/it, loss=0.196, lr=0.0001]
Steps:  56%|█████▌    | 1112/2000 [33:26<25:09,  1.70s/it, loss=0.228, lr=0.0001]
Steps:  56%|█████▌    | 1112/2000 [33:26<25:09,  1.70s/it, loss=0.114, lr=0.0001]
Steps:  56%|█████▌    | 1112/2000 [33:26<25:09,  1.70s/it, loss=0.0612, lr=0.0001]
Steps:  56%|█████▌    | 1112/2000 [33:27<25:09,  1.70s/it, loss=0.179, lr=0.0001] 
Steps:  56%|█████▌    | 1113/2000 [33:27<25:51,  1.75s/it, loss=0.179, lr=0.0001]
Steps:  56%|█████▌    | 1113/2000 [33:27<25:51,  1.75s/it, loss=0.233, lr=0.0001]
Steps:  56%|█████▌    | 1113/2000 [33:28<25:51,  1.75s/it, loss=0.225, lr=0.0001]
Steps:  56%|█████▌    | 1113/2000 [33:28<25:51,  1.75s/it, loss=0.133, lr=0.0001]
Steps:  56%|█████▌    | 1113/2000 [33:29<25:51,  1.75s/it, loss=0.673, lr=0.0001]
Steps:  56%|█████▌    | 1114/2000 [33:29<25:21,  1.72s/it, loss=0.673, lr=0.0001]
Steps:  56%|█████▌    | 1114/2000 [33:29<25:21,  1.72s/it, loss=0.103, lr=0.0001]
Steps:  56%|█████▌    | 1114/2000 [33:29<25:21,  1.72s/it, loss=0.143, lr=0.0001]
Steps:  56%|█████▌    | 1114/2000 [33:30<25:21,  1.72s/it, loss=0.247, lr=0.0001]
Steps:  56%|█████▌    | 1114/2000 [33:30<25:21,  1.72s/it, loss=0.114, lr=0.0001]
Steps:  56%|█████▌    | 1115/2000 [33:31<24:58,  1.69s/it, loss=0.114, lr=0.0001]
Steps:  56%|█████▌    | 1115/2000 [33:31<24:58,  1.69s/it, loss=0.15, lr=0.0001] 
Steps:  56%|█████▌    | 1115/2000 [33:31<24:58,  1.69s/it, loss=0.105, lr=0.0001]
Steps:  56%|█████▌    | 1115/2000 [33:31<24:58,  1.69s/it, loss=0.143, lr=0.0001]
Steps:  56%|█████▌    | 1115/2000 [33:32<24:58,  1.69s/it, loss=0.16, lr=0.0001] 
Steps:  56%|█████▌    | 1116/2000 [33:32<24:44,  1.68s/it, loss=0.16, lr=0.0001]
Steps:  56%|█████▌    | 1116/2000 [33:32<24:44,  1.68s/it, loss=0.244, lr=0.0001]
Steps:  56%|█████▌    | 1116/2000 [33:33<24:44,  1.68s/it, loss=0.157, lr=0.0001]
Steps:  56%|█████▌    | 1116/2000 [33:33<24:44,  1.68s/it, loss=0.234, lr=0.0001]
Steps:  56%|█████▌    | 1116/2000 [33:34<24:44,  1.68s/it, loss=0.198, lr=0.0001]
Steps:  56%|█████▌    | 1117/2000 [33:34<25:43,  1.75s/it, loss=0.198, lr=0.0001]
Steps:  56%|█████▌    | 1117/2000 [33:34<25:43,  1.75s/it, loss=0.0963, lr=0.0001]
Steps:  56%|█████▌    | 1117/2000 [33:35<25:43,  1.75s/it, loss=0.269, lr=0.0001] 
Steps:  56%|█████▌    | 1117/2000 [33:35<25:43,  1.75s/it, loss=0.173, lr=0.0001]
Steps:  56%|█████▌    | 1117/2000 [33:35<25:43,  1.75s/it, loss=0.212, lr=0.0001]
Steps:  56%|█████▌    | 1118/2000 [33:36<25:24,  1.73s/it, loss=0.212, lr=0.0001]
Steps:  56%|█████▌    | 1118/2000 [33:36<25:24,  1.73s/it, loss=0.148, lr=0.0001]
Steps:  56%|█████▌    | 1118/2000 [33:36<25:24,  1.73s/it, loss=0.342, lr=0.0001]
Steps:  56%|█████▌    | 1118/2000 [33:37<25:24,  1.73s/it, loss=0.191, lr=0.0001]
Steps:  56%|█████▌    | 1118/2000 [33:37<25:24,  1.73s/it, loss=0.0935, lr=0.0001]
Steps:  56%|█████▌    | 1119/2000 [33:38<25:01,  1.70s/it, loss=0.0935, lr=0.0001]
Steps:  56%|█████▌    | 1119/2000 [33:38<25:01,  1.70s/it, loss=0.309, lr=0.0001] 
Steps:  56%|█████▌    | 1119/2000 [33:38<25:01,  1.70s/it, loss=0.153, lr=0.0001]
Steps:  56%|█████▌    | 1119/2000 [33:39<25:01,  1.70s/it, loss=0.154, lr=0.0001]
Steps:  56%|█████▌    | 1119/2000 [33:39<25:01,  1.70s/it, loss=0.0732, lr=0.0001]
Steps:  56%|█████▌    | 1120/2000 [33:39<26:00,  1.77s/it, loss=0.0732, lr=0.0001]
Steps:  56%|█████▌    | 1120/2000 [33:39<26:00,  1.77s/it, loss=0.0869, lr=0.0001]
Steps:  56%|█████▌    | 1120/2000 [33:40<26:00,  1.77s/it, loss=0.135, lr=0.0001] 
Steps:  56%|█████▌    | 1120/2000 [33:40<26:00,  1.77s/it, loss=0.127, lr=0.0001]
Steps:  56%|█████▌    | 1120/2000 [33:41<26:00,  1.77s/it, loss=0.145, lr=0.0001]
Steps:  56%|█████▌    | 1121/2000 [33:41<25:20,  1.73s/it, loss=0.145, lr=0.0001]
Steps:  56%|█████▌    | 1121/2000 [33:41<25:20,  1.73s/it, loss=0.185, lr=0.0001]
Steps:  56%|█████▌    | 1121/2000 [33:41<25:20,  1.73s/it, loss=0.25, lr=0.0001] 
Steps:  56%|█████▌    | 1121/2000 [33:42<25:20,  1.73s/it, loss=0.143, lr=0.0001]
Steps:  56%|█████▌    | 1121/2000 [33:42<25:20,  1.73s/it, loss=0.195, lr=0.0001]
Steps:  56%|█████▌    | 1122/2000 [33:43<24:58,  1.71s/it, loss=0.195, lr=0.0001]
Steps:  56%|█████▌    | 1122/2000 [33:43<24:58,  1.71s/it, loss=0.24, lr=0.0001] 
Steps:  56%|█████▌    | 1122/2000 [33:43<24:58,  1.71s/it, loss=0.111, lr=0.0001]
Steps:  56%|█████▌    | 1122/2000 [33:44<24:58,  1.71s/it, loss=0.173, lr=0.0001]
Steps:  56%|█████▌    | 1122/2000 [33:44<24:58,  1.71s/it, loss=0.143, lr=0.0001]
Steps:  56%|█████▌    | 1123/2000 [33:45<25:36,  1.75s/it, loss=0.143, lr=0.0001]
Steps:  56%|█████▌    | 1123/2000 [33:45<25:36,  1.75s/it, loss=0.209, lr=0.0001]
Steps:  56%|█████▌    | 1123/2000 [33:45<25:36,  1.75s/it, loss=0.146, lr=0.0001]
Steps:  56%|█████▌    | 1123/2000 [33:45<25:36,  1.75s/it, loss=0.232, lr=0.0001]
Steps:  56%|█████▌    | 1123/2000 [33:46<25:36,  1.75s/it, loss=0.176, lr=0.0001]
Steps:  56%|█████▌    | 1124/2000 [33:46<25:02,  1.71s/it, loss=0.176, lr=0.0001]
Steps:  56%|█████▌    | 1124/2000 [33:46<25:02,  1.71s/it, loss=0.265, lr=0.0001]
Steps:  56%|█████▌    | 1124/2000 [33:47<25:02,  1.71s/it, loss=0.0591, lr=0.0001]
Steps:  56%|█████▌    | 1124/2000 [33:47<25:02,  1.71s/it, loss=0.163, lr=0.0001] 
Steps:  56%|█████▌    | 1124/2000 [33:47<25:02,  1.71s/it, loss=0.113, lr=0.0001]
Steps:  56%|█████▋    | 1125/2000 [33:48<24:43,  1.70s/it, loss=0.113, lr=0.0001]
Steps:  56%|█████▋    | 1125/2000 [33:48<24:43,  1.70s/it, loss=0.158, lr=0.0001]
Steps:  56%|█████▋    | 1125/2000 [33:48<24:43,  1.70s/it, loss=0.51, lr=0.0001] 
Steps:  56%|█████▋    | 1125/2000 [33:49<24:43,  1.70s/it, loss=0.107, lr=0.0001]
Steps:  56%|█████▋    | 1125/2000 [33:49<24:43,  1.70s/it, loss=0.157, lr=0.0001]
Steps:  56%|█████▋    | 1126/2000 [33:50<25:23,  1.74s/it, loss=0.157, lr=0.0001]
Steps:  56%|█████▋    | 1126/2000 [33:50<25:23,  1.74s/it, loss=0.154, lr=0.0001]
Steps:  56%|█████▋    | 1126/2000 [33:50<25:23,  1.74s/it, loss=0.2, lr=0.0001]  
Steps:  56%|█████▋    | 1126/2000 [33:51<25:23,  1.74s/it, loss=0.581, lr=0.0001]
Steps:  56%|█████▋    | 1126/2000 [33:51<25:23,  1.74s/it, loss=0.19, lr=0.0001] 
Steps:  56%|█████▋    | 1127/2000 [33:51<24:51,  1.71s/it, loss=0.19, lr=0.0001]
Steps:  56%|█████▋    | 1127/2000 [33:51<24:51,  1.71s/it, loss=0.708, lr=0.0001]
Steps:  56%|█████▋    | 1127/2000 [33:52<24:51,  1.71s/it, loss=0.137, lr=0.0001]
Steps:  56%|█████▋    | 1127/2000 [33:52<24:51,  1.71s/it, loss=0.17, lr=0.0001] 
Steps:  56%|█████▋    | 1127/2000 [33:53<24:51,  1.71s/it, loss=0.154, lr=0.0001]
Steps:  56%|█████▋    | 1128/2000 [33:53<24:32,  1.69s/it, loss=0.154, lr=0.0001]
Steps:  56%|█████▋    | 1128/2000 [33:53<24:32,  1.69s/it, loss=0.216, lr=0.0001]
Steps:  56%|█████▋    | 1128/2000 [33:53<24:32,  1.69s/it, loss=0.215, lr=0.0001]
Steps:  56%|█████▋    | 1128/2000 [33:54<24:32,  1.69s/it, loss=0.362, lr=0.0001]
Steps:  56%|█████▋    | 1128/2000 [33:54<24:32,  1.69s/it, loss=0.327, lr=0.0001]
Steps:  56%|█████▋    | 1129/2000 [33:55<25:15,  1.74s/it, loss=0.327, lr=0.0001]
Steps:  56%|█████▋    | 1129/2000 [33:55<25:15,  1.74s/it, loss=0.154, lr=0.0001]
Steps:  56%|█████▋    | 1129/2000 [33:55<25:15,  1.74s/it, loss=0.169, lr=0.0001]
Steps:  56%|█████▋    | 1129/2000 [33:56<25:15,  1.74s/it, loss=0.805, lr=0.0001]
Steps:  56%|█████▋    | 1129/2000 [33:56<25:15,  1.74s/it, loss=0.185, lr=0.0001]
Steps:  56%|█████▋    | 1130/2000 [33:57<24:53,  1.72s/it, loss=0.185, lr=0.0001]
Steps:  56%|█████▋    | 1130/2000 [33:57<24:53,  1.72s/it, loss=0.454, lr=0.0001]
Steps:  56%|█████▋    | 1130/2000 [33:57<24:53,  1.72s/it, loss=0.279, lr=0.0001]
Steps:  56%|█████▋    | 1130/2000 [33:57<24:53,  1.72s/it, loss=0.0958, lr=0.0001]
Steps:  56%|█████▋    | 1130/2000 [33:58<24:53,  1.72s/it, loss=0.999, lr=0.0001] 
Steps:  57%|█████▋    | 1131/2000 [33:58<24:40,  1.70s/it, loss=0.999, lr=0.0001]
Steps:  57%|█████▋    | 1131/2000 [33:58<24:40,  1.70s/it, loss=0.174, lr=0.0001]
Steps:  57%|█████▋    | 1131/2000 [33:59<24:40,  1.70s/it, loss=0.211, lr=0.0001]
Steps:  57%|█████▋    | 1131/2000 [33:59<24:40,  1.70s/it, loss=0.141, lr=0.0001]
Steps:  57%|█████▋    | 1131/2000 [33:59<24:40,  1.70s/it, loss=0.254, lr=0.0001]
Steps:  57%|█████▋    | 1132/2000 [34:00<25:34,  1.77s/it, loss=0.254, lr=0.0001]
Steps:  57%|█████▋    | 1132/2000 [34:00<25:34,  1.77s/it, loss=0.27, lr=0.0001] 
Steps:  57%|█████▋    | 1132/2000 [34:01<25:34,  1.77s/it, loss=0.0769, lr=0.0001]
Steps:  57%|█████▋    | 1132/2000 [34:01<25:34,  1.77s/it, loss=0.0735, lr=0.0001]
Steps:  57%|█████▋    | 1132/2000 [34:01<25:34,  1.77s/it, loss=0.166, lr=0.0001] 
Steps:  57%|█████▋    | 1133/2000 [34:02<25:04,  1.74s/it, loss=0.166, lr=0.0001]
Steps:  57%|█████▋    | 1133/2000 [34:02<25:04,  1.74s/it, loss=0.18, lr=0.0001] 
Steps:  57%|█████▋    | 1133/2000 [34:02<25:04,  1.74s/it, loss=0.129, lr=0.0001]
Steps:  57%|█████▋    | 1133/2000 [34:03<25:04,  1.74s/it, loss=0.202, lr=0.0001]
Steps:  57%|█████▋    | 1133/2000 [34:03<25:04,  1.74s/it, loss=0.102, lr=0.0001]
Steps:  57%|█████▋    | 1134/2000 [34:03<24:41,  1.71s/it, loss=0.102, lr=0.0001]
Steps:  57%|█████▋    | 1134/2000 [34:03<24:41,  1.71s/it, loss=0.139, lr=0.0001]
Steps:  57%|█████▋    | 1134/2000 [34:04<24:41,  1.71s/it, loss=0.116, lr=0.0001]
Steps:  57%|█████▋    | 1134/2000 [34:04<24:41,  1.71s/it, loss=0.221, lr=0.0001]
Steps:  57%|█████▋    | 1134/2000 [34:05<24:41,  1.71s/it, loss=0.127, lr=0.0001]
Steps:  57%|█████▋    | 1135/2000 [34:05<24:21,  1.69s/it, loss=0.127, lr=0.0001]
Steps:  57%|█████▋    | 1135/2000 [34:05<24:21,  1.69s/it, loss=0.0735, lr=0.0001]
Steps:  57%|█████▋    | 1135/2000 [34:06<24:21,  1.69s/it, loss=0.0674, lr=0.0001]
Steps:  57%|█████▋    | 1135/2000 [34:06<24:21,  1.69s/it, loss=0.131, lr=0.0001] 
Steps:  57%|█████▋    | 1135/2000 [34:07<24:21,  1.69s/it, loss=0.21, lr=0.0001] 
Steps:  57%|█████▋    | 1136/2000 [34:07<25:12,  1.75s/it, loss=0.21, lr=0.0001]
Steps:  57%|█████▋    | 1136/2000 [34:07<25:12,  1.75s/it, loss=0.113, lr=0.0001]
Steps:  57%|█████▋    | 1136/2000 [34:07<25:12,  1.75s/it, loss=0.129, lr=0.0001]
Steps:  57%|█████▋    | 1136/2000 [34:08<25:12,  1.75s/it, loss=0.0667, lr=0.0001]
Steps:  57%|█████▋    | 1136/2000 [34:08<25:12,  1.75s/it, loss=0.138, lr=0.0001] 
Steps:  57%|█████▋    | 1137/2000 [34:09<24:45,  1.72s/it, loss=0.138, lr=0.0001]
Steps:  57%|█████▋    | 1137/2000 [34:09<24:45,  1.72s/it, loss=0.225, lr=0.0001]
Steps:  57%|█████▋    | 1137/2000 [34:09<24:45,  1.72s/it, loss=0.355, lr=0.0001]
Steps:  57%|█████▋    | 1137/2000 [34:09<24:45,  1.72s/it, loss=0.097, lr=0.0001]
Steps:  57%|█████▋    | 1137/2000 [34:10<24:45,  1.72s/it, loss=0.183, lr=0.0001]
Steps:  57%|█████▋    | 1138/2000 [34:10<24:34,  1.71s/it, loss=0.183, lr=0.0001]
Steps:  57%|█████▋    | 1138/2000 [34:10<24:34,  1.71s/it, loss=0.21, lr=0.0001] 
Steps:  57%|█████▋    | 1138/2000 [34:11<24:34,  1.71s/it, loss=0.158, lr=0.0001]
Steps:  57%|█████▋    | 1138/2000 [34:11<24:34,  1.71s/it, loss=0.109, lr=0.0001]
Steps:  57%|█████▋    | 1138/2000 [34:12<24:34,  1.71s/it, loss=0.213, lr=0.0001]
Steps:  57%|█████▋    | 1139/2000 [34:12<25:13,  1.76s/it, loss=0.213, lr=0.0001]
Steps:  57%|█████▋    | 1139/2000 [34:12<25:13,  1.76s/it, loss=0.179, lr=0.0001]
Steps:  57%|█████▋    | 1139/2000 [34:13<25:13,  1.76s/it, loss=0.214, lr=0.0001]
Steps:  57%|█████▋    | 1139/2000 [34:13<25:13,  1.76s/it, loss=0.195, lr=0.0001]
Steps:  57%|█████▋    | 1139/2000 [34:13<25:13,  1.76s/it, loss=0.0616, lr=0.0001]
Steps:  57%|█████▋    | 1140/2000 [34:14<24:40,  1.72s/it, loss=0.0616, lr=0.0001]
Steps:  57%|█████▋    | 1140/2000 [34:14<24:40,  1.72s/it, loss=0.147, lr=0.0001] 
Steps:  57%|█████▋    | 1140/2000 [34:14<24:40,  1.72s/it, loss=0.0893, lr=0.0001]
Steps:  57%|█████▋    | 1140/2000 [34:15<24:40,  1.72s/it, loss=0.15, lr=0.0001]  
Steps:  57%|█████▋    | 1140/2000 [34:15<24:40,  1.72s/it, loss=0.154, lr=0.0001]
Steps:  57%|█████▋    | 1141/2000 [34:15<24:18,  1.70s/it, loss=0.154, lr=0.0001]
Steps:  57%|█████▋    | 1141/2000 [34:15<24:18,  1.70s/it, loss=0.175, lr=0.0001]
Steps:  57%|█████▋    | 1141/2000 [34:16<24:18,  1.70s/it, loss=0.933, lr=0.0001]
Steps:  57%|█████▋    | 1141/2000 [34:16<24:18,  1.70s/it, loss=0.204, lr=0.0001]
Steps:  57%|█████▋    | 1141/2000 [34:17<24:18,  1.70s/it, loss=0.151, lr=0.0001]
Steps:  57%|█████▋    | 1142/2000 [34:17<25:04,  1.75s/it, loss=0.151, lr=0.0001]
Steps:  57%|█████▋    | 1142/2000 [34:17<25:04,  1.75s/it, loss=1.05, lr=0.0001] 
Steps:  57%|█████▋    | 1142/2000 [34:18<25:04,  1.75s/it, loss=0.203, lr=0.0001]
Steps:  57%|█████▋    | 1142/2000 [34:18<25:04,  1.75s/it, loss=0.229, lr=0.0001]
Steps:  57%|█████▋    | 1142/2000 [34:19<25:04,  1.75s/it, loss=0.158, lr=0.0001]
Steps:  57%|█████▋    | 1143/2000 [34:19<24:33,  1.72s/it, loss=0.158, lr=0.0001]
Steps:  57%|█████▋    | 1143/2000 [34:19<24:33,  1.72s/it, loss=0.136, lr=0.0001]
Steps:  57%|█████▋    | 1143/2000 [34:19<24:33,  1.72s/it, loss=0.106, lr=0.0001]
Steps:  57%|█████▋    | 1143/2000 [34:20<24:33,  1.72s/it, loss=0.161, lr=0.0001]
Steps:  57%|█████▋    | 1143/2000 [34:20<24:33,  1.72s/it, loss=0.191, lr=0.0001]
Steps:  57%|█████▋    | 1144/2000 [34:21<24:18,  1.70s/it, loss=0.191, lr=0.0001]
Steps:  57%|█████▋    | 1144/2000 [34:21<24:18,  1.70s/it, loss=1.14, lr=0.0001] 
Steps:  57%|█████▋    | 1144/2000 [34:21<24:18,  1.70s/it, loss=0.28, lr=0.0001]
Steps:  57%|█████▋    | 1144/2000 [34:21<24:18,  1.70s/it, loss=0.165, lr=0.0001]
Steps:  57%|█████▋    | 1144/2000 [34:22<24:18,  1.70s/it, loss=0.166, lr=0.0001]
Steps:  57%|█████▋    | 1145/2000 [34:23<24:55,  1.75s/it, loss=0.166, lr=0.0001]
Steps:  57%|█████▋    | 1145/2000 [34:23<24:55,  1.75s/it, loss=0.264, lr=0.0001]
Steps:  57%|█████▋    | 1145/2000 [34:23<24:55,  1.75s/it, loss=0.0945, lr=0.0001]
Steps:  57%|█████▋    | 1145/2000 [34:23<24:55,  1.75s/it, loss=0.234, lr=0.0001] 
Steps:  57%|█████▋    | 1145/2000 [34:24<24:55,  1.75s/it, loss=0.142, lr=0.0001]
Steps:  57%|█████▋    | 1146/2000 [34:24<24:26,  1.72s/it, loss=0.142, lr=0.0001]
Steps:  57%|█████▋    | 1146/2000 [34:24<24:26,  1.72s/it, loss=0.293, lr=0.0001]
Steps:  57%|█████▋    | 1146/2000 [34:25<24:26,  1.72s/it, loss=0.839, lr=0.0001]
Steps:  57%|█████▋    | 1146/2000 [34:25<24:26,  1.72s/it, loss=0.129, lr=0.0001]
Steps:  57%|█████▋    | 1146/2000 [34:25<24:26,  1.72s/it, loss=0.0495, lr=0.0001]
Steps:  57%|█████▋    | 1147/2000 [34:26<24:13,  1.70s/it, loss=0.0495, lr=0.0001]
Steps:  57%|█████▋    | 1147/2000 [34:26<24:13,  1.70s/it, loss=0.112, lr=0.0001] 
Steps:  57%|█████▋    | 1147/2000 [34:26<24:13,  1.70s/it, loss=0.274, lr=0.0001]
Steps:  57%|█████▋    | 1147/2000 [34:27<24:13,  1.70s/it, loss=0.18, lr=0.0001] 
Steps:  57%|█████▋    | 1147/2000 [34:27<24:13,  1.70s/it, loss=0.295, lr=0.0001]
Steps:  57%|█████▋    | 1148/2000 [34:28<24:55,  1.75s/it, loss=0.295, lr=0.0001]
Steps:  57%|█████▋    | 1148/2000 [34:28<24:55,  1.75s/it, loss=0.227, lr=0.0001]
Steps:  57%|█████▋    | 1148/2000 [34:28<24:55,  1.75s/it, loss=0.518, lr=0.0001]
Steps:  57%|█████▋    | 1148/2000 [34:28<24:55,  1.75s/it, loss=0.0869, lr=0.0001]
Steps:  57%|█████▋    | 1148/2000 [34:29<24:55,  1.75s/it, loss=0.158, lr=0.0001] 
Steps:  57%|█████▋    | 1149/2000 [34:29<24:30,  1.73s/it, loss=0.158, lr=0.0001]
Steps:  57%|█████▋    | 1149/2000 [34:29<24:30,  1.73s/it, loss=0.345, lr=0.0001]
Steps:  57%|█████▋    | 1149/2000 [34:30<24:30,  1.73s/it, loss=0.255, lr=0.0001]
Steps:  57%|█████▋    | 1149/2000 [34:30<24:30,  1.73s/it, loss=0.24, lr=0.0001] 
Steps:  57%|█████▋    | 1149/2000 [34:31<24:30,  1.73s/it, loss=0.174, lr=0.0001]
Steps:  57%|█████▊    | 1150/2000 [34:31<24:08,  1.70s/it, loss=0.174, lr=0.0001]
Steps:  57%|█████▊    | 1150/2000 [34:31<24:08,  1.70s/it, loss=0.213, lr=0.0001]
Steps:  57%|█████▊    | 1150/2000 [34:31<24:08,  1.70s/it, loss=0.092, lr=0.0001]
Steps:  57%|█████▊    | 1150/2000 [34:32<24:08,  1.70s/it, loss=0.154, lr=0.0001]
Steps:  57%|█████▊    | 1150/2000 [34:32<24:08,  1.70s/it, loss=0.149, lr=0.0001]
Steps:  58%|█████▊    | 1151/2000 [34:33<23:50,  1.68s/it, loss=0.149, lr=0.0001]
Steps:  58%|█████▊    | 1151/2000 [34:33<23:50,  1.68s/it, loss=0.173, lr=0.0001]
Steps:  58%|█████▊    | 1151/2000 [34:33<23:50,  1.68s/it, loss=0.152, lr=0.0001]
Steps:  58%|█████▊    | 1151/2000 [34:34<23:50,  1.68s/it, loss=0.181, lr=0.0001]
Steps:  58%|█████▊    | 1151/2000 [34:34<23:50,  1.68s/it, loss=0.223, lr=0.0001]
Steps:  58%|█████▊    | 1152/2000 [34:35<24:44,  1.75s/it, loss=0.223, lr=0.0001]
Steps:  58%|█████▊    | 1152/2000 [34:35<24:44,  1.75s/it, loss=0.21, lr=0.0001] 
Steps:  58%|█████▊    | 1152/2000 [34:35<24:44,  1.75s/it, loss=0.375, lr=0.0001]
Steps:  58%|█████▊    | 1152/2000 [34:35<24:44,  1.75s/it, loss=0.194, lr=0.0001]
Steps:  58%|█████▊    | 1152/2000 [34:36<24:44,  1.75s/it, loss=0.123, lr=0.0001]
Steps:  58%|█████▊    | 1153/2000 [34:36<24:15,  1.72s/it, loss=0.123, lr=0.0001]
Steps:  58%|█████▊    | 1153/2000 [34:36<24:15,  1.72s/it, loss=0.263, lr=0.0001]
Steps:  58%|█████▊    | 1153/2000 [34:37<24:15,  1.72s/it, loss=0.109, lr=0.0001]
Steps:  58%|█████▊    | 1153/2000 [34:37<24:15,  1.72s/it, loss=0.134, lr=0.0001]
Steps:  58%|█████▊    | 1153/2000 [34:37<24:15,  1.72s/it, loss=0.134, lr=0.0001]
Steps:  58%|█████▊    | 1154/2000 [34:38<24:07,  1.71s/it, loss=0.134, lr=0.0001]
Steps:  58%|█████▊    | 1154/2000 [34:38<24:07,  1.71s/it, loss=0.294, lr=0.0001]
Steps:  58%|█████▊    | 1154/2000 [34:38<24:07,  1.71s/it, loss=0.287, lr=0.0001]
Steps:  58%|█████▊    | 1154/2000 [34:39<24:07,  1.71s/it, loss=0.272, lr=0.0001]
Steps:  58%|█████▊    | 1154/2000 [34:39<24:07,  1.71s/it, loss=0.121, lr=0.0001]
Steps:  58%|█████▊    | 1155/2000 [34:40<24:47,  1.76s/it, loss=0.121, lr=0.0001]
Steps:  58%|█████▊    | 1155/2000 [34:40<24:47,  1.76s/it, loss=0.117, lr=0.0001]05/30/2026 09:07:05 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/config.json "HTTP/1.1 200 OK"
05/30/2026 09:07:05 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/config.json "HTTP/1.1 200 OK"
05/30/2026 09:07:05 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/model.safetensors "HTTP/1.1 302 Found"


Loading weights:   0%|          | 0/196 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 196/196 [00:00<00:00, 7317.30it/s]
05/30/2026 09:07:05 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/config.json "HTTP/1.1 200 OK"
05/30/2026 09:07:06 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/config.json "HTTP/1.1 200 OK"
05/30/2026 09:07:06 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/model.safetensors "HTTP/1.1 404 Not Found"
05/30/2026 09:07:06 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/model.safetensors.index.json "HTTP/1.1 200 OK"
05/30/2026 09:07:06 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev/revision/main "HTTP/1.1 200 OK"


Fetching 2 files:   0%|          | 0/2 [00:00<?, ?it/s]
Fetching 2 files: 100%|██████████| 2/2 [00:00<00:00, 3538.00it/s]


Loading weights:   0%|          | 0/219 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 219/219 [00:00<00:00, 7079.57it/s]
05/30/2026 09:07:06 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev "HTTP/1.1 200 OK"
05/30/2026 09:07:06 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/model_index.json "HTTP/1.1 200 OK"
{'feature_extractor', 'image_encoder'} was not found in config. Values will be initialized to default values.


Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]Loaded tokenizer_2 as T5TokenizerFast from `tokenizer_2` subfolder of black-forest-labs/FLUX.1-dev.


Loading pipeline components...:  43%|████▎     | 3/7 [00:00<00:00, 17.99it/s]Loaded tokenizer as CLIPTokenizer from `tokenizer` subfolder of black-forest-labs/FLUX.1-dev.
{'stochastic_sampling', 'use_beta_sigmas', 'invert_sigmas', 'time_shift_type', 'use_exponential_sigmas', 'shift_terminal', 'use_karras_sigmas'} was not found in config. Values will be initialized to default values.
Loaded scheduler as FlowMatchEulerDiscreteScheduler from `scheduler` subfolder of black-forest-labs/FLUX.1-dev.

Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 31.55it/s]
05/30/2026 09:07:06 - INFO - __main__ - [RANK 0] Running validation... 
 Generating 1 images with prompt: emj icon of a pelican with a hat, centered on a plain white background.

Steps:  58%|█████▊    | 1155/2000 [34:52<24:47,  1.76s/it, loss=0.17, lr=0.0001] 
Steps:  58%|█████▊    | 1155/2000 [34:53<24:47,  1.76s/it, loss=0.152, lr=0.0001]
Steps:  58%|█████▊    | 1155/2000 [34:53<24:47,  1.76s/it, loss=0.191, lr=0.0001]
Steps:  58%|█████▊    | 1156/2000 [34:53<1:14:57,  5.33s/it, loss=0.191, lr=0.0001]
Steps:  58%|█████▊    | 1156/2000 [34:53<1:14:57,  5.33s/it, loss=0.252, lr=0.0001]
Steps:  58%|█████▊    | 1156/2000 [34:54<1:14:57,  5.33s/it, loss=0.145, lr=0.0001]
Steps:  58%|█████▊    | 1156/2000 [34:54<1:14:57,  5.33s/it, loss=0.288, lr=0.0001]
Steps:  58%|█████▊    | 1156/2000 [34:55<1:14:57,  5.33s/it, loss=0.0983, lr=0.0001]
Steps:  58%|█████▊    | 1157/2000 [34:55<59:32,  4.24s/it, loss=0.0983, lr=0.0001]  
Steps:  58%|█████▊    | 1157/2000 [34:55<59:32,  4.24s/it, loss=0.12, lr=0.0001]  
Steps:  58%|█████▊    | 1157/2000 [34:56<59:32,  4.24s/it, loss=0.135, lr=0.0001]
Steps:  58%|█████▊    | 1157/2000 [34:56<59:32,  4.24s/it, loss=0.108, lr=0.0001]
Steps:  58%|█████▊    | 1157/2000 [34:56<59:32,  4.24s/it, loss=0.14, lr=0.0001] 
Steps:  58%|█████▊    | 1158/2000 [34:57<48:45,  3.47s/it, loss=0.14, lr=0.0001]
Steps:  58%|█████▊    | 1158/2000 [34:57<48:45,  3.47s/it, loss=0.17, lr=0.0001]
Steps:  58%|█████▊    | 1158/2000 [34:57<48:45,  3.47s/it, loss=0.123, lr=0.0001]
Steps:  58%|█████▊    | 1158/2000 [34:58<48:45,  3.47s/it, loss=0.16, lr=0.0001] 
Steps:  58%|█████▊    | 1158/2000 [34:58<48:45,  3.47s/it, loss=0.0754, lr=0.0001]
Steps:  58%|█████▊    | 1159/2000 [34:59<42:08,  3.01s/it, loss=0.0754, lr=0.0001]
Steps:  58%|█████▊    | 1159/2000 [34:59<42:08,  3.01s/it, loss=0.149, lr=0.0001] 
Steps:  58%|█████▊    | 1159/2000 [34:59<42:08,  3.01s/it, loss=0.134, lr=0.0001]
Steps:  58%|█████▊    | 1159/2000 [35:00<42:08,  3.01s/it, loss=0.135, lr=0.0001]
Steps:  58%|█████▊    | 1159/2000 [35:00<42:08,  3.01s/it, loss=0.112, lr=0.0001]
Steps:  58%|█████▊    | 1160/2000 [35:00<36:36,  2.61s/it, loss=0.112, lr=0.0001]
Steps:  58%|█████▊    | 1160/2000 [35:00<36:36,  2.61s/it, loss=0.13, lr=0.0001] 
Steps:  58%|█████▊    | 1160/2000 [35:01<36:36,  2.61s/it, loss=0.0716, lr=0.0001]
Steps:  58%|█████▊    | 1160/2000 [35:01<36:36,  2.61s/it, loss=0.178, lr=0.0001] 
Steps:  58%|█████▊    | 1160/2000 [35:02<36:36,  2.61s/it, loss=0.854, lr=0.0001]
Steps:  58%|█████▊    | 1161/2000 [35:02<32:40,  2.34s/it, loss=0.854, lr=0.0001]
Steps:  58%|█████▊    | 1161/2000 [35:02<32:40,  2.34s/it, loss=0.422, lr=0.0001]
Steps:  58%|█████▊    | 1161/2000 [35:03<32:40,  2.34s/it, loss=0.293, lr=0.0001]
Steps:  58%|█████▊    | 1161/2000 [35:03<32:40,  2.34s/it, loss=0.149, lr=0.0001]
Steps:  58%|█████▊    | 1161/2000 [35:04<32:40,  2.34s/it, loss=0.0252, lr=0.0001]
Steps:  58%|█████▊    | 1162/2000 [35:04<30:58,  2.22s/it, loss=0.0252, lr=0.0001]
Steps:  58%|█████▊    | 1162/2000 [35:04<30:58,  2.22s/it, loss=0.694, lr=0.0001] 
Steps:  58%|█████▊    | 1162/2000 [35:04<30:58,  2.22s/it, loss=0.861, lr=0.0001]
Steps:  58%|█████▊    | 1162/2000 [35:05<30:58,  2.22s/it, loss=0.125, lr=0.0001]
Steps:  58%|█████▊    | 1162/2000 [35:05<30:58,  2.22s/it, loss=0.186, lr=0.0001]
Steps:  58%|█████▊    | 1163/2000 [35:06<28:51,  2.07s/it, loss=0.186, lr=0.0001]
Steps:  58%|█████▊    | 1163/2000 [35:06<28:51,  2.07s/it, loss=0.164, lr=0.0001]
Steps:  58%|█████▊    | 1163/2000 [35:06<28:51,  2.07s/it, loss=0.148, lr=0.0001]
Steps:  58%|█████▊    | 1163/2000 [35:07<28:51,  2.07s/it, loss=0.239, lr=0.0001]
Steps:  58%|█████▊    | 1163/2000 [35:07<28:51,  2.07s/it, loss=0.267, lr=0.0001]
Steps:  58%|█████▊    | 1164/2000 [35:07<27:19,  1.96s/it, loss=0.267, lr=0.0001]
Steps:  58%|█████▊    | 1164/2000 [35:07<27:19,  1.96s/it, loss=0.2, lr=0.0001]  
Steps:  58%|█████▊    | 1164/2000 [35:08<27:19,  1.96s/it, loss=0.238, lr=0.0001]
Steps:  58%|█████▊    | 1164/2000 [35:08<27:19,  1.96s/it, loss=0.176, lr=0.0001]
Steps:  58%|█████▊    | 1164/2000 [35:09<27:19,  1.96s/it, loss=0.337, lr=0.0001]
Steps:  58%|█████▊    | 1165/2000 [35:09<27:08,  1.95s/it, loss=0.337, lr=0.0001]
Steps:  58%|█████▊    | 1165/2000 [35:09<27:08,  1.95s/it, loss=0.163, lr=0.0001]
Steps:  58%|█████▊    | 1165/2000 [35:10<27:08,  1.95s/it, loss=0.594, lr=0.0001]
Steps:  58%|█████▊    | 1165/2000 [35:10<27:08,  1.95s/it, loss=0.241, lr=0.0001]
Steps:  58%|█████▊    | 1165/2000 [35:11<27:08,  1.95s/it, loss=0.155, lr=0.0001]
Steps:  58%|█████▊    | 1166/2000 [35:11<26:02,  1.87s/it, loss=0.155, lr=0.0001]
Steps:  58%|█████▊    | 1166/2000 [35:11<26:02,  1.87s/it, loss=0.133, lr=0.0001]
Steps:  58%|█████▊    | 1166/2000 [35:12<26:02,  1.87s/it, loss=0.162, lr=0.0001]
Steps:  58%|█████▊    | 1166/2000 [35:12<26:02,  1.87s/it, loss=0.108, lr=0.0001]
Steps:  58%|█████▊    | 1166/2000 [35:12<26:02,  1.87s/it, loss=0.518, lr=0.0001]
Steps:  58%|█████▊    | 1167/2000 [35:13<25:09,  1.81s/it, loss=0.518, lr=0.0001]
Steps:  58%|█████▊    | 1167/2000 [35:13<25:09,  1.81s/it, loss=0.178, lr=0.0001]
Steps:  58%|█████▊    | 1167/2000 [35:13<25:09,  1.81s/it, loss=0.206, lr=0.0001]
Steps:  58%|█████▊    | 1167/2000 [35:14<25:09,  1.81s/it, loss=1.27, lr=0.0001] 
Steps:  58%|█████▊    | 1167/2000 [35:14<25:09,  1.81s/it, loss=1.03, lr=0.0001]
Steps:  58%|█████▊    | 1168/2000 [35:15<25:41,  1.85s/it, loss=1.03, lr=0.0001]
Steps:  58%|█████▊    | 1168/2000 [35:15<25:41,  1.85s/it, loss=0.119, lr=0.0001]
Steps:  58%|█████▊    | 1168/2000 [35:15<25:41,  1.85s/it, loss=0.156, lr=0.0001]
Steps:  58%|█████▊    | 1168/2000 [35:16<25:41,  1.85s/it, loss=0.568, lr=0.0001]
Steps:  58%|█████▊    | 1168/2000 [35:16<25:41,  1.85s/it, loss=0.111, lr=0.0001]
Steps:  58%|█████▊    | 1169/2000 [35:16<24:54,  1.80s/it, loss=0.111, lr=0.0001]
Steps:  58%|█████▊    | 1169/2000 [35:16<24:54,  1.80s/it, loss=0.21, lr=0.0001] 
Steps:  58%|█████▊    | 1169/2000 [35:17<24:54,  1.80s/it, loss=0.219, lr=0.0001]
Steps:  58%|█████▊    | 1169/2000 [35:17<24:54,  1.80s/it, loss=0.208, lr=0.0001]
Steps:  58%|█████▊    | 1169/2000 [35:18<24:54,  1.80s/it, loss=0.803, lr=0.0001]
Steps:  58%|█████▊    | 1170/2000 [35:18<24:18,  1.76s/it, loss=0.803, lr=0.0001]
Steps:  58%|█████▊    | 1170/2000 [35:18<24:18,  1.76s/it, loss=0.214, lr=0.0001]
Steps:  58%|█████▊    | 1170/2000 [35:18<24:18,  1.76s/it, loss=0.0741, lr=0.0001]
Steps:  58%|█████▊    | 1170/2000 [35:19<24:18,  1.76s/it, loss=0.173, lr=0.0001] 
Steps:  58%|█████▊    | 1170/2000 [35:20<24:18,  1.76s/it, loss=0.135, lr=0.0001]
Steps:  59%|█████▊    | 1171/2000 [35:20<25:18,  1.83s/it, loss=0.135, lr=0.0001]
Steps:  59%|█████▊    | 1171/2000 [35:20<25:18,  1.83s/it, loss=0.0645, lr=0.0001]
Steps:  59%|█████▊    | 1171/2000 [35:20<25:18,  1.83s/it, loss=0.222, lr=0.0001] 
Steps:  59%|█████▊    | 1171/2000 [35:21<25:18,  1.83s/it, loss=0.153, lr=0.0001]
Steps:  59%|█████▊    | 1171/2000 [35:21<25:18,  1.83s/it, loss=0.146, lr=0.0001]
Steps:  59%|█████▊    | 1172/2000 [35:22<24:43,  1.79s/it, loss=0.146, lr=0.0001]
Steps:  59%|█████▊    | 1172/2000 [35:22<24:43,  1.79s/it, loss=0.213, lr=0.0001]
Steps:  59%|█████▊    | 1172/2000 [35:22<24:43,  1.79s/it, loss=0.0905, lr=0.0001]
Steps:  59%|█████▊    | 1172/2000 [35:23<24:43,  1.79s/it, loss=0.294, lr=0.0001] 
Steps:  59%|█████▊    | 1172/2000 [35:23<24:43,  1.79s/it, loss=0.165, lr=0.0001]
Steps:  59%|█████▊    | 1173/2000 [35:23<24:17,  1.76s/it, loss=0.165, lr=0.0001]
Steps:  59%|█████▊    | 1173/2000 [35:23<24:17,  1.76s/it, loss=0.596, lr=0.0001]
Steps:  59%|█████▊    | 1173/2000 [35:24<24:17,  1.76s/it, loss=0.187, lr=0.0001]
Steps:  59%|█████▊    | 1173/2000 [35:24<24:17,  1.76s/it, loss=0.196, lr=0.0001]
Steps:  59%|█████▊    | 1173/2000 [35:25<24:17,  1.76s/it, loss=0.23, lr=0.0001] 
Steps:  59%|█████▊    | 1174/2000 [35:25<24:52,  1.81s/it, loss=0.23, lr=0.0001]
Steps:  59%|█████▊    | 1174/2000 [35:25<24:52,  1.81s/it, loss=0.198, lr=0.0001]
Steps:  59%|█████▊    | 1174/2000 [35:26<24:52,  1.81s/it, loss=0.137, lr=0.0001]
Steps:  59%|█████▊    | 1174/2000 [35:26<24:52,  1.81s/it, loss=0.219, lr=0.0001]
Steps:  59%|█████▊    | 1174/2000 [35:27<24:52,  1.81s/it, loss=0.232, lr=0.0001]
Steps:  59%|█████▉    | 1175/2000 [35:27<24:17,  1.77s/it, loss=0.232, lr=0.0001]
Steps:  59%|█████▉    | 1175/2000 [35:27<24:17,  1.77s/it, loss=0.142, lr=0.0001]
Steps:  59%|█████▉    | 1175/2000 [35:27<24:17,  1.77s/it, loss=0.317, lr=0.0001]
Steps:  59%|█████▉    | 1175/2000 [35:28<24:17,  1.77s/it, loss=0.618, lr=0.0001]
Steps:  59%|█████▉    | 1175/2000 [35:28<24:17,  1.77s/it, loss=0.068, lr=0.0001]
Steps:  59%|█████▉    | 1176/2000 [35:29<23:57,  1.74s/it, loss=0.068, lr=0.0001]
Steps:  59%|█████▉    | 1176/2000 [35:29<23:57,  1.74s/it, loss=0.25, lr=0.0001] 
Steps:  59%|█████▉    | 1176/2000 [35:29<23:57,  1.74s/it, loss=0.136, lr=0.0001]
Steps:  59%|█████▉    | 1176/2000 [35:30<23:57,  1.74s/it, loss=0.345, lr=0.0001]
Steps:  59%|█████▉    | 1176/2000 [35:30<23:57,  1.74s/it, loss=0.242, lr=0.0001]
Steps:  59%|█████▉    | 1177/2000 [35:30<23:40,  1.73s/it, loss=0.242, lr=0.0001]
Steps:  59%|█████▉    | 1177/2000 [35:30<23:40,  1.73s/it, loss=0.224, lr=0.0001]
Steps:  59%|█████▉    | 1177/2000 [35:31<23:40,  1.73s/it, loss=0.0563, lr=0.0001]
Steps:  59%|█████▉    | 1177/2000 [35:31<23:40,  1.73s/it, loss=0.181, lr=0.0001] 
Steps:  59%|█████▉    | 1177/2000 [35:32<23:40,  1.73s/it, loss=0.242, lr=0.0001]
Steps:  59%|█████▉    | 1178/2000 [35:32<24:23,  1.78s/it, loss=0.242, lr=0.0001]
Steps:  59%|█████▉    | 1178/2000 [35:32<24:23,  1.78s/it, loss=0.114, lr=0.0001]
Steps:  59%|█████▉    | 1178/2000 [35:33<24:23,  1.78s/it, loss=0.134, lr=0.0001]
Steps:  59%|█████▉    | 1178/2000 [35:33<24:23,  1.78s/it, loss=0.2, lr=0.0001]  
Steps:  59%|█████▉    | 1178/2000 [35:34<24:23,  1.78s/it, loss=0.17, lr=0.0001]
Steps:  59%|█████▉    | 1179/2000 [35:34<23:53,  1.75s/it, loss=0.17, lr=0.0001]
Steps:  59%|█████▉    | 1179/2000 [35:34<23:53,  1.75s/it, loss=0.128, lr=0.0001]
Steps:  59%|█████▉    | 1179/2000 [35:34<23:53,  1.75s/it, loss=0.237, lr=0.0001]
Steps:  59%|█████▉    | 1179/2000 [35:35<23:53,  1.75s/it, loss=0.127, lr=0.0001]
Steps:  59%|█████▉    | 1179/2000 [35:35<23:53,  1.75s/it, loss=0.404, lr=0.0001]
Steps:  59%|█████▉    | 1180/2000 [35:36<23:36,  1.73s/it, loss=0.404, lr=0.0001]
Steps:  59%|█████▉    | 1180/2000 [35:36<23:36,  1.73s/it, loss=0.195, lr=0.0001]
Steps:  59%|█████▉    | 1180/2000 [35:36<23:36,  1.73s/it, loss=0.196, lr=0.0001]
Steps:  59%|█████▉    | 1180/2000 [35:37<23:36,  1.73s/it, loss=0.441, lr=0.0001]
Steps:  59%|█████▉    | 1180/2000 [35:37<23:36,  1.73s/it, loss=0.172, lr=0.0001]
Steps:  59%|█████▉    | 1181/2000 [35:38<24:18,  1.78s/it, loss=0.172, lr=0.0001]
Steps:  59%|█████▉    | 1181/2000 [35:38<24:18,  1.78s/it, loss=0.567, lr=0.0001]
Steps:  59%|█████▉    | 1181/2000 [35:38<24:18,  1.78s/it, loss=0.352, lr=0.0001]
Steps:  59%|█████▉    | 1181/2000 [35:38<24:18,  1.78s/it, loss=0.279, lr=0.0001]
Steps:  59%|█████▉    | 1181/2000 [35:39<24:18,  1.78s/it, loss=0.145, lr=0.0001]
Steps:  59%|█████▉    | 1182/2000 [35:39<23:56,  1.76s/it, loss=0.145, lr=0.0001]
Steps:  59%|█████▉    | 1182/2000 [35:39<23:56,  1.76s/it, loss=0.143, lr=0.0001]
Steps:  59%|█████▉    | 1182/2000 [35:40<23:56,  1.76s/it, loss=0.759, lr=0.0001]
Steps:  59%|█████▉    | 1182/2000 [35:40<23:56,  1.76s/it, loss=0.168, lr=0.0001]
Steps:  59%|█████▉    | 1182/2000 [35:41<23:56,  1.76s/it, loss=0.128, lr=0.0001]
Steps:  59%|█████▉    | 1183/2000 [35:41<23:46,  1.75s/it, loss=0.128, lr=0.0001]
Steps:  59%|█████▉    | 1183/2000 [35:41<23:46,  1.75s/it, loss=0.213, lr=0.0001]
Steps:  59%|█████▉    | 1183/2000 [35:41<23:46,  1.75s/it, loss=0.237, lr=0.0001]
Steps:  59%|█████▉    | 1183/2000 [35:42<23:46,  1.75s/it, loss=0.176, lr=0.0001]
Steps:  59%|█████▉    | 1183/2000 [35:42<23:46,  1.75s/it, loss=0.28, lr=0.0001] 
Steps:  59%|█████▉    | 1184/2000 [35:43<24:33,  1.81s/it, loss=0.28, lr=0.0001]
Steps:  59%|█████▉    | 1184/2000 [35:43<24:33,  1.81s/it, loss=0.509, lr=0.0001]
Steps:  59%|█████▉    | 1184/2000 [35:43<24:33,  1.81s/it, loss=0.186, lr=0.0001]
Steps:  59%|█████▉    | 1184/2000 [35:44<24:33,  1.81s/it, loss=0.104, lr=0.0001]
Steps:  59%|█████▉    | 1184/2000 [35:44<24:33,  1.81s/it, loss=0.434, lr=0.0001]
Steps:  59%|█████▉    | 1185/2000 [35:45<24:07,  1.78s/it, loss=0.434, lr=0.0001]
Steps:  59%|█████▉    | 1185/2000 [35:45<24:07,  1.78s/it, loss=0.218, lr=0.0001]
Steps:  59%|█████▉    | 1185/2000 [35:45<24:07,  1.78s/it, loss=0.14, lr=0.0001] 
Steps:  59%|█████▉    | 1185/2000 [35:45<24:07,  1.78s/it, loss=0.2, lr=0.0001] 
Steps:  59%|█████▉    | 1185/2000 [35:46<24:07,  1.78s/it, loss=0.269, lr=0.0001]
Steps:  59%|█████▉    | 1186/2000 [35:46<23:43,  1.75s/it, loss=0.269, lr=0.0001]
Steps:  59%|█████▉    | 1186/2000 [35:46<23:43,  1.75s/it, loss=0.114, lr=0.0001]
Steps:  59%|█████▉    | 1186/2000 [35:47<23:43,  1.75s/it, loss=0.232, lr=0.0001]
Steps:  59%|█████▉    | 1186/2000 [35:47<23:43,  1.75s/it, loss=0.0811, lr=0.0001]
Steps:  59%|█████▉    | 1186/2000 [35:48<23:43,  1.75s/it, loss=0.1, lr=0.0001]   
Steps:  59%|█████▉    | 1187/2000 [35:48<24:41,  1.82s/it, loss=0.1, lr=0.0001]
Steps:  59%|█████▉    | 1187/2000 [35:48<24:41,  1.82s/it, loss=0.289, lr=0.0001]
Steps:  59%|█████▉    | 1187/2000 [35:49<24:41,  1.82s/it, loss=0.198, lr=0.0001]
Steps:  59%|█████▉    | 1187/2000 [35:49<24:41,  1.82s/it, loss=0.0694, lr=0.0001]
Steps:  59%|█████▉    | 1187/2000 [35:50<24:41,  1.82s/it, loss=0.15, lr=0.0001]  
Steps:  59%|█████▉    | 1188/2000 [35:50<24:11,  1.79s/it, loss=0.15, lr=0.0001]
Steps:  59%|█████▉    | 1188/2000 [35:50<24:11,  1.79s/it, loss=0.129, lr=0.0001]
Steps:  59%|█████▉    | 1188/2000 [35:50<24:11,  1.79s/it, loss=0.196, lr=0.0001]
Steps:  59%|█████▉    | 1188/2000 [35:51<24:11,  1.79s/it, loss=0.159, lr=0.0001]
Steps:  59%|█████▉    | 1188/2000 [35:51<24:11,  1.79s/it, loss=0.229, lr=0.0001]
Steps:  59%|█████▉    | 1189/2000 [35:52<23:33,  1.74s/it, loss=0.229, lr=0.0001]
Steps:  59%|█████▉    | 1189/2000 [35:52<23:33,  1.74s/it, loss=0.356, lr=0.0001]
Steps:  59%|█████▉    | 1189/2000 [35:52<23:33,  1.74s/it, loss=0.132, lr=0.0001]
Steps:  59%|█████▉    | 1189/2000 [35:52<23:33,  1.74s/it, loss=0.197, lr=0.0001]
Steps:  59%|█████▉    | 1189/2000 [35:53<23:33,  1.74s/it, loss=0.352, lr=0.0001]
Steps:  60%|█████▉    | 1190/2000 [35:54<24:11,  1.79s/it, loss=0.352, lr=0.0001]
Steps:  60%|█████▉    | 1190/2000 [35:54<24:11,  1.79s/it, loss=0.145, lr=0.0001]
Steps:  60%|█████▉    | 1190/2000 [35:54<24:11,  1.79s/it, loss=0.191, lr=0.0001]
Steps:  60%|█████▉    | 1190/2000 [35:54<24:11,  1.79s/it, loss=0.624, lr=0.0001]
Steps:  60%|█████▉    | 1190/2000 [35:55<24:11,  1.79s/it, loss=0.16, lr=0.0001] 
Steps:  60%|█████▉    | 1191/2000 [35:55<23:33,  1.75s/it, loss=0.16, lr=0.0001]
Steps:  60%|█████▉    | 1191/2000 [35:55<23:33,  1.75s/it, loss=0.11, lr=0.0001]
Steps:  60%|█████▉    | 1191/2000 [35:56<23:33,  1.75s/it, loss=0.154, lr=0.0001]
Steps:  60%|█████▉    | 1191/2000 [35:56<23:33,  1.75s/it, loss=0.174, lr=0.0001]
Steps:  60%|█████▉    | 1191/2000 [35:56<23:33,  1.75s/it, loss=0.152, lr=0.0001]
Steps:  60%|█████▉    | 1192/2000 [35:57<23:08,  1.72s/it, loss=0.152, lr=0.0001]
Steps:  60%|█████▉    | 1192/2000 [35:57<23:08,  1.72s/it, loss=0.108, lr=0.0001]
Steps:  60%|█████▉    | 1192/2000 [35:57<23:08,  1.72s/it, loss=0.169, lr=0.0001]
Steps:  60%|█████▉    | 1192/2000 [35:58<23:08,  1.72s/it, loss=0.166, lr=0.0001]
Steps:  60%|█████▉    | 1192/2000 [35:58<23:08,  1.72s/it, loss=0.163, lr=0.0001]
Steps:  60%|█████▉    | 1193/2000 [35:59<23:41,  1.76s/it, loss=0.163, lr=0.0001]
Steps:  60%|█████▉    | 1193/2000 [35:59<23:41,  1.76s/it, loss=0.191, lr=0.0001]
Steps:  60%|█████▉    | 1193/2000 [35:59<23:41,  1.76s/it, loss=0.411, lr=0.0001]
Steps:  60%|█████▉    | 1193/2000 [36:00<23:41,  1.76s/it, loss=0.107, lr=0.0001]
Steps:  60%|█████▉    | 1193/2000 [36:00<23:41,  1.76s/it, loss=0.629, lr=0.0001]
Steps:  60%|█████▉    | 1194/2000 [36:00<23:24,  1.74s/it, loss=0.629, lr=0.0001]
Steps:  60%|█████▉    | 1194/2000 [36:00<23:24,  1.74s/it, loss=0.194, lr=0.0001]
Steps:  60%|█████▉    | 1194/2000 [36:01<23:24,  1.74s/it, loss=0.149, lr=0.0001]
Steps:  60%|█████▉    | 1194/2000 [36:01<23:24,  1.74s/it, loss=0.171, lr=0.0001]
Steps:  60%|█████▉    | 1194/2000 [36:02<23:24,  1.74s/it, loss=0.202, lr=0.0001]
Steps:  60%|█████▉    | 1195/2000 [36:02<23:02,  1.72s/it, loss=0.202, lr=0.0001]
Steps:  60%|█████▉    | 1195/2000 [36:02<23:02,  1.72s/it, loss=0.651, lr=0.0001]
Steps:  60%|█████▉    | 1195/2000 [36:02<23:02,  1.72s/it, loss=0.129, lr=0.0001]
Steps:  60%|█████▉    | 1195/2000 [36:03<23:02,  1.72s/it, loss=0.246, lr=0.0001]
Steps:  60%|█████▉    | 1195/2000 [36:03<23:02,  1.72s/it, loss=0.155, lr=0.0001]
Steps:  60%|█████▉    | 1196/2000 [36:04<22:40,  1.69s/it, loss=0.155, lr=0.0001]
Steps:  60%|█████▉    | 1196/2000 [36:04<22:40,  1.69s/it, loss=0.45, lr=0.0001] 
Steps:  60%|█████▉    | 1196/2000 [36:04<22:40,  1.69s/it, loss=0.633, lr=0.0001]
Steps:  60%|█████▉    | 1196/2000 [36:05<22:40,  1.69s/it, loss=0.144, lr=0.0001]
Steps:  60%|█████▉    | 1196/2000 [36:05<22:40,  1.69s/it, loss=0.157, lr=0.0001]
Steps:  60%|█████▉    | 1197/2000 [36:06<23:31,  1.76s/it, loss=0.157, lr=0.0001]
Steps:  60%|█████▉    | 1197/2000 [36:06<23:31,  1.76s/it, loss=0.141, lr=0.0001]
Steps:  60%|█████▉    | 1197/2000 [36:06<23:31,  1.76s/it, loss=0.0498, lr=0.0001]
Steps:  60%|█████▉    | 1197/2000 [36:06<23:31,  1.76s/it, loss=0.188, lr=0.0001] 
Steps:  60%|█████▉    | 1197/2000 [36:07<23:31,  1.76s/it, loss=0.0897, lr=0.0001]
Steps:  60%|█████▉    | 1198/2000 [36:07<23:03,  1.73s/it, loss=0.0897, lr=0.0001]
Steps:  60%|█████▉    | 1198/2000 [36:07<23:03,  1.73s/it, loss=0.198, lr=0.0001] 
Steps:  60%|█████▉    | 1198/2000 [36:08<23:03,  1.73s/it, loss=0.219, lr=0.0001]
Steps:  60%|█████▉    | 1198/2000 [36:08<23:03,  1.73s/it, loss=0.163, lr=0.0001]
Steps:  60%|█████▉    | 1198/2000 [36:08<23:03,  1.73s/it, loss=0.208, lr=0.0001]
Steps:  60%|█████▉    | 1199/2000 [36:09<22:46,  1.71s/it, loss=0.208, lr=0.0001]
Steps:  60%|█████▉    | 1199/2000 [36:09<22:46,  1.71s/it, loss=0.179, lr=0.0001]
Steps:  60%|█████▉    | 1199/2000 [36:10<22:46,  1.71s/it, loss=0.584, lr=0.0001]
Steps:  60%|█████▉    | 1199/2000 [36:10<22:46,  1.71s/it, loss=0.08, lr=0.0001] 
Steps:  60%|█████▉    | 1199/2000 [36:10<22:46,  1.71s/it, loss=0.268, lr=0.0001]
Steps:  60%|██████    | 1200/2000 [36:11<23:31,  1.76s/it, loss=0.268, lr=0.0001]
Steps:  60%|██████    | 1200/2000 [36:11<23:31,  1.76s/it, loss=0.736, lr=0.0001]
Steps:  60%|██████    | 1200/2000 [36:11<23:31,  1.76s/it, loss=0.224, lr=0.0001]
Steps:  60%|██████    | 1200/2000 [36:12<23:31,  1.76s/it, loss=0.173, lr=0.0001]
Steps:  60%|██████    | 1200/2000 [36:12<23:31,  1.76s/it, loss=0.0823, lr=0.0001]
Steps:  60%|██████    | 1201/2000 [36:12<23:02,  1.73s/it, loss=0.0823, lr=0.0001]
Steps:  60%|██████    | 1201/2000 [36:12<23:02,  1.73s/it, loss=0.132, lr=0.0001] 
Steps:  60%|██████    | 1201/2000 [36:13<23:02,  1.73s/it, loss=0.946, lr=0.0001]
Steps:  60%|██████    | 1201/2000 [36:13<23:02,  1.73s/it, loss=0.101, lr=0.0001]
Steps:  60%|██████    | 1201/2000 [36:14<23:02,  1.73s/it, loss=0.221, lr=0.0001]
Steps:  60%|██████    | 1202/2000 [36:14<22:40,  1.70s/it, loss=0.221, lr=0.0001]
Steps:  60%|██████    | 1202/2000 [36:14<22:40,  1.70s/it, loss=0.316, lr=0.0001]
Steps:  60%|██████    | 1202/2000 [36:15<22:40,  1.70s/it, loss=0.124, lr=0.0001]
Steps:  60%|██████    | 1202/2000 [36:15<22:40,  1.70s/it, loss=0.149, lr=0.0001]
Steps:  60%|██████    | 1202/2000 [36:16<22:40,  1.70s/it, loss=0.116, lr=0.0001]
Steps:  60%|██████    | 1203/2000 [36:16<23:20,  1.76s/it, loss=0.116, lr=0.0001]
Steps:  60%|██████    | 1203/2000 [36:16<23:20,  1.76s/it, loss=0.242, lr=0.0001]
Steps:  60%|██████    | 1203/2000 [36:16<23:20,  1.76s/it, loss=0.135, lr=0.0001]
Steps:  60%|██████    | 1203/2000 [36:17<23:20,  1.76s/it, loss=0.195, lr=0.0001]
Steps:  60%|██████    | 1203/2000 [36:17<23:20,  1.76s/it, loss=0.161, lr=0.0001]
Steps:  60%|██████    | 1204/2000 [36:18<22:52,  1.72s/it, loss=0.161, lr=0.0001]
Steps:  60%|██████    | 1204/2000 [36:18<22:52,  1.72s/it, loss=0.197, lr=0.0001]
Steps:  60%|██████    | 1204/2000 [36:18<22:52,  1.72s/it, loss=0.133, lr=0.0001]
Steps:  60%|██████    | 1204/2000 [36:18<22:52,  1.72s/it, loss=0.193, lr=0.0001]
Steps:  60%|██████    | 1204/2000 [36:19<22:52,  1.72s/it, loss=0.0944, lr=0.0001]
Steps:  60%|██████    | 1205/2000 [36:19<22:32,  1.70s/it, loss=0.0944, lr=0.0001]
Steps:  60%|██████    | 1205/2000 [36:19<22:32,  1.70s/it, loss=0.28, lr=0.0001]  
Steps:  60%|██████    | 1205/2000 [36:20<22:32,  1.70s/it, loss=0.201, lr=0.0001]
Steps:  60%|██████    | 1205/2000 [36:20<22:32,  1.70s/it, loss=0.164, lr=0.0001]
Steps:  60%|██████    | 1205/2000 [36:21<22:32,  1.70s/it, loss=0.128, lr=0.0001]
Steps:  60%|██████    | 1206/2000 [36:21<23:14,  1.76s/it, loss=0.128, lr=0.0001]
Steps:  60%|██████    | 1206/2000 [36:21<23:14,  1.76s/it, loss=0.26, lr=0.0001] 
Steps:  60%|██████    | 1206/2000 [36:22<23:14,  1.76s/it, loss=0.4, lr=0.0001] 
Steps:  60%|██████    | 1206/2000 [36:22<23:14,  1.76s/it, loss=0.141, lr=0.0001]
Steps:  60%|██████    | 1206/2000 [36:22<23:14,  1.76s/it, loss=0.246, lr=0.0001]
Steps:  60%|██████    | 1207/2000 [36:23<22:59,  1.74s/it, loss=0.246, lr=0.0001]
Steps:  60%|██████    | 1207/2000 [36:23<22:59,  1.74s/it, loss=0.199, lr=0.0001]
Steps:  60%|██████    | 1207/2000 [36:23<22:59,  1.74s/it, loss=0.761, lr=0.0001]
Steps:  60%|██████    | 1207/2000 [36:24<22:59,  1.74s/it, loss=0.119, lr=0.0001]
Steps:  60%|██████    | 1207/2000 [36:24<22:59,  1.74s/it, loss=0.0707, lr=0.0001]
Steps:  60%|██████    | 1208/2000 [36:25<22:37,  1.71s/it, loss=0.0707, lr=0.0001]
Steps:  60%|██████    | 1208/2000 [36:25<22:37,  1.71s/it, loss=0.159, lr=0.0001] 
Steps:  60%|██████    | 1208/2000 [36:25<22:37,  1.71s/it, loss=0.201, lr=0.0001]
Steps:  60%|██████    | 1208/2000 [36:25<22:37,  1.71s/it, loss=0.163, lr=0.0001]
Steps:  60%|██████    | 1208/2000 [36:26<22:37,  1.71s/it, loss=0.235, lr=0.0001]
Steps:  60%|██████    | 1209/2000 [36:26<23:14,  1.76s/it, loss=0.235, lr=0.0001]
Steps:  60%|██████    | 1209/2000 [36:26<23:14,  1.76s/it, loss=0.127, lr=0.0001]
Steps:  60%|██████    | 1209/2000 [36:27<23:14,  1.76s/it, loss=0.208, lr=0.0001]
Steps:  60%|██████    | 1209/2000 [36:27<23:14,  1.76s/it, loss=0.112, lr=0.0001]
Steps:  60%|██████    | 1209/2000 [36:28<23:14,  1.76s/it, loss=0.161, lr=0.0001]
Steps:  60%|██████    | 1210/2000 [36:28<22:48,  1.73s/it, loss=0.161, lr=0.0001]
Steps:  60%|██████    | 1210/2000 [36:28<22:48,  1.73s/it, loss=0.104, lr=0.0001]
Steps:  60%|██████    | 1210/2000 [36:28<22:48,  1.73s/it, loss=0.212, lr=0.0001]
Steps:  60%|██████    | 1210/2000 [36:29<22:48,  1.73s/it, loss=0.0259, lr=0.0001]
Steps:  60%|██████    | 1210/2000 [36:29<22:48,  1.73s/it, loss=0.294, lr=0.0001] 
Steps:  61%|██████    | 1211/2000 [36:30<22:32,  1.71s/it, loss=0.294, lr=0.0001]
Steps:  61%|██████    | 1211/2000 [36:30<22:32,  1.71s/it, loss=0.394, lr=0.0001]
Steps:  61%|██████    | 1211/2000 [36:30<22:32,  1.71s/it, loss=0.283, lr=0.0001]
Steps:  61%|██████    | 1211/2000 [36:31<22:32,  1.71s/it, loss=0.104, lr=0.0001]
Steps:  61%|██████    | 1211/2000 [36:31<22:32,  1.71s/it, loss=0.192, lr=0.0001]
Steps:  61%|██████    | 1212/2000 [36:32<23:16,  1.77s/it, loss=0.192, lr=0.0001]
Steps:  61%|██████    | 1212/2000 [36:32<23:16,  1.77s/it, loss=0.202, lr=0.0001]
Steps:  61%|██████    | 1212/2000 [36:32<23:16,  1.77s/it, loss=0.128, lr=0.0001]
Steps:  61%|██████    | 1212/2000 [36:32<23:16,  1.77s/it, loss=0.124, lr=0.0001]
Steps:  61%|██████    | 1212/2000 [36:33<23:16,  1.77s/it, loss=0.147, lr=0.0001]
Steps:  61%|██████    | 1213/2000 [36:33<22:46,  1.74s/it, loss=0.147, lr=0.0001]
Steps:  61%|██████    | 1213/2000 [36:33<22:46,  1.74s/it, loss=0.159, lr=0.0001]
Steps:  61%|██████    | 1213/2000 [36:34<22:46,  1.74s/it, loss=0.229, lr=0.0001]
Steps:  61%|██████    | 1213/2000 [36:34<22:46,  1.74s/it, loss=0.154, lr=0.0001]
Steps:  61%|██████    | 1213/2000 [36:35<22:46,  1.74s/it, loss=0.232, lr=0.0001]
Steps:  61%|██████    | 1214/2000 [36:35<22:37,  1.73s/it, loss=0.232, lr=0.0001]
Steps:  61%|██████    | 1214/2000 [36:35<22:37,  1.73s/it, loss=0.11, lr=0.0001] 
Steps:  61%|██████    | 1214/2000 [36:35<22:37,  1.73s/it, loss=0.0505, lr=0.0001]
Steps:  61%|██████    | 1214/2000 [36:36<22:37,  1.73s/it, loss=0.174, lr=0.0001] 
Steps:  61%|██████    | 1214/2000 [36:36<22:37,  1.73s/it, loss=0.0983, lr=0.0001]
Steps:  61%|██████    | 1215/2000 [36:37<23:13,  1.77s/it, loss=0.0983, lr=0.0001]
Steps:  61%|██████    | 1215/2000 [36:37<23:13,  1.77s/it, loss=0.157, lr=0.0001] 
Steps:  61%|██████    | 1215/2000 [36:37<23:13,  1.77s/it, loss=0.131, lr=0.0001]
Steps:  61%|██████    | 1215/2000 [36:38<23:13,  1.77s/it, loss=0.138, lr=0.0001]
Steps:  61%|██████    | 1215/2000 [36:38<23:13,  1.77s/it, loss=0.36, lr=0.0001] 
Steps:  61%|██████    | 1216/2000 [36:39<22:47,  1.74s/it, loss=0.36, lr=0.0001]
Steps:  61%|██████    | 1216/2000 [36:39<22:47,  1.74s/it, loss=0.215, lr=0.0001]
Steps:  61%|██████    | 1216/2000 [36:39<22:47,  1.74s/it, loss=0.218, lr=0.0001]
Steps:  61%|██████    | 1216/2000 [36:39<22:47,  1.74s/it, loss=0.206, lr=0.0001]
Steps:  61%|██████    | 1216/2000 [36:40<22:47,  1.74s/it, loss=0.139, lr=0.0001]
Steps:  61%|██████    | 1217/2000 [36:40<22:32,  1.73s/it, loss=0.139, lr=0.0001]
Steps:  61%|██████    | 1217/2000 [36:40<22:32,  1.73s/it, loss=0.209, lr=0.0001]
Steps:  61%|██████    | 1217/2000 [36:41<22:32,  1.73s/it, loss=0.1, lr=0.0001]  
Steps:  61%|██████    | 1217/2000 [36:41<22:32,  1.73s/it, loss=0.14, lr=0.0001]
Steps:  61%|██████    | 1217/2000 [36:41<22:32,  1.73s/it, loss=0.109, lr=0.0001]
Steps:  61%|██████    | 1218/2000 [36:42<22:19,  1.71s/it, loss=0.109, lr=0.0001]
Steps:  61%|██████    | 1218/2000 [36:42<22:19,  1.71s/it, loss=0.0836, lr=0.0001]
Steps:  61%|██████    | 1218/2000 [36:43<22:19,  1.71s/it, loss=0.0796, lr=0.0001]
Steps:  61%|██████    | 1218/2000 [36:43<22:19,  1.71s/it, loss=0.161, lr=0.0001] 
Steps:  61%|██████    | 1218/2000 [36:43<22:19,  1.71s/it, loss=0.307, lr=0.0001]
Steps:  61%|██████    | 1219/2000 [36:44<22:58,  1.77s/it, loss=0.307, lr=0.0001]
Steps:  61%|██████    | 1219/2000 [36:44<22:58,  1.77s/it, loss=0.0868, lr=0.0001]
Steps:  61%|██████    | 1219/2000 [36:44<22:58,  1.77s/it, loss=0.099, lr=0.0001] 
Steps:  61%|██████    | 1219/2000 [36:45<22:58,  1.77s/it, loss=0.172, lr=0.0001]
Steps:  61%|██████    | 1219/2000 [36:45<22:58,  1.77s/it, loss=0.144, lr=0.0001]
Steps:  61%|██████    | 1220/2000 [36:45<22:30,  1.73s/it, loss=0.144, lr=0.0001]
Steps:  61%|██████    | 1220/2000 [36:45<22:30,  1.73s/it, loss=0.25, lr=0.0001] 
Steps:  61%|██████    | 1220/2000 [36:46<22:30,  1.73s/it, loss=0.159, lr=0.0001]
Steps:  61%|██████    | 1220/2000 [36:46<22:30,  1.73s/it, loss=0.13, lr=0.0001] 
Steps:  61%|██████    | 1220/2000 [36:47<22:30,  1.73s/it, loss=0.254, lr=0.0001]
Steps:  61%|██████    | 1221/2000 [36:47<22:13,  1.71s/it, loss=0.254, lr=0.0001]
Steps:  61%|██████    | 1221/2000 [36:47<22:13,  1.71s/it, loss=0.227, lr=0.0001]
Steps:  61%|██████    | 1221/2000 [36:48<22:13,  1.71s/it, loss=0.413, lr=0.0001]
Steps:  61%|██████    | 1221/2000 [36:48<22:13,  1.71s/it, loss=0.13, lr=0.0001] 
Steps:  61%|██████    | 1221/2000 [36:49<22:13,  1.71s/it, loss=0.138, lr=0.0001]
Steps:  61%|██████    | 1222/2000 [36:49<22:52,  1.76s/it, loss=0.138, lr=0.0001]
Steps:  61%|██████    | 1222/2000 [36:49<22:52,  1.76s/it, loss=0.22, lr=0.0001] 
Steps:  61%|██████    | 1222/2000 [36:49<22:52,  1.76s/it, loss=0.181, lr=0.0001]
Steps:  61%|██████    | 1222/2000 [36:50<22:52,  1.76s/it, loss=0.131, lr=0.0001]
Steps:  61%|██████    | 1222/2000 [36:50<22:52,  1.76s/it, loss=0.145, lr=0.0001]
Steps:  61%|██████    | 1223/2000 [36:51<22:23,  1.73s/it, loss=0.145, lr=0.0001]
Steps:  61%|██████    | 1223/2000 [36:51<22:23,  1.73s/it, loss=0.421, lr=0.0001]
Steps:  61%|██████    | 1223/2000 [36:51<22:23,  1.73s/it, loss=0.147, lr=0.0001]
Steps:  61%|██████    | 1223/2000 [36:51<22:23,  1.73s/it, loss=0.187, lr=0.0001]
Steps:  61%|██████    | 1223/2000 [36:52<22:23,  1.73s/it, loss=0.215, lr=0.0001]
Steps:  61%|██████    | 1224/2000 [36:52<22:04,  1.71s/it, loss=0.215, lr=0.0001]
Steps:  61%|██████    | 1224/2000 [36:52<22:04,  1.71s/it, loss=0.181, lr=0.0001]
Steps:  61%|██████    | 1224/2000 [36:53<22:04,  1.71s/it, loss=0.107, lr=0.0001]
Steps:  61%|██████    | 1224/2000 [36:53<22:04,  1.71s/it, loss=0.482, lr=0.0001]
Steps:  61%|██████    | 1224/2000 [36:54<22:04,  1.71s/it, loss=0.544, lr=0.0001]
Steps:  61%|██████▏   | 1225/2000 [36:54<22:45,  1.76s/it, loss=0.544, lr=0.0001]
Steps:  61%|██████▏   | 1225/2000 [36:54<22:45,  1.76s/it, loss=0.182, lr=0.0001]
Steps:  61%|██████▏   | 1225/2000 [36:55<22:45,  1.76s/it, loss=0.301, lr=0.0001]
Steps:  61%|██████▏   | 1225/2000 [36:55<22:45,  1.76s/it, loss=0.124, lr=0.0001]
Steps:  61%|██████▏   | 1225/2000 [36:55<22:45,  1.76s/it, loss=0.432, lr=0.0001]
Steps:  61%|██████▏   | 1226/2000 [36:56<22:17,  1.73s/it, loss=0.432, lr=0.0001]
Steps:  61%|██████▏   | 1226/2000 [36:56<22:17,  1.73s/it, loss=0.167, lr=0.0001]
Steps:  61%|██████▏   | 1226/2000 [36:56<22:17,  1.73s/it, loss=0.13, lr=0.0001] 
Steps:  61%|██████▏   | 1226/2000 [36:57<22:17,  1.73s/it, loss=0.21, lr=0.0001]
Steps:  61%|██████▏   | 1226/2000 [36:57<22:17,  1.73s/it, loss=0.237, lr=0.0001]
Steps:  61%|██████▏   | 1227/2000 [36:58<21:57,  1.70s/it, loss=0.237, lr=0.0001]
Steps:  61%|██████▏   | 1227/2000 [36:58<21:57,  1.70s/it, loss=0.149, lr=0.0001]
Steps:  61%|██████▏   | 1227/2000 [36:58<21:57,  1.70s/it, loss=0.247, lr=0.0001]
Steps:  61%|██████▏   | 1227/2000 [36:59<21:57,  1.70s/it, loss=0.164, lr=0.0001]
Steps:  61%|██████▏   | 1227/2000 [36:59<21:57,  1.70s/it, loss=1.06, lr=0.0001] 
Steps:  61%|██████▏   | 1228/2000 [36:59<22:37,  1.76s/it, loss=1.06, lr=0.0001]
Steps:  61%|██████▏   | 1228/2000 [36:59<22:37,  1.76s/it, loss=0.26, lr=0.0001]
Steps:  61%|██████▏   | 1228/2000 [37:00<22:37,  1.76s/it, loss=0.118, lr=0.0001]
Steps:  61%|██████▏   | 1228/2000 [37:00<22:37,  1.76s/it, loss=0.204, lr=0.0001]
Steps:  61%|██████▏   | 1228/2000 [37:01<22:37,  1.76s/it, loss=0.106, lr=0.0001]
Steps:  61%|██████▏   | 1229/2000 [37:01<22:16,  1.73s/it, loss=0.106, lr=0.0001]
Steps:  61%|██████▏   | 1229/2000 [37:01<22:16,  1.73s/it, loss=0.849, lr=0.0001]
Steps:  61%|██████▏   | 1229/2000 [37:01<22:16,  1.73s/it, loss=0.327, lr=0.0001]
Steps:  61%|██████▏   | 1229/2000 [37:02<22:16,  1.73s/it, loss=0.147, lr=0.0001]
Steps:  61%|██████▏   | 1229/2000 [37:02<22:16,  1.73s/it, loss=0.912, lr=0.0001]
Steps:  62%|██████▏   | 1230/2000 [37:03<21:57,  1.71s/it, loss=0.912, lr=0.0001]
Steps:  62%|██████▏   | 1230/2000 [37:03<21:57,  1.71s/it, loss=0.106, lr=0.0001]
Steps:  62%|██████▏   | 1230/2000 [37:03<21:57,  1.71s/it, loss=0.275, lr=0.0001]
Steps:  62%|██████▏   | 1230/2000 [37:04<21:57,  1.71s/it, loss=0.181, lr=0.0001]
Steps:  62%|██████▏   | 1230/2000 [37:04<21:57,  1.71s/it, loss=0.0695, lr=0.0001]
Steps:  62%|██████▏   | 1231/2000 [37:05<22:43,  1.77s/it, loss=0.0695, lr=0.0001]
Steps:  62%|██████▏   | 1231/2000 [37:05<22:43,  1.77s/it, loss=0.196, lr=0.0001] 
Steps:  62%|██████▏   | 1231/2000 [37:05<22:43,  1.77s/it, loss=0.624, lr=0.0001]
Steps:  62%|██████▏   | 1231/2000 [37:05<22:43,  1.77s/it, loss=0.186, lr=0.0001]
Steps:  62%|██████▏   | 1231/2000 [37:06<22:43,  1.77s/it, loss=0.211, lr=0.0001]
Steps:  62%|██████▏   | 1232/2000 [37:06<22:22,  1.75s/it, loss=0.211, lr=0.0001]
Steps:  62%|██████▏   | 1232/2000 [37:06<22:22,  1.75s/it, loss=0.164, lr=0.0001]
Steps:  62%|██████▏   | 1232/2000 [37:07<22:22,  1.75s/it, loss=0.129, lr=0.0001]
Steps:  62%|██████▏   | 1232/2000 [37:07<22:22,  1.75s/it, loss=0.186, lr=0.0001]
Steps:  62%|██████▏   | 1232/2000 [37:08<22:22,  1.75s/it, loss=0.178, lr=0.0001]
Steps:  62%|██████▏   | 1233/2000 [37:08<22:07,  1.73s/it, loss=0.178, lr=0.0001]
Steps:  62%|██████▏   | 1233/2000 [37:08<22:07,  1.73s/it, loss=0.203, lr=0.0001]
Steps:  62%|██████▏   | 1233/2000 [37:08<22:07,  1.73s/it, loss=0.131, lr=0.0001]
Steps:  62%|██████▏   | 1233/2000 [37:09<22:07,  1.73s/it, loss=0.173, lr=0.0001]
Steps:  62%|██████▏   | 1233/2000 [37:10<22:07,  1.73s/it, loss=0.173, lr=0.0001]
Steps:  62%|██████▏   | 1234/2000 [37:10<22:51,  1.79s/it, loss=0.173, lr=0.0001]
Steps:  62%|██████▏   | 1234/2000 [37:10<22:51,  1.79s/it, loss=0.194, lr=0.0001]
Steps:  62%|██████▏   | 1234/2000 [37:10<22:51,  1.79s/it, loss=0.175, lr=0.0001]
Steps:  62%|██████▏   | 1234/2000 [37:11<22:51,  1.79s/it, loss=0.152, lr=0.0001]
Steps:  62%|██████▏   | 1234/2000 [37:11<22:51,  1.79s/it, loss=0.156, lr=0.0001]
Steps:  62%|██████▏   | 1235/2000 [37:12<22:17,  1.75s/it, loss=0.156, lr=0.0001]
Steps:  62%|██████▏   | 1235/2000 [37:12<22:17,  1.75s/it, loss=0.395, lr=0.0001]
Steps:  62%|██████▏   | 1235/2000 [37:12<22:17,  1.75s/it, loss=0.233, lr=0.0001]
Steps:  62%|██████▏   | 1235/2000 [37:12<22:17,  1.75s/it, loss=0.163, lr=0.0001]
Steps:  62%|██████▏   | 1235/2000 [37:13<22:17,  1.75s/it, loss=0.583, lr=0.0001]
Steps:  62%|██████▏   | 1236/2000 [37:13<21:54,  1.72s/it, loss=0.583, lr=0.0001]
Steps:  62%|██████▏   | 1236/2000 [37:13<21:54,  1.72s/it, loss=0.153, lr=0.0001]
Steps:  62%|██████▏   | 1236/2000 [37:14<21:54,  1.72s/it, loss=0.219, lr=0.0001]
Steps:  62%|██████▏   | 1236/2000 [37:14<21:54,  1.72s/it, loss=0.218, lr=0.0001]
Steps:  62%|██████▏   | 1236/2000 [37:14<21:54,  1.72s/it, loss=0.143, lr=0.0001]
Steps:  62%|██████▏   | 1237/2000 [37:15<22:30,  1.77s/it, loss=0.143, lr=0.0001]
Steps:  62%|██████▏   | 1237/2000 [37:15<22:30,  1.77s/it, loss=0.16, lr=0.0001] 
Steps:  62%|██████▏   | 1237/2000 [37:16<22:30,  1.77s/it, loss=0.111, lr=0.0001]
Steps:  62%|██████▏   | 1237/2000 [37:16<22:30,  1.77s/it, loss=0.166, lr=0.0001]
Steps:  62%|██████▏   | 1237/2000 [37:16<22:30,  1.77s/it, loss=0.207, lr=0.0001]
Steps:  62%|██████▏   | 1238/2000 [37:17<22:02,  1.74s/it, loss=0.207, lr=0.0001]
Steps:  62%|██████▏   | 1238/2000 [37:17<22:02,  1.74s/it, loss=0.825, lr=0.0001]
Steps:  62%|██████▏   | 1238/2000 [37:17<22:02,  1.74s/it, loss=0.194, lr=0.0001]
Steps:  62%|██████▏   | 1238/2000 [37:18<22:02,  1.74s/it, loss=0.145, lr=0.0001]
Steps:  62%|██████▏   | 1238/2000 [37:18<22:02,  1.74s/it, loss=0.243, lr=0.0001]
Steps:  62%|██████▏   | 1239/2000 [37:18<21:43,  1.71s/it, loss=0.243, lr=0.0001]
Steps:  62%|██████▏   | 1239/2000 [37:18<21:43,  1.71s/it, loss=0.106, lr=0.0001]
Steps:  62%|██████▏   | 1239/2000 [37:19<21:43,  1.71s/it, loss=0.178, lr=0.0001]
Steps:  62%|██████▏   | 1239/2000 [37:19<21:43,  1.71s/it, loss=0.233, lr=0.0001]
Steps:  62%|██████▏   | 1239/2000 [37:20<21:43,  1.71s/it, loss=0.281, lr=0.0001]
Steps:  62%|██████▏   | 1240/2000 [37:20<21:27,  1.69s/it, loss=0.281, lr=0.0001]
Steps:  62%|██████▏   | 1240/2000 [37:20<21:27,  1.69s/it, loss=0.227, lr=0.0001]
Steps:  62%|██████▏   | 1240/2000 [37:21<21:27,  1.69s/it, loss=0.157, lr=0.0001]
Steps:  62%|██████▏   | 1240/2000 [37:21<21:27,  1.69s/it, loss=0.145, lr=0.0001]
Steps:  62%|██████▏   | 1240/2000 [37:22<21:27,  1.69s/it, loss=0.119, lr=0.0001]
Steps:  62%|██████▏   | 1241/2000 [37:22<22:09,  1.75s/it, loss=0.119, lr=0.0001]
Steps:  62%|██████▏   | 1241/2000 [37:22<22:09,  1.75s/it, loss=0.147, lr=0.0001]
Steps:  62%|██████▏   | 1241/2000 [37:22<22:09,  1.75s/it, loss=0.185, lr=0.0001]
Steps:  62%|██████▏   | 1241/2000 [37:23<22:09,  1.75s/it, loss=1.24, lr=0.0001] 
Steps:  62%|██████▏   | 1241/2000 [37:23<22:09,  1.75s/it, loss=0.0971, lr=0.0001]
Steps:  62%|██████▏   | 1242/2000 [37:24<21:47,  1.73s/it, loss=0.0971, lr=0.0001]
Steps:  62%|██████▏   | 1242/2000 [37:24<21:47,  1.73s/it, loss=0.177, lr=0.0001] 
Steps:  62%|██████▏   | 1242/2000 [37:24<21:47,  1.73s/it, loss=0.161, lr=0.0001]
Steps:  62%|██████▏   | 1242/2000 [37:24<21:47,  1.73s/it, loss=0.282, lr=0.0001]
Steps:  62%|██████▏   | 1242/2000 [37:25<21:47,  1.73s/it, loss=0.191, lr=0.0001]
Steps:  62%|██████▏   | 1243/2000 [37:25<21:29,  1.70s/it, loss=0.191, lr=0.0001]
Steps:  62%|██████▏   | 1243/2000 [37:25<21:29,  1.70s/it, loss=0.244, lr=0.0001]
Steps:  62%|██████▏   | 1243/2000 [37:26<21:29,  1.70s/it, loss=0.127, lr=0.0001]
Steps:  62%|██████▏   | 1243/2000 [37:26<21:29,  1.70s/it, loss=0.212, lr=0.0001]
Steps:  62%|██████▏   | 1243/2000 [37:27<21:29,  1.70s/it, loss=0.824, lr=0.0001]
Steps:  62%|██████▏   | 1244/2000 [37:27<22:13,  1.76s/it, loss=0.824, lr=0.0001]
Steps:  62%|██████▏   | 1244/2000 [37:27<22:13,  1.76s/it, loss=0.221, lr=0.0001]
Steps:  62%|██████▏   | 1244/2000 [37:28<22:13,  1.76s/it, loss=0.123, lr=0.0001]
Steps:  62%|██████▏   | 1244/2000 [37:28<22:13,  1.76s/it, loss=0.208, lr=0.0001]
Steps:  62%|██████▏   | 1244/2000 [37:28<22:13,  1.76s/it, loss=0.073, lr=0.0001]
Steps:  62%|██████▏   | 1245/2000 [37:29<21:48,  1.73s/it, loss=0.073, lr=0.0001]
Steps:  62%|██████▏   | 1245/2000 [37:29<21:48,  1.73s/it, loss=0.191, lr=0.0001]
Steps:  62%|██████▏   | 1245/2000 [37:29<21:48,  1.73s/it, loss=0.129, lr=0.0001]
Steps:  62%|██████▏   | 1245/2000 [37:30<21:48,  1.73s/it, loss=0.209, lr=0.0001]
Steps:  62%|██████▏   | 1245/2000 [37:30<21:48,  1.73s/it, loss=0.182, lr=0.0001]
Steps:  62%|██████▏   | 1246/2000 [37:31<21:28,  1.71s/it, loss=0.182, lr=0.0001]
Steps:  62%|██████▏   | 1246/2000 [37:31<21:28,  1.71s/it, loss=0.155, lr=0.0001]
Steps:  62%|██████▏   | 1246/2000 [37:31<21:28,  1.71s/it, loss=0.156, lr=0.0001]
Steps:  62%|██████▏   | 1246/2000 [37:32<21:28,  1.71s/it, loss=0.437, lr=0.0001]
Steps:  62%|██████▏   | 1246/2000 [37:32<21:28,  1.71s/it, loss=0.131, lr=0.0001]
Steps:  62%|██████▏   | 1247/2000 [37:32<22:11,  1.77s/it, loss=0.131, lr=0.0001]
Steps:  62%|██████▏   | 1247/2000 [37:32<22:11,  1.77s/it, loss=0.202, lr=0.0001]
Steps:  62%|██████▏   | 1247/2000 [37:33<22:11,  1.77s/it, loss=0.235, lr=0.0001]
Steps:  62%|██████▏   | 1247/2000 [37:33<22:11,  1.77s/it, loss=0.144, lr=0.0001]
Steps:  62%|██████▏   | 1247/2000 [37:34<22:11,  1.77s/it, loss=0.181, lr=0.0001]
Steps:  62%|██████▏   | 1248/2000 [37:34<21:48,  1.74s/it, loss=0.181, lr=0.0001]
Steps:  62%|██████▏   | 1248/2000 [37:34<21:48,  1.74s/it, loss=0.159, lr=0.0001]
Steps:  62%|██████▏   | 1248/2000 [37:35<21:48,  1.74s/it, loss=0.12, lr=0.0001] 
Steps:  62%|██████▏   | 1248/2000 [37:35<21:48,  1.74s/it, loss=0.159, lr=0.0001]
Steps:  62%|██████▏   | 1248/2000 [37:35<21:48,  1.74s/it, loss=0.138, lr=0.0001]
Steps:  62%|██████▏   | 1249/2000 [37:36<21:31,  1.72s/it, loss=0.138, lr=0.0001]
Steps:  62%|██████▏   | 1249/2000 [37:36<21:31,  1.72s/it, loss=0.153, lr=0.0001]
Steps:  62%|██████▏   | 1249/2000 [37:36<21:31,  1.72s/it, loss=0.147, lr=0.0001]
Steps:  62%|██████▏   | 1249/2000 [37:37<21:31,  1.72s/it, loss=0.986, lr=0.0001]
Steps:  62%|██████▏   | 1249/2000 [37:37<21:31,  1.72s/it, loss=0.201, lr=0.0001]
Steps:  62%|██████▎   | 1250/2000 [37:38<22:07,  1.77s/it, loss=0.201, lr=0.0001]05/30/2026 09:10:03 - INFO - accelerate.accelerator - [RANK 0] Saving current state to /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1250
Model weights saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1250/pytorch_lora_weights.safetensors
05/30/2026 09:10:04 - INFO - accelerate.checkpointing - [RANK 0] Optimizer state saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1250/optimizer.bin
05/30/2026 09:10:04 - INFO - accelerate.checkpointing - [RANK 0] Scheduler state saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1250/scheduler.bin
05/30/2026 09:10:04 - INFO - accelerate.checkpointing - [RANK 0] Sampler state for dataloader 0 saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1250/sampler.bin
05/30/2026 09:10:04 - INFO - accelerate.checkpointing - [RANK 0] Random states saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1250/random_states_0.pkl
05/30/2026 09:10:04 - INFO - __main__ - [RANK 0] Saved state to /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1250

Steps:  62%|██████▎   | 1250/2000 [37:38<22:07,  1.77s/it, loss=0.0868, lr=0.0001]
Steps:  62%|██████▎   | 1250/2000 [37:39<22:07,  1.77s/it, loss=0.0719, lr=0.0001]
Steps:  62%|██████▎   | 1250/2000 [37:39<22:07,  1.77s/it, loss=0.323, lr=0.0001] 
Steps:  62%|██████▎   | 1250/2000 [37:40<22:07,  1.77s/it, loss=0.204, lr=0.0001]
Steps:  63%|██████▎   | 1251/2000 [37:40<24:39,  1.97s/it, loss=0.204, lr=0.0001]
Steps:  63%|██████▎   | 1251/2000 [37:40<24:39,  1.97s/it, loss=0.212, lr=0.0001]
Steps:  63%|██████▎   | 1251/2000 [37:41<24:39,  1.97s/it, loss=0.287, lr=0.0001]
Steps:  63%|██████▎   | 1251/2000 [37:41<24:39,  1.97s/it, loss=0.179, lr=0.0001]
Steps:  63%|██████▎   | 1251/2000 [37:41<24:39,  1.97s/it, loss=0.241, lr=0.0001]
Steps:  63%|██████▎   | 1252/2000 [37:42<23:36,  1.89s/it, loss=0.241, lr=0.0001]
Steps:  63%|██████▎   | 1252/2000 [37:42<23:36,  1.89s/it, loss=0.165, lr=0.0001]
Steps:  63%|██████▎   | 1252/2000 [37:42<23:36,  1.89s/it, loss=0.173, lr=0.0001]
Steps:  63%|██████▎   | 1252/2000 [37:43<23:36,  1.89s/it, loss=0.0956, lr=0.0001]
Steps:  63%|██████▎   | 1252/2000 [37:43<23:36,  1.89s/it, loss=0.17, lr=0.0001]  
Steps:  63%|██████▎   | 1253/2000 [37:44<23:36,  1.90s/it, loss=0.17, lr=0.0001]
Steps:  63%|██████▎   | 1253/2000 [37:44<23:36,  1.90s/it, loss=0.16, lr=0.0001]
Steps:  63%|██████▎   | 1253/2000 [37:44<23:36,  1.90s/it, loss=0.427, lr=0.0001]
Steps:  63%|██████▎   | 1253/2000 [37:45<23:36,  1.90s/it, loss=0.217, lr=0.0001]
Steps:  63%|██████▎   | 1253/2000 [37:45<23:36,  1.90s/it, loss=0.181, lr=0.0001]
Steps:  63%|██████▎   | 1254/2000 [37:45<22:40,  1.82s/it, loss=0.181, lr=0.0001]
Steps:  63%|██████▎   | 1254/2000 [37:45<22:40,  1.82s/it, loss=0.478, lr=0.0001]
Steps:  63%|██████▎   | 1254/2000 [37:46<22:40,  1.82s/it, loss=0.179, lr=0.0001]
Steps:  63%|██████▎   | 1254/2000 [37:46<22:40,  1.82s/it, loss=0.14, lr=0.0001] 
Steps:  63%|██████▎   | 1254/2000 [37:47<22:40,  1.82s/it, loss=0.309, lr=0.0001]
Steps:  63%|██████▎   | 1255/2000 [37:47<22:05,  1.78s/it, loss=0.309, lr=0.0001]
Steps:  63%|██████▎   | 1255/2000 [37:47<22:05,  1.78s/it, loss=0.127, lr=0.0001]
Steps:  63%|██████▎   | 1255/2000 [37:47<22:05,  1.78s/it, loss=0.127, lr=0.0001]
Steps:  63%|██████▎   | 1255/2000 [37:48<22:05,  1.78s/it, loss=0.124, lr=0.0001]
Steps:  63%|██████▎   | 1255/2000 [37:49<22:05,  1.78s/it, loss=0.173, lr=0.0001]
Steps:  63%|██████▎   | 1256/2000 [37:49<22:31,  1.82s/it, loss=0.173, lr=0.0001]
Steps:  63%|██████▎   | 1256/2000 [37:49<22:31,  1.82s/it, loss=0.264, lr=0.0001]
Steps:  63%|██████▎   | 1256/2000 [37:49<22:31,  1.82s/it, loss=0.147, lr=0.0001]
Steps:  63%|██████▎   | 1256/2000 [37:50<22:31,  1.82s/it, loss=0.243, lr=0.0001]
Steps:  63%|██████▎   | 1256/2000 [37:50<22:31,  1.82s/it, loss=0.142, lr=0.0001]
Steps:  63%|██████▎   | 1257/2000 [37:51<21:50,  1.76s/it, loss=0.142, lr=0.0001]
Steps:  63%|██████▎   | 1257/2000 [37:51<21:50,  1.76s/it, loss=0.195, lr=0.0001]
Steps:  63%|██████▎   | 1257/2000 [37:51<21:50,  1.76s/it, loss=0.293, lr=0.0001]
Steps:  63%|██████▎   | 1257/2000 [37:51<21:50,  1.76s/it, loss=0.357, lr=0.0001]
Steps:  63%|██████▎   | 1257/2000 [37:52<21:50,  1.76s/it, loss=0.565, lr=0.0001]
Steps:  63%|██████▎   | 1258/2000 [37:52<21:27,  1.74s/it, loss=0.565, lr=0.0001]
Steps:  63%|██████▎   | 1258/2000 [37:52<21:27,  1.74s/it, loss=0.628, lr=0.0001]
Steps:  63%|██████▎   | 1258/2000 [37:53<21:27,  1.74s/it, loss=0.134, lr=0.0001]
Steps:  63%|██████▎   | 1258/2000 [37:53<21:27,  1.74s/it, loss=0.294, lr=0.0001]
Steps:  63%|██████▎   | 1258/2000 [37:54<21:27,  1.74s/it, loss=0.174, lr=0.0001]
Steps:  63%|██████▎   | 1259/2000 [37:54<22:06,  1.79s/it, loss=0.174, lr=0.0001]
Steps:  63%|██████▎   | 1259/2000 [37:54<22:06,  1.79s/it, loss=0.0675, lr=0.0001]
Steps:  63%|██████▎   | 1259/2000 [37:55<22:06,  1.79s/it, loss=0.799, lr=0.0001] 
Steps:  63%|██████▎   | 1259/2000 [37:55<22:06,  1.79s/it, loss=0.119, lr=0.0001]
Steps:  63%|██████▎   | 1259/2000 [37:55<22:06,  1.79s/it, loss=0.171, lr=0.0001]
Steps:  63%|██████▎   | 1260/2000 [37:56<21:36,  1.75s/it, loss=0.171, lr=0.0001]
Steps:  63%|██████▎   | 1260/2000 [37:56<21:36,  1.75s/it, loss=0.176, lr=0.0001]
Steps:  63%|██████▎   | 1260/2000 [37:56<21:36,  1.75s/it, loss=0.206, lr=0.0001]
Steps:  63%|██████▎   | 1260/2000 [37:57<21:36,  1.75s/it, loss=0.214, lr=0.0001]
Steps:  63%|██████▎   | 1260/2000 [37:57<21:36,  1.75s/it, loss=0.147, lr=0.0001]
Steps:  63%|██████▎   | 1261/2000 [37:58<21:17,  1.73s/it, loss=0.147, lr=0.0001]
Steps:  63%|██████▎   | 1261/2000 [37:58<21:17,  1.73s/it, loss=0.16, lr=0.0001] 
Steps:  63%|██████▎   | 1261/2000 [37:58<21:17,  1.73s/it, loss=0.112, lr=0.0001]
Steps:  63%|██████▎   | 1261/2000 [37:58<21:17,  1.73s/it, loss=0.198, lr=0.0001]
Steps:  63%|██████▎   | 1261/2000 [37:59<21:17,  1.73s/it, loss=0.186, lr=0.0001]
Steps:  63%|██████▎   | 1262/2000 [37:59<21:50,  1.78s/it, loss=0.186, lr=0.0001]
Steps:  63%|██████▎   | 1262/2000 [37:59<21:50,  1.78s/it, loss=0.266, lr=0.0001]
Steps:  63%|██████▎   | 1262/2000 [38:00<21:50,  1.78s/it, loss=0.505, lr=0.0001]
Steps:  63%|██████▎   | 1262/2000 [38:00<21:50,  1.78s/it, loss=0.129, lr=0.0001]
Steps:  63%|██████▎   | 1262/2000 [38:01<21:50,  1.78s/it, loss=0.357, lr=0.0001]
Steps:  63%|██████▎   | 1263/2000 [38:01<21:27,  1.75s/it, loss=0.357, lr=0.0001]
Steps:  63%|██████▎   | 1263/2000 [38:01<21:27,  1.75s/it, loss=0.0337, lr=0.0001]
Steps:  63%|██████▎   | 1263/2000 [38:02<21:27,  1.75s/it, loss=0.0904, lr=0.0001]
Steps:  63%|██████▎   | 1263/2000 [38:02<21:27,  1.75s/it, loss=0.185, lr=0.0001] 
Steps:  63%|██████▎   | 1263/2000 [38:02<21:27,  1.75s/it, loss=1.9, lr=0.0001]  
Steps:  63%|██████▎   | 1264/2000 [38:03<21:06,  1.72s/it, loss=1.9, lr=0.0001]
Steps:  63%|██████▎   | 1264/2000 [38:03<21:06,  1.72s/it, loss=0.0933, lr=0.0001]
Steps:  63%|██████▎   | 1264/2000 [38:03<21:06,  1.72s/it, loss=0.172, lr=0.0001] 
Steps:  63%|██████▎   | 1264/2000 [38:04<21:06,  1.72s/it, loss=0.117, lr=0.0001]
Steps:  63%|██████▎   | 1264/2000 [38:04<21:06,  1.72s/it, loss=1.04, lr=0.0001] 
Steps:  63%|██████▎   | 1265/2000 [38:04<20:46,  1.70s/it, loss=1.04, lr=0.0001]
Steps:  63%|██████▎   | 1265/2000 [38:04<20:46,  1.70s/it, loss=0.209, lr=0.0001]
Steps:  63%|██████▎   | 1265/2000 [38:05<20:46,  1.70s/it, loss=0.145, lr=0.0001]
Steps:  63%|██████▎   | 1265/2000 [38:05<20:46,  1.70s/it, loss=0.197, lr=0.0001]
Steps:  63%|██████▎   | 1265/2000 [38:06<20:46,  1.70s/it, loss=0.0795, lr=0.0001]
Steps:  63%|██████▎   | 1266/2000 [38:06<21:26,  1.75s/it, loss=0.0795, lr=0.0001]
Steps:  63%|██████▎   | 1266/2000 [38:06<21:26,  1.75s/it, loss=1.16, lr=0.0001]  
Steps:  63%|██████▎   | 1266/2000 [38:07<21:26,  1.75s/it, loss=0.354, lr=0.0001]
Steps:  63%|██████▎   | 1266/2000 [38:07<21:26,  1.75s/it, loss=0.239, lr=0.0001]
Steps:  63%|██████▎   | 1266/2000 [38:08<21:26,  1.75s/it, loss=0.168, lr=0.0001]
Steps:  63%|██████▎   | 1267/2000 [38:08<21:02,  1.72s/it, loss=0.168, lr=0.0001]
Steps:  63%|██████▎   | 1267/2000 [38:08<21:02,  1.72s/it, loss=0.431, lr=0.0001]
Steps:  63%|██████▎   | 1267/2000 [38:08<21:02,  1.72s/it, loss=0.133, lr=0.0001]
Steps:  63%|██████▎   | 1267/2000 [38:09<21:02,  1.72s/it, loss=0.379, lr=0.0001]
Steps:  63%|██████▎   | 1267/2000 [38:09<21:02,  1.72s/it, loss=0.61, lr=0.0001] 
Steps:  63%|██████▎   | 1268/2000 [38:10<20:46,  1.70s/it, loss=0.61, lr=0.0001]
Steps:  63%|██████▎   | 1268/2000 [38:10<20:46,  1.70s/it, loss=0.173, lr=0.0001]
Steps:  63%|██████▎   | 1268/2000 [38:10<20:46,  1.70s/it, loss=0.399, lr=0.0001]
Steps:  63%|██████▎   | 1268/2000 [38:11<20:46,  1.70s/it, loss=0.154, lr=0.0001]
Steps:  63%|██████▎   | 1268/2000 [38:11<20:46,  1.70s/it, loss=0.31, lr=0.0001] 
Steps:  63%|██████▎   | 1269/2000 [38:11<21:22,  1.75s/it, loss=0.31, lr=0.0001]
Steps:  63%|██████▎   | 1269/2000 [38:11<21:22,  1.75s/it, loss=0.166, lr=0.0001]
Steps:  63%|██████▎   | 1269/2000 [38:12<21:22,  1.75s/it, loss=0.169, lr=0.0001]
Steps:  63%|██████▎   | 1269/2000 [38:12<21:22,  1.75s/it, loss=0.161, lr=0.0001]
Steps:  63%|██████▎   | 1269/2000 [38:13<21:22,  1.75s/it, loss=0.135, lr=0.0001]
Steps:  64%|██████▎   | 1270/2000 [38:13<20:58,  1.72s/it, loss=0.135, lr=0.0001]
Steps:  64%|██████▎   | 1270/2000 [38:13<20:58,  1.72s/it, loss=0.141, lr=0.0001]
Steps:  64%|██████▎   | 1270/2000 [38:14<20:58,  1.72s/it, loss=0.259, lr=0.0001]
Steps:  64%|██████▎   | 1270/2000 [38:14<20:58,  1.72s/it, loss=0.0761, lr=0.0001]
Steps:  64%|██████▎   | 1270/2000 [38:14<20:58,  1.72s/it, loss=0.168, lr=0.0001] 
Steps:  64%|██████▎   | 1271/2000 [38:15<20:40,  1.70s/it, loss=0.168, lr=0.0001]
Steps:  64%|██████▎   | 1271/2000 [38:15<20:40,  1.70s/it, loss=0.183, lr=0.0001]
Steps:  64%|██████▎   | 1271/2000 [38:15<20:40,  1.70s/it, loss=0.21, lr=0.0001] 
Steps:  64%|██████▎   | 1271/2000 [38:16<20:40,  1.70s/it, loss=0.191, lr=0.0001]
Steps:  64%|██████▎   | 1271/2000 [38:16<20:40,  1.70s/it, loss=0.161, lr=0.0001]
Steps:  64%|██████▎   | 1272/2000 [38:17<21:19,  1.76s/it, loss=0.161, lr=0.0001]
Steps:  64%|██████▎   | 1272/2000 [38:17<21:19,  1.76s/it, loss=0.0964, lr=0.0001]
Steps:  64%|██████▎   | 1272/2000 [38:17<21:19,  1.76s/it, loss=0.425, lr=0.0001] 
Steps:  64%|██████▎   | 1272/2000 [38:18<21:19,  1.76s/it, loss=0.156, lr=0.0001]
Steps:  64%|██████▎   | 1272/2000 [38:18<21:19,  1.76s/it, loss=0.096, lr=0.0001]
Steps:  64%|██████▎   | 1273/2000 [38:18<21:06,  1.74s/it, loss=0.096, lr=0.0001]
Steps:  64%|██████▎   | 1273/2000 [38:18<21:06,  1.74s/it, loss=0.262, lr=0.0001]
Steps:  64%|██████▎   | 1273/2000 [38:19<21:06,  1.74s/it, loss=0.206, lr=0.0001]
Steps:  64%|██████▎   | 1273/2000 [38:19<21:06,  1.74s/it, loss=0.128, lr=0.0001]
Steps:  64%|██████▎   | 1273/2000 [38:20<21:06,  1.74s/it, loss=0.253, lr=0.0001]
Steps:  64%|██████▎   | 1274/2000 [38:20<20:44,  1.71s/it, loss=0.253, lr=0.0001]
Steps:  64%|██████▎   | 1274/2000 [38:20<20:44,  1.71s/it, loss=0.186, lr=0.0001]
Steps:  64%|██████▎   | 1274/2000 [38:20<20:44,  1.71s/it, loss=0.0929, lr=0.0001]
Steps:  64%|██████▎   | 1274/2000 [38:21<20:44,  1.71s/it, loss=0.109, lr=0.0001] 
Steps:  64%|██████▎   | 1274/2000 [38:21<20:44,  1.71s/it, loss=0.157, lr=0.0001]
Steps:  64%|██████▍   | 1275/2000 [38:22<21:21,  1.77s/it, loss=0.157, lr=0.0001]
Steps:  64%|██████▍   | 1275/2000 [38:22<21:21,  1.77s/it, loss=0.195, lr=0.0001]
Steps:  64%|██████▍   | 1275/2000 [38:22<21:21,  1.77s/it, loss=0.238, lr=0.0001]
Steps:  64%|██████▍   | 1275/2000 [38:23<21:21,  1.77s/it, loss=0.222, lr=0.0001]
Steps:  64%|██████▍   | 1275/2000 [38:23<21:21,  1.77s/it, loss=0.0994, lr=0.0001]
Steps:  64%|██████▍   | 1276/2000 [38:24<20:55,  1.73s/it, loss=0.0994, lr=0.0001]
Steps:  64%|██████▍   | 1276/2000 [38:24<20:55,  1.73s/it, loss=0.289, lr=0.0001] 
Steps:  64%|██████▍   | 1276/2000 [38:24<20:55,  1.73s/it, loss=0.547, lr=0.0001]
Steps:  64%|██████▍   | 1276/2000 [38:24<20:55,  1.73s/it, loss=0.112, lr=0.0001]
Steps:  64%|██████▍   | 1276/2000 [38:25<20:55,  1.73s/it, loss=0.126, lr=0.0001]
Steps:  64%|██████▍   | 1277/2000 [38:25<20:36,  1.71s/it, loss=0.126, lr=0.0001]
Steps:  64%|██████▍   | 1277/2000 [38:25<20:36,  1.71s/it, loss=0.131, lr=0.0001]
Steps:  64%|██████▍   | 1277/2000 [38:26<20:36,  1.71s/it, loss=0.231, lr=0.0001]
Steps:  64%|██████▍   | 1277/2000 [38:26<20:36,  1.71s/it, loss=0.188, lr=0.0001]
Steps:  64%|██████▍   | 1277/2000 [38:27<20:36,  1.71s/it, loss=0.129, lr=0.0001]
Steps:  64%|██████▍   | 1278/2000 [38:27<21:11,  1.76s/it, loss=0.129, lr=0.0001]
Steps:  64%|██████▍   | 1278/2000 [38:27<21:11,  1.76s/it, loss=0.186, lr=0.0001]
Steps:  64%|██████▍   | 1278/2000 [38:28<21:11,  1.76s/it, loss=0.142, lr=0.0001]
Steps:  64%|██████▍   | 1278/2000 [38:28<21:11,  1.76s/it, loss=0.125, lr=0.0001]
Steps:  64%|██████▍   | 1278/2000 [38:28<21:11,  1.76s/it, loss=0.188, lr=0.0001]
Steps:  64%|██████▍   | 1279/2000 [38:29<20:54,  1.74s/it, loss=0.188, lr=0.0001]
Steps:  64%|██████▍   | 1279/2000 [38:29<20:54,  1.74s/it, loss=0.188, lr=0.0001]
Steps:  64%|██████▍   | 1279/2000 [38:29<20:54,  1.74s/it, loss=0.189, lr=0.0001]
Steps:  64%|██████▍   | 1279/2000 [38:30<20:54,  1.74s/it, loss=0.139, lr=0.0001]
Steps:  64%|██████▍   | 1279/2000 [38:30<20:54,  1.74s/it, loss=0.175, lr=0.0001]
Steps:  64%|██████▍   | 1280/2000 [38:30<20:37,  1.72s/it, loss=0.175, lr=0.0001]
Steps:  64%|██████▍   | 1280/2000 [38:30<20:37,  1.72s/it, loss=0.33, lr=0.0001] 
Steps:  64%|██████▍   | 1280/2000 [38:31<20:37,  1.72s/it, loss=0.127, lr=0.0001]
Steps:  64%|██████▍   | 1280/2000 [38:31<20:37,  1.72s/it, loss=0.119, lr=0.0001]
Steps:  64%|██████▍   | 1280/2000 [38:32<20:37,  1.72s/it, loss=0.184, lr=0.0001]
Steps:  64%|██████▍   | 1281/2000 [38:32<21:14,  1.77s/it, loss=0.184, lr=0.0001]
Steps:  64%|██████▍   | 1281/2000 [38:32<21:14,  1.77s/it, loss=0.0705, lr=0.0001]
Steps:  64%|██████▍   | 1281/2000 [38:33<21:14,  1.77s/it, loss=0.962, lr=0.0001] 
Steps:  64%|██████▍   | 1281/2000 [38:33<21:14,  1.77s/it, loss=0.929, lr=0.0001]
Steps:  64%|██████▍   | 1281/2000 [38:34<21:14,  1.77s/it, loss=0.229, lr=0.0001]
Steps:  64%|██████▍   | 1282/2000 [38:34<20:47,  1.74s/it, loss=0.229, lr=0.0001]
Steps:  64%|██████▍   | 1282/2000 [38:34<20:47,  1.74s/it, loss=0.397, lr=0.0001]
Steps:  64%|██████▍   | 1282/2000 [38:34<20:47,  1.74s/it, loss=0.164, lr=0.0001]
Steps:  64%|██████▍   | 1282/2000 [38:35<20:47,  1.74s/it, loss=0.0878, lr=0.0001]
Steps:  64%|██████▍   | 1282/2000 [38:35<20:47,  1.74s/it, loss=0.183, lr=0.0001] 
Steps:  64%|██████▍   | 1283/2000 [38:36<20:31,  1.72s/it, loss=0.183, lr=0.0001]
Steps:  64%|██████▍   | 1283/2000 [38:36<20:31,  1.72s/it, loss=0.0957, lr=0.0001]
Steps:  64%|██████▍   | 1283/2000 [38:36<20:31,  1.72s/it, loss=0.235, lr=0.0001] 
Steps:  64%|██████▍   | 1283/2000 [38:37<20:31,  1.72s/it, loss=0.167, lr=0.0001]
Steps:  64%|██████▍   | 1283/2000 [38:37<20:31,  1.72s/it, loss=0.236, lr=0.0001]
Steps:  64%|██████▍   | 1284/2000 [38:37<20:19,  1.70s/it, loss=0.236, lr=0.0001]
Steps:  64%|██████▍   | 1284/2000 [38:37<20:19,  1.70s/it, loss=0.227, lr=0.0001]
Steps:  64%|██████▍   | 1284/2000 [38:38<20:19,  1.70s/it, loss=0.201, lr=0.0001]
Steps:  64%|██████▍   | 1284/2000 [38:38<20:19,  1.70s/it, loss=0.751, lr=0.0001]
Steps:  64%|██████▍   | 1284/2000 [38:39<20:19,  1.70s/it, loss=0.212, lr=0.0001]
Steps:  64%|██████▍   | 1285/2000 [38:39<21:05,  1.77s/it, loss=0.212, lr=0.0001]
Steps:  64%|██████▍   | 1285/2000 [38:39<21:05,  1.77s/it, loss=0.252, lr=0.0001]
Steps:  64%|██████▍   | 1285/2000 [38:40<21:05,  1.77s/it, loss=0.21, lr=0.0001] 
Steps:  64%|██████▍   | 1285/2000 [38:40<21:05,  1.77s/it, loss=0.135, lr=0.0001]
Steps:  64%|██████▍   | 1285/2000 [38:41<21:05,  1.77s/it, loss=0.137, lr=0.0001]
Steps:  64%|██████▍   | 1286/2000 [38:41<20:38,  1.73s/it, loss=0.137, lr=0.0001]
Steps:  64%|██████▍   | 1286/2000 [38:41<20:38,  1.73s/it, loss=0.153, lr=0.0001]
Steps:  64%|██████▍   | 1286/2000 [38:41<20:38,  1.73s/it, loss=1.04, lr=0.0001] 
Steps:  64%|██████▍   | 1286/2000 [38:42<20:38,  1.73s/it, loss=0.634, lr=0.0001]
Steps:  64%|██████▍   | 1286/2000 [38:42<20:38,  1.73s/it, loss=0.294, lr=0.0001]
Steps:  64%|██████▍   | 1287/2000 [38:43<20:22,  1.72s/it, loss=0.294, lr=0.0001]
Steps:  64%|██████▍   | 1287/2000 [38:43<20:22,  1.72s/it, loss=0.0806, lr=0.0001]
Steps:  64%|██████▍   | 1287/2000 [38:43<20:22,  1.72s/it, loss=4.77, lr=0.0001]  
Steps:  64%|██████▍   | 1287/2000 [38:44<20:22,  1.72s/it, loss=0.0627, lr=0.0001]
Steps:  64%|██████▍   | 1287/2000 [38:44<20:22,  1.72s/it, loss=0.154, lr=0.0001] 
Steps:  64%|██████▍   | 1288/2000 [38:44<20:54,  1.76s/it, loss=0.154, lr=0.0001]
Steps:  64%|██████▍   | 1288/2000 [38:44<20:54,  1.76s/it, loss=0.0587, lr=0.0001]
Steps:  64%|██████▍   | 1288/2000 [38:45<20:54,  1.76s/it, loss=0.266, lr=0.0001] 
Steps:  64%|██████▍   | 1288/2000 [38:45<20:54,  1.76s/it, loss=0.187, lr=0.0001]
Steps:  64%|██████▍   | 1288/2000 [38:46<20:54,  1.76s/it, loss=0.523, lr=0.0001]
Steps:  64%|██████▍   | 1289/2000 [38:46<20:31,  1.73s/it, loss=0.523, lr=0.0001]
Steps:  64%|██████▍   | 1289/2000 [38:46<20:31,  1.73s/it, loss=0.236, lr=0.0001]
Steps:  64%|██████▍   | 1289/2000 [38:47<20:31,  1.73s/it, loss=0.0961, lr=0.0001]
Steps:  64%|██████▍   | 1289/2000 [38:47<20:31,  1.73s/it, loss=0.131, lr=0.0001] 
Steps:  64%|██████▍   | 1289/2000 [38:47<20:31,  1.73s/it, loss=0.299, lr=0.0001]
Steps:  64%|██████▍   | 1290/2000 [38:48<20:08,  1.70s/it, loss=0.299, lr=0.0001]
Steps:  64%|██████▍   | 1290/2000 [38:48<20:08,  1.70s/it, loss=0.164, lr=0.0001]
Steps:  64%|██████▍   | 1290/2000 [38:48<20:08,  1.70s/it, loss=0.0597, lr=0.0001]
Steps:  64%|██████▍   | 1290/2000 [38:49<20:08,  1.70s/it, loss=0.187, lr=0.0001] 
Steps:  64%|██████▍   | 1290/2000 [38:49<20:08,  1.70s/it, loss=0.18, lr=0.0001] 
Steps:  65%|██████▍   | 1291/2000 [38:50<20:38,  1.75s/it, loss=0.18, lr=0.0001]
Steps:  65%|██████▍   | 1291/2000 [38:50<20:38,  1.75s/it, loss=0.308, lr=0.0001]
Steps:  65%|██████▍   | 1291/2000 [38:50<20:38,  1.75s/it, loss=0.147, lr=0.0001]
Steps:  65%|██████▍   | 1291/2000 [38:50<20:38,  1.75s/it, loss=0.253, lr=0.0001]
Steps:  65%|██████▍   | 1291/2000 [38:51<20:38,  1.75s/it, loss=0.232, lr=0.0001]
Steps:  65%|██████▍   | 1292/2000 [38:51<20:11,  1.71s/it, loss=0.232, lr=0.0001]
Steps:  65%|██████▍   | 1292/2000 [38:51<20:11,  1.71s/it, loss=0.151, lr=0.0001]
Steps:  65%|██████▍   | 1292/2000 [38:52<20:11,  1.71s/it, loss=0.185, lr=0.0001]
Steps:  65%|██████▍   | 1292/2000 [38:52<20:11,  1.71s/it, loss=0.0956, lr=0.0001]
Steps:  65%|██████▍   | 1292/2000 [38:52<20:11,  1.71s/it, loss=0.135, lr=0.0001] 
Steps:  65%|██████▍   | 1293/2000 [38:53<19:53,  1.69s/it, loss=0.135, lr=0.0001]
Steps:  65%|██████▍   | 1293/2000 [38:53<19:53,  1.69s/it, loss=0.188, lr=0.0001]
Steps:  65%|██████▍   | 1293/2000 [38:53<19:53,  1.69s/it, loss=0.178, lr=0.0001]
Steps:  65%|██████▍   | 1293/2000 [38:54<19:53,  1.69s/it, loss=0.161, lr=0.0001]
Steps:  65%|██████▍   | 1293/2000 [38:54<19:53,  1.69s/it, loss=0.159, lr=0.0001]
Steps:  65%|██████▍   | 1294/2000 [38:55<20:26,  1.74s/it, loss=0.159, lr=0.0001]
Steps:  65%|██████▍   | 1294/2000 [38:55<20:26,  1.74s/it, loss=0.11, lr=0.0001] 
Steps:  65%|██████▍   | 1294/2000 [38:55<20:26,  1.74s/it, loss=0.19, lr=0.0001]
Steps:  65%|██████▍   | 1294/2000 [38:56<20:26,  1.74s/it, loss=0.206, lr=0.0001]
Steps:  65%|██████▍   | 1294/2000 [38:56<20:26,  1.74s/it, loss=0.122, lr=0.0001]
Steps:  65%|██████▍   | 1295/2000 [38:56<20:01,  1.70s/it, loss=0.122, lr=0.0001]
Steps:  65%|██████▍   | 1295/2000 [38:56<20:01,  1.70s/it, loss=0.193, lr=0.0001]
Steps:  65%|██████▍   | 1295/2000 [38:57<20:01,  1.70s/it, loss=0.181, lr=0.0001]
Steps:  65%|██████▍   | 1295/2000 [38:57<20:01,  1.70s/it, loss=0.138, lr=0.0001]
Steps:  65%|██████▍   | 1295/2000 [38:58<20:01,  1.70s/it, loss=0.223, lr=0.0001]
Steps:  65%|██████▍   | 1296/2000 [38:58<19:42,  1.68s/it, loss=0.223, lr=0.0001]
Steps:  65%|██████▍   | 1296/2000 [38:58<19:42,  1.68s/it, loss=0.344, lr=0.0001]
Steps:  65%|██████▍   | 1296/2000 [38:58<19:42,  1.68s/it, loss=0.109, lr=0.0001]
Steps:  65%|██████▍   | 1296/2000 [38:59<19:42,  1.68s/it, loss=1.65, lr=0.0001] 
Steps:  65%|██████▍   | 1296/2000 [38:59<19:42,  1.68s/it, loss=0.17, lr=0.0001]
Steps:  65%|██████▍   | 1297/2000 [39:00<20:16,  1.73s/it, loss=0.17, lr=0.0001]
Steps:  65%|██████▍   | 1297/2000 [39:00<20:16,  1.73s/it, loss=0.16, lr=0.0001]
Steps:  65%|██████▍   | 1297/2000 [39:00<20:16,  1.73s/it, loss=0.773, lr=0.0001]
Steps:  65%|██████▍   | 1297/2000 [39:01<20:16,  1.73s/it, loss=0.105, lr=0.0001]
Steps:  65%|██████▍   | 1297/2000 [39:01<20:16,  1.73s/it, loss=0.333, lr=0.0001]
Steps:  65%|██████▍   | 1298/2000 [39:02<20:00,  1.71s/it, loss=0.333, lr=0.0001]
Steps:  65%|██████▍   | 1298/2000 [39:02<20:00,  1.71s/it, loss=1.03, lr=0.0001] 
Steps:  65%|██████▍   | 1298/2000 [39:02<20:00,  1.71s/it, loss=0.235, lr=0.0001]
Steps:  65%|██████▍   | 1298/2000 [39:02<20:00,  1.71s/it, loss=0.169, lr=0.0001]
Steps:  65%|██████▍   | 1298/2000 [39:03<20:00,  1.71s/it, loss=0.138, lr=0.0001]
Steps:  65%|██████▍   | 1299/2000 [39:03<19:42,  1.69s/it, loss=0.138, lr=0.0001]
Steps:  65%|██████▍   | 1299/2000 [39:03<19:42,  1.69s/it, loss=0.18, lr=0.0001] 
Steps:  65%|██████▍   | 1299/2000 [39:04<19:42,  1.69s/it, loss=0.177, lr=0.0001]
Steps:  65%|██████▍   | 1299/2000 [39:04<19:42,  1.69s/it, loss=0.133, lr=0.0001]
Steps:  65%|██████▍   | 1299/2000 [39:05<19:42,  1.69s/it, loss=0.32, lr=0.0001] 
Steps:  65%|██████▌   | 1300/2000 [39:05<20:20,  1.74s/it, loss=0.32, lr=0.0001]
Steps:  65%|██████▌   | 1300/2000 [39:05<20:20,  1.74s/it, loss=0.331, lr=0.0001]
Steps:  65%|██████▌   | 1300/2000 [39:05<20:20,  1.74s/it, loss=0.31, lr=0.0001] 
Steps:  65%|██████▌   | 1300/2000 [39:06<20:20,  1.74s/it, loss=0.172, lr=0.0001]
Steps:  65%|██████▌   | 1300/2000 [39:06<20:20,  1.74s/it, loss=0.182, lr=0.0001]
Steps:  65%|██████▌   | 1301/2000 [39:07<20:02,  1.72s/it, loss=0.182, lr=0.0001]
Steps:  65%|██████▌   | 1301/2000 [39:07<20:02,  1.72s/it, loss=0.219, lr=0.0001]
Steps:  65%|██████▌   | 1301/2000 [39:07<20:02,  1.72s/it, loss=0.0688, lr=0.0001]
Steps:  65%|██████▌   | 1301/2000 [39:07<20:02,  1.72s/it, loss=0.236, lr=0.0001] 
Steps:  65%|██████▌   | 1301/2000 [39:08<20:02,  1.72s/it, loss=0.199, lr=0.0001]
Steps:  65%|██████▌   | 1302/2000 [39:08<19:40,  1.69s/it, loss=0.199, lr=0.0001]
Steps:  65%|██████▌   | 1302/2000 [39:08<19:40,  1.69s/it, loss=0.145, lr=0.0001]
Steps:  65%|██████▌   | 1302/2000 [39:09<19:40,  1.69s/it, loss=0.262, lr=0.0001]
Steps:  65%|██████▌   | 1302/2000 [39:09<19:40,  1.69s/it, loss=0.182, lr=0.0001]
Steps:  65%|██████▌   | 1302/2000 [39:10<19:40,  1.69s/it, loss=0.152, lr=0.0001]
Steps:  65%|██████▌   | 1303/2000 [39:10<20:14,  1.74s/it, loss=0.152, lr=0.0001]
Steps:  65%|██████▌   | 1303/2000 [39:10<20:14,  1.74s/it, loss=0.221, lr=0.0001]
Steps:  65%|██████▌   | 1303/2000 [39:11<20:14,  1.74s/it, loss=0.236, lr=0.0001]
Steps:  65%|██████▌   | 1303/2000 [39:11<20:14,  1.74s/it, loss=0.189, lr=0.0001]
Steps:  65%|██████▌   | 1303/2000 [39:11<20:14,  1.74s/it, loss=0.253, lr=0.0001]
Steps:  65%|██████▌   | 1304/2000 [39:12<19:49,  1.71s/it, loss=0.253, lr=0.0001]
Steps:  65%|██████▌   | 1304/2000 [39:12<19:49,  1.71s/it, loss=0.182, lr=0.0001]
Steps:  65%|██████▌   | 1304/2000 [39:12<19:49,  1.71s/it, loss=0.293, lr=0.0001]
Steps:  65%|██████▌   | 1304/2000 [39:13<19:49,  1.71s/it, loss=0.202, lr=0.0001]
Steps:  65%|██████▌   | 1304/2000 [39:13<19:49,  1.71s/it, loss=0.178, lr=0.0001]
Steps:  65%|██████▌   | 1305/2000 [39:13<19:30,  1.68s/it, loss=0.178, lr=0.0001]
Steps:  65%|██████▌   | 1305/2000 [39:13<19:30,  1.68s/it, loss=0.177, lr=0.0001]
Steps:  65%|██████▌   | 1305/2000 [39:14<19:30,  1.68s/it, loss=0.209, lr=0.0001]
Steps:  65%|██████▌   | 1305/2000 [39:14<19:30,  1.68s/it, loss=0.317, lr=0.0001]
Steps:  65%|██████▌   | 1305/2000 [39:15<19:30,  1.68s/it, loss=0.112, lr=0.0001]
Steps:  65%|██████▌   | 1306/2000 [39:15<19:31,  1.69s/it, loss=0.112, lr=0.0001]
Steps:  65%|██████▌   | 1306/2000 [39:15<19:31,  1.69s/it, loss=0.22, lr=0.0001] 
Steps:  65%|██████▌   | 1306/2000 [39:16<19:31,  1.69s/it, loss=0.231, lr=0.0001]
Steps:  65%|██████▌   | 1306/2000 [39:16<19:31,  1.69s/it, loss=0.241, lr=0.0001]
Steps:  65%|██████▌   | 1306/2000 [39:17<19:31,  1.69s/it, loss=0.0718, lr=0.0001]
Steps:  65%|██████▌   | 1307/2000 [39:17<20:06,  1.74s/it, loss=0.0718, lr=0.0001]
Steps:  65%|██████▌   | 1307/2000 [39:17<20:06,  1.74s/it, loss=0.14, lr=0.0001]  
Steps:  65%|██████▌   | 1307/2000 [39:17<20:06,  1.74s/it, loss=0.174, lr=0.0001]
Steps:  65%|██████▌   | 1307/2000 [39:18<20:06,  1.74s/it, loss=0.135, lr=0.0001]
Steps:  65%|██████▌   | 1307/2000 [39:18<20:06,  1.74s/it, loss=0.0734, lr=0.0001]
Steps:  65%|██████▌   | 1308/2000 [39:19<19:42,  1.71s/it, loss=0.0734, lr=0.0001]
Steps:  65%|██████▌   | 1308/2000 [39:19<19:42,  1.71s/it, loss=0.272, lr=0.0001] 
Steps:  65%|██████▌   | 1308/2000 [39:19<19:42,  1.71s/it, loss=0.158, lr=0.0001]
Steps:  65%|██████▌   | 1308/2000 [39:19<19:42,  1.71s/it, loss=0.0893, lr=0.0001]
Steps:  65%|██████▌   | 1308/2000 [39:20<19:42,  1.71s/it, loss=0.155, lr=0.0001] 
Steps:  65%|██████▌   | 1309/2000 [39:20<19:25,  1.69s/it, loss=0.155, lr=0.0001]
Steps:  65%|██████▌   | 1309/2000 [39:20<19:25,  1.69s/it, loss=0.19, lr=0.0001] 
Steps:  65%|██████▌   | 1309/2000 [39:21<19:25,  1.69s/it, loss=0.254, lr=0.0001]
Steps:  65%|██████▌   | 1309/2000 [39:21<19:25,  1.69s/it, loss=0.158, lr=0.0001]
Steps:  65%|██████▌   | 1309/2000 [39:22<19:25,  1.69s/it, loss=0.315, lr=0.0001]
Steps:  66%|██████▌   | 1310/2000 [39:22<20:02,  1.74s/it, loss=0.315, lr=0.0001]
Steps:  66%|██████▌   | 1310/2000 [39:22<20:02,  1.74s/it, loss=0.144, lr=0.0001]
Steps:  66%|██████▌   | 1310/2000 [39:23<20:02,  1.74s/it, loss=0.165, lr=0.0001]
Steps:  66%|██████▌   | 1310/2000 [39:23<20:02,  1.74s/it, loss=0.284, lr=0.0001]
Steps:  66%|██████▌   | 1310/2000 [39:23<20:02,  1.74s/it, loss=0.19, lr=0.0001] 
Steps:  66%|██████▌   | 1311/2000 [39:24<19:38,  1.71s/it, loss=0.19, lr=0.0001]
Steps:  66%|██████▌   | 1311/2000 [39:24<19:38,  1.71s/it, loss=0.178, lr=0.0001]
Steps:  66%|██████▌   | 1311/2000 [39:24<19:38,  1.71s/it, loss=0.116, lr=0.0001]
Steps:  66%|██████▌   | 1311/2000 [39:25<19:38,  1.71s/it, loss=0.188, lr=0.0001]
Steps:  66%|██████▌   | 1311/2000 [39:25<19:38,  1.71s/it, loss=0.267, lr=0.0001]
Steps:  66%|██████▌   | 1312/2000 [39:25<19:20,  1.69s/it, loss=0.267, lr=0.0001]
Steps:  66%|██████▌   | 1312/2000 [39:25<19:20,  1.69s/it, loss=0.336, lr=0.0001]
Steps:  66%|██████▌   | 1312/2000 [39:26<19:20,  1.69s/it, loss=0.178, lr=0.0001]
Steps:  66%|██████▌   | 1312/2000 [39:26<19:20,  1.69s/it, loss=0.176, lr=0.0001]
Steps:  66%|██████▌   | 1312/2000 [39:27<19:20,  1.69s/it, loss=0.178, lr=0.0001]
Steps:  66%|██████▌   | 1313/2000 [39:27<19:53,  1.74s/it, loss=0.178, lr=0.0001]
Steps:  66%|██████▌   | 1313/2000 [39:27<19:53,  1.74s/it, loss=0.101, lr=0.0001]
Steps:  66%|██████▌   | 1313/2000 [39:28<19:53,  1.74s/it, loss=0.147, lr=0.0001]
Steps:  66%|██████▌   | 1313/2000 [39:28<19:53,  1.74s/it, loss=0.229, lr=0.0001]
Steps:  66%|██████▌   | 1313/2000 [39:28<19:53,  1.74s/it, loss=0.0862, lr=0.0001]
Steps:  66%|██████▌   | 1314/2000 [39:29<19:32,  1.71s/it, loss=0.0862, lr=0.0001]
Steps:  66%|██████▌   | 1314/2000 [39:29<19:32,  1.71s/it, loss=0.141, lr=0.0001] 
Steps:  66%|██████▌   | 1314/2000 [39:29<19:32,  1.71s/it, loss=0.143, lr=0.0001]
Steps:  66%|██████▌   | 1314/2000 [39:30<19:32,  1.71s/it, loss=0.151, lr=0.0001]
Steps:  66%|██████▌   | 1314/2000 [39:30<19:32,  1.71s/it, loss=0.721, lr=0.0001]
Steps:  66%|██████▌   | 1315/2000 [39:31<19:14,  1.69s/it, loss=0.721, lr=0.0001]
Steps:  66%|██████▌   | 1315/2000 [39:31<19:14,  1.69s/it, loss=0.177, lr=0.0001]
Steps:  66%|██████▌   | 1315/2000 [39:31<19:14,  1.69s/it, loss=0.152, lr=0.0001]
Steps:  66%|██████▌   | 1315/2000 [39:32<19:14,  1.69s/it, loss=0.133, lr=0.0001]
Steps:  66%|██████▌   | 1315/2000 [39:32<19:14,  1.69s/it, loss=0.16, lr=0.0001] 
Steps:  66%|██████▌   | 1316/2000 [39:32<19:49,  1.74s/it, loss=0.16, lr=0.0001]
Steps:  66%|██████▌   | 1316/2000 [39:32<19:49,  1.74s/it, loss=0.135, lr=0.0001]
Steps:  66%|██████▌   | 1316/2000 [39:33<19:49,  1.74s/it, loss=0.226, lr=0.0001]
Steps:  66%|██████▌   | 1316/2000 [39:33<19:49,  1.74s/it, loss=0.58, lr=0.0001] 
Steps:  66%|██████▌   | 1316/2000 [39:34<19:49,  1.74s/it, loss=0.106, lr=0.0001]
Steps:  66%|██████▌   | 1317/2000 [39:34<19:41,  1.73s/it, loss=0.106, lr=0.0001]
Steps:  66%|██████▌   | 1317/2000 [39:34<19:41,  1.73s/it, loss=0.0457, lr=0.0001]
Steps:  66%|██████▌   | 1317/2000 [39:34<19:41,  1.73s/it, loss=0.102, lr=0.0001] 
Steps:  66%|██████▌   | 1317/2000 [39:35<19:41,  1.73s/it, loss=0.145, lr=0.0001]
Steps:  66%|██████▌   | 1317/2000 [39:35<19:41,  1.73s/it, loss=0.268, lr=0.0001]
Steps:  66%|██████▌   | 1318/2000 [39:36<19:21,  1.70s/it, loss=0.268, lr=0.0001]
Steps:  66%|██████▌   | 1318/2000 [39:36<19:21,  1.70s/it, loss=0.131, lr=0.0001]
Steps:  66%|██████▌   | 1318/2000 [39:36<19:21,  1.70s/it, loss=0.165, lr=0.0001]
Steps:  66%|██████▌   | 1318/2000 [39:37<19:21,  1.70s/it, loss=0.0571, lr=0.0001]
Steps:  66%|██████▌   | 1318/2000 [39:37<19:21,  1.70s/it, loss=0.162, lr=0.0001] 
Steps:  66%|██████▌   | 1319/2000 [39:38<19:51,  1.75s/it, loss=0.162, lr=0.0001]
Steps:  66%|██████▌   | 1319/2000 [39:38<19:51,  1.75s/it, loss=0.177, lr=0.0001]
Steps:  66%|██████▌   | 1319/2000 [39:38<19:51,  1.75s/it, loss=0.355, lr=0.0001]
Steps:  66%|██████▌   | 1319/2000 [39:38<19:51,  1.75s/it, loss=0.199, lr=0.0001]
Steps:  66%|██████▌   | 1319/2000 [39:39<19:51,  1.75s/it, loss=0.13, lr=0.0001] 
Steps:  66%|██████▌   | 1320/2000 [39:39<19:25,  1.71s/it, loss=0.13, lr=0.0001]
Steps:  66%|██████▌   | 1320/2000 [39:39<19:25,  1.71s/it, loss=0.249, lr=0.0001]
Steps:  66%|██████▌   | 1320/2000 [39:40<19:25,  1.71s/it, loss=0.222, lr=0.0001]
Steps:  66%|██████▌   | 1320/2000 [39:40<19:25,  1.71s/it, loss=0.233, lr=0.0001]
Steps:  66%|██████▌   | 1320/2000 [39:40<19:25,  1.71s/it, loss=0.354, lr=0.0001]
Steps:  66%|██████▌   | 1321/2000 [39:41<19:16,  1.70s/it, loss=0.354, lr=0.0001]
Steps:  66%|██████▌   | 1321/2000 [39:41<19:16,  1.70s/it, loss=0.104, lr=0.0001]
Steps:  66%|██████▌   | 1321/2000 [39:41<19:16,  1.70s/it, loss=0.195, lr=0.0001]
Steps:  66%|██████▌   | 1321/2000 [39:42<19:16,  1.70s/it, loss=0.18, lr=0.0001] 
Steps:  66%|██████▌   | 1321/2000 [39:42<19:16,  1.70s/it, loss=0.15, lr=0.0001]
Steps:  66%|██████▌   | 1322/2000 [39:43<19:49,  1.75s/it, loss=0.15, lr=0.0001]
Steps:  66%|██████▌   | 1322/2000 [39:43<19:49,  1.75s/it, loss=0.116, lr=0.0001]
Steps:  66%|██████▌   | 1322/2000 [39:43<19:49,  1.75s/it, loss=0.319, lr=0.0001]
Steps:  66%|██████▌   | 1322/2000 [39:44<19:49,  1.75s/it, loss=0.183, lr=0.0001]
Steps:  66%|██████▌   | 1322/2000 [39:44<19:49,  1.75s/it, loss=0.211, lr=0.0001]
Steps:  66%|██████▌   | 1323/2000 [39:44<19:25,  1.72s/it, loss=0.211, lr=0.0001]
Steps:  66%|██████▌   | 1323/2000 [39:44<19:25,  1.72s/it, loss=0.151, lr=0.0001]
Steps:  66%|██████▌   | 1323/2000 [39:45<19:25,  1.72s/it, loss=0.31, lr=0.0001] 
Steps:  66%|██████▌   | 1323/2000 [39:45<19:25,  1.72s/it, loss=0.42, lr=0.0001]
Steps:  66%|██████▌   | 1323/2000 [39:46<19:25,  1.72s/it, loss=0.203, lr=0.0001]
Steps:  66%|██████▌   | 1324/2000 [39:46<19:09,  1.70s/it, loss=0.203, lr=0.0001]
Steps:  66%|██████▌   | 1324/2000 [39:46<19:09,  1.70s/it, loss=0.269, lr=0.0001]
Steps:  66%|██████▌   | 1324/2000 [39:46<19:09,  1.70s/it, loss=0.384, lr=0.0001]
Steps:  66%|██████▌   | 1324/2000 [39:47<19:09,  1.70s/it, loss=0.18, lr=0.0001] 
Steps:  66%|██████▌   | 1324/2000 [39:47<19:09,  1.70s/it, loss=0.0632, lr=0.0001]
Steps:  66%|██████▋   | 1325/2000 [39:48<19:58,  1.78s/it, loss=0.0632, lr=0.0001]
Steps:  66%|██████▋   | 1325/2000 [39:48<19:58,  1.78s/it, loss=0.188, lr=0.0001] 
Steps:  66%|██████▋   | 1325/2000 [39:48<19:58,  1.78s/it, loss=0.249, lr=0.0001]
Steps:  66%|██████▋   | 1325/2000 [39:49<19:58,  1.78s/it, loss=0.221, lr=0.0001]
Steps:  66%|██████▋   | 1325/2000 [39:49<19:58,  1.78s/it, loss=0.217, lr=0.0001]
Steps:  66%|██████▋   | 1326/2000 [39:50<19:31,  1.74s/it, loss=0.217, lr=0.0001]
Steps:  66%|██████▋   | 1326/2000 [39:50<19:31,  1.74s/it, loss=0.118, lr=0.0001]
Steps:  66%|██████▋   | 1326/2000 [39:50<19:31,  1.74s/it, loss=0.153, lr=0.0001]
Steps:  66%|██████▋   | 1326/2000 [39:50<19:31,  1.74s/it, loss=0.175, lr=0.0001]
Steps:  66%|██████▋   | 1326/2000 [39:51<19:31,  1.74s/it, loss=0.131, lr=0.0001]
Steps:  66%|██████▋   | 1327/2000 [39:51<19:11,  1.71s/it, loss=0.131, lr=0.0001]
Steps:  66%|██████▋   | 1327/2000 [39:51<19:11,  1.71s/it, loss=0.207, lr=0.0001]
Steps:  66%|██████▋   | 1327/2000 [39:52<19:11,  1.71s/it, loss=0.164, lr=0.0001]
Steps:  66%|██████▋   | 1327/2000 [39:52<19:11,  1.71s/it, loss=0.133, lr=0.0001]
Steps:  66%|██████▋   | 1327/2000 [39:53<19:11,  1.71s/it, loss=0.221, lr=0.0001]
Steps:  66%|██████▋   | 1328/2000 [39:53<18:57,  1.69s/it, loss=0.221, lr=0.0001]
Steps:  66%|██████▋   | 1328/2000 [39:53<18:57,  1.69s/it, loss=0.2, lr=0.0001]  
Steps:  66%|██████▋   | 1328/2000 [39:54<18:57,  1.69s/it, loss=0.295, lr=0.0001]
Steps:  66%|██████▋   | 1328/2000 [39:54<18:57,  1.69s/it, loss=0.253, lr=0.0001]
Steps:  66%|██████▋   | 1328/2000 [39:54<18:57,  1.69s/it, loss=0.118, lr=0.0001]
Steps:  66%|██████▋   | 1329/2000 [39:55<19:31,  1.75s/it, loss=0.118, lr=0.0001]
Steps:  66%|██████▋   | 1329/2000 [39:55<19:31,  1.75s/it, loss=0.286, lr=0.0001]
Steps:  66%|██████▋   | 1329/2000 [39:55<19:31,  1.75s/it, loss=0.184, lr=0.0001]
Steps:  66%|██████▋   | 1329/2000 [39:56<19:31,  1.75s/it, loss=0.262, lr=0.0001]
Steps:  66%|██████▋   | 1329/2000 [39:56<19:31,  1.75s/it, loss=0.175, lr=0.0001]
Steps:  66%|██████▋   | 1330/2000 [39:56<19:09,  1.72s/it, loss=0.175, lr=0.0001]
Steps:  66%|██████▋   | 1330/2000 [39:56<19:09,  1.72s/it, loss=0.0573, lr=0.0001]
Steps:  66%|██████▋   | 1330/2000 [39:57<19:09,  1.72s/it, loss=0.153, lr=0.0001] 
Steps:  66%|██████▋   | 1330/2000 [39:57<19:09,  1.72s/it, loss=0.347, lr=0.0001]
Steps:  66%|██████▋   | 1330/2000 [39:58<19:09,  1.72s/it, loss=0.073, lr=0.0001]
Steps:  67%|██████▋   | 1331/2000 [39:58<18:53,  1.69s/it, loss=0.073, lr=0.0001]
Steps:  67%|██████▋   | 1331/2000 [39:58<18:53,  1.69s/it, loss=0.14, lr=0.0001] 
Steps:  67%|██████▋   | 1331/2000 [39:59<18:53,  1.69s/it, loss=0.132, lr=0.0001]
Steps:  67%|██████▋   | 1331/2000 [39:59<18:53,  1.69s/it, loss=0.72, lr=0.0001] 
Steps:  67%|██████▋   | 1331/2000 [40:00<18:53,  1.69s/it, loss=1.01, lr=0.0001]
Steps:  67%|██████▋   | 1332/2000 [40:00<19:27,  1.75s/it, loss=1.01, lr=0.0001]
Steps:  67%|██████▋   | 1332/2000 [40:00<19:27,  1.75s/it, loss=0.116, lr=0.0001]
Steps:  67%|██████▋   | 1332/2000 [40:00<19:27,  1.75s/it, loss=0.134, lr=0.0001]
Steps:  67%|██████▋   | 1332/2000 [40:01<19:27,  1.75s/it, loss=0.271, lr=0.0001]
Steps:  67%|██████▋   | 1332/2000 [40:01<19:27,  1.75s/it, loss=0.147, lr=0.0001]
Steps:  67%|██████▋   | 1333/2000 [40:02<19:10,  1.72s/it, loss=0.147, lr=0.0001]
Steps:  67%|██████▋   | 1333/2000 [40:02<19:10,  1.72s/it, loss=0.0932, lr=0.0001]
Steps:  67%|██████▋   | 1333/2000 [40:02<19:10,  1.72s/it, loss=0.124, lr=0.0001] 
Steps:  67%|██████▋   | 1333/2000 [40:02<19:10,  1.72s/it, loss=0.647, lr=0.0001]
Steps:  67%|██████▋   | 1333/2000 [40:03<19:10,  1.72s/it, loss=0.129, lr=0.0001]
Steps:  67%|██████▋   | 1334/2000 [40:03<18:57,  1.71s/it, loss=0.129, lr=0.0001]
Steps:  67%|██████▋   | 1334/2000 [40:03<18:57,  1.71s/it, loss=0.124, lr=0.0001]
Steps:  67%|██████▋   | 1334/2000 [40:04<18:57,  1.71s/it, loss=0.0957, lr=0.0001]
Steps:  67%|██████▋   | 1334/2000 [40:04<18:57,  1.71s/it, loss=0.198, lr=0.0001] 
Steps:  67%|██████▋   | 1334/2000 [40:05<18:57,  1.71s/it, loss=0.229, lr=0.0001]
Steps:  67%|██████▋   | 1335/2000 [40:05<19:31,  1.76s/it, loss=0.229, lr=0.0001]
Steps:  67%|██████▋   | 1335/2000 [40:05<19:31,  1.76s/it, loss=0.137, lr=0.0001]
Steps:  67%|██████▋   | 1335/2000 [40:06<19:31,  1.76s/it, loss=0.176, lr=0.0001]
Steps:  67%|██████▋   | 1335/2000 [40:06<19:31,  1.76s/it, loss=0.159, lr=0.0001]
Steps:  67%|██████▋   | 1335/2000 [40:06<19:31,  1.76s/it, loss=0.56, lr=0.0001] 
Steps:  67%|██████▋   | 1336/2000 [40:07<19:10,  1.73s/it, loss=0.56, lr=0.0001]
Steps:  67%|██████▋   | 1336/2000 [40:07<19:10,  1.73s/it, loss=0.108, lr=0.0001]
Steps:  67%|██████▋   | 1336/2000 [40:07<19:10,  1.73s/it, loss=0.192, lr=0.0001]
Steps:  67%|██████▋   | 1336/2000 [40:08<19:10,  1.73s/it, loss=0.248, lr=0.0001]
Steps:  67%|██████▋   | 1336/2000 [40:08<19:10,  1.73s/it, loss=0.276, lr=0.0001]
Steps:  67%|██████▋   | 1337/2000 [40:09<18:53,  1.71s/it, loss=0.276, lr=0.0001]
Steps:  67%|██████▋   | 1337/2000 [40:09<18:53,  1.71s/it, loss=0.175, lr=0.0001]
Steps:  67%|██████▋   | 1337/2000 [40:09<18:53,  1.71s/it, loss=0.12, lr=0.0001] 
Steps:  67%|██████▋   | 1337/2000 [40:09<18:53,  1.71s/it, loss=0.25, lr=0.0001]
Steps:  67%|██████▋   | 1337/2000 [40:10<18:53,  1.71s/it, loss=0.213, lr=0.0001]
Steps:  67%|██████▋   | 1338/2000 [40:10<19:27,  1.76s/it, loss=0.213, lr=0.0001]
Steps:  67%|██████▋   | 1338/2000 [40:10<19:27,  1.76s/it, loss=0.2, lr=0.0001]  
Steps:  67%|██████▋   | 1338/2000 [40:11<19:27,  1.76s/it, loss=0.163, lr=0.0001]
Steps:  67%|██████▋   | 1338/2000 [40:11<19:27,  1.76s/it, loss=0.0721, lr=0.0001]
Steps:  67%|██████▋   | 1338/2000 [40:12<19:27,  1.76s/it, loss=0.117, lr=0.0001] 
Steps:  67%|██████▋   | 1339/2000 [40:12<19:06,  1.73s/it, loss=0.117, lr=0.0001]
Steps:  67%|██████▋   | 1339/2000 [40:12<19:06,  1.73s/it, loss=0.172, lr=0.0001]
Steps:  67%|██████▋   | 1339/2000 [40:13<19:06,  1.73s/it, loss=0.0492, lr=0.0001]
Steps:  67%|██████▋   | 1339/2000 [40:13<19:06,  1.73s/it, loss=0.133, lr=0.0001] 
Steps:  67%|██████▋   | 1339/2000 [40:13<19:06,  1.73s/it, loss=0.191, lr=0.0001]
Steps:  67%|██████▋   | 1340/2000 [40:14<18:52,  1.72s/it, loss=0.191, lr=0.0001]
Steps:  67%|██████▋   | 1340/2000 [40:14<18:52,  1.72s/it, loss=0.132, lr=0.0001]
Steps:  67%|██████▋   | 1340/2000 [40:14<18:52,  1.72s/it, loss=0.0873, lr=0.0001]
Steps:  67%|██████▋   | 1340/2000 [40:15<18:52,  1.72s/it, loss=0.225, lr=0.0001] 
Steps:  67%|██████▋   | 1340/2000 [40:15<18:52,  1.72s/it, loss=0.121, lr=0.0001]
Steps:  67%|██████▋   | 1341/2000 [40:16<19:29,  1.78s/it, loss=0.121, lr=0.0001]
Steps:  67%|██████▋   | 1341/2000 [40:16<19:29,  1.78s/it, loss=0.194, lr=0.0001]
Steps:  67%|██████▋   | 1341/2000 [40:16<19:29,  1.78s/it, loss=0.0759, lr=0.0001]
Steps:  67%|██████▋   | 1341/2000 [40:16<19:29,  1.78s/it, loss=0.151, lr=0.0001] 
Steps:  67%|██████▋   | 1341/2000 [40:17<19:29,  1.78s/it, loss=0.161, lr=0.0001]
Steps:  67%|██████▋   | 1342/2000 [40:17<19:04,  1.74s/it, loss=0.161, lr=0.0001]
Steps:  67%|██████▋   | 1342/2000 [40:17<19:04,  1.74s/it, loss=0.107, lr=0.0001]
Steps:  67%|██████▋   | 1342/2000 [40:18<19:04,  1.74s/it, loss=0.219, lr=0.0001]
Steps:  67%|██████▋   | 1342/2000 [40:18<19:04,  1.74s/it, loss=0.186, lr=0.0001]
Steps:  67%|██████▋   | 1342/2000 [40:19<19:04,  1.74s/it, loss=0.207, lr=0.0001]
Steps:  67%|██████▋   | 1343/2000 [40:19<18:57,  1.73s/it, loss=0.207, lr=0.0001]
Steps:  67%|██████▋   | 1343/2000 [40:19<18:57,  1.73s/it, loss=0.342, lr=0.0001]
Steps:  67%|██████▋   | 1343/2000 [40:19<18:57,  1.73s/it, loss=0.108, lr=0.0001]
Steps:  67%|██████▋   | 1343/2000 [40:20<18:57,  1.73s/it, loss=0.202, lr=0.0001]
Steps:  67%|██████▋   | 1343/2000 [40:20<18:57,  1.73s/it, loss=0.151, lr=0.0001]
Steps:  67%|██████▋   | 1344/2000 [40:21<19:24,  1.78s/it, loss=0.151, lr=0.0001]
Steps:  67%|██████▋   | 1344/2000 [40:21<19:24,  1.78s/it, loss=0.261, lr=0.0001]
Steps:  67%|██████▋   | 1344/2000 [40:21<19:24,  1.78s/it, loss=0.178, lr=0.0001]
Steps:  67%|██████▋   | 1344/2000 [40:22<19:24,  1.78s/it, loss=0.0987, lr=0.0001]
Steps:  67%|██████▋   | 1344/2000 [40:22<19:24,  1.78s/it, loss=0.172, lr=0.0001] 
Steps:  67%|██████▋   | 1345/2000 [40:23<18:57,  1.74s/it, loss=0.172, lr=0.0001]
Steps:  67%|██████▋   | 1345/2000 [40:23<18:57,  1.74s/it, loss=0.126, lr=0.0001]
Steps:  67%|██████▋   | 1345/2000 [40:23<18:57,  1.74s/it, loss=0.27, lr=0.0001] 
Steps:  67%|██████▋   | 1345/2000 [40:23<18:57,  1.74s/it, loss=0.385, lr=0.0001]
Steps:  67%|██████▋   | 1345/2000 [40:24<18:57,  1.74s/it, loss=0.209, lr=0.0001]
Steps:  67%|██████▋   | 1346/2000 [40:24<18:37,  1.71s/it, loss=0.209, lr=0.0001]
Steps:  67%|██████▋   | 1346/2000 [40:24<18:37,  1.71s/it, loss=0.212, lr=0.0001]
Steps:  67%|██████▋   | 1346/2000 [40:25<18:37,  1.71s/it, loss=0.167, lr=0.0001]
Steps:  67%|██████▋   | 1346/2000 [40:25<18:37,  1.71s/it, loss=0.13, lr=0.0001] 
Steps:  67%|██████▋   | 1346/2000 [40:25<18:37,  1.71s/it, loss=0.175, lr=0.0001]
Steps:  67%|██████▋   | 1347/2000 [40:26<19:09,  1.76s/it, loss=0.175, lr=0.0001]
Steps:  67%|██████▋   | 1347/2000 [40:26<19:09,  1.76s/it, loss=0.309, lr=0.0001]
Steps:  67%|██████▋   | 1347/2000 [40:27<19:09,  1.76s/it, loss=0.208, lr=0.0001]
Steps:  67%|██████▋   | 1347/2000 [40:27<19:09,  1.76s/it, loss=0.107, lr=0.0001]
Steps:  67%|██████▋   | 1347/2000 [40:27<19:09,  1.76s/it, loss=0.114, lr=0.0001]
Steps:  67%|██████▋   | 1348/2000 [40:28<18:46,  1.73s/it, loss=0.114, lr=0.0001]
Steps:  67%|██████▋   | 1348/2000 [40:28<18:46,  1.73s/it, loss=0.188, lr=0.0001]
Steps:  67%|██████▋   | 1348/2000 [40:28<18:46,  1.73s/it, loss=0.201, lr=0.0001]
Steps:  67%|██████▋   | 1348/2000 [40:29<18:46,  1.73s/it, loss=0.548, lr=0.0001]
Steps:  67%|██████▋   | 1348/2000 [40:29<18:46,  1.73s/it, loss=0.132, lr=0.0001]
Steps:  67%|██████▋   | 1349/2000 [40:29<18:31,  1.71s/it, loss=0.132, lr=0.0001]
Steps:  67%|██████▋   | 1349/2000 [40:29<18:31,  1.71s/it, loss=0.144, lr=0.0001]
Steps:  67%|██████▋   | 1349/2000 [40:30<18:31,  1.71s/it, loss=0.188, lr=0.0001]
Steps:  67%|██████▋   | 1349/2000 [40:30<18:31,  1.71s/it, loss=0.405, lr=0.0001]
Steps:  67%|██████▋   | 1349/2000 [40:31<18:31,  1.71s/it, loss=0.19, lr=0.0001] 
Steps:  68%|██████▊   | 1350/2000 [40:31<18:22,  1.70s/it, loss=0.19, lr=0.0001]
Steps:  68%|██████▊   | 1350/2000 [40:31<18:22,  1.70s/it, loss=0.264, lr=0.0001]
Steps:  68%|██████▊   | 1350/2000 [40:32<18:22,  1.70s/it, loss=0.57, lr=0.0001] 
Steps:  68%|██████▊   | 1350/2000 [40:32<18:22,  1.70s/it, loss=0.0454, lr=0.0001]
Steps:  68%|██████▊   | 1350/2000 [40:33<18:22,  1.70s/it, loss=0.225, lr=0.0001] 
Steps:  68%|██████▊   | 1351/2000 [40:33<19:00,  1.76s/it, loss=0.225, lr=0.0001]
Steps:  68%|██████▊   | 1351/2000 [40:33<19:00,  1.76s/it, loss=0.0695, lr=0.0001]
Steps:  68%|██████▊   | 1351/2000 [40:33<19:00,  1.76s/it, loss=0.12, lr=0.0001]  
Steps:  68%|██████▊   | 1351/2000 [40:34<19:00,  1.76s/it, loss=0.211, lr=0.0001]
Steps:  68%|██████▊   | 1351/2000 [40:34<19:00,  1.76s/it, loss=0.108, lr=0.0001]
Steps:  68%|██████▊   | 1352/2000 [40:35<18:38,  1.73s/it, loss=0.108, lr=0.0001]
Steps:  68%|██████▊   | 1352/2000 [40:35<18:38,  1.73s/it, loss=0.113, lr=0.0001]
Steps:  68%|██████▊   | 1352/2000 [40:35<18:38,  1.73s/it, loss=0.535, lr=0.0001]
Steps:  68%|██████▊   | 1352/2000 [40:35<18:38,  1.73s/it, loss=0.166, lr=0.0001]
Steps:  68%|██████▊   | 1352/2000 [40:36<18:38,  1.73s/it, loss=0.119, lr=0.0001]
Steps:  68%|██████▊   | 1353/2000 [40:36<18:21,  1.70s/it, loss=0.119, lr=0.0001]
Steps:  68%|██████▊   | 1353/2000 [40:36<18:21,  1.70s/it, loss=0.218, lr=0.0001]
Steps:  68%|██████▊   | 1353/2000 [40:37<18:21,  1.70s/it, loss=0.177, lr=0.0001]
Steps:  68%|██████▊   | 1353/2000 [40:37<18:21,  1.70s/it, loss=0.148, lr=0.0001]
Steps:  68%|██████▊   | 1353/2000 [40:38<18:21,  1.70s/it, loss=0.714, lr=0.0001]
Steps:  68%|██████▊   | 1354/2000 [40:38<18:54,  1.76s/it, loss=0.714, lr=0.0001]
Steps:  68%|██████▊   | 1354/2000 [40:38<18:54,  1.76s/it, loss=0.0829, lr=0.0001]
Steps:  68%|██████▊   | 1354/2000 [40:39<18:54,  1.76s/it, loss=0.785, lr=0.0001] 
Steps:  68%|██████▊   | 1354/2000 [40:39<18:54,  1.76s/it, loss=0.147, lr=0.0001]
Steps:  68%|██████▊   | 1354/2000 [40:39<18:54,  1.76s/it, loss=0.177, lr=0.0001]
Steps:  68%|██████▊   | 1355/2000 [40:40<18:33,  1.73s/it, loss=0.177, lr=0.0001]
Steps:  68%|██████▊   | 1355/2000 [40:40<18:33,  1.73s/it, loss=0.179, lr=0.0001]
Steps:  68%|██████▊   | 1355/2000 [40:40<18:33,  1.73s/it, loss=0.717, lr=0.0001]
Steps:  68%|██████▊   | 1355/2000 [40:41<18:33,  1.73s/it, loss=0.0777, lr=0.0001]
Steps:  68%|██████▊   | 1355/2000 [40:41<18:33,  1.73s/it, loss=0.226, lr=0.0001] 
Steps:  68%|██████▊   | 1356/2000 [40:41<18:17,  1.70s/it, loss=0.226, lr=0.0001]
Steps:  68%|██████▊   | 1356/2000 [40:41<18:17,  1.70s/it, loss=0.0477, lr=0.0001]
Steps:  68%|██████▊   | 1356/2000 [40:42<18:17,  1.70s/it, loss=0.128, lr=0.0001] 
Steps:  68%|██████▊   | 1356/2000 [40:43<18:17,  1.70s/it, loss=0.375, lr=0.0001]
Steps:  68%|██████▊   | 1356/2000 [40:43<18:17,  1.70s/it, loss=0.101, lr=0.0001]
Steps:  68%|██████▊   | 1357/2000 [40:43<18:50,  1.76s/it, loss=0.101, lr=0.0001]
Steps:  68%|██████▊   | 1357/2000 [40:43<18:50,  1.76s/it, loss=0.225, lr=0.0001]
Steps:  68%|██████▊   | 1357/2000 [40:44<18:50,  1.76s/it, loss=0.096, lr=0.0001]
Steps:  68%|██████▊   | 1357/2000 [40:44<18:50,  1.76s/it, loss=0.265, lr=0.0001]
Steps:  68%|██████▊   | 1357/2000 [40:45<18:50,  1.76s/it, loss=0.21, lr=0.0001] 
Steps:  68%|██████▊   | 1358/2000 [40:45<18:29,  1.73s/it, loss=0.21, lr=0.0001]
Steps:  68%|██████▊   | 1358/2000 [40:45<18:29,  1.73s/it, loss=0.119, lr=0.0001]
Steps:  68%|██████▊   | 1358/2000 [40:45<18:29,  1.73s/it, loss=0.177, lr=0.0001]
Steps:  68%|██████▊   | 1358/2000 [40:46<18:29,  1.73s/it, loss=0.131, lr=0.0001]
Steps:  68%|██████▊   | 1358/2000 [40:46<18:29,  1.73s/it, loss=1, lr=0.0001]    
Steps:  68%|██████▊   | 1359/2000 [40:47<18:12,  1.70s/it, loss=1, lr=0.0001]
Steps:  68%|██████▊   | 1359/2000 [40:47<18:12,  1.70s/it, loss=0.219, lr=0.0001]
Steps:  68%|██████▊   | 1359/2000 [40:47<18:12,  1.70s/it, loss=0.154, lr=0.0001]
Steps:  68%|██████▊   | 1359/2000 [40:47<18:12,  1.70s/it, loss=0.207, lr=0.0001]
Steps:  68%|██████▊   | 1359/2000 [40:48<18:12,  1.70s/it, loss=0.506, lr=0.0001]
Steps:  68%|██████▊   | 1360/2000 [40:49<18:43,  1.75s/it, loss=0.506, lr=0.0001]
Steps:  68%|██████▊   | 1360/2000 [40:49<18:43,  1.75s/it, loss=1.12, lr=0.0001] 
Steps:  68%|██████▊   | 1360/2000 [40:49<18:43,  1.75s/it, loss=0.377, lr=0.0001]
Steps:  68%|██████▊   | 1360/2000 [40:49<18:43,  1.75s/it, loss=0.133, lr=0.0001]
Steps:  68%|██████▊   | 1360/2000 [40:50<18:43,  1.75s/it, loss=0.226, lr=0.0001]
Steps:  68%|██████▊   | 1361/2000 [40:50<18:24,  1.73s/it, loss=0.226, lr=0.0001]
Steps:  68%|██████▊   | 1361/2000 [40:50<18:24,  1.73s/it, loss=0.109, lr=0.0001]
Steps:  68%|██████▊   | 1361/2000 [40:51<18:24,  1.73s/it, loss=0.607, lr=0.0001]
Steps:  68%|██████▊   | 1361/2000 [40:51<18:24,  1.73s/it, loss=0.158, lr=0.0001]
Steps:  68%|██████▊   | 1361/2000 [40:51<18:24,  1.73s/it, loss=0.138, lr=0.0001]
Steps:  68%|██████▊   | 1362/2000 [40:52<18:10,  1.71s/it, loss=0.138, lr=0.0001]
Steps:  68%|██████▊   | 1362/2000 [40:52<18:10,  1.71s/it, loss=0.133, lr=0.0001]
Steps:  68%|██████▊   | 1362/2000 [40:52<18:10,  1.71s/it, loss=0.209, lr=0.0001]
Steps:  68%|██████▊   | 1362/2000 [40:53<18:10,  1.71s/it, loss=0.17, lr=0.0001] 
Steps:  68%|██████▊   | 1362/2000 [40:53<18:10,  1.71s/it, loss=0.32, lr=0.0001]
Steps:  68%|██████▊   | 1363/2000 [40:54<18:45,  1.77s/it, loss=0.32, lr=0.0001]
Steps:  68%|██████▊   | 1363/2000 [40:54<18:45,  1.77s/it, loss=0.177, lr=0.0001]
Steps:  68%|██████▊   | 1363/2000 [40:54<18:45,  1.77s/it, loss=0.212, lr=0.0001]
Steps:  68%|██████▊   | 1363/2000 [40:55<18:45,  1.77s/it, loss=0.897, lr=0.0001]
Steps:  68%|██████▊   | 1363/2000 [40:55<18:45,  1.77s/it, loss=0.208, lr=0.0001]
Steps:  68%|██████▊   | 1364/2000 [40:55<18:28,  1.74s/it, loss=0.208, lr=0.0001]
Steps:  68%|██████▊   | 1364/2000 [40:55<18:28,  1.74s/it, loss=0.158, lr=0.0001]
Steps:  68%|██████▊   | 1364/2000 [40:56<18:28,  1.74s/it, loss=0.196, lr=0.0001]
Steps:  68%|██████▊   | 1364/2000 [40:56<18:28,  1.74s/it, loss=0.157, lr=0.0001]
Steps:  68%|██████▊   | 1364/2000 [40:57<18:28,  1.74s/it, loss=0.148, lr=0.0001]
Steps:  68%|██████▊   | 1365/2000 [40:57<18:14,  1.72s/it, loss=0.148, lr=0.0001]
Steps:  68%|██████▊   | 1365/2000 [40:57<18:14,  1.72s/it, loss=0.173, lr=0.0001]
Steps:  68%|██████▊   | 1365/2000 [40:58<18:14,  1.72s/it, loss=0.159, lr=0.0001]
Steps:  68%|██████▊   | 1365/2000 [40:58<18:14,  1.72s/it, loss=0.186, lr=0.0001]
Steps:  68%|██████▊   | 1365/2000 [40:58<18:14,  1.72s/it, loss=0.0642, lr=0.0001]
Steps:  68%|██████▊   | 1366/2000 [40:59<18:43,  1.77s/it, loss=0.0642, lr=0.0001]
Steps:  68%|██████▊   | 1366/2000 [40:59<18:43,  1.77s/it, loss=0.187, lr=0.0001] 
Steps:  68%|██████▊   | 1366/2000 [40:59<18:43,  1.77s/it, loss=0.623, lr=0.0001]
Steps:  68%|██████▊   | 1366/2000 [41:00<18:43,  1.77s/it, loss=0.137, lr=0.0001]
Steps:  68%|██████▊   | 1366/2000 [41:00<18:43,  1.77s/it, loss=0.256, lr=0.0001]
Steps:  68%|██████▊   | 1367/2000 [41:01<18:29,  1.75s/it, loss=0.256, lr=0.0001]
Steps:  68%|██████▊   | 1367/2000 [41:01<18:29,  1.75s/it, loss=0.0783, lr=0.0001]
Steps:  68%|██████▊   | 1367/2000 [41:01<18:29,  1.75s/it, loss=0.145, lr=0.0001] 
Steps:  68%|██████▊   | 1367/2000 [41:02<18:29,  1.75s/it, loss=0.385, lr=0.0001]
Steps:  68%|██████▊   | 1367/2000 [41:02<18:29,  1.75s/it, loss=0.149, lr=0.0001]
Steps:  68%|██████▊   | 1368/2000 [41:02<18:06,  1.72s/it, loss=0.149, lr=0.0001]
Steps:  68%|██████▊   | 1368/2000 [41:02<18:06,  1.72s/it, loss=0.219, lr=0.0001]
Steps:  68%|██████▊   | 1368/2000 [41:03<18:06,  1.72s/it, loss=0.0912, lr=0.0001]
Steps:  68%|██████▊   | 1368/2000 [41:03<18:06,  1.72s/it, loss=0.731, lr=0.0001] 
Steps:  68%|██████▊   | 1368/2000 [41:04<18:06,  1.72s/it, loss=0.212, lr=0.0001]
Steps:  68%|██████▊   | 1369/2000 [41:04<17:50,  1.70s/it, loss=0.212, lr=0.0001]
Steps:  68%|██████▊   | 1369/2000 [41:04<17:50,  1.70s/it, loss=0.15, lr=0.0001] 
Steps:  68%|██████▊   | 1369/2000 [41:05<17:50,  1.70s/it, loss=0.321, lr=0.0001]
Steps:  68%|██████▊   | 1369/2000 [41:05<17:50,  1.70s/it, loss=0.116, lr=0.0001]
Steps:  68%|██████▊   | 1369/2000 [41:05<17:50,  1.70s/it, loss=0.264, lr=0.0001]
Steps:  68%|██████▊   | 1370/2000 [41:06<18:20,  1.75s/it, loss=0.264, lr=0.0001]
Steps:  68%|██████▊   | 1370/2000 [41:06<18:20,  1.75s/it, loss=0.475, lr=0.0001]
Steps:  68%|██████▊   | 1370/2000 [41:06<18:20,  1.75s/it, loss=0.237, lr=0.0001]
Steps:  68%|██████▊   | 1370/2000 [41:07<18:20,  1.75s/it, loss=0.183, lr=0.0001]
Steps:  68%|██████▊   | 1370/2000 [41:07<18:20,  1.75s/it, loss=0.222, lr=0.0001]
Steps:  69%|██████▊   | 1371/2000 [41:08<17:58,  1.72s/it, loss=0.222, lr=0.0001]
Steps:  69%|██████▊   | 1371/2000 [41:08<17:58,  1.72s/it, loss=0.163, lr=0.0001]
Steps:  69%|██████▊   | 1371/2000 [41:08<17:58,  1.72s/it, loss=0.242, lr=0.0001]
Steps:  69%|██████▊   | 1371/2000 [41:08<17:58,  1.72s/it, loss=0.138, lr=0.0001]
Steps:  69%|██████▊   | 1371/2000 [41:09<17:58,  1.72s/it, loss=1.49, lr=0.0001] 
Steps:  69%|██████▊   | 1372/2000 [41:09<17:43,  1.69s/it, loss=1.49, lr=0.0001]
Steps:  69%|██████▊   | 1372/2000 [41:09<17:43,  1.69s/it, loss=0.126, lr=0.0001]
Steps:  69%|██████▊   | 1372/2000 [41:10<17:43,  1.69s/it, loss=0.152, lr=0.0001]
Steps:  69%|██████▊   | 1372/2000 [41:10<17:43,  1.69s/it, loss=0.291, lr=0.0001]
Steps:  69%|██████▊   | 1372/2000 [41:11<17:43,  1.69s/it, loss=0.197, lr=0.0001]
Steps:  69%|██████▊   | 1373/2000 [41:11<18:15,  1.75s/it, loss=0.197, lr=0.0001]
Steps:  69%|██████▊   | 1373/2000 [41:11<18:15,  1.75s/it, loss=0.0267, lr=0.0001]
Steps:  69%|██████▊   | 1373/2000 [41:11<18:15,  1.75s/it, loss=0.152, lr=0.0001] 
Steps:  69%|██████▊   | 1373/2000 [41:12<18:15,  1.75s/it, loss=0.0832, lr=0.0001]
Steps:  69%|██████▊   | 1373/2000 [41:12<18:15,  1.75s/it, loss=0.0637, lr=0.0001]
Steps:  69%|██████▊   | 1374/2000 [41:13<17:53,  1.72s/it, loss=0.0637, lr=0.0001]
Steps:  69%|██████▊   | 1374/2000 [41:13<17:53,  1.72s/it, loss=0.1, lr=0.0001]   
Steps:  69%|██████▊   | 1374/2000 [41:13<17:53,  1.72s/it, loss=0.156, lr=0.0001]
Steps:  69%|██████▊   | 1374/2000 [41:13<17:53,  1.72s/it, loss=0.114, lr=0.0001]
Steps:  69%|██████▊   | 1374/2000 [41:14<17:53,  1.72s/it, loss=0.225, lr=0.0001]
Steps:  69%|██████▉   | 1375/2000 [41:14<17:36,  1.69s/it, loss=0.225, lr=0.0001]
Steps:  69%|██████▉   | 1375/2000 [41:14<17:36,  1.69s/it, loss=0.132, lr=0.0001]
Steps:  69%|██████▉   | 1375/2000 [41:15<17:36,  1.69s/it, loss=0.228, lr=0.0001]
Steps:  69%|██████▉   | 1375/2000 [41:15<17:36,  1.69s/it, loss=0.141, lr=0.0001]
Steps:  69%|██████▉   | 1375/2000 [41:16<17:36,  1.69s/it, loss=0.231, lr=0.0001]
Steps:  69%|██████▉   | 1376/2000 [41:16<18:09,  1.75s/it, loss=0.231, lr=0.0001]
Steps:  69%|██████▉   | 1376/2000 [41:16<18:09,  1.75s/it, loss=0.142, lr=0.0001]
Steps:  69%|██████▉   | 1376/2000 [41:17<18:09,  1.75s/it, loss=0.0993, lr=0.0001]
Steps:  69%|██████▉   | 1376/2000 [41:17<18:09,  1.75s/it, loss=0.116, lr=0.0001] 
Steps:  69%|██████▉   | 1376/2000 [41:17<18:09,  1.75s/it, loss=0.158, lr=0.0001]
Steps:  69%|██████▉   | 1377/2000 [41:18<17:45,  1.71s/it, loss=0.158, lr=0.0001]
Steps:  69%|██████▉   | 1377/2000 [41:18<17:45,  1.71s/it, loss=0.14, lr=0.0001] 
Steps:  69%|██████▉   | 1377/2000 [41:18<17:45,  1.71s/it, loss=0.145, lr=0.0001]
Steps:  69%|██████▉   | 1377/2000 [41:19<17:45,  1.71s/it, loss=0.275, lr=0.0001]
Steps:  69%|██████▉   | 1377/2000 [41:19<17:45,  1.71s/it, loss=0.157, lr=0.0001]
Steps:  69%|██████▉   | 1378/2000 [41:19<17:29,  1.69s/it, loss=0.157, lr=0.0001]
Steps:  69%|██████▉   | 1378/2000 [41:19<17:29,  1.69s/it, loss=0.115, lr=0.0001]
Steps:  69%|██████▉   | 1378/2000 [41:20<17:29,  1.69s/it, loss=0.175, lr=0.0001]
Steps:  69%|██████▉   | 1378/2000 [41:20<17:29,  1.69s/it, loss=0.511, lr=0.0001]
Steps:  69%|██████▉   | 1378/2000 [41:21<17:29,  1.69s/it, loss=0.218, lr=0.0001]
Steps:  69%|██████▉   | 1379/2000 [41:21<18:03,  1.75s/it, loss=0.218, lr=0.0001]
Steps:  69%|██████▉   | 1379/2000 [41:21<18:03,  1.75s/it, loss=0.145, lr=0.0001]
Steps:  69%|██████▉   | 1379/2000 [41:22<18:03,  1.75s/it, loss=0.167, lr=0.0001]
Steps:  69%|██████▉   | 1379/2000 [41:22<18:03,  1.75s/it, loss=0.342, lr=0.0001]
Steps:  69%|██████▉   | 1379/2000 [41:23<18:03,  1.75s/it, loss=0.301, lr=0.0001]
Steps:  69%|██████▉   | 1380/2000 [41:23<18:10,  1.76s/it, loss=0.301, lr=0.0001]
Steps:  69%|██████▉   | 1380/2000 [41:23<18:10,  1.76s/it, loss=0.133, lr=0.0001]
Steps:  69%|██████▉   | 1380/2000 [41:24<18:10,  1.76s/it, loss=0.209, lr=0.0001]
Steps:  69%|██████▉   | 1380/2000 [41:24<18:10,  1.76s/it, loss=0.143, lr=0.0001]
Steps:  69%|██████▉   | 1380/2000 [41:24<18:10,  1.76s/it, loss=0.253, lr=0.0001]
Steps:  69%|██████▉   | 1381/2000 [41:25<17:47,  1.72s/it, loss=0.253, lr=0.0001]
Steps:  69%|██████▉   | 1381/2000 [41:25<17:47,  1.72s/it, loss=0.937, lr=0.0001]
Steps:  69%|██████▉   | 1381/2000 [41:25<17:47,  1.72s/it, loss=0.161, lr=0.0001]
Steps:  69%|██████▉   | 1381/2000 [41:26<17:47,  1.72s/it, loss=0.185, lr=0.0001]
Steps:  69%|██████▉   | 1381/2000 [41:26<17:47,  1.72s/it, loss=0.147, lr=0.0001]
Steps:  69%|██████▉   | 1382/2000 [41:27<18:11,  1.77s/it, loss=0.147, lr=0.0001]
Steps:  69%|██████▉   | 1382/2000 [41:27<18:11,  1.77s/it, loss=0.248, lr=0.0001]
Steps:  69%|██████▉   | 1382/2000 [41:27<18:11,  1.77s/it, loss=0.227, lr=0.0001]
Steps:  69%|██████▉   | 1382/2000 [41:27<18:11,  1.77s/it, loss=0.112, lr=0.0001]
Steps:  69%|██████▉   | 1382/2000 [41:28<18:11,  1.77s/it, loss=0.388, lr=0.0001]
Steps:  69%|██████▉   | 1383/2000 [41:28<17:45,  1.73s/it, loss=0.388, lr=0.0001]
Steps:  69%|██████▉   | 1383/2000 [41:28<17:45,  1.73s/it, loss=0.301, lr=0.0001]
Steps:  69%|██████▉   | 1383/2000 [41:29<17:45,  1.73s/it, loss=0.196, lr=0.0001]
Steps:  69%|██████▉   | 1383/2000 [41:29<17:45,  1.73s/it, loss=0.243, lr=0.0001]
Steps:  69%|██████▉   | 1383/2000 [41:29<17:45,  1.73s/it, loss=0.154, lr=0.0001]
Steps:  69%|██████▉   | 1384/2000 [41:30<17:26,  1.70s/it, loss=0.154, lr=0.0001]
Steps:  69%|██████▉   | 1384/2000 [41:30<17:26,  1.70s/it, loss=0.139, lr=0.0001]
Steps:  69%|██████▉   | 1384/2000 [41:30<17:26,  1.70s/it, loss=0.128, lr=0.0001]
Steps:  69%|██████▉   | 1384/2000 [41:31<17:26,  1.70s/it, loss=0.212, lr=0.0001]
Steps:  69%|██████▉   | 1384/2000 [41:31<17:26,  1.70s/it, loss=0.566, lr=0.0001]
Steps:  69%|██████▉   | 1385/2000 [41:32<17:55,  1.75s/it, loss=0.566, lr=0.0001]
Steps:  69%|██████▉   | 1385/2000 [41:32<17:55,  1.75s/it, loss=0.235, lr=0.0001]
Steps:  69%|██████▉   | 1385/2000 [41:32<17:55,  1.75s/it, loss=0.166, lr=0.0001]
Steps:  69%|██████▉   | 1385/2000 [41:33<17:55,  1.75s/it, loss=0.224, lr=0.0001]
Steps:  69%|██████▉   | 1385/2000 [41:33<17:55,  1.75s/it, loss=0.189, lr=0.0001]
Steps:  69%|██████▉   | 1386/2000 [41:33<17:41,  1.73s/it, loss=0.189, lr=0.0001]
Steps:  69%|██████▉   | 1386/2000 [41:33<17:41,  1.73s/it, loss=0.271, lr=0.0001]
Steps:  69%|██████▉   | 1386/2000 [41:34<17:41,  1.73s/it, loss=0.126, lr=0.0001]
Steps:  69%|██████▉   | 1386/2000 [41:34<17:41,  1.73s/it, loss=0.107, lr=0.0001]
Steps:  69%|██████▉   | 1386/2000 [41:35<17:41,  1.73s/it, loss=0.188, lr=0.0001]
Steps:  69%|██████▉   | 1387/2000 [41:35<17:22,  1.70s/it, loss=0.188, lr=0.0001]
Steps:  69%|██████▉   | 1387/2000 [41:35<17:22,  1.70s/it, loss=0.199, lr=0.0001]
Steps:  69%|██████▉   | 1387/2000 [41:35<17:22,  1.70s/it, loss=0.0897, lr=0.0001]
Steps:  69%|██████▉   | 1387/2000 [41:36<17:22,  1.70s/it, loss=0.233, lr=0.0001] 
Steps:  69%|██████▉   | 1387/2000 [41:36<17:22,  1.70s/it, loss=0.124, lr=0.0001]
Steps:  69%|██████▉   | 1388/2000 [41:37<17:08,  1.68s/it, loss=0.124, lr=0.0001]
Steps:  69%|██████▉   | 1388/2000 [41:37<17:08,  1.68s/it, loss=0.229, lr=0.0001]
Steps:  69%|██████▉   | 1388/2000 [41:37<17:08,  1.68s/it, loss=0.0651, lr=0.0001]
Steps:  69%|██████▉   | 1388/2000 [41:38<17:08,  1.68s/it, loss=0.179, lr=0.0001] 
Steps:  69%|██████▉   | 1388/2000 [41:38<17:08,  1.68s/it, loss=0.17, lr=0.0001] 
Steps:  69%|██████▉   | 1389/2000 [41:39<17:39,  1.73s/it, loss=0.17, lr=0.0001]
Steps:  69%|██████▉   | 1389/2000 [41:39<17:39,  1.73s/it, loss=0.106, lr=0.0001]
Steps:  69%|██████▉   | 1389/2000 [41:39<17:39,  1.73s/it, loss=0.19, lr=0.0001] 
Steps:  69%|██████▉   | 1389/2000 [41:39<17:39,  1.73s/it, loss=0.074, lr=0.0001]
Steps:  69%|██████▉   | 1389/2000 [41:40<17:39,  1.73s/it, loss=0.286, lr=0.0001]
Steps:  70%|██████▉   | 1390/2000 [41:40<17:20,  1.71s/it, loss=0.286, lr=0.0001]
Steps:  70%|██████▉   | 1390/2000 [41:40<17:20,  1.71s/it, loss=0.242, lr=0.0001]
Steps:  70%|██████▉   | 1390/2000 [41:41<17:20,  1.71s/it, loss=0.148, lr=0.0001]
Steps:  70%|██████▉   | 1390/2000 [41:41<17:20,  1.71s/it, loss=0.194, lr=0.0001]
Steps:  70%|██████▉   | 1390/2000 [41:41<17:20,  1.71s/it, loss=0.0847, lr=0.0001]
Steps:  70%|██████▉   | 1391/2000 [41:42<17:05,  1.68s/it, loss=0.0847, lr=0.0001]
Steps:  70%|██████▉   | 1391/2000 [41:42<17:05,  1.68s/it, loss=0.166, lr=0.0001] 
Steps:  70%|██████▉   | 1391/2000 [41:42<17:05,  1.68s/it, loss=0.155, lr=0.0001]
Steps:  70%|██████▉   | 1391/2000 [41:43<17:05,  1.68s/it, loss=0.135, lr=0.0001]
Steps:  70%|██████▉   | 1391/2000 [41:43<17:05,  1.68s/it, loss=0.176, lr=0.0001]
Steps:  70%|██████▉   | 1392/2000 [41:44<17:42,  1.75s/it, loss=0.176, lr=0.0001]
Steps:  70%|██████▉   | 1392/2000 [41:44<17:42,  1.75s/it, loss=0.092, lr=0.0001]
Steps:  70%|██████▉   | 1392/2000 [41:44<17:42,  1.75s/it, loss=0.147, lr=0.0001]
Steps:  70%|██████▉   | 1392/2000 [41:45<17:42,  1.75s/it, loss=0.207, lr=0.0001]
Steps:  70%|██████▉   | 1392/2000 [41:45<17:42,  1.75s/it, loss=0.135, lr=0.0001]
Steps:  70%|██████▉   | 1393/2000 [41:45<17:28,  1.73s/it, loss=0.135, lr=0.0001]
Steps:  70%|██████▉   | 1393/2000 [41:45<17:28,  1.73s/it, loss=0.684, lr=0.0001]
Steps:  70%|██████▉   | 1393/2000 [41:46<17:28,  1.73s/it, loss=0.137, lr=0.0001]
Steps:  70%|██████▉   | 1393/2000 [41:46<17:28,  1.73s/it, loss=0.22, lr=0.0001] 
Steps:  70%|██████▉   | 1393/2000 [41:47<17:28,  1.73s/it, loss=0.31, lr=0.0001]
Steps:  70%|██████▉   | 1394/2000 [41:47<17:10,  1.70s/it, loss=0.31, lr=0.0001]
Steps:  70%|██████▉   | 1394/2000 [41:47<17:10,  1.70s/it, loss=0.0683, lr=0.0001]
Steps:  70%|██████▉   | 1394/2000 [41:47<17:10,  1.70s/it, loss=0.154, lr=0.0001] 
Steps:  70%|██████▉   | 1394/2000 [41:48<17:10,  1.70s/it, loss=0.44, lr=0.0001] 
Steps:  70%|██████▉   | 1394/2000 [41:48<17:10,  1.70s/it, loss=0.0964, lr=0.0001]
Steps:  70%|██████▉   | 1395/2000 [41:49<17:40,  1.75s/it, loss=0.0964, lr=0.0001]
Steps:  70%|██████▉   | 1395/2000 [41:49<17:40,  1.75s/it, loss=0.127, lr=0.0001] 
Steps:  70%|██████▉   | 1395/2000 [41:49<17:40,  1.75s/it, loss=0.203, lr=0.0001]
Steps:  70%|██████▉   | 1395/2000 [41:50<17:40,  1.75s/it, loss=0.0746, lr=0.0001]
Steps:  70%|██████▉   | 1395/2000 [41:50<17:40,  1.75s/it, loss=0.161, lr=0.0001] 
Steps:  70%|██████▉   | 1396/2000 [41:51<17:19,  1.72s/it, loss=0.161, lr=0.0001]
Steps:  70%|██████▉   | 1396/2000 [41:51<17:19,  1.72s/it, loss=0.0579, lr=0.0001]
Steps:  70%|██████▉   | 1396/2000 [41:51<17:19,  1.72s/it, loss=0.252, lr=0.0001] 
Steps:  70%|██████▉   | 1396/2000 [41:51<17:19,  1.72s/it, loss=0.251, lr=0.0001]
Steps:  70%|██████▉   | 1396/2000 [41:52<17:19,  1.72s/it, loss=0.865, lr=0.0001]
Steps:  70%|██████▉   | 1397/2000 [41:52<17:03,  1.70s/it, loss=0.865, lr=0.0001]
Steps:  70%|██████▉   | 1397/2000 [41:52<17:03,  1.70s/it, loss=0.219, lr=0.0001]
Steps:  70%|██████▉   | 1397/2000 [41:53<17:03,  1.70s/it, loss=0.173, lr=0.0001]
Steps:  70%|██████▉   | 1397/2000 [41:53<17:03,  1.70s/it, loss=0.155, lr=0.0001]
Steps:  70%|██████▉   | 1397/2000 [41:53<17:03,  1.70s/it, loss=0.22, lr=0.0001] 
Steps:  70%|██████▉   | 1398/2000 [41:54<17:35,  1.75s/it, loss=0.22, lr=0.0001]
Steps:  70%|██████▉   | 1398/2000 [41:54<17:35,  1.75s/it, loss=0.213, lr=0.0001]
Steps:  70%|██████▉   | 1398/2000 [41:55<17:35,  1.75s/it, loss=0.234, lr=0.0001]
Steps:  70%|██████▉   | 1398/2000 [41:55<17:35,  1.75s/it, loss=0.245, lr=0.0001]
Steps:  70%|██████▉   | 1398/2000 [41:55<17:35,  1.75s/it, loss=0.389, lr=0.0001]
Steps:  70%|██████▉   | 1399/2000 [41:56<17:13,  1.72s/it, loss=0.389, lr=0.0001]
Steps:  70%|██████▉   | 1399/2000 [41:56<17:13,  1.72s/it, loss=0.219, lr=0.0001]
Steps:  70%|██████▉   | 1399/2000 [41:56<17:13,  1.72s/it, loss=0.182, lr=0.0001]
Steps:  70%|██████▉   | 1399/2000 [41:57<17:13,  1.72s/it, loss=0.232, lr=0.0001]
Steps:  70%|██████▉   | 1399/2000 [41:57<17:13,  1.72s/it, loss=0.138, lr=0.0001]
Steps:  70%|███████   | 1400/2000 [41:57<16:59,  1.70s/it, loss=0.138, lr=0.0001]
Steps:  70%|███████   | 1400/2000 [41:57<16:59,  1.70s/it, loss=0.177, lr=0.0001]
Steps:  70%|███████   | 1400/2000 [41:58<16:59,  1.70s/it, loss=0.163, lr=0.0001]
Steps:  70%|███████   | 1400/2000 [41:58<16:59,  1.70s/it, loss=0.221, lr=0.0001]
Steps:  70%|███████   | 1400/2000 [41:59<16:59,  1.70s/it, loss=0.0965, lr=0.0001]
Steps:  70%|███████   | 1401/2000 [41:59<17:31,  1.76s/it, loss=0.0965, lr=0.0001]
Steps:  70%|███████   | 1401/2000 [41:59<17:31,  1.76s/it, loss=0.15, lr=0.0001]  
Steps:  70%|███████   | 1401/2000 [42:00<17:31,  1.76s/it, loss=0.088, lr=0.0001]
Steps:  70%|███████   | 1401/2000 [42:00<17:31,  1.76s/it, loss=0.277, lr=0.0001]
Steps:  70%|███████   | 1401/2000 [42:01<17:31,  1.76s/it, loss=0.139, lr=0.0001]
Steps:  70%|███████   | 1402/2000 [42:01<17:11,  1.72s/it, loss=0.139, lr=0.0001]
Steps:  70%|███████   | 1402/2000 [42:01<17:11,  1.72s/it, loss=0.154, lr=0.0001]
Steps:  70%|███████   | 1402/2000 [42:01<17:11,  1.72s/it, loss=0.232, lr=0.0001]
Steps:  70%|███████   | 1402/2000 [42:02<17:11,  1.72s/it, loss=0.16, lr=0.0001] 
Steps:  70%|███████   | 1402/2000 [42:02<17:11,  1.72s/it, loss=0.113, lr=0.0001]
Steps:  70%|███████   | 1403/2000 [42:03<16:55,  1.70s/it, loss=0.113, lr=0.0001]
Steps:  70%|███████   | 1403/2000 [42:03<16:55,  1.70s/it, loss=0.0806, lr=0.0001]
Steps:  70%|███████   | 1403/2000 [42:03<16:55,  1.70s/it, loss=0.0825, lr=0.0001]
Steps:  70%|███████   | 1403/2000 [42:03<16:55,  1.70s/it, loss=0.13, lr=0.0001]  
Steps:  70%|███████   | 1403/2000 [42:04<16:55,  1.70s/it, loss=0.131, lr=0.0001]
Steps:  70%|███████   | 1404/2000 [42:04<16:44,  1.69s/it, loss=0.131, lr=0.0001]
Steps:  70%|███████   | 1404/2000 [42:04<16:44,  1.69s/it, loss=0.237, lr=0.0001]
Steps:  70%|███████   | 1404/2000 [42:05<16:44,  1.69s/it, loss=0.119, lr=0.0001]
Steps:  70%|███████   | 1404/2000 [42:05<16:44,  1.69s/it, loss=0.0644, lr=0.0001]
Steps:  70%|███████   | 1404/2000 [42:06<16:44,  1.69s/it, loss=0.153, lr=0.0001] 
Steps:  70%|███████   | 1405/2000 [42:06<17:19,  1.75s/it, loss=0.153, lr=0.0001]
Steps:  70%|███████   | 1405/2000 [42:06<17:19,  1.75s/it, loss=0.177, lr=0.0001]
Steps:  70%|███████   | 1405/2000 [42:07<17:19,  1.75s/it, loss=0.305, lr=0.0001]
Steps:  70%|███████   | 1405/2000 [42:07<17:19,  1.75s/it, loss=0.311, lr=0.0001]
Steps:  70%|███████   | 1405/2000 [42:07<17:19,  1.75s/it, loss=0.15, lr=0.0001] 
Steps:  70%|███████   | 1406/2000 [42:08<17:00,  1.72s/it, loss=0.15, lr=0.0001]
Steps:  70%|███████   | 1406/2000 [42:08<17:00,  1.72s/it, loss=0.239, lr=0.0001]
Steps:  70%|███████   | 1406/2000 [42:08<17:00,  1.72s/it, loss=0.157, lr=0.0001]
Steps:  70%|███████   | 1406/2000 [42:09<17:00,  1.72s/it, loss=0.177, lr=0.0001]
Steps:  70%|███████   | 1406/2000 [42:09<17:00,  1.72s/it, loss=0.159, lr=0.0001]
Steps:  70%|███████   | 1407/2000 [42:09<16:46,  1.70s/it, loss=0.159, lr=0.0001]
Steps:  70%|███████   | 1407/2000 [42:09<16:46,  1.70s/it, loss=0.159, lr=0.0001]
Steps:  70%|███████   | 1407/2000 [42:10<16:46,  1.70s/it, loss=0.165, lr=0.0001]
Steps:  70%|███████   | 1407/2000 [42:10<16:46,  1.70s/it, loss=0.191, lr=0.0001]
Steps:  70%|███████   | 1407/2000 [42:11<16:46,  1.70s/it, loss=0.164, lr=0.0001]
Steps:  70%|███████   | 1408/2000 [42:11<17:16,  1.75s/it, loss=0.164, lr=0.0001]
Steps:  70%|███████   | 1408/2000 [42:11<17:16,  1.75s/it, loss=0.262, lr=0.0001]
Steps:  70%|███████   | 1408/2000 [42:12<17:16,  1.75s/it, loss=0.217, lr=0.0001]
Steps:  70%|███████   | 1408/2000 [42:12<17:16,  1.75s/it, loss=0.215, lr=0.0001]
Steps:  70%|███████   | 1408/2000 [42:13<17:16,  1.75s/it, loss=0.209, lr=0.0001]
Steps:  70%|███████   | 1409/2000 [42:13<16:58,  1.72s/it, loss=0.209, lr=0.0001]
Steps:  70%|███████   | 1409/2000 [42:13<16:58,  1.72s/it, loss=0.178, lr=0.0001]
Steps:  70%|███████   | 1409/2000 [42:13<16:58,  1.72s/it, loss=0.0447, lr=0.0001]
Steps:  70%|███████   | 1409/2000 [42:14<16:58,  1.72s/it, loss=0.27, lr=0.0001]  
Steps:  70%|███████   | 1409/2000 [42:14<16:58,  1.72s/it, loss=0.336, lr=0.0001]
Steps:  70%|███████   | 1410/2000 [42:15<16:47,  1.71s/it, loss=0.336, lr=0.0001]
Steps:  70%|███████   | 1410/2000 [42:15<16:47,  1.71s/it, loss=0.22, lr=0.0001] 
Steps:  70%|███████   | 1410/2000 [42:15<16:47,  1.71s/it, loss=0.0636, lr=0.0001]
Steps:  70%|███████   | 1410/2000 [42:16<16:47,  1.71s/it, loss=0.0226, lr=0.0001]
Steps:  70%|███████   | 1410/2000 [42:16<16:47,  1.71s/it, loss=0.101, lr=0.0001] 
Steps:  71%|███████   | 1411/2000 [42:17<17:24,  1.77s/it, loss=0.101, lr=0.0001]
Steps:  71%|███████   | 1411/2000 [42:17<17:24,  1.77s/it, loss=0.193, lr=0.0001]
Steps:  71%|███████   | 1411/2000 [42:17<17:24,  1.77s/it, loss=0.229, lr=0.0001]
Steps:  71%|███████   | 1411/2000 [42:17<17:24,  1.77s/it, loss=0.134, lr=0.0001]
Steps:  71%|███████   | 1411/2000 [42:18<17:24,  1.77s/it, loss=0.234, lr=0.0001]
Steps:  71%|███████   | 1412/2000 [42:18<17:06,  1.75s/it, loss=0.234, lr=0.0001]
Steps:  71%|███████   | 1412/2000 [42:18<17:06,  1.75s/it, loss=0.0718, lr=0.0001]
Steps:  71%|███████   | 1412/2000 [42:19<17:06,  1.75s/it, loss=0.258, lr=0.0001] 
Steps:  71%|███████   | 1412/2000 [42:19<17:06,  1.75s/it, loss=0.1, lr=0.0001]  
Steps:  71%|███████   | 1412/2000 [42:19<17:06,  1.75s/it, loss=0.132, lr=0.0001]
Steps:  71%|███████   | 1413/2000 [42:20<16:56,  1.73s/it, loss=0.132, lr=0.0001]
Steps:  71%|███████   | 1413/2000 [42:20<16:56,  1.73s/it, loss=0.0819, lr=0.0001]
Steps:  71%|███████   | 1413/2000 [42:20<16:56,  1.73s/it, loss=0.177, lr=0.0001] 
Steps:  71%|███████   | 1413/2000 [42:21<16:56,  1.73s/it, loss=0.479, lr=0.0001]
Steps:  71%|███████   | 1413/2000 [42:21<16:56,  1.73s/it, loss=0.168, lr=0.0001]
Steps:  71%|███████   | 1414/2000 [42:22<17:31,  1.79s/it, loss=0.168, lr=0.0001]
Steps:  71%|███████   | 1414/2000 [42:22<17:31,  1.79s/it, loss=0.187, lr=0.0001]
Steps:  71%|███████   | 1414/2000 [42:22<17:31,  1.79s/it, loss=0.129, lr=0.0001]
Steps:  71%|███████   | 1414/2000 [42:23<17:31,  1.79s/it, loss=0.197, lr=0.0001]
Steps:  71%|███████   | 1414/2000 [42:23<17:31,  1.79s/it, loss=0.174, lr=0.0001]
Steps:  71%|███████   | 1415/2000 [42:24<17:18,  1.77s/it, loss=0.174, lr=0.0001]
Steps:  71%|███████   | 1415/2000 [42:24<17:18,  1.77s/it, loss=0.142, lr=0.0001]
Steps:  71%|███████   | 1415/2000 [42:24<17:18,  1.77s/it, loss=0.229, lr=0.0001]
Steps:  71%|███████   | 1415/2000 [42:24<17:18,  1.77s/it, loss=0.13, lr=0.0001] 
Steps:  71%|███████   | 1415/2000 [42:25<17:18,  1.77s/it, loss=0.185, lr=0.0001]
Steps:  71%|███████   | 1416/2000 [42:25<17:05,  1.76s/it, loss=0.185, lr=0.0001]
Steps:  71%|███████   | 1416/2000 [42:25<17:05,  1.76s/it, loss=0.131, lr=0.0001]
Steps:  71%|███████   | 1416/2000 [42:26<17:05,  1.76s/it, loss=0.178, lr=0.0001]
Steps:  71%|███████   | 1416/2000 [42:26<17:05,  1.76s/it, loss=0.186, lr=0.0001]
Steps:  71%|███████   | 1416/2000 [42:27<17:05,  1.76s/it, loss=0.3, lr=0.0001]  
Steps:  71%|███████   | 1417/2000 [42:27<17:27,  1.80s/it, loss=0.3, lr=0.0001]
Steps:  71%|███████   | 1417/2000 [42:27<17:27,  1.80s/it, loss=0.0984, lr=0.0001]
Steps:  71%|███████   | 1417/2000 [42:28<17:27,  1.80s/it, loss=0.225, lr=0.0001] 
Steps:  71%|███████   | 1417/2000 [42:28<17:27,  1.80s/it, loss=0.213, lr=0.0001]
Steps:  71%|███████   | 1417/2000 [42:28<17:27,  1.80s/it, loss=0.311, lr=0.0001]
Steps:  71%|███████   | 1418/2000 [42:29<16:59,  1.75s/it, loss=0.311, lr=0.0001]
Steps:  71%|███████   | 1418/2000 [42:29<16:59,  1.75s/it, loss=0.146, lr=0.0001]
Steps:  71%|███████   | 1418/2000 [42:29<16:59,  1.75s/it, loss=0.0949, lr=0.0001]
Steps:  71%|███████   | 1418/2000 [42:30<16:59,  1.75s/it, loss=0.468, lr=0.0001] 
Steps:  71%|███████   | 1418/2000 [42:30<16:59,  1.75s/it, loss=0.0844, lr=0.0001]
Steps:  71%|███████   | 1419/2000 [42:31<16:38,  1.72s/it, loss=0.0844, lr=0.0001]
Steps:  71%|███████   | 1419/2000 [42:31<16:38,  1.72s/it, loss=0.158, lr=0.0001] 
Steps:  71%|███████   | 1419/2000 [42:31<16:38,  1.72s/it, loss=0.142, lr=0.0001]
Steps:  71%|███████   | 1419/2000 [42:31<16:38,  1.72s/it, loss=0.216, lr=0.0001]
Steps:  71%|███████   | 1419/2000 [42:32<16:38,  1.72s/it, loss=0.127, lr=0.0001]
Steps:  71%|███████   | 1420/2000 [42:32<17:04,  1.77s/it, loss=0.127, lr=0.0001]
Steps:  71%|███████   | 1420/2000 [42:32<17:04,  1.77s/it, loss=0.339, lr=0.0001]
Steps:  71%|███████   | 1420/2000 [42:33<17:04,  1.77s/it, loss=0.168, lr=0.0001]
Steps:  71%|███████   | 1420/2000 [42:33<17:04,  1.77s/it, loss=0.291, lr=0.0001]
Steps:  71%|███████   | 1420/2000 [42:34<17:04,  1.77s/it, loss=0.149, lr=0.0001]
Steps:  71%|███████   | 1421/2000 [42:34<16:42,  1.73s/it, loss=0.149, lr=0.0001]
Steps:  71%|███████   | 1421/2000 [42:34<16:42,  1.73s/it, loss=0.0819, lr=0.0001]
Steps:  71%|███████   | 1421/2000 [42:34<16:42,  1.73s/it, loss=0.827, lr=0.0001] 
Steps:  71%|███████   | 1421/2000 [42:35<16:42,  1.73s/it, loss=0.183, lr=0.0001]
Steps:  71%|███████   | 1421/2000 [42:35<16:42,  1.73s/it, loss=0.176, lr=0.0001]
Steps:  71%|███████   | 1422/2000 [42:36<16:24,  1.70s/it, loss=0.176, lr=0.0001]
Steps:  71%|███████   | 1422/2000 [42:36<16:24,  1.70s/it, loss=0.0999, lr=0.0001]
Steps:  71%|███████   | 1422/2000 [42:36<16:24,  1.70s/it, loss=0.235, lr=0.0001] 
Steps:  71%|███████   | 1422/2000 [42:36<16:24,  1.70s/it, loss=0.249, lr=0.0001]
Steps:  71%|███████   | 1422/2000 [42:37<16:24,  1.70s/it, loss=0.216, lr=0.0001]
Steps:  71%|███████   | 1423/2000 [42:37<16:12,  1.69s/it, loss=0.216, lr=0.0001]
Steps:  71%|███████   | 1423/2000 [42:37<16:12,  1.69s/it, loss=0.15, lr=0.0001] 
Steps:  71%|███████   | 1423/2000 [42:38<16:12,  1.69s/it, loss=0.234, lr=0.0001]
Steps:  71%|███████   | 1423/2000 [42:38<16:12,  1.69s/it, loss=0.228, lr=0.0001]
Steps:  71%|███████   | 1423/2000 [42:39<16:12,  1.69s/it, loss=0.19, lr=0.0001] 
Steps:  71%|███████   | 1424/2000 [42:39<16:43,  1.74s/it, loss=0.19, lr=0.0001]
Steps:  71%|███████   | 1424/2000 [42:39<16:43,  1.74s/it, loss=0.232, lr=0.0001]
Steps:  71%|███████   | 1424/2000 [42:40<16:43,  1.74s/it, loss=0.106, lr=0.0001]
Steps:  71%|███████   | 1424/2000 [42:40<16:43,  1.74s/it, loss=0.17, lr=0.0001] 
Steps:  71%|███████   | 1424/2000 [42:40<16:43,  1.74s/it, loss=0.148, lr=0.0001]
Steps:  71%|███████▏  | 1425/2000 [42:41<16:24,  1.71s/it, loss=0.148, lr=0.0001]
Steps:  71%|███████▏  | 1425/2000 [42:41<16:24,  1.71s/it, loss=0.144, lr=0.0001]
Steps:  71%|███████▏  | 1425/2000 [42:41<16:24,  1.71s/it, loss=0.126, lr=0.0001]
Steps:  71%|███████▏  | 1425/2000 [42:42<16:24,  1.71s/it, loss=0.16, lr=0.0001] 
Steps:  71%|███████▏  | 1425/2000 [42:42<16:24,  1.71s/it, loss=0.322, lr=0.0001]
Steps:  71%|███████▏  | 1426/2000 [42:42<16:12,  1.69s/it, loss=0.322, lr=0.0001]
Steps:  71%|███████▏  | 1426/2000 [42:42<16:12,  1.69s/it, loss=0.739, lr=0.0001]
Steps:  71%|███████▏  | 1426/2000 [42:43<16:12,  1.69s/it, loss=0.121, lr=0.0001]
Steps:  71%|███████▏  | 1426/2000 [42:44<16:12,  1.69s/it, loss=0.804, lr=0.0001]
Steps:  71%|███████▏  | 1426/2000 [42:44<16:12,  1.69s/it, loss=0.211, lr=0.0001]
Steps:  71%|███████▏  | 1427/2000 [42:44<16:42,  1.75s/it, loss=0.211, lr=0.0001]
Steps:  71%|███████▏  | 1427/2000 [42:44<16:42,  1.75s/it, loss=0.153, lr=0.0001]
Steps:  71%|███████▏  | 1427/2000 [42:45<16:42,  1.75s/it, loss=0.118, lr=0.0001]
Steps:  71%|███████▏  | 1427/2000 [42:45<16:42,  1.75s/it, loss=0.344, lr=0.0001]
Steps:  71%|███████▏  | 1427/2000 [42:46<16:42,  1.75s/it, loss=0.131, lr=0.0001]
Steps:  71%|███████▏  | 1428/2000 [42:46<16:25,  1.72s/it, loss=0.131, lr=0.0001]
Steps:  71%|███████▏  | 1428/2000 [42:46<16:25,  1.72s/it, loss=0.151, lr=0.0001]
Steps:  71%|███████▏  | 1428/2000 [42:46<16:25,  1.72s/it, loss=0.0655, lr=0.0001]
Steps:  71%|███████▏  | 1428/2000 [42:47<16:25,  1.72s/it, loss=0.295, lr=0.0001] 
Steps:  71%|███████▏  | 1428/2000 [42:47<16:25,  1.72s/it, loss=0.218, lr=0.0001]
Steps:  71%|███████▏  | 1429/2000 [42:48<16:10,  1.70s/it, loss=0.218, lr=0.0001]
Steps:  71%|███████▏  | 1429/2000 [42:48<16:10,  1.70s/it, loss=0.183, lr=0.0001]
Steps:  71%|███████▏  | 1429/2000 [42:48<16:10,  1.70s/it, loss=0.198, lr=0.0001]
Steps:  71%|███████▏  | 1429/2000 [42:49<16:10,  1.70s/it, loss=0.143, lr=0.0001]
Steps:  71%|███████▏  | 1429/2000 [42:49<16:10,  1.70s/it, loss=0.139, lr=0.0001]
Steps:  72%|███████▏  | 1430/2000 [42:50<16:40,  1.76s/it, loss=0.139, lr=0.0001]
Steps:  72%|███████▏  | 1430/2000 [42:50<16:40,  1.76s/it, loss=0.136, lr=0.0001]05/30/2026 09:15:15 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/config.json "HTTP/1.1 200 OK"
05/30/2026 09:15:15 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/config.json "HTTP/1.1 200 OK"
05/30/2026 09:15:15 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/model.safetensors "HTTP/1.1 302 Found"


Loading weights:   0%|          | 0/196 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 196/196 [00:00<00:00, 7137.07it/s]
05/30/2026 09:15:15 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/config.json "HTTP/1.1 200 OK"
05/30/2026 09:15:15 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/config.json "HTTP/1.1 200 OK"
05/30/2026 09:15:15 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/model.safetensors "HTTP/1.1 404 Not Found"
05/30/2026 09:15:16 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/model.safetensors.index.json "HTTP/1.1 200 OK"
05/30/2026 09:15:16 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev/revision/main "HTTP/1.1 200 OK"


Fetching 2 files:   0%|          | 0/2 [00:00<?, ?it/s]
Fetching 2 files: 100%|██████████| 2/2 [00:00<00:00, 4405.78it/s]


Loading weights:   0%|          | 0/219 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 219/219 [00:00<00:00, 7031.12it/s]
05/30/2026 09:15:16 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev "HTTP/1.1 200 OK"
05/30/2026 09:15:16 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/model_index.json "HTTP/1.1 200 OK"
{'feature_extractor', 'image_encoder'} was not found in config. Values will be initialized to default values.


Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]Loaded tokenizer_2 as T5TokenizerFast from `tokenizer_2` subfolder of black-forest-labs/FLUX.1-dev.


Loading pipeline components...:  43%|████▎     | 3/7 [00:00<00:00, 17.29it/s]Loaded tokenizer as CLIPTokenizer from `tokenizer` subfolder of black-forest-labs/FLUX.1-dev.
{'stochastic_sampling', 'use_beta_sigmas', 'invert_sigmas', 'time_shift_type', 'use_exponential_sigmas', 'shift_terminal', 'use_karras_sigmas'} was not found in config. Values will be initialized to default values.
Loaded scheduler as FlowMatchEulerDiscreteScheduler from `scheduler` subfolder of black-forest-labs/FLUX.1-dev.

Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 28.14it/s]
05/30/2026 09:15:16 - INFO - __main__ - [RANK 0] Running validation... 
 Generating 1 images with prompt: emj icon of a pelican with a hat, centered on a plain white background.

Steps:  72%|███████▏  | 1430/2000 [43:02<16:40,  1.76s/it, loss=0.146, lr=0.0001]
Steps:  72%|███████▏  | 1430/2000 [43:02<16:40,  1.76s/it, loss=0.13, lr=0.0001] 
Steps:  72%|███████▏  | 1430/2000 [43:03<16:40,  1.76s/it, loss=0.298, lr=0.0001]
Steps:  72%|███████▏  | 1431/2000 [43:03<50:27,  5.32s/it, loss=0.298, lr=0.0001]
Steps:  72%|███████▏  | 1431/2000 [43:03<50:27,  5.32s/it, loss=0.0708, lr=0.0001]
Steps:  72%|███████▏  | 1431/2000 [43:04<50:27,  5.32s/it, loss=0.0966, lr=0.0001]
Steps:  72%|███████▏  | 1431/2000 [43:04<50:27,  5.32s/it, loss=0.274, lr=0.0001] 
Steps:  72%|███████▏  | 1431/2000 [43:04<50:27,  5.32s/it, loss=0.129, lr=0.0001]
Steps:  72%|███████▏  | 1432/2000 [43:05<40:01,  4.23s/it, loss=0.129, lr=0.0001]
Steps:  72%|███████▏  | 1432/2000 [43:05<40:01,  4.23s/it, loss=0.148, lr=0.0001]
Steps:  72%|███████▏  | 1432/2000 [43:05<40:01,  4.23s/it, loss=0.0992, lr=0.0001]
Steps:  72%|███████▏  | 1432/2000 [43:06<40:01,  4.23s/it, loss=0.237, lr=0.0001] 
Steps:  72%|███████▏  | 1432/2000 [43:06<40:01,  4.23s/it, loss=0.155, lr=0.0001]
Steps:  72%|███████▏  | 1433/2000 [43:07<32:39,  3.46s/it, loss=0.155, lr=0.0001]
Steps:  72%|███████▏  | 1433/2000 [43:07<32:39,  3.46s/it, loss=0.568, lr=0.0001]
Steps:  72%|███████▏  | 1433/2000 [43:07<32:39,  3.46s/it, loss=0.156, lr=0.0001]
Steps:  72%|███████▏  | 1433/2000 [43:08<32:39,  3.46s/it, loss=0.228, lr=0.0001]
Steps:  72%|███████▏  | 1433/2000 [43:08<32:39,  3.46s/it, loss=0.198, lr=0.0001]
Steps:  72%|███████▏  | 1434/2000 [43:08<28:14,  2.99s/it, loss=0.198, lr=0.0001]
Steps:  72%|███████▏  | 1434/2000 [43:08<28:14,  2.99s/it, loss=0.0866, lr=0.0001]
Steps:  72%|███████▏  | 1434/2000 [43:09<28:14,  2.99s/it, loss=0.146, lr=0.0001] 
Steps:  72%|███████▏  | 1434/2000 [43:09<28:14,  2.99s/it, loss=0.286, lr=0.0001]
Steps:  72%|███████▏  | 1434/2000 [43:10<28:14,  2.99s/it, loss=0.168, lr=0.0001]
Steps:  72%|███████▏  | 1435/2000 [43:10<24:25,  2.59s/it, loss=0.168, lr=0.0001]
Steps:  72%|███████▏  | 1435/2000 [43:10<24:25,  2.59s/it, loss=0.0349, lr=0.0001]
Steps:  72%|███████▏  | 1435/2000 [43:11<24:25,  2.59s/it, loss=0.0868, lr=0.0001]
Steps:  72%|███████▏  | 1435/2000 [43:11<24:25,  2.59s/it, loss=0.197, lr=0.0001] 
Steps:  72%|███████▏  | 1435/2000 [43:11<24:25,  2.59s/it, loss=0.08, lr=0.0001] 
Steps:  72%|███████▏  | 1436/2000 [43:12<21:44,  2.31s/it, loss=0.08, lr=0.0001]
Steps:  72%|███████▏  | 1436/2000 [43:12<21:44,  2.31s/it, loss=0.173, lr=0.0001]
Steps:  72%|███████▏  | 1436/2000 [43:12<21:44,  2.31s/it, loss=0.21, lr=0.0001] 
Steps:  72%|███████▏  | 1436/2000 [43:13<21:44,  2.31s/it, loss=0.132, lr=0.0001]
Steps:  72%|███████▏  | 1436/2000 [43:13<21:44,  2.31s/it, loss=0.227, lr=0.0001]
Steps:  72%|███████▏  | 1437/2000 [43:14<20:30,  2.19s/it, loss=0.227, lr=0.0001]
Steps:  72%|███████▏  | 1437/2000 [43:14<20:30,  2.19s/it, loss=0.149, lr=0.0001]
Steps:  72%|███████▏  | 1437/2000 [43:14<20:30,  2.19s/it, loss=0.182, lr=0.0001]
Steps:  72%|███████▏  | 1437/2000 [43:14<20:30,  2.19s/it, loss=0.174, lr=0.0001]
Steps:  72%|███████▏  | 1437/2000 [43:15<20:30,  2.19s/it, loss=0.198, lr=0.0001]
Steps:  72%|███████▏  | 1438/2000 [43:15<19:01,  2.03s/it, loss=0.198, lr=0.0001]
Steps:  72%|███████▏  | 1438/2000 [43:15<19:01,  2.03s/it, loss=0.0927, lr=0.0001]
Steps:  72%|███████▏  | 1438/2000 [43:16<19:01,  2.03s/it, loss=0.214, lr=0.0001] 
Steps:  72%|███████▏  | 1438/2000 [43:16<19:01,  2.03s/it, loss=0.222, lr=0.0001]
Steps:  72%|███████▏  | 1438/2000 [43:17<19:01,  2.03s/it, loss=0.224, lr=0.0001]
Steps:  72%|███████▏  | 1439/2000 [43:17<17:56,  1.92s/it, loss=0.224, lr=0.0001]
Steps:  72%|███████▏  | 1439/2000 [43:17<17:56,  1.92s/it, loss=0.247, lr=0.0001]
Steps:  72%|███████▏  | 1439/2000 [43:17<17:56,  1.92s/it, loss=0.171, lr=0.0001]
Steps:  72%|███████▏  | 1439/2000 [43:18<17:56,  1.92s/it, loss=0.145, lr=0.0001]
Steps:  72%|███████▏  | 1439/2000 [43:18<17:56,  1.92s/it, loss=0.205, lr=0.0001]
Steps:  72%|███████▏  | 1440/2000 [43:19<17:51,  1.91s/it, loss=0.205, lr=0.0001]
Steps:  72%|███████▏  | 1440/2000 [43:19<17:51,  1.91s/it, loss=0.107, lr=0.0001]
Steps:  72%|███████▏  | 1440/2000 [43:19<17:51,  1.91s/it, loss=0.282, lr=0.0001]
Steps:  72%|███████▏  | 1440/2000 [43:20<17:51,  1.91s/it, loss=0.161, lr=0.0001]
Steps:  72%|███████▏  | 1440/2000 [43:20<17:51,  1.91s/it, loss=0.202, lr=0.0001]
Steps:  72%|███████▏  | 1441/2000 [43:21<17:06,  1.84s/it, loss=0.202, lr=0.0001]
Steps:  72%|███████▏  | 1441/2000 [43:21<17:06,  1.84s/it, loss=0.161, lr=0.0001]
Steps:  72%|███████▏  | 1441/2000 [43:21<17:06,  1.84s/it, loss=0.698, lr=0.0001]
Steps:  72%|███████▏  | 1441/2000 [43:21<17:06,  1.84s/it, loss=0.0552, lr=0.0001]
Steps:  72%|███████▏  | 1441/2000 [43:22<17:06,  1.84s/it, loss=0.187, lr=0.0001] 
Steps:  72%|███████▏  | 1442/2000 [43:22<16:37,  1.79s/it, loss=0.187, lr=0.0001]
Steps:  72%|███████▏  | 1442/2000 [43:22<16:37,  1.79s/it, loss=0.277, lr=0.0001]
Steps:  72%|███████▏  | 1442/2000 [43:23<16:37,  1.79s/it, loss=0.165, lr=0.0001]
Steps:  72%|███████▏  | 1442/2000 [43:23<16:37,  1.79s/it, loss=0.159, lr=0.0001]
Steps:  72%|███████▏  | 1442/2000 [43:24<16:37,  1.79s/it, loss=0.081, lr=0.0001]
Steps:  72%|███████▏  | 1443/2000 [43:24<16:54,  1.82s/it, loss=0.081, lr=0.0001]
Steps:  72%|███████▏  | 1443/2000 [43:24<16:54,  1.82s/it, loss=0.315, lr=0.0001]
Steps:  72%|███████▏  | 1443/2000 [43:25<16:54,  1.82s/it, loss=0.187, lr=0.0001]
Steps:  72%|███████▏  | 1443/2000 [43:25<16:54,  1.82s/it, loss=0.168, lr=0.0001]
Steps:  72%|███████▏  | 1443/2000 [43:25<16:54,  1.82s/it, loss=0.154, lr=0.0001]
Steps:  72%|███████▏  | 1444/2000 [43:26<16:26,  1.77s/it, loss=0.154, lr=0.0001]
Steps:  72%|███████▏  | 1444/2000 [43:26<16:26,  1.77s/it, loss=0.415, lr=0.0001]
Steps:  72%|███████▏  | 1444/2000 [43:26<16:26,  1.77s/it, loss=0.308, lr=0.0001]
Steps:  72%|███████▏  | 1444/2000 [43:27<16:26,  1.77s/it, loss=0.19, lr=0.0001] 
Steps:  72%|███████▏  | 1444/2000 [43:27<16:26,  1.77s/it, loss=0.212, lr=0.0001]
Steps:  72%|███████▏  | 1445/2000 [43:27<16:11,  1.75s/it, loss=0.212, lr=0.0001]
Steps:  72%|███████▏  | 1445/2000 [43:27<16:11,  1.75s/it, loss=0.175, lr=0.0001]
Steps:  72%|███████▏  | 1445/2000 [43:28<16:11,  1.75s/it, loss=0.39, lr=0.0001] 
Steps:  72%|███████▏  | 1445/2000 [43:28<16:11,  1.75s/it, loss=0.214, lr=0.0001]
Steps:  72%|███████▏  | 1445/2000 [43:29<16:11,  1.75s/it, loss=0.226, lr=0.0001]
Steps:  72%|███████▏  | 1446/2000 [43:29<16:40,  1.81s/it, loss=0.226, lr=0.0001]
Steps:  72%|███████▏  | 1446/2000 [43:29<16:40,  1.81s/it, loss=0.359, lr=0.0001]
Steps:  72%|███████▏  | 1446/2000 [43:30<16:40,  1.81s/it, loss=0.384, lr=0.0001]
Steps:  72%|███████▏  | 1446/2000 [43:30<16:40,  1.81s/it, loss=0.301, lr=0.0001]
Steps:  72%|███████▏  | 1446/2000 [43:31<16:40,  1.81s/it, loss=0.278, lr=0.0001]
Steps:  72%|███████▏  | 1447/2000 [43:31<16:15,  1.76s/it, loss=0.278, lr=0.0001]
Steps:  72%|███████▏  | 1447/2000 [43:31<16:15,  1.76s/it, loss=0.15, lr=0.0001] 
Steps:  72%|███████▏  | 1447/2000 [43:31<16:15,  1.76s/it, loss=0.153, lr=0.0001]
Steps:  72%|███████▏  | 1447/2000 [43:32<16:15,  1.76s/it, loss=0.112, lr=0.0001]
Steps:  72%|███████▏  | 1447/2000 [43:32<16:15,  1.76s/it, loss=0.257, lr=0.0001]
Steps:  72%|███████▏  | 1448/2000 [43:33<16:03,  1.74s/it, loss=0.257, lr=0.0001]
Steps:  72%|███████▏  | 1448/2000 [43:33<16:03,  1.74s/it, loss=0.522, lr=0.0001]
Steps:  72%|███████▏  | 1448/2000 [43:33<16:03,  1.74s/it, loss=0.31, lr=0.0001] 
Steps:  72%|███████▏  | 1448/2000 [43:34<16:03,  1.74s/it, loss=0.165, lr=0.0001]
Steps:  72%|███████▏  | 1448/2000 [43:34<16:03,  1.74s/it, loss=0.148, lr=0.0001]
Steps:  72%|███████▏  | 1449/2000 [43:35<16:25,  1.79s/it, loss=0.148, lr=0.0001]
Steps:  72%|███████▏  | 1449/2000 [43:35<16:25,  1.79s/it, loss=0.154, lr=0.0001]
Steps:  72%|███████▏  | 1449/2000 [43:35<16:25,  1.79s/it, loss=0.127, lr=0.0001]
Steps:  72%|███████▏  | 1449/2000 [43:35<16:25,  1.79s/it, loss=0.548, lr=0.0001]
Steps:  72%|███████▏  | 1449/2000 [43:36<16:25,  1.79s/it, loss=0.139, lr=0.0001]
Steps:  72%|███████▎  | 1450/2000 [43:36<16:02,  1.75s/it, loss=0.139, lr=0.0001]
Steps:  72%|███████▎  | 1450/2000 [43:36<16:02,  1.75s/it, loss=0.238, lr=0.0001]
Steps:  72%|███████▎  | 1450/2000 [43:37<16:02,  1.75s/it, loss=0.269, lr=0.0001]
Steps:  72%|███████▎  | 1450/2000 [43:37<16:02,  1.75s/it, loss=0.201, lr=0.0001]
Steps:  72%|███████▎  | 1450/2000 [43:38<16:02,  1.75s/it, loss=0.142, lr=0.0001]
Steps:  73%|███████▎  | 1451/2000 [43:38<15:47,  1.73s/it, loss=0.142, lr=0.0001]
Steps:  73%|███████▎  | 1451/2000 [43:38<15:47,  1.73s/it, loss=0.112, lr=0.0001]
Steps:  73%|███████▎  | 1451/2000 [43:38<15:47,  1.73s/it, loss=0.157, lr=0.0001]
Steps:  73%|███████▎  | 1451/2000 [43:39<15:47,  1.73s/it, loss=0.225, lr=0.0001]
Steps:  73%|███████▎  | 1451/2000 [43:39<15:47,  1.73s/it, loss=0.083, lr=0.0001]
Steps:  73%|███████▎  | 1452/2000 [43:40<15:36,  1.71s/it, loss=0.083, lr=0.0001]
Steps:  73%|███████▎  | 1452/2000 [43:40<15:36,  1.71s/it, loss=0.136, lr=0.0001]
Steps:  73%|███████▎  | 1452/2000 [43:40<15:36,  1.71s/it, loss=0.151, lr=0.0001]
Steps:  73%|███████▎  | 1452/2000 [43:41<15:36,  1.71s/it, loss=0.193, lr=0.0001]
Steps:  73%|███████▎  | 1452/2000 [43:41<15:36,  1.71s/it, loss=0.203, lr=0.0001]
Steps:  73%|███████▎  | 1453/2000 [43:42<16:08,  1.77s/it, loss=0.203, lr=0.0001]
Steps:  73%|███████▎  | 1453/2000 [43:42<16:08,  1.77s/it, loss=0.13, lr=0.0001] 
Steps:  73%|███████▎  | 1453/2000 [43:42<16:08,  1.77s/it, loss=0.213, lr=0.0001]
Steps:  73%|███████▎  | 1453/2000 [43:42<16:08,  1.77s/it, loss=0.164, lr=0.0001]
Steps:  73%|███████▎  | 1453/2000 [43:43<16:08,  1.77s/it, loss=0.0865, lr=0.0001]
Steps:  73%|███████▎  | 1454/2000 [43:43<15:51,  1.74s/it, loss=0.0865, lr=0.0001]
Steps:  73%|███████▎  | 1454/2000 [43:43<15:51,  1.74s/it, loss=0.153, lr=0.0001] 
Steps:  73%|███████▎  | 1454/2000 [43:44<15:51,  1.74s/it, loss=0.0909, lr=0.0001]
Steps:  73%|███████▎  | 1454/2000 [43:44<15:51,  1.74s/it, loss=0.115, lr=0.0001] 
Steps:  73%|███████▎  | 1454/2000 [43:44<15:51,  1.74s/it, loss=0.412, lr=0.0001]
Steps:  73%|███████▎  | 1455/2000 [43:45<15:36,  1.72s/it, loss=0.412, lr=0.0001]
Steps:  73%|███████▎  | 1455/2000 [43:45<15:36,  1.72s/it, loss=0.195, lr=0.0001]
Steps:  73%|███████▎  | 1455/2000 [43:45<15:36,  1.72s/it, loss=0.406, lr=0.0001]
Steps:  73%|███████▎  | 1455/2000 [43:46<15:36,  1.72s/it, loss=0.192, lr=0.0001]
Steps:  73%|███████▎  | 1455/2000 [43:46<15:36,  1.72s/it, loss=0.555, lr=0.0001]
Steps:  73%|███████▎  | 1456/2000 [43:47<16:15,  1.79s/it, loss=0.555, lr=0.0001]
Steps:  73%|███████▎  | 1456/2000 [43:47<16:15,  1.79s/it, loss=0.165, lr=0.0001]
Steps:  73%|███████▎  | 1456/2000 [43:47<16:15,  1.79s/it, loss=0.125, lr=0.0001]
Steps:  73%|███████▎  | 1456/2000 [43:48<16:15,  1.79s/it, loss=0.335, lr=0.0001]
Steps:  73%|███████▎  | 1456/2000 [43:48<16:15,  1.79s/it, loss=0.735, lr=0.0001]
Steps:  73%|███████▎  | 1457/2000 [43:49<15:53,  1.76s/it, loss=0.735, lr=0.0001]
Steps:  73%|███████▎  | 1457/2000 [43:49<15:53,  1.76s/it, loss=0.15, lr=0.0001] 
Steps:  73%|███████▎  | 1457/2000 [43:49<15:53,  1.76s/it, loss=0.459, lr=0.0001]
Steps:  73%|███████▎  | 1457/2000 [43:49<15:53,  1.76s/it, loss=0.0867, lr=0.0001]
Steps:  73%|███████▎  | 1457/2000 [43:50<15:53,  1.76s/it, loss=0.262, lr=0.0001] 
Steps:  73%|███████▎  | 1458/2000 [43:50<15:37,  1.73s/it, loss=0.262, lr=0.0001]
Steps:  73%|███████▎  | 1458/2000 [43:50<15:37,  1.73s/it, loss=0.226, lr=0.0001]
Steps:  73%|███████▎  | 1458/2000 [43:51<15:37,  1.73s/it, loss=0.267, lr=0.0001]
Steps:  73%|███████▎  | 1458/2000 [43:51<15:37,  1.73s/it, loss=0.236, lr=0.0001]
Steps:  73%|███████▎  | 1458/2000 [43:52<15:37,  1.73s/it, loss=1.54, lr=0.0001] 
Steps:  73%|███████▎  | 1459/2000 [43:52<16:03,  1.78s/it, loss=1.54, lr=0.0001]
Steps:  73%|███████▎  | 1459/2000 [43:52<16:03,  1.78s/it, loss=0.359, lr=0.0001]
Steps:  73%|███████▎  | 1459/2000 [43:53<16:03,  1.78s/it, loss=0.105, lr=0.0001]
Steps:  73%|███████▎  | 1459/2000 [43:53<16:03,  1.78s/it, loss=0.186, lr=0.0001]
Steps:  73%|███████▎  | 1459/2000 [43:53<16:03,  1.78s/it, loss=0.411, lr=0.0001]
Steps:  73%|███████▎  | 1460/2000 [43:54<15:45,  1.75s/it, loss=0.411, lr=0.0001]
Steps:  73%|███████▎  | 1460/2000 [43:54<15:45,  1.75s/it, loss=0.172, lr=0.0001]
Steps:  73%|███████▎  | 1460/2000 [43:54<15:45,  1.75s/it, loss=0.3, lr=0.0001]  
Steps:  73%|███████▎  | 1460/2000 [43:55<15:45,  1.75s/it, loss=0.181, lr=0.0001]
Steps:  73%|███████▎  | 1460/2000 [43:55<15:45,  1.75s/it, loss=0.147, lr=0.0001]
Steps:  73%|███████▎  | 1461/2000 [43:55<15:32,  1.73s/it, loss=0.147, lr=0.0001]
Steps:  73%|███████▎  | 1461/2000 [43:55<15:32,  1.73s/it, loss=0.512, lr=0.0001]
Steps:  73%|███████▎  | 1461/2000 [43:56<15:32,  1.73s/it, loss=0.255, lr=0.0001]
Steps:  73%|███████▎  | 1461/2000 [43:57<15:32,  1.73s/it, loss=0.213, lr=0.0001]
Steps:  73%|███████▎  | 1461/2000 [43:57<15:32,  1.73s/it, loss=0.273, lr=0.0001]
Steps:  73%|███████▎  | 1462/2000 [43:57<16:05,  1.79s/it, loss=0.273, lr=0.0001]
Steps:  73%|███████▎  | 1462/2000 [43:57<16:05,  1.79s/it, loss=0.166, lr=0.0001]
Steps:  73%|███████▎  | 1462/2000 [43:58<16:05,  1.79s/it, loss=0.253, lr=0.0001]
Steps:  73%|███████▎  | 1462/2000 [43:58<16:05,  1.79s/it, loss=0.1, lr=0.0001]  
Steps:  73%|███████▎  | 1462/2000 [43:59<16:05,  1.79s/it, loss=0.162, lr=0.0001]
Steps:  73%|███████▎  | 1463/2000 [43:59<15:42,  1.76s/it, loss=0.162, lr=0.0001]
Steps:  73%|███████▎  | 1463/2000 [43:59<15:42,  1.76s/it, loss=0.18, lr=0.0001] 
Steps:  73%|███████▎  | 1463/2000 [43:59<15:42,  1.76s/it, loss=0.191, lr=0.0001]
Steps:  73%|███████▎  | 1463/2000 [44:00<15:42,  1.76s/it, loss=0.227, lr=0.0001]
Steps:  73%|███████▎  | 1463/2000 [44:00<15:42,  1.76s/it, loss=0.168, lr=0.0001]
Steps:  73%|███████▎  | 1464/2000 [44:01<15:28,  1.73s/it, loss=0.168, lr=0.0001]
Steps:  73%|███████▎  | 1464/2000 [44:01<15:28,  1.73s/it, loss=0.149, lr=0.0001]
Steps:  73%|███████▎  | 1464/2000 [44:01<15:28,  1.73s/it, loss=0.102, lr=0.0001]
Steps:  73%|███████▎  | 1464/2000 [44:02<15:28,  1.73s/it, loss=0.217, lr=0.0001]
Steps:  73%|███████▎  | 1464/2000 [44:02<15:28,  1.73s/it, loss=0.233, lr=0.0001]
Steps:  73%|███████▎  | 1465/2000 [44:03<15:56,  1.79s/it, loss=0.233, lr=0.0001]
Steps:  73%|███████▎  | 1465/2000 [44:03<15:56,  1.79s/it, loss=0.123, lr=0.0001]
Steps:  73%|███████▎  | 1465/2000 [44:03<15:56,  1.79s/it, loss=0.169, lr=0.0001]
Steps:  73%|███████▎  | 1465/2000 [44:03<15:56,  1.79s/it, loss=0.0709, lr=0.0001]
Steps:  73%|███████▎  | 1465/2000 [44:04<15:56,  1.79s/it, loss=0.137, lr=0.0001] 
Steps:  73%|███████▎  | 1466/2000 [44:04<15:33,  1.75s/it, loss=0.137, lr=0.0001]
Steps:  73%|███████▎  | 1466/2000 [44:04<15:33,  1.75s/it, loss=0.101, lr=0.0001]
Steps:  73%|███████▎  | 1466/2000 [44:05<15:33,  1.75s/it, loss=0.125, lr=0.0001]
Steps:  73%|███████▎  | 1466/2000 [44:05<15:33,  1.75s/it, loss=0.187, lr=0.0001]
Steps:  73%|███████▎  | 1466/2000 [44:06<15:33,  1.75s/it, loss=0.184, lr=0.0001]
Steps:  73%|███████▎  | 1467/2000 [44:06<15:17,  1.72s/it, loss=0.184, lr=0.0001]
Steps:  73%|███████▎  | 1467/2000 [44:06<15:17,  1.72s/it, loss=0.155, lr=0.0001]
Steps:  73%|███████▎  | 1467/2000 [44:06<15:17,  1.72s/it, loss=0.159, lr=0.0001]
Steps:  73%|███████▎  | 1467/2000 [44:07<15:17,  1.72s/it, loss=0.144, lr=0.0001]
Steps:  73%|███████▎  | 1467/2000 [44:07<15:17,  1.72s/it, loss=0.117, lr=0.0001]
Steps:  73%|███████▎  | 1468/2000 [44:08<15:45,  1.78s/it, loss=0.117, lr=0.0001]
Steps:  73%|███████▎  | 1468/2000 [44:08<15:45,  1.78s/it, loss=0.146, lr=0.0001]
Steps:  73%|███████▎  | 1468/2000 [44:08<15:45,  1.78s/it, loss=0.132, lr=0.0001]
Steps:  73%|███████▎  | 1468/2000 [44:09<15:45,  1.78s/it, loss=0.283, lr=0.0001]
Steps:  73%|███████▎  | 1468/2000 [44:09<15:45,  1.78s/it, loss=0.192, lr=0.0001]
Steps:  73%|███████▎  | 1469/2000 [44:10<15:30,  1.75s/it, loss=0.192, lr=0.0001]
Steps:  73%|███████▎  | 1469/2000 [44:10<15:30,  1.75s/it, loss=0.276, lr=0.0001]
Steps:  73%|███████▎  | 1469/2000 [44:10<15:30,  1.75s/it, loss=0.303, lr=0.0001]
Steps:  73%|███████▎  | 1469/2000 [44:10<15:30,  1.75s/it, loss=0.194, lr=0.0001]
Steps:  73%|███████▎  | 1469/2000 [44:11<15:30,  1.75s/it, loss=0.115, lr=0.0001]
Steps:  74%|███████▎  | 1470/2000 [44:11<15:15,  1.73s/it, loss=0.115, lr=0.0001]
Steps:  74%|███████▎  | 1470/2000 [44:11<15:15,  1.73s/it, loss=0.315, lr=0.0001]
Steps:  74%|███████▎  | 1470/2000 [44:12<15:15,  1.73s/it, loss=0.205, lr=0.0001]
Steps:  74%|███████▎  | 1470/2000 [44:12<15:15,  1.73s/it, loss=0.158, lr=0.0001]
Steps:  74%|███████▎  | 1470/2000 [44:12<15:15,  1.73s/it, loss=0.123, lr=0.0001]
Steps:  74%|███████▎  | 1471/2000 [44:13<15:03,  1.71s/it, loss=0.123, lr=0.0001]
Steps:  74%|███████▎  | 1471/2000 [44:13<15:03,  1.71s/it, loss=0.13, lr=0.0001] 
Steps:  74%|███████▎  | 1471/2000 [44:14<15:03,  1.71s/it, loss=0.424, lr=0.0001]
Steps:  74%|███████▎  | 1471/2000 [44:14<15:03,  1.71s/it, loss=0.324, lr=0.0001]
Steps:  74%|███████▎  | 1471/2000 [44:14<15:03,  1.71s/it, loss=0.213, lr=0.0001]
Steps:  74%|███████▎  | 1472/2000 [44:15<15:30,  1.76s/it, loss=0.213, lr=0.0001]
Steps:  74%|███████▎  | 1472/2000 [44:15<15:30,  1.76s/it, loss=0.212, lr=0.0001]
Steps:  74%|███████▎  | 1472/2000 [44:15<15:30,  1.76s/it, loss=0.0488, lr=0.0001]
Steps:  74%|███████▎  | 1472/2000 [44:16<15:30,  1.76s/it, loss=0.223, lr=0.0001] 
Steps:  74%|███████▎  | 1472/2000 [44:16<15:30,  1.76s/it, loss=0.125, lr=0.0001]
Steps:  74%|███████▎  | 1473/2000 [44:16<15:15,  1.74s/it, loss=0.125, lr=0.0001]
Steps:  74%|███████▎  | 1473/2000 [44:16<15:15,  1.74s/it, loss=0.273, lr=0.0001]
Steps:  74%|███████▎  | 1473/2000 [44:17<15:15,  1.74s/it, loss=0.124, lr=0.0001]
Steps:  74%|███████▎  | 1473/2000 [44:17<15:15,  1.74s/it, loss=0.247, lr=0.0001]
Steps:  74%|███████▎  | 1473/2000 [44:18<15:15,  1.74s/it, loss=0.0908, lr=0.0001]
Steps:  74%|███████▎  | 1474/2000 [44:18<15:00,  1.71s/it, loss=0.0908, lr=0.0001]
Steps:  74%|███████▎  | 1474/2000 [44:18<15:00,  1.71s/it, loss=0.0486, lr=0.0001]
Steps:  74%|███████▎  | 1474/2000 [44:19<15:00,  1.71s/it, loss=0.168, lr=0.0001] 
Steps:  74%|███████▎  | 1474/2000 [44:19<15:00,  1.71s/it, loss=0.189, lr=0.0001]
Steps:  74%|███████▎  | 1474/2000 [44:20<15:00,  1.71s/it, loss=0.251, lr=0.0001]
Steps:  74%|███████▍  | 1475/2000 [44:20<15:29,  1.77s/it, loss=0.251, lr=0.0001]
Steps:  74%|███████▍  | 1475/2000 [44:20<15:29,  1.77s/it, loss=0.238, lr=0.0001]
Steps:  74%|███████▍  | 1475/2000 [44:20<15:29,  1.77s/it, loss=0.261, lr=0.0001]
Steps:  74%|███████▍  | 1475/2000 [44:21<15:29,  1.77s/it, loss=0.146, lr=0.0001]
Steps:  74%|███████▍  | 1475/2000 [44:21<15:29,  1.77s/it, loss=0.288, lr=0.0001]
Steps:  74%|███████▍  | 1476/2000 [44:22<15:12,  1.74s/it, loss=0.288, lr=0.0001]
Steps:  74%|███████▍  | 1476/2000 [44:22<15:12,  1.74s/it, loss=0.189, lr=0.0001]
Steps:  74%|███████▍  | 1476/2000 [44:22<15:12,  1.74s/it, loss=0.0702, lr=0.0001]
Steps:  74%|███████▍  | 1476/2000 [44:23<15:12,  1.74s/it, loss=0.15, lr=0.0001]  
Steps:  74%|███████▍  | 1476/2000 [44:23<15:12,  1.74s/it, loss=0.61, lr=0.0001]
Steps:  74%|███████▍  | 1477/2000 [44:23<14:57,  1.72s/it, loss=0.61, lr=0.0001]
Steps:  74%|███████▍  | 1477/2000 [44:23<14:57,  1.72s/it, loss=0.24, lr=0.0001]
Steps:  74%|███████▍  | 1477/2000 [44:24<14:57,  1.72s/it, loss=0.102, lr=0.0001]
Steps:  74%|███████▍  | 1477/2000 [44:24<14:57,  1.72s/it, loss=0.15, lr=0.0001] 
Steps:  74%|███████▍  | 1477/2000 [44:25<14:57,  1.72s/it, loss=0.0872, lr=0.0001]
Steps:  74%|███████▍  | 1478/2000 [44:25<15:23,  1.77s/it, loss=0.0872, lr=0.0001]
Steps:  74%|███████▍  | 1478/2000 [44:25<15:23,  1.77s/it, loss=0.127, lr=0.0001] 
Steps:  74%|███████▍  | 1478/2000 [44:26<15:23,  1.77s/it, loss=0.147, lr=0.0001]
Steps:  74%|███████▍  | 1478/2000 [44:26<15:23,  1.77s/it, loss=0.146, lr=0.0001]
Steps:  74%|███████▍  | 1478/2000 [44:27<15:23,  1.77s/it, loss=0.125, lr=0.0001]
Steps:  74%|███████▍  | 1479/2000 [44:27<15:06,  1.74s/it, loss=0.125, lr=0.0001]
Steps:  74%|███████▍  | 1479/2000 [44:27<15:06,  1.74s/it, loss=0.145, lr=0.0001]
Steps:  74%|███████▍  | 1479/2000 [44:27<15:06,  1.74s/it, loss=0.097, lr=0.0001]
Steps:  74%|███████▍  | 1479/2000 [44:28<15:06,  1.74s/it, loss=0.188, lr=0.0001]
Steps:  74%|███████▍  | 1479/2000 [44:28<15:06,  1.74s/it, loss=0.122, lr=0.0001]
Steps:  74%|███████▍  | 1480/2000 [44:29<14:53,  1.72s/it, loss=0.122, lr=0.0001]
Steps:  74%|███████▍  | 1480/2000 [44:29<14:53,  1.72s/it, loss=0.0727, lr=0.0001]
Steps:  74%|███████▍  | 1480/2000 [44:29<14:53,  1.72s/it, loss=0.118, lr=0.0001] 
Steps:  74%|███████▍  | 1480/2000 [44:30<14:53,  1.72s/it, loss=1.2, lr=0.0001]  
Steps:  74%|███████▍  | 1480/2000 [44:30<14:53,  1.72s/it, loss=0.251, lr=0.0001]
Steps:  74%|███████▍  | 1481/2000 [44:31<15:19,  1.77s/it, loss=0.251, lr=0.0001]
Steps:  74%|███████▍  | 1481/2000 [44:31<15:19,  1.77s/it, loss=0.118, lr=0.0001]
Steps:  74%|███████▍  | 1481/2000 [44:31<15:19,  1.77s/it, loss=0.144, lr=0.0001]
Steps:  74%|███████▍  | 1481/2000 [44:31<15:19,  1.77s/it, loss=0.129, lr=0.0001]
Steps:  74%|███████▍  | 1481/2000 [44:32<15:19,  1.77s/it, loss=0.13, lr=0.0001] 
Steps:  74%|███████▍  | 1482/2000 [44:32<15:02,  1.74s/it, loss=0.13, lr=0.0001]
Steps:  74%|███████▍  | 1482/2000 [44:32<15:02,  1.74s/it, loss=0.154, lr=0.0001]
Steps:  74%|███████▍  | 1482/2000 [44:33<15:02,  1.74s/it, loss=0.62, lr=0.0001] 
Steps:  74%|███████▍  | 1482/2000 [44:33<15:02,  1.74s/it, loss=0.171, lr=0.0001]
Steps:  74%|███████▍  | 1482/2000 [44:33<15:02,  1.74s/it, loss=0.13, lr=0.0001] 
Steps:  74%|███████▍  | 1483/2000 [44:34<14:47,  1.72s/it, loss=0.13, lr=0.0001]
Steps:  74%|███████▍  | 1483/2000 [44:34<14:47,  1.72s/it, loss=0.389, lr=0.0001]
Steps:  74%|███████▍  | 1483/2000 [44:34<14:47,  1.72s/it, loss=0.836, lr=0.0001]
Steps:  74%|███████▍  | 1483/2000 [44:35<14:47,  1.72s/it, loss=0.204, lr=0.0001]
Steps:  74%|███████▍  | 1483/2000 [44:35<14:47,  1.72s/it, loss=0.107, lr=0.0001]
Steps:  74%|███████▍  | 1484/2000 [44:36<15:12,  1.77s/it, loss=0.107, lr=0.0001]
Steps:  74%|███████▍  | 1484/2000 [44:36<15:12,  1.77s/it, loss=0.232, lr=0.0001]
Steps:  74%|███████▍  | 1484/2000 [44:36<15:12,  1.77s/it, loss=0.221, lr=0.0001]
Steps:  74%|███████▍  | 1484/2000 [44:37<15:12,  1.77s/it, loss=0.224, lr=0.0001]
Steps:  74%|███████▍  | 1484/2000 [44:37<15:12,  1.77s/it, loss=0.193, lr=0.0001]
Steps:  74%|███████▍  | 1485/2000 [44:37<14:57,  1.74s/it, loss=0.193, lr=0.0001]
Steps:  74%|███████▍  | 1485/2000 [44:37<14:57,  1.74s/it, loss=0.365, lr=0.0001]
Steps:  74%|███████▍  | 1485/2000 [44:38<14:57,  1.74s/it, loss=0.314, lr=0.0001]
Steps:  74%|███████▍  | 1485/2000 [44:38<14:57,  1.74s/it, loss=0.1, lr=0.0001]  
Steps:  74%|███████▍  | 1485/2000 [44:39<14:57,  1.74s/it, loss=0.193, lr=0.0001]
Steps:  74%|███████▍  | 1486/2000 [44:39<14:44,  1.72s/it, loss=0.193, lr=0.0001]
Steps:  74%|███████▍  | 1486/2000 [44:39<14:44,  1.72s/it, loss=0.163, lr=0.0001]
Steps:  74%|███████▍  | 1486/2000 [44:39<14:44,  1.72s/it, loss=0.0873, lr=0.0001]
Steps:  74%|███████▍  | 1486/2000 [44:40<14:44,  1.72s/it, loss=0.149, lr=0.0001] 
Steps:  74%|███████▍  | 1486/2000 [44:41<14:44,  1.72s/it, loss=0.166, lr=0.0001]
Steps:  74%|███████▍  | 1487/2000 [44:41<15:09,  1.77s/it, loss=0.166, lr=0.0001]
Steps:  74%|███████▍  | 1487/2000 [44:41<15:09,  1.77s/it, loss=0.162, lr=0.0001]
Steps:  74%|███████▍  | 1487/2000 [44:41<15:09,  1.77s/it, loss=0.111, lr=0.0001]
Steps:  74%|███████▍  | 1487/2000 [44:42<15:09,  1.77s/it, loss=0.441, lr=0.0001]
Steps:  74%|███████▍  | 1487/2000 [44:42<15:09,  1.77s/it, loss=0.138, lr=0.0001]
Steps:  74%|███████▍  | 1488/2000 [44:43<14:56,  1.75s/it, loss=0.138, lr=0.0001]
Steps:  74%|███████▍  | 1488/2000 [44:43<14:56,  1.75s/it, loss=0.18, lr=0.0001] 
Steps:  74%|███████▍  | 1488/2000 [44:43<14:56,  1.75s/it, loss=0.178, lr=0.0001]
Steps:  74%|███████▍  | 1488/2000 [44:43<14:56,  1.75s/it, loss=0.0859, lr=0.0001]
Steps:  74%|███████▍  | 1488/2000 [44:44<14:56,  1.75s/it, loss=0.256, lr=0.0001] 
Steps:  74%|███████▍  | 1489/2000 [44:44<14:39,  1.72s/it, loss=0.256, lr=0.0001]
Steps:  74%|███████▍  | 1489/2000 [44:44<14:39,  1.72s/it, loss=0.239, lr=0.0001]
Steps:  74%|███████▍  | 1489/2000 [44:45<14:39,  1.72s/it, loss=0.117, lr=0.0001]
Steps:  74%|███████▍  | 1489/2000 [44:45<14:39,  1.72s/it, loss=0.117, lr=0.0001]
Steps:  74%|███████▍  | 1489/2000 [44:46<14:39,  1.72s/it, loss=0.0876, lr=0.0001]
Steps:  74%|███████▍  | 1490/2000 [44:46<15:07,  1.78s/it, loss=0.0876, lr=0.0001]
Steps:  74%|███████▍  | 1490/2000 [44:46<15:07,  1.78s/it, loss=0.26, lr=0.0001]  
Steps:  74%|███████▍  | 1490/2000 [44:47<15:07,  1.78s/it, loss=0.336, lr=0.0001]
Steps:  74%|███████▍  | 1490/2000 [44:47<15:07,  1.78s/it, loss=0.137, lr=0.0001]
Steps:  74%|███████▍  | 1490/2000 [44:47<15:07,  1.78s/it, loss=0.225, lr=0.0001]
Steps:  75%|███████▍  | 1491/2000 [44:48<14:46,  1.74s/it, loss=0.225, lr=0.0001]
Steps:  75%|███████▍  | 1491/2000 [44:48<14:46,  1.74s/it, loss=0.2, lr=0.0001]  
Steps:  75%|███████▍  | 1491/2000 [44:48<14:46,  1.74s/it, loss=0.0916, lr=0.0001]
Steps:  75%|███████▍  | 1491/2000 [44:49<14:46,  1.74s/it, loss=0.243, lr=0.0001] 
Steps:  75%|███████▍  | 1491/2000 [44:49<14:46,  1.74s/it, loss=0.0307, lr=0.0001]
Steps:  75%|███████▍  | 1492/2000 [44:50<14:33,  1.72s/it, loss=0.0307, lr=0.0001]
Steps:  75%|███████▍  | 1492/2000 [44:50<14:33,  1.72s/it, loss=0.168, lr=0.0001] 
Steps:  75%|███████▍  | 1492/2000 [44:50<14:33,  1.72s/it, loss=0.42, lr=0.0001] 
Steps:  75%|███████▍  | 1492/2000 [44:50<14:33,  1.72s/it, loss=0.228, lr=0.0001]
Steps:  75%|███████▍  | 1492/2000 [44:51<14:33,  1.72s/it, loss=0.211, lr=0.0001]
Steps:  75%|███████▍  | 1493/2000 [44:51<14:28,  1.71s/it, loss=0.211, lr=0.0001]
Steps:  75%|███████▍  | 1493/2000 [44:51<14:28,  1.71s/it, loss=0.163, lr=0.0001]
Steps:  75%|███████▍  | 1493/2000 [44:52<14:28,  1.71s/it, loss=0.188, lr=0.0001]
Steps:  75%|███████▍  | 1493/2000 [44:52<14:28,  1.71s/it, loss=0.255, lr=0.0001]
Steps:  75%|███████▍  | 1493/2000 [44:53<14:28,  1.71s/it, loss=0.18, lr=0.0001] 
Steps:  75%|███████▍  | 1494/2000 [44:53<15:00,  1.78s/it, loss=0.18, lr=0.0001]
Steps:  75%|███████▍  | 1494/2000 [44:53<15:00,  1.78s/it, loss=0.122, lr=0.0001]
Steps:  75%|███████▍  | 1494/2000 [44:54<15:00,  1.78s/it, loss=0.105, lr=0.0001]
Steps:  75%|███████▍  | 1494/2000 [44:54<15:00,  1.78s/it, loss=0.364, lr=0.0001]
Steps:  75%|███████▍  | 1494/2000 [44:54<15:00,  1.78s/it, loss=0.144, lr=0.0001]
Steps:  75%|███████▍  | 1495/2000 [44:55<14:48,  1.76s/it, loss=0.144, lr=0.0001]
Steps:  75%|███████▍  | 1495/2000 [44:55<14:48,  1.76s/it, loss=0.145, lr=0.0001]
Steps:  75%|███████▍  | 1495/2000 [44:55<14:48,  1.76s/it, loss=0.206, lr=0.0001]
Steps:  75%|███████▍  | 1495/2000 [44:56<14:48,  1.76s/it, loss=0.175, lr=0.0001]
Steps:  75%|███████▍  | 1495/2000 [44:56<14:48,  1.76s/it, loss=0.23, lr=0.0001] 
Steps:  75%|███████▍  | 1496/2000 [44:57<14:30,  1.73s/it, loss=0.23, lr=0.0001]
Steps:  75%|███████▍  | 1496/2000 [44:57<14:30,  1.73s/it, loss=0.133, lr=0.0001]
Steps:  75%|███████▍  | 1496/2000 [44:57<14:30,  1.73s/it, loss=0.117, lr=0.0001]
Steps:  75%|███████▍  | 1496/2000 [44:58<14:30,  1.73s/it, loss=0.162, lr=0.0001]
Steps:  75%|███████▍  | 1496/2000 [44:58<14:30,  1.73s/it, loss=0.0973, lr=0.0001]
Steps:  75%|███████▍  | 1497/2000 [44:58<14:51,  1.77s/it, loss=0.0973, lr=0.0001]
Steps:  75%|███████▍  | 1497/2000 [44:58<14:51,  1.77s/it, loss=0.362, lr=0.0001] 
Steps:  75%|███████▍  | 1497/2000 [44:59<14:51,  1.77s/it, loss=0.111, lr=0.0001]
Steps:  75%|███████▍  | 1497/2000 [44:59<14:51,  1.77s/it, loss=0.541, lr=0.0001]
Steps:  75%|███████▍  | 1497/2000 [45:00<14:51,  1.77s/it, loss=0.209, lr=0.0001]
Steps:  75%|███████▍  | 1498/2000 [45:00<14:31,  1.74s/it, loss=0.209, lr=0.0001]
Steps:  75%|███████▍  | 1498/2000 [45:00<14:31,  1.74s/it, loss=0.135, lr=0.0001]
Steps:  75%|███████▍  | 1498/2000 [45:00<14:31,  1.74s/it, loss=0.22, lr=0.0001] 
Steps:  75%|███████▍  | 1498/2000 [45:01<14:31,  1.74s/it, loss=0.121, lr=0.0001]
Steps:  75%|███████▍  | 1498/2000 [45:01<14:31,  1.74s/it, loss=0.22, lr=0.0001] 
Steps:  75%|███████▍  | 1499/2000 [45:02<14:16,  1.71s/it, loss=0.22, lr=0.0001]
Steps:  75%|███████▍  | 1499/2000 [45:02<14:16,  1.71s/it, loss=0.103, lr=0.0001]
Steps:  75%|███████▍  | 1499/2000 [45:02<14:16,  1.71s/it, loss=0.147, lr=0.0001]
Steps:  75%|███████▍  | 1499/2000 [45:03<14:16,  1.71s/it, loss=0.214, lr=0.0001]
Steps:  75%|███████▍  | 1499/2000 [45:03<14:16,  1.71s/it, loss=0.24, lr=0.0001] 
Steps:  75%|███████▌  | 1500/2000 [45:04<14:42,  1.77s/it, loss=0.24, lr=0.0001]05/30/2026 09:17:29 - INFO - accelerate.accelerator - [RANK 0] Saving current state to /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1500
Model weights saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1500/pytorch_lora_weights.safetensors
05/30/2026 09:17:29 - INFO - accelerate.checkpointing - [RANK 0] Optimizer state saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1500/optimizer.bin
05/30/2026 09:17:29 - INFO - accelerate.checkpointing - [RANK 0] Scheduler state saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1500/scheduler.bin
05/30/2026 09:17:29 - INFO - accelerate.checkpointing - [RANK 0] Sampler state for dataloader 0 saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1500/sampler.bin
05/30/2026 09:17:29 - INFO - accelerate.checkpointing - [RANK 0] Random states saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1500/random_states_0.pkl
05/30/2026 09:17:29 - INFO - __main__ - [RANK 0] Saved state to /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1500

Steps:  75%|███████▌  | 1500/2000 [45:04<14:42,  1.77s/it, loss=0.16, lr=0.0001]
Steps:  75%|███████▌  | 1500/2000 [45:05<14:42,  1.77s/it, loss=0.344, lr=0.0001]
Steps:  75%|███████▌  | 1500/2000 [45:05<14:42,  1.77s/it, loss=0.168, lr=0.0001]
Steps:  75%|███████▌  | 1500/2000 [45:06<14:42,  1.77s/it, loss=0.144, lr=0.0001]
Steps:  75%|███████▌  | 1501/2000 [45:06<16:18,  1.96s/it, loss=0.144, lr=0.0001]
Steps:  75%|███████▌  | 1501/2000 [45:06<16:18,  1.96s/it, loss=0.242, lr=0.0001]
Steps:  75%|███████▌  | 1501/2000 [45:06<16:18,  1.96s/it, loss=0.264, lr=0.0001]
Steps:  75%|███████▌  | 1501/2000 [45:07<16:18,  1.96s/it, loss=0.304, lr=0.0001]
Steps:  75%|███████▌  | 1501/2000 [45:07<16:18,  1.96s/it, loss=0.206, lr=0.0001]
Steps:  75%|███████▌  | 1502/2000 [45:08<15:30,  1.87s/it, loss=0.206, lr=0.0001]
Steps:  75%|███████▌  | 1502/2000 [45:08<15:30,  1.87s/it, loss=0.17, lr=0.0001] 
Steps:  75%|███████▌  | 1502/2000 [45:08<15:30,  1.87s/it, loss=0.204, lr=0.0001]
Steps:  75%|███████▌  | 1502/2000 [45:09<15:30,  1.87s/it, loss=0.139, lr=0.0001]
Steps:  75%|███████▌  | 1502/2000 [45:09<15:30,  1.87s/it, loss=0.0985, lr=0.0001]
Steps:  75%|███████▌  | 1503/2000 [45:10<15:33,  1.88s/it, loss=0.0985, lr=0.0001]
Steps:  75%|███████▌  | 1503/2000 [45:10<15:33,  1.88s/it, loss=0.313, lr=0.0001] 
Steps:  75%|███████▌  | 1503/2000 [45:10<15:33,  1.88s/it, loss=0.183, lr=0.0001]
Steps:  75%|███████▌  | 1503/2000 [45:10<15:33,  1.88s/it, loss=0.231, lr=0.0001]
Steps:  75%|███████▌  | 1503/2000 [45:11<15:33,  1.88s/it, loss=0.094, lr=0.0001]
Steps:  75%|███████▌  | 1504/2000 [45:11<15:00,  1.82s/it, loss=0.094, lr=0.0001]
Steps:  75%|███████▌  | 1504/2000 [45:11<15:00,  1.82s/it, loss=0.135, lr=0.0001]
Steps:  75%|███████▌  | 1504/2000 [45:12<15:00,  1.82s/it, loss=0.174, lr=0.0001]
Steps:  75%|███████▌  | 1504/2000 [45:12<15:00,  1.82s/it, loss=1.54, lr=0.0001] 
Steps:  75%|███████▌  | 1504/2000 [45:12<15:00,  1.82s/it, loss=0.23, lr=0.0001]
Steps:  75%|███████▌  | 1505/2000 [45:13<14:35,  1.77s/it, loss=0.23, lr=0.0001]
Steps:  75%|███████▌  | 1505/2000 [45:13<14:35,  1.77s/it, loss=0.215, lr=0.0001]
Steps:  75%|███████▌  | 1505/2000 [45:13<14:35,  1.77s/it, loss=0.177, lr=0.0001]
Steps:  75%|███████▌  | 1505/2000 [45:14<14:35,  1.77s/it, loss=0.139, lr=0.0001]
Steps:  75%|███████▌  | 1505/2000 [45:14<14:35,  1.77s/it, loss=0.121, lr=0.0001]
Steps:  75%|███████▌  | 1506/2000 [45:15<14:52,  1.81s/it, loss=0.121, lr=0.0001]
Steps:  75%|███████▌  | 1506/2000 [45:15<14:52,  1.81s/it, loss=0.347, lr=0.0001]
Steps:  75%|███████▌  | 1506/2000 [45:15<14:52,  1.81s/it, loss=0.278, lr=0.0001]
Steps:  75%|███████▌  | 1506/2000 [45:16<14:52,  1.81s/it, loss=0.0788, lr=0.0001]
Steps:  75%|███████▌  | 1506/2000 [45:16<14:52,  1.81s/it, loss=0.159, lr=0.0001] 
Steps:  75%|███████▌  | 1507/2000 [45:17<14:32,  1.77s/it, loss=0.159, lr=0.0001]
Steps:  75%|███████▌  | 1507/2000 [45:17<14:32,  1.77s/it, loss=0.163, lr=0.0001]
Steps:  75%|███████▌  | 1507/2000 [45:17<14:32,  1.77s/it, loss=0.194, lr=0.0001]
Steps:  75%|███████▌  | 1507/2000 [45:17<14:32,  1.77s/it, loss=0.178, lr=0.0001]
Steps:  75%|███████▌  | 1507/2000 [45:18<14:32,  1.77s/it, loss=0.181, lr=0.0001]
Steps:  75%|███████▌  | 1508/2000 [45:18<14:14,  1.74s/it, loss=0.181, lr=0.0001]
Steps:  75%|███████▌  | 1508/2000 [45:18<14:14,  1.74s/it, loss=0.418, lr=0.0001]
Steps:  75%|███████▌  | 1508/2000 [45:19<14:14,  1.74s/it, loss=0.12, lr=0.0001] 
Steps:  75%|███████▌  | 1508/2000 [45:19<14:14,  1.74s/it, loss=0.0754, lr=0.0001]
Steps:  75%|███████▌  | 1508/2000 [45:20<14:14,  1.74s/it, loss=0.297, lr=0.0001] 
Steps:  75%|███████▌  | 1509/2000 [45:20<14:35,  1.78s/it, loss=0.297, lr=0.0001]
Steps:  75%|███████▌  | 1509/2000 [45:20<14:35,  1.78s/it, loss=0.191, lr=0.0001]
Steps:  75%|███████▌  | 1509/2000 [45:20<14:35,  1.78s/it, loss=0.15, lr=0.0001] 
Steps:  75%|███████▌  | 1509/2000 [45:21<14:35,  1.78s/it, loss=0.0486, lr=0.0001]
Steps:  75%|███████▌  | 1509/2000 [45:21<14:35,  1.78s/it, loss=0.176, lr=0.0001] 
Steps:  76%|███████▌  | 1510/2000 [45:22<14:20,  1.76s/it, loss=0.176, lr=0.0001]
Steps:  76%|███████▌  | 1510/2000 [45:22<14:20,  1.76s/it, loss=0.119, lr=0.0001]
Steps:  76%|███████▌  | 1510/2000 [45:22<14:20,  1.76s/it, loss=0.17, lr=0.0001] 
Steps:  76%|███████▌  | 1510/2000 [45:23<14:20,  1.76s/it, loss=0.253, lr=0.0001]
Steps:  76%|███████▌  | 1510/2000 [45:23<14:20,  1.76s/it, loss=0.16, lr=0.0001] 
Steps:  76%|███████▌  | 1511/2000 [45:24<14:17,  1.75s/it, loss=0.16, lr=0.0001]
Steps:  76%|███████▌  | 1511/2000 [45:24<14:17,  1.75s/it, loss=0.0585, lr=0.0001]
Steps:  76%|███████▌  | 1511/2000 [45:24<14:17,  1.75s/it, loss=0.15, lr=0.0001]  
Steps:  76%|███████▌  | 1511/2000 [45:24<14:17,  1.75s/it, loss=0.236, lr=0.0001]
Steps:  76%|███████▌  | 1511/2000 [45:25<14:17,  1.75s/it, loss=0.131, lr=0.0001]
Steps:  76%|███████▌  | 1512/2000 [45:25<14:49,  1.82s/it, loss=0.131, lr=0.0001]
Steps:  76%|███████▌  | 1512/2000 [45:25<14:49,  1.82s/it, loss=0.175, lr=0.0001]
Steps:  76%|███████▌  | 1512/2000 [45:26<14:49,  1.82s/it, loss=0.134, lr=0.0001]
Steps:  76%|███████▌  | 1512/2000 [45:26<14:49,  1.82s/it, loss=0.335, lr=0.0001]
Steps:  76%|███████▌  | 1512/2000 [45:27<14:49,  1.82s/it, loss=0.197, lr=0.0001]
Steps:  76%|███████▌  | 1513/2000 [45:27<14:23,  1.77s/it, loss=0.197, lr=0.0001]
Steps:  76%|███████▌  | 1513/2000 [45:27<14:23,  1.77s/it, loss=0.205, lr=0.0001]
Steps:  76%|███████▌  | 1513/2000 [45:28<14:23,  1.77s/it, loss=0.272, lr=0.0001]
Steps:  76%|███████▌  | 1513/2000 [45:28<14:23,  1.77s/it, loss=0.45, lr=0.0001] 
Steps:  76%|███████▌  | 1513/2000 [45:28<14:23,  1.77s/it, loss=0.253, lr=0.0001]
Steps:  76%|███████▌  | 1514/2000 [45:29<14:04,  1.74s/it, loss=0.253, lr=0.0001]
Steps:  76%|███████▌  | 1514/2000 [45:29<14:04,  1.74s/it, loss=0.206, lr=0.0001]
Steps:  76%|███████▌  | 1514/2000 [45:29<14:04,  1.74s/it, loss=0.162, lr=0.0001]
Steps:  76%|███████▌  | 1514/2000 [45:30<14:04,  1.74s/it, loss=0.145, lr=0.0001]
Steps:  76%|███████▌  | 1514/2000 [45:30<14:04,  1.74s/it, loss=0.239, lr=0.0001]
Steps:  76%|███████▌  | 1515/2000 [45:30<13:50,  1.71s/it, loss=0.239, lr=0.0001]
Steps:  76%|███████▌  | 1515/2000 [45:30<13:50,  1.71s/it, loss=0.301, lr=0.0001]
Steps:  76%|███████▌  | 1515/2000 [45:31<13:50,  1.71s/it, loss=0.216, lr=0.0001]
Steps:  76%|███████▌  | 1515/2000 [45:31<13:50,  1.71s/it, loss=0.204, lr=0.0001]
Steps:  76%|███████▌  | 1515/2000 [45:32<13:50,  1.71s/it, loss=0.372, lr=0.0001]
Steps:  76%|███████▌  | 1516/2000 [45:32<14:11,  1.76s/it, loss=0.372, lr=0.0001]
Steps:  76%|███████▌  | 1516/2000 [45:32<14:11,  1.76s/it, loss=0.177, lr=0.0001]
Steps:  76%|███████▌  | 1516/2000 [45:33<14:11,  1.76s/it, loss=0.152, lr=0.0001]
Steps:  76%|███████▌  | 1516/2000 [45:33<14:11,  1.76s/it, loss=0.223, lr=0.0001]
Steps:  76%|███████▌  | 1516/2000 [45:34<14:11,  1.76s/it, loss=0.169, lr=0.0001]
Steps:  76%|███████▌  | 1517/2000 [45:34<13:53,  1.73s/it, loss=0.169, lr=0.0001]
Steps:  76%|███████▌  | 1517/2000 [45:34<13:53,  1.73s/it, loss=0.187, lr=0.0001]
Steps:  76%|███████▌  | 1517/2000 [45:34<13:53,  1.73s/it, loss=0.182, lr=0.0001]
Steps:  76%|███████▌  | 1517/2000 [45:35<13:53,  1.73s/it, loss=0.0597, lr=0.0001]
Steps:  76%|███████▌  | 1517/2000 [45:35<13:53,  1.73s/it, loss=0.138, lr=0.0001] 
Steps:  76%|███████▌  | 1518/2000 [45:36<13:43,  1.71s/it, loss=0.138, lr=0.0001]
Steps:  76%|███████▌  | 1518/2000 [45:36<13:43,  1.71s/it, loss=0.256, lr=0.0001]
Steps:  76%|███████▌  | 1518/2000 [45:36<13:43,  1.71s/it, loss=0.171, lr=0.0001]
Steps:  76%|███████▌  | 1518/2000 [45:37<13:43,  1.71s/it, loss=0.472, lr=0.0001]
Steps:  76%|███████▌  | 1518/2000 [45:37<13:43,  1.71s/it, loss=0.134, lr=0.0001]
Steps:  76%|███████▌  | 1519/2000 [45:38<14:06,  1.76s/it, loss=0.134, lr=0.0001]
Steps:  76%|███████▌  | 1519/2000 [45:38<14:06,  1.76s/it, loss=0.185, lr=0.0001]
Steps:  76%|███████▌  | 1519/2000 [45:38<14:06,  1.76s/it, loss=0.142, lr=0.0001]
Steps:  76%|███████▌  | 1519/2000 [45:38<14:06,  1.76s/it, loss=0.214, lr=0.0001]
Steps:  76%|███████▌  | 1519/2000 [45:39<14:06,  1.76s/it, loss=0.128, lr=0.0001]
Steps:  76%|███████▌  | 1520/2000 [45:39<13:49,  1.73s/it, loss=0.128, lr=0.0001]
Steps:  76%|███████▌  | 1520/2000 [45:39<13:49,  1.73s/it, loss=0.218, lr=0.0001]
Steps:  76%|███████▌  | 1520/2000 [45:40<13:49,  1.73s/it, loss=0.181, lr=0.0001]
Steps:  76%|███████▌  | 1520/2000 [45:40<13:49,  1.73s/it, loss=0.336, lr=0.0001]
Steps:  76%|███████▌  | 1520/2000 [45:40<13:49,  1.73s/it, loss=0.221, lr=0.0001]
Steps:  76%|███████▌  | 1521/2000 [45:41<13:37,  1.71s/it, loss=0.221, lr=0.0001]
Steps:  76%|███████▌  | 1521/2000 [45:41<13:37,  1.71s/it, loss=0.24, lr=0.0001] 
Steps:  76%|███████▌  | 1521/2000 [45:41<13:37,  1.71s/it, loss=0.335, lr=0.0001]
Steps:  76%|███████▌  | 1521/2000 [45:42<13:37,  1.71s/it, loss=0.158, lr=0.0001]
Steps:  76%|███████▌  | 1521/2000 [45:42<13:37,  1.71s/it, loss=0.296, lr=0.0001]
Steps:  76%|███████▌  | 1522/2000 [45:43<14:07,  1.77s/it, loss=0.296, lr=0.0001]
Steps:  76%|███████▌  | 1522/2000 [45:43<14:07,  1.77s/it, loss=0.127, lr=0.0001]
Steps:  76%|███████▌  | 1522/2000 [45:43<14:07,  1.77s/it, loss=0.185, lr=0.0001]
Steps:  76%|███████▌  | 1522/2000 [45:44<14:07,  1.77s/it, loss=0.162, lr=0.0001]
Steps:  76%|███████▌  | 1522/2000 [45:44<14:07,  1.77s/it, loss=0.264, lr=0.0001]
Steps:  76%|███████▌  | 1523/2000 [45:45<14:06,  1.78s/it, loss=0.264, lr=0.0001]
Steps:  76%|███████▌  | 1523/2000 [45:45<14:06,  1.78s/it, loss=0.145, lr=0.0001]
Steps:  76%|███████▌  | 1523/2000 [45:45<14:06,  1.78s/it, loss=0.178, lr=0.0001]
Steps:  76%|███████▌  | 1523/2000 [45:45<14:06,  1.78s/it, loss=0.084, lr=0.0001]
Steps:  76%|███████▌  | 1523/2000 [45:46<14:06,  1.78s/it, loss=0.13, lr=0.0001] 
Steps:  76%|███████▌  | 1524/2000 [45:46<13:47,  1.74s/it, loss=0.13, lr=0.0001]
Steps:  76%|███████▌  | 1524/2000 [45:46<13:47,  1.74s/it, loss=0.38, lr=0.0001]
Steps:  76%|███████▌  | 1524/2000 [45:47<13:47,  1.74s/it, loss=0.223, lr=0.0001]
Steps:  76%|███████▌  | 1524/2000 [45:47<13:47,  1.74s/it, loss=0.232, lr=0.0001]
Steps:  76%|███████▌  | 1524/2000 [45:48<13:47,  1.74s/it, loss=0.0878, lr=0.0001]
Steps:  76%|███████▋  | 1525/2000 [45:48<14:04,  1.78s/it, loss=0.0878, lr=0.0001]
Steps:  76%|███████▋  | 1525/2000 [45:48<14:04,  1.78s/it, loss=0.141, lr=0.0001] 
Steps:  76%|███████▋  | 1525/2000 [45:48<14:04,  1.78s/it, loss=0.229, lr=0.0001]
Steps:  76%|███████▋  | 1525/2000 [45:49<14:04,  1.78s/it, loss=0.0937, lr=0.0001]
Steps:  76%|███████▋  | 1525/2000 [45:49<14:04,  1.78s/it, loss=0.256, lr=0.0001] 
Steps:  76%|███████▋  | 1526/2000 [45:50<13:53,  1.76s/it, loss=0.256, lr=0.0001]
Steps:  76%|███████▋  | 1526/2000 [45:50<13:53,  1.76s/it, loss=0.093, lr=0.0001]
Steps:  76%|███████▋  | 1526/2000 [45:50<13:53,  1.76s/it, loss=0.115, lr=0.0001]
Steps:  76%|███████▋  | 1526/2000 [45:51<13:53,  1.76s/it, loss=0.163, lr=0.0001]
Steps:  76%|███████▋  | 1526/2000 [45:51<13:53,  1.76s/it, loss=0.248, lr=0.0001]
Steps:  76%|███████▋  | 1527/2000 [45:51<13:39,  1.73s/it, loss=0.248, lr=0.0001]
Steps:  76%|███████▋  | 1527/2000 [45:51<13:39,  1.73s/it, loss=0.114, lr=0.0001]
Steps:  76%|███████▋  | 1527/2000 [45:52<13:39,  1.73s/it, loss=0.213, lr=0.0001]
Steps:  76%|███████▋  | 1527/2000 [45:52<13:39,  1.73s/it, loss=0.155, lr=0.0001]
Steps:  76%|███████▋  | 1527/2000 [45:53<13:39,  1.73s/it, loss=0.159, lr=0.0001]
Steps:  76%|███████▋  | 1528/2000 [45:53<14:02,  1.78s/it, loss=0.159, lr=0.0001]
Steps:  76%|███████▋  | 1528/2000 [45:53<14:02,  1.78s/it, loss=0.256, lr=0.0001]
Steps:  76%|███████▋  | 1528/2000 [45:54<14:02,  1.78s/it, loss=0.144, lr=0.0001]
Steps:  76%|███████▋  | 1528/2000 [45:54<14:02,  1.78s/it, loss=0.0973, lr=0.0001]
Steps:  76%|███████▋  | 1528/2000 [45:55<14:02,  1.78s/it, loss=0.153, lr=0.0001] 
Steps:  76%|███████▋  | 1529/2000 [45:55<13:41,  1.74s/it, loss=0.153, lr=0.0001]
Steps:  76%|███████▋  | 1529/2000 [45:55<13:41,  1.74s/it, loss=0.0927, lr=0.0001]
Steps:  76%|███████▋  | 1529/2000 [45:55<13:41,  1.74s/it, loss=0.151, lr=0.0001] 
Steps:  76%|███████▋  | 1529/2000 [45:56<13:41,  1.74s/it, loss=0.186, lr=0.0001]
Steps:  76%|███████▋  | 1529/2000 [45:56<13:41,  1.74s/it, loss=0.152, lr=0.0001]
Steps:  76%|███████▋  | 1530/2000 [45:57<13:26,  1.72s/it, loss=0.152, lr=0.0001]
Steps:  76%|███████▋  | 1530/2000 [45:57<13:26,  1.72s/it, loss=0.219, lr=0.0001]
Steps:  76%|███████▋  | 1530/2000 [45:57<13:26,  1.72s/it, loss=0.0852, lr=0.0001]
Steps:  76%|███████▋  | 1530/2000 [45:57<13:26,  1.72s/it, loss=0.199, lr=0.0001] 
Steps:  76%|███████▋  | 1530/2000 [45:58<13:26,  1.72s/it, loss=0.206, lr=0.0001]
Steps:  77%|███████▋  | 1531/2000 [45:59<13:49,  1.77s/it, loss=0.206, lr=0.0001]
Steps:  77%|███████▋  | 1531/2000 [45:59<13:49,  1.77s/it, loss=0.234, lr=0.0001]
Steps:  77%|███████▋  | 1531/2000 [45:59<13:49,  1.77s/it, loss=0.369, lr=0.0001]
Steps:  77%|███████▋  | 1531/2000 [45:59<13:49,  1.77s/it, loss=0.0964, lr=0.0001]
Steps:  77%|███████▋  | 1531/2000 [46:00<13:49,  1.77s/it, loss=0.234, lr=0.0001] 
Steps:  77%|███████▋  | 1532/2000 [46:00<13:33,  1.74s/it, loss=0.234, lr=0.0001]
Steps:  77%|███████▋  | 1532/2000 [46:00<13:33,  1.74s/it, loss=0.134, lr=0.0001]
Steps:  77%|███████▋  | 1532/2000 [46:01<13:33,  1.74s/it, loss=0.196, lr=0.0001]
Steps:  77%|███████▋  | 1532/2000 [46:01<13:33,  1.74s/it, loss=0.0978, lr=0.0001]
Steps:  77%|███████▋  | 1532/2000 [46:01<13:33,  1.74s/it, loss=0.232, lr=0.0001] 
Steps:  77%|███████▋  | 1533/2000 [46:02<13:19,  1.71s/it, loss=0.232, lr=0.0001]
Steps:  77%|███████▋  | 1533/2000 [46:02<13:19,  1.71s/it, loss=0.0693, lr=0.0001]
Steps:  77%|███████▋  | 1533/2000 [46:02<13:19,  1.71s/it, loss=0.21, lr=0.0001]  
Steps:  77%|███████▋  | 1533/2000 [46:03<13:19,  1.71s/it, loss=0.0894, lr=0.0001]
Steps:  77%|███████▋  | 1533/2000 [46:03<13:19,  1.71s/it, loss=0.284, lr=0.0001] 
Steps:  77%|███████▋  | 1534/2000 [46:04<13:41,  1.76s/it, loss=0.284, lr=0.0001]
Steps:  77%|███████▋  | 1534/2000 [46:04<13:41,  1.76s/it, loss=0.192, lr=0.0001]
Steps:  77%|███████▋  | 1534/2000 [46:04<13:41,  1.76s/it, loss=1.06, lr=0.0001] 
Steps:  77%|███████▋  | 1534/2000 [46:05<13:41,  1.76s/it, loss=0.163, lr=0.0001]
Steps:  77%|███████▋  | 1534/2000 [46:05<13:41,  1.76s/it, loss=0.486, lr=0.0001]
Steps:  77%|███████▋  | 1535/2000 [46:05<13:25,  1.73s/it, loss=0.486, lr=0.0001]
Steps:  77%|███████▋  | 1535/2000 [46:05<13:25,  1.73s/it, loss=0.184, lr=0.0001]
Steps:  77%|███████▋  | 1535/2000 [46:06<13:25,  1.73s/it, loss=0.173, lr=0.0001]
Steps:  77%|███████▋  | 1535/2000 [46:06<13:25,  1.73s/it, loss=0.178, lr=0.0001]
Steps:  77%|███████▋  | 1535/2000 [46:07<13:25,  1.73s/it, loss=0.0826, lr=0.0001]
Steps:  77%|███████▋  | 1536/2000 [46:07<13:15,  1.71s/it, loss=0.0826, lr=0.0001]
Steps:  77%|███████▋  | 1536/2000 [46:07<13:15,  1.71s/it, loss=0.212, lr=0.0001] 
Steps:  77%|███████▋  | 1536/2000 [46:07<13:15,  1.71s/it, loss=0.379, lr=0.0001]
Steps:  77%|███████▋  | 1536/2000 [46:08<13:15,  1.71s/it, loss=0.153, lr=0.0001]
Steps:  77%|███████▋  | 1536/2000 [46:08<13:15,  1.71s/it, loss=0.12, lr=0.0001] 
Steps:  77%|███████▋  | 1537/2000 [46:09<13:09,  1.70s/it, loss=0.12, lr=0.0001]
Steps:  77%|███████▋  | 1537/2000 [46:09<13:09,  1.70s/it, loss=0.0522, lr=0.0001]
Steps:  77%|███████▋  | 1537/2000 [46:09<13:09,  1.70s/it, loss=0.131, lr=0.0001] 
Steps:  77%|███████▋  | 1537/2000 [46:10<13:09,  1.70s/it, loss=0.166, lr=0.0001]
Steps:  77%|███████▋  | 1537/2000 [46:10<13:09,  1.70s/it, loss=0.152, lr=0.0001]
Steps:  77%|███████▋  | 1538/2000 [46:11<13:33,  1.76s/it, loss=0.152, lr=0.0001]
Steps:  77%|███████▋  | 1538/2000 [46:11<13:33,  1.76s/it, loss=0.157, lr=0.0001]
Steps:  77%|███████▋  | 1538/2000 [46:11<13:33,  1.76s/it, loss=0.134, lr=0.0001]
Steps:  77%|███████▋  | 1538/2000 [46:11<13:33,  1.76s/it, loss=0.0834, lr=0.0001]
Steps:  77%|███████▋  | 1538/2000 [46:12<13:33,  1.76s/it, loss=0.026, lr=0.0001] 
Steps:  77%|███████▋  | 1539/2000 [46:12<13:17,  1.73s/it, loss=0.026, lr=0.0001]
Steps:  77%|███████▋  | 1539/2000 [46:12<13:17,  1.73s/it, loss=0.246, lr=0.0001]
Steps:  77%|███████▋  | 1539/2000 [46:13<13:17,  1.73s/it, loss=0.328, lr=0.0001]
Steps:  77%|███████▋  | 1539/2000 [46:13<13:17,  1.73s/it, loss=0.233, lr=0.0001]
Steps:  77%|███████▋  | 1539/2000 [46:14<13:17,  1.73s/it, loss=0.136, lr=0.0001]
Steps:  77%|███████▋  | 1540/2000 [46:14<13:04,  1.71s/it, loss=0.136, lr=0.0001]
Steps:  77%|███████▋  | 1540/2000 [46:14<13:04,  1.71s/it, loss=0.195, lr=0.0001]
Steps:  77%|███████▋  | 1540/2000 [46:15<13:04,  1.71s/it, loss=0.207, lr=0.0001]
Steps:  77%|███████▋  | 1540/2000 [46:15<13:04,  1.71s/it, loss=0.518, lr=0.0001]
Steps:  77%|███████▋  | 1540/2000 [46:15<13:04,  1.71s/it, loss=0.226, lr=0.0001]
Steps:  77%|███████▋  | 1541/2000 [46:16<13:35,  1.78s/it, loss=0.226, lr=0.0001]
Steps:  77%|███████▋  | 1541/2000 [46:16<13:35,  1.78s/it, loss=0.236, lr=0.0001]
Steps:  77%|███████▋  | 1541/2000 [46:16<13:35,  1.78s/it, loss=0.147, lr=0.0001]
Steps:  77%|███████▋  | 1541/2000 [46:17<13:35,  1.78s/it, loss=0.845, lr=0.0001]
Steps:  77%|███████▋  | 1541/2000 [46:17<13:35,  1.78s/it, loss=0.0202, lr=0.0001]
Steps:  77%|███████▋  | 1542/2000 [46:18<13:19,  1.74s/it, loss=0.0202, lr=0.0001]
Steps:  77%|███████▋  | 1542/2000 [46:18<13:19,  1.74s/it, loss=0.141, lr=0.0001] 
Steps:  77%|███████▋  | 1542/2000 [46:18<13:19,  1.74s/it, loss=0.131, lr=0.0001]
Steps:  77%|███████▋  | 1542/2000 [46:18<13:19,  1.74s/it, loss=0.102, lr=0.0001]
Steps:  77%|███████▋  | 1542/2000 [46:19<13:19,  1.74s/it, loss=0.231, lr=0.0001]
Steps:  77%|███████▋  | 1543/2000 [46:19<13:03,  1.71s/it, loss=0.231, lr=0.0001]
Steps:  77%|███████▋  | 1543/2000 [46:19<13:03,  1.71s/it, loss=0.839, lr=0.0001]
Steps:  77%|███████▋  | 1543/2000 [46:20<13:03,  1.71s/it, loss=0.233, lr=0.0001]
Steps:  77%|███████▋  | 1543/2000 [46:20<13:03,  1.71s/it, loss=0.134, lr=0.0001]
Steps:  77%|███████▋  | 1543/2000 [46:21<13:03,  1.71s/it, loss=0.153, lr=0.0001]
Steps:  77%|███████▋  | 1544/2000 [46:21<13:24,  1.77s/it, loss=0.153, lr=0.0001]
Steps:  77%|███████▋  | 1544/2000 [46:21<13:24,  1.77s/it, loss=0.229, lr=0.0001]
Steps:  77%|███████▋  | 1544/2000 [46:22<13:24,  1.77s/it, loss=0.123, lr=0.0001]
Steps:  77%|███████▋  | 1544/2000 [46:22<13:24,  1.77s/it, loss=0.181, lr=0.0001]
Steps:  77%|███████▋  | 1544/2000 [46:22<13:24,  1.77s/it, loss=0.203, lr=0.0001]
Steps:  77%|███████▋  | 1545/2000 [46:23<13:09,  1.73s/it, loss=0.203, lr=0.0001]
Steps:  77%|███████▋  | 1545/2000 [46:23<13:09,  1.73s/it, loss=0.589, lr=0.0001]
Steps:  77%|███████▋  | 1545/2000 [46:23<13:09,  1.73s/it, loss=0.141, lr=0.0001]
Steps:  77%|███████▋  | 1545/2000 [46:24<13:09,  1.73s/it, loss=0.129, lr=0.0001]
Steps:  77%|███████▋  | 1545/2000 [46:24<13:09,  1.73s/it, loss=0.126, lr=0.0001]
Steps:  77%|███████▋  | 1546/2000 [46:24<12:56,  1.71s/it, loss=0.126, lr=0.0001]
Steps:  77%|███████▋  | 1546/2000 [46:24<12:56,  1.71s/it, loss=0.257, lr=0.0001]
Steps:  77%|███████▋  | 1546/2000 [46:25<12:56,  1.71s/it, loss=0.132, lr=0.0001]
Steps:  77%|███████▋  | 1546/2000 [46:25<12:56,  1.71s/it, loss=0.15, lr=0.0001] 
Steps:  77%|███████▋  | 1546/2000 [46:26<12:56,  1.71s/it, loss=0.177, lr=0.0001]
Steps:  77%|███████▋  | 1547/2000 [46:26<13:23,  1.77s/it, loss=0.177, lr=0.0001]
Steps:  77%|███████▋  | 1547/2000 [46:26<13:23,  1.77s/it, loss=0.191, lr=0.0001]
Steps:  77%|███████▋  | 1547/2000 [46:27<13:23,  1.77s/it, loss=0.17, lr=0.0001] 
Steps:  77%|███████▋  | 1547/2000 [46:27<13:23,  1.77s/it, loss=0.509, lr=0.0001]
Steps:  77%|███████▋  | 1547/2000 [46:28<13:23,  1.77s/it, loss=0.209, lr=0.0001]
Steps:  77%|███████▋  | 1548/2000 [46:28<13:10,  1.75s/it, loss=0.209, lr=0.0001]
Steps:  77%|███████▋  | 1548/2000 [46:28<13:10,  1.75s/it, loss=0.186, lr=0.0001]
Steps:  77%|███████▋  | 1548/2000 [46:28<13:10,  1.75s/it, loss=0.105, lr=0.0001]
Steps:  77%|███████▋  | 1548/2000 [46:29<13:10,  1.75s/it, loss=0.119, lr=0.0001]
Steps:  77%|███████▋  | 1548/2000 [46:29<13:10,  1.75s/it, loss=0.146, lr=0.0001]
Steps:  77%|███████▋  | 1549/2000 [46:30<12:59,  1.73s/it, loss=0.146, lr=0.0001]
Steps:  77%|███████▋  | 1549/2000 [46:30<12:59,  1.73s/it, loss=0.106, lr=0.0001]
Steps:  77%|███████▋  | 1549/2000 [46:30<12:59,  1.73s/it, loss=0.154, lr=0.0001]
Steps:  77%|███████▋  | 1549/2000 [46:31<12:59,  1.73s/it, loss=0.425, lr=0.0001]
Steps:  77%|███████▋  | 1549/2000 [46:31<12:59,  1.73s/it, loss=0.115, lr=0.0001]
Steps:  78%|███████▊  | 1550/2000 [46:32<13:24,  1.79s/it, loss=0.115, lr=0.0001]
Steps:  78%|███████▊  | 1550/2000 [46:32<13:24,  1.79s/it, loss=0.277, lr=0.0001]
Steps:  78%|███████▊  | 1550/2000 [46:32<13:24,  1.79s/it, loss=0.279, lr=0.0001]
Steps:  78%|███████▊  | 1550/2000 [46:32<13:24,  1.79s/it, loss=0.0535, lr=0.0001]
Steps:  78%|███████▊  | 1550/2000 [46:33<13:24,  1.79s/it, loss=0.13, lr=0.0001]  
Steps:  78%|███████▊  | 1551/2000 [46:33<13:06,  1.75s/it, loss=0.13, lr=0.0001]
Steps:  78%|███████▊  | 1551/2000 [46:33<13:06,  1.75s/it, loss=0.0999, lr=0.0001]
Steps:  78%|███████▊  | 1551/2000 [46:34<13:06,  1.75s/it, loss=0.194, lr=0.0001] 
Steps:  78%|███████▊  | 1551/2000 [46:34<13:06,  1.75s/it, loss=0.0677, lr=0.0001]
Steps:  78%|███████▊  | 1551/2000 [46:35<13:06,  1.75s/it, loss=0.155, lr=0.0001] 
Steps:  78%|███████▊  | 1552/2000 [46:35<13:01,  1.74s/it, loss=0.155, lr=0.0001]
Steps:  78%|███████▊  | 1552/2000 [46:35<13:01,  1.74s/it, loss=1.04, lr=0.0001] 
Steps:  78%|███████▊  | 1552/2000 [46:35<13:01,  1.74s/it, loss=0.334, lr=0.0001]
Steps:  78%|███████▊  | 1552/2000 [46:36<13:01,  1.74s/it, loss=0.541, lr=0.0001]
Steps:  78%|███████▊  | 1552/2000 [46:37<13:01,  1.74s/it, loss=0.27, lr=0.0001] 
Steps:  78%|███████▊  | 1553/2000 [46:37<13:21,  1.79s/it, loss=0.27, lr=0.0001]
Steps:  78%|███████▊  | 1553/2000 [46:37<13:21,  1.79s/it, loss=0.288, lr=0.0001]
Steps:  78%|███████▊  | 1553/2000 [46:37<13:21,  1.79s/it, loss=0.572, lr=0.0001]
Steps:  78%|███████▊  | 1553/2000 [46:38<13:21,  1.79s/it, loss=0.0879, lr=0.0001]
Steps:  78%|███████▊  | 1553/2000 [46:38<13:21,  1.79s/it, loss=0.181, lr=0.0001] 
Steps:  78%|███████▊  | 1554/2000 [46:39<13:01,  1.75s/it, loss=0.181, lr=0.0001]
Steps:  78%|███████▊  | 1554/2000 [46:39<13:01,  1.75s/it, loss=0.231, lr=0.0001]
Steps:  78%|███████▊  | 1554/2000 [46:39<13:01,  1.75s/it, loss=0.17, lr=0.0001] 
Steps:  78%|███████▊  | 1554/2000 [46:39<13:01,  1.75s/it, loss=0.411, lr=0.0001]
Steps:  78%|███████▊  | 1554/2000 [46:40<13:01,  1.75s/it, loss=0.218, lr=0.0001]
Steps:  78%|███████▊  | 1555/2000 [46:40<12:45,  1.72s/it, loss=0.218, lr=0.0001]
Steps:  78%|███████▊  | 1555/2000 [46:40<12:45,  1.72s/it, loss=0.975, lr=0.0001]
Steps:  78%|███████▊  | 1555/2000 [46:41<12:45,  1.72s/it, loss=0.0898, lr=0.0001]
Steps:  78%|███████▊  | 1555/2000 [46:41<12:45,  1.72s/it, loss=0.153, lr=0.0001] 
Steps:  78%|███████▊  | 1555/2000 [46:41<12:45,  1.72s/it, loss=0.264, lr=0.0001]
Steps:  78%|███████▊  | 1556/2000 [46:42<13:10,  1.78s/it, loss=0.264, lr=0.0001]
Steps:  78%|███████▊  | 1556/2000 [46:42<13:10,  1.78s/it, loss=0.488, lr=0.0001]
Steps:  78%|███████▊  | 1556/2000 [46:43<13:10,  1.78s/it, loss=0.177, lr=0.0001]
Steps:  78%|███████▊  | 1556/2000 [46:43<13:10,  1.78s/it, loss=0.28, lr=0.0001] 
Steps:  78%|███████▊  | 1556/2000 [46:43<13:10,  1.78s/it, loss=0.264, lr=0.0001]
Steps:  78%|███████▊  | 1557/2000 [46:44<13:00,  1.76s/it, loss=0.264, lr=0.0001]
Steps:  78%|███████▊  | 1557/2000 [46:44<13:00,  1.76s/it, loss=0.22, lr=0.0001] 
Steps:  78%|███████▊  | 1557/2000 [46:44<13:00,  1.76s/it, loss=0.152, lr=0.0001]
Steps:  78%|███████▊  | 1557/2000 [46:45<13:00,  1.76s/it, loss=0.983, lr=0.0001]
Steps:  78%|███████▊  | 1557/2000 [46:45<13:00,  1.76s/it, loss=0.24, lr=0.0001] 
Steps:  78%|███████▊  | 1558/2000 [46:46<12:45,  1.73s/it, loss=0.24, lr=0.0001]
Steps:  78%|███████▊  | 1558/2000 [46:46<12:45,  1.73s/it, loss=0.141, lr=0.0001]
Steps:  78%|███████▊  | 1558/2000 [46:46<12:45,  1.73s/it, loss=0.285, lr=0.0001]
Steps:  78%|███████▊  | 1558/2000 [46:46<12:45,  1.73s/it, loss=0.148, lr=0.0001]
Steps:  78%|███████▊  | 1558/2000 [46:47<12:45,  1.73s/it, loss=0.224, lr=0.0001]
Steps:  78%|███████▊  | 1559/2000 [46:47<12:33,  1.71s/it, loss=0.224, lr=0.0001]
Steps:  78%|███████▊  | 1559/2000 [46:47<12:33,  1.71s/it, loss=0.187, lr=0.0001]
Steps:  78%|███████▊  | 1559/2000 [46:48<12:33,  1.71s/it, loss=0.305, lr=0.0001]
Steps:  78%|███████▊  | 1559/2000 [46:48<12:33,  1.71s/it, loss=0.148, lr=0.0001]
Steps:  78%|███████▊  | 1559/2000 [46:49<12:33,  1.71s/it, loss=0.22, lr=0.0001] 
Steps:  78%|███████▊  | 1560/2000 [46:49<12:59,  1.77s/it, loss=0.22, lr=0.0001]
Steps:  78%|███████▊  | 1560/2000 [46:49<12:59,  1.77s/it, loss=0.158, lr=0.0001]
Steps:  78%|███████▊  | 1560/2000 [46:50<12:59,  1.77s/it, loss=0.176, lr=0.0001]
Steps:  78%|███████▊  | 1560/2000 [46:50<12:59,  1.77s/it, loss=0.207, lr=0.0001]
Steps:  78%|███████▊  | 1560/2000 [46:50<12:59,  1.77s/it, loss=0.26, lr=0.0001] 
Steps:  78%|███████▊  | 1561/2000 [46:51<12:46,  1.75s/it, loss=0.26, lr=0.0001]
Steps:  78%|███████▊  | 1561/2000 [46:51<12:46,  1.75s/it, loss=0.0916, lr=0.0001]
Steps:  78%|███████▊  | 1561/2000 [46:51<12:46,  1.75s/it, loss=0.0946, lr=0.0001]
Steps:  78%|███████▊  | 1561/2000 [46:52<12:46,  1.75s/it, loss=0.181, lr=0.0001] 
Steps:  78%|███████▊  | 1561/2000 [46:52<12:46,  1.75s/it, loss=0.256, lr=0.0001]
Steps:  78%|███████▊  | 1562/2000 [46:52<12:33,  1.72s/it, loss=0.256, lr=0.0001]
Steps:  78%|███████▊  | 1562/2000 [46:52<12:33,  1.72s/it, loss=0.237, lr=0.0001]
Steps:  78%|███████▊  | 1562/2000 [46:53<12:33,  1.72s/it, loss=0.245, lr=0.0001]
Steps:  78%|███████▊  | 1562/2000 [46:54<12:33,  1.72s/it, loss=0.129, lr=0.0001]
Steps:  78%|███████▊  | 1562/2000 [46:54<12:33,  1.72s/it, loss=0.0879, lr=0.0001]
Steps:  78%|███████▊  | 1563/2000 [46:54<12:53,  1.77s/it, loss=0.0879, lr=0.0001]
Steps:  78%|███████▊  | 1563/2000 [46:54<12:53,  1.77s/it, loss=0.213, lr=0.0001] 
Steps:  78%|███████▊  | 1563/2000 [46:55<12:53,  1.77s/it, loss=0.116, lr=0.0001]
Steps:  78%|███████▊  | 1563/2000 [46:55<12:53,  1.77s/it, loss=0.211, lr=0.0001]
Steps:  78%|███████▊  | 1563/2000 [46:56<12:53,  1.77s/it, loss=0.216, lr=0.0001]
Steps:  78%|███████▊  | 1564/2000 [46:56<12:39,  1.74s/it, loss=0.216, lr=0.0001]
Steps:  78%|███████▊  | 1564/2000 [46:56<12:39,  1.74s/it, loss=0.096, lr=0.0001]
Steps:  78%|███████▊  | 1564/2000 [46:56<12:39,  1.74s/it, loss=0.341, lr=0.0001]
Steps:  78%|███████▊  | 1564/2000 [46:57<12:39,  1.74s/it, loss=0.23, lr=0.0001] 
Steps:  78%|███████▊  | 1564/2000 [46:57<12:39,  1.74s/it, loss=0.359, lr=0.0001]
Steps:  78%|███████▊  | 1565/2000 [46:58<12:27,  1.72s/it, loss=0.359, lr=0.0001]
Steps:  78%|███████▊  | 1565/2000 [46:58<12:27,  1.72s/it, loss=0.0686, lr=0.0001]
Steps:  78%|███████▊  | 1565/2000 [46:58<12:27,  1.72s/it, loss=0.274, lr=0.0001] 
Steps:  78%|███████▊  | 1565/2000 [46:59<12:27,  1.72s/it, loss=0.187, lr=0.0001]
Steps:  78%|███████▊  | 1565/2000 [46:59<12:27,  1.72s/it, loss=0.14, lr=0.0001] 
Steps:  78%|███████▊  | 1566/2000 [47:00<12:47,  1.77s/it, loss=0.14, lr=0.0001]
Steps:  78%|███████▊  | 1566/2000 [47:00<12:47,  1.77s/it, loss=0.162, lr=0.0001]
Steps:  78%|███████▊  | 1566/2000 [47:00<12:47,  1.77s/it, loss=0.318, lr=0.0001]
Steps:  78%|███████▊  | 1566/2000 [47:00<12:47,  1.77s/it, loss=0.167, lr=0.0001]
Steps:  78%|███████▊  | 1566/2000 [47:01<12:47,  1.77s/it, loss=0.234, lr=0.0001]
Steps:  78%|███████▊  | 1567/2000 [47:01<12:33,  1.74s/it, loss=0.234, lr=0.0001]
Steps:  78%|███████▊  | 1567/2000 [47:01<12:33,  1.74s/it, loss=0.0582, lr=0.0001]
Steps:  78%|███████▊  | 1567/2000 [47:02<12:33,  1.74s/it, loss=0.313, lr=0.0001] 
Steps:  78%|███████▊  | 1567/2000 [47:02<12:33,  1.74s/it, loss=0.211, lr=0.0001]
Steps:  78%|███████▊  | 1567/2000 [47:02<12:33,  1.74s/it, loss=0.155, lr=0.0001]
Steps:  78%|███████▊  | 1568/2000 [47:03<12:20,  1.71s/it, loss=0.155, lr=0.0001]
Steps:  78%|███████▊  | 1568/2000 [47:03<12:20,  1.71s/it, loss=0.25, lr=0.0001] 
Steps:  78%|███████▊  | 1568/2000 [47:03<12:20,  1.71s/it, loss=0.0878, lr=0.0001]
Steps:  78%|███████▊  | 1568/2000 [47:04<12:20,  1.71s/it, loss=0.171, lr=0.0001] 
Steps:  78%|███████▊  | 1568/2000 [47:04<12:20,  1.71s/it, loss=0.259, lr=0.0001]
Steps:  78%|███████▊  | 1569/2000 [47:05<12:40,  1.76s/it, loss=0.259, lr=0.0001]
Steps:  78%|███████▊  | 1569/2000 [47:05<12:40,  1.76s/it, loss=0.499, lr=0.0001]
Steps:  78%|███████▊  | 1569/2000 [47:05<12:40,  1.76s/it, loss=0.38, lr=0.0001] 
Steps:  78%|███████▊  | 1569/2000 [47:06<12:40,  1.76s/it, loss=0.274, lr=0.0001]
Steps:  78%|███████▊  | 1569/2000 [47:06<12:40,  1.76s/it, loss=0.171, lr=0.0001]
Steps:  78%|███████▊  | 1570/2000 [47:06<12:27,  1.74s/it, loss=0.171, lr=0.0001]
Steps:  78%|███████▊  | 1570/2000 [47:06<12:27,  1.74s/it, loss=0.7, lr=0.0001]  
Steps:  78%|███████▊  | 1570/2000 [47:07<12:27,  1.74s/it, loss=0.236, lr=0.0001]
Steps:  78%|███████▊  | 1570/2000 [47:07<12:27,  1.74s/it, loss=0.214, lr=0.0001]
Steps:  78%|███████▊  | 1570/2000 [47:08<12:27,  1.74s/it, loss=0.0767, lr=0.0001]
Steps:  79%|███████▊  | 1571/2000 [47:08<12:15,  1.71s/it, loss=0.0767, lr=0.0001]
Steps:  79%|███████▊  | 1571/2000 [47:08<12:15,  1.71s/it, loss=0.122, lr=0.0001] 
Steps:  79%|███████▊  | 1571/2000 [47:09<12:15,  1.71s/it, loss=0.192, lr=0.0001]
Steps:  79%|███████▊  | 1571/2000 [47:09<12:15,  1.71s/it, loss=0.0868, lr=0.0001]
Steps:  79%|███████▊  | 1571/2000 [47:10<12:15,  1.71s/it, loss=0.142, lr=0.0001] 
Steps:  79%|███████▊  | 1572/2000 [47:10<12:44,  1.79s/it, loss=0.142, lr=0.0001]
Steps:  79%|███████▊  | 1572/2000 [47:10<12:44,  1.79s/it, loss=0.0695, lr=0.0001]
Steps:  79%|███████▊  | 1572/2000 [47:10<12:44,  1.79s/it, loss=0.419, lr=0.0001] 
Steps:  79%|███████▊  | 1572/2000 [47:11<12:44,  1.79s/it, loss=0.234, lr=0.0001]
Steps:  79%|███████▊  | 1572/2000 [47:11<12:44,  1.79s/it, loss=0.365, lr=0.0001]
Steps:  79%|███████▊  | 1573/2000 [47:12<12:25,  1.75s/it, loss=0.365, lr=0.0001]
Steps:  79%|███████▊  | 1573/2000 [47:12<12:25,  1.75s/it, loss=0.518, lr=0.0001]
Steps:  79%|███████▊  | 1573/2000 [47:12<12:25,  1.75s/it, loss=0.211, lr=0.0001]
Steps:  79%|███████▊  | 1573/2000 [47:13<12:25,  1.75s/it, loss=0.322, lr=0.0001]
Steps:  79%|███████▊  | 1573/2000 [47:13<12:25,  1.75s/it, loss=0.158, lr=0.0001]
Steps:  79%|███████▊  | 1574/2000 [47:13<12:14,  1.72s/it, loss=0.158, lr=0.0001]
Steps:  79%|███████▊  | 1574/2000 [47:13<12:14,  1.72s/it, loss=0.158, lr=0.0001]
Steps:  79%|███████▊  | 1574/2000 [47:14<12:14,  1.72s/it, loss=0.626, lr=0.0001]
Steps:  79%|███████▊  | 1574/2000 [47:14<12:14,  1.72s/it, loss=0.239, lr=0.0001]
Steps:  79%|███████▊  | 1574/2000 [47:15<12:14,  1.72s/it, loss=0.151, lr=0.0001]
Steps:  79%|███████▉  | 1575/2000 [47:15<12:51,  1.82s/it, loss=0.151, lr=0.0001]
Steps:  79%|███████▉  | 1575/2000 [47:15<12:51,  1.82s/it, loss=0.158, lr=0.0001]
Steps:  79%|███████▉  | 1575/2000 [47:16<12:51,  1.82s/it, loss=0.153, lr=0.0001]
Steps:  79%|███████▉  | 1575/2000 [47:16<12:51,  1.82s/it, loss=0.143, lr=0.0001]
Steps:  79%|███████▉  | 1575/2000 [47:17<12:51,  1.82s/it, loss=0.188, lr=0.0001]
Steps:  79%|███████▉  | 1576/2000 [47:17<12:28,  1.77s/it, loss=0.188, lr=0.0001]
Steps:  79%|███████▉  | 1576/2000 [47:17<12:28,  1.77s/it, loss=0.16, lr=0.0001] 
Steps:  79%|███████▉  | 1576/2000 [47:17<12:28,  1.77s/it, loss=0.257, lr=0.0001]
Steps:  79%|███████▉  | 1576/2000 [47:18<12:28,  1.77s/it, loss=0.228, lr=0.0001]
Steps:  79%|███████▉  | 1576/2000 [47:18<12:28,  1.77s/it, loss=0.164, lr=0.0001]
Steps:  79%|███████▉  | 1577/2000 [47:19<12:12,  1.73s/it, loss=0.164, lr=0.0001]
Steps:  79%|███████▉  | 1577/2000 [47:19<12:12,  1.73s/it, loss=0.312, lr=0.0001]
Steps:  79%|███████▉  | 1577/2000 [47:19<12:12,  1.73s/it, loss=0.168, lr=0.0001]
Steps:  79%|███████▉  | 1577/2000 [47:20<12:12,  1.73s/it, loss=0.156, lr=0.0001]
Steps:  79%|███████▉  | 1577/2000 [47:20<12:12,  1.73s/it, loss=0.129, lr=0.0001]
Steps:  79%|███████▉  | 1578/2000 [47:21<12:30,  1.78s/it, loss=0.129, lr=0.0001]
Steps:  79%|███████▉  | 1578/2000 [47:21<12:30,  1.78s/it, loss=0.203, lr=0.0001]
Steps:  79%|███████▉  | 1578/2000 [47:21<12:30,  1.78s/it, loss=0.303, lr=0.0001]
Steps:  79%|███████▉  | 1578/2000 [47:21<12:30,  1.78s/it, loss=0.115, lr=0.0001]
Steps:  79%|███████▉  | 1578/2000 [47:22<12:30,  1.78s/it, loss=0.133, lr=0.0001]
Steps:  79%|███████▉  | 1579/2000 [47:22<12:16,  1.75s/it, loss=0.133, lr=0.0001]
Steps:  79%|███████▉  | 1579/2000 [47:22<12:16,  1.75s/it, loss=0.288, lr=0.0001]
Steps:  79%|███████▉  | 1579/2000 [47:23<12:16,  1.75s/it, loss=0.144, lr=0.0001]
Steps:  79%|███████▉  | 1579/2000 [47:23<12:16,  1.75s/it, loss=0.446, lr=0.0001]
Steps:  79%|███████▉  | 1579/2000 [47:24<12:16,  1.75s/it, loss=0.153, lr=0.0001]
Steps:  79%|███████▉  | 1580/2000 [47:24<12:02,  1.72s/it, loss=0.153, lr=0.0001]
Steps:  79%|███████▉  | 1580/2000 [47:24<12:02,  1.72s/it, loss=0.156, lr=0.0001]
Steps:  79%|███████▉  | 1580/2000 [47:24<12:02,  1.72s/it, loss=0.0809, lr=0.0001]
Steps:  79%|███████▉  | 1580/2000 [47:25<12:02,  1.72s/it, loss=0.19, lr=0.0001]  
Steps:  79%|███████▉  | 1580/2000 [47:25<12:02,  1.72s/it, loss=0.146, lr=0.0001]
Steps:  79%|███████▉  | 1581/2000 [47:26<11:54,  1.71s/it, loss=0.146, lr=0.0001]
Steps:  79%|███████▉  | 1581/2000 [47:26<11:54,  1.71s/it, loss=0.555, lr=0.0001]
Steps:  79%|███████▉  | 1581/2000 [47:26<11:54,  1.71s/it, loss=0.376, lr=0.0001]
Steps:  79%|███████▉  | 1581/2000 [47:27<11:54,  1.71s/it, loss=0.124, lr=0.0001]
Steps:  79%|███████▉  | 1581/2000 [47:27<11:54,  1.71s/it, loss=0.103, lr=0.0001]
Steps:  79%|███████▉  | 1582/2000 [47:28<12:19,  1.77s/it, loss=0.103, lr=0.0001]
Steps:  79%|███████▉  | 1582/2000 [47:28<12:19,  1.77s/it, loss=0.163, lr=0.0001]
Steps:  79%|███████▉  | 1582/2000 [47:28<12:19,  1.77s/it, loss=0.0819, lr=0.0001]
Steps:  79%|███████▉  | 1582/2000 [47:28<12:19,  1.77s/it, loss=0.102, lr=0.0001] 
Steps:  79%|███████▉  | 1582/2000 [47:29<12:19,  1.77s/it, loss=0.211, lr=0.0001]
Steps:  79%|███████▉  | 1583/2000 [47:29<12:05,  1.74s/it, loss=0.211, lr=0.0001]
Steps:  79%|███████▉  | 1583/2000 [47:29<12:05,  1.74s/it, loss=0.164, lr=0.0001]
Steps:  79%|███████▉  | 1583/2000 [47:30<12:05,  1.74s/it, loss=0.115, lr=0.0001]
Steps:  79%|███████▉  | 1583/2000 [47:30<12:05,  1.74s/it, loss=0.175, lr=0.0001]
Steps:  79%|███████▉  | 1583/2000 [47:30<12:05,  1.74s/it, loss=0.161, lr=0.0001]
Steps:  79%|███████▉  | 1584/2000 [47:31<11:55,  1.72s/it, loss=0.161, lr=0.0001]
Steps:  79%|███████▉  | 1584/2000 [47:31<11:55,  1.72s/it, loss=0.772, lr=0.0001]
Steps:  79%|███████▉  | 1584/2000 [47:31<11:55,  1.72s/it, loss=0.551, lr=0.0001]
Steps:  79%|███████▉  | 1584/2000 [47:32<11:55,  1.72s/it, loss=0.13, lr=0.0001] 
Steps:  79%|███████▉  | 1584/2000 [47:32<11:55,  1.72s/it, loss=0.209, lr=0.0001]
Steps:  79%|███████▉  | 1585/2000 [47:33<12:16,  1.78s/it, loss=0.209, lr=0.0001]
Steps:  79%|███████▉  | 1585/2000 [47:33<12:16,  1.78s/it, loss=0.207, lr=0.0001]
Steps:  79%|███████▉  | 1585/2000 [47:33<12:16,  1.78s/it, loss=0.0829, lr=0.0001]
Steps:  79%|███████▉  | 1585/2000 [47:34<12:16,  1.78s/it, loss=0.238, lr=0.0001] 
Steps:  79%|███████▉  | 1585/2000 [47:34<12:16,  1.78s/it, loss=0.164, lr=0.0001]
Steps:  79%|███████▉  | 1586/2000 [47:34<11:59,  1.74s/it, loss=0.164, lr=0.0001]
Steps:  79%|███████▉  | 1586/2000 [47:34<11:59,  1.74s/it, loss=0.154, lr=0.0001]
Steps:  79%|███████▉  | 1586/2000 [47:35<11:59,  1.74s/it, loss=0.254, lr=0.0001]
Steps:  79%|███████▉  | 1586/2000 [47:35<11:59,  1.74s/it, loss=0.131, lr=0.0001]
Steps:  79%|███████▉  | 1586/2000 [47:36<11:59,  1.74s/it, loss=0.126, lr=0.0001]
Steps:  79%|███████▉  | 1587/2000 [47:36<11:49,  1.72s/it, loss=0.126, lr=0.0001]
Steps:  79%|███████▉  | 1587/2000 [47:36<11:49,  1.72s/it, loss=0.189, lr=0.0001]
Steps:  79%|███████▉  | 1587/2000 [47:37<11:49,  1.72s/it, loss=0.203, lr=0.0001]
Steps:  79%|███████▉  | 1587/2000 [47:37<11:49,  1.72s/it, loss=0.113, lr=0.0001]
Steps:  79%|███████▉  | 1587/2000 [47:38<11:49,  1.72s/it, loss=0.249, lr=0.0001]
Steps:  79%|███████▉  | 1588/2000 [47:38<12:09,  1.77s/it, loss=0.249, lr=0.0001]
Steps:  79%|███████▉  | 1588/2000 [47:38<12:09,  1.77s/it, loss=0.0995, lr=0.0001]
Steps:  79%|███████▉  | 1588/2000 [47:38<12:09,  1.77s/it, loss=0.129, lr=0.0001] 
Steps:  79%|███████▉  | 1588/2000 [47:39<12:09,  1.77s/it, loss=0.111, lr=0.0001]
Steps:  79%|███████▉  | 1588/2000 [47:39<12:09,  1.77s/it, loss=0.195, lr=0.0001]
Steps:  79%|███████▉  | 1589/2000 [47:40<11:53,  1.73s/it, loss=0.195, lr=0.0001]
Steps:  79%|███████▉  | 1589/2000 [47:40<11:53,  1.73s/it, loss=0.184, lr=0.0001]
Steps:  79%|███████▉  | 1589/2000 [47:40<11:53,  1.73s/it, loss=0.113, lr=0.0001]
Steps:  79%|███████▉  | 1589/2000 [47:40<11:53,  1.73s/it, loss=0.159, lr=0.0001]
Steps:  79%|███████▉  | 1589/2000 [47:41<11:53,  1.73s/it, loss=0.254, lr=0.0001]
Steps:  80%|███████▉  | 1590/2000 [47:41<11:41,  1.71s/it, loss=0.254, lr=0.0001]
Steps:  80%|███████▉  | 1590/2000 [47:41<11:41,  1.71s/it, loss=0.154, lr=0.0001]
Steps:  80%|███████▉  | 1590/2000 [47:42<11:41,  1.71s/it, loss=0.128, lr=0.0001]
Steps:  80%|███████▉  | 1590/2000 [47:42<11:41,  1.71s/it, loss=0.0945, lr=0.0001]
Steps:  80%|███████▉  | 1590/2000 [47:43<11:41,  1.71s/it, loss=0.216, lr=0.0001] 
Steps:  80%|███████▉  | 1591/2000 [47:43<11:59,  1.76s/it, loss=0.216, lr=0.0001]
Steps:  80%|███████▉  | 1591/2000 [47:43<11:59,  1.76s/it, loss=0.126, lr=0.0001]
Steps:  80%|███████▉  | 1591/2000 [47:44<11:59,  1.76s/it, loss=0.201, lr=0.0001]
Steps:  80%|███████▉  | 1591/2000 [47:44<11:59,  1.76s/it, loss=0.847, lr=0.0001]
Steps:  80%|███████▉  | 1591/2000 [47:44<11:59,  1.76s/it, loss=0.13, lr=0.0001] 
Steps:  80%|███████▉  | 1592/2000 [47:45<11:43,  1.73s/it, loss=0.13, lr=0.0001]
Steps:  80%|███████▉  | 1592/2000 [47:45<11:43,  1.73s/it, loss=0.472, lr=0.0001]
Steps:  80%|███████▉  | 1592/2000 [47:45<11:43,  1.73s/it, loss=0.172, lr=0.0001]
Steps:  80%|███████▉  | 1592/2000 [47:46<11:43,  1.73s/it, loss=0.131, lr=0.0001]
Steps:  80%|███████▉  | 1592/2000 [47:46<11:43,  1.73s/it, loss=0.229, lr=0.0001]
Steps:  80%|███████▉  | 1593/2000 [47:47<11:36,  1.71s/it, loss=0.229, lr=0.0001]
Steps:  80%|███████▉  | 1593/2000 [47:47<11:36,  1.71s/it, loss=0.194, lr=0.0001]
Steps:  80%|███████▉  | 1593/2000 [47:47<11:36,  1.71s/it, loss=0.169, lr=0.0001]
Steps:  80%|███████▉  | 1593/2000 [47:47<11:36,  1.71s/it, loss=0.144, lr=0.0001]
Steps:  80%|███████▉  | 1593/2000 [47:48<11:36,  1.71s/it, loss=0.247, lr=0.0001]
Steps:  80%|███████▉  | 1594/2000 [47:48<12:01,  1.78s/it, loss=0.247, lr=0.0001]
Steps:  80%|███████▉  | 1594/2000 [47:48<12:01,  1.78s/it, loss=0.292, lr=0.0001]
Steps:  80%|███████▉  | 1594/2000 [47:49<12:01,  1.78s/it, loss=0.0889, lr=0.0001]
Steps:  80%|███████▉  | 1594/2000 [47:49<12:01,  1.78s/it, loss=0.163, lr=0.0001] 
Steps:  80%|███████▉  | 1594/2000 [47:50<12:01,  1.78s/it, loss=0.0531, lr=0.0001]
Steps:  80%|███████▉  | 1595/2000 [47:50<11:50,  1.75s/it, loss=0.0531, lr=0.0001]
Steps:  80%|███████▉  | 1595/2000 [47:50<11:50,  1.75s/it, loss=0.176, lr=0.0001] 
Steps:  80%|███████▉  | 1595/2000 [47:51<11:50,  1.75s/it, loss=0.214, lr=0.0001]
Steps:  80%|███████▉  | 1595/2000 [47:51<11:50,  1.75s/it, loss=0.0897, lr=0.0001]
Steps:  80%|███████▉  | 1595/2000 [47:51<11:50,  1.75s/it, loss=0.326, lr=0.0001] 
Steps:  80%|███████▉  | 1596/2000 [47:52<11:48,  1.75s/it, loss=0.326, lr=0.0001]
Steps:  80%|███████▉  | 1596/2000 [47:52<11:48,  1.75s/it, loss=0.135, lr=0.0001]
Steps:  80%|███████▉  | 1596/2000 [47:52<11:48,  1.75s/it, loss=0.288, lr=0.0001]
Steps:  80%|███████▉  | 1596/2000 [47:53<11:48,  1.75s/it, loss=0.275, lr=0.0001]
Steps:  80%|███████▉  | 1596/2000 [47:53<11:48,  1.75s/it, loss=0.16, lr=0.0001] 
Steps:  80%|███████▉  | 1597/2000 [47:54<12:10,  1.81s/it, loss=0.16, lr=0.0001]
Steps:  80%|███████▉  | 1597/2000 [47:54<12:10,  1.81s/it, loss=0.139, lr=0.0001]
Steps:  80%|███████▉  | 1597/2000 [47:54<12:10,  1.81s/it, loss=0.0964, lr=0.0001]
Steps:  80%|███████▉  | 1597/2000 [47:55<12:10,  1.81s/it, loss=0.13, lr=0.0001]  
Steps:  80%|███████▉  | 1597/2000 [47:55<12:10,  1.81s/it, loss=0.232, lr=0.0001]
Steps:  80%|███████▉  | 1598/2000 [47:56<11:55,  1.78s/it, loss=0.232, lr=0.0001]
Steps:  80%|███████▉  | 1598/2000 [47:56<11:55,  1.78s/it, loss=0.0971, lr=0.0001]
Steps:  80%|███████▉  | 1598/2000 [47:56<11:55,  1.78s/it, loss=0.158, lr=0.0001] 
Steps:  80%|███████▉  | 1598/2000 [47:56<11:55,  1.78s/it, loss=0.19, lr=0.0001] 
Steps:  80%|███████▉  | 1598/2000 [47:57<11:55,  1.78s/it, loss=0.19, lr=0.0001]
Steps:  80%|███████▉  | 1599/2000 [47:57<11:44,  1.76s/it, loss=0.19, lr=0.0001]
Steps:  80%|███████▉  | 1599/2000 [47:57<11:44,  1.76s/it, loss=0.174, lr=0.0001]
Steps:  80%|███████▉  | 1599/2000 [47:58<11:44,  1.76s/it, loss=0.467, lr=0.0001]
Steps:  80%|███████▉  | 1599/2000 [47:58<11:44,  1.76s/it, loss=0.193, lr=0.0001]
Steps:  80%|███████▉  | 1599/2000 [47:59<11:44,  1.76s/it, loss=0.236, lr=0.0001]
Steps:  80%|████████  | 1600/2000 [47:59<11:37,  1.74s/it, loss=0.236, lr=0.0001]
Steps:  80%|████████  | 1600/2000 [47:59<11:37,  1.74s/it, loss=0.154, lr=0.0001]
Steps:  80%|████████  | 1600/2000 [48:00<11:37,  1.74s/it, loss=0.223, lr=0.0001]
Steps:  80%|████████  | 1600/2000 [48:00<11:37,  1.74s/it, loss=0.358, lr=0.0001]
Steps:  80%|████████  | 1600/2000 [48:00<11:37,  1.74s/it, loss=0.0979, lr=0.0001]
Steps:  80%|████████  | 1601/2000 [48:01<12:06,  1.82s/it, loss=0.0979, lr=0.0001]
Steps:  80%|████████  | 1601/2000 [48:01<12:06,  1.82s/it, loss=0.51, lr=0.0001]  
Steps:  80%|████████  | 1601/2000 [48:01<12:06,  1.82s/it, loss=0.172, lr=0.0001]
Steps:  80%|████████  | 1601/2000 [48:02<12:06,  1.82s/it, loss=0.172, lr=0.0001]
Steps:  80%|████████  | 1601/2000 [48:02<12:06,  1.82s/it, loss=0.173, lr=0.0001]
Steps:  80%|████████  | 1602/2000 [48:03<11:53,  1.79s/it, loss=0.173, lr=0.0001]
Steps:  80%|████████  | 1602/2000 [48:03<11:53,  1.79s/it, loss=0.199, lr=0.0001]
Steps:  80%|████████  | 1602/2000 [48:03<11:53,  1.79s/it, loss=0.194, lr=0.0001]
Steps:  80%|████████  | 1602/2000 [48:04<11:53,  1.79s/it, loss=0.0946, lr=0.0001]
Steps:  80%|████████  | 1602/2000 [48:04<11:53,  1.79s/it, loss=0.177, lr=0.0001] 
Steps:  80%|████████  | 1603/2000 [48:05<11:54,  1.80s/it, loss=0.177, lr=0.0001]
Steps:  80%|████████  | 1603/2000 [48:05<11:54,  1.80s/it, loss=0.237, lr=0.0001]
Steps:  80%|████████  | 1603/2000 [48:05<11:54,  1.80s/it, loss=0.137, lr=0.0001]
Steps:  80%|████████  | 1603/2000 [48:06<11:54,  1.80s/it, loss=0.151, lr=0.0001]
Steps:  80%|████████  | 1603/2000 [48:06<11:54,  1.80s/it, loss=0.224, lr=0.0001]
Steps:  80%|████████  | 1604/2000 [48:06<12:09,  1.84s/it, loss=0.224, lr=0.0001]
Steps:  80%|████████  | 1604/2000 [48:06<12:09,  1.84s/it, loss=0.306, lr=0.0001]
Steps:  80%|████████  | 1604/2000 [48:07<12:09,  1.84s/it, loss=0.145, lr=0.0001]
Steps:  80%|████████  | 1604/2000 [48:07<12:09,  1.84s/it, loss=0.915, lr=0.0001]
Steps:  80%|████████  | 1604/2000 [48:08<12:09,  1.84s/it, loss=0.124, lr=0.0001]
Steps:  80%|████████  | 1605/2000 [48:08<11:51,  1.80s/it, loss=0.124, lr=0.0001]
Steps:  80%|████████  | 1605/2000 [48:08<11:51,  1.80s/it, loss=0.149, lr=0.0001]
Steps:  80%|████████  | 1605/2000 [48:09<11:51,  1.80s/it, loss=0.206, lr=0.0001]
Steps:  80%|████████  | 1605/2000 [48:09<11:51,  1.80s/it, loss=0.288, lr=0.0001]
Steps:  80%|████████  | 1605/2000 [48:09<11:51,  1.80s/it, loss=0.183, lr=0.0001]
Steps:  80%|████████  | 1606/2000 [48:10<11:48,  1.80s/it, loss=0.183, lr=0.0001]
Steps:  80%|████████  | 1606/2000 [48:10<11:48,  1.80s/it, loss=0.147, lr=0.0001]
Steps:  80%|████████  | 1606/2000 [48:10<11:48,  1.80s/it, loss=0.138, lr=0.0001]
Steps:  80%|████████  | 1606/2000 [48:11<11:48,  1.80s/it, loss=0.132, lr=0.0001]
Steps:  80%|████████  | 1606/2000 [48:11<11:48,  1.80s/it, loss=0.0618, lr=0.0001]
Steps:  80%|████████  | 1607/2000 [48:12<12:00,  1.83s/it, loss=0.0618, lr=0.0001]
Steps:  80%|████████  | 1607/2000 [48:12<12:00,  1.83s/it, loss=0.164, lr=0.0001] 
Steps:  80%|████████  | 1607/2000 [48:12<12:00,  1.83s/it, loss=0.251, lr=0.0001]
Steps:  80%|████████  | 1607/2000 [48:13<12:00,  1.83s/it, loss=0.193, lr=0.0001]
Steps:  80%|████████  | 1607/2000 [48:13<12:00,  1.83s/it, loss=0.19, lr=0.0001] 
Steps:  80%|████████  | 1608/2000 [48:14<11:38,  1.78s/it, loss=0.19, lr=0.0001]
Steps:  80%|████████  | 1608/2000 [48:14<11:38,  1.78s/it, loss=0.176, lr=0.0001]
Steps:  80%|████████  | 1608/2000 [48:14<11:38,  1.78s/it, loss=0.196, lr=0.0001]
Steps:  80%|████████  | 1608/2000 [48:14<11:38,  1.78s/it, loss=0.0471, lr=0.0001]
Steps:  80%|████████  | 1608/2000 [48:15<11:38,  1.78s/it, loss=1.12, lr=0.0001]  
Steps:  80%|████████  | 1609/2000 [48:15<11:21,  1.74s/it, loss=1.12, lr=0.0001]
Steps:  80%|████████  | 1609/2000 [48:15<11:21,  1.74s/it, loss=0.159, lr=0.0001]
Steps:  80%|████████  | 1609/2000 [48:16<11:21,  1.74s/it, loss=0.161, lr=0.0001]
Steps:  80%|████████  | 1609/2000 [48:16<11:21,  1.74s/it, loss=1.06, lr=0.0001] 
Steps:  80%|████████  | 1609/2000 [48:17<11:21,  1.74s/it, loss=0.183, lr=0.0001]
Steps:  80%|████████  | 1610/2000 [48:17<11:38,  1.79s/it, loss=0.183, lr=0.0001]
Steps:  80%|████████  | 1610/2000 [48:17<11:38,  1.79s/it, loss=0.231, lr=0.0001]
Steps:  80%|████████  | 1610/2000 [48:17<11:38,  1.79s/it, loss=0.215, lr=0.0001]
Steps:  80%|████████  | 1610/2000 [48:18<11:38,  1.79s/it, loss=0.11, lr=0.0001] 
Steps:  80%|████████  | 1610/2000 [48:18<11:38,  1.79s/it, loss=0.0812, lr=0.0001]
Steps:  81%|████████  | 1611/2000 [48:19<11:22,  1.75s/it, loss=0.0812, lr=0.0001]
Steps:  81%|████████  | 1611/2000 [48:19<11:22,  1.75s/it, loss=0.163, lr=0.0001] 
Steps:  81%|████████  | 1611/2000 [48:19<11:22,  1.75s/it, loss=0.216, lr=0.0001]
Steps:  81%|████████  | 1611/2000 [48:20<11:22,  1.75s/it, loss=0.165, lr=0.0001]
Steps:  81%|████████  | 1611/2000 [48:20<11:22,  1.75s/it, loss=0.361, lr=0.0001]
Steps:  81%|████████  | 1612/2000 [48:20<11:08,  1.72s/it, loss=0.361, lr=0.0001]
Steps:  81%|████████  | 1612/2000 [48:20<11:08,  1.72s/it, loss=0.165, lr=0.0001]
Steps:  81%|████████  | 1612/2000 [48:21<11:08,  1.72s/it, loss=0.171, lr=0.0001]
Steps:  81%|████████  | 1612/2000 [48:21<11:08,  1.72s/it, loss=0.213, lr=0.0001]
Steps:  81%|████████  | 1612/2000 [48:22<11:08,  1.72s/it, loss=0.185, lr=0.0001]
Steps:  81%|████████  | 1613/2000 [48:22<11:24,  1.77s/it, loss=0.185, lr=0.0001]
Steps:  81%|████████  | 1613/2000 [48:22<11:24,  1.77s/it, loss=0.203, lr=0.0001]
Steps:  81%|████████  | 1613/2000 [48:23<11:24,  1.77s/it, loss=0.157, lr=0.0001]
Steps:  81%|████████  | 1613/2000 [48:23<11:24,  1.77s/it, loss=0.295, lr=0.0001]
Steps:  81%|████████  | 1613/2000 [48:23<11:24,  1.77s/it, loss=0.152, lr=0.0001]
Steps:  81%|████████  | 1614/2000 [48:24<11:08,  1.73s/it, loss=0.152, lr=0.0001]
Steps:  81%|████████  | 1614/2000 [48:24<11:08,  1.73s/it, loss=0.12, lr=0.0001] 
Steps:  81%|████████  | 1614/2000 [48:24<11:08,  1.73s/it, loss=0.195, lr=0.0001]
Steps:  81%|████████  | 1614/2000 [48:25<11:08,  1.73s/it, loss=0.156, lr=0.0001]
Steps:  81%|████████  | 1614/2000 [48:25<11:08,  1.73s/it, loss=0.0658, lr=0.0001]
Steps:  81%|████████  | 1615/2000 [48:26<10:57,  1.71s/it, loss=0.0658, lr=0.0001]
Steps:  81%|████████  | 1615/2000 [48:26<10:57,  1.71s/it, loss=0.226, lr=0.0001] 
Steps:  81%|████████  | 1615/2000 [48:26<10:57,  1.71s/it, loss=0.186, lr=0.0001]
Steps:  81%|████████  | 1615/2000 [48:26<10:57,  1.71s/it, loss=0.105, lr=0.0001]
Steps:  81%|████████  | 1615/2000 [48:27<10:57,  1.71s/it, loss=0.205, lr=0.0001]
Steps:  81%|████████  | 1616/2000 [48:27<11:15,  1.76s/it, loss=0.205, lr=0.0001]
Steps:  81%|████████  | 1616/2000 [48:27<11:15,  1.76s/it, loss=0.218, lr=0.0001]
Steps:  81%|████████  | 1616/2000 [48:28<11:15,  1.76s/it, loss=0.325, lr=0.0001]
Steps:  81%|████████  | 1616/2000 [48:28<11:15,  1.76s/it, loss=0.785, lr=0.0001]
Steps:  81%|████████  | 1616/2000 [48:29<11:15,  1.76s/it, loss=0.203, lr=0.0001]
Steps:  81%|████████  | 1617/2000 [48:29<11:04,  1.73s/it, loss=0.203, lr=0.0001]
Steps:  81%|████████  | 1617/2000 [48:29<11:04,  1.73s/it, loss=0.198, lr=0.0001]
Steps:  81%|████████  | 1617/2000 [48:30<11:04,  1.73s/it, loss=0.22, lr=0.0001] 
Steps:  81%|████████  | 1617/2000 [48:30<11:04,  1.73s/it, loss=0.0983, lr=0.0001]
Steps:  81%|████████  | 1617/2000 [48:30<11:04,  1.73s/it, loss=0.209, lr=0.0001] 
Steps:  81%|████████  | 1618/2000 [48:31<10:53,  1.71s/it, loss=0.209, lr=0.0001]
Steps:  81%|████████  | 1618/2000 [48:31<10:53,  1.71s/it, loss=0.0859, lr=0.0001]
Steps:  81%|████████  | 1618/2000 [48:31<10:53,  1.71s/it, loss=0.101, lr=0.0001] 
Steps:  81%|████████  | 1618/2000 [48:32<10:53,  1.71s/it, loss=0.23, lr=0.0001] 
Steps:  81%|████████  | 1618/2000 [48:32<10:53,  1.71s/it, loss=0.176, lr=0.0001]
Steps:  81%|████████  | 1619/2000 [48:32<10:46,  1.70s/it, loss=0.176, lr=0.0001]
Steps:  81%|████████  | 1619/2000 [48:32<10:46,  1.70s/it, loss=0.19, lr=0.0001] 
Steps:  81%|████████  | 1619/2000 [48:33<10:46,  1.70s/it, loss=0.284, lr=0.0001]
Steps:  81%|████████  | 1619/2000 [48:33<10:46,  1.70s/it, loss=0.113, lr=0.0001]
Steps:  81%|████████  | 1619/2000 [48:34<10:46,  1.70s/it, loss=0.176, lr=0.0001]
Steps:  81%|████████  | 1620/2000 [48:34<11:05,  1.75s/it, loss=0.176, lr=0.0001]
Steps:  81%|████████  | 1620/2000 [48:34<11:05,  1.75s/it, loss=0.218, lr=0.0001]
Steps:  81%|████████  | 1620/2000 [48:35<11:05,  1.75s/it, loss=0.886, lr=0.0001]
Steps:  81%|████████  | 1620/2000 [48:35<11:05,  1.75s/it, loss=0.177, lr=0.0001]
Steps:  81%|████████  | 1620/2000 [48:36<11:05,  1.75s/it, loss=0.214, lr=0.0001]
Steps:  81%|████████  | 1621/2000 [48:36<10:51,  1.72s/it, loss=0.214, lr=0.0001]
Steps:  81%|████████  | 1621/2000 [48:36<10:51,  1.72s/it, loss=0.135, lr=0.0001]
Steps:  81%|████████  | 1621/2000 [48:36<10:51,  1.72s/it, loss=0.0823, lr=0.0001]
Steps:  81%|████████  | 1621/2000 [48:37<10:51,  1.72s/it, loss=0.142, lr=0.0001] 
Steps:  81%|████████  | 1621/2000 [48:37<10:51,  1.72s/it, loss=0.103, lr=0.0001]
Steps:  81%|████████  | 1622/2000 [48:38<10:41,  1.70s/it, loss=0.103, lr=0.0001]
Steps:  81%|████████  | 1622/2000 [48:38<10:41,  1.70s/it, loss=0.179, lr=0.0001]
Steps:  81%|████████  | 1622/2000 [48:38<10:41,  1.70s/it, loss=0.119, lr=0.0001]
Steps:  81%|████████  | 1622/2000 [48:39<10:41,  1.70s/it, loss=0.15, lr=0.0001] 
Steps:  81%|████████  | 1622/2000 [48:39<10:41,  1.70s/it, loss=0.214, lr=0.0001]
Steps:  81%|████████  | 1623/2000 [48:39<10:59,  1.75s/it, loss=0.214, lr=0.0001]
Steps:  81%|████████  | 1623/2000 [48:39<10:59,  1.75s/it, loss=0.22, lr=0.0001] 
Steps:  81%|████████  | 1623/2000 [48:40<10:59,  1.75s/it, loss=0.652, lr=0.0001]
Steps:  81%|████████  | 1623/2000 [48:40<10:59,  1.75s/it, loss=0.276, lr=0.0001]
Steps:  81%|████████  | 1623/2000 [48:41<10:59,  1.75s/it, loss=0.171, lr=0.0001]
Steps:  81%|████████  | 1624/2000 [48:41<10:46,  1.72s/it, loss=0.171, lr=0.0001]
Steps:  81%|████████  | 1624/2000 [48:41<10:46,  1.72s/it, loss=0.159, lr=0.0001]
Steps:  81%|████████  | 1624/2000 [48:42<10:46,  1.72s/it, loss=0.173, lr=0.0001]
Steps:  81%|████████  | 1624/2000 [48:42<10:46,  1.72s/it, loss=0.689, lr=0.0001]
Steps:  81%|████████  | 1624/2000 [48:42<10:46,  1.72s/it, loss=0.267, lr=0.0001]
Steps:  81%|████████▏ | 1625/2000 [48:43<10:41,  1.71s/it, loss=0.267, lr=0.0001]
Steps:  81%|████████▏ | 1625/2000 [48:43<10:41,  1.71s/it, loss=0.113, lr=0.0001]
Steps:  81%|████████▏ | 1625/2000 [48:43<10:41,  1.71s/it, loss=0.145, lr=0.0001]
Steps:  81%|████████▏ | 1625/2000 [48:44<10:41,  1.71s/it, loss=0.21, lr=0.0001] 
Steps:  81%|████████▏ | 1625/2000 [48:44<10:41,  1.71s/it, loss=0.166, lr=0.0001]
Steps:  81%|████████▏ | 1626/2000 [48:45<10:58,  1.76s/it, loss=0.166, lr=0.0001]
Steps:  81%|████████▏ | 1626/2000 [48:45<10:58,  1.76s/it, loss=0.0716, lr=0.0001]
Steps:  81%|████████▏ | 1626/2000 [48:45<10:58,  1.76s/it, loss=0.145, lr=0.0001] 
Steps:  81%|████████▏ | 1626/2000 [48:46<10:58,  1.76s/it, loss=0.274, lr=0.0001]
Steps:  81%|████████▏ | 1626/2000 [48:46<10:58,  1.76s/it, loss=0.24, lr=0.0001] 
Steps:  81%|████████▏ | 1627/2000 [48:46<10:44,  1.73s/it, loss=0.24, lr=0.0001]
Steps:  81%|████████▏ | 1627/2000 [48:46<10:44,  1.73s/it, loss=0.114, lr=0.0001]
Steps:  81%|████████▏ | 1627/2000 [48:47<10:44,  1.73s/it, loss=0.137, lr=0.0001]
Steps:  81%|████████▏ | 1627/2000 [48:47<10:44,  1.73s/it, loss=0.268, lr=0.0001]
Steps:  81%|████████▏ | 1627/2000 [48:48<10:44,  1.73s/it, loss=0.264, lr=0.0001]
Steps:  81%|████████▏ | 1628/2000 [48:48<10:33,  1.70s/it, loss=0.264, lr=0.0001]
Steps:  81%|████████▏ | 1628/2000 [48:48<10:33,  1.70s/it, loss=0.356, lr=0.0001]
Steps:  81%|████████▏ | 1628/2000 [48:48<10:33,  1.70s/it, loss=0.133, lr=0.0001]
Steps:  81%|████████▏ | 1628/2000 [48:49<10:33,  1.70s/it, loss=0.208, lr=0.0001]
Steps:  81%|████████▏ | 1628/2000 [48:49<10:33,  1.70s/it, loss=0.157, lr=0.0001]
Steps:  81%|████████▏ | 1629/2000 [48:50<10:53,  1.76s/it, loss=0.157, lr=0.0001]
Steps:  81%|████████▏ | 1629/2000 [48:50<10:53,  1.76s/it, loss=0.123, lr=0.0001]
Steps:  81%|████████▏ | 1629/2000 [48:50<10:53,  1.76s/it, loss=0.167, lr=0.0001]
Steps:  81%|████████▏ | 1629/2000 [48:51<10:53,  1.76s/it, loss=0.164, lr=0.0001]
Steps:  81%|████████▏ | 1629/2000 [48:51<10:53,  1.76s/it, loss=0.143, lr=0.0001]
Steps:  82%|████████▏ | 1630/2000 [48:52<10:38,  1.73s/it, loss=0.143, lr=0.0001]
Steps:  82%|████████▏ | 1630/2000 [48:52<10:38,  1.73s/it, loss=0.26, lr=0.0001] 
Steps:  82%|████████▏ | 1630/2000 [48:52<10:38,  1.73s/it, loss=0.12, lr=0.0001]
Steps:  82%|████████▏ | 1630/2000 [48:52<10:38,  1.73s/it, loss=0.265, lr=0.0001]
Steps:  82%|████████▏ | 1630/2000 [48:53<10:38,  1.73s/it, loss=0.157, lr=0.0001]
Steps:  82%|████████▏ | 1631/2000 [48:53<10:31,  1.71s/it, loss=0.157, lr=0.0001]
Steps:  82%|████████▏ | 1631/2000 [48:53<10:31,  1.71s/it, loss=0.116, lr=0.0001]
Steps:  82%|████████▏ | 1631/2000 [48:54<10:31,  1.71s/it, loss=0.106, lr=0.0001]
Steps:  82%|████████▏ | 1631/2000 [48:54<10:31,  1.71s/it, loss=0.518, lr=0.0001]
Steps:  82%|████████▏ | 1631/2000 [48:54<10:31,  1.71s/it, loss=0.0881, lr=0.0001]
Steps:  82%|████████▏ | 1632/2000 [48:55<10:48,  1.76s/it, loss=0.0881, lr=0.0001]
Steps:  82%|████████▏ | 1632/2000 [48:55<10:48,  1.76s/it, loss=0.146, lr=0.0001] 
Steps:  82%|████████▏ | 1632/2000 [48:56<10:48,  1.76s/it, loss=0.184, lr=0.0001]
Steps:  82%|████████▏ | 1632/2000 [48:56<10:48,  1.76s/it, loss=0.132, lr=0.0001]
Steps:  82%|████████▏ | 1632/2000 [48:56<10:48,  1.76s/it, loss=0.313, lr=0.0001]
Steps:  82%|████████▏ | 1633/2000 [48:57<10:34,  1.73s/it, loss=0.313, lr=0.0001]
Steps:  82%|████████▏ | 1633/2000 [48:57<10:34,  1.73s/it, loss=0.111, lr=0.0001]
Steps:  82%|████████▏ | 1633/2000 [48:57<10:34,  1.73s/it, loss=0.165, lr=0.0001]
Steps:  82%|████████▏ | 1633/2000 [48:58<10:34,  1.73s/it, loss=0.187, lr=0.0001]
Steps:  82%|████████▏ | 1633/2000 [48:58<10:34,  1.73s/it, loss=0.18, lr=0.0001] 
Steps:  82%|████████▏ | 1634/2000 [48:58<10:29,  1.72s/it, loss=0.18, lr=0.0001]
Steps:  82%|████████▏ | 1634/2000 [48:58<10:29,  1.72s/it, loss=0.0908, lr=0.0001]
Steps:  82%|████████▏ | 1634/2000 [48:59<10:29,  1.72s/it, loss=0.167, lr=0.0001] 
Steps:  82%|████████▏ | 1634/2000 [48:59<10:29,  1.72s/it, loss=0.189, lr=0.0001]
Steps:  82%|████████▏ | 1634/2000 [49:00<10:29,  1.72s/it, loss=0.272, lr=0.0001]
Steps:  82%|████████▏ | 1635/2000 [49:00<10:20,  1.70s/it, loss=0.272, lr=0.0001]
Steps:  82%|████████▏ | 1635/2000 [49:00<10:20,  1.70s/it, loss=0.192, lr=0.0001]
Steps:  82%|████████▏ | 1635/2000 [49:01<10:20,  1.70s/it, loss=0.243, lr=0.0001]
Steps:  82%|████████▏ | 1635/2000 [49:01<10:20,  1.70s/it, loss=0.843, lr=0.0001]
Steps:  82%|████████▏ | 1635/2000 [49:02<10:20,  1.70s/it, loss=0.167, lr=0.0001]
Steps:  82%|████████▏ | 1636/2000 [49:03<11:42,  1.93s/it, loss=0.167, lr=0.0001]
Steps:  82%|████████▏ | 1636/2000 [49:03<11:42,  1.93s/it, loss=0.236, lr=0.0001]
Steps:  82%|████████▏ | 1636/2000 [49:03<11:42,  1.93s/it, loss=0.127, lr=0.0001]
Steps:  82%|████████▏ | 1636/2000 [49:03<11:42,  1.93s/it, loss=0.129, lr=0.0001]
Steps:  82%|████████▏ | 1636/2000 [49:04<11:42,  1.93s/it, loss=0.748, lr=0.0001]
Steps:  82%|████████▏ | 1637/2000 [49:04<11:24,  1.88s/it, loss=0.748, lr=0.0001]
Steps:  82%|████████▏ | 1637/2000 [49:04<11:24,  1.88s/it, loss=0.191, lr=0.0001]
Steps:  82%|████████▏ | 1637/2000 [49:05<11:24,  1.88s/it, loss=0.0225, lr=0.0001]
Steps:  82%|████████▏ | 1637/2000 [49:05<11:24,  1.88s/it, loss=0.12, lr=0.0001]  
Steps:  82%|████████▏ | 1637/2000 [49:06<11:24,  1.88s/it, loss=0.0961, lr=0.0001]
Steps:  82%|████████▏ | 1638/2000 [49:06<11:12,  1.86s/it, loss=0.0961, lr=0.0001]
Steps:  82%|████████▏ | 1638/2000 [49:06<11:12,  1.86s/it, loss=0.283, lr=0.0001] 
Steps:  82%|████████▏ | 1638/2000 [49:07<11:12,  1.86s/it, loss=0.135, lr=0.0001]
Steps:  82%|████████▏ | 1638/2000 [49:07<11:12,  1.86s/it, loss=0.224, lr=0.0001]
Steps:  82%|████████▏ | 1638/2000 [49:08<11:12,  1.86s/it, loss=0.234, lr=0.0001]
Steps:  82%|████████▏ | 1639/2000 [49:08<11:13,  1.87s/it, loss=0.234, lr=0.0001]
Steps:  82%|████████▏ | 1639/2000 [49:08<11:13,  1.87s/it, loss=0.16, lr=0.0001] 
Steps:  82%|████████▏ | 1639/2000 [49:08<11:13,  1.87s/it, loss=0.22, lr=0.0001]
Steps:  82%|████████▏ | 1639/2000 [49:09<11:13,  1.87s/it, loss=0.166, lr=0.0001]
Steps:  82%|████████▏ | 1639/2000 [49:09<11:13,  1.87s/it, loss=0.279, lr=0.0001]
Steps:  82%|████████▏ | 1640/2000 [49:10<10:46,  1.79s/it, loss=0.279, lr=0.0001]
Steps:  82%|████████▏ | 1640/2000 [49:10<10:46,  1.79s/it, loss=0.218, lr=0.0001]
Steps:  82%|████████▏ | 1640/2000 [49:10<10:46,  1.79s/it, loss=0.211, lr=0.0001]
Steps:  82%|████████▏ | 1640/2000 [49:10<10:46,  1.79s/it, loss=0.424, lr=0.0001]
Steps:  82%|████████▏ | 1640/2000 [49:11<10:46,  1.79s/it, loss=0.216, lr=0.0001]
Steps:  82%|████████▏ | 1641/2000 [49:11<10:26,  1.75s/it, loss=0.216, lr=0.0001]
Steps:  82%|████████▏ | 1641/2000 [49:11<10:26,  1.75s/it, loss=0.127, lr=0.0001]
Steps:  82%|████████▏ | 1641/2000 [49:12<10:26,  1.75s/it, loss=0.174, lr=0.0001]
Steps:  82%|████████▏ | 1641/2000 [49:12<10:26,  1.75s/it, loss=0.279, lr=0.0001]
Steps:  82%|████████▏ | 1641/2000 [49:13<10:26,  1.75s/it, loss=0.185, lr=0.0001]
Steps:  82%|████████▏ | 1642/2000 [49:13<10:36,  1.78s/it, loss=0.185, lr=0.0001]
Steps:  82%|████████▏ | 1642/2000 [49:13<10:36,  1.78s/it, loss=0.0977, lr=0.0001]
Steps:  82%|████████▏ | 1642/2000 [49:14<10:36,  1.78s/it, loss=0.179, lr=0.0001] 
Steps:  82%|████████▏ | 1642/2000 [49:14<10:36,  1.78s/it, loss=0.0633, lr=0.0001]
Steps:  82%|████████▏ | 1642/2000 [49:14<10:36,  1.78s/it, loss=0.204, lr=0.0001] 
Steps:  82%|████████▏ | 1643/2000 [49:15<10:18,  1.73s/it, loss=0.204, lr=0.0001]
Steps:  82%|████████▏ | 1643/2000 [49:15<10:18,  1.73s/it, loss=0.267, lr=0.0001]
Steps:  82%|████████▏ | 1643/2000 [49:15<10:18,  1.73s/it, loss=0.126, lr=0.0001]
Steps:  82%|████████▏ | 1643/2000 [49:16<10:18,  1.73s/it, loss=0.144, lr=0.0001]
Steps:  82%|████████▏ | 1643/2000 [49:16<10:18,  1.73s/it, loss=0.225, lr=0.0001]
Steps:  82%|████████▏ | 1644/2000 [49:16<10:06,  1.70s/it, loss=0.225, lr=0.0001]
Steps:  82%|████████▏ | 1644/2000 [49:16<10:06,  1.70s/it, loss=0.175, lr=0.0001]
Steps:  82%|████████▏ | 1644/2000 [49:17<10:06,  1.70s/it, loss=0.14, lr=0.0001] 
Steps:  82%|████████▏ | 1644/2000 [49:17<10:06,  1.70s/it, loss=0.0386, lr=0.0001]
Steps:  82%|████████▏ | 1644/2000 [49:18<10:06,  1.70s/it, loss=0.16, lr=0.0001]  
Steps:  82%|████████▏ | 1645/2000 [49:18<10:22,  1.75s/it, loss=0.16, lr=0.0001]
Steps:  82%|████████▏ | 1645/2000 [49:18<10:22,  1.75s/it, loss=0.15, lr=0.0001]
Steps:  82%|████████▏ | 1645/2000 [49:19<10:22,  1.75s/it, loss=0.372, lr=0.0001]
Steps:  82%|████████▏ | 1645/2000 [49:19<10:22,  1.75s/it, loss=0.108, lr=0.0001]
Steps:  82%|████████▏ | 1645/2000 [49:19<10:22,  1.75s/it, loss=0.425, lr=0.0001]
Steps:  82%|████████▏ | 1646/2000 [49:20<10:07,  1.72s/it, loss=0.425, lr=0.0001]
Steps:  82%|████████▏ | 1646/2000 [49:20<10:07,  1.72s/it, loss=0.854, lr=0.0001]
Steps:  82%|████████▏ | 1646/2000 [49:20<10:07,  1.72s/it, loss=0.0857, lr=0.0001]
Steps:  82%|████████▏ | 1646/2000 [49:21<10:07,  1.72s/it, loss=0.366, lr=0.0001] 
Steps:  82%|████████▏ | 1646/2000 [49:21<10:07,  1.72s/it, loss=0.265, lr=0.0001]
Steps:  82%|████████▏ | 1647/2000 [49:22<09:56,  1.69s/it, loss=0.265, lr=0.0001]
Steps:  82%|████████▏ | 1647/2000 [49:22<09:56,  1.69s/it, loss=0.153, lr=0.0001]
Steps:  82%|████████▏ | 1647/2000 [49:22<09:56,  1.69s/it, loss=0.165, lr=0.0001]
Steps:  82%|████████▏ | 1647/2000 [49:22<09:56,  1.69s/it, loss=0.135, lr=0.0001]
Steps:  82%|████████▏ | 1647/2000 [49:23<09:56,  1.69s/it, loss=0.0715, lr=0.0001]
Steps:  82%|████████▏ | 1648/2000 [49:23<10:11,  1.74s/it, loss=0.0715, lr=0.0001]
Steps:  82%|████████▏ | 1648/2000 [49:23<10:11,  1.74s/it, loss=0.0593, lr=0.0001]
Steps:  82%|████████▏ | 1648/2000 [49:24<10:11,  1.74s/it, loss=0.164, lr=0.0001] 
Steps:  82%|████████▏ | 1648/2000 [49:24<10:11,  1.74s/it, loss=0.172, lr=0.0001]
Steps:  82%|████████▏ | 1648/2000 [49:25<10:11,  1.74s/it, loss=0.216, lr=0.0001]
Steps:  82%|████████▏ | 1649/2000 [49:25<09:59,  1.71s/it, loss=0.216, lr=0.0001]
Steps:  82%|████████▏ | 1649/2000 [49:25<09:59,  1.71s/it, loss=0.102, lr=0.0001]
Steps:  82%|████████▏ | 1649/2000 [49:25<09:59,  1.71s/it, loss=0.27, lr=0.0001] 
Steps:  82%|████████▏ | 1649/2000 [49:26<09:59,  1.71s/it, loss=0.35, lr=0.0001]
Steps:  82%|████████▏ | 1649/2000 [49:26<09:59,  1.71s/it, loss=0.313, lr=0.0001]
Steps:  82%|████████▎ | 1650/2000 [49:27<09:50,  1.69s/it, loss=0.313, lr=0.0001]
Steps:  82%|████████▎ | 1650/2000 [49:27<09:50,  1.69s/it, loss=0.108, lr=0.0001]
Steps:  82%|████████▎ | 1650/2000 [49:27<09:50,  1.69s/it, loss=0.123, lr=0.0001]
Steps:  82%|████████▎ | 1650/2000 [49:27<09:50,  1.69s/it, loss=0.26, lr=0.0001] 
Steps:  82%|████████▎ | 1650/2000 [49:28<09:50,  1.69s/it, loss=0.28, lr=0.0001]
Steps:  83%|████████▎ | 1651/2000 [49:29<10:15,  1.76s/it, loss=0.28, lr=0.0001]
Steps:  83%|████████▎ | 1651/2000 [49:29<10:15,  1.76s/it, loss=0.0986, lr=0.0001]
Steps:  83%|████████▎ | 1651/2000 [49:29<10:15,  1.76s/it, loss=0.237, lr=0.0001] 
Steps:  83%|████████▎ | 1651/2000 [49:29<10:15,  1.76s/it, loss=0.206, lr=0.0001]
Steps:  83%|████████▎ | 1651/2000 [49:30<10:15,  1.76s/it, loss=0.0653, lr=0.0001]
Steps:  83%|████████▎ | 1652/2000 [49:30<10:01,  1.73s/it, loss=0.0653, lr=0.0001]
Steps:  83%|████████▎ | 1652/2000 [49:30<10:01,  1.73s/it, loss=0.445, lr=0.0001] 
Steps:  83%|████████▎ | 1652/2000 [49:31<10:01,  1.73s/it, loss=0.19, lr=0.0001] 
Steps:  83%|████████▎ | 1652/2000 [49:31<10:01,  1.73s/it, loss=0.176, lr=0.0001]
Steps:  83%|████████▎ | 1652/2000 [49:31<10:01,  1.73s/it, loss=0.299, lr=0.0001]
Steps:  83%|████████▎ | 1653/2000 [49:32<09:53,  1.71s/it, loss=0.299, lr=0.0001]
Steps:  83%|████████▎ | 1653/2000 [49:32<09:53,  1.71s/it, loss=0.251, lr=0.0001]
Steps:  83%|████████▎ | 1653/2000 [49:32<09:53,  1.71s/it, loss=0.109, lr=0.0001]
Steps:  83%|████████▎ | 1653/2000 [49:33<09:53,  1.71s/it, loss=0.215, lr=0.0001]
Steps:  83%|████████▎ | 1653/2000 [49:33<09:53,  1.71s/it, loss=0.16, lr=0.0001] 
Steps:  83%|████████▎ | 1654/2000 [49:34<09:45,  1.69s/it, loss=0.16, lr=0.0001]
Steps:  83%|████████▎ | 1654/2000 [49:34<09:45,  1.69s/it, loss=0.405, lr=0.0001]
Steps:  83%|████████▎ | 1654/2000 [49:34<09:45,  1.69s/it, loss=0.948, lr=0.0001]
Steps:  83%|████████▎ | 1654/2000 [49:35<09:45,  1.69s/it, loss=0.158, lr=0.0001]
Steps:  83%|████████▎ | 1654/2000 [49:35<09:45,  1.69s/it, loss=0.144, lr=0.0001]
Steps:  83%|████████▎ | 1655/2000 [49:36<10:10,  1.77s/it, loss=0.144, lr=0.0001]
Steps:  83%|████████▎ | 1655/2000 [49:36<10:10,  1.77s/it, loss=0.24, lr=0.0001] 
Steps:  83%|████████▎ | 1655/2000 [49:36<10:10,  1.77s/it, loss=0.0214, lr=0.0001]
Steps:  83%|████████▎ | 1655/2000 [49:36<10:10,  1.77s/it, loss=0.541, lr=0.0001] 
Steps:  83%|████████▎ | 1655/2000 [49:37<10:10,  1.77s/it, loss=0.113, lr=0.0001]
Steps:  83%|████████▎ | 1656/2000 [49:37<09:54,  1.73s/it, loss=0.113, lr=0.0001]
Steps:  83%|████████▎ | 1656/2000 [49:37<09:54,  1.73s/it, loss=0.147, lr=0.0001]
Steps:  83%|████████▎ | 1656/2000 [49:38<09:54,  1.73s/it, loss=0.164, lr=0.0001]
Steps:  83%|████████▎ | 1656/2000 [49:38<09:54,  1.73s/it, loss=0.074, lr=0.0001]
Steps:  83%|████████▎ | 1656/2000 [49:38<09:54,  1.73s/it, loss=0.0872, lr=0.0001]
Steps:  83%|████████▎ | 1657/2000 [49:39<09:44,  1.70s/it, loss=0.0872, lr=0.0001]
Steps:  83%|████████▎ | 1657/2000 [49:39<09:44,  1.70s/it, loss=0.127, lr=0.0001] 
Steps:  83%|████████▎ | 1657/2000 [49:39<09:44,  1.70s/it, loss=0.959, lr=0.0001]
Steps:  83%|████████▎ | 1657/2000 [49:40<09:44,  1.70s/it, loss=0.178, lr=0.0001]
Steps:  83%|████████▎ | 1657/2000 [49:40<09:44,  1.70s/it, loss=0.211, lr=0.0001]
Steps:  83%|████████▎ | 1658/2000 [49:41<10:01,  1.76s/it, loss=0.211, lr=0.0001]
Steps:  83%|████████▎ | 1658/2000 [49:41<10:01,  1.76s/it, loss=0.182, lr=0.0001]
Steps:  83%|████████▎ | 1658/2000 [49:41<10:01,  1.76s/it, loss=0.123, lr=0.0001]
Steps:  83%|████████▎ | 1658/2000 [49:41<10:01,  1.76s/it, loss=0.199, lr=0.0001]
Steps:  83%|████████▎ | 1658/2000 [49:42<10:01,  1.76s/it, loss=0.138, lr=0.0001]
Steps:  83%|████████▎ | 1659/2000 [49:42<09:48,  1.73s/it, loss=0.138, lr=0.0001]
Steps:  83%|████████▎ | 1659/2000 [49:42<09:48,  1.73s/it, loss=0.186, lr=0.0001]
Steps:  83%|████████▎ | 1659/2000 [49:43<09:48,  1.73s/it, loss=0.202, lr=0.0001]
Steps:  83%|████████▎ | 1659/2000 [49:43<09:48,  1.73s/it, loss=0.128, lr=0.0001]
Steps:  83%|████████▎ | 1659/2000 [49:44<09:48,  1.73s/it, loss=0.307, lr=0.0001]
Steps:  83%|████████▎ | 1660/2000 [49:44<09:39,  1.71s/it, loss=0.307, lr=0.0001]
Steps:  83%|████████▎ | 1660/2000 [49:44<09:39,  1.71s/it, loss=0.568, lr=0.0001]
Steps:  83%|████████▎ | 1660/2000 [49:44<09:39,  1.71s/it, loss=0.166, lr=0.0001]
Steps:  83%|████████▎ | 1660/2000 [49:45<09:39,  1.71s/it, loss=0.142, lr=0.0001]
Steps:  83%|████████▎ | 1660/2000 [49:45<09:39,  1.71s/it, loss=0.316, lr=0.0001]
Steps:  83%|████████▎ | 1661/2000 [49:46<10:01,  1.77s/it, loss=0.316, lr=0.0001]
Steps:  83%|████████▎ | 1661/2000 [49:46<10:01,  1.77s/it, loss=0.206, lr=0.0001]
Steps:  83%|████████▎ | 1661/2000 [49:46<10:01,  1.77s/it, loss=0.197, lr=0.0001]
Steps:  83%|████████▎ | 1661/2000 [49:47<10:01,  1.77s/it, loss=0.141, lr=0.0001]
Steps:  83%|████████▎ | 1661/2000 [49:47<10:01,  1.77s/it, loss=0.0975, lr=0.0001]
Steps:  83%|████████▎ | 1662/2000 [49:48<09:47,  1.74s/it, loss=0.0975, lr=0.0001]
Steps:  83%|████████▎ | 1662/2000 [49:48<09:47,  1.74s/it, loss=0.156, lr=0.0001] 
Steps:  83%|████████▎ | 1662/2000 [49:48<09:47,  1.74s/it, loss=0.412, lr=0.0001]
Steps:  83%|████████▎ | 1662/2000 [49:48<09:47,  1.74s/it, loss=0.209, lr=0.0001]
Steps:  83%|████████▎ | 1662/2000 [49:49<09:47,  1.74s/it, loss=0.214, lr=0.0001]
Steps:  83%|████████▎ | 1663/2000 [49:49<09:37,  1.71s/it, loss=0.214, lr=0.0001]
Steps:  83%|████████▎ | 1663/2000 [49:49<09:37,  1.71s/it, loss=0.337, lr=0.0001]
Steps:  83%|████████▎ | 1663/2000 [49:50<09:37,  1.71s/it, loss=0.11, lr=0.0001] 
Steps:  83%|████████▎ | 1663/2000 [49:50<09:37,  1.71s/it, loss=0.165, lr=0.0001]
Steps:  83%|████████▎ | 1663/2000 [49:51<09:37,  1.71s/it, loss=0.219, lr=0.0001]
Steps:  83%|████████▎ | 1664/2000 [49:51<09:53,  1.77s/it, loss=0.219, lr=0.0001]
Steps:  83%|████████▎ | 1664/2000 [49:51<09:53,  1.77s/it, loss=1.24, lr=0.0001] 
Steps:  83%|████████▎ | 1664/2000 [49:52<09:53,  1.77s/it, loss=0.095, lr=0.0001]
Steps:  83%|████████▎ | 1664/2000 [49:52<09:53,  1.77s/it, loss=0.263, lr=0.0001]
Steps:  83%|████████▎ | 1664/2000 [49:52<09:53,  1.77s/it, loss=0.225, lr=0.0001]
Steps:  83%|████████▎ | 1665/2000 [49:53<09:39,  1.73s/it, loss=0.225, lr=0.0001]
Steps:  83%|████████▎ | 1665/2000 [49:53<09:39,  1.73s/it, loss=0.204, lr=0.0001]
Steps:  83%|████████▎ | 1665/2000 [49:53<09:39,  1.73s/it, loss=0.0981, lr=0.0001]
Steps:  83%|████████▎ | 1665/2000 [49:54<09:39,  1.73s/it, loss=0.225, lr=0.0001] 
Steps:  83%|████████▎ | 1665/2000 [49:54<09:39,  1.73s/it, loss=0.156, lr=0.0001]
Steps:  83%|████████▎ | 1666/2000 [49:54<09:28,  1.70s/it, loss=0.156, lr=0.0001]
Steps:  83%|████████▎ | 1666/2000 [49:54<09:28,  1.70s/it, loss=0.156, lr=0.0001]
Steps:  83%|████████▎ | 1666/2000 [49:55<09:28,  1.70s/it, loss=0.134, lr=0.0001]
Steps:  83%|████████▎ | 1666/2000 [49:55<09:28,  1.70s/it, loss=0.152, lr=0.0001]
Steps:  83%|████████▎ | 1666/2000 [49:56<09:28,  1.70s/it, loss=0.13, lr=0.0001] 
Steps:  83%|████████▎ | 1667/2000 [49:56<09:43,  1.75s/it, loss=0.13, lr=0.0001]
Steps:  83%|████████▎ | 1667/2000 [49:56<09:43,  1.75s/it, loss=0.175, lr=0.0001]
Steps:  83%|████████▎ | 1667/2000 [49:57<09:43,  1.75s/it, loss=0.158, lr=0.0001]
Steps:  83%|████████▎ | 1667/2000 [49:57<09:43,  1.75s/it, loss=0.0989, lr=0.0001]
Steps:  83%|████████▎ | 1667/2000 [49:57<09:43,  1.75s/it, loss=0.332, lr=0.0001] 
Steps:  83%|████████▎ | 1668/2000 [49:58<09:31,  1.72s/it, loss=0.332, lr=0.0001]
Steps:  83%|████████▎ | 1668/2000 [49:58<09:31,  1.72s/it, loss=0.161, lr=0.0001]
Steps:  83%|████████▎ | 1668/2000 [49:58<09:31,  1.72s/it, loss=0.158, lr=0.0001]
Steps:  83%|████████▎ | 1668/2000 [49:59<09:31,  1.72s/it, loss=0.232, lr=0.0001]
Steps:  83%|████████▎ | 1668/2000 [49:59<09:31,  1.72s/it, loss=0.26, lr=0.0001] 
Steps:  83%|████████▎ | 1669/2000 [50:00<09:25,  1.71s/it, loss=0.26, lr=0.0001]
Steps:  83%|████████▎ | 1669/2000 [50:00<09:25,  1.71s/it, loss=0.379, lr=0.0001]
Steps:  83%|████████▎ | 1669/2000 [50:00<09:25,  1.71s/it, loss=0.121, lr=0.0001]
Steps:  83%|████████▎ | 1669/2000 [50:00<09:25,  1.71s/it, loss=0.0749, lr=0.0001]
Steps:  83%|████████▎ | 1669/2000 [50:01<09:25,  1.71s/it, loss=0.22, lr=0.0001]  
Steps:  84%|████████▎ | 1670/2000 [50:02<09:44,  1.77s/it, loss=0.22, lr=0.0001]
Steps:  84%|████████▎ | 1670/2000 [50:02<09:44,  1.77s/it, loss=0.183, lr=0.0001]
Steps:  84%|████████▎ | 1670/2000 [50:02<09:44,  1.77s/it, loss=0.535, lr=0.0001]
Steps:  84%|████████▎ | 1670/2000 [50:02<09:44,  1.77s/it, loss=0.249, lr=0.0001]
Steps:  84%|████████▎ | 1670/2000 [50:03<09:44,  1.77s/it, loss=0.0682, lr=0.0001]
Steps:  84%|████████▎ | 1671/2000 [50:03<09:32,  1.74s/it, loss=0.0682, lr=0.0001]
Steps:  84%|████████▎ | 1671/2000 [50:03<09:32,  1.74s/it, loss=0.178, lr=0.0001] 
Steps:  84%|████████▎ | 1671/2000 [50:04<09:32,  1.74s/it, loss=0.169, lr=0.0001]
Steps:  84%|████████▎ | 1671/2000 [50:04<09:32,  1.74s/it, loss=0.217, lr=0.0001]
Steps:  84%|████████▎ | 1671/2000 [50:04<09:32,  1.74s/it, loss=0.171, lr=0.0001]
Steps:  84%|████████▎ | 1672/2000 [50:05<09:26,  1.73s/it, loss=0.171, lr=0.0001]
Steps:  84%|████████▎ | 1672/2000 [50:05<09:26,  1.73s/it, loss=0.178, lr=0.0001]
Steps:  84%|████████▎ | 1672/2000 [50:05<09:26,  1.73s/it, loss=0.281, lr=0.0001]
Steps:  84%|████████▎ | 1672/2000 [50:06<09:26,  1.73s/it, loss=0.246, lr=0.0001]
Steps:  84%|████████▎ | 1672/2000 [50:06<09:26,  1.73s/it, loss=0.203, lr=0.0001]
Steps:  84%|████████▎ | 1673/2000 [50:07<09:44,  1.79s/it, loss=0.203, lr=0.0001]
Steps:  84%|████████▎ | 1673/2000 [50:07<09:44,  1.79s/it, loss=0.158, lr=0.0001]
Steps:  84%|████████▎ | 1673/2000 [50:07<09:44,  1.79s/it, loss=0.138, lr=0.0001]
Steps:  84%|████████▎ | 1673/2000 [50:08<09:44,  1.79s/it, loss=0.126, lr=0.0001]
Steps:  84%|████████▎ | 1673/2000 [50:08<09:44,  1.79s/it, loss=0.152, lr=0.0001]
Steps:  84%|████████▎ | 1674/2000 [50:08<09:29,  1.75s/it, loss=0.152, lr=0.0001]
Steps:  84%|████████▎ | 1674/2000 [50:08<09:29,  1.75s/it, loss=0.164, lr=0.0001]
Steps:  84%|████████▎ | 1674/2000 [50:09<09:29,  1.75s/it, loss=0.314, lr=0.0001]
Steps:  84%|████████▎ | 1674/2000 [50:09<09:29,  1.75s/it, loss=0.185, lr=0.0001]
Steps:  84%|████████▎ | 1674/2000 [50:10<09:29,  1.75s/it, loss=0.165, lr=0.0001]
Steps:  84%|████████▍ | 1675/2000 [50:10<09:28,  1.75s/it, loss=0.165, lr=0.0001]
Steps:  84%|████████▍ | 1675/2000 [50:10<09:28,  1.75s/it, loss=0.125, lr=0.0001]
Steps:  84%|████████▍ | 1675/2000 [50:11<09:28,  1.75s/it, loss=0.0783, lr=0.0001]
Steps:  84%|████████▍ | 1675/2000 [50:11<09:28,  1.75s/it, loss=0.157, lr=0.0001] 
Steps:  84%|████████▍ | 1675/2000 [50:11<09:28,  1.75s/it, loss=0.206, lr=0.0001]
Steps:  84%|████████▍ | 1676/2000 [50:12<09:19,  1.73s/it, loss=0.206, lr=0.0001]
Steps:  84%|████████▍ | 1676/2000 [50:12<09:19,  1.73s/it, loss=0.199, lr=0.0001]
Steps:  84%|████████▍ | 1676/2000 [50:13<09:19,  1.73s/it, loss=0.102, lr=0.0001]
Steps:  84%|████████▍ | 1676/2000 [50:13<09:19,  1.73s/it, loss=0.254, lr=0.0001]
Steps:  84%|████████▍ | 1676/2000 [50:13<09:19,  1.73s/it, loss=0.14, lr=0.0001] 
Steps:  84%|████████▍ | 1677/2000 [50:14<09:37,  1.79s/it, loss=0.14, lr=0.0001]
Steps:  84%|████████▍ | 1677/2000 [50:14<09:37,  1.79s/it, loss=0.229, lr=0.0001]
Steps:  84%|████████▍ | 1677/2000 [50:14<09:37,  1.79s/it, loss=0.81, lr=0.0001] 
Steps:  84%|████████▍ | 1677/2000 [50:15<09:37,  1.79s/it, loss=0.163, lr=0.0001]
Steps:  84%|████████▍ | 1677/2000 [50:15<09:37,  1.79s/it, loss=0.129, lr=0.0001]
Steps:  84%|████████▍ | 1678/2000 [50:15<09:23,  1.75s/it, loss=0.129, lr=0.0001]
Steps:  84%|████████▍ | 1678/2000 [50:15<09:23,  1.75s/it, loss=0.113, lr=0.0001]
Steps:  84%|████████▍ | 1678/2000 [50:16<09:23,  1.75s/it, loss=0.141, lr=0.0001]
Steps:  84%|████████▍ | 1678/2000 [50:16<09:23,  1.75s/it, loss=0.224, lr=0.0001]
Steps:  84%|████████▍ | 1678/2000 [50:17<09:23,  1.75s/it, loss=0.0347, lr=0.0001]
Steps:  84%|████████▍ | 1679/2000 [50:17<09:16,  1.73s/it, loss=0.0347, lr=0.0001]
Steps:  84%|████████▍ | 1679/2000 [50:17<09:16,  1.73s/it, loss=0.277, lr=0.0001] 
Steps:  84%|████████▍ | 1679/2000 [50:18<09:16,  1.73s/it, loss=0.104, lr=0.0001]
Steps:  84%|████████▍ | 1679/2000 [50:18<09:16,  1.73s/it, loss=0.611, lr=0.0001]
Steps:  84%|████████▍ | 1679/2000 [50:19<09:16,  1.73s/it, loss=0.18, lr=0.0001] 
Steps:  84%|████████▍ | 1680/2000 [50:19<09:33,  1.79s/it, loss=0.18, lr=0.0001]
Steps:  84%|████████▍ | 1680/2000 [50:19<09:33,  1.79s/it, loss=0.149, lr=0.0001]
Steps:  84%|████████▍ | 1680/2000 [50:20<09:33,  1.79s/it, loss=0.197, lr=0.0001]
Steps:  84%|████████▍ | 1680/2000 [50:20<09:33,  1.79s/it, loss=0.169, lr=0.0001]
Steps:  84%|████████▍ | 1680/2000 [50:20<09:33,  1.79s/it, loss=0.895, lr=0.0001]
Steps:  84%|████████▍ | 1681/2000 [50:21<09:21,  1.76s/it, loss=0.895, lr=0.0001]
Steps:  84%|████████▍ | 1681/2000 [50:21<09:21,  1.76s/it, loss=0.142, lr=0.0001]
Steps:  84%|████████▍ | 1681/2000 [50:21<09:21,  1.76s/it, loss=0.182, lr=0.0001]
Steps:  84%|████████▍ | 1681/2000 [50:22<09:21,  1.76s/it, loss=0.158, lr=0.0001]
Steps:  84%|████████▍ | 1681/2000 [50:22<09:21,  1.76s/it, loss=0.323, lr=0.0001]
Steps:  84%|████████▍ | 1682/2000 [50:22<09:13,  1.74s/it, loss=0.323, lr=0.0001]
Steps:  84%|████████▍ | 1682/2000 [50:22<09:13,  1.74s/it, loss=0.0508, lr=0.0001]
Steps:  84%|████████▍ | 1682/2000 [50:23<09:13,  1.74s/it, loss=0.217, lr=0.0001] 
Steps:  84%|████████▍ | 1682/2000 [50:24<09:13,  1.74s/it, loss=0.12, lr=0.0001] 
Steps:  84%|████████▍ | 1682/2000 [50:24<09:13,  1.74s/it, loss=0.0868, lr=0.0001]
Steps:  84%|████████▍ | 1683/2000 [50:24<09:28,  1.79s/it, loss=0.0868, lr=0.0001]
Steps:  84%|████████▍ | 1683/2000 [50:24<09:28,  1.79s/it, loss=0.161, lr=0.0001] 
Steps:  84%|████████▍ | 1683/2000 [50:25<09:28,  1.79s/it, loss=0.261, lr=0.0001]
Steps:  84%|████████▍ | 1683/2000 [50:25<09:28,  1.79s/it, loss=0.109, lr=0.0001]
Steps:  84%|████████▍ | 1683/2000 [50:26<09:28,  1.79s/it, loss=0.126, lr=0.0001]
Steps:  84%|████████▍ | 1684/2000 [50:26<09:14,  1.75s/it, loss=0.126, lr=0.0001]
Steps:  84%|████████▍ | 1684/2000 [50:26<09:14,  1.75s/it, loss=0.165, lr=0.0001]
Steps:  84%|████████▍ | 1684/2000 [50:26<09:14,  1.75s/it, loss=0.138, lr=0.0001]
Steps:  84%|████████▍ | 1684/2000 [50:27<09:14,  1.75s/it, loss=0.148, lr=0.0001]
Steps:  84%|████████▍ | 1684/2000 [50:27<09:14,  1.75s/it, loss=0.217, lr=0.0001]
Steps:  84%|████████▍ | 1685/2000 [50:28<09:06,  1.74s/it, loss=0.217, lr=0.0001]
Steps:  84%|████████▍ | 1685/2000 [50:28<09:06,  1.74s/it, loss=0.157, lr=0.0001]
Steps:  84%|████████▍ | 1685/2000 [50:28<09:06,  1.74s/it, loss=0.207, lr=0.0001]
Steps:  84%|████████▍ | 1685/2000 [50:29<09:06,  1.74s/it, loss=0.213, lr=0.0001]
Steps:  84%|████████▍ | 1685/2000 [50:29<09:06,  1.74s/it, loss=0.113, lr=0.0001]
Steps:  84%|████████▍ | 1686/2000 [50:30<09:20,  1.79s/it, loss=0.113, lr=0.0001]
Steps:  84%|████████▍ | 1686/2000 [50:30<09:20,  1.79s/it, loss=0.116, lr=0.0001]
Steps:  84%|████████▍ | 1686/2000 [50:30<09:20,  1.79s/it, loss=0.0823, lr=0.0001]
Steps:  84%|████████▍ | 1686/2000 [50:30<09:20,  1.79s/it, loss=0.222, lr=0.0001] 
Steps:  84%|████████▍ | 1686/2000 [50:31<09:20,  1.79s/it, loss=0.101, lr=0.0001]
Steps:  84%|████████▍ | 1687/2000 [50:31<09:07,  1.75s/it, loss=0.101, lr=0.0001]
Steps:  84%|████████▍ | 1687/2000 [50:31<09:07,  1.75s/it, loss=0.838, lr=0.0001]
Steps:  84%|████████▍ | 1687/2000 [50:32<09:07,  1.75s/it, loss=0.226, lr=0.0001]
Steps:  84%|████████▍ | 1687/2000 [50:32<09:07,  1.75s/it, loss=0.116, lr=0.0001]
Steps:  84%|████████▍ | 1687/2000 [50:33<09:07,  1.75s/it, loss=0.532, lr=0.0001]
Steps:  84%|████████▍ | 1688/2000 [50:33<08:57,  1.72s/it, loss=0.532, lr=0.0001]
Steps:  84%|████████▍ | 1688/2000 [50:33<08:57,  1.72s/it, loss=0.14, lr=0.0001] 
Steps:  84%|████████▍ | 1688/2000 [50:33<08:57,  1.72s/it, loss=0.118, lr=0.0001]
Steps:  84%|████████▍ | 1688/2000 [50:34<08:57,  1.72s/it, loss=0.0998, lr=0.0001]
Steps:  84%|████████▍ | 1688/2000 [50:34<08:57,  1.72s/it, loss=0.247, lr=0.0001] 
Steps:  84%|████████▍ | 1689/2000 [50:35<09:12,  1.77s/it, loss=0.247, lr=0.0001]
Steps:  84%|████████▍ | 1689/2000 [50:35<09:12,  1.77s/it, loss=0.261, lr=0.0001]
Steps:  84%|████████▍ | 1689/2000 [50:35<09:12,  1.77s/it, loss=0.15, lr=0.0001] 
Steps:  84%|████████▍ | 1689/2000 [50:36<09:12,  1.77s/it, loss=0.151, lr=0.0001]
Steps:  84%|████████▍ | 1689/2000 [50:36<09:12,  1.77s/it, loss=0.138, lr=0.0001]
Steps:  84%|████████▍ | 1690/2000 [50:37<09:01,  1.75s/it, loss=0.138, lr=0.0001]
Steps:  84%|████████▍ | 1690/2000 [50:37<09:01,  1.75s/it, loss=0.0924, lr=0.0001]
Steps:  84%|████████▍ | 1690/2000 [50:37<09:01,  1.75s/it, loss=0.121, lr=0.0001] 
Steps:  84%|████████▍ | 1690/2000 [50:37<09:01,  1.75s/it, loss=0.171, lr=0.0001]
Steps:  84%|████████▍ | 1690/2000 [50:38<09:01,  1.75s/it, loss=0.114, lr=0.0001]
Steps:  85%|████████▍ | 1691/2000 [50:38<08:52,  1.72s/it, loss=0.114, lr=0.0001]
Steps:  85%|████████▍ | 1691/2000 [50:38<08:52,  1.72s/it, loss=0.208, lr=0.0001]
Steps:  85%|████████▍ | 1691/2000 [50:39<08:52,  1.72s/it, loss=0.287, lr=0.0001]
Steps:  85%|████████▍ | 1691/2000 [50:39<08:52,  1.72s/it, loss=0.193, lr=0.0001]
Steps:  85%|████████▍ | 1691/2000 [50:40<08:52,  1.72s/it, loss=0.171, lr=0.0001]
Steps:  85%|████████▍ | 1692/2000 [50:40<09:05,  1.77s/it, loss=0.171, lr=0.0001]
Steps:  85%|████████▍ | 1692/2000 [50:40<09:05,  1.77s/it, loss=0.333, lr=0.0001]
Steps:  85%|████████▍ | 1692/2000 [50:41<09:05,  1.77s/it, loss=0.167, lr=0.0001]
Steps:  85%|████████▍ | 1692/2000 [50:41<09:05,  1.77s/it, loss=0.0975, lr=0.0001]
Steps:  85%|████████▍ | 1692/2000 [50:41<09:05,  1.77s/it, loss=0.0938, lr=0.0001]
Steps:  85%|████████▍ | 1693/2000 [50:42<08:54,  1.74s/it, loss=0.0938, lr=0.0001]
Steps:  85%|████████▍ | 1693/2000 [50:42<08:54,  1.74s/it, loss=0.146, lr=0.0001] 
Steps:  85%|████████▍ | 1693/2000 [50:42<08:54,  1.74s/it, loss=0.199, lr=0.0001]
Steps:  85%|████████▍ | 1693/2000 [50:43<08:54,  1.74s/it, loss=0.239, lr=0.0001]
Steps:  85%|████████▍ | 1693/2000 [50:43<08:54,  1.74s/it, loss=0.144, lr=0.0001]
Steps:  85%|████████▍ | 1694/2000 [50:43<08:47,  1.72s/it, loss=0.144, lr=0.0001]
Steps:  85%|████████▍ | 1694/2000 [50:43<08:47,  1.72s/it, loss=0.195, lr=0.0001]
Steps:  85%|████████▍ | 1694/2000 [50:44<08:47,  1.72s/it, loss=0.141, lr=0.0001]
Steps:  85%|████████▍ | 1694/2000 [50:44<08:47,  1.72s/it, loss=0.207, lr=0.0001]
Steps:  85%|████████▍ | 1694/2000 [50:45<08:47,  1.72s/it, loss=0.0836, lr=0.0001]
Steps:  85%|████████▍ | 1695/2000 [50:45<09:03,  1.78s/it, loss=0.0836, lr=0.0001]
Steps:  85%|████████▍ | 1695/2000 [50:45<09:03,  1.78s/it, loss=0.366, lr=0.0001] 
Steps:  85%|████████▍ | 1695/2000 [50:46<09:03,  1.78s/it, loss=0.154, lr=0.0001]
Steps:  85%|████████▍ | 1695/2000 [50:46<09:03,  1.78s/it, loss=0.0556, lr=0.0001]
Steps:  85%|████████▍ | 1695/2000 [50:47<09:03,  1.78s/it, loss=0.946, lr=0.0001] 
Steps:  85%|████████▍ | 1696/2000 [50:47<08:50,  1.75s/it, loss=0.946, lr=0.0001]
Steps:  85%|████████▍ | 1696/2000 [50:47<08:50,  1.75s/it, loss=0.214, lr=0.0001]
Steps:  85%|████████▍ | 1696/2000 [50:47<08:50,  1.75s/it, loss=0.162, lr=0.0001]
Steps:  85%|████████▍ | 1696/2000 [50:48<08:50,  1.75s/it, loss=0.107, lr=0.0001]
Steps:  85%|████████▍ | 1696/2000 [50:48<08:50,  1.75s/it, loss=0.119, lr=0.0001]
Steps:  85%|████████▍ | 1697/2000 [50:49<08:41,  1.72s/it, loss=0.119, lr=0.0001]
Steps:  85%|████████▍ | 1697/2000 [50:49<08:41,  1.72s/it, loss=0.213, lr=0.0001]
Steps:  85%|████████▍ | 1697/2000 [50:49<08:41,  1.72s/it, loss=0.0472, lr=0.0001]
Steps:  85%|████████▍ | 1697/2000 [50:50<08:41,  1.72s/it, loss=0.194, lr=0.0001] 
Steps:  85%|████████▍ | 1697/2000 [50:50<08:41,  1.72s/it, loss=0.59, lr=0.0001] 
Steps:  85%|████████▍ | 1698/2000 [50:50<08:34,  1.70s/it, loss=0.59, lr=0.0001]
Steps:  85%|████████▍ | 1698/2000 [50:50<08:34,  1.70s/it, loss=1.06, lr=0.0001]
Steps:  85%|████████▍ | 1698/2000 [50:51<08:34,  1.70s/it, loss=0.183, lr=0.0001]
Steps:  85%|████████▍ | 1698/2000 [50:51<08:34,  1.70s/it, loss=0.434, lr=0.0001]
Steps:  85%|████████▍ | 1698/2000 [50:52<08:34,  1.70s/it, loss=0.253, lr=0.0001]
Steps:  85%|████████▍ | 1699/2000 [50:52<08:49,  1.76s/it, loss=0.253, lr=0.0001]
Steps:  85%|████████▍ | 1699/2000 [50:52<08:49,  1.76s/it, loss=0.134, lr=0.0001]
Steps:  85%|████████▍ | 1699/2000 [50:53<08:49,  1.76s/it, loss=0.144, lr=0.0001]
Steps:  85%|████████▍ | 1699/2000 [50:53<08:49,  1.76s/it, loss=0.0751, lr=0.0001]
Steps:  85%|████████▍ | 1699/2000 [50:53<08:49,  1.76s/it, loss=0.0759, lr=0.0001]
Steps:  85%|████████▌ | 1700/2000 [50:54<08:38,  1.73s/it, loss=0.0759, lr=0.0001]
Steps:  85%|████████▌ | 1700/2000 [50:54<08:38,  1.73s/it, loss=0.177, lr=0.0001] 
Steps:  85%|████████▌ | 1700/2000 [50:54<08:38,  1.73s/it, loss=0.151, lr=0.0001]
Steps:  85%|████████▌ | 1700/2000 [50:55<08:38,  1.73s/it, loss=0.141, lr=0.0001]
Steps:  85%|████████▌ | 1700/2000 [50:55<08:38,  1.73s/it, loss=0.225, lr=0.0001]
Steps:  85%|████████▌ | 1701/2000 [50:56<08:33,  1.72s/it, loss=0.225, lr=0.0001]
Steps:  85%|████████▌ | 1701/2000 [50:56<08:33,  1.72s/it, loss=0.0957, lr=0.0001]
Steps:  85%|████████▌ | 1701/2000 [50:56<08:33,  1.72s/it, loss=0.336, lr=0.0001] 
Steps:  85%|████████▌ | 1701/2000 [50:57<08:33,  1.72s/it, loss=0.12, lr=0.0001] 
Steps:  85%|████████▌ | 1701/2000 [50:57<08:33,  1.72s/it, loss=0.154, lr=0.0001]
Steps:  85%|████████▌ | 1702/2000 [50:58<08:46,  1.77s/it, loss=0.154, lr=0.0001]
Steps:  85%|████████▌ | 1702/2000 [50:58<08:46,  1.77s/it, loss=0.339, lr=0.0001]
Steps:  85%|████████▌ | 1702/2000 [50:58<08:46,  1.77s/it, loss=0.0732, lr=0.0001]
Steps:  85%|████████▌ | 1702/2000 [50:58<08:46,  1.77s/it, loss=0.148, lr=0.0001] 
Steps:  85%|████████▌ | 1702/2000 [50:59<08:46,  1.77s/it, loss=0.173, lr=0.0001]
Steps:  85%|████████▌ | 1703/2000 [50:59<08:45,  1.77s/it, loss=0.173, lr=0.0001]
Steps:  85%|████████▌ | 1703/2000 [50:59<08:45,  1.77s/it, loss=0.068, lr=0.0001]
Steps:  85%|████████▌ | 1703/2000 [51:00<08:45,  1.77s/it, loss=0.0889, lr=0.0001]
Steps:  85%|████████▌ | 1703/2000 [51:00<08:45,  1.77s/it, loss=0.0753, lr=0.0001]
Steps:  85%|████████▌ | 1703/2000 [51:00<08:45,  1.77s/it, loss=0.342, lr=0.0001] 
Steps:  85%|████████▌ | 1704/2000 [51:01<08:33,  1.73s/it, loss=0.342, lr=0.0001]
Steps:  85%|████████▌ | 1704/2000 [51:01<08:33,  1.73s/it, loss=0.137, lr=0.0001]
Steps:  85%|████████▌ | 1704/2000 [51:01<08:33,  1.73s/it, loss=0.135, lr=0.0001]
Steps:  85%|████████▌ | 1704/2000 [51:02<08:33,  1.73s/it, loss=0.282, lr=0.0001]
Steps:  85%|████████▌ | 1704/2000 [51:02<08:33,  1.73s/it, loss=0.21, lr=0.0001] 
Steps:  85%|████████▌ | 1705/2000 [51:03<08:45,  1.78s/it, loss=0.21, lr=0.0001]
Steps:  85%|████████▌ | 1705/2000 [51:03<08:45,  1.78s/it, loss=0.218, lr=0.0001]05/30/2026 09:23:28 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/config.json "HTTP/1.1 200 OK"
05/30/2026 09:23:29 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/config.json "HTTP/1.1 200 OK"
05/30/2026 09:23:29 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/model.safetensors "HTTP/1.1 302 Found"


Loading weights:   0%|          | 0/196 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 196/196 [00:00<00:00, 7009.16it/s]
05/30/2026 09:23:29 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/config.json "HTTP/1.1 200 OK"
05/30/2026 09:23:30 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/config.json "HTTP/1.1 200 OK"
05/30/2026 09:23:30 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/model.safetensors "HTTP/1.1 404 Not Found"
05/30/2026 09:23:30 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/model.safetensors.index.json "HTTP/1.1 200 OK"
05/30/2026 09:23:31 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev/revision/main "HTTP/1.1 200 OK"


Fetching 2 files:   0%|          | 0/2 [00:00<?, ?it/s]
Fetching 2 files: 100%|██████████| 2/2 [00:00<00:00, 4050.51it/s]


Loading weights:   0%|          | 0/219 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 219/219 [00:00<00:00, 9604.27it/s]
05/30/2026 09:23:31 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev "HTTP/1.1 200 OK"
05/30/2026 09:23:32 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/model_index.json "HTTP/1.1 200 OK"
{'feature_extractor', 'image_encoder'} was not found in config. Values will be initialized to default values.


Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]Loaded tokenizer_2 as T5TokenizerFast from `tokenizer_2` subfolder of black-forest-labs/FLUX.1-dev.


Loading pipeline components...:  43%|████▎     | 3/7 [00:00<00:00, 15.76it/s]Loaded tokenizer as CLIPTokenizer from `tokenizer` subfolder of black-forest-labs/FLUX.1-dev.
{'stochastic_sampling', 'use_beta_sigmas', 'invert_sigmas', 'time_shift_type', 'use_exponential_sigmas', 'shift_terminal', 'use_karras_sigmas'} was not found in config. Values will be initialized to default values.
Loaded scheduler as FlowMatchEulerDiscreteScheduler from `scheduler` subfolder of black-forest-labs/FLUX.1-dev.

Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 28.55it/s]
05/30/2026 09:23:32 - INFO - __main__ - [RANK 0] Running validation... 
 Generating 1 images with prompt: emj icon of a pelican with a hat, centered on a plain white background.

Steps:  85%|████████▌ | 1705/2000 [51:18<08:45,  1.78s/it, loss=0.0929, lr=0.0001]
Steps:  85%|████████▌ | 1705/2000 [51:18<08:45,  1.78s/it, loss=0.187, lr=0.0001] 
Steps:  85%|████████▌ | 1705/2000 [51:18<08:45,  1.78s/it, loss=0.161, lr=0.0001]
Steps:  85%|████████▌ | 1706/2000 [51:19<29:44,  6.07s/it, loss=0.161, lr=0.0001]
Steps:  85%|████████▌ | 1706/2000 [51:19<29:44,  6.07s/it, loss=0.188, lr=0.0001]
Steps:  85%|████████▌ | 1706/2000 [51:19<29:44,  6.07s/it, loss=0.188, lr=0.0001]
Steps:  85%|████████▌ | 1706/2000 [51:20<29:44,  6.07s/it, loss=0.174, lr=0.0001]
Steps:  85%|████████▌ | 1706/2000 [51:20<29:44,  6.07s/it, loss=0.0846, lr=0.0001]
Steps:  85%|████████▌ | 1707/2000 [51:21<23:12,  4.75s/it, loss=0.0846, lr=0.0001]
Steps:  85%|████████▌ | 1707/2000 [51:21<23:12,  4.75s/it, loss=0.143, lr=0.0001] 
Steps:  85%|████████▌ | 1707/2000 [51:21<23:12,  4.75s/it, loss=0.259, lr=0.0001]
Steps:  85%|████████▌ | 1707/2000 [51:21<23:12,  4.75s/it, loss=0.243, lr=0.0001]
Steps:  85%|████████▌ | 1707/2000 [51:22<23:12,  4.75s/it, loss=0.291, lr=0.0001]
Steps:  85%|████████▌ | 1708/2000 [51:22<18:37,  3.83s/it, loss=0.291, lr=0.0001]
Steps:  85%|████████▌ | 1708/2000 [51:22<18:37,  3.83s/it, loss=0.0865, lr=0.0001]
Steps:  85%|████████▌ | 1708/2000 [51:23<18:37,  3.83s/it, loss=0.305, lr=0.0001] 
Steps:  85%|████████▌ | 1708/2000 [51:23<18:37,  3.83s/it, loss=0.0577, lr=0.0001]
Steps:  85%|████████▌ | 1708/2000 [51:24<18:37,  3.83s/it, loss=0.176, lr=0.0001] 
Steps:  85%|████████▌ | 1709/2000 [51:24<15:44,  3.25s/it, loss=0.176, lr=0.0001]
Steps:  85%|████████▌ | 1709/2000 [51:24<15:44,  3.25s/it, loss=0.178, lr=0.0001]
Steps:  85%|████████▌ | 1709/2000 [51:25<15:44,  3.25s/it, loss=0.272, lr=0.0001]
Steps:  85%|████████▌ | 1709/2000 [51:25<15:44,  3.25s/it, loss=0.136, lr=0.0001]
Steps:  85%|████████▌ | 1709/2000 [51:25<15:44,  3.25s/it, loss=0.227, lr=0.0001]
Steps:  86%|████████▌ | 1710/2000 [51:26<13:24,  2.77s/it, loss=0.227, lr=0.0001]
Steps:  86%|████████▌ | 1710/2000 [51:26<13:24,  2.77s/it, loss=0.157, lr=0.0001]
Steps:  86%|████████▌ | 1710/2000 [51:26<13:24,  2.77s/it, loss=0.0979, lr=0.0001]
Steps:  86%|████████▌ | 1710/2000 [51:27<13:24,  2.77s/it, loss=0.26, lr=0.0001]  
Steps:  86%|████████▌ | 1710/2000 [51:27<13:24,  2.77s/it, loss=0.113, lr=0.0001]
Steps:  86%|████████▌ | 1711/2000 [51:27<11:44,  2.44s/it, loss=0.113, lr=0.0001]
Steps:  86%|████████▌ | 1711/2000 [51:27<11:44,  2.44s/it, loss=0.204, lr=0.0001]
Steps:  86%|████████▌ | 1711/2000 [51:28<11:44,  2.44s/it, loss=0.109, lr=0.0001]
Steps:  86%|████████▌ | 1711/2000 [51:29<11:44,  2.44s/it, loss=0.189, lr=0.0001]
Steps:  86%|████████▌ | 1711/2000 [51:29<11:44,  2.44s/it, loss=0.211, lr=0.0001]
Steps:  86%|████████▌ | 1712/2000 [51:29<10:56,  2.28s/it, loss=0.211, lr=0.0001]
Steps:  86%|████████▌ | 1712/2000 [51:29<10:56,  2.28s/it, loss=0.25, lr=0.0001] 
Steps:  86%|████████▌ | 1712/2000 [51:30<10:56,  2.28s/it, loss=0.199, lr=0.0001]
Steps:  86%|████████▌ | 1712/2000 [51:30<10:56,  2.28s/it, loss=0.128, lr=0.0001]
Steps:  86%|████████▌ | 1712/2000 [51:31<10:56,  2.28s/it, loss=0.14, lr=0.0001] 
Steps:  86%|████████▌ | 1713/2000 [51:31<10:01,  2.10s/it, loss=0.14, lr=0.0001]
Steps:  86%|████████▌ | 1713/2000 [51:31<10:01,  2.10s/it, loss=0.136, lr=0.0001]
Steps:  86%|████████▌ | 1713/2000 [51:31<10:01,  2.10s/it, loss=0.0975, lr=0.0001]
Steps:  86%|████████▌ | 1713/2000 [51:32<10:01,  2.10s/it, loss=0.0966, lr=0.0001]
Steps:  86%|████████▌ | 1713/2000 [51:32<10:01,  2.10s/it, loss=0.201, lr=0.0001] 
Steps:  86%|████████▌ | 1714/2000 [51:33<09:22,  1.97s/it, loss=0.201, lr=0.0001]
Steps:  86%|████████▌ | 1714/2000 [51:33<09:22,  1.97s/it, loss=0.165, lr=0.0001]
Steps:  86%|████████▌ | 1714/2000 [51:33<09:22,  1.97s/it, loss=0.216, lr=0.0001]
Steps:  86%|████████▌ | 1714/2000 [51:34<09:22,  1.97s/it, loss=0.156, lr=0.0001]
Steps:  86%|████████▌ | 1714/2000 [51:34<09:22,  1.97s/it, loss=0.116, lr=0.0001]
Steps:  86%|████████▌ | 1715/2000 [51:35<09:14,  1.95s/it, loss=0.116, lr=0.0001]
Steps:  86%|████████▌ | 1715/2000 [51:35<09:14,  1.95s/it, loss=0.16, lr=0.0001] 
Steps:  86%|████████▌ | 1715/2000 [51:35<09:14,  1.95s/it, loss=0.216, lr=0.0001]
Steps:  86%|████████▌ | 1715/2000 [51:35<09:14,  1.95s/it, loss=0.153, lr=0.0001]
Steps:  86%|████████▌ | 1715/2000 [51:36<09:14,  1.95s/it, loss=0.135, lr=0.0001]
Steps:  86%|████████▌ | 1716/2000 [51:36<08:49,  1.86s/it, loss=0.135, lr=0.0001]
Steps:  86%|████████▌ | 1716/2000 [51:36<08:49,  1.86s/it, loss=0.149, lr=0.0001]
Steps:  86%|████████▌ | 1716/2000 [51:37<08:49,  1.86s/it, loss=0.233, lr=0.0001]
Steps:  86%|████████▌ | 1716/2000 [51:37<08:49,  1.86s/it, loss=0.231, lr=0.0001]
Steps:  86%|████████▌ | 1716/2000 [51:38<08:49,  1.86s/it, loss=0.351, lr=0.0001]
Steps:  86%|████████▌ | 1717/2000 [51:38<08:35,  1.82s/it, loss=0.351, lr=0.0001]
Steps:  86%|████████▌ | 1717/2000 [51:38<08:35,  1.82s/it, loss=0.195, lr=0.0001]
Steps:  86%|████████▌ | 1717/2000 [51:38<08:35,  1.82s/it, loss=0.955, lr=0.0001]
Steps:  86%|████████▌ | 1717/2000 [51:39<08:35,  1.82s/it, loss=0.12, lr=0.0001] 
Steps:  86%|████████▌ | 1717/2000 [51:39<08:35,  1.82s/it, loss=0.359, lr=0.0001]
Steps:  86%|████████▌ | 1718/2000 [51:40<08:40,  1.85s/it, loss=0.359, lr=0.0001]
Steps:  86%|████████▌ | 1718/2000 [51:40<08:40,  1.85s/it, loss=0.11, lr=0.0001] 
Steps:  86%|████████▌ | 1718/2000 [51:40<08:40,  1.85s/it, loss=0.0521, lr=0.0001]
Steps:  86%|████████▌ | 1718/2000 [51:41<08:40,  1.85s/it, loss=0.218, lr=0.0001] 
Steps:  86%|████████▌ | 1718/2000 [51:41<08:40,  1.85s/it, loss=0.143, lr=0.0001]
Steps:  86%|████████▌ | 1719/2000 [51:42<08:25,  1.80s/it, loss=0.143, lr=0.0001]
Steps:  86%|████████▌ | 1719/2000 [51:42<08:25,  1.80s/it, loss=0.19, lr=0.0001] 
Steps:  86%|████████▌ | 1719/2000 [51:42<08:25,  1.80s/it, loss=0.128, lr=0.0001]
Steps:  86%|████████▌ | 1719/2000 [51:42<08:25,  1.80s/it, loss=0.169, lr=0.0001]
Steps:  86%|████████▌ | 1719/2000 [51:43<08:25,  1.80s/it, loss=0.271, lr=0.0001]
Steps:  86%|████████▌ | 1720/2000 [51:43<08:15,  1.77s/it, loss=0.271, lr=0.0001]
Steps:  86%|████████▌ | 1720/2000 [51:43<08:15,  1.77s/it, loss=0.409, lr=0.0001]
Steps:  86%|████████▌ | 1720/2000 [51:44<08:15,  1.77s/it, loss=0.171, lr=0.0001]
Steps:  86%|████████▌ | 1720/2000 [51:44<08:15,  1.77s/it, loss=0.235, lr=0.0001]
Steps:  86%|████████▌ | 1720/2000 [51:45<08:15,  1.77s/it, loss=0.21, lr=0.0001] 
Steps:  86%|████████▌ | 1721/2000 [51:45<08:25,  1.81s/it, loss=0.21, lr=0.0001]
Steps:  86%|████████▌ | 1721/2000 [51:45<08:25,  1.81s/it, loss=0.379, lr=0.0001]
Steps:  86%|████████▌ | 1721/2000 [51:46<08:25,  1.81s/it, loss=0.416, lr=0.0001]
Steps:  86%|████████▌ | 1721/2000 [51:46<08:25,  1.81s/it, loss=0.119, lr=0.0001]
Steps:  86%|████████▌ | 1721/2000 [51:46<08:25,  1.81s/it, loss=0.257, lr=0.0001]
Steps:  86%|████████▌ | 1722/2000 [51:47<08:12,  1.77s/it, loss=0.257, lr=0.0001]
Steps:  86%|████████▌ | 1722/2000 [51:47<08:12,  1.77s/it, loss=0.177, lr=0.0001]
Steps:  86%|████████▌ | 1722/2000 [51:47<08:12,  1.77s/it, loss=0.141, lr=0.0001]
Steps:  86%|████████▌ | 1722/2000 [51:48<08:12,  1.77s/it, loss=0.177, lr=0.0001]
Steps:  86%|████████▌ | 1722/2000 [51:48<08:12,  1.77s/it, loss=0.189, lr=0.0001]
Steps:  86%|████████▌ | 1723/2000 [51:49<08:01,  1.74s/it, loss=0.189, lr=0.0001]
Steps:  86%|████████▌ | 1723/2000 [51:49<08:01,  1.74s/it, loss=0.311, lr=0.0001]
Steps:  86%|████████▌ | 1723/2000 [51:49<08:01,  1.74s/it, loss=0.252, lr=0.0001]
Steps:  86%|████████▌ | 1723/2000 [51:49<08:01,  1.74s/it, loss=0.0732, lr=0.0001]
Steps:  86%|████████▌ | 1723/2000 [51:50<08:01,  1.74s/it, loss=1.31, lr=0.0001]  
Steps:  86%|████████▌ | 1724/2000 [51:50<08:16,  1.80s/it, loss=1.31, lr=0.0001]
Steps:  86%|████████▌ | 1724/2000 [51:50<08:16,  1.80s/it, loss=0.0167, lr=0.0001]
Steps:  86%|████████▌ | 1724/2000 [51:51<08:16,  1.80s/it, loss=0.777, lr=0.0001] 
Steps:  86%|████████▌ | 1724/2000 [51:51<08:16,  1.80s/it, loss=0.0648, lr=0.0001]
Steps:  86%|████████▌ | 1724/2000 [51:52<08:16,  1.80s/it, loss=0.169, lr=0.0001] 
Steps:  86%|████████▋ | 1725/2000 [51:52<08:05,  1.77s/it, loss=0.169, lr=0.0001]
Steps:  86%|████████▋ | 1725/2000 [51:52<08:05,  1.77s/it, loss=0.217, lr=0.0001]
Steps:  86%|████████▋ | 1725/2000 [51:53<08:05,  1.77s/it, loss=1.07, lr=0.0001] 
Steps:  86%|████████▋ | 1725/2000 [51:53<08:05,  1.77s/it, loss=0.13, lr=0.0001]
Steps:  86%|████████▋ | 1725/2000 [51:53<08:05,  1.77s/it, loss=0.661, lr=0.0001]
Steps:  86%|████████▋ | 1726/2000 [51:54<07:56,  1.74s/it, loss=0.661, lr=0.0001]
Steps:  86%|████████▋ | 1726/2000 [51:54<07:56,  1.74s/it, loss=0.195, lr=0.0001]
Steps:  86%|████████▋ | 1726/2000 [51:54<07:56,  1.74s/it, loss=0.118, lr=0.0001]
Steps:  86%|████████▋ | 1726/2000 [51:55<07:56,  1.74s/it, loss=0.203, lr=0.0001]
Steps:  86%|████████▋ | 1726/2000 [51:55<07:56,  1.74s/it, loss=0.18, lr=0.0001] 
Steps:  86%|████████▋ | 1727/2000 [51:56<07:49,  1.72s/it, loss=0.18, lr=0.0001]
Steps:  86%|████████▋ | 1727/2000 [51:56<07:49,  1.72s/it, loss=0.178, lr=0.0001]
Steps:  86%|████████▋ | 1727/2000 [51:56<07:49,  1.72s/it, loss=0.41, lr=0.0001] 
Steps:  86%|████████▋ | 1727/2000 [51:57<07:49,  1.72s/it, loss=0.21, lr=0.0001]
Steps:  86%|████████▋ | 1727/2000 [51:57<07:49,  1.72s/it, loss=0.373, lr=0.0001]
Steps:  86%|████████▋ | 1728/2000 [51:57<08:05,  1.79s/it, loss=0.373, lr=0.0001]
Steps:  86%|████████▋ | 1728/2000 [51:57<08:05,  1.79s/it, loss=0.168, lr=0.0001]
Steps:  86%|████████▋ | 1728/2000 [51:58<08:05,  1.79s/it, loss=0.346, lr=0.0001]
Steps:  86%|████████▋ | 1728/2000 [51:58<08:05,  1.79s/it, loss=0.146, lr=0.0001]
Steps:  86%|████████▋ | 1728/2000 [51:59<08:05,  1.79s/it, loss=0.171, lr=0.0001]
Steps:  86%|████████▋ | 1729/2000 [51:59<07:54,  1.75s/it, loss=0.171, lr=0.0001]
Steps:  86%|████████▋ | 1729/2000 [51:59<07:54,  1.75s/it, loss=0.554, lr=0.0001]
Steps:  86%|████████▋ | 1729/2000 [52:00<07:54,  1.75s/it, loss=0.17, lr=0.0001] 
Steps:  86%|████████▋ | 1729/2000 [52:00<07:54,  1.75s/it, loss=0.0827, lr=0.0001]
Steps:  86%|████████▋ | 1729/2000 [52:00<07:54,  1.75s/it, loss=0.256, lr=0.0001] 
Steps:  86%|████████▋ | 1730/2000 [52:01<07:46,  1.73s/it, loss=0.256, lr=0.0001]
Steps:  86%|████████▋ | 1730/2000 [52:01<07:46,  1.73s/it, loss=0.197, lr=0.0001]
Steps:  86%|████████▋ | 1730/2000 [52:01<07:46,  1.73s/it, loss=0.165, lr=0.0001]
Steps:  86%|████████▋ | 1730/2000 [52:02<07:46,  1.73s/it, loss=0.222, lr=0.0001]
Steps:  86%|████████▋ | 1730/2000 [52:02<07:46,  1.73s/it, loss=0.0612, lr=0.0001]
Steps:  87%|████████▋ | 1731/2000 [52:03<07:58,  1.78s/it, loss=0.0612, lr=0.0001]
Steps:  87%|████████▋ | 1731/2000 [52:03<07:58,  1.78s/it, loss=0.16, lr=0.0001]  
Steps:  87%|████████▋ | 1731/2000 [52:03<07:58,  1.78s/it, loss=0.153, lr=0.0001]
Steps:  87%|████████▋ | 1731/2000 [52:04<07:58,  1.78s/it, loss=0.0764, lr=0.0001]
Steps:  87%|████████▋ | 1731/2000 [52:04<07:58,  1.78s/it, loss=0.148, lr=0.0001] 
Steps:  87%|████████▋ | 1732/2000 [52:04<07:48,  1.75s/it, loss=0.148, lr=0.0001]
Steps:  87%|████████▋ | 1732/2000 [52:04<07:48,  1.75s/it, loss=0.319, lr=0.0001]
Steps:  87%|████████▋ | 1732/2000 [52:05<07:48,  1.75s/it, loss=0.305, lr=0.0001]
Steps:  87%|████████▋ | 1732/2000 [52:05<07:48,  1.75s/it, loss=0.139, lr=0.0001]
Steps:  87%|████████▋ | 1732/2000 [52:06<07:48,  1.75s/it, loss=0.142, lr=0.0001]
Steps:  87%|████████▋ | 1733/2000 [52:06<07:39,  1.72s/it, loss=0.142, lr=0.0001]
Steps:  87%|████████▋ | 1733/2000 [52:06<07:39,  1.72s/it, loss=0.183, lr=0.0001]
Steps:  87%|████████▋ | 1733/2000 [52:06<07:39,  1.72s/it, loss=0.235, lr=0.0001]
Steps:  87%|████████▋ | 1733/2000 [52:07<07:39,  1.72s/it, loss=0.283, lr=0.0001]
Steps:  87%|████████▋ | 1733/2000 [52:08<07:39,  1.72s/it, loss=0.127, lr=0.0001]
Steps:  87%|████████▋ | 1734/2000 [52:08<07:53,  1.78s/it, loss=0.127, lr=0.0001]
Steps:  87%|████████▋ | 1734/2000 [52:08<07:53,  1.78s/it, loss=0.138, lr=0.0001]
Steps:  87%|████████▋ | 1734/2000 [52:08<07:53,  1.78s/it, loss=0.155, lr=0.0001]
Steps:  87%|████████▋ | 1734/2000 [52:09<07:53,  1.78s/it, loss=0.214, lr=0.0001]
Steps:  87%|████████▋ | 1734/2000 [52:09<07:53,  1.78s/it, loss=0.121, lr=0.0001]
Steps:  87%|████████▋ | 1735/2000 [52:10<07:42,  1.75s/it, loss=0.121, lr=0.0001]
Steps:  87%|████████▋ | 1735/2000 [52:10<07:42,  1.75s/it, loss=0.14, lr=0.0001] 
Steps:  87%|████████▋ | 1735/2000 [52:10<07:42,  1.75s/it, loss=0.129, lr=0.0001]
Steps:  87%|████████▋ | 1735/2000 [52:10<07:42,  1.75s/it, loss=0.337, lr=0.0001]
Steps:  87%|████████▋ | 1735/2000 [52:11<07:42,  1.75s/it, loss=0.211, lr=0.0001]
Steps:  87%|████████▋ | 1736/2000 [52:11<07:33,  1.72s/it, loss=0.211, lr=0.0001]
Steps:  87%|████████▋ | 1736/2000 [52:11<07:33,  1.72s/it, loss=0.147, lr=0.0001]
Steps:  87%|████████▋ | 1736/2000 [52:12<07:33,  1.72s/it, loss=0.155, lr=0.0001]
Steps:  87%|████████▋ | 1736/2000 [52:12<07:33,  1.72s/it, loss=0.196, lr=0.0001]
Steps:  87%|████████▋ | 1736/2000 [52:13<07:33,  1.72s/it, loss=0.0591, lr=0.0001]
Steps:  87%|████████▋ | 1737/2000 [52:13<07:48,  1.78s/it, loss=0.0591, lr=0.0001]
Steps:  87%|████████▋ | 1737/2000 [52:13<07:48,  1.78s/it, loss=0.733, lr=0.0001] 
Steps:  87%|████████▋ | 1737/2000 [52:14<07:48,  1.78s/it, loss=0.309, lr=0.0001]
Steps:  87%|████████▋ | 1737/2000 [52:14<07:48,  1.78s/it, loss=0.142, lr=0.0001]
Steps:  87%|████████▋ | 1737/2000 [52:14<07:48,  1.78s/it, loss=0.196, lr=0.0001]
Steps:  87%|████████▋ | 1738/2000 [52:15<07:37,  1.75s/it, loss=0.196, lr=0.0001]
Steps:  87%|████████▋ | 1738/2000 [52:15<07:37,  1.75s/it, loss=0.222, lr=0.0001]
Steps:  87%|████████▋ | 1738/2000 [52:15<07:37,  1.75s/it, loss=0.209, lr=0.0001]
Steps:  87%|████████▋ | 1738/2000 [52:16<07:37,  1.75s/it, loss=0.174, lr=0.0001]
Steps:  87%|████████▋ | 1738/2000 [52:16<07:37,  1.75s/it, loss=0.154, lr=0.0001]
Steps:  87%|████████▋ | 1739/2000 [52:17<07:28,  1.72s/it, loss=0.154, lr=0.0001]
Steps:  87%|████████▋ | 1739/2000 [52:17<07:28,  1.72s/it, loss=0.129, lr=0.0001]
Steps:  87%|████████▋ | 1739/2000 [52:17<07:28,  1.72s/it, loss=0.156, lr=0.0001]
Steps:  87%|████████▋ | 1739/2000 [52:17<07:28,  1.72s/it, loss=0.601, lr=0.0001]
Steps:  87%|████████▋ | 1739/2000 [52:18<07:28,  1.72s/it, loss=0.165, lr=0.0001]
Steps:  87%|████████▋ | 1740/2000 [52:18<07:41,  1.77s/it, loss=0.165, lr=0.0001]
Steps:  87%|████████▋ | 1740/2000 [52:18<07:41,  1.77s/it, loss=0.121, lr=0.0001]
Steps:  87%|████████▋ | 1740/2000 [52:19<07:41,  1.77s/it, loss=0.18, lr=0.0001] 
Steps:  87%|████████▋ | 1740/2000 [52:19<07:41,  1.77s/it, loss=0.128, lr=0.0001]
Steps:  87%|████████▋ | 1740/2000 [52:20<07:41,  1.77s/it, loss=0.0896, lr=0.0001]
Steps:  87%|████████▋ | 1741/2000 [52:20<07:30,  1.74s/it, loss=0.0896, lr=0.0001]
Steps:  87%|████████▋ | 1741/2000 [52:20<07:30,  1.74s/it, loss=1.17, lr=0.0001]  
Steps:  87%|████████▋ | 1741/2000 [52:20<07:30,  1.74s/it, loss=0.211, lr=0.0001]
Steps:  87%|████████▋ | 1741/2000 [52:21<07:30,  1.74s/it, loss=0.286, lr=0.0001]
Steps:  87%|████████▋ | 1741/2000 [52:21<07:30,  1.74s/it, loss=0.134, lr=0.0001]
Steps:  87%|████████▋ | 1742/2000 [52:22<07:21,  1.71s/it, loss=0.134, lr=0.0001]
Steps:  87%|████████▋ | 1742/2000 [52:22<07:21,  1.71s/it, loss=0.226, lr=0.0001]
Steps:  87%|████████▋ | 1742/2000 [52:22<07:21,  1.71s/it, loss=0.183, lr=0.0001]
Steps:  87%|████████▋ | 1742/2000 [52:23<07:21,  1.71s/it, loss=0.127, lr=0.0001]
Steps:  87%|████████▋ | 1742/2000 [52:23<07:21,  1.71s/it, loss=0.13, lr=0.0001] 
Steps:  87%|████████▋ | 1743/2000 [52:24<07:33,  1.76s/it, loss=0.13, lr=0.0001]
Steps:  87%|████████▋ | 1743/2000 [52:24<07:33,  1.76s/it, loss=0.217, lr=0.0001]
Steps:  87%|████████▋ | 1743/2000 [52:24<07:33,  1.76s/it, loss=0.186, lr=0.0001]
Steps:  87%|████████▋ | 1743/2000 [52:24<07:33,  1.76s/it, loss=0.142, lr=0.0001]
Steps:  87%|████████▋ | 1743/2000 [52:25<07:33,  1.76s/it, loss=0.168, lr=0.0001]
Steps:  87%|████████▋ | 1744/2000 [52:25<07:22,  1.73s/it, loss=0.168, lr=0.0001]
Steps:  87%|████████▋ | 1744/2000 [52:25<07:22,  1.73s/it, loss=0.153, lr=0.0001]
Steps:  87%|████████▋ | 1744/2000 [52:26<07:22,  1.73s/it, loss=0.138, lr=0.0001]
Steps:  87%|████████▋ | 1744/2000 [52:26<07:22,  1.73s/it, loss=0.18, lr=0.0001] 
Steps:  87%|████████▋ | 1744/2000 [52:26<07:22,  1.73s/it, loss=0.11, lr=0.0001]
Steps:  87%|████████▋ | 1745/2000 [52:27<07:15,  1.71s/it, loss=0.11, lr=0.0001]
Steps:  87%|████████▋ | 1745/2000 [52:27<07:15,  1.71s/it, loss=0.597, lr=0.0001]
Steps:  87%|████████▋ | 1745/2000 [52:27<07:15,  1.71s/it, loss=0.176, lr=0.0001]
Steps:  87%|████████▋ | 1745/2000 [52:28<07:15,  1.71s/it, loss=0.547, lr=0.0001]
Steps:  87%|████████▋ | 1745/2000 [52:28<07:15,  1.71s/it, loss=0.218, lr=0.0001]
Steps:  87%|████████▋ | 1746/2000 [52:29<07:09,  1.69s/it, loss=0.218, lr=0.0001]
Steps:  87%|████████▋ | 1746/2000 [52:29<07:09,  1.69s/it, loss=0.106, lr=0.0001]
Steps:  87%|████████▋ | 1746/2000 [52:29<07:09,  1.69s/it, loss=0.242, lr=0.0001]
Steps:  87%|████████▋ | 1746/2000 [52:30<07:09,  1.69s/it, loss=0.283, lr=0.0001]
Steps:  87%|████████▋ | 1746/2000 [52:30<07:09,  1.69s/it, loss=0.399, lr=0.0001]
Steps:  87%|████████▋ | 1747/2000 [52:30<07:23,  1.75s/it, loss=0.399, lr=0.0001]
Steps:  87%|████████▋ | 1747/2000 [52:30<07:23,  1.75s/it, loss=0.0879, lr=0.0001]
Steps:  87%|████████▋ | 1747/2000 [52:31<07:23,  1.75s/it, loss=0.047, lr=0.0001] 
Steps:  87%|████████▋ | 1747/2000 [52:31<07:23,  1.75s/it, loss=0.278, lr=0.0001]
Steps:  87%|████████▋ | 1747/2000 [52:32<07:23,  1.75s/it, loss=0.217, lr=0.0001]
Steps:  87%|████████▋ | 1748/2000 [52:32<07:14,  1.72s/it, loss=0.217, lr=0.0001]
Steps:  87%|████████▋ | 1748/2000 [52:32<07:14,  1.72s/it, loss=0.209, lr=0.0001]
Steps:  87%|████████▋ | 1748/2000 [52:33<07:14,  1.72s/it, loss=0.204, lr=0.0001]
Steps:  87%|████████▋ | 1748/2000 [52:33<07:14,  1.72s/it, loss=0.324, lr=0.0001]
Steps:  87%|████████▋ | 1748/2000 [52:33<07:14,  1.72s/it, loss=0.178, lr=0.0001]
Steps:  87%|████████▋ | 1749/2000 [52:34<07:08,  1.71s/it, loss=0.178, lr=0.0001]
Steps:  87%|████████▋ | 1749/2000 [52:34<07:08,  1.71s/it, loss=0.229, lr=0.0001]
Steps:  87%|████████▋ | 1749/2000 [52:34<07:08,  1.71s/it, loss=0.213, lr=0.0001]
Steps:  87%|████████▋ | 1749/2000 [52:35<07:08,  1.71s/it, loss=0.203, lr=0.0001]
Steps:  87%|████████▋ | 1749/2000 [52:35<07:08,  1.71s/it, loss=0.759, lr=0.0001]
Steps:  88%|████████▊ | 1750/2000 [52:36<07:21,  1.76s/it, loss=0.759, lr=0.0001]05/30/2026 09:25:01 - INFO - accelerate.accelerator - [RANK 0] Saving current state to /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1750
Model weights saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1750/pytorch_lora_weights.safetensors
05/30/2026 09:25:01 - INFO - accelerate.checkpointing - [RANK 0] Optimizer state saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1750/optimizer.bin
05/30/2026 09:25:01 - INFO - accelerate.checkpointing - [RANK 0] Scheduler state saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1750/scheduler.bin
05/30/2026 09:25:01 - INFO - accelerate.checkpointing - [RANK 0] Sampler state for dataloader 0 saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1750/sampler.bin
05/30/2026 09:25:01 - INFO - accelerate.checkpointing - [RANK 0] Random states saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1750/random_states_0.pkl
05/30/2026 09:25:01 - INFO - __main__ - [RANK 0] Saved state to /workspace/output/flux-dev-apple-emoji-lora/checkpoint-1750

Steps:  88%|████████▊ | 1750/2000 [52:36<07:21,  1.76s/it, loss=0.216, lr=0.0001]
Steps:  88%|████████▊ | 1750/2000 [52:37<07:21,  1.76s/it, loss=0.0615, lr=0.0001]
Steps:  88%|████████▊ | 1750/2000 [52:37<07:21,  1.76s/it, loss=0.147, lr=0.0001] 
Steps:  88%|████████▊ | 1750/2000 [52:38<07:21,  1.76s/it, loss=0.101, lr=0.0001]
Steps:  88%|████████▊ | 1751/2000 [52:38<08:04,  1.95s/it, loss=0.101, lr=0.0001]
Steps:  88%|████████▊ | 1751/2000 [52:38<08:04,  1.95s/it, loss=0.274, lr=0.0001]
Steps:  88%|████████▊ | 1751/2000 [52:38<08:04,  1.95s/it, loss=0.159, lr=0.0001]
Steps:  88%|████████▊ | 1751/2000 [52:39<08:04,  1.95s/it, loss=0.452, lr=0.0001]
Steps:  88%|████████▊ | 1751/2000 [52:39<08:04,  1.95s/it, loss=0.148, lr=0.0001]
Steps:  88%|████████▊ | 1752/2000 [52:40<07:58,  1.93s/it, loss=0.148, lr=0.0001]
Steps:  88%|████████▊ | 1752/2000 [52:40<07:58,  1.93s/it, loss=0.144, lr=0.0001]
Steps:  88%|████████▊ | 1752/2000 [52:40<07:58,  1.93s/it, loss=0.166, lr=0.0001]
Steps:  88%|████████▊ | 1752/2000 [52:41<07:58,  1.93s/it, loss=0.206, lr=0.0001]
Steps:  88%|████████▊ | 1752/2000 [52:41<07:58,  1.93s/it, loss=0.224, lr=0.0001]
Steps:  88%|████████▊ | 1753/2000 [52:42<07:36,  1.85s/it, loss=0.224, lr=0.0001]
Steps:  88%|████████▊ | 1753/2000 [52:42<07:36,  1.85s/it, loss=0.19, lr=0.0001] 
Steps:  88%|████████▊ | 1753/2000 [52:42<07:36,  1.85s/it, loss=0.195, lr=0.0001]
Steps:  88%|████████▊ | 1753/2000 [52:42<07:36,  1.85s/it, loss=0.137, lr=0.0001]
Steps:  88%|████████▊ | 1753/2000 [52:43<07:36,  1.85s/it, loss=0.274, lr=0.0001]
Steps:  88%|████████▊ | 1754/2000 [52:43<07:20,  1.79s/it, loss=0.274, lr=0.0001]
Steps:  88%|████████▊ | 1754/2000 [52:43<07:20,  1.79s/it, loss=0.412, lr=0.0001]
Steps:  88%|████████▊ | 1754/2000 [52:44<07:20,  1.79s/it, loss=0.139, lr=0.0001]
Steps:  88%|████████▊ | 1754/2000 [52:44<07:20,  1.79s/it, loss=0.14, lr=0.0001] 
Steps:  88%|████████▊ | 1754/2000 [52:45<07:20,  1.79s/it, loss=0.132, lr=0.0001]
Steps:  88%|████████▊ | 1755/2000 [52:45<07:13,  1.77s/it, loss=0.132, lr=0.0001]
Steps:  88%|████████▊ | 1755/2000 [52:45<07:13,  1.77s/it, loss=0.0961, lr=0.0001]
Steps:  88%|████████▊ | 1755/2000 [52:46<07:13,  1.77s/it, loss=0.222, lr=0.0001] 
Steps:  88%|████████▊ | 1755/2000 [52:46<07:13,  1.77s/it, loss=0.182, lr=0.0001]
Steps:  88%|████████▊ | 1755/2000 [52:46<07:13,  1.77s/it, loss=0.877, lr=0.0001]
Steps:  88%|████████▊ | 1756/2000 [52:47<07:21,  1.81s/it, loss=0.877, lr=0.0001]
Steps:  88%|████████▊ | 1756/2000 [52:47<07:21,  1.81s/it, loss=0.149, lr=0.0001]
Steps:  88%|████████▊ | 1756/2000 [52:47<07:21,  1.81s/it, loss=0.104, lr=0.0001]
Steps:  88%|████████▊ | 1756/2000 [52:48<07:21,  1.81s/it, loss=0.345, lr=0.0001]
Steps:  88%|████████▊ | 1756/2000 [52:48<07:21,  1.81s/it, loss=0.202, lr=0.0001]
Steps:  88%|████████▊ | 1757/2000 [52:49<07:10,  1.77s/it, loss=0.202, lr=0.0001]
Steps:  88%|████████▊ | 1757/2000 [52:49<07:10,  1.77s/it, loss=0.206, lr=0.0001]
Steps:  88%|████████▊ | 1757/2000 [52:49<07:10,  1.77s/it, loss=0.264, lr=0.0001]
Steps:  88%|████████▊ | 1757/2000 [52:49<07:10,  1.77s/it, loss=0.221, lr=0.0001]
Steps:  88%|████████▊ | 1757/2000 [52:50<07:10,  1.77s/it, loss=0.259, lr=0.0001]
Steps:  88%|████████▊ | 1758/2000 [52:50<07:00,  1.74s/it, loss=0.259, lr=0.0001]
Steps:  88%|████████▊ | 1758/2000 [52:50<07:00,  1.74s/it, loss=0.161, lr=0.0001]
Steps:  88%|████████▊ | 1758/2000 [52:51<07:00,  1.74s/it, loss=0.187, lr=0.0001]
Steps:  88%|████████▊ | 1758/2000 [52:51<07:00,  1.74s/it, loss=0.12, lr=0.0001] 
Steps:  88%|████████▊ | 1758/2000 [52:52<07:00,  1.74s/it, loss=0.218, lr=0.0001]
Steps:  88%|████████▊ | 1759/2000 [52:52<07:09,  1.78s/it, loss=0.218, lr=0.0001]
Steps:  88%|████████▊ | 1759/2000 [52:52<07:09,  1.78s/it, loss=0.236, lr=0.0001]
Steps:  88%|████████▊ | 1759/2000 [52:53<07:09,  1.78s/it, loss=0.176, lr=0.0001]
Steps:  88%|████████▊ | 1759/2000 [52:53<07:09,  1.78s/it, loss=0.148, lr=0.0001]
Steps:  88%|████████▊ | 1759/2000 [52:53<07:09,  1.78s/it, loss=0.317, lr=0.0001]
Steps:  88%|████████▊ | 1760/2000 [52:54<06:58,  1.74s/it, loss=0.317, lr=0.0001]
Steps:  88%|████████▊ | 1760/2000 [52:54<06:58,  1.74s/it, loss=0.27, lr=0.0001] 
Steps:  88%|████████▊ | 1760/2000 [52:54<06:58,  1.74s/it, loss=0.155, lr=0.0001]
Steps:  88%|████████▊ | 1760/2000 [52:55<06:58,  1.74s/it, loss=0.213, lr=0.0001]
Steps:  88%|████████▊ | 1760/2000 [52:55<06:58,  1.74s/it, loss=0.13, lr=0.0001] 
Steps:  88%|████████▊ | 1761/2000 [52:55<06:51,  1.72s/it, loss=0.13, lr=0.0001]
Steps:  88%|████████▊ | 1761/2000 [52:55<06:51,  1.72s/it, loss=0.158, lr=0.0001]
Steps:  88%|████████▊ | 1761/2000 [52:56<06:51,  1.72s/it, loss=0.217, lr=0.0001]
Steps:  88%|████████▊ | 1761/2000 [52:56<06:51,  1.72s/it, loss=0.214, lr=0.0001]
Steps:  88%|████████▊ | 1761/2000 [52:57<06:51,  1.72s/it, loss=0.135, lr=0.0001]
Steps:  88%|████████▊ | 1762/2000 [52:57<07:00,  1.77s/it, loss=0.135, lr=0.0001]
Steps:  88%|████████▊ | 1762/2000 [52:57<07:00,  1.77s/it, loss=0.882, lr=0.0001]
Steps:  88%|████████▊ | 1762/2000 [52:58<07:00,  1.77s/it, loss=0.202, lr=0.0001]
Steps:  88%|████████▊ | 1762/2000 [52:58<07:00,  1.77s/it, loss=0.159, lr=0.0001]
Steps:  88%|████████▊ | 1762/2000 [52:59<07:00,  1.77s/it, loss=0.222, lr=0.0001]
Steps:  88%|████████▊ | 1763/2000 [52:59<06:51,  1.73s/it, loss=0.222, lr=0.0001]
Steps:  88%|████████▊ | 1763/2000 [52:59<06:51,  1.73s/it, loss=0.474, lr=0.0001]
Steps:  88%|████████▊ | 1763/2000 [52:59<06:51,  1.73s/it, loss=0.542, lr=0.0001]
Steps:  88%|████████▊ | 1763/2000 [53:00<06:51,  1.73s/it, loss=0.167, lr=0.0001]
Steps:  88%|████████▊ | 1763/2000 [53:00<06:51,  1.73s/it, loss=0.17, lr=0.0001] 
Steps:  88%|████████▊ | 1764/2000 [53:01<06:43,  1.71s/it, loss=0.17, lr=0.0001]
Steps:  88%|████████▊ | 1764/2000 [53:01<06:43,  1.71s/it, loss=0.219, lr=0.0001]
Steps:  88%|████████▊ | 1764/2000 [53:01<06:43,  1.71s/it, loss=0.274, lr=0.0001]
Steps:  88%|████████▊ | 1764/2000 [53:01<06:43,  1.71s/it, loss=0.132, lr=0.0001]
Steps:  88%|████████▊ | 1764/2000 [53:02<06:43,  1.71s/it, loss=0.14, lr=0.0001] 
Steps:  88%|████████▊ | 1765/2000 [53:03<06:53,  1.76s/it, loss=0.14, lr=0.0001]
Steps:  88%|████████▊ | 1765/2000 [53:03<06:53,  1.76s/it, loss=0.151, lr=0.0001]
Steps:  88%|████████▊ | 1765/2000 [53:03<06:53,  1.76s/it, loss=0.167, lr=0.0001]
Steps:  88%|████████▊ | 1765/2000 [53:03<06:53,  1.76s/it, loss=0.18, lr=0.0001] 
Steps:  88%|████████▊ | 1765/2000 [53:04<06:53,  1.76s/it, loss=0.51, lr=0.0001]
Steps:  88%|████████▊ | 1766/2000 [53:04<06:44,  1.73s/it, loss=0.51, lr=0.0001]
Steps:  88%|████████▊ | 1766/2000 [53:04<06:44,  1.73s/it, loss=0.229, lr=0.0001]
Steps:  88%|████████▊ | 1766/2000 [53:05<06:44,  1.73s/it, loss=0.258, lr=0.0001]
Steps:  88%|████████▊ | 1766/2000 [53:05<06:44,  1.73s/it, loss=0.16, lr=0.0001] 
Steps:  88%|████████▊ | 1766/2000 [53:06<06:44,  1.73s/it, loss=0.183, lr=0.0001]
Steps:  88%|████████▊ | 1767/2000 [53:06<06:46,  1.75s/it, loss=0.183, lr=0.0001]
Steps:  88%|████████▊ | 1767/2000 [53:06<06:46,  1.75s/it, loss=0.145, lr=0.0001]
Steps:  88%|████████▊ | 1767/2000 [53:06<06:46,  1.75s/it, loss=0.43, lr=0.0001] 
Steps:  88%|████████▊ | 1767/2000 [53:07<06:46,  1.75s/it, loss=0.108, lr=0.0001]
Steps:  88%|████████▊ | 1767/2000 [53:07<06:46,  1.75s/it, loss=0.123, lr=0.0001]
Steps:  88%|████████▊ | 1768/2000 [53:08<06:54,  1.79s/it, loss=0.123, lr=0.0001]
Steps:  88%|████████▊ | 1768/2000 [53:08<06:54,  1.79s/it, loss=0.446, lr=0.0001]
Steps:  88%|████████▊ | 1768/2000 [53:08<06:54,  1.79s/it, loss=0.574, lr=0.0001]
Steps:  88%|████████▊ | 1768/2000 [53:09<06:54,  1.79s/it, loss=0.168, lr=0.0001]
Steps:  88%|████████▊ | 1768/2000 [53:09<06:54,  1.79s/it, loss=0.116, lr=0.0001]
Steps:  88%|████████▊ | 1769/2000 [53:09<06:43,  1.75s/it, loss=0.116, lr=0.0001]
Steps:  88%|████████▊ | 1769/2000 [53:09<06:43,  1.75s/it, loss=0.173, lr=0.0001]
Steps:  88%|████████▊ | 1769/2000 [53:10<06:43,  1.75s/it, loss=0.317, lr=0.0001]
Steps:  88%|████████▊ | 1769/2000 [53:10<06:43,  1.75s/it, loss=0.193, lr=0.0001]
Steps:  88%|████████▊ | 1769/2000 [53:11<06:43,  1.75s/it, loss=0.12, lr=0.0001] 
Steps:  88%|████████▊ | 1770/2000 [53:11<06:35,  1.72s/it, loss=0.12, lr=0.0001]
Steps:  88%|████████▊ | 1770/2000 [53:11<06:35,  1.72s/it, loss=0.139, lr=0.0001]
Steps:  88%|████████▊ | 1770/2000 [53:12<06:35,  1.72s/it, loss=0.208, lr=0.0001]
Steps:  88%|████████▊ | 1770/2000 [53:12<06:35,  1.72s/it, loss=0.277, lr=0.0001]
Steps:  88%|████████▊ | 1770/2000 [53:12<06:35,  1.72s/it, loss=0.212, lr=0.0001]
Steps:  89%|████████▊ | 1771/2000 [53:13<06:29,  1.70s/it, loss=0.212, lr=0.0001]
Steps:  89%|████████▊ | 1771/2000 [53:13<06:29,  1.70s/it, loss=0.213, lr=0.0001]
Steps:  89%|████████▊ | 1771/2000 [53:13<06:29,  1.70s/it, loss=0.161, lr=0.0001]
Steps:  89%|████████▊ | 1771/2000 [53:14<06:29,  1.70s/it, loss=0.213, lr=0.0001]
Steps:  89%|████████▊ | 1771/2000 [53:14<06:29,  1.70s/it, loss=0.233, lr=0.0001]
Steps:  89%|████████▊ | 1772/2000 [53:15<06:41,  1.76s/it, loss=0.233, lr=0.0001]
Steps:  89%|████████▊ | 1772/2000 [53:15<06:41,  1.76s/it, loss=0.226, lr=0.0001]
Steps:  89%|████████▊ | 1772/2000 [53:15<06:41,  1.76s/it, loss=0.14, lr=0.0001] 
Steps:  89%|████████▊ | 1772/2000 [53:15<06:41,  1.76s/it, loss=0.134, lr=0.0001]
Steps:  89%|████████▊ | 1772/2000 [53:16<06:41,  1.76s/it, loss=0.172, lr=0.0001]
Steps:  89%|████████▊ | 1773/2000 [53:16<06:32,  1.73s/it, loss=0.172, lr=0.0001]
Steps:  89%|████████▊ | 1773/2000 [53:16<06:32,  1.73s/it, loss=0.0751, lr=0.0001]
Steps:  89%|████████▊ | 1773/2000 [53:17<06:32,  1.73s/it, loss=0.105, lr=0.0001] 
Steps:  89%|████████▊ | 1773/2000 [53:17<06:32,  1.73s/it, loss=0.191, lr=0.0001]
Steps:  89%|████████▊ | 1773/2000 [53:18<06:32,  1.73s/it, loss=0.16, lr=0.0001] 
Steps:  89%|████████▊ | 1774/2000 [53:18<06:27,  1.72s/it, loss=0.16, lr=0.0001]
Steps:  89%|████████▊ | 1774/2000 [53:18<06:27,  1.72s/it, loss=0.115, lr=0.0001]
Steps:  89%|████████▊ | 1774/2000 [53:18<06:27,  1.72s/it, loss=0.0843, lr=0.0001]
Steps:  89%|████████▊ | 1774/2000 [53:19<06:27,  1.72s/it, loss=0.0446, lr=0.0001]
Steps:  89%|████████▊ | 1774/2000 [53:19<06:27,  1.72s/it, loss=0.177, lr=0.0001] 
Steps:  89%|████████▉ | 1775/2000 [53:20<06:36,  1.76s/it, loss=0.177, lr=0.0001]
Steps:  89%|████████▉ | 1775/2000 [53:20<06:36,  1.76s/it, loss=0.365, lr=0.0001]
Steps:  89%|████████▉ | 1775/2000 [53:20<06:36,  1.76s/it, loss=0.219, lr=0.0001]
Steps:  89%|████████▉ | 1775/2000 [53:21<06:36,  1.76s/it, loss=0.141, lr=0.0001]
Steps:  89%|████████▉ | 1775/2000 [53:21<06:36,  1.76s/it, loss=0.223, lr=0.0001]
Steps:  89%|████████▉ | 1776/2000 [53:22<06:27,  1.73s/it, loss=0.223, lr=0.0001]
Steps:  89%|████████▉ | 1776/2000 [53:22<06:27,  1.73s/it, loss=0.979, lr=0.0001]
Steps:  89%|████████▉ | 1776/2000 [53:22<06:27,  1.73s/it, loss=0.211, lr=0.0001]
Steps:  89%|████████▉ | 1776/2000 [53:22<06:27,  1.73s/it, loss=0.147, lr=0.0001]
Steps:  89%|████████▉ | 1776/2000 [53:23<06:27,  1.73s/it, loss=0.113, lr=0.0001]
Steps:  89%|████████▉ | 1777/2000 [53:23<06:21,  1.71s/it, loss=0.113, lr=0.0001]
Steps:  89%|████████▉ | 1777/2000 [53:23<06:21,  1.71s/it, loss=0.211, lr=0.0001]
Steps:  89%|████████▉ | 1777/2000 [53:24<06:21,  1.71s/it, loss=0.195, lr=0.0001]
Steps:  89%|████████▉ | 1777/2000 [53:24<06:21,  1.71s/it, loss=0.263, lr=0.0001]
Steps:  89%|████████▉ | 1777/2000 [53:25<06:21,  1.71s/it, loss=0.21, lr=0.0001] 
Steps:  89%|████████▉ | 1778/2000 [53:25<06:31,  1.76s/it, loss=0.21, lr=0.0001]
Steps:  89%|████████▉ | 1778/2000 [53:25<06:31,  1.76s/it, loss=0.121, lr=0.0001]
Steps:  89%|████████▉ | 1778/2000 [53:26<06:31,  1.76s/it, loss=0.143, lr=0.0001]
Steps:  89%|████████▉ | 1778/2000 [53:26<06:31,  1.76s/it, loss=0.174, lr=0.0001]
Steps:  89%|████████▉ | 1778/2000 [53:26<06:31,  1.76s/it, loss=0.575, lr=0.0001]
Steps:  89%|████████▉ | 1779/2000 [53:27<06:28,  1.76s/it, loss=0.575, lr=0.0001]
Steps:  89%|████████▉ | 1779/2000 [53:27<06:28,  1.76s/it, loss=0.177, lr=0.0001]
Steps:  89%|████████▉ | 1779/2000 [53:27<06:28,  1.76s/it, loss=0.16, lr=0.0001] 
Steps:  89%|████████▉ | 1779/2000 [53:28<06:28,  1.76s/it, loss=0.189, lr=0.0001]
Steps:  89%|████████▉ | 1779/2000 [53:28<06:28,  1.76s/it, loss=1.24, lr=0.0001] 
Steps:  89%|████████▉ | 1780/2000 [53:29<06:21,  1.73s/it, loss=1.24, lr=0.0001]
Steps:  89%|████████▉ | 1780/2000 [53:29<06:21,  1.73s/it, loss=0.11, lr=0.0001]
Steps:  89%|████████▉ | 1780/2000 [53:29<06:21,  1.73s/it, loss=0.194, lr=0.0001]
Steps:  89%|████████▉ | 1780/2000 [53:29<06:21,  1.73s/it, loss=0.157, lr=0.0001]
Steps:  89%|████████▉ | 1780/2000 [53:30<06:21,  1.73s/it, loss=0.153, lr=0.0001]
Steps:  89%|████████▉ | 1781/2000 [53:30<06:32,  1.79s/it, loss=0.153, lr=0.0001]
Steps:  89%|████████▉ | 1781/2000 [53:30<06:32,  1.79s/it, loss=0.123, lr=0.0001]
Steps:  89%|████████▉ | 1781/2000 [53:31<06:32,  1.79s/it, loss=0.131, lr=0.0001]
Steps:  89%|████████▉ | 1781/2000 [53:31<06:32,  1.79s/it, loss=0.135, lr=0.0001]
Steps:  89%|████████▉ | 1781/2000 [53:32<06:32,  1.79s/it, loss=0.187, lr=0.0001]
Steps:  89%|████████▉ | 1782/2000 [53:32<06:21,  1.75s/it, loss=0.187, lr=0.0001]
Steps:  89%|████████▉ | 1782/2000 [53:32<06:21,  1.75s/it, loss=0.118, lr=0.0001]
Steps:  89%|████████▉ | 1782/2000 [53:33<06:21,  1.75s/it, loss=0.223, lr=0.0001]
Steps:  89%|████████▉ | 1782/2000 [53:33<06:21,  1.75s/it, loss=0.151, lr=0.0001]
Steps:  89%|████████▉ | 1782/2000 [53:33<06:21,  1.75s/it, loss=0.0823, lr=0.0001]
Steps:  89%|████████▉ | 1783/2000 [53:34<06:14,  1.72s/it, loss=0.0823, lr=0.0001]
Steps:  89%|████████▉ | 1783/2000 [53:34<06:14,  1.72s/it, loss=0.186, lr=0.0001] 
Steps:  89%|████████▉ | 1783/2000 [53:34<06:14,  1.72s/it, loss=0.0829, lr=0.0001]
Steps:  89%|████████▉ | 1783/2000 [53:35<06:14,  1.72s/it, loss=0.302, lr=0.0001] 
Steps:  89%|████████▉ | 1783/2000 [53:35<06:14,  1.72s/it, loss=0.316, lr=0.0001]
Steps:  89%|████████▉ | 1784/2000 [53:36<06:24,  1.78s/it, loss=0.316, lr=0.0001]
Steps:  89%|████████▉ | 1784/2000 [53:36<06:24,  1.78s/it, loss=0.0761, lr=0.0001]
Steps:  89%|████████▉ | 1784/2000 [53:36<06:24,  1.78s/it, loss=0.0948, lr=0.0001]
Steps:  89%|████████▉ | 1784/2000 [53:37<06:24,  1.78s/it, loss=0.131, lr=0.0001] 
Steps:  89%|████████▉ | 1784/2000 [53:37<06:24,  1.78s/it, loss=0.141, lr=0.0001]
Steps:  89%|████████▉ | 1785/2000 [53:37<06:17,  1.76s/it, loss=0.141, lr=0.0001]
Steps:  89%|████████▉ | 1785/2000 [53:37<06:17,  1.76s/it, loss=0.242, lr=0.0001]
Steps:  89%|████████▉ | 1785/2000 [53:38<06:17,  1.76s/it, loss=0.166, lr=0.0001]
Steps:  89%|████████▉ | 1785/2000 [53:38<06:17,  1.76s/it, loss=0.133, lr=0.0001]
Steps:  89%|████████▉ | 1785/2000 [53:39<06:17,  1.76s/it, loss=0.176, lr=0.0001]
Steps:  89%|████████▉ | 1786/2000 [53:39<06:10,  1.73s/it, loss=0.176, lr=0.0001]
Steps:  89%|████████▉ | 1786/2000 [53:39<06:10,  1.73s/it, loss=0.175, lr=0.0001]
Steps:  89%|████████▉ | 1786/2000 [53:39<06:10,  1.73s/it, loss=0.304, lr=0.0001]
Steps:  89%|████████▉ | 1786/2000 [53:40<06:10,  1.73s/it, loss=0.13, lr=0.0001] 
Steps:  89%|████████▉ | 1786/2000 [53:40<06:10,  1.73s/it, loss=0.212, lr=0.0001]
Steps:  89%|████████▉ | 1787/2000 [53:41<06:19,  1.78s/it, loss=0.212, lr=0.0001]
Steps:  89%|████████▉ | 1787/2000 [53:41<06:19,  1.78s/it, loss=0.186, lr=0.0001]
Steps:  89%|████████▉ | 1787/2000 [53:41<06:19,  1.78s/it, loss=0.236, lr=0.0001]
Steps:  89%|████████▉ | 1787/2000 [53:42<06:19,  1.78s/it, loss=0.931, lr=0.0001]
Steps:  89%|████████▉ | 1787/2000 [53:42<06:19,  1.78s/it, loss=0.118, lr=0.0001]
Steps:  89%|████████▉ | 1788/2000 [53:43<06:10,  1.75s/it, loss=0.118, lr=0.0001]
Steps:  89%|████████▉ | 1788/2000 [53:43<06:10,  1.75s/it, loss=0.207, lr=0.0001]
Steps:  89%|████████▉ | 1788/2000 [53:43<06:10,  1.75s/it, loss=0.596, lr=0.0001]
Steps:  89%|████████▉ | 1788/2000 [53:43<06:10,  1.75s/it, loss=0.156, lr=0.0001]
Steps:  89%|████████▉ | 1788/2000 [53:44<06:10,  1.75s/it, loss=0.123, lr=0.0001]
Steps:  89%|████████▉ | 1789/2000 [53:44<06:04,  1.73s/it, loss=0.123, lr=0.0001]
Steps:  89%|████████▉ | 1789/2000 [53:44<06:04,  1.73s/it, loss=0.168, lr=0.0001]
Steps:  89%|████████▉ | 1789/2000 [53:45<06:04,  1.73s/it, loss=0.213, lr=0.0001]
Steps:  89%|████████▉ | 1789/2000 [53:45<06:04,  1.73s/it, loss=0.253, lr=0.0001]
Steps:  89%|████████▉ | 1789/2000 [53:46<06:04,  1.73s/it, loss=0.0741, lr=0.0001]
Steps:  90%|████████▉ | 1790/2000 [53:46<05:59,  1.71s/it, loss=0.0741, lr=0.0001]
Steps:  90%|████████▉ | 1790/2000 [53:46<05:59,  1.71s/it, loss=0.215, lr=0.0001] 
Steps:  90%|████████▉ | 1790/2000 [53:47<05:59,  1.71s/it, loss=0.207, lr=0.0001]
Steps:  90%|████████▉ | 1790/2000 [53:47<05:59,  1.71s/it, loss=0.188, lr=0.0001]
Steps:  90%|████████▉ | 1790/2000 [53:47<05:59,  1.71s/it, loss=0.216, lr=0.0001]
Steps:  90%|████████▉ | 1791/2000 [53:48<06:10,  1.77s/it, loss=0.216, lr=0.0001]
Steps:  90%|████████▉ | 1791/2000 [53:48<06:10,  1.77s/it, loss=0.542, lr=0.0001]
Steps:  90%|████████▉ | 1791/2000 [53:48<06:10,  1.77s/it, loss=0.174, lr=0.0001]
Steps:  90%|████████▉ | 1791/2000 [53:49<06:10,  1.77s/it, loss=0.442, lr=0.0001]
Steps:  90%|████████▉ | 1791/2000 [53:49<06:10,  1.77s/it, loss=0.171, lr=0.0001]
Steps:  90%|████████▉ | 1792/2000 [53:50<06:01,  1.74s/it, loss=0.171, lr=0.0001]
Steps:  90%|████████▉ | 1792/2000 [53:50<06:01,  1.74s/it, loss=0.132, lr=0.0001]
Steps:  90%|████████▉ | 1792/2000 [53:50<06:01,  1.74s/it, loss=0.16, lr=0.0001] 
Steps:  90%|████████▉ | 1792/2000 [53:50<06:01,  1.74s/it, loss=0.087, lr=0.0001]
Steps:  90%|████████▉ | 1792/2000 [53:51<06:01,  1.74s/it, loss=0.127, lr=0.0001]
Steps:  90%|████████▉ | 1793/2000 [53:51<05:55,  1.72s/it, loss=0.127, lr=0.0001]
Steps:  90%|████████▉ | 1793/2000 [53:51<05:55,  1.72s/it, loss=0.154, lr=0.0001]
Steps:  90%|████████▉ | 1793/2000 [53:52<05:55,  1.72s/it, loss=0.243, lr=0.0001]
Steps:  90%|████████▉ | 1793/2000 [53:52<05:55,  1.72s/it, loss=0.114, lr=0.0001]
Steps:  90%|████████▉ | 1793/2000 [53:53<05:55,  1.72s/it, loss=0.162, lr=0.0001]
Steps:  90%|████████▉ | 1794/2000 [53:53<06:06,  1.78s/it, loss=0.162, lr=0.0001]
Steps:  90%|████████▉ | 1794/2000 [53:53<06:06,  1.78s/it, loss=0.11, lr=0.0001] 
Steps:  90%|████████▉ | 1794/2000 [53:54<06:06,  1.78s/it, loss=0.287, lr=0.0001]
Steps:  90%|████████▉ | 1794/2000 [53:54<06:06,  1.78s/it, loss=0.165, lr=0.0001]
Steps:  90%|████████▉ | 1794/2000 [53:54<06:06,  1.78s/it, loss=0.119, lr=0.0001]
Steps:  90%|████████▉ | 1795/2000 [53:55<05:58,  1.75s/it, loss=0.119, lr=0.0001]
Steps:  90%|████████▉ | 1795/2000 [53:55<05:58,  1.75s/it, loss=0.122, lr=0.0001]
Steps:  90%|████████▉ | 1795/2000 [53:55<05:58,  1.75s/it, loss=0.0781, lr=0.0001]
Steps:  90%|████████▉ | 1795/2000 [53:56<05:58,  1.75s/it, loss=0.321, lr=0.0001] 
Steps:  90%|████████▉ | 1795/2000 [53:56<05:58,  1.75s/it, loss=0.249, lr=0.0001]
Steps:  90%|████████▉ | 1796/2000 [53:56<05:52,  1.73s/it, loss=0.249, lr=0.0001]
Steps:  90%|████████▉ | 1796/2000 [53:56<05:52,  1.73s/it, loss=0.767, lr=0.0001]
Steps:  90%|████████▉ | 1796/2000 [53:57<05:52,  1.73s/it, loss=0.208, lr=0.0001]
Steps:  90%|████████▉ | 1796/2000 [53:58<05:52,  1.73s/it, loss=0.214, lr=0.0001]
Steps:  90%|████████▉ | 1796/2000 [53:58<05:52,  1.73s/it, loss=0.0717, lr=0.0001]
Steps:  90%|████████▉ | 1797/2000 [53:58<06:07,  1.81s/it, loss=0.0717, lr=0.0001]
Steps:  90%|████████▉ | 1797/2000 [53:58<06:07,  1.81s/it, loss=0.661, lr=0.0001] 
Steps:  90%|████████▉ | 1797/2000 [53:59<06:07,  1.81s/it, loss=0.108, lr=0.0001]
Steps:  90%|████████▉ | 1797/2000 [53:59<06:07,  1.81s/it, loss=0.154, lr=0.0001]
Steps:  90%|████████▉ | 1797/2000 [54:00<06:07,  1.81s/it, loss=1.31, lr=0.0001] 
Steps:  90%|████████▉ | 1798/2000 [54:00<05:56,  1.76s/it, loss=1.31, lr=0.0001]
Steps:  90%|████████▉ | 1798/2000 [54:00<05:56,  1.76s/it, loss=0.0392, lr=0.0001]
Steps:  90%|████████▉ | 1798/2000 [54:01<05:56,  1.76s/it, loss=0.212, lr=0.0001] 
Steps:  90%|████████▉ | 1798/2000 [54:01<05:56,  1.76s/it, loss=0.0695, lr=0.0001]
Steps:  90%|████████▉ | 1798/2000 [54:01<05:56,  1.76s/it, loss=0.122, lr=0.0001] 
Steps:  90%|████████▉ | 1799/2000 [54:02<05:48,  1.74s/it, loss=0.122, lr=0.0001]
Steps:  90%|████████▉ | 1799/2000 [54:02<05:48,  1.74s/it, loss=0.147, lr=0.0001]
Steps:  90%|████████▉ | 1799/2000 [54:02<05:48,  1.74s/it, loss=0.198, lr=0.0001]
Steps:  90%|████████▉ | 1799/2000 [54:03<05:48,  1.74s/it, loss=0.109, lr=0.0001]
Steps:  90%|████████▉ | 1799/2000 [54:03<05:48,  1.74s/it, loss=0.237, lr=0.0001]
Steps:  90%|█████████ | 1800/2000 [54:04<05:56,  1.78s/it, loss=0.237, lr=0.0001]
Steps:  90%|█████████ | 1800/2000 [54:04<05:56,  1.78s/it, loss=0.143, lr=0.0001]
Steps:  90%|█████████ | 1800/2000 [54:04<05:56,  1.78s/it, loss=0.174, lr=0.0001]
Steps:  90%|█████████ | 1800/2000 [54:05<05:56,  1.78s/it, loss=0.153, lr=0.0001]
Steps:  90%|█████████ | 1800/2000 [54:05<05:56,  1.78s/it, loss=0.0791, lr=0.0001]
Steps:  90%|█████████ | 1801/2000 [54:05<05:48,  1.75s/it, loss=0.0791, lr=0.0001]
Steps:  90%|█████████ | 1801/2000 [54:05<05:48,  1.75s/it, loss=0.168, lr=0.0001] 
Steps:  90%|█████████ | 1801/2000 [54:06<05:48,  1.75s/it, loss=0.196, lr=0.0001]
Steps:  90%|█████████ | 1801/2000 [54:06<05:48,  1.75s/it, loss=0.119, lr=0.0001]
Steps:  90%|█████████ | 1801/2000 [54:07<05:48,  1.75s/it, loss=0.239, lr=0.0001]
Steps:  90%|█████████ | 1802/2000 [54:07<05:41,  1.72s/it, loss=0.239, lr=0.0001]
Steps:  90%|█████████ | 1802/2000 [54:07<05:41,  1.72s/it, loss=0.159, lr=0.0001]
Steps:  90%|█████████ | 1802/2000 [54:07<05:41,  1.72s/it, loss=0.13, lr=0.0001] 
Steps:  90%|█████████ | 1802/2000 [54:08<05:41,  1.72s/it, loss=0.288, lr=0.0001]
Steps:  90%|█████████ | 1802/2000 [54:08<05:41,  1.72s/it, loss=0.0575, lr=0.0001]
Steps:  90%|█████████ | 1803/2000 [54:09<05:49,  1.77s/it, loss=0.0575, lr=0.0001]
Steps:  90%|█████████ | 1803/2000 [54:09<05:49,  1.77s/it, loss=0.11, lr=0.0001]  
Steps:  90%|█████████ | 1803/2000 [54:09<05:49,  1.77s/it, loss=0.175, lr=0.0001]
Steps:  90%|█████████ | 1803/2000 [54:10<05:49,  1.77s/it, loss=0.0829, lr=0.0001]
Steps:  90%|█████████ | 1803/2000 [54:10<05:49,  1.77s/it, loss=0.147, lr=0.0001] 
Steps:  90%|█████████ | 1804/2000 [54:11<05:40,  1.74s/it, loss=0.147, lr=0.0001]
Steps:  90%|█████████ | 1804/2000 [54:11<05:40,  1.74s/it, loss=0.143, lr=0.0001]
Steps:  90%|█████████ | 1804/2000 [54:11<05:40,  1.74s/it, loss=0.422, lr=0.0001]
Steps:  90%|█████████ | 1804/2000 [54:11<05:40,  1.74s/it, loss=0.187, lr=0.0001]
Steps:  90%|█████████ | 1804/2000 [54:12<05:40,  1.74s/it, loss=0.127, lr=0.0001]
Steps:  90%|█████████ | 1805/2000 [54:12<05:34,  1.72s/it, loss=0.127, lr=0.0001]
Steps:  90%|█████████ | 1805/2000 [54:12<05:34,  1.72s/it, loss=0.181, lr=0.0001]
Steps:  90%|█████████ | 1805/2000 [54:13<05:34,  1.72s/it, loss=0.385, lr=0.0001]
Steps:  90%|█████████ | 1805/2000 [54:13<05:34,  1.72s/it, loss=0.194, lr=0.0001]
Steps:  90%|█████████ | 1805/2000 [54:13<05:34,  1.72s/it, loss=0.141, lr=0.0001]
Steps:  90%|█████████ | 1806/2000 [54:14<05:43,  1.77s/it, loss=0.141, lr=0.0001]
Steps:  90%|█████████ | 1806/2000 [54:14<05:43,  1.77s/it, loss=0.15, lr=0.0001] 
Steps:  90%|█████████ | 1806/2000 [54:15<05:43,  1.77s/it, loss=0.107, lr=0.0001]
Steps:  90%|█████████ | 1806/2000 [54:15<05:43,  1.77s/it, loss=0.181, lr=0.0001]
Steps:  90%|█████████ | 1806/2000 [54:15<05:43,  1.77s/it, loss=0.296, lr=0.0001]
Steps:  90%|█████████ | 1807/2000 [54:16<05:36,  1.74s/it, loss=0.296, lr=0.0001]
Steps:  90%|█████████ | 1807/2000 [54:16<05:36,  1.74s/it, loss=0.256, lr=0.0001]
Steps:  90%|█████████ | 1807/2000 [54:16<05:36,  1.74s/it, loss=0.572, lr=0.0001]
Steps:  90%|█████████ | 1807/2000 [54:17<05:36,  1.74s/it, loss=0.318, lr=0.0001]
Steps:  90%|█████████ | 1807/2000 [54:17<05:36,  1.74s/it, loss=0.146, lr=0.0001]
Steps:  90%|█████████ | 1808/2000 [54:18<05:32,  1.73s/it, loss=0.146, lr=0.0001]
Steps:  90%|█████████ | 1808/2000 [54:18<05:32,  1.73s/it, loss=0.245, lr=0.0001]
Steps:  90%|█████████ | 1808/2000 [54:18<05:32,  1.73s/it, loss=0.103, lr=0.0001]
Steps:  90%|█████████ | 1808/2000 [54:18<05:32,  1.73s/it, loss=0.148, lr=0.0001]
Steps:  90%|█████████ | 1808/2000 [54:19<05:32,  1.73s/it, loss=0.141, lr=0.0001]
Steps:  90%|█████████ | 1809/2000 [54:19<05:29,  1.72s/it, loss=0.141, lr=0.0001]
Steps:  90%|█████████ | 1809/2000 [54:19<05:29,  1.72s/it, loss=0.148, lr=0.0001]
Steps:  90%|█████████ | 1809/2000 [54:20<05:29,  1.72s/it, loss=0.195, lr=0.0001]
Steps:  90%|█████████ | 1809/2000 [54:20<05:29,  1.72s/it, loss=0.138, lr=0.0001]
Steps:  90%|█████████ | 1809/2000 [54:21<05:29,  1.72s/it, loss=0.15, lr=0.0001] 
Steps:  90%|█████████ | 1810/2000 [54:21<05:36,  1.77s/it, loss=0.15, lr=0.0001]
Steps:  90%|█████████ | 1810/2000 [54:21<05:36,  1.77s/it, loss=0.362, lr=0.0001]
Steps:  90%|█████████ | 1810/2000 [54:22<05:36,  1.77s/it, loss=0.0821, lr=0.0001]
Steps:  90%|█████████ | 1810/2000 [54:22<05:36,  1.77s/it, loss=0.21, lr=0.0001]  
Steps:  90%|█████████ | 1810/2000 [54:22<05:36,  1.77s/it, loss=0.166, lr=0.0001]
Steps:  91%|█████████ | 1811/2000 [54:23<05:29,  1.75s/it, loss=0.166, lr=0.0001]
Steps:  91%|█████████ | 1811/2000 [54:23<05:29,  1.75s/it, loss=0.202, lr=0.0001]
Steps:  91%|█████████ | 1811/2000 [54:23<05:29,  1.75s/it, loss=0.328, lr=0.0001]
Steps:  91%|█████████ | 1811/2000 [54:24<05:29,  1.75s/it, loss=0.131, lr=0.0001]
Steps:  91%|█████████ | 1811/2000 [54:24<05:29,  1.75s/it, loss=0.234, lr=0.0001]
Steps:  91%|█████████ | 1812/2000 [54:24<05:23,  1.72s/it, loss=0.234, lr=0.0001]
Steps:  91%|█████████ | 1812/2000 [54:24<05:23,  1.72s/it, loss=0.216, lr=0.0001]
Steps:  91%|█████████ | 1812/2000 [54:25<05:23,  1.72s/it, loss=0.172, lr=0.0001]
Steps:  91%|█████████ | 1812/2000 [54:26<05:23,  1.72s/it, loss=0.0905, lr=0.0001]
Steps:  91%|█████████ | 1812/2000 [54:26<05:23,  1.72s/it, loss=0.199, lr=0.0001] 
Steps:  91%|█████████ | 1813/2000 [54:26<05:32,  1.78s/it, loss=0.199, lr=0.0001]
Steps:  91%|█████████ | 1813/2000 [54:26<05:32,  1.78s/it, loss=0.275, lr=0.0001]
Steps:  91%|█████████ | 1813/2000 [54:27<05:32,  1.78s/it, loss=0.242, lr=0.0001]
Steps:  91%|█████████ | 1813/2000 [54:27<05:32,  1.78s/it, loss=0.0933, lr=0.0001]
Steps:  91%|█████████ | 1813/2000 [54:28<05:32,  1.78s/it, loss=0.156, lr=0.0001] 
Steps:  91%|█████████ | 1814/2000 [54:28<05:24,  1.74s/it, loss=0.156, lr=0.0001]
Steps:  91%|█████████ | 1814/2000 [54:28<05:24,  1.74s/it, loss=0.161, lr=0.0001]
Steps:  91%|█████████ | 1814/2000 [54:28<05:24,  1.74s/it, loss=0.159, lr=0.0001]
Steps:  91%|█████████ | 1814/2000 [54:29<05:24,  1.74s/it, loss=0.108, lr=0.0001]
Steps:  91%|█████████ | 1814/2000 [54:29<05:24,  1.74s/it, loss=0.101, lr=0.0001]
Steps:  91%|█████████ | 1815/2000 [54:30<05:17,  1.72s/it, loss=0.101, lr=0.0001]
Steps:  91%|█████████ | 1815/2000 [54:30<05:17,  1.72s/it, loss=0.132, lr=0.0001]
Steps:  91%|█████████ | 1815/2000 [54:30<05:17,  1.72s/it, loss=0.373, lr=0.0001]
Steps:  91%|█████████ | 1815/2000 [54:31<05:17,  1.72s/it, loss=0.146, lr=0.0001]
Steps:  91%|█████████ | 1815/2000 [54:31<05:17,  1.72s/it, loss=0.0485, lr=0.0001]
Steps:  91%|█████████ | 1816/2000 [54:32<05:27,  1.78s/it, loss=0.0485, lr=0.0001]
Steps:  91%|█████████ | 1816/2000 [54:32<05:27,  1.78s/it, loss=0.152, lr=0.0001] 
Steps:  91%|█████████ | 1816/2000 [54:32<05:27,  1.78s/it, loss=0.133, lr=0.0001]
Steps:  91%|█████████ | 1816/2000 [54:32<05:27,  1.78s/it, loss=0.173, lr=0.0001]
Steps:  91%|█████████ | 1816/2000 [54:33<05:27,  1.78s/it, loss=0.203, lr=0.0001]
Steps:  91%|█████████ | 1817/2000 [54:33<05:19,  1.75s/it, loss=0.203, lr=0.0001]
Steps:  91%|█████████ | 1817/2000 [54:33<05:19,  1.75s/it, loss=0.208, lr=0.0001]
Steps:  91%|█████████ | 1817/2000 [54:34<05:19,  1.75s/it, loss=0.131, lr=0.0001]
Steps:  91%|█████████ | 1817/2000 [54:34<05:19,  1.75s/it, loss=0.149, lr=0.0001]
Steps:  91%|█████████ | 1817/2000 [54:35<05:19,  1.75s/it, loss=0.198, lr=0.0001]
Steps:  91%|█████████ | 1818/2000 [54:35<05:12,  1.72s/it, loss=0.198, lr=0.0001]
Steps:  91%|█████████ | 1818/2000 [54:35<05:12,  1.72s/it, loss=0.236, lr=0.0001]
Steps:  91%|█████████ | 1818/2000 [54:35<05:12,  1.72s/it, loss=0.202, lr=0.0001]
Steps:  91%|█████████ | 1818/2000 [54:36<05:12,  1.72s/it, loss=0.177, lr=0.0001]
Steps:  91%|█████████ | 1818/2000 [54:36<05:12,  1.72s/it, loss=0.159, lr=0.0001]
Steps:  91%|█████████ | 1819/2000 [54:37<05:22,  1.78s/it, loss=0.159, lr=0.0001]
Steps:  91%|█████████ | 1819/2000 [54:37<05:22,  1.78s/it, loss=0.25, lr=0.0001] 
Steps:  91%|█████████ | 1819/2000 [54:37<05:22,  1.78s/it, loss=0.17, lr=0.0001]
Steps:  91%|█████████ | 1819/2000 [54:38<05:22,  1.78s/it, loss=0.228, lr=0.0001]
Steps:  91%|█████████ | 1819/2000 [54:38<05:22,  1.78s/it, loss=0.172, lr=0.0001]
Steps:  91%|█████████ | 1820/2000 [54:39<05:17,  1.77s/it, loss=0.172, lr=0.0001]
Steps:  91%|█████████ | 1820/2000 [54:39<05:17,  1.77s/it, loss=0.243, lr=0.0001]
Steps:  91%|█████████ | 1820/2000 [54:39<05:17,  1.77s/it, loss=0.244, lr=0.0001]
Steps:  91%|█████████ | 1820/2000 [54:39<05:17,  1.77s/it, loss=0.217, lr=0.0001]
Steps:  91%|█████████ | 1820/2000 [54:40<05:17,  1.77s/it, loss=0.0924, lr=0.0001]
Steps:  91%|█████████ | 1821/2000 [54:40<05:10,  1.73s/it, loss=0.0924, lr=0.0001]
Steps:  91%|█████████ | 1821/2000 [54:40<05:10,  1.73s/it, loss=0.117, lr=0.0001] 
Steps:  91%|█████████ | 1821/2000 [54:41<05:10,  1.73s/it, loss=0.133, lr=0.0001]
Steps:  91%|█████████ | 1821/2000 [54:41<05:10,  1.73s/it, loss=0.0981, lr=0.0001]
Steps:  91%|█████████ | 1821/2000 [54:42<05:10,  1.73s/it, loss=0.116, lr=0.0001] 
Steps:  91%|█████████ | 1822/2000 [54:42<05:19,  1.79s/it, loss=0.116, lr=0.0001]
Steps:  91%|█████████ | 1822/2000 [54:42<05:19,  1.79s/it, loss=0.146, lr=0.0001]
Steps:  91%|█████████ | 1822/2000 [54:43<05:19,  1.79s/it, loss=0.176, lr=0.0001]
Steps:  91%|█████████ | 1822/2000 [54:43<05:19,  1.79s/it, loss=0.185, lr=0.0001]
Steps:  91%|█████████ | 1822/2000 [54:43<05:19,  1.79s/it, loss=0.536, lr=0.0001]
Steps:  91%|█████████ | 1823/2000 [54:44<05:10,  1.75s/it, loss=0.536, lr=0.0001]
Steps:  91%|█████████ | 1823/2000 [54:44<05:10,  1.75s/it, loss=0.247, lr=0.0001]
Steps:  91%|█████████ | 1823/2000 [54:44<05:10,  1.75s/it, loss=0.311, lr=0.0001]
Steps:  91%|█████████ | 1823/2000 [54:45<05:10,  1.75s/it, loss=0.161, lr=0.0001]
Steps:  91%|█████████ | 1823/2000 [54:45<05:10,  1.75s/it, loss=0.152, lr=0.0001]
Steps:  91%|█████████ | 1824/2000 [54:46<05:05,  1.73s/it, loss=0.152, lr=0.0001]
Steps:  91%|█████████ | 1824/2000 [54:46<05:05,  1.73s/it, loss=0.224, lr=0.0001]
Steps:  91%|█████████ | 1824/2000 [54:46<05:05,  1.73s/it, loss=0.0833, lr=0.0001]
Steps:  91%|█████████ | 1824/2000 [54:46<05:05,  1.73s/it, loss=0.108, lr=0.0001] 
Steps:  91%|█████████ | 1824/2000 [54:47<05:05,  1.73s/it, loss=0.139, lr=0.0001]
Steps:  91%|█████████▏| 1825/2000 [54:47<05:13,  1.79s/it, loss=0.139, lr=0.0001]
Steps:  91%|█████████▏| 1825/2000 [54:47<05:13,  1.79s/it, loss=0.0995, lr=0.0001]
Steps:  91%|█████████▏| 1825/2000 [54:48<05:13,  1.79s/it, loss=0.345, lr=0.0001] 
Steps:  91%|█████████▏| 1825/2000 [54:48<05:13,  1.79s/it, loss=0.172, lr=0.0001]
Steps:  91%|█████████▏| 1825/2000 [54:49<05:13,  1.79s/it, loss=0.103, lr=0.0001]
Steps:  91%|█████████▏| 1826/2000 [54:49<05:05,  1.76s/it, loss=0.103, lr=0.0001]
Steps:  91%|█████████▏| 1826/2000 [54:49<05:05,  1.76s/it, loss=0.313, lr=0.0001]
Steps:  91%|█████████▏| 1826/2000 [54:50<05:05,  1.76s/it, loss=0.162, lr=0.0001]
Steps:  91%|█████████▏| 1826/2000 [54:50<05:05,  1.76s/it, loss=0.159, lr=0.0001]
Steps:  91%|█████████▏| 1826/2000 [54:50<05:05,  1.76s/it, loss=0.138, lr=0.0001]
Steps:  91%|█████████▏| 1827/2000 [54:51<04:59,  1.73s/it, loss=0.138, lr=0.0001]
Steps:  91%|█████████▏| 1827/2000 [54:51<04:59,  1.73s/it, loss=0.212, lr=0.0001]
Steps:  91%|█████████▏| 1827/2000 [54:51<04:59,  1.73s/it, loss=0.0792, lr=0.0001]
Steps:  91%|█████████▏| 1827/2000 [54:52<04:59,  1.73s/it, loss=0.117, lr=0.0001] 
Steps:  91%|█████████▏| 1827/2000 [54:52<04:59,  1.73s/it, loss=0.109, lr=0.0001]
Steps:  91%|█████████▏| 1828/2000 [54:53<05:08,  1.79s/it, loss=0.109, lr=0.0001]
Steps:  91%|█████████▏| 1828/2000 [54:53<05:08,  1.79s/it, loss=0.238, lr=0.0001]
Steps:  91%|█████████▏| 1828/2000 [54:53<05:08,  1.79s/it, loss=0.0831, lr=0.0001]
Steps:  91%|█████████▏| 1828/2000 [54:54<05:08,  1.79s/it, loss=0.19, lr=0.0001]  
Steps:  91%|█████████▏| 1828/2000 [54:54<05:08,  1.79s/it, loss=0.299, lr=0.0001]
Steps:  91%|█████████▏| 1829/2000 [54:54<05:00,  1.76s/it, loss=0.299, lr=0.0001]
Steps:  91%|█████████▏| 1829/2000 [54:54<05:00,  1.76s/it, loss=0.177, lr=0.0001]
Steps:  91%|█████████▏| 1829/2000 [54:55<05:00,  1.76s/it, loss=0.0921, lr=0.0001]
Steps:  91%|█████████▏| 1829/2000 [54:55<05:00,  1.76s/it, loss=0.115, lr=0.0001] 
Steps:  91%|█████████▏| 1829/2000 [54:56<05:00,  1.76s/it, loss=0.232, lr=0.0001]
Steps:  92%|█████████▏| 1830/2000 [54:56<04:54,  1.73s/it, loss=0.232, lr=0.0001]
Steps:  92%|█████████▏| 1830/2000 [54:56<04:54,  1.73s/it, loss=0.416, lr=0.0001]
Steps:  92%|█████████▏| 1830/2000 [54:57<04:54,  1.73s/it, loss=0.156, lr=0.0001]
Steps:  92%|█████████▏| 1830/2000 [54:57<04:54,  1.73s/it, loss=0.486, lr=0.0001]
Steps:  92%|█████████▏| 1830/2000 [54:57<04:54,  1.73s/it, loss=0.172, lr=0.0001]
Steps:  92%|█████████▏| 1831/2000 [54:58<04:57,  1.76s/it, loss=0.172, lr=0.0001]
Steps:  92%|█████████▏| 1831/2000 [54:58<04:57,  1.76s/it, loss=0.178, lr=0.0001]
Steps:  92%|█████████▏| 1831/2000 [54:59<04:57,  1.76s/it, loss=0.199, lr=0.0001]
Steps:  92%|█████████▏| 1831/2000 [54:59<04:57,  1.76s/it, loss=0.121, lr=0.0001]
Steps:  92%|█████████▏| 1831/2000 [54:59<04:57,  1.76s/it, loss=0.234, lr=0.0001]
Steps:  92%|█████████▏| 1832/2000 [55:00<05:04,  1.81s/it, loss=0.234, lr=0.0001]
Steps:  92%|█████████▏| 1832/2000 [55:00<05:04,  1.81s/it, loss=0.253, lr=0.0001]
Steps:  92%|█████████▏| 1832/2000 [55:00<05:04,  1.81s/it, loss=0.16, lr=0.0001] 
Steps:  92%|█████████▏| 1832/2000 [55:01<05:04,  1.81s/it, loss=0.192, lr=0.0001]
Steps:  92%|█████████▏| 1832/2000 [55:01<05:04,  1.81s/it, loss=0.148, lr=0.0001]
Steps:  92%|█████████▏| 1833/2000 [55:02<04:55,  1.77s/it, loss=0.148, lr=0.0001]
Steps:  92%|█████████▏| 1833/2000 [55:02<04:55,  1.77s/it, loss=0.209, lr=0.0001]
Steps:  92%|█████████▏| 1833/2000 [55:02<04:55,  1.77s/it, loss=0.164, lr=0.0001]
Steps:  92%|█████████▏| 1833/2000 [55:02<04:55,  1.77s/it, loss=0.418, lr=0.0001]
Steps:  92%|█████████▏| 1833/2000 [55:03<04:55,  1.77s/it, loss=0.146, lr=0.0001]
Steps:  92%|█████████▏| 1834/2000 [55:03<04:53,  1.77s/it, loss=0.146, lr=0.0001]
Steps:  92%|█████████▏| 1834/2000 [55:03<04:53,  1.77s/it, loss=0.0862, lr=0.0001]
Steps:  92%|█████████▏| 1834/2000 [55:04<04:53,  1.77s/it, loss=0.156, lr=0.0001] 
Steps:  92%|█████████▏| 1834/2000 [55:04<04:53,  1.77s/it, loss=0.291, lr=0.0001]
Steps:  92%|█████████▏| 1834/2000 [55:05<04:53,  1.77s/it, loss=0.13, lr=0.0001] 
Steps:  92%|█████████▏| 1835/2000 [55:05<04:59,  1.81s/it, loss=0.13, lr=0.0001]
Steps:  92%|█████████▏| 1835/2000 [55:05<04:59,  1.81s/it, loss=0.079, lr=0.0001]
Steps:  92%|█████████▏| 1835/2000 [55:06<04:59,  1.81s/it, loss=0.12, lr=0.0001] 
Steps:  92%|█████████▏| 1835/2000 [55:06<04:59,  1.81s/it, loss=0.156, lr=0.0001]
Steps:  92%|█████████▏| 1835/2000 [55:06<04:59,  1.81s/it, loss=0.408, lr=0.0001]
Steps:  92%|█████████▏| 1836/2000 [55:07<04:49,  1.77s/it, loss=0.408, lr=0.0001]
Steps:  92%|█████████▏| 1836/2000 [55:07<04:49,  1.77s/it, loss=0.332, lr=0.0001]
Steps:  92%|█████████▏| 1836/2000 [55:07<04:49,  1.77s/it, loss=0.173, lr=0.0001]
Steps:  92%|█████████▏| 1836/2000 [55:08<04:49,  1.77s/it, loss=0.127, lr=0.0001]
Steps:  92%|█████████▏| 1836/2000 [55:08<04:49,  1.77s/it, loss=0.07, lr=0.0001] 
Steps:  92%|█████████▏| 1837/2000 [55:09<04:42,  1.73s/it, loss=0.07, lr=0.0001]
Steps:  92%|█████████▏| 1837/2000 [55:09<04:42,  1.73s/it, loss=0.233, lr=0.0001]
Steps:  92%|█████████▏| 1837/2000 [55:09<04:42,  1.73s/it, loss=0.212, lr=0.0001]
Steps:  92%|█████████▏| 1837/2000 [55:10<04:42,  1.73s/it, loss=0.174, lr=0.0001]
Steps:  92%|█████████▏| 1837/2000 [55:10<04:42,  1.73s/it, loss=0.135, lr=0.0001]
Steps:  92%|█████████▏| 1838/2000 [55:11<04:53,  1.81s/it, loss=0.135, lr=0.0001]
Steps:  92%|█████████▏| 1838/2000 [55:11<04:53,  1.81s/it, loss=0.0912, lr=0.0001]
Steps:  92%|█████████▏| 1838/2000 [55:11<04:53,  1.81s/it, loss=0.127, lr=0.0001] 
Steps:  92%|█████████▏| 1838/2000 [55:11<04:53,  1.81s/it, loss=0.192, lr=0.0001]
Steps:  92%|█████████▏| 1838/2000 [55:12<04:53,  1.81s/it, loss=0.173, lr=0.0001]
Steps:  92%|█████████▏| 1839/2000 [55:12<04:45,  1.77s/it, loss=0.173, lr=0.0001]
Steps:  92%|█████████▏| 1839/2000 [55:12<04:45,  1.77s/it, loss=0.0474, lr=0.0001]
Steps:  92%|█████████▏| 1839/2000 [55:13<04:45,  1.77s/it, loss=0.204, lr=0.0001] 
Steps:  92%|█████████▏| 1839/2000 [55:13<04:45,  1.77s/it, loss=0.325, lr=0.0001]
Steps:  92%|█████████▏| 1839/2000 [55:13<04:45,  1.77s/it, loss=0.211, lr=0.0001]
Steps:  92%|█████████▏| 1840/2000 [55:14<04:39,  1.75s/it, loss=0.211, lr=0.0001]
Steps:  92%|█████████▏| 1840/2000 [55:14<04:39,  1.75s/it, loss=0.34, lr=0.0001] 
Steps:  92%|█████████▏| 1840/2000 [55:14<04:39,  1.75s/it, loss=0.268, lr=0.0001]
Steps:  92%|█████████▏| 1840/2000 [55:15<04:39,  1.75s/it, loss=0.206, lr=0.0001]
Steps:  92%|█████████▏| 1840/2000 [55:15<04:39,  1.75s/it, loss=0.176, lr=0.0001]
Steps:  92%|█████████▏| 1841/2000 [55:16<04:47,  1.81s/it, loss=0.176, lr=0.0001]
Steps:  92%|█████████▏| 1841/2000 [55:16<04:47,  1.81s/it, loss=0.149, lr=0.0001]
Steps:  92%|█████████▏| 1841/2000 [55:16<04:47,  1.81s/it, loss=0.243, lr=0.0001]
Steps:  92%|█████████▏| 1841/2000 [55:17<04:47,  1.81s/it, loss=0.19, lr=0.0001] 
Steps:  92%|█████████▏| 1841/2000 [55:17<04:47,  1.81s/it, loss=0.0956, lr=0.0001]
Steps:  92%|█████████▏| 1842/2000 [55:18<04:38,  1.76s/it, loss=0.0956, lr=0.0001]
Steps:  92%|█████████▏| 1842/2000 [55:18<04:38,  1.76s/it, loss=0.161, lr=0.0001] 
Steps:  92%|█████████▏| 1842/2000 [55:18<04:38,  1.76s/it, loss=0.175, lr=0.0001]
Steps:  92%|█████████▏| 1842/2000 [55:18<04:38,  1.76s/it, loss=0.15, lr=0.0001] 
Steps:  92%|█████████▏| 1842/2000 [55:19<04:38,  1.76s/it, loss=0.227, lr=0.0001]
Steps:  92%|█████████▏| 1843/2000 [55:19<04:33,  1.74s/it, loss=0.227, lr=0.0001]
Steps:  92%|█████████▏| 1843/2000 [55:19<04:33,  1.74s/it, loss=0.217, lr=0.0001]
Steps:  92%|█████████▏| 1843/2000 [55:20<04:33,  1.74s/it, loss=0.157, lr=0.0001]
Steps:  92%|█████████▏| 1843/2000 [55:20<04:33,  1.74s/it, loss=0.116, lr=0.0001]
Steps:  92%|█████████▏| 1843/2000 [55:21<04:33,  1.74s/it, loss=0.177, lr=0.0001]
Steps:  92%|█████████▏| 1844/2000 [55:21<04:47,  1.84s/it, loss=0.177, lr=0.0001]
Steps:  92%|█████████▏| 1844/2000 [55:21<04:47,  1.84s/it, loss=0.133, lr=0.0001]
Steps:  92%|█████████▏| 1844/2000 [55:22<04:47,  1.84s/it, loss=0.27, lr=0.0001] 
Steps:  92%|█████████▏| 1844/2000 [55:22<04:47,  1.84s/it, loss=1.08, lr=0.0001]
Steps:  92%|█████████▏| 1844/2000 [55:22<04:47,  1.84s/it, loss=0.179, lr=0.0001]
Steps:  92%|█████████▏| 1845/2000 [55:23<04:38,  1.80s/it, loss=0.179, lr=0.0001]
Steps:  92%|█████████▏| 1845/2000 [55:23<04:38,  1.80s/it, loss=0.145, lr=0.0001]
Steps:  92%|█████████▏| 1845/2000 [55:23<04:38,  1.80s/it, loss=0.131, lr=0.0001]
Steps:  92%|█████████▏| 1845/2000 [55:24<04:38,  1.80s/it, loss=0.177, lr=0.0001]
Steps:  92%|█████████▏| 1845/2000 [55:24<04:38,  1.80s/it, loss=0.143, lr=0.0001]
Steps:  92%|█████████▏| 1846/2000 [55:25<04:30,  1.76s/it, loss=0.143, lr=0.0001]
Steps:  92%|█████████▏| 1846/2000 [55:25<04:30,  1.76s/it, loss=0.115, lr=0.0001]
Steps:  92%|█████████▏| 1846/2000 [55:25<04:30,  1.76s/it, loss=0.182, lr=0.0001]
Steps:  92%|█████████▏| 1846/2000 [55:25<04:30,  1.76s/it, loss=0.227, lr=0.0001]
Steps:  92%|█████████▏| 1846/2000 [55:26<04:30,  1.76s/it, loss=0.117, lr=0.0001]
Steps:  92%|█████████▏| 1847/2000 [55:27<04:36,  1.81s/it, loss=0.117, lr=0.0001]
Steps:  92%|█████████▏| 1847/2000 [55:27<04:36,  1.81s/it, loss=0.238, lr=0.0001]
Steps:  92%|█████████▏| 1847/2000 [55:27<04:36,  1.81s/it, loss=0.385, lr=0.0001]
Steps:  92%|█████████▏| 1847/2000 [55:27<04:36,  1.81s/it, loss=0.142, lr=0.0001]
Steps:  92%|█████████▏| 1847/2000 [55:28<04:36,  1.81s/it, loss=0.149, lr=0.0001]
Steps:  92%|█████████▏| 1848/2000 [55:28<04:28,  1.77s/it, loss=0.149, lr=0.0001]
Steps:  92%|█████████▏| 1848/2000 [55:28<04:28,  1.77s/it, loss=0.287, lr=0.0001]
Steps:  92%|█████████▏| 1848/2000 [55:29<04:28,  1.77s/it, loss=0.374, lr=0.0001]
Steps:  92%|█████████▏| 1848/2000 [55:29<04:28,  1.77s/it, loss=0.401, lr=0.0001]
Steps:  92%|█████████▏| 1848/2000 [55:29<04:28,  1.77s/it, loss=0.216, lr=0.0001]
Steps:  92%|█████████▏| 1849/2000 [55:30<04:21,  1.73s/it, loss=0.216, lr=0.0001]
Steps:  92%|█████████▏| 1849/2000 [55:30<04:21,  1.73s/it, loss=0.138, lr=0.0001]
Steps:  92%|█████████▏| 1849/2000 [55:30<04:21,  1.73s/it, loss=0.466, lr=0.0001]
Steps:  92%|█████████▏| 1849/2000 [55:31<04:21,  1.73s/it, loss=0.0871, lr=0.0001]
Steps:  92%|█████████▏| 1849/2000 [55:31<04:21,  1.73s/it, loss=0.133, lr=0.0001] 
Steps:  92%|█████████▎| 1850/2000 [55:32<04:28,  1.79s/it, loss=0.133, lr=0.0001]
Steps:  92%|█████████▎| 1850/2000 [55:32<04:28,  1.79s/it, loss=0.305, lr=0.0001]
Steps:  92%|█████████▎| 1850/2000 [55:32<04:28,  1.79s/it, loss=0.149, lr=0.0001]
Steps:  92%|█████████▎| 1850/2000 [55:33<04:28,  1.79s/it, loss=1.44, lr=0.0001] 
Steps:  92%|█████████▎| 1850/2000 [55:33<04:28,  1.79s/it, loss=0.514, lr=0.0001]
Steps:  93%|█████████▎| 1851/2000 [55:33<04:21,  1.76s/it, loss=0.514, lr=0.0001]
Steps:  93%|█████████▎| 1851/2000 [55:33<04:21,  1.76s/it, loss=0.177, lr=0.0001]
Steps:  93%|█████████▎| 1851/2000 [55:34<04:21,  1.76s/it, loss=0.388, lr=0.0001]
Steps:  93%|█████████▎| 1851/2000 [55:34<04:21,  1.76s/it, loss=0.207, lr=0.0001]
Steps:  93%|█████████▎| 1851/2000 [55:35<04:21,  1.76s/it, loss=0.202, lr=0.0001]
Steps:  93%|█████████▎| 1852/2000 [55:35<04:16,  1.74s/it, loss=0.202, lr=0.0001]
Steps:  93%|█████████▎| 1852/2000 [55:35<04:16,  1.74s/it, loss=0.247, lr=0.0001]
Steps:  93%|█████████▎| 1852/2000 [55:36<04:16,  1.74s/it, loss=0.0974, lr=0.0001]
Steps:  93%|█████████▎| 1852/2000 [55:36<04:16,  1.74s/it, loss=0.203, lr=0.0001] 
Steps:  93%|█████████▎| 1852/2000 [55:36<04:16,  1.74s/it, loss=0.135, lr=0.0001]
Steps:  93%|█████████▎| 1853/2000 [55:37<04:12,  1.72s/it, loss=0.135, lr=0.0001]
Steps:  93%|█████████▎| 1853/2000 [55:37<04:12,  1.72s/it, loss=0.163, lr=0.0001]
Steps:  93%|█████████▎| 1853/2000 [55:37<04:12,  1.72s/it, loss=0.165, lr=0.0001]
Steps:  93%|█████████▎| 1853/2000 [55:38<04:12,  1.72s/it, loss=0.21, lr=0.0001] 
Steps:  93%|█████████▎| 1853/2000 [55:38<04:12,  1.72s/it, loss=0.0743, lr=0.0001]
Steps:  93%|█████████▎| 1854/2000 [55:39<04:20,  1.78s/it, loss=0.0743, lr=0.0001]
Steps:  93%|█████████▎| 1854/2000 [55:39<04:20,  1.78s/it, loss=0.214, lr=0.0001] 
Steps:  93%|█████████▎| 1854/2000 [55:39<04:20,  1.78s/it, loss=0.144, lr=0.0001]
Steps:  93%|█████████▎| 1854/2000 [55:40<04:20,  1.78s/it, loss=0.175, lr=0.0001]
Steps:  93%|█████████▎| 1854/2000 [55:40<04:20,  1.78s/it, loss=0.113, lr=0.0001]
Steps:  93%|█████████▎| 1855/2000 [55:40<04:13,  1.75s/it, loss=0.113, lr=0.0001]
Steps:  93%|█████████▎| 1855/2000 [55:40<04:13,  1.75s/it, loss=0.264, lr=0.0001]
Steps:  93%|█████████▎| 1855/2000 [55:41<04:13,  1.75s/it, loss=0.228, lr=0.0001]
Steps:  93%|█████████▎| 1855/2000 [55:41<04:13,  1.75s/it, loss=0.133, lr=0.0001]
Steps:  93%|█████████▎| 1855/2000 [55:42<04:13,  1.75s/it, loss=0.119, lr=0.0001]
Steps:  93%|█████████▎| 1856/2000 [55:42<04:07,  1.72s/it, loss=0.119, lr=0.0001]
Steps:  93%|█████████▎| 1856/2000 [55:42<04:07,  1.72s/it, loss=0.174, lr=0.0001]
Steps:  93%|█████████▎| 1856/2000 [55:42<04:07,  1.72s/it, loss=0.21, lr=0.0001] 
Steps:  93%|█████████▎| 1856/2000 [55:43<04:07,  1.72s/it, loss=0.146, lr=0.0001]
Steps:  93%|█████████▎| 1856/2000 [55:44<04:07,  1.72s/it, loss=0.174, lr=0.0001]
Steps:  93%|█████████▎| 1857/2000 [55:44<04:13,  1.77s/it, loss=0.174, lr=0.0001]
Steps:  93%|█████████▎| 1857/2000 [55:44<04:13,  1.77s/it, loss=0.214, lr=0.0001]
Steps:  93%|█████████▎| 1857/2000 [55:44<04:13,  1.77s/it, loss=0.203, lr=0.0001]
Steps:  93%|█████████▎| 1857/2000 [55:45<04:13,  1.77s/it, loss=0.285, lr=0.0001]
Steps:  93%|█████████▎| 1857/2000 [55:45<04:13,  1.77s/it, loss=0.278, lr=0.0001]
Steps:  93%|█████████▎| 1858/2000 [55:46<04:07,  1.74s/it, loss=0.278, lr=0.0001]
Steps:  93%|█████████▎| 1858/2000 [55:46<04:07,  1.74s/it, loss=0.123, lr=0.0001]
Steps:  93%|█████████▎| 1858/2000 [55:46<04:07,  1.74s/it, loss=0.167, lr=0.0001]
Steps:  93%|█████████▎| 1858/2000 [55:46<04:07,  1.74s/it, loss=0.0325, lr=0.0001]
Steps:  93%|█████████▎| 1858/2000 [55:47<04:07,  1.74s/it, loss=0.297, lr=0.0001] 
Steps:  93%|█████████▎| 1859/2000 [55:47<04:01,  1.71s/it, loss=0.297, lr=0.0001]
Steps:  93%|█████████▎| 1859/2000 [55:47<04:01,  1.71s/it, loss=0.181, lr=0.0001]
Steps:  93%|█████████▎| 1859/2000 [55:48<04:01,  1.71s/it, loss=0.17, lr=0.0001] 
Steps:  93%|█████████▎| 1859/2000 [55:48<04:01,  1.71s/it, loss=0.226, lr=0.0001]
Steps:  93%|█████████▎| 1859/2000 [55:49<04:01,  1.71s/it, loss=0.21, lr=0.0001] 
Steps:  93%|█████████▎| 1860/2000 [55:49<04:07,  1.77s/it, loss=0.21, lr=0.0001]
Steps:  93%|█████████▎| 1860/2000 [55:49<04:07,  1.77s/it, loss=0.258, lr=0.0001]
Steps:  93%|█████████▎| 1860/2000 [55:50<04:07,  1.77s/it, loss=0.199, lr=0.0001]
Steps:  93%|█████████▎| 1860/2000 [55:50<04:07,  1.77s/it, loss=0.176, lr=0.0001]
Steps:  93%|█████████▎| 1860/2000 [55:50<04:07,  1.77s/it, loss=0.122, lr=0.0001]
Steps:  93%|█████████▎| 1861/2000 [55:51<04:01,  1.74s/it, loss=0.122, lr=0.0001]
Steps:  93%|█████████▎| 1861/2000 [55:51<04:01,  1.74s/it, loss=0.164, lr=0.0001]
Steps:  93%|█████████▎| 1861/2000 [55:51<04:01,  1.74s/it, loss=0.233, lr=0.0001]
Steps:  93%|█████████▎| 1861/2000 [55:52<04:01,  1.74s/it, loss=0.133, lr=0.0001]
Steps:  93%|█████████▎| 1861/2000 [55:52<04:01,  1.74s/it, loss=0.31, lr=0.0001] 
Steps:  93%|█████████▎| 1862/2000 [55:53<03:56,  1.72s/it, loss=0.31, lr=0.0001]
Steps:  93%|█████████▎| 1862/2000 [55:53<03:56,  1.72s/it, loss=0.198, lr=0.0001]
Steps:  93%|█████████▎| 1862/2000 [55:53<03:56,  1.72s/it, loss=0.147, lr=0.0001]
Steps:  93%|█████████▎| 1862/2000 [55:53<03:56,  1.72s/it, loss=0.515, lr=0.0001]
Steps:  93%|█████████▎| 1862/2000 [55:54<03:56,  1.72s/it, loss=0.131, lr=0.0001]
Steps:  93%|█████████▎| 1863/2000 [55:54<04:02,  1.77s/it, loss=0.131, lr=0.0001]
Steps:  93%|█████████▎| 1863/2000 [55:54<04:02,  1.77s/it, loss=0.135, lr=0.0001]
Steps:  93%|█████████▎| 1863/2000 [55:55<04:02,  1.77s/it, loss=0.134, lr=0.0001]
Steps:  93%|█████████▎| 1863/2000 [55:55<04:02,  1.77s/it, loss=0.12, lr=0.0001] 
Steps:  93%|█████████▎| 1863/2000 [55:56<04:02,  1.77s/it, loss=0.114, lr=0.0001]
Steps:  93%|█████████▎| 1864/2000 [55:56<03:56,  1.74s/it, loss=0.114, lr=0.0001]
Steps:  93%|█████████▎| 1864/2000 [55:56<03:56,  1.74s/it, loss=0.194, lr=0.0001]
Steps:  93%|█████████▎| 1864/2000 [55:56<03:56,  1.74s/it, loss=0.145, lr=0.0001]
Steps:  93%|█████████▎| 1864/2000 [55:57<03:56,  1.74s/it, loss=0.131, lr=0.0001]
Steps:  93%|█████████▎| 1864/2000 [55:57<03:56,  1.74s/it, loss=0.0824, lr=0.0001]
Steps:  93%|█████████▎| 1865/2000 [55:58<03:50,  1.71s/it, loss=0.0824, lr=0.0001]
Steps:  93%|█████████▎| 1865/2000 [55:58<03:50,  1.71s/it, loss=0.0558, lr=0.0001]
Steps:  93%|█████████▎| 1865/2000 [55:58<03:50,  1.71s/it, loss=0.182, lr=0.0001] 
Steps:  93%|█████████▎| 1865/2000 [55:59<03:50,  1.71s/it, loss=0.249, lr=0.0001]
Steps:  93%|█████████▎| 1865/2000 [55:59<03:50,  1.71s/it, loss=0.174, lr=0.0001]
Steps:  93%|█████████▎| 1866/2000 [56:00<03:56,  1.76s/it, loss=0.174, lr=0.0001]
Steps:  93%|█████████▎| 1866/2000 [56:00<03:56,  1.76s/it, loss=0.136, lr=0.0001]
Steps:  93%|█████████▎| 1866/2000 [56:00<03:56,  1.76s/it, loss=0.22, lr=0.0001] 
Steps:  93%|█████████▎| 1866/2000 [56:00<03:56,  1.76s/it, loss=0.782, lr=0.0001]
Steps:  93%|█████████▎| 1866/2000 [56:01<03:56,  1.76s/it, loss=0.22, lr=0.0001] 
Steps:  93%|█████████▎| 1867/2000 [56:01<03:50,  1.73s/it, loss=0.22, lr=0.0001]
Steps:  93%|█████████▎| 1867/2000 [56:01<03:50,  1.73s/it, loss=0.17, lr=0.0001]
Steps:  93%|█████████▎| 1867/2000 [56:02<03:50,  1.73s/it, loss=0.117, lr=0.0001]
Steps:  93%|█████████▎| 1867/2000 [56:02<03:50,  1.73s/it, loss=0.145, lr=0.0001]
Steps:  93%|█████████▎| 1867/2000 [56:03<03:50,  1.73s/it, loss=0.196, lr=0.0001]
Steps:  93%|█████████▎| 1868/2000 [56:03<03:45,  1.71s/it, loss=0.196, lr=0.0001]
Steps:  93%|█████████▎| 1868/2000 [56:03<03:45,  1.71s/it, loss=0.221, lr=0.0001]
Steps:  93%|█████████▎| 1868/2000 [56:03<03:45,  1.71s/it, loss=0.59, lr=0.0001] 
Steps:  93%|█████████▎| 1868/2000 [56:04<03:45,  1.71s/it, loss=0.113, lr=0.0001]
Steps:  93%|█████████▎| 1868/2000 [56:04<03:45,  1.71s/it, loss=0.0649, lr=0.0001]
Steps:  93%|█████████▎| 1869/2000 [56:05<03:52,  1.78s/it, loss=0.0649, lr=0.0001]
Steps:  93%|█████████▎| 1869/2000 [56:05<03:52,  1.78s/it, loss=0.149, lr=0.0001] 
Steps:  93%|█████████▎| 1869/2000 [56:05<03:52,  1.78s/it, loss=0.198, lr=0.0001]
Steps:  93%|█████████▎| 1869/2000 [56:06<03:52,  1.78s/it, loss=0.134, lr=0.0001]
Steps:  93%|█████████▎| 1869/2000 [56:06<03:52,  1.78s/it, loss=0.238, lr=0.0001]
Steps:  94%|█████████▎| 1870/2000 [56:07<03:47,  1.75s/it, loss=0.238, lr=0.0001]
Steps:  94%|█████████▎| 1870/2000 [56:07<03:47,  1.75s/it, loss=0.193, lr=0.0001]
Steps:  94%|█████████▎| 1870/2000 [56:07<03:47,  1.75s/it, loss=0.168, lr=0.0001]
Steps:  94%|█████████▎| 1870/2000 [56:07<03:47,  1.75s/it, loss=1.04, lr=0.0001] 
Steps:  94%|█████████▎| 1870/2000 [56:08<03:47,  1.75s/it, loss=0.133, lr=0.0001]
Steps:  94%|█████████▎| 1871/2000 [56:08<03:42,  1.72s/it, loss=0.133, lr=0.0001]
Steps:  94%|█████████▎| 1871/2000 [56:08<03:42,  1.72s/it, loss=0.12, lr=0.0001] 
Steps:  94%|█████████▎| 1871/2000 [56:09<03:42,  1.72s/it, loss=0.176, lr=0.0001]
Steps:  94%|█████████▎| 1871/2000 [56:09<03:42,  1.72s/it, loss=0.19, lr=0.0001] 
Steps:  94%|█████████▎| 1871/2000 [56:10<03:42,  1.72s/it, loss=0.112, lr=0.0001]
Steps:  94%|█████████▎| 1872/2000 [56:10<03:49,  1.79s/it, loss=0.112, lr=0.0001]
Steps:  94%|█████████▎| 1872/2000 [56:10<03:49,  1.79s/it, loss=0.513, lr=0.0001]
Steps:  94%|█████████▎| 1872/2000 [56:11<03:49,  1.79s/it, loss=0.116, lr=0.0001]
Steps:  94%|█████████▎| 1872/2000 [56:11<03:49,  1.79s/it, loss=0.575, lr=0.0001]
Steps:  94%|█████████▎| 1872/2000 [56:11<03:49,  1.79s/it, loss=0.404, lr=0.0001]
Steps:  94%|█████████▎| 1873/2000 [56:12<03:42,  1.75s/it, loss=0.404, lr=0.0001]
Steps:  94%|█████████▎| 1873/2000 [56:12<03:42,  1.75s/it, loss=0.0767, lr=0.0001]
Steps:  94%|█████████▎| 1873/2000 [56:12<03:42,  1.75s/it, loss=0.164, lr=0.0001] 
Steps:  94%|█████████▎| 1873/2000 [56:13<03:42,  1.75s/it, loss=0.224, lr=0.0001]
Steps:  94%|█████████▎| 1873/2000 [56:13<03:42,  1.75s/it, loss=0.169, lr=0.0001]
Steps:  94%|█████████▎| 1874/2000 [56:13<03:37,  1.72s/it, loss=0.169, lr=0.0001]
Steps:  94%|█████████▎| 1874/2000 [56:13<03:37,  1.72s/it, loss=0.247, lr=0.0001]
Steps:  94%|█████████▎| 1874/2000 [56:14<03:37,  1.72s/it, loss=0.178, lr=0.0001]
Steps:  94%|█████████▎| 1874/2000 [56:14<03:37,  1.72s/it, loss=0.0233, lr=0.0001]
Steps:  94%|█████████▎| 1874/2000 [56:15<03:37,  1.72s/it, loss=0.168, lr=0.0001] 
Steps:  94%|█████████▍| 1875/2000 [56:15<03:33,  1.71s/it, loss=0.168, lr=0.0001]
Steps:  94%|█████████▍| 1875/2000 [56:15<03:33,  1.71s/it, loss=0.121, lr=0.0001]
Steps:  94%|█████████▍| 1875/2000 [56:16<03:33,  1.71s/it, loss=0.114, lr=0.0001]
Steps:  94%|█████████▍| 1875/2000 [56:16<03:33,  1.71s/it, loss=0.232, lr=0.0001]
Steps:  94%|█████████▍| 1875/2000 [56:17<03:33,  1.71s/it, loss=0.158, lr=0.0001]
Steps:  94%|█████████▍| 1876/2000 [56:17<03:39,  1.77s/it, loss=0.158, lr=0.0001]
Steps:  94%|█████████▍| 1876/2000 [56:17<03:39,  1.77s/it, loss=0.186, lr=0.0001]
Steps:  94%|█████████▍| 1876/2000 [56:17<03:39,  1.77s/it, loss=0.17, lr=0.0001] 
Steps:  94%|█████████▍| 1876/2000 [56:18<03:39,  1.77s/it, loss=0.386, lr=0.0001]
Steps:  94%|█████████▍| 1876/2000 [56:18<03:39,  1.77s/it, loss=0.0838, lr=0.0001]
Steps:  94%|█████████▍| 1877/2000 [56:19<03:34,  1.75s/it, loss=0.0838, lr=0.0001]
Steps:  94%|█████████▍| 1877/2000 [56:19<03:34,  1.75s/it, loss=0.139, lr=0.0001] 
Steps:  94%|█████████▍| 1877/2000 [56:19<03:34,  1.75s/it, loss=0.194, lr=0.0001]
Steps:  94%|█████████▍| 1877/2000 [56:20<03:34,  1.75s/it, loss=0.175, lr=0.0001]
Steps:  94%|█████████▍| 1877/2000 [56:20<03:34,  1.75s/it, loss=0.152, lr=0.0001]
Steps:  94%|█████████▍| 1878/2000 [56:20<03:29,  1.72s/it, loss=0.152, lr=0.0001]
Steps:  94%|█████████▍| 1878/2000 [56:20<03:29,  1.72s/it, loss=0.203, lr=0.0001]
Steps:  94%|█████████▍| 1878/2000 [56:21<03:29,  1.72s/it, loss=0.16, lr=0.0001] 
Steps:  94%|█████████▍| 1878/2000 [56:21<03:29,  1.72s/it, loss=0.12, lr=0.0001]
Steps:  94%|█████████▍| 1878/2000 [56:22<03:29,  1.72s/it, loss=0.174, lr=0.0001]
Steps:  94%|█████████▍| 1879/2000 [56:22<03:34,  1.77s/it, loss=0.174, lr=0.0001]
Steps:  94%|█████████▍| 1879/2000 [56:22<03:34,  1.77s/it, loss=0.129, lr=0.0001]
Steps:  94%|█████████▍| 1879/2000 [56:23<03:34,  1.77s/it, loss=0.263, lr=0.0001]
Steps:  94%|█████████▍| 1879/2000 [56:23<03:34,  1.77s/it, loss=0.609, lr=0.0001]
Steps:  94%|█████████▍| 1879/2000 [56:24<03:34,  1.77s/it, loss=0.148, lr=0.0001]
Steps:  94%|█████████▍| 1880/2000 [56:24<03:29,  1.74s/it, loss=0.148, lr=0.0001]
Steps:  94%|█████████▍| 1880/2000 [56:24<03:29,  1.74s/it, loss=0.0885, lr=0.0001]
Steps:  94%|█████████▍| 1880/2000 [56:24<03:29,  1.74s/it, loss=0.109, lr=0.0001] 
Steps:  94%|█████████▍| 1880/2000 [56:25<03:29,  1.74s/it, loss=0.14, lr=0.0001] 
Steps:  94%|█████████▍| 1880/2000 [56:25<03:29,  1.74s/it, loss=0.106, lr=0.0001]
Steps:  94%|█████████▍| 1881/2000 [56:26<03:24,  1.72s/it, loss=0.106, lr=0.0001]
Steps:  94%|█████████▍| 1881/2000 [56:26<03:24,  1.72s/it, loss=0.173, lr=0.0001]
Steps:  94%|█████████▍| 1881/2000 [56:26<03:24,  1.72s/it, loss=0.0831, lr=0.0001]
Steps:  94%|█████████▍| 1881/2000 [56:27<03:24,  1.72s/it, loss=0.346, lr=0.0001] 
Steps:  94%|█████████▍| 1881/2000 [56:27<03:24,  1.72s/it, loss=0.107, lr=0.0001]
Steps:  94%|█████████▍| 1882/2000 [56:28<03:28,  1.77s/it, loss=0.107, lr=0.0001]
Steps:  94%|█████████▍| 1882/2000 [56:28<03:28,  1.77s/it, loss=0.357, lr=0.0001]
Steps:  94%|█████████▍| 1882/2000 [56:28<03:28,  1.77s/it, loss=0.188, lr=0.0001]
Steps:  94%|█████████▍| 1882/2000 [56:28<03:28,  1.77s/it, loss=0.14, lr=0.0001] 
Steps:  94%|█████████▍| 1882/2000 [56:29<03:28,  1.77s/it, loss=0.169, lr=0.0001]
Steps:  94%|█████████▍| 1883/2000 [56:29<03:22,  1.73s/it, loss=0.169, lr=0.0001]
Steps:  94%|█████████▍| 1883/2000 [56:29<03:22,  1.73s/it, loss=0.506, lr=0.0001]
Steps:  94%|█████████▍| 1883/2000 [56:30<03:22,  1.73s/it, loss=0.177, lr=0.0001]
Steps:  94%|█████████▍| 1883/2000 [56:30<03:22,  1.73s/it, loss=0.199, lr=0.0001]
Steps:  94%|█████████▍| 1883/2000 [56:30<03:22,  1.73s/it, loss=0.481, lr=0.0001]
Steps:  94%|█████████▍| 1884/2000 [56:31<03:18,  1.71s/it, loss=0.481, lr=0.0001]
Steps:  94%|█████████▍| 1884/2000 [56:31<03:18,  1.71s/it, loss=0.219, lr=0.0001]
Steps:  94%|█████████▍| 1884/2000 [56:31<03:18,  1.71s/it, loss=0.494, lr=0.0001]
Steps:  94%|█████████▍| 1884/2000 [56:32<03:18,  1.71s/it, loss=0.204, lr=0.0001]
Steps:  94%|█████████▍| 1884/2000 [56:32<03:18,  1.71s/it, loss=0.131, lr=0.0001]
Steps:  94%|█████████▍| 1885/2000 [56:33<03:23,  1.77s/it, loss=0.131, lr=0.0001]
Steps:  94%|█████████▍| 1885/2000 [56:33<03:23,  1.77s/it, loss=0.182, lr=0.0001]
Steps:  94%|█████████▍| 1885/2000 [56:33<03:23,  1.77s/it, loss=0.342, lr=0.0001]
Steps:  94%|█████████▍| 1885/2000 [56:34<03:23,  1.77s/it, loss=0.208, lr=0.0001]
Steps:  94%|█████████▍| 1885/2000 [56:34<03:23,  1.77s/it, loss=0.181, lr=0.0001]
Steps:  94%|█████████▍| 1886/2000 [56:34<03:17,  1.73s/it, loss=0.181, lr=0.0001]
Steps:  94%|█████████▍| 1886/2000 [56:34<03:17,  1.73s/it, loss=0.204, lr=0.0001]
Steps:  94%|█████████▍| 1886/2000 [56:35<03:17,  1.73s/it, loss=0.265, lr=0.0001]
Steps:  94%|█████████▍| 1886/2000 [56:35<03:17,  1.73s/it, loss=0.0626, lr=0.0001]
Steps:  94%|█████████▍| 1886/2000 [56:36<03:17,  1.73s/it, loss=0.22, lr=0.0001]  
Steps:  94%|█████████▍| 1887/2000 [56:36<03:13,  1.71s/it, loss=0.22, lr=0.0001]
Steps:  94%|█████████▍| 1887/2000 [56:36<03:13,  1.71s/it, loss=0.199, lr=0.0001]
Steps:  94%|█████████▍| 1887/2000 [56:36<03:13,  1.71s/it, loss=0.179, lr=0.0001]
Steps:  94%|█████████▍| 1887/2000 [56:37<03:13,  1.71s/it, loss=0.24, lr=0.0001] 
Steps:  94%|█████████▍| 1887/2000 [56:37<03:13,  1.71s/it, loss=0.322, lr=0.0001]
Steps:  94%|█████████▍| 1888/2000 [56:38<03:18,  1.77s/it, loss=0.322, lr=0.0001]
Steps:  94%|█████████▍| 1888/2000 [56:38<03:18,  1.77s/it, loss=0.607, lr=0.0001]
Steps:  94%|█████████▍| 1888/2000 [56:38<03:18,  1.77s/it, loss=0.196, lr=0.0001]
Steps:  94%|█████████▍| 1888/2000 [56:39<03:18,  1.77s/it, loss=0.129, lr=0.0001]
Steps:  94%|█████████▍| 1888/2000 [56:39<03:18,  1.77s/it, loss=0.414, lr=0.0001]
Steps:  94%|█████████▍| 1889/2000 [56:40<03:13,  1.74s/it, loss=0.414, lr=0.0001]
Steps:  94%|█████████▍| 1889/2000 [56:40<03:13,  1.74s/it, loss=0.467, lr=0.0001]
Steps:  94%|█████████▍| 1889/2000 [56:40<03:13,  1.74s/it, loss=0.462, lr=0.0001]
Steps:  94%|█████████▍| 1889/2000 [56:40<03:13,  1.74s/it, loss=0.0676, lr=0.0001]
Steps:  94%|█████████▍| 1889/2000 [56:41<03:13,  1.74s/it, loss=0.153, lr=0.0001] 
Steps:  94%|█████████▍| 1890/2000 [56:41<03:12,  1.75s/it, loss=0.153, lr=0.0001]
Steps:  94%|█████████▍| 1890/2000 [56:41<03:12,  1.75s/it, loss=0.176, lr=0.0001]
Steps:  94%|█████████▍| 1890/2000 [56:42<03:12,  1.75s/it, loss=0.137, lr=0.0001]
Steps:  94%|█████████▍| 1890/2000 [56:42<03:12,  1.75s/it, loss=0.15, lr=0.0001] 
Steps:  94%|█████████▍| 1890/2000 [56:43<03:12,  1.75s/it, loss=0.204, lr=0.0001]
Steps:  95%|█████████▍| 1891/2000 [56:43<03:16,  1.80s/it, loss=0.204, lr=0.0001]
Steps:  95%|█████████▍| 1891/2000 [56:43<03:16,  1.80s/it, loss=0.155, lr=0.0001]
Steps:  95%|█████████▍| 1891/2000 [56:44<03:16,  1.80s/it, loss=0.0865, lr=0.0001]
Steps:  95%|█████████▍| 1891/2000 [56:44<03:16,  1.80s/it, loss=0.15, lr=0.0001]  
Steps:  95%|█████████▍| 1891/2000 [56:45<03:16,  1.80s/it, loss=0.165, lr=0.0001]
Steps:  95%|█████████▍| 1892/2000 [56:45<03:09,  1.76s/it, loss=0.165, lr=0.0001]
Steps:  95%|█████████▍| 1892/2000 [56:45<03:09,  1.76s/it, loss=0.0971, lr=0.0001]
Steps:  95%|█████████▍| 1892/2000 [56:45<03:09,  1.76s/it, loss=0.223, lr=0.0001] 
Steps:  95%|█████████▍| 1892/2000 [56:46<03:09,  1.76s/it, loss=0.203, lr=0.0001]
Steps:  95%|█████████▍| 1892/2000 [56:46<03:09,  1.76s/it, loss=0.0524, lr=0.0001]
Steps:  95%|█████████▍| 1893/2000 [56:47<03:04,  1.73s/it, loss=0.0524, lr=0.0001]
Steps:  95%|█████████▍| 1893/2000 [56:47<03:04,  1.73s/it, loss=0.422, lr=0.0001] 
Steps:  95%|█████████▍| 1893/2000 [56:47<03:04,  1.73s/it, loss=0.239, lr=0.0001]
Steps:  95%|█████████▍| 1893/2000 [56:47<03:04,  1.73s/it, loss=0.128, lr=0.0001]
Steps:  95%|█████████▍| 1893/2000 [56:48<03:04,  1.73s/it, loss=0.168, lr=0.0001]
Steps:  95%|█████████▍| 1894/2000 [56:48<03:00,  1.71s/it, loss=0.168, lr=0.0001]
Steps:  95%|█████████▍| 1894/2000 [56:48<03:00,  1.71s/it, loss=0.0772, lr=0.0001]
Steps:  95%|█████████▍| 1894/2000 [56:49<03:00,  1.71s/it, loss=0.184, lr=0.0001] 
Steps:  95%|█████████▍| 1894/2000 [56:49<03:00,  1.71s/it, loss=0.176, lr=0.0001]
Steps:  95%|█████████▍| 1894/2000 [56:50<03:00,  1.71s/it, loss=0.214, lr=0.0001]
Steps:  95%|█████████▍| 1895/2000 [56:50<03:04,  1.76s/it, loss=0.214, lr=0.0001]
Steps:  95%|█████████▍| 1895/2000 [56:50<03:04,  1.76s/it, loss=0.145, lr=0.0001]
Steps:  95%|█████████▍| 1895/2000 [56:51<03:04,  1.76s/it, loss=0.0488, lr=0.0001]
Steps:  95%|█████████▍| 1895/2000 [56:51<03:04,  1.76s/it, loss=0.206, lr=0.0001] 
Steps:  95%|█████████▍| 1895/2000 [56:51<03:04,  1.76s/it, loss=0.127, lr=0.0001]
Steps:  95%|█████████▍| 1896/2000 [56:52<02:59,  1.73s/it, loss=0.127, lr=0.0001]
Steps:  95%|█████████▍| 1896/2000 [56:52<02:59,  1.73s/it, loss=0.138, lr=0.0001]
Steps:  95%|█████████▍| 1896/2000 [56:52<02:59,  1.73s/it, loss=0.0886, lr=0.0001]
Steps:  95%|█████████▍| 1896/2000 [56:53<02:59,  1.73s/it, loss=0.166, lr=0.0001] 
Steps:  95%|█████████▍| 1896/2000 [56:53<02:59,  1.73s/it, loss=0.137, lr=0.0001]
Steps:  95%|█████████▍| 1897/2000 [56:54<02:57,  1.72s/it, loss=0.137, lr=0.0001]
Steps:  95%|█████████▍| 1897/2000 [56:54<02:57,  1.72s/it, loss=0.141, lr=0.0001]
Steps:  95%|█████████▍| 1897/2000 [56:54<02:57,  1.72s/it, loss=0.19, lr=0.0001] 
Steps:  95%|█████████▍| 1897/2000 [56:55<02:57,  1.72s/it, loss=0.0997, lr=0.0001]
Steps:  95%|█████████▍| 1897/2000 [56:55<02:57,  1.72s/it, loss=0.103, lr=0.0001] 
Steps:  95%|█████████▍| 1898/2000 [56:55<03:00,  1.77s/it, loss=0.103, lr=0.0001]
Steps:  95%|█████████▍| 1898/2000 [56:55<03:00,  1.77s/it, loss=0.142, lr=0.0001]
Steps:  95%|█████████▍| 1898/2000 [56:56<03:00,  1.77s/it, loss=0.168, lr=0.0001]
Steps:  95%|█████████▍| 1898/2000 [56:56<03:00,  1.77s/it, loss=0.153, lr=0.0001]
Steps:  95%|█████████▍| 1898/2000 [56:57<03:00,  1.77s/it, loss=0.575, lr=0.0001]
Steps:  95%|█████████▍| 1899/2000 [56:57<02:55,  1.74s/it, loss=0.575, lr=0.0001]
Steps:  95%|█████████▍| 1899/2000 [56:57<02:55,  1.74s/it, loss=0.243, lr=0.0001]
Steps:  95%|█████████▍| 1899/2000 [56:57<02:55,  1.74s/it, loss=0.445, lr=0.0001]
Steps:  95%|█████████▍| 1899/2000 [56:58<02:55,  1.74s/it, loss=0.22, lr=0.0001] 
Steps:  95%|█████████▍| 1899/2000 [56:58<02:55,  1.74s/it, loss=0.153, lr=0.0001]
Steps:  95%|█████████▌| 1900/2000 [56:59<02:51,  1.71s/it, loss=0.153, lr=0.0001]
Steps:  95%|█████████▌| 1900/2000 [56:59<02:51,  1.71s/it, loss=0.248, lr=0.0001]
Steps:  95%|█████████▌| 1900/2000 [56:59<02:51,  1.71s/it, loss=0.194, lr=0.0001]
Steps:  95%|█████████▌| 1900/2000 [57:00<02:51,  1.71s/it, loss=0.0796, lr=0.0001]
Steps:  95%|█████████▌| 1900/2000 [57:00<02:51,  1.71s/it, loss=0.361, lr=0.0001] 
Steps:  95%|█████████▌| 1901/2000 [57:01<02:55,  1.77s/it, loss=0.361, lr=0.0001]
Steps:  95%|█████████▌| 1901/2000 [57:01<02:55,  1.77s/it, loss=0.161, lr=0.0001]
Steps:  95%|█████████▌| 1901/2000 [57:01<02:55,  1.77s/it, loss=0.232, lr=0.0001]
Steps:  95%|█████████▌| 1901/2000 [57:01<02:55,  1.77s/it, loss=0.232, lr=0.0001]
Steps:  95%|█████████▌| 1901/2000 [57:02<02:55,  1.77s/it, loss=0.0868, lr=0.0001]
Steps:  95%|█████████▌| 1902/2000 [57:02<02:50,  1.74s/it, loss=0.0868, lr=0.0001]
Steps:  95%|█████████▌| 1902/2000 [57:02<02:50,  1.74s/it, loss=0.0431, lr=0.0001]
Steps:  95%|█████████▌| 1902/2000 [57:03<02:50,  1.74s/it, loss=0.132, lr=0.0001] 
Steps:  95%|█████████▌| 1902/2000 [57:03<02:50,  1.74s/it, loss=0.321, lr=0.0001]
Steps:  95%|█████████▌| 1902/2000 [57:04<02:50,  1.74s/it, loss=0.121, lr=0.0001]
Steps:  95%|█████████▌| 1903/2000 [57:04<02:46,  1.71s/it, loss=0.121, lr=0.0001]
Steps:  95%|█████████▌| 1903/2000 [57:04<02:46,  1.71s/it, loss=0.226, lr=0.0001]
Steps:  95%|█████████▌| 1903/2000 [57:04<02:46,  1.71s/it, loss=0.0661, lr=0.0001]
Steps:  95%|█████████▌| 1903/2000 [57:05<02:46,  1.71s/it, loss=0.517, lr=0.0001] 
Steps:  95%|█████████▌| 1903/2000 [57:05<02:46,  1.71s/it, loss=0.143, lr=0.0001]
Steps:  95%|█████████▌| 1904/2000 [57:06<02:50,  1.77s/it, loss=0.143, lr=0.0001]
Steps:  95%|█████████▌| 1904/2000 [57:06<02:50,  1.77s/it, loss=0.147, lr=0.0001]
Steps:  95%|█████████▌| 1904/2000 [57:06<02:50,  1.77s/it, loss=0.168, lr=0.0001]
Steps:  95%|█████████▌| 1904/2000 [57:07<02:50,  1.77s/it, loss=0.151, lr=0.0001]
Steps:  95%|█████████▌| 1904/2000 [57:07<02:50,  1.77s/it, loss=0.197, lr=0.0001]
Steps:  95%|█████████▌| 1905/2000 [57:08<02:44,  1.73s/it, loss=0.197, lr=0.0001]
Steps:  95%|█████████▌| 1905/2000 [57:08<02:44,  1.73s/it, loss=0.276, lr=0.0001]
Steps:  95%|█████████▌| 1905/2000 [57:08<02:44,  1.73s/it, loss=0.155, lr=0.0001]
Steps:  95%|█████████▌| 1905/2000 [57:08<02:44,  1.73s/it, loss=0.188, lr=0.0001]
Steps:  95%|█████████▌| 1905/2000 [57:09<02:44,  1.73s/it, loss=0.115, lr=0.0001]
Steps:  95%|█████████▌| 1906/2000 [57:09<02:40,  1.71s/it, loss=0.115, lr=0.0001]
Steps:  95%|█████████▌| 1906/2000 [57:09<02:40,  1.71s/it, loss=0.131, lr=0.0001]
Steps:  95%|█████████▌| 1906/2000 [57:10<02:40,  1.71s/it, loss=0.175, lr=0.0001]
Steps:  95%|█████████▌| 1906/2000 [57:10<02:40,  1.71s/it, loss=0.178, lr=0.0001]
Steps:  95%|█████████▌| 1906/2000 [57:10<02:40,  1.71s/it, loss=0.111, lr=0.0001]
Steps:  95%|█████████▌| 1907/2000 [57:11<02:44,  1.77s/it, loss=0.111, lr=0.0001]
Steps:  95%|█████████▌| 1907/2000 [57:11<02:44,  1.77s/it, loss=0.181, lr=0.0001]
Steps:  95%|█████████▌| 1907/2000 [57:12<02:44,  1.77s/it, loss=0.163, lr=0.0001]
Steps:  95%|█████████▌| 1907/2000 [57:12<02:44,  1.77s/it, loss=0.197, lr=0.0001]
Steps:  95%|█████████▌| 1907/2000 [57:12<02:44,  1.77s/it, loss=0.255, lr=0.0001]
Steps:  95%|█████████▌| 1908/2000 [57:13<02:40,  1.74s/it, loss=0.255, lr=0.0001]
Steps:  95%|█████████▌| 1908/2000 [57:13<02:40,  1.74s/it, loss=0.182, lr=0.0001]
Steps:  95%|█████████▌| 1908/2000 [57:13<02:40,  1.74s/it, loss=0.163, lr=0.0001]
Steps:  95%|█████████▌| 1908/2000 [57:14<02:40,  1.74s/it, loss=0.144, lr=0.0001]
Steps:  95%|█████████▌| 1908/2000 [57:14<02:40,  1.74s/it, loss=0.312, lr=0.0001]
Steps:  95%|█████████▌| 1909/2000 [57:15<02:38,  1.74s/it, loss=0.312, lr=0.0001]
Steps:  95%|█████████▌| 1909/2000 [57:15<02:38,  1.74s/it, loss=0.108, lr=0.0001]
Steps:  95%|█████████▌| 1909/2000 [57:15<02:38,  1.74s/it, loss=0.205, lr=0.0001]
Steps:  95%|█████████▌| 1909/2000 [57:15<02:38,  1.74s/it, loss=0.183, lr=0.0001]
Steps:  95%|█████████▌| 1909/2000 [57:16<02:38,  1.74s/it, loss=0.0796, lr=0.0001]
Steps:  96%|█████████▌| 1910/2000 [57:16<02:41,  1.79s/it, loss=0.0796, lr=0.0001]
Steps:  96%|█████████▌| 1910/2000 [57:16<02:41,  1.79s/it, loss=0.275, lr=0.0001] 
Steps:  96%|█████████▌| 1910/2000 [57:17<02:41,  1.79s/it, loss=0.197, lr=0.0001]
Steps:  96%|█████████▌| 1910/2000 [57:17<02:41,  1.79s/it, loss=0.247, lr=0.0001]
Steps:  96%|█████████▌| 1910/2000 [57:18<02:41,  1.79s/it, loss=0.169, lr=0.0001]
Steps:  96%|█████████▌| 1911/2000 [57:18<02:35,  1.74s/it, loss=0.169, lr=0.0001]
Steps:  96%|█████████▌| 1911/2000 [57:18<02:35,  1.74s/it, loss=0.12, lr=0.0001] 
Steps:  96%|█████████▌| 1911/2000 [57:18<02:35,  1.74s/it, loss=0.786, lr=0.0001]
Steps:  96%|█████████▌| 1911/2000 [57:19<02:35,  1.74s/it, loss=0.212, lr=0.0001]
Steps:  96%|█████████▌| 1911/2000 [57:19<02:35,  1.74s/it, loss=0.244, lr=0.0001]
Steps:  96%|█████████▌| 1912/2000 [57:20<02:30,  1.71s/it, loss=0.244, lr=0.0001]
Steps:  96%|█████████▌| 1912/2000 [57:20<02:30,  1.71s/it, loss=1.16, lr=0.0001] 
Steps:  96%|█████████▌| 1912/2000 [57:20<02:30,  1.71s/it, loss=0.168, lr=0.0001]
Steps:  96%|█████████▌| 1912/2000 [57:20<02:30,  1.71s/it, loss=0.795, lr=0.0001]
Steps:  96%|█████████▌| 1912/2000 [57:21<02:30,  1.71s/it, loss=0.474, lr=0.0001]
Steps:  96%|█████████▌| 1913/2000 [57:21<02:27,  1.69s/it, loss=0.474, lr=0.0001]
Steps:  96%|█████████▌| 1913/2000 [57:21<02:27,  1.69s/it, loss=0.225, lr=0.0001]
Steps:  96%|█████████▌| 1913/2000 [57:22<02:27,  1.69s/it, loss=0.152, lr=0.0001]
Steps:  96%|█████████▌| 1913/2000 [57:22<02:27,  1.69s/it, loss=0.347, lr=0.0001]
Steps:  96%|█████████▌| 1913/2000 [57:23<02:27,  1.69s/it, loss=0.198, lr=0.0001]
Steps:  96%|█████████▌| 1914/2000 [57:23<02:30,  1.74s/it, loss=0.198, lr=0.0001]
Steps:  96%|█████████▌| 1914/2000 [57:23<02:30,  1.74s/it, loss=0.07, lr=0.0001] 
Steps:  96%|█████████▌| 1914/2000 [57:24<02:30,  1.74s/it, loss=0.226, lr=0.0001]
Steps:  96%|█████████▌| 1914/2000 [57:24<02:30,  1.74s/it, loss=0.108, lr=0.0001]
Steps:  96%|█████████▌| 1914/2000 [57:24<02:30,  1.74s/it, loss=0.277, lr=0.0001]
Steps:  96%|█████████▌| 1915/2000 [57:25<02:25,  1.71s/it, loss=0.277, lr=0.0001]
Steps:  96%|█████████▌| 1915/2000 [57:25<02:25,  1.71s/it, loss=0.196, lr=0.0001]
Steps:  96%|█████████▌| 1915/2000 [57:25<02:25,  1.71s/it, loss=0.201, lr=0.0001]
Steps:  96%|█████████▌| 1915/2000 [57:26<02:25,  1.71s/it, loss=0.295, lr=0.0001]
Steps:  96%|█████████▌| 1915/2000 [57:26<02:25,  1.71s/it, loss=0.144, lr=0.0001]
Steps:  96%|█████████▌| 1916/2000 [57:26<02:21,  1.69s/it, loss=0.144, lr=0.0001]
Steps:  96%|█████████▌| 1916/2000 [57:26<02:21,  1.69s/it, loss=0.839, lr=0.0001]
Steps:  96%|█████████▌| 1916/2000 [57:27<02:21,  1.69s/it, loss=0.109, lr=0.0001]
Steps:  96%|█████████▌| 1916/2000 [57:28<02:21,  1.69s/it, loss=0.26, lr=0.0001] 
Steps:  96%|█████████▌| 1916/2000 [57:28<02:21,  1.69s/it, loss=0.349, lr=0.0001]
Steps:  96%|█████████▌| 1917/2000 [57:28<02:24,  1.75s/it, loss=0.349, lr=0.0001]
Steps:  96%|█████████▌| 1917/2000 [57:28<02:24,  1.75s/it, loss=0.283, lr=0.0001]
Steps:  96%|█████████▌| 1917/2000 [57:29<02:24,  1.75s/it, loss=0.651, lr=0.0001]
Steps:  96%|█████████▌| 1917/2000 [57:29<02:24,  1.75s/it, loss=0.311, lr=0.0001]
Steps:  96%|█████████▌| 1917/2000 [57:30<02:24,  1.75s/it, loss=0.127, lr=0.0001]
Steps:  96%|█████████▌| 1918/2000 [57:30<02:20,  1.71s/it, loss=0.127, lr=0.0001]
Steps:  96%|█████████▌| 1918/2000 [57:30<02:20,  1.71s/it, loss=0.0925, lr=0.0001]
Steps:  96%|█████████▌| 1918/2000 [57:30<02:20,  1.71s/it, loss=0.175, lr=0.0001] 
Steps:  96%|█████████▌| 1918/2000 [57:31<02:20,  1.71s/it, loss=0.206, lr=0.0001]
Steps:  96%|█████████▌| 1918/2000 [57:31<02:20,  1.71s/it, loss=0.0907, lr=0.0001]
Steps:  96%|█████████▌| 1919/2000 [57:32<02:17,  1.69s/it, loss=0.0907, lr=0.0001]
Steps:  96%|█████████▌| 1919/2000 [57:32<02:17,  1.69s/it, loss=0.109, lr=0.0001] 
Steps:  96%|█████████▌| 1919/2000 [57:32<02:17,  1.69s/it, loss=0.134, lr=0.0001]
Steps:  96%|█████████▌| 1919/2000 [57:33<02:17,  1.69s/it, loss=0.091, lr=0.0001]
Steps:  96%|█████████▌| 1919/2000 [57:33<02:17,  1.69s/it, loss=0.236, lr=0.0001]
Steps:  96%|█████████▌| 1920/2000 [57:34<02:20,  1.76s/it, loss=0.236, lr=0.0001]
Steps:  96%|█████████▌| 1920/2000 [57:34<02:20,  1.76s/it, loss=0.155, lr=0.0001]
Steps:  96%|█████████▌| 1920/2000 [57:34<02:20,  1.76s/it, loss=0.253, lr=0.0001]
Steps:  96%|█████████▌| 1920/2000 [57:34<02:20,  1.76s/it, loss=0.081, lr=0.0001]
Steps:  96%|█████████▌| 1920/2000 [57:35<02:20,  1.76s/it, loss=0.35, lr=0.0001] 
Steps:  96%|█████████▌| 1921/2000 [57:35<02:16,  1.72s/it, loss=0.35, lr=0.0001]
Steps:  96%|█████████▌| 1921/2000 [57:35<02:16,  1.72s/it, loss=0.199, lr=0.0001]
Steps:  96%|█████████▌| 1921/2000 [57:36<02:16,  1.72s/it, loss=0.199, lr=0.0001]
Steps:  96%|█████████▌| 1921/2000 [57:36<02:16,  1.72s/it, loss=0.18, lr=0.0001] 
Steps:  96%|█████████▌| 1921/2000 [57:36<02:16,  1.72s/it, loss=0.223, lr=0.0001]
Steps:  96%|█████████▌| 1922/2000 [57:37<02:12,  1.70s/it, loss=0.223, lr=0.0001]
Steps:  96%|█████████▌| 1922/2000 [57:37<02:12,  1.70s/it, loss=0.12, lr=0.0001] 
Steps:  96%|█████████▌| 1922/2000 [57:37<02:12,  1.70s/it, loss=0.879, lr=0.0001]
Steps:  96%|█████████▌| 1922/2000 [57:38<02:12,  1.70s/it, loss=0.156, lr=0.0001]
Steps:  96%|█████████▌| 1922/2000 [57:38<02:12,  1.70s/it, loss=0.218, lr=0.0001]
Steps:  96%|█████████▌| 1923/2000 [57:39<02:15,  1.76s/it, loss=0.218, lr=0.0001]
Steps:  96%|█████████▌| 1923/2000 [57:39<02:15,  1.76s/it, loss=0.349, lr=0.0001]
Steps:  96%|█████████▌| 1923/2000 [57:39<02:15,  1.76s/it, loss=0.166, lr=0.0001]
Steps:  96%|█████████▌| 1923/2000 [57:40<02:15,  1.76s/it, loss=0.0742, lr=0.0001]
Steps:  96%|█████████▌| 1923/2000 [57:40<02:15,  1.76s/it, loss=0.262, lr=0.0001] 
Steps:  96%|█████████▌| 1924/2000 [57:40<02:11,  1.73s/it, loss=0.262, lr=0.0001]
Steps:  96%|█████████▌| 1924/2000 [57:40<02:11,  1.73s/it, loss=0.258, lr=0.0001]
Steps:  96%|█████████▌| 1924/2000 [57:41<02:11,  1.73s/it, loss=0.159, lr=0.0001]
Steps:  96%|█████████▌| 1924/2000 [57:41<02:11,  1.73s/it, loss=0.221, lr=0.0001]
Steps:  96%|█████████▌| 1924/2000 [57:42<02:11,  1.73s/it, loss=0.131, lr=0.0001]
Steps:  96%|█████████▋| 1925/2000 [57:42<02:07,  1.70s/it, loss=0.131, lr=0.0001]
Steps:  96%|█████████▋| 1925/2000 [57:42<02:07,  1.70s/it, loss=0.4, lr=0.0001]  
Steps:  96%|█████████▋| 1925/2000 [57:42<02:07,  1.70s/it, loss=0.173, lr=0.0001]
Steps:  96%|█████████▋| 1925/2000 [57:43<02:07,  1.70s/it, loss=0.771, lr=0.0001]
Steps:  96%|█████████▋| 1925/2000 [57:43<02:07,  1.70s/it, loss=0.921, lr=0.0001]
Steps:  96%|█████████▋| 1926/2000 [57:44<02:10,  1.76s/it, loss=0.921, lr=0.0001]
Steps:  96%|█████████▋| 1926/2000 [57:44<02:10,  1.76s/it, loss=0.171, lr=0.0001]
Steps:  96%|█████████▋| 1926/2000 [57:44<02:10,  1.76s/it, loss=0.0857, lr=0.0001]
Steps:  96%|█████████▋| 1926/2000 [57:45<02:10,  1.76s/it, loss=0.165, lr=0.0001] 
Steps:  96%|█████████▋| 1926/2000 [57:45<02:10,  1.76s/it, loss=0.306, lr=0.0001]
Steps:  96%|█████████▋| 1927/2000 [57:46<02:06,  1.74s/it, loss=0.306, lr=0.0001]
Steps:  96%|█████████▋| 1927/2000 [57:46<02:06,  1.74s/it, loss=0.338, lr=0.0001]
Steps:  96%|█████████▋| 1927/2000 [57:46<02:06,  1.74s/it, loss=0.275, lr=0.0001]
Steps:  96%|█████████▋| 1927/2000 [57:46<02:06,  1.74s/it, loss=0.152, lr=0.0001]
Steps:  96%|█████████▋| 1927/2000 [57:47<02:06,  1.74s/it, loss=0.139, lr=0.0001]
Steps:  96%|█████████▋| 1928/2000 [57:47<02:03,  1.71s/it, loss=0.139, lr=0.0001]
Steps:  96%|█████████▋| 1928/2000 [57:47<02:03,  1.71s/it, loss=0.307, lr=0.0001]
Steps:  96%|█████████▋| 1928/2000 [57:48<02:03,  1.71s/it, loss=0.274, lr=0.0001]
Steps:  96%|█████████▋| 1928/2000 [57:48<02:03,  1.71s/it, loss=0.11, lr=0.0001] 
Steps:  96%|█████████▋| 1928/2000 [57:48<02:03,  1.71s/it, loss=0.162, lr=0.0001]
Steps:  96%|█████████▋| 1929/2000 [57:49<02:01,  1.71s/it, loss=0.162, lr=0.0001]
Steps:  96%|█████████▋| 1929/2000 [57:49<02:01,  1.71s/it, loss=0.188, lr=0.0001]
Steps:  96%|█████████▋| 1929/2000 [57:50<02:01,  1.71s/it, loss=0.154, lr=0.0001]
Steps:  96%|█████████▋| 1929/2000 [57:50<02:01,  1.71s/it, loss=0.151, lr=0.0001]
Steps:  96%|█████████▋| 1929/2000 [57:50<02:01,  1.71s/it, loss=0.141, lr=0.0001]
Steps:  96%|█████████▋| 1930/2000 [57:51<02:03,  1.77s/it, loss=0.141, lr=0.0001]
Steps:  96%|█████████▋| 1930/2000 [57:51<02:03,  1.77s/it, loss=0.133, lr=0.0001]
Steps:  96%|█████████▋| 1930/2000 [57:51<02:03,  1.77s/it, loss=0.317, lr=0.0001]
Steps:  96%|█████████▋| 1930/2000 [57:52<02:03,  1.77s/it, loss=0.617, lr=0.0001]
Steps:  96%|█████████▋| 1930/2000 [57:52<02:03,  1.77s/it, loss=0.18, lr=0.0001] 
Steps:  97%|█████████▋| 1931/2000 [57:53<01:59,  1.73s/it, loss=0.18, lr=0.0001]
Steps:  97%|█████████▋| 1931/2000 [57:53<01:59,  1.73s/it, loss=0.105, lr=0.0001]
Steps:  97%|█████████▋| 1931/2000 [57:53<01:59,  1.73s/it, loss=0.239, lr=0.0001]
Steps:  97%|█████████▋| 1931/2000 [57:53<01:59,  1.73s/it, loss=0.106, lr=0.0001]
Steps:  97%|█████████▋| 1931/2000 [57:54<01:59,  1.73s/it, loss=0.125, lr=0.0001]
Steps:  97%|█████████▋| 1932/2000 [57:54<01:55,  1.70s/it, loss=0.125, lr=0.0001]
Steps:  97%|█████████▋| 1932/2000 [57:54<01:55,  1.70s/it, loss=0.105, lr=0.0001]
Steps:  97%|█████████▋| 1932/2000 [57:55<01:55,  1.70s/it, loss=0.647, lr=0.0001]
Steps:  97%|█████████▋| 1932/2000 [57:55<01:55,  1.70s/it, loss=0.273, lr=0.0001]
Steps:  97%|█████████▋| 1932/2000 [57:56<01:55,  1.70s/it, loss=0.254, lr=0.0001]
Steps:  97%|█████████▋| 1933/2000 [57:56<01:57,  1.76s/it, loss=0.254, lr=0.0001]
Steps:  97%|█████████▋| 1933/2000 [57:56<01:57,  1.76s/it, loss=0.289, lr=0.0001]
Steps:  97%|█████████▋| 1933/2000 [57:56<01:57,  1.76s/it, loss=0.154, lr=0.0001]
Steps:  97%|█████████▋| 1933/2000 [57:57<01:57,  1.76s/it, loss=0.109, lr=0.0001]
Steps:  97%|█████████▋| 1933/2000 [57:57<01:57,  1.76s/it, loss=0.13, lr=0.0001] 
Steps:  97%|█████████▋| 1934/2000 [57:58<01:53,  1.73s/it, loss=0.13, lr=0.0001]
Steps:  97%|█████████▋| 1934/2000 [57:58<01:53,  1.73s/it, loss=0.719, lr=0.0001]
Steps:  97%|█████████▋| 1934/2000 [57:58<01:53,  1.73s/it, loss=0.241, lr=0.0001]
Steps:  97%|█████████▋| 1934/2000 [57:58<01:53,  1.73s/it, loss=0.158, lr=0.0001]
Steps:  97%|█████████▋| 1934/2000 [57:59<01:53,  1.73s/it, loss=0.143, lr=0.0001]
Steps:  97%|█████████▋| 1935/2000 [57:59<01:50,  1.70s/it, loss=0.143, lr=0.0001]
Steps:  97%|█████████▋| 1935/2000 [57:59<01:50,  1.70s/it, loss=0.126, lr=0.0001]
Steps:  97%|█████████▋| 1935/2000 [58:00<01:50,  1.70s/it, loss=0.221, lr=0.0001]
Steps:  97%|█████████▋| 1935/2000 [58:00<01:50,  1.70s/it, loss=0.238, lr=0.0001]
Steps:  97%|█████████▋| 1935/2000 [58:01<01:50,  1.70s/it, loss=0.185, lr=0.0001]
Steps:  97%|█████████▋| 1936/2000 [58:01<01:52,  1.75s/it, loss=0.185, lr=0.0001]
Steps:  97%|█████████▋| 1936/2000 [58:01<01:52,  1.75s/it, loss=0.219, lr=0.0001]
Steps:  97%|█████████▋| 1936/2000 [58:02<01:52,  1.75s/it, loss=0.251, lr=0.0001]
Steps:  97%|█████████▋| 1936/2000 [58:02<01:52,  1.75s/it, loss=0.151, lr=0.0001]
Steps:  97%|█████████▋| 1936/2000 [58:02<01:52,  1.75s/it, loss=0.259, lr=0.0001]
Steps:  97%|█████████▋| 1937/2000 [58:03<01:48,  1.72s/it, loss=0.259, lr=0.0001]
Steps:  97%|█████████▋| 1937/2000 [58:03<01:48,  1.72s/it, loss=0.352, lr=0.0001]
Steps:  97%|█████████▋| 1937/2000 [58:03<01:48,  1.72s/it, loss=0.25, lr=0.0001] 
Steps:  97%|█████████▋| 1937/2000 [58:04<01:48,  1.72s/it, loss=0.184, lr=0.0001]
Steps:  97%|█████████▋| 1937/2000 [58:04<01:48,  1.72s/it, loss=0.395, lr=0.0001]
Steps:  97%|█████████▋| 1938/2000 [58:05<01:45,  1.70s/it, loss=0.395, lr=0.0001]
Steps:  97%|█████████▋| 1938/2000 [58:05<01:45,  1.70s/it, loss=0.202, lr=0.0001]
Steps:  97%|█████████▋| 1938/2000 [58:05<01:45,  1.70s/it, loss=0.0824, lr=0.0001]
Steps:  97%|█████████▋| 1938/2000 [58:06<01:45,  1.70s/it, loss=0.16, lr=0.0001]  
Steps:  97%|█████████▋| 1938/2000 [58:06<01:45,  1.70s/it, loss=0.212, lr=0.0001]
Steps:  97%|█████████▋| 1939/2000 [58:06<01:47,  1.76s/it, loss=0.212, lr=0.0001]
Steps:  97%|█████████▋| 1939/2000 [58:06<01:47,  1.76s/it, loss=0.0789, lr=0.0001]
Steps:  97%|█████████▋| 1939/2000 [58:07<01:47,  1.76s/it, loss=0.902, lr=0.0001] 
Steps:  97%|█████████▋| 1939/2000 [58:07<01:47,  1.76s/it, loss=0.147, lr=0.0001]
Steps:  97%|█████████▋| 1939/2000 [58:08<01:47,  1.76s/it, loss=0.142, lr=0.0001]
Steps:  97%|█████████▋| 1940/2000 [58:08<01:44,  1.75s/it, loss=0.142, lr=0.0001]
Steps:  97%|█████████▋| 1940/2000 [58:08<01:44,  1.75s/it, loss=0.159, lr=0.0001]
Steps:  97%|█████████▋| 1940/2000 [58:09<01:44,  1.75s/it, loss=0.35, lr=0.0001] 
Steps:  97%|█████████▋| 1940/2000 [58:09<01:44,  1.75s/it, loss=0.138, lr=0.0001]
Steps:  97%|█████████▋| 1940/2000 [58:09<01:44,  1.75s/it, loss=0.203, lr=0.0001]
Steps:  97%|█████████▋| 1941/2000 [58:10<01:41,  1.72s/it, loss=0.203, lr=0.0001]
Steps:  97%|█████████▋| 1941/2000 [58:10<01:41,  1.72s/it, loss=0.168, lr=0.0001]
Steps:  97%|█████████▋| 1941/2000 [58:10<01:41,  1.72s/it, loss=0.164, lr=0.0001]
Steps:  97%|█████████▋| 1941/2000 [58:11<01:41,  1.72s/it, loss=0.23, lr=0.0001] 
Steps:  97%|█████████▋| 1941/2000 [58:11<01:41,  1.72s/it, loss=0.271, lr=0.0001]
Steps:  97%|█████████▋| 1942/2000 [58:12<01:42,  1.77s/it, loss=0.271, lr=0.0001]
Steps:  97%|█████████▋| 1942/2000 [58:12<01:42,  1.77s/it, loss=0.162, lr=0.0001]
Steps:  97%|█████████▋| 1942/2000 [58:12<01:42,  1.77s/it, loss=0.172, lr=0.0001]
Steps:  97%|█████████▋| 1942/2000 [58:12<01:42,  1.77s/it, loss=0.11, lr=0.0001] 
Steps:  97%|█████████▋| 1942/2000 [58:13<01:42,  1.77s/it, loss=0.0671, lr=0.0001]
Steps:  97%|█████████▋| 1943/2000 [58:13<01:40,  1.76s/it, loss=0.0671, lr=0.0001]
Steps:  97%|█████████▋| 1943/2000 [58:13<01:40,  1.76s/it, loss=0.235, lr=0.0001] 
Steps:  97%|█████████▋| 1943/2000 [58:14<01:40,  1.76s/it, loss=0.0959, lr=0.0001]
Steps:  97%|█████████▋| 1943/2000 [58:14<01:40,  1.76s/it, loss=0.219, lr=0.0001] 
Steps:  97%|█████████▋| 1943/2000 [58:15<01:40,  1.76s/it, loss=0.192, lr=0.0001]
Steps:  97%|█████████▋| 1944/2000 [58:15<01:37,  1.74s/it, loss=0.192, lr=0.0001]
Steps:  97%|█████████▋| 1944/2000 [58:15<01:37,  1.74s/it, loss=0.142, lr=0.0001]
Steps:  97%|█████████▋| 1944/2000 [58:15<01:37,  1.74s/it, loss=0.0775, lr=0.0001]
Steps:  97%|█████████▋| 1944/2000 [58:16<01:37,  1.74s/it, loss=0.0608, lr=0.0001]
Steps:  97%|█████████▋| 1944/2000 [58:16<01:37,  1.74s/it, loss=0.0977, lr=0.0001]
Steps:  97%|█████████▋| 1945/2000 [58:17<01:38,  1.78s/it, loss=0.0977, lr=0.0001]
Steps:  97%|█████████▋| 1945/2000 [58:17<01:38,  1.78s/it, loss=0.128, lr=0.0001] 
Steps:  97%|█████████▋| 1945/2000 [58:17<01:38,  1.78s/it, loss=0.262, lr=0.0001]
Steps:  97%|█████████▋| 1945/2000 [58:18<01:38,  1.78s/it, loss=0.189, lr=0.0001]
Steps:  97%|█████████▋| 1945/2000 [58:18<01:38,  1.78s/it, loss=0.149, lr=0.0001]
Steps:  97%|█████████▋| 1946/2000 [58:19<01:34,  1.75s/it, loss=0.149, lr=0.0001]
Steps:  97%|█████████▋| 1946/2000 [58:19<01:34,  1.75s/it, loss=0.368, lr=0.0001]
Steps:  97%|█████████▋| 1946/2000 [58:19<01:34,  1.75s/it, loss=0.118, lr=0.0001]
Steps:  97%|█████████▋| 1946/2000 [58:19<01:34,  1.75s/it, loss=0.339, lr=0.0001]
Steps:  97%|█████████▋| 1946/2000 [58:20<01:34,  1.75s/it, loss=0.53, lr=0.0001] 
Steps:  97%|█████████▋| 1947/2000 [58:20<01:31,  1.72s/it, loss=0.53, lr=0.0001]
Steps:  97%|█████████▋| 1947/2000 [58:20<01:31,  1.72s/it, loss=0.225, lr=0.0001]
Steps:  97%|█████████▋| 1947/2000 [58:21<01:31,  1.72s/it, loss=0.156, lr=0.0001]
Steps:  97%|█████████▋| 1947/2000 [58:21<01:31,  1.72s/it, loss=0.139, lr=0.0001]
Steps:  97%|█████████▋| 1947/2000 [58:22<01:31,  1.72s/it, loss=0.124, lr=0.0001]
Steps:  97%|█████████▋| 1948/2000 [58:22<01:28,  1.71s/it, loss=0.124, lr=0.0001]
Steps:  97%|█████████▋| 1948/2000 [58:22<01:28,  1.71s/it, loss=0.0806, lr=0.0001]
Steps:  97%|█████████▋| 1948/2000 [58:23<01:28,  1.71s/it, loss=0.213, lr=0.0001] 
Steps:  97%|█████████▋| 1948/2000 [58:23<01:28,  1.71s/it, loss=0.116, lr=0.0001]
Steps:  97%|█████████▋| 1948/2000 [58:23<01:28,  1.71s/it, loss=0.229, lr=0.0001]
Steps:  97%|█████████▋| 1949/2000 [58:24<01:29,  1.76s/it, loss=0.229, lr=0.0001]
Steps:  97%|█████████▋| 1949/2000 [58:24<01:29,  1.76s/it, loss=0.225, lr=0.0001]
Steps:  97%|█████████▋| 1949/2000 [58:24<01:29,  1.76s/it, loss=0.2, lr=0.0001]  
Steps:  97%|█████████▋| 1949/2000 [58:25<01:29,  1.76s/it, loss=0.191, lr=0.0001]
Steps:  97%|█████████▋| 1949/2000 [58:25<01:29,  1.76s/it, loss=0.414, lr=0.0001]
Steps:  98%|█████████▊| 1950/2000 [58:25<01:26,  1.72s/it, loss=0.414, lr=0.0001]
Steps:  98%|█████████▊| 1950/2000 [58:25<01:26,  1.72s/it, loss=0.306, lr=0.0001]
Steps:  98%|█████████▊| 1950/2000 [58:26<01:26,  1.72s/it, loss=0.28, lr=0.0001] 
Steps:  98%|█████████▊| 1950/2000 [58:26<01:26,  1.72s/it, loss=0.171, lr=0.0001]
Steps:  98%|█████████▊| 1950/2000 [58:27<01:26,  1.72s/it, loss=0.207, lr=0.0001]
Steps:  98%|█████████▊| 1951/2000 [58:27<01:23,  1.70s/it, loss=0.207, lr=0.0001]
Steps:  98%|█████████▊| 1951/2000 [58:27<01:23,  1.70s/it, loss=0.171, lr=0.0001]
Steps:  98%|█████████▊| 1951/2000 [58:28<01:23,  1.70s/it, loss=0.171, lr=0.0001]
Steps:  98%|█████████▊| 1951/2000 [58:28<01:23,  1.70s/it, loss=0.166, lr=0.0001]
Steps:  98%|█████████▊| 1951/2000 [58:29<01:23,  1.70s/it, loss=0.343, lr=0.0001]
Steps:  98%|█████████▊| 1952/2000 [58:29<01:23,  1.75s/it, loss=0.343, lr=0.0001]
Steps:  98%|█████████▊| 1952/2000 [58:29<01:23,  1.75s/it, loss=0.147, lr=0.0001]
Steps:  98%|█████████▊| 1952/2000 [58:29<01:23,  1.75s/it, loss=0.172, lr=0.0001]
Steps:  98%|█████████▊| 1952/2000 [58:30<01:23,  1.75s/it, loss=0.122, lr=0.0001]
Steps:  98%|█████████▊| 1952/2000 [58:30<01:23,  1.75s/it, loss=0.166, lr=0.0001]
Steps:  98%|█████████▊| 1953/2000 [58:31<01:20,  1.72s/it, loss=0.166, lr=0.0001]
Steps:  98%|█████████▊| 1953/2000 [58:31<01:20,  1.72s/it, loss=0.132, lr=0.0001]
Steps:  98%|█████████▊| 1953/2000 [58:31<01:20,  1.72s/it, loss=0.186, lr=0.0001]
Steps:  98%|█████████▊| 1953/2000 [58:31<01:20,  1.72s/it, loss=0.193, lr=0.0001]
Steps:  98%|█████████▊| 1953/2000 [58:32<01:20,  1.72s/it, loss=0.114, lr=0.0001]
Steps:  98%|█████████▊| 1954/2000 [58:32<01:18,  1.71s/it, loss=0.114, lr=0.0001]
Steps:  98%|█████████▊| 1954/2000 [58:32<01:18,  1.71s/it, loss=0.18, lr=0.0001] 
Steps:  98%|█████████▊| 1954/2000 [58:33<01:18,  1.71s/it, loss=0.711, lr=0.0001]
Steps:  98%|█████████▊| 1954/2000 [58:33<01:18,  1.71s/it, loss=0.228, lr=0.0001]
Steps:  98%|█████████▊| 1954/2000 [58:34<01:18,  1.71s/it, loss=0.0792, lr=0.0001]
Steps:  98%|█████████▊| 1955/2000 [58:34<01:20,  1.78s/it, loss=0.0792, lr=0.0001]
Steps:  98%|█████████▊| 1955/2000 [58:34<01:20,  1.78s/it, loss=0.265, lr=0.0001] 
Steps:  98%|█████████▊| 1955/2000 [58:35<01:20,  1.78s/it, loss=0.116, lr=0.0001]
Steps:  98%|█████████▊| 1955/2000 [58:35<01:20,  1.78s/it, loss=0.131, lr=0.0001]
Steps:  98%|█████████▊| 1955/2000 [58:35<01:20,  1.78s/it, loss=0.0732, lr=0.0001]
Steps:  98%|█████████▊| 1956/2000 [58:36<01:16,  1.74s/it, loss=0.0732, lr=0.0001]
Steps:  98%|█████████▊| 1956/2000 [58:36<01:16,  1.74s/it, loss=0.461, lr=0.0001] 
Steps:  98%|█████████▊| 1956/2000 [58:36<01:16,  1.74s/it, loss=0.503, lr=0.0001]
Steps:  98%|█████████▊| 1956/2000 [58:37<01:16,  1.74s/it, loss=0.178, lr=0.0001]
Steps:  98%|█████████▊| 1956/2000 [58:37<01:16,  1.74s/it, loss=0.0604, lr=0.0001]
Steps:  98%|█████████▊| 1957/2000 [58:38<01:13,  1.72s/it, loss=0.0604, lr=0.0001]
Steps:  98%|█████████▊| 1957/2000 [58:38<01:13,  1.72s/it, loss=0.184, lr=0.0001] 
Steps:  98%|█████████▊| 1957/2000 [58:38<01:13,  1.72s/it, loss=0.212, lr=0.0001]
Steps:  98%|█████████▊| 1957/2000 [58:39<01:13,  1.72s/it, loss=0.134, lr=0.0001]
Steps:  98%|█████████▊| 1957/2000 [58:39<01:13,  1.72s/it, loss=0.237, lr=0.0001]
Steps:  98%|█████████▊| 1958/2000 [58:40<01:15,  1.79s/it, loss=0.237, lr=0.0001]
Steps:  98%|█████████▊| 1958/2000 [58:40<01:15,  1.79s/it, loss=0.248, lr=0.0001]
Steps:  98%|█████████▊| 1958/2000 [58:40<01:15,  1.79s/it, loss=0.24, lr=0.0001] 
Steps:  98%|█████████▊| 1958/2000 [58:40<01:15,  1.79s/it, loss=0.135, lr=0.0001]
Steps:  98%|█████████▊| 1958/2000 [58:41<01:15,  1.79s/it, loss=0.181, lr=0.0001]
Steps:  98%|█████████▊| 1959/2000 [58:41<01:11,  1.76s/it, loss=0.181, lr=0.0001]
Steps:  98%|█████████▊| 1959/2000 [58:41<01:11,  1.76s/it, loss=0.0938, lr=0.0001]
Steps:  98%|█████████▊| 1959/2000 [58:42<01:11,  1.76s/it, loss=0.179, lr=0.0001] 
Steps:  98%|█████████▊| 1959/2000 [58:42<01:11,  1.76s/it, loss=0.174, lr=0.0001]
Steps:  98%|█████████▊| 1959/2000 [58:42<01:11,  1.76s/it, loss=0.149, lr=0.0001]
Steps:  98%|█████████▊| 1960/2000 [58:43<01:09,  1.75s/it, loss=0.149, lr=0.0001]
Steps:  98%|█████████▊| 1960/2000 [58:43<01:09,  1.75s/it, loss=0.172, lr=0.0001]
Steps:  98%|█████████▊| 1960/2000 [58:43<01:09,  1.75s/it, loss=0.171, lr=0.0001]
Steps:  98%|█████████▊| 1960/2000 [58:44<01:09,  1.75s/it, loss=0.122, lr=0.0001]
Steps:  98%|█████████▊| 1960/2000 [58:44<01:09,  1.75s/it, loss=0.105, lr=0.0001]
Steps:  98%|█████████▊| 1961/2000 [58:45<01:10,  1.80s/it, loss=0.105, lr=0.0001]
Steps:  98%|█████████▊| 1961/2000 [58:45<01:10,  1.80s/it, loss=0.135, lr=0.0001]
Steps:  98%|█████████▊| 1961/2000 [58:45<01:10,  1.80s/it, loss=0.179, lr=0.0001]
Steps:  98%|█████████▊| 1961/2000 [58:46<01:10,  1.80s/it, loss=0.419, lr=0.0001]
Steps:  98%|█████████▊| 1961/2000 [58:46<01:10,  1.80s/it, loss=0.147, lr=0.0001]
Steps:  98%|█████████▊| 1962/2000 [58:47<01:07,  1.78s/it, loss=0.147, lr=0.0001]
Steps:  98%|█████████▊| 1962/2000 [58:47<01:07,  1.78s/it, loss=0.159, lr=0.0001]
Steps:  98%|█████████▊| 1962/2000 [58:47<01:07,  1.78s/it, loss=0.273, lr=0.0001]
Steps:  98%|█████████▊| 1962/2000 [58:47<01:07,  1.78s/it, loss=0.228, lr=0.0001]
Steps:  98%|█████████▊| 1962/2000 [58:48<01:07,  1.78s/it, loss=0.0749, lr=0.0001]
Steps:  98%|█████████▊| 1963/2000 [58:48<01:04,  1.75s/it, loss=0.0749, lr=0.0001]
Steps:  98%|█████████▊| 1963/2000 [58:48<01:04,  1.75s/it, loss=0.196, lr=0.0001] 
Steps:  98%|█████████▊| 1963/2000 [58:49<01:04,  1.75s/it, loss=0.205, lr=0.0001]
Steps:  98%|█████████▊| 1963/2000 [58:49<01:04,  1.75s/it, loss=1.03, lr=0.0001] 
Steps:  98%|█████████▊| 1963/2000 [58:50<01:04,  1.75s/it, loss=1.04, lr=0.0001]
Steps:  98%|█████████▊| 1964/2000 [58:50<01:05,  1.82s/it, loss=1.04, lr=0.0001]
Steps:  98%|█████████▊| 1964/2000 [58:50<01:05,  1.82s/it, loss=0.093, lr=0.0001]
Steps:  98%|█████████▊| 1964/2000 [58:51<01:05,  1.82s/it, loss=0.0686, lr=0.0001]
Steps:  98%|█████████▊| 1964/2000 [58:51<01:05,  1.82s/it, loss=0.158, lr=0.0001] 
Steps:  98%|█████████▊| 1964/2000 [58:52<01:05,  1.82s/it, loss=0.28, lr=0.0001] 
Steps:  98%|█████████▊| 1965/2000 [58:52<01:02,  1.79s/it, loss=0.28, lr=0.0001]
Steps:  98%|█████████▊| 1965/2000 [58:52<01:02,  1.79s/it, loss=0.206, lr=0.0001]
Steps:  98%|█████████▊| 1965/2000 [58:52<01:02,  1.79s/it, loss=0.133, lr=0.0001]
Steps:  98%|█████████▊| 1965/2000 [58:53<01:02,  1.79s/it, loss=0.0935, lr=0.0001]
Steps:  98%|█████████▊| 1965/2000 [58:53<01:02,  1.79s/it, loss=0.173, lr=0.0001] 
Steps:  98%|█████████▊| 1966/2000 [58:54<00:59,  1.76s/it, loss=0.173, lr=0.0001]
Steps:  98%|█████████▊| 1966/2000 [58:54<00:59,  1.76s/it, loss=0.779, lr=0.0001]
Steps:  98%|█████████▊| 1966/2000 [58:54<00:59,  1.76s/it, loss=0.0698, lr=0.0001]
Steps:  98%|█████████▊| 1966/2000 [58:54<00:59,  1.76s/it, loss=0.141, lr=0.0001] 
Steps:  98%|█████████▊| 1966/2000 [58:55<00:59,  1.76s/it, loss=0.244, lr=0.0001]
Steps:  98%|█████████▊| 1967/2000 [58:56<00:59,  1.79s/it, loss=0.244, lr=0.0001]
Steps:  98%|█████████▊| 1967/2000 [58:56<00:59,  1.79s/it, loss=0.183, lr=0.0001]
Steps:  98%|█████████▊| 1967/2000 [58:56<00:59,  1.79s/it, loss=0.179, lr=0.0001]
Steps:  98%|█████████▊| 1967/2000 [58:56<00:59,  1.79s/it, loss=0.276, lr=0.0001]
Steps:  98%|█████████▊| 1967/2000 [58:57<00:59,  1.79s/it, loss=0.136, lr=0.0001]
Steps:  98%|█████████▊| 1968/2000 [58:57<00:56,  1.76s/it, loss=0.136, lr=0.0001]
Steps:  98%|█████████▊| 1968/2000 [58:57<00:56,  1.76s/it, loss=0.218, lr=0.0001]
Steps:  98%|█████████▊| 1968/2000 [58:58<00:56,  1.76s/it, loss=0.0498, lr=0.0001]
Steps:  98%|█████████▊| 1968/2000 [58:58<00:56,  1.76s/it, loss=0.475, lr=0.0001] 
Steps:  98%|█████████▊| 1968/2000 [58:58<00:56,  1.76s/it, loss=0.237, lr=0.0001]
Steps:  98%|█████████▊| 1969/2000 [58:59<00:54,  1.74s/it, loss=0.237, lr=0.0001]
Steps:  98%|█████████▊| 1969/2000 [58:59<00:54,  1.74s/it, loss=0.099, lr=0.0001]
Steps:  98%|█████████▊| 1969/2000 [58:59<00:54,  1.74s/it, loss=0.139, lr=0.0001]
Steps:  98%|█████████▊| 1969/2000 [59:00<00:54,  1.74s/it, loss=0.15, lr=0.0001] 
Steps:  98%|█████████▊| 1969/2000 [59:00<00:54,  1.74s/it, loss=0.156, lr=0.0001]
Steps:  98%|█████████▊| 1970/2000 [59:01<00:52,  1.74s/it, loss=0.156, lr=0.0001]
Steps:  98%|█████████▊| 1970/2000 [59:01<00:52,  1.74s/it, loss=0.256, lr=0.0001]
Steps:  98%|█████████▊| 1970/2000 [59:01<00:52,  1.74s/it, loss=0.179, lr=0.0001]
Steps:  98%|█████████▊| 1970/2000 [59:02<00:52,  1.74s/it, loss=1.28, lr=0.0001] 
Steps:  98%|█████████▊| 1970/2000 [59:02<00:52,  1.74s/it, loss=0.155, lr=0.0001]
Steps:  99%|█████████▊| 1971/2000 [59:03<00:51,  1.79s/it, loss=0.155, lr=0.0001]
Steps:  99%|█████████▊| 1971/2000 [59:03<00:51,  1.79s/it, loss=0.28, lr=0.0001] 
Steps:  99%|█████████▊| 1971/2000 [59:03<00:51,  1.79s/it, loss=0.0747, lr=0.0001]
Steps:  99%|█████████▊| 1971/2000 [59:03<00:51,  1.79s/it, loss=0.278, lr=0.0001] 
Steps:  99%|█████████▊| 1971/2000 [59:04<00:51,  1.79s/it, loss=0.16, lr=0.0001] 
Steps:  99%|█████████▊| 1972/2000 [59:04<00:49,  1.75s/it, loss=0.16, lr=0.0001]
Steps:  99%|█████████▊| 1972/2000 [59:04<00:49,  1.75s/it, loss=0.982, lr=0.0001]
Steps:  99%|█████████▊| 1972/2000 [59:05<00:49,  1.75s/it, loss=0.137, lr=0.0001]
Steps:  99%|█████████▊| 1972/2000 [59:05<00:49,  1.75s/it, loss=0.119, lr=0.0001]
Steps:  99%|█████████▊| 1972/2000 [59:05<00:49,  1.75s/it, loss=0.841, lr=0.0001]
Steps:  99%|█████████▊| 1973/2000 [59:06<00:46,  1.73s/it, loss=0.841, lr=0.0001]
Steps:  99%|█████████▊| 1973/2000 [59:06<00:46,  1.73s/it, loss=0.982, lr=0.0001]
Steps:  99%|█████████▊| 1973/2000 [59:07<00:46,  1.73s/it, loss=0.0488, lr=0.0001]
Steps:  99%|█████████▊| 1973/2000 [59:07<00:46,  1.73s/it, loss=0.135, lr=0.0001] 
Steps:  99%|█████████▊| 1973/2000 [59:07<00:46,  1.73s/it, loss=1.02, lr=0.0001] 
Steps:  99%|█████████▊| 1974/2000 [59:08<00:46,  1.78s/it, loss=1.02, lr=0.0001]
Steps:  99%|█████████▊| 1974/2000 [59:08<00:46,  1.78s/it, loss=0.198, lr=0.0001]
Steps:  99%|█████████▊| 1974/2000 [59:08<00:46,  1.78s/it, loss=0.264, lr=0.0001]
Steps:  99%|█████████▊| 1974/2000 [59:09<00:46,  1.78s/it, loss=0.341, lr=0.0001]
Steps:  99%|█████████▊| 1974/2000 [59:09<00:46,  1.78s/it, loss=0.11, lr=0.0001] 
Steps:  99%|█████████▉| 1975/2000 [59:10<00:43,  1.76s/it, loss=0.11, lr=0.0001]
Steps:  99%|█████████▉| 1975/2000 [59:10<00:43,  1.76s/it, loss=0.113, lr=0.0001]
Steps:  99%|█████████▉| 1975/2000 [59:10<00:43,  1.76s/it, loss=0.0848, lr=0.0001]
Steps:  99%|█████████▉| 1975/2000 [59:10<00:43,  1.76s/it, loss=0.229, lr=0.0001] 
Steps:  99%|█████████▉| 1975/2000 [59:11<00:43,  1.76s/it, loss=0.126, lr=0.0001]
Steps:  99%|█████████▉| 1976/2000 [59:11<00:41,  1.74s/it, loss=0.126, lr=0.0001]
Steps:  99%|█████████▉| 1976/2000 [59:11<00:41,  1.74s/it, loss=0.13, lr=0.0001] 
Steps:  99%|█████████▉| 1976/2000 [59:12<00:41,  1.74s/it, loss=0.224, lr=0.0001]
Steps:  99%|█████████▉| 1976/2000 [59:12<00:41,  1.74s/it, loss=0.155, lr=0.0001]
Steps:  99%|█████████▉| 1976/2000 [59:13<00:41,  1.74s/it, loss=0.291, lr=0.0001]
Steps:  99%|█████████▉| 1977/2000 [59:13<00:41,  1.79s/it, loss=0.291, lr=0.0001]
Steps:  99%|█████████▉| 1977/2000 [59:13<00:41,  1.79s/it, loss=0.133, lr=0.0001]
Steps:  99%|█████████▉| 1977/2000 [59:14<00:41,  1.79s/it, loss=0.204, lr=0.0001]
Steps:  99%|█████████▉| 1977/2000 [59:14<00:41,  1.79s/it, loss=0.159, lr=0.0001]
Steps:  99%|█████████▉| 1977/2000 [59:14<00:41,  1.79s/it, loss=0.147, lr=0.0001]
Steps:  99%|█████████▉| 1978/2000 [59:15<00:38,  1.75s/it, loss=0.147, lr=0.0001]
Steps:  99%|█████████▉| 1978/2000 [59:15<00:38,  1.75s/it, loss=0.299, lr=0.0001]
Steps:  99%|█████████▉| 1978/2000 [59:15<00:38,  1.75s/it, loss=0.203, lr=0.0001]
Steps:  99%|█████████▉| 1978/2000 [59:16<00:38,  1.75s/it, loss=0.0491, lr=0.0001]
Steps:  99%|█████████▉| 1978/2000 [59:16<00:38,  1.75s/it, loss=0.534, lr=0.0001] 
Steps:  99%|█████████▉| 1979/2000 [59:16<00:36,  1.72s/it, loss=0.534, lr=0.0001]
Steps:  99%|█████████▉| 1979/2000 [59:16<00:36,  1.72s/it, loss=0.306, lr=0.0001]
Steps:  99%|█████████▉| 1979/2000 [59:17<00:36,  1.72s/it, loss=0.123, lr=0.0001]
Steps:  99%|█████████▉| 1979/2000 [59:18<00:36,  1.72s/it, loss=0.262, lr=0.0001]
Steps:  99%|█████████▉| 1979/2000 [59:18<00:36,  1.72s/it, loss=1.02, lr=0.0001] 
Steps:  99%|█████████▉| 1980/2000 [59:18<00:35,  1.78s/it, loss=1.02, lr=0.0001]
Steps:  99%|█████████▉| 1980/2000 [59:18<00:35,  1.78s/it, loss=0.133, lr=0.0001]05/30/2026 09:31:44 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/config.json "HTTP/1.1 200 OK"
05/30/2026 09:31:44 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/config.json "HTTP/1.1 200 OK"
05/30/2026 09:31:44 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder/model.safetensors "HTTP/1.1 302 Found"


Loading weights:   0%|          | 0/196 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 196/196 [00:00<00:00, 6901.19it/s]
05/30/2026 09:31:44 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/config.json "HTTP/1.1 200 OK"
05/30/2026 09:31:44 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/config.json "HTTP/1.1 200 OK"
05/30/2026 09:31:44 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/model.safetensors "HTTP/1.1 404 Not Found"
05/30/2026 09:31:45 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/text_encoder_2/model.safetensors.index.json "HTTP/1.1 200 OK"
05/30/2026 09:31:45 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev/revision/main "HTTP/1.1 200 OK"


Fetching 2 files:   0%|          | 0/2 [00:00<?, ?it/s]
Fetching 2 files: 100%|██████████| 2/2 [00:00<00:00, 3743.24it/s]


Loading weights:   0%|          | 0/219 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 219/219 [00:00<00:00, 6801.12it/s]
05/30/2026 09:31:45 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev "HTTP/1.1 200 OK"
05/30/2026 09:31:45 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/model_index.json "HTTP/1.1 200 OK"
{'feature_extractor', 'image_encoder'} was not found in config. Values will be initialized to default values.


Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]Loaded tokenizer_2 as T5TokenizerFast from `tokenizer_2` subfolder of black-forest-labs/FLUX.1-dev.


Loading pipeline components...:  43%|████▎     | 3/7 [00:00<00:00, 17.23it/s]Loaded tokenizer as CLIPTokenizer from `tokenizer` subfolder of black-forest-labs/FLUX.1-dev.
{'stochastic_sampling', 'use_beta_sigmas', 'invert_sigmas', 'time_shift_type', 'use_exponential_sigmas', 'shift_terminal', 'use_karras_sigmas'} was not found in config. Values will be initialized to default values.
Loaded scheduler as FlowMatchEulerDiscreteScheduler from `scheduler` subfolder of black-forest-labs/FLUX.1-dev.

Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 30.57it/s]
05/30/2026 09:31:45 - INFO - __main__ - [RANK 0] Running validation... 
 Generating 1 images with prompt: emj icon of a pelican with a hat, centered on a plain white background.

Steps:  99%|█████████▉| 1980/2000 [59:31<00:35,  1.78s/it, loss=0.306, lr=0.0001]
Steps:  99%|█████████▉| 1980/2000 [59:31<00:35,  1.78s/it, loss=0.118, lr=0.0001]
Steps:  99%|█████████▉| 1980/2000 [59:32<00:35,  1.78s/it, loss=0.221, lr=0.0001]
Steps:  99%|█████████▉| 1981/2000 [59:32<01:42,  5.41s/it, loss=0.221, lr=0.0001]
Steps:  99%|█████████▉| 1981/2000 [59:32<01:42,  5.41s/it, loss=0.162, lr=0.0001]
Steps:  99%|█████████▉| 1981/2000 [59:33<01:42,  5.41s/it, loss=0.266, lr=0.0001]
Steps:  99%|█████████▉| 1981/2000 [59:33<01:42,  5.41s/it, loss=0.105, lr=0.0001]
Steps:  99%|█████████▉| 1981/2000 [59:33<01:42,  5.41s/it, loss=0.12, lr=0.0001] 
Steps:  99%|█████████▉| 1982/2000 [59:34<01:17,  4.28s/it, loss=0.12, lr=0.0001]
Steps:  99%|█████████▉| 1982/2000 [59:34<01:17,  4.28s/it, loss=0.176, lr=0.0001]
Steps:  99%|█████████▉| 1982/2000 [59:34<01:17,  4.28s/it, loss=0.204, lr=0.0001]
Steps:  99%|█████████▉| 1982/2000 [59:35<01:17,  4.28s/it, loss=0.164, lr=0.0001]
Steps:  99%|█████████▉| 1982/2000 [59:35<01:17,  4.28s/it, loss=0.176, lr=0.0001]
Steps:  99%|█████████▉| 1983/2000 [59:36<00:59,  3.52s/it, loss=0.176, lr=0.0001]
Steps:  99%|█████████▉| 1983/2000 [59:36<00:59,  3.52s/it, loss=0.131, lr=0.0001]
Steps:  99%|█████████▉| 1983/2000 [59:36<00:59,  3.52s/it, loss=0.245, lr=0.0001]
Steps:  99%|█████████▉| 1983/2000 [59:37<00:59,  3.52s/it, loss=0.166, lr=0.0001]
Steps:  99%|█████████▉| 1983/2000 [59:37<00:59,  3.52s/it, loss=0.191, lr=0.0001]
Steps:  99%|█████████▉| 1984/2000 [59:38<00:48,  3.05s/it, loss=0.191, lr=0.0001]
Steps:  99%|█████████▉| 1984/2000 [59:38<00:48,  3.05s/it, loss=0.257, lr=0.0001]
Steps:  99%|█████████▉| 1984/2000 [59:38<00:48,  3.05s/it, loss=0.157, lr=0.0001]
Steps:  99%|█████████▉| 1984/2000 [59:38<00:48,  3.05s/it, loss=0.455, lr=0.0001]
Steps:  99%|█████████▉| 1984/2000 [59:39<00:48,  3.05s/it, loss=0.0569, lr=0.0001]
Steps:  99%|█████████▉| 1985/2000 [59:39<00:39,  2.63s/it, loss=0.0569, lr=0.0001]
Steps:  99%|█████████▉| 1985/2000 [59:39<00:39,  2.63s/it, loss=0.172, lr=0.0001] 
Steps:  99%|█████████▉| 1985/2000 [59:40<00:39,  2.63s/it, loss=0.124, lr=0.0001]
Steps:  99%|█████████▉| 1985/2000 [59:40<00:39,  2.63s/it, loss=0.274, lr=0.0001]
Steps:  99%|█████████▉| 1985/2000 [59:40<00:39,  2.63s/it, loss=0.254, lr=0.0001]
Steps:  99%|█████████▉| 1986/2000 [59:41<00:32,  2.33s/it, loss=0.254, lr=0.0001]
Steps:  99%|█████████▉| 1986/2000 [59:41<00:32,  2.33s/it, loss=0.144, lr=0.0001]
Steps:  99%|█████████▉| 1986/2000 [59:41<00:32,  2.33s/it, loss=0.217, lr=0.0001]
Steps:  99%|█████████▉| 1986/2000 [59:42<00:32,  2.33s/it, loss=0.326, lr=0.0001]
Steps:  99%|█████████▉| 1986/2000 [59:42<00:32,  2.33s/it, loss=0.145, lr=0.0001]
Steps:  99%|█████████▉| 1987/2000 [59:43<00:28,  2.20s/it, loss=0.145, lr=0.0001]
Steps:  99%|█████████▉| 1987/2000 [59:43<00:28,  2.20s/it, loss=0.0555, lr=0.0001]
Steps:  99%|█████████▉| 1987/2000 [59:43<00:28,  2.20s/it, loss=0.151, lr=0.0001] 
Steps:  99%|█████████▉| 1987/2000 [59:44<00:28,  2.20s/it, loss=0.155, lr=0.0001]
Steps:  99%|█████████▉| 1987/2000 [59:44<00:28,  2.20s/it, loss=0.0929, lr=0.0001]
Steps:  99%|█████████▉| 1988/2000 [59:44<00:24,  2.04s/it, loss=0.0929, lr=0.0001]
Steps:  99%|█████████▉| 1988/2000 [59:44<00:24,  2.04s/it, loss=0.154, lr=0.0001] 
Steps:  99%|█████████▉| 1988/2000 [59:45<00:24,  2.04s/it, loss=0.123, lr=0.0001]
Steps:  99%|█████████▉| 1988/2000 [59:45<00:24,  2.04s/it, loss=0.292, lr=0.0001]
Steps:  99%|█████████▉| 1988/2000 [59:46<00:24,  2.04s/it, loss=0.165, lr=0.0001]
Steps:  99%|█████████▉| 1989/2000 [59:46<00:21,  1.93s/it, loss=0.165, lr=0.0001]
Steps:  99%|█████████▉| 1989/2000 [59:46<00:21,  1.93s/it, loss=0.0972, lr=0.0001]
Steps:  99%|█████████▉| 1989/2000 [59:47<00:21,  1.93s/it, loss=0.112, lr=0.0001] 
Steps:  99%|█████████▉| 1989/2000 [59:47<00:21,  1.93s/it, loss=0.189, lr=0.0001]
Steps:  99%|█████████▉| 1989/2000 [59:48<00:21,  1.93s/it, loss=0.159, lr=0.0001]
Steps: 100%|█████████▉| 1990/2000 [59:48<00:19,  1.92s/it, loss=0.159, lr=0.0001]
Steps: 100%|█████████▉| 1990/2000 [59:48<00:19,  1.92s/it, loss=0.117, lr=0.0001]
Steps: 100%|█████████▉| 1990/2000 [59:48<00:19,  1.92s/it, loss=0.132, lr=0.0001]
Steps: 100%|█████████▉| 1990/2000 [59:49<00:19,  1.92s/it, loss=0.112, lr=0.0001]
Steps: 100%|█████████▉| 1990/2000 [59:49<00:19,  1.92s/it, loss=0.127, lr=0.0001]
Steps: 100%|█████████▉| 1991/2000 [59:50<00:16,  1.85s/it, loss=0.127, lr=0.0001]
Steps: 100%|█████████▉| 1991/2000 [59:50<00:16,  1.85s/it, loss=0.127, lr=0.0001]
Steps: 100%|█████████▉| 1991/2000 [59:50<00:16,  1.85s/it, loss=0.35, lr=0.0001] 
Steps: 100%|█████████▉| 1991/2000 [59:50<00:16,  1.85s/it, loss=0.192, lr=0.0001]
Steps: 100%|█████████▉| 1991/2000 [59:51<00:16,  1.85s/it, loss=0.127, lr=0.0001]
Steps: 100%|█████████▉| 1992/2000 [59:51<00:14,  1.79s/it, loss=0.127, lr=0.0001]
Steps: 100%|█████████▉| 1992/2000 [59:51<00:14,  1.79s/it, loss=0.189, lr=0.0001]
Steps: 100%|█████████▉| 1992/2000 [59:52<00:14,  1.79s/it, loss=0.122, lr=0.0001]
Steps: 100%|█████████▉| 1992/2000 [59:52<00:14,  1.79s/it, loss=0.136, lr=0.0001]
Steps: 100%|█████████▉| 1992/2000 [59:53<00:14,  1.79s/it, loss=0.164, lr=0.0001]
Steps: 100%|█████████▉| 1993/2000 [59:53<00:12,  1.82s/it, loss=0.164, lr=0.0001]
Steps: 100%|█████████▉| 1993/2000 [59:53<00:12,  1.82s/it, loss=0.126, lr=0.0001]
Steps: 100%|█████████▉| 1993/2000 [59:54<00:12,  1.82s/it, loss=0.146, lr=0.0001]
Steps: 100%|█████████▉| 1993/2000 [59:54<00:12,  1.82s/it, loss=0.126, lr=0.0001]
Steps: 100%|█████████▉| 1993/2000 [59:54<00:12,  1.82s/it, loss=0.202, lr=0.0001]
Steps: 100%|█████████▉| 1994/2000 [59:55<00:10,  1.76s/it, loss=0.202, lr=0.0001]
Steps: 100%|█████████▉| 1994/2000 [59:55<00:10,  1.76s/it, loss=0.195, lr=0.0001]
Steps: 100%|█████████▉| 1994/2000 [59:55<00:10,  1.76s/it, loss=0.166, lr=0.0001]
Steps: 100%|█████████▉| 1994/2000 [59:56<00:10,  1.76s/it, loss=0.155, lr=0.0001]
Steps: 100%|█████████▉| 1994/2000 [59:56<00:10,  1.76s/it, loss=0.666, lr=0.0001]
Steps: 100%|█████████▉| 1995/2000 [59:57<00:08,  1.73s/it, loss=0.666, lr=0.0001]
Steps: 100%|█████████▉| 1995/2000 [59:57<00:08,  1.73s/it, loss=0.2, lr=0.0001]  
Steps: 100%|█████████▉| 1995/2000 [59:57<00:08,  1.73s/it, loss=0.427, lr=0.0001]
Steps: 100%|█████████▉| 1995/2000 [59:57<00:08,  1.73s/it, loss=0.185, lr=0.0001]
Steps: 100%|█████████▉| 1995/2000 [59:58<00:08,  1.73s/it, loss=0.11, lr=0.0001] 
Steps: 100%|█████████▉| 1996/2000 [59:58<00:07,  1.78s/it, loss=0.11, lr=0.0001]
Steps: 100%|█████████▉| 1996/2000 [59:58<00:07,  1.78s/it, loss=0.0759, lr=0.0001]
Steps: 100%|█████████▉| 1996/2000 [59:59<00:07,  1.78s/it, loss=0.571, lr=0.0001] 
Steps: 100%|█████████▉| 1996/2000 [59:59<00:07,  1.78s/it, loss=0.272, lr=0.0001]
Steps: 100%|█████████▉| 1996/2000 [1:00:00<00:07,  1.78s/it, loss=0.171, lr=0.0001]
Steps: 100%|█████████▉| 1997/2000 [1:00:00<00:05,  1.74s/it, loss=0.171, lr=0.0001]
Steps: 100%|█████████▉| 1997/2000 [1:00:00<00:05,  1.74s/it, loss=1.24, lr=0.0001] 
Steps: 100%|█████████▉| 1997/2000 [1:00:00<00:05,  1.74s/it, loss=0.195, lr=0.0001]
Steps: 100%|█████████▉| 1997/2000 [1:00:01<00:05,  1.74s/it, loss=0.132, lr=0.0001]
Steps: 100%|█████████▉| 1997/2000 [1:00:01<00:05,  1.74s/it, loss=0.196, lr=0.0001]
Steps: 100%|█████████▉| 1998/2000 [1:00:02<00:03,  1.71s/it, loss=0.196, lr=0.0001]
Steps: 100%|█████████▉| 1998/2000 [1:00:02<00:03,  1.71s/it, loss=0.245, lr=0.0001]
Steps: 100%|█████████▉| 1998/2000 [1:00:02<00:03,  1.71s/it, loss=0.142, lr=0.0001]
Steps: 100%|█████████▉| 1998/2000 [1:00:03<00:03,  1.71s/it, loss=0.231, lr=0.0001]
Steps: 100%|█████████▉| 1998/2000 [1:00:03<00:03,  1.71s/it, loss=0.169, lr=0.0001]
Steps: 100%|█████████▉| 1999/2000 [1:00:04<00:01,  1.77s/it, loss=0.169, lr=0.0001]
Steps: 100%|█████████▉| 1999/2000 [1:00:04<00:01,  1.77s/it, loss=0.204, lr=0.0001]
Steps: 100%|█████████▉| 1999/2000 [1:00:04<00:01,  1.77s/it, loss=0.0823, lr=0.0001]
Steps: 100%|█████████▉| 1999/2000 [1:00:04<00:01,  1.77s/it, loss=0.246, lr=0.0001] 
Steps: 100%|█████████▉| 1999/2000 [1:00:05<00:01,  1.77s/it, loss=0.149, lr=0.0001]
Steps: 100%|██████████| 2000/2000 [1:00:05<00:00,  1.73s/it, loss=0.149, lr=0.0001]05/30/2026 09:32:30 - INFO - accelerate.accelerator - [RANK 0] Saving current state to /workspace/output/flux-dev-apple-emoji-lora/checkpoint-2000
Model weights saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-2000/pytorch_lora_weights.safetensors
05/30/2026 09:32:31 - INFO - accelerate.checkpointing - [RANK 0] Optimizer state saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-2000/optimizer.bin
05/30/2026 09:32:31 - INFO - accelerate.checkpointing - [RANK 0] Scheduler state saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-2000/scheduler.bin
05/30/2026 09:32:31 - INFO - accelerate.checkpointing - [RANK 0] Sampler state for dataloader 0 saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-2000/sampler.bin
05/30/2026 09:32:31 - INFO - accelerate.checkpointing - [RANK 0] Random states saved in /workspace/output/flux-dev-apple-emoji-lora/checkpoint-2000/random_states_0.pkl
05/30/2026 09:32:31 - INFO - __main__ - [RANK 0] Saved state to /workspace/output/flux-dev-apple-emoji-lora/checkpoint-2000

Steps: 100%|██████████| 2000/2000 [1:00:06<00:00,  1.73s/it, loss=0.145, lr=0.0001]Model weights saved in /workspace/output/flux-dev-apple-emoji-lora/pytorch_lora_weights.safetensors
05/30/2026 09:32:32 - INFO - httpx - HTTP Request: GET https://huggingface.co/api/models/black-forest-labs/FLUX.1-dev "HTTP/1.1 200 OK"
05/30/2026 09:32:32 - INFO - httpx - HTTP Request: HEAD https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/model_index.json "HTTP/1.1 200 OK"
{'feature_extractor', 'image_encoder'} was not found in config. Values will be initialized to default values.


Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]Instantiating FluxTransformer2DModel model under default dtype torch.bfloat16.
{'out_channels', 'axes_dims_rope'} was not found in config. Values will be initialized to default values.



Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]
Loading checkpoint shards: 100%|██████████| 3/3 [00:00<00:00, 35.79it/s]
All model checkpoint weights were used when initializing FluxTransformer2DModel.

All the weights of FluxTransformer2DModel were initialized from the model checkpoint at /workspace/.cache/huggingface/hub/models--black-forest-labs--FLUX.1-dev/snapshots/3de623fc3c33e44ffbe2bad470d0f45bccf2eb21/transformer.
If your task is similar to the task the model of the checkpoint was trained on, you can already use FluxTransformer2DModel for predictions without further training.
Loaded transformer as FluxTransformer2DModel from `transformer` subfolder of black-forest-labs/FLUX.1-dev.


Loading pipeline components...:  14%|█▍        | 1/7 [00:00<00:01,  4.39it/s]Instantiating AutoencoderKL model under default dtype torch.bfloat16.
All model checkpoint weights were used when initializing AutoencoderKL.

All the weights of AutoencoderKL were initialized from the model checkpoint at /workspace/.cache/huggingface/hub/models--black-forest-labs--FLUX.1-dev/snapshots/3de623fc3c33e44ffbe2bad470d0f45bccf2eb21/vae.
If your task is similar to the task the model of the checkpoint was trained on, you can already use AutoencoderKL for predictions without further training.
Loaded vae as AutoencoderKL from `vae` subfolder of black-forest-labs/FLUX.1-dev.
Loaded tokenizer_2 as T5TokenizerFast from `tokenizer_2` subfolder of black-forest-labs/FLUX.1-dev.


Loading pipeline components...:  43%|████▎     | 3/7 [00:00<00:00,  8.81it/s]Loaded tokenizer as CLIPTokenizer from `tokenizer` subfolder of black-forest-labs/FLUX.1-dev.
{'stochastic_sampling', 'use_beta_sigmas', 'invert_sigmas', 'time_shift_type', 'use_exponential_sigmas', 'shift_terminal', 'use_karras_sigmas'} was not found in config. Values will be initialized to default values.
Loaded scheduler as FlowMatchEulerDiscreteScheduler from `scheduler` subfolder of black-forest-labs/FLUX.1-dev.



Loading weights:   0%|          | 0/196 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 196/196 [00:00<00:00, 9972.39it/s]
Loaded text_encoder as CLIPTextModel from `text_encoder` subfolder of black-forest-labs/FLUX.1-dev.


Loading pipeline components...:  86%|████████▌ | 6/7 [00:00<00:00, 15.37it/s]


Loading weights:   0%|          | 0/219 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 219/219 [00:00<00:00, 11388.66it/s]
Loaded text_encoder_2 as T5EncoderModel from `text_encoder_2` subfolder of black-forest-labs/FLUX.1-dev.

Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00, 12.95it/s]
Loading transformer.
No LoRA keys associated to CLIPTextModel found with the prefix='text_encoder'. This is safe to ignore if LoRA state dict didn't originally have any CLIPTextModel related params. You can also try specifying `prefix=None` to resolve the warning. Otherwise, open an issue if you think it's unexpected: https://github.com/huggingface/diffusers/issues/new
05/30/2026 09:32:34 - INFO - __main__ - [RANK 0] Running validation... 
 Generating 1 images with prompt: emj icon of a pelican with a hat, centered on a plain white background.

Steps: 100%|██████████| 2000/2000 [1:00:22<00:00,  1.81s/it, loss=0.145, lr=0.0001]