Image-Text-to-Text
Transformers
Safetensors
PyTorch
English
clip-mtl
feature-extraction
mmhs150k
multimodal
hate-speech-detection
content-moderation
clip
multi-task-learning
custom_code
Eval Results (legacy)
Instructions to use Amirhossein75/clip-vit-base-mmhs150k-mtl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Amirhossein75/clip-vit-base-mmhs150k-mtl with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Amirhossein75/clip-vit-base-mmhs150k-mtl", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Amirhossein75/clip-vit-base-mmhs150k-mtl", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Amirhossein75/clip-vit-base-mmhs150k-mtl with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Amirhossein75/clip-vit-base-mmhs150k-mtl" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Amirhossein75/clip-vit-base-mmhs150k-mtl", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Amirhossein75/clip-vit-base-mmhs150k-mtl
- SGLang
How to use Amirhossein75/clip-vit-base-mmhs150k-mtl with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Amirhossein75/clip-vit-base-mmhs150k-mtl" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Amirhossein75/clip-vit-base-mmhs150k-mtl", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Amirhossein75/clip-vit-base-mmhs150k-mtl" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Amirhossein75/clip-vit-base-mmhs150k-mtl", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Amirhossein75/clip-vit-base-mmhs150k-mtl with Docker Model Runner:
docker model run hf.co/Amirhossein75/clip-vit-base-mmhs150k-mtl
Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +1632 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,1632 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 11236,
|
| 3 |
+
"best_metric": 0.5682024245488293,
|
| 4 |
+
"best_model_checkpoint": "runs/clip_mtl_mmhshateful\\checkpoint-11236",
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 11236,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0044499822000712,
|
| 14 |
+
"grad_norm": 0.6930296421051025,
|
| 15 |
+
"learning_rate": 1.9999985928231315e-05,
|
| 16 |
+
"loss": 1.1543,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0088999644001424,
|
| 21 |
+
"grad_norm": 0.9534976482391357,
|
| 22 |
+
"learning_rate": 1.99999413432439e-05,
|
| 23 |
+
"loss": 1.0927,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.013349946600213599,
|
| 28 |
+
"grad_norm": 0.8714975118637085,
|
| 29 |
+
"learning_rate": 1.9999866220743754e-05,
|
| 30 |
+
"loss": 0.9653,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0177999288002848,
|
| 35 |
+
"grad_norm": 1.0742043256759644,
|
| 36 |
+
"learning_rate": 1.9999760560960283e-05,
|
| 37 |
+
"loss": 1.2235,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.022249911000355997,
|
| 42 |
+
"grad_norm": 2.212294101715088,
|
| 43 |
+
"learning_rate": 1.9999624364216147e-05,
|
| 44 |
+
"loss": 1.371,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.026699893200427198,
|
| 49 |
+
"grad_norm": 3.4641246795654297,
|
| 50 |
+
"learning_rate": 1.999946488655439e-05,
|
| 51 |
+
"loss": 1.205,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0311498754004984,
|
| 56 |
+
"grad_norm": 1.0936462879180908,
|
| 57 |
+
"learning_rate": 1.9999268838660392e-05,
|
| 58 |
+
"loss": 0.9664,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.0355998576005696,
|
| 63 |
+
"grad_norm": 1.8520387411117554,
|
| 64 |
+
"learning_rate": 1.9999042255307332e-05,
|
| 65 |
+
"loss": 1.0667,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0400498398006408,
|
| 70 |
+
"grad_norm": 1.1343063116073608,
|
| 71 |
+
"learning_rate": 1.999878513718715e-05,
|
| 72 |
+
"loss": 1.0061,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.044499822000711994,
|
| 77 |
+
"grad_norm": 1.8512768745422363,
|
| 78 |
+
"learning_rate": 1.9998497485085022e-05,
|
| 79 |
+
"loss": 1.1225,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.048949804200783195,
|
| 84 |
+
"grad_norm": 11.832172393798828,
|
| 85 |
+
"learning_rate": 1.999817929987937e-05,
|
| 86 |
+
"loss": 1.1131,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.053399786400854396,
|
| 91 |
+
"grad_norm": 11.022147178649902,
|
| 92 |
+
"learning_rate": 1.9997830582541863e-05,
|
| 93 |
+
"loss": 1.0418,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.0578497686009256,
|
| 98 |
+
"grad_norm": 1.15188729763031,
|
| 99 |
+
"learning_rate": 1.9997459218302607e-05,
|
| 100 |
+
"loss": 1.384,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.0622997508009968,
|
| 105 |
+
"grad_norm": 0.8350585699081421,
|
| 106 |
+
"learning_rate": 1.9997058533115497e-05,
|
| 107 |
+
"loss": 1.0089,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.066749733001068,
|
| 112 |
+
"grad_norm": 2.022878885269165,
|
| 113 |
+
"learning_rate": 1.999661944726586e-05,
|
| 114 |
+
"loss": 1.0024,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.0711997152011392,
|
| 119 |
+
"grad_norm": 1.1452044248580933,
|
| 120 |
+
"learning_rate": 1.9996149834047797e-05,
|
| 121 |
+
"loss": 1.1402,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.0756496974012104,
|
| 126 |
+
"grad_norm": 0.855829119682312,
|
| 127 |
+
"learning_rate": 1.9995649694895397e-05,
|
| 128 |
+
"loss": 0.9612,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.0800996796012816,
|
| 133 |
+
"grad_norm": 11.837068557739258,
|
| 134 |
+
"learning_rate": 1.9995119031335967e-05,
|
| 135 |
+
"loss": 1.0198,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.08454966180135279,
|
| 140 |
+
"grad_norm": 0.9849753379821777,
|
| 141 |
+
"learning_rate": 1.999455784499003e-05,
|
| 142 |
+
"loss": 1.2736,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.08899964400142399,
|
| 147 |
+
"grad_norm": 1.7843427658081055,
|
| 148 |
+
"learning_rate": 1.9993966137571323e-05,
|
| 149 |
+
"loss": 1.0706,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.09344962620149519,
|
| 154 |
+
"grad_norm": 3.2881357669830322,
|
| 155 |
+
"learning_rate": 1.999334391088678e-05,
|
| 156 |
+
"loss": 1.1104,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.09789960840156639,
|
| 161 |
+
"grad_norm": 19.132781982421875,
|
| 162 |
+
"learning_rate": 1.999269116683654e-05,
|
| 163 |
+
"loss": 1.1803,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.10234959060163759,
|
| 168 |
+
"grad_norm": 1.0581350326538086,
|
| 169 |
+
"learning_rate": 1.9992007907413935e-05,
|
| 170 |
+
"loss": 1.1744,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.10679957280170879,
|
| 175 |
+
"grad_norm": 3.8312244415283203,
|
| 176 |
+
"learning_rate": 1.999129413470548e-05,
|
| 177 |
+
"loss": 1.0072,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.11124955500177999,
|
| 182 |
+
"grad_norm": 0.6719951033592224,
|
| 183 |
+
"learning_rate": 1.999054985089087e-05,
|
| 184 |
+
"loss": 1.0091,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.1156995372018512,
|
| 189 |
+
"grad_norm": 3.9404165744781494,
|
| 190 |
+
"learning_rate": 1.9989775058242976e-05,
|
| 191 |
+
"loss": 1.3107,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.1201495194019224,
|
| 196 |
+
"grad_norm": 16.099702835083008,
|
| 197 |
+
"learning_rate": 1.9988969759127837e-05,
|
| 198 |
+
"loss": 1.2654,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.1245995016019936,
|
| 203 |
+
"grad_norm": 0.6801987886428833,
|
| 204 |
+
"learning_rate": 1.9988133956004657e-05,
|
| 205 |
+
"loss": 1.1379,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.1290494838020648,
|
| 210 |
+
"grad_norm": 0.9160261154174805,
|
| 211 |
+
"learning_rate": 1.9987267651425776e-05,
|
| 212 |
+
"loss": 0.9095,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.133499466002136,
|
| 217 |
+
"grad_norm": 1.217660665512085,
|
| 218 |
+
"learning_rate": 1.9986370848036688e-05,
|
| 219 |
+
"loss": 1.3063,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.1379494482022072,
|
| 224 |
+
"grad_norm": 0.7348505258560181,
|
| 225 |
+
"learning_rate": 1.9985443548576034e-05,
|
| 226 |
+
"loss": 1.062,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.1423994304022784,
|
| 231 |
+
"grad_norm": 12.344593048095703,
|
| 232 |
+
"learning_rate": 1.9984485755875563e-05,
|
| 233 |
+
"loss": 1.249,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.1468494126023496,
|
| 238 |
+
"grad_norm": 3.754258155822754,
|
| 239 |
+
"learning_rate": 1.9983497472860156e-05,
|
| 240 |
+
"loss": 1.1423,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.1512993948024208,
|
| 245 |
+
"grad_norm": 1.3361784219741821,
|
| 246 |
+
"learning_rate": 1.9982478702547802e-05,
|
| 247 |
+
"loss": 1.1729,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.155749377002492,
|
| 252 |
+
"grad_norm": 1.674297571182251,
|
| 253 |
+
"learning_rate": 1.9981429448049584e-05,
|
| 254 |
+
"loss": 1.0536,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.1601993592025632,
|
| 259 |
+
"grad_norm": 1.6976128816604614,
|
| 260 |
+
"learning_rate": 1.9980349712569696e-05,
|
| 261 |
+
"loss": 1.0989,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.1646493414026344,
|
| 266 |
+
"grad_norm": 12.235713005065918,
|
| 267 |
+
"learning_rate": 1.997923949940539e-05,
|
| 268 |
+
"loss": 1.0191,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.16909932360270558,
|
| 273 |
+
"grad_norm": 8.77859115600586,
|
| 274 |
+
"learning_rate": 1.9978098811947005e-05,
|
| 275 |
+
"loss": 1.2005,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.17354930580277678,
|
| 280 |
+
"grad_norm": 1.0547969341278076,
|
| 281 |
+
"learning_rate": 1.9976927653677937e-05,
|
| 282 |
+
"loss": 1.1798,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.17799928800284798,
|
| 287 |
+
"grad_norm": 16.349029541015625,
|
| 288 |
+
"learning_rate": 1.997572602817463e-05,
|
| 289 |
+
"loss": 1.201,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.18244927020291918,
|
| 294 |
+
"grad_norm": 11.384589195251465,
|
| 295 |
+
"learning_rate": 1.9974493939106575e-05,
|
| 296 |
+
"loss": 1.0481,
|
| 297 |
+
"step": 2050
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.18689925240299038,
|
| 301 |
+
"grad_norm": 10.341683387756348,
|
| 302 |
+
"learning_rate": 1.9973231390236287e-05,
|
| 303 |
+
"loss": 1.2775,
|
| 304 |
+
"step": 2100
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.19134923460306158,
|
| 308 |
+
"grad_norm": 0.7568284273147583,
|
| 309 |
+
"learning_rate": 1.9971938385419298e-05,
|
| 310 |
+
"loss": 0.9456,
|
| 311 |
+
"step": 2150
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.19579921680313278,
|
| 315 |
+
"grad_norm": 0.719429075717926,
|
| 316 |
+
"learning_rate": 1.9970614928604144e-05,
|
| 317 |
+
"loss": 1.198,
|
| 318 |
+
"step": 2200
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.20024919900320398,
|
| 322 |
+
"grad_norm": 11.964608192443848,
|
| 323 |
+
"learning_rate": 1.996926102383236e-05,
|
| 324 |
+
"loss": 1.2098,
|
| 325 |
+
"step": 2250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.20469918120327518,
|
| 329 |
+
"grad_norm": 32.06000518798828,
|
| 330 |
+
"learning_rate": 1.996787667523846e-05,
|
| 331 |
+
"loss": 1.3231,
|
| 332 |
+
"step": 2300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.20914916340334638,
|
| 336 |
+
"grad_norm": 4.2478108406066895,
|
| 337 |
+
"learning_rate": 1.996646188704992e-05,
|
| 338 |
+
"loss": 1.0375,
|
| 339 |
+
"step": 2350
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.21359914560341758,
|
| 343 |
+
"grad_norm": 3.896465301513672,
|
| 344 |
+
"learning_rate": 1.996501666358718e-05,
|
| 345 |
+
"loss": 1.0432,
|
| 346 |
+
"step": 2400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.21804912780348878,
|
| 350 |
+
"grad_norm": 3.1395533084869385,
|
| 351 |
+
"learning_rate": 1.9963541009263615e-05,
|
| 352 |
+
"loss": 1.1409,
|
| 353 |
+
"step": 2450
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.22249911000355999,
|
| 357 |
+
"grad_norm": 1.3287521600723267,
|
| 358 |
+
"learning_rate": 1.996203492858554e-05,
|
| 359 |
+
"loss": 0.9895,
|
| 360 |
+
"step": 2500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.2269490922036312,
|
| 364 |
+
"grad_norm": 1.846510648727417,
|
| 365 |
+
"learning_rate": 1.996049842615217e-05,
|
| 366 |
+
"loss": 1.1018,
|
| 367 |
+
"step": 2550
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.2313990744037024,
|
| 371 |
+
"grad_norm": 0.8593488931655884,
|
| 372 |
+
"learning_rate": 1.9958931506655635e-05,
|
| 373 |
+
"loss": 1.2726,
|
| 374 |
+
"step": 2600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.2358490566037736,
|
| 378 |
+
"grad_norm": 1.4827325344085693,
|
| 379 |
+
"learning_rate": 1.995733417488094e-05,
|
| 380 |
+
"loss": 0.8561,
|
| 381 |
+
"step": 2650
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.2402990388038448,
|
| 385 |
+
"grad_norm": 0.7320635318756104,
|
| 386 |
+
"learning_rate": 1.995570643570597e-05,
|
| 387 |
+
"loss": 1.0547,
|
| 388 |
+
"step": 2700
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.244749021003916,
|
| 392 |
+
"grad_norm": 2.179614305496216,
|
| 393 |
+
"learning_rate": 1.995404829410147e-05,
|
| 394 |
+
"loss": 1.2316,
|
| 395 |
+
"step": 2750
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.2491990032039872,
|
| 399 |
+
"grad_norm": 3.888511896133423,
|
| 400 |
+
"learning_rate": 1.995235975513101e-05,
|
| 401 |
+
"loss": 1.3863,
|
| 402 |
+
"step": 2800
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.2536489854040584,
|
| 406 |
+
"grad_norm": 11.913590431213379,
|
| 407 |
+
"learning_rate": 1.9950640823951013e-05,
|
| 408 |
+
"loss": 1.0316,
|
| 409 |
+
"step": 2850
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.2580989676041296,
|
| 413 |
+
"grad_norm": 1.4524823427200317,
|
| 414 |
+
"learning_rate": 1.9948891505810685e-05,
|
| 415 |
+
"loss": 1.1805,
|
| 416 |
+
"step": 2900
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.2625489498042008,
|
| 420 |
+
"grad_norm": 0.8905289173126221,
|
| 421 |
+
"learning_rate": 1.9947111806052044e-05,
|
| 422 |
+
"loss": 1.2089,
|
| 423 |
+
"step": 2950
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.266998932004272,
|
| 427 |
+
"grad_norm": 0.6847230792045593,
|
| 428 |
+
"learning_rate": 1.9945301730109884e-05,
|
| 429 |
+
"loss": 1.0075,
|
| 430 |
+
"step": 3000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.2714489142043432,
|
| 434 |
+
"grad_norm": 0.8868160843849182,
|
| 435 |
+
"learning_rate": 1.9943461283511763e-05,
|
| 436 |
+
"loss": 0.8334,
|
| 437 |
+
"step": 3050
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.2758988964044144,
|
| 441 |
+
"grad_norm": 1.7983331680297852,
|
| 442 |
+
"learning_rate": 1.994159047187797e-05,
|
| 443 |
+
"loss": 1.1179,
|
| 444 |
+
"step": 3100
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.2803488786044856,
|
| 448 |
+
"grad_norm": 0.7640360593795776,
|
| 449 |
+
"learning_rate": 1.9939689300921538e-05,
|
| 450 |
+
"loss": 1.0782,
|
| 451 |
+
"step": 3150
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.2847988608045568,
|
| 455 |
+
"grad_norm": 2.1053290367126465,
|
| 456 |
+
"learning_rate": 1.9937757776448204e-05,
|
| 457 |
+
"loss": 1.3257,
|
| 458 |
+
"step": 3200
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.289248843004628,
|
| 462 |
+
"grad_norm": 2.609022855758667,
|
| 463 |
+
"learning_rate": 1.99357959043564e-05,
|
| 464 |
+
"loss": 1.1516,
|
| 465 |
+
"step": 3250
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.2936988252046992,
|
| 469 |
+
"grad_norm": 1.6748881340026855,
|
| 470 |
+
"learning_rate": 1.9933803690637225e-05,
|
| 471 |
+
"loss": 1.1508,
|
| 472 |
+
"step": 3300
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.2981488074047704,
|
| 476 |
+
"grad_norm": 5.622939109802246,
|
| 477 |
+
"learning_rate": 1.9931781141374447e-05,
|
| 478 |
+
"loss": 0.8668,
|
| 479 |
+
"step": 3350
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.3025987896048416,
|
| 483 |
+
"grad_norm": 2.957125186920166,
|
| 484 |
+
"learning_rate": 1.992972826274446e-05,
|
| 485 |
+
"loss": 1.374,
|
| 486 |
+
"step": 3400
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.3070487718049128,
|
| 490 |
+
"grad_norm": 1.5037779808044434,
|
| 491 |
+
"learning_rate": 1.9927645061016278e-05,
|
| 492 |
+
"loss": 1.1594,
|
| 493 |
+
"step": 3450
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.311498754004984,
|
| 497 |
+
"grad_norm": 1.0722275972366333,
|
| 498 |
+
"learning_rate": 1.9925531542551524e-05,
|
| 499 |
+
"loss": 1.2182,
|
| 500 |
+
"step": 3500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.3159487362050552,
|
| 504 |
+
"grad_norm": 0.5968232750892639,
|
| 505 |
+
"learning_rate": 1.9923387713804393e-05,
|
| 506 |
+
"loss": 1.2872,
|
| 507 |
+
"step": 3550
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.3203987184051264,
|
| 511 |
+
"grad_norm": 1.0795742273330688,
|
| 512 |
+
"learning_rate": 1.9921213581321646e-05,
|
| 513 |
+
"loss": 1.1279,
|
| 514 |
+
"step": 3600
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.3248487006051976,
|
| 518 |
+
"grad_norm": 0.9048451781272888,
|
| 519 |
+
"learning_rate": 1.991900915174258e-05,
|
| 520 |
+
"loss": 1.212,
|
| 521 |
+
"step": 3650
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.3292986828052688,
|
| 525 |
+
"grad_norm": 9.705388069152832,
|
| 526 |
+
"learning_rate": 1.9916774431799017e-05,
|
| 527 |
+
"loss": 1.3017,
|
| 528 |
+
"step": 3700
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.33374866500534,
|
| 532 |
+
"grad_norm": 1.7905807495117188,
|
| 533 |
+
"learning_rate": 1.9914509428315266e-05,
|
| 534 |
+
"loss": 0.9617,
|
| 535 |
+
"step": 3750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.33819864720541115,
|
| 539 |
+
"grad_norm": 7.1238603591918945,
|
| 540 |
+
"learning_rate": 1.9912214148208137e-05,
|
| 541 |
+
"loss": 1.1694,
|
| 542 |
+
"step": 3800
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.34264862940548235,
|
| 546 |
+
"grad_norm": 1.6141045093536377,
|
| 547 |
+
"learning_rate": 1.9909888598486878e-05,
|
| 548 |
+
"loss": 1.0389,
|
| 549 |
+
"step": 3850
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.34709861160555355,
|
| 553 |
+
"grad_norm": 2.56583309173584,
|
| 554 |
+
"learning_rate": 1.9907532786253183e-05,
|
| 555 |
+
"loss": 1.2183,
|
| 556 |
+
"step": 3900
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.35154859380562475,
|
| 560 |
+
"grad_norm": 1.3100908994674683,
|
| 561 |
+
"learning_rate": 1.990514671870116e-05,
|
| 562 |
+
"loss": 1.2688,
|
| 563 |
+
"step": 3950
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.35599857600569595,
|
| 567 |
+
"grad_norm": 2.074667453765869,
|
| 568 |
+
"learning_rate": 1.990273040311731e-05,
|
| 569 |
+
"loss": 1.091,
|
| 570 |
+
"step": 4000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.36044855820576716,
|
| 574 |
+
"grad_norm": 0.7037174105644226,
|
| 575 |
+
"learning_rate": 1.9900283846880498e-05,
|
| 576 |
+
"loss": 0.998,
|
| 577 |
+
"step": 4050
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.36489854040583836,
|
| 581 |
+
"grad_norm": 2.9290120601654053,
|
| 582 |
+
"learning_rate": 1.9897807057461946e-05,
|
| 583 |
+
"loss": 0.9211,
|
| 584 |
+
"step": 4100
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.36934852260590956,
|
| 588 |
+
"grad_norm": 8.646696090698242,
|
| 589 |
+
"learning_rate": 1.9895300042425196e-05,
|
| 590 |
+
"loss": 1.2834,
|
| 591 |
+
"step": 4150
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.37379850480598076,
|
| 595 |
+
"grad_norm": 0.8763217329978943,
|
| 596 |
+
"learning_rate": 1.989276280942609e-05,
|
| 597 |
+
"loss": 1.0883,
|
| 598 |
+
"step": 4200
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.37824848700605196,
|
| 602 |
+
"grad_norm": 0.8757887482643127,
|
| 603 |
+
"learning_rate": 1.989019536621276e-05,
|
| 604 |
+
"loss": 1.3121,
|
| 605 |
+
"step": 4250
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.38269846920612316,
|
| 609 |
+
"grad_norm": 20.988733291625977,
|
| 610 |
+
"learning_rate": 1.988759772062558e-05,
|
| 611 |
+
"loss": 1.1183,
|
| 612 |
+
"step": 4300
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.38714845140619436,
|
| 616 |
+
"grad_norm": 0.7720549702644348,
|
| 617 |
+
"learning_rate": 1.9884969880597162e-05,
|
| 618 |
+
"loss": 1.2385,
|
| 619 |
+
"step": 4350
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.39159843360626556,
|
| 623 |
+
"grad_norm": 2.226048469543457,
|
| 624 |
+
"learning_rate": 1.9882311854152318e-05,
|
| 625 |
+
"loss": 1.2543,
|
| 626 |
+
"step": 4400
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.39604841580633676,
|
| 630 |
+
"grad_norm": 1.131201148033142,
|
| 631 |
+
"learning_rate": 1.987962364940805e-05,
|
| 632 |
+
"loss": 1.0842,
|
| 633 |
+
"step": 4450
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.40049839800640796,
|
| 637 |
+
"grad_norm": 14.457625389099121,
|
| 638 |
+
"learning_rate": 1.987690527457352e-05,
|
| 639 |
+
"loss": 1.0695,
|
| 640 |
+
"step": 4500
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.40494838020647916,
|
| 644 |
+
"grad_norm": 0.8496118187904358,
|
| 645 |
+
"learning_rate": 1.9874156737950008e-05,
|
| 646 |
+
"loss": 1.2233,
|
| 647 |
+
"step": 4550
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.40939836240655036,
|
| 651 |
+
"grad_norm": 1.1709364652633667,
|
| 652 |
+
"learning_rate": 1.9871378047930915e-05,
|
| 653 |
+
"loss": 1.0452,
|
| 654 |
+
"step": 4600
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.41384834460662157,
|
| 658 |
+
"grad_norm": 0.7952430248260498,
|
| 659 |
+
"learning_rate": 1.9868569213001722e-05,
|
| 660 |
+
"loss": 1.1319,
|
| 661 |
+
"step": 4650
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.41829832680669277,
|
| 665 |
+
"grad_norm": 10.694504737854004,
|
| 666 |
+
"learning_rate": 1.9865730241739958e-05,
|
| 667 |
+
"loss": 1.0488,
|
| 668 |
+
"step": 4700
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.42274830900676397,
|
| 672 |
+
"grad_norm": 0.7666745781898499,
|
| 673 |
+
"learning_rate": 1.986286114281519e-05,
|
| 674 |
+
"loss": 1.2433,
|
| 675 |
+
"step": 4750
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.42719829120683517,
|
| 679 |
+
"grad_norm": 0.5612050890922546,
|
| 680 |
+
"learning_rate": 1.9859961924988977e-05,
|
| 681 |
+
"loss": 0.7798,
|
| 682 |
+
"step": 4800
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.43164827340690637,
|
| 686 |
+
"grad_norm": 1.1437429189682007,
|
| 687 |
+
"learning_rate": 1.985703259711487e-05,
|
| 688 |
+
"loss": 1.0582,
|
| 689 |
+
"step": 4850
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.43609825560697757,
|
| 693 |
+
"grad_norm": 1.3851732015609741,
|
| 694 |
+
"learning_rate": 1.9854073168138354e-05,
|
| 695 |
+
"loss": 1.2503,
|
| 696 |
+
"step": 4900
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.44054823780704877,
|
| 700 |
+
"grad_norm": 0.5759838819503784,
|
| 701 |
+
"learning_rate": 1.985108364709684e-05,
|
| 702 |
+
"loss": 1.0713,
|
| 703 |
+
"step": 4950
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.44499822000711997,
|
| 707 |
+
"grad_norm": 0.9803907871246338,
|
| 708 |
+
"learning_rate": 1.9848064043119644e-05,
|
| 709 |
+
"loss": 1.0747,
|
| 710 |
+
"step": 5000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.44944820220719117,
|
| 714 |
+
"grad_norm": 1.4427608251571655,
|
| 715 |
+
"learning_rate": 1.9845014365427936e-05,
|
| 716 |
+
"loss": 0.9888,
|
| 717 |
+
"step": 5050
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.4538981844072624,
|
| 721 |
+
"grad_norm": 0.6690992712974548,
|
| 722 |
+
"learning_rate": 1.984193462333472e-05,
|
| 723 |
+
"loss": 1.1711,
|
| 724 |
+
"step": 5100
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.4583481666073336,
|
| 728 |
+
"grad_norm": 12.372550964355469,
|
| 729 |
+
"learning_rate": 1.983882482624483e-05,
|
| 730 |
+
"loss": 1.0621,
|
| 731 |
+
"step": 5150
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.4627981488074048,
|
| 735 |
+
"grad_norm": 1.351020336151123,
|
| 736 |
+
"learning_rate": 1.983568498365486e-05,
|
| 737 |
+
"loss": 0.9669,
|
| 738 |
+
"step": 5200
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.467248131007476,
|
| 742 |
+
"grad_norm": 1.8895344734191895,
|
| 743 |
+
"learning_rate": 1.9832515105153165e-05,
|
| 744 |
+
"loss": 1.334,
|
| 745 |
+
"step": 5250
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.4716981132075472,
|
| 749 |
+
"grad_norm": 2.086756467819214,
|
| 750 |
+
"learning_rate": 1.9829315200419824e-05,
|
| 751 |
+
"loss": 1.1035,
|
| 752 |
+
"step": 5300
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.4761480954076184,
|
| 756 |
+
"grad_norm": 2.531623363494873,
|
| 757 |
+
"learning_rate": 1.9826085279226612e-05,
|
| 758 |
+
"loss": 0.9576,
|
| 759 |
+
"step": 5350
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.4805980776076896,
|
| 763 |
+
"grad_norm": 13.519452095031738,
|
| 764 |
+
"learning_rate": 1.9822825351436952e-05,
|
| 765 |
+
"loss": 1.1265,
|
| 766 |
+
"step": 5400
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.4850480598077608,
|
| 770 |
+
"grad_norm": Infinity,
|
| 771 |
+
"learning_rate": 1.9819535427005925e-05,
|
| 772 |
+
"loss": 0.987,
|
| 773 |
+
"step": 5450
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.489498042007832,
|
| 777 |
+
"grad_norm": 2.1377389430999756,
|
| 778 |
+
"learning_rate": 1.981628220800391e-05,
|
| 779 |
+
"loss": 1.1994,
|
| 780 |
+
"step": 5500
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.4939480242079032,
|
| 784 |
+
"grad_norm": 1.4191107749938965,
|
| 785 |
+
"learning_rate": 1.9812932919950892e-05,
|
| 786 |
+
"loss": 1.0367,
|
| 787 |
+
"step": 5550
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.4983980064079744,
|
| 791 |
+
"grad_norm": 1.5782831907272339,
|
| 792 |
+
"learning_rate": 1.9809553665465705e-05,
|
| 793 |
+
"loss": 1.2628,
|
| 794 |
+
"step": 5600
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.5028479886080456,
|
| 798 |
+
"grad_norm": 1.0732156038284302,
|
| 799 |
+
"learning_rate": 1.980614445486781e-05,
|
| 800 |
+
"loss": 0.946,
|
| 801 |
+
"step": 5650
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.5072979708081168,
|
| 805 |
+
"grad_norm": 1.3754124641418457,
|
| 806 |
+
"learning_rate": 1.9802705298568146e-05,
|
| 807 |
+
"loss": 1.0594,
|
| 808 |
+
"step": 5700
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.511747953008188,
|
| 812 |
+
"grad_norm": 1.3374049663543701,
|
| 813 |
+
"learning_rate": 1.9799236207069107e-05,
|
| 814 |
+
"loss": 1.16,
|
| 815 |
+
"step": 5750
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.5161979352082592,
|
| 819 |
+
"grad_norm": 0.9600222110748291,
|
| 820 |
+
"learning_rate": 1.9795737190964495e-05,
|
| 821 |
+
"loss": 1.2729,
|
| 822 |
+
"step": 5800
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.5206479174083304,
|
| 826 |
+
"grad_norm": 2.389089345932007,
|
| 827 |
+
"learning_rate": 1.9792208260939496e-05,
|
| 828 |
+
"loss": 0.8978,
|
| 829 |
+
"step": 5850
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.5250978996084016,
|
| 833 |
+
"grad_norm": 1.7863914966583252,
|
| 834 |
+
"learning_rate": 1.9788649427770656e-05,
|
| 835 |
+
"loss": 1.1304,
|
| 836 |
+
"step": 5900
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.5295478818084728,
|
| 840 |
+
"grad_norm": 7.10957670211792,
|
| 841 |
+
"learning_rate": 1.9785060702325817e-05,
|
| 842 |
+
"loss": 1.4896,
|
| 843 |
+
"step": 5950
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.533997864008544,
|
| 847 |
+
"grad_norm": 2.2545292377471924,
|
| 848 |
+
"learning_rate": 1.978144209556413e-05,
|
| 849 |
+
"loss": 1.2495,
|
| 850 |
+
"step": 6000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.5384478462086152,
|
| 854 |
+
"grad_norm": 1.3546550273895264,
|
| 855 |
+
"learning_rate": 1.9777793618535977e-05,
|
| 856 |
+
"loss": 1.1406,
|
| 857 |
+
"step": 6050
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.5428978284086864,
|
| 861 |
+
"grad_norm": 3.378833532333374,
|
| 862 |
+
"learning_rate": 1.9774115282382972e-05,
|
| 863 |
+
"loss": 1.2241,
|
| 864 |
+
"step": 6100
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.5473478106087576,
|
| 868 |
+
"grad_norm": 17.440778732299805,
|
| 869 |
+
"learning_rate": 1.9770407098337895e-05,
|
| 870 |
+
"loss": 1.0015,
|
| 871 |
+
"step": 6150
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.5517977928088288,
|
| 875 |
+
"grad_norm": 0.8993490934371948,
|
| 876 |
+
"learning_rate": 1.9766669077724695e-05,
|
| 877 |
+
"loss": 1.028,
|
| 878 |
+
"step": 6200
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.5562477750089,
|
| 882 |
+
"grad_norm": 9.617663383483887,
|
| 883 |
+
"learning_rate": 1.9762901231958414e-05,
|
| 884 |
+
"loss": 1.0712,
|
| 885 |
+
"step": 6250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.5606977572089712,
|
| 889 |
+
"grad_norm": 3.0811498165130615,
|
| 890 |
+
"learning_rate": 1.9759103572545192e-05,
|
| 891 |
+
"loss": 1.0916,
|
| 892 |
+
"step": 6300
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.5651477394090424,
|
| 896 |
+
"grad_norm": 12.106643676757812,
|
| 897 |
+
"learning_rate": 1.97552761110822e-05,
|
| 898 |
+
"loss": 1.1821,
|
| 899 |
+
"step": 6350
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.5695977216091136,
|
| 903 |
+
"grad_norm": 1.0771924257278442,
|
| 904 |
+
"learning_rate": 1.975141885925762e-05,
|
| 905 |
+
"loss": 1.1795,
|
| 906 |
+
"step": 6400
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.5740477038091848,
|
| 910 |
+
"grad_norm": 10.235311508178711,
|
| 911 |
+
"learning_rate": 1.974753182885061e-05,
|
| 912 |
+
"loss": 0.9752,
|
| 913 |
+
"step": 6450
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.578497686009256,
|
| 917 |
+
"grad_norm": 0.8106779456138611,
|
| 918 |
+
"learning_rate": 1.9743615031731267e-05,
|
| 919 |
+
"loss": 0.846,
|
| 920 |
+
"step": 6500
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.5829476682093272,
|
| 924 |
+
"grad_norm": 0.7819272875785828,
|
| 925 |
+
"learning_rate": 1.9739668479860583e-05,
|
| 926 |
+
"loss": 1.1892,
|
| 927 |
+
"step": 6550
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.5873976504093984,
|
| 931 |
+
"grad_norm": 13.416181564331055,
|
| 932 |
+
"learning_rate": 1.9735692185290415e-05,
|
| 933 |
+
"loss": 0.9261,
|
| 934 |
+
"step": 6600
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.5918476326094696,
|
| 938 |
+
"grad_norm": 1.678322196006775,
|
| 939 |
+
"learning_rate": 1.9731686160163452e-05,
|
| 940 |
+
"loss": 1.0477,
|
| 941 |
+
"step": 6650
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.5962976148095408,
|
| 945 |
+
"grad_norm": 1.0335452556610107,
|
| 946 |
+
"learning_rate": 1.972765041671317e-05,
|
| 947 |
+
"loss": 1.1307,
|
| 948 |
+
"step": 6700
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.600747597009612,
|
| 952 |
+
"grad_norm": 11.833608627319336,
|
| 953 |
+
"learning_rate": 1.972358496726379e-05,
|
| 954 |
+
"loss": 1.278,
|
| 955 |
+
"step": 6750
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.6051975792096832,
|
| 959 |
+
"grad_norm": 1.0137460231781006,
|
| 960 |
+
"learning_rate": 1.9719489824230268e-05,
|
| 961 |
+
"loss": 0.9707,
|
| 962 |
+
"step": 6800
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.6096475614097544,
|
| 966 |
+
"grad_norm": 1.0877763032913208,
|
| 967 |
+
"learning_rate": 1.971536500011822e-05,
|
| 968 |
+
"loss": 1.0194,
|
| 969 |
+
"step": 6850
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.6140975436098256,
|
| 973 |
+
"grad_norm": 0.6494864821434021,
|
| 974 |
+
"learning_rate": 1.9711210507523906e-05,
|
| 975 |
+
"loss": 1.223,
|
| 976 |
+
"step": 6900
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.6185475258098968,
|
| 980 |
+
"grad_norm": 1.7761880159378052,
|
| 981 |
+
"learning_rate": 1.970702635913419e-05,
|
| 982 |
+
"loss": 1.1327,
|
| 983 |
+
"step": 6950
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.622997508009968,
|
| 987 |
+
"grad_norm": 2.3199312686920166,
|
| 988 |
+
"learning_rate": 1.9702812567726493e-05,
|
| 989 |
+
"loss": 1.1433,
|
| 990 |
+
"step": 7000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.6274474902100392,
|
| 994 |
+
"grad_norm": 231.38368225097656,
|
| 995 |
+
"learning_rate": 1.9698569146168762e-05,
|
| 996 |
+
"loss": 1.1537,
|
| 997 |
+
"step": 7050
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.6318974724101104,
|
| 1001 |
+
"grad_norm": 1.9424742460250854,
|
| 1002 |
+
"learning_rate": 1.969429610741943e-05,
|
| 1003 |
+
"loss": 0.8475,
|
| 1004 |
+
"step": 7100
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.6363474546101816,
|
| 1008 |
+
"grad_norm": 1.5187716484069824,
|
| 1009 |
+
"learning_rate": 1.9689993464527363e-05,
|
| 1010 |
+
"loss": 1.1439,
|
| 1011 |
+
"step": 7150
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.6407974368102528,
|
| 1015 |
+
"grad_norm": 0.7318978309631348,
|
| 1016 |
+
"learning_rate": 1.968566123063185e-05,
|
| 1017 |
+
"loss": 0.9806,
|
| 1018 |
+
"step": 7200
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.645247419010324,
|
| 1022 |
+
"grad_norm": 1.2728520631790161,
|
| 1023 |
+
"learning_rate": 1.9681299418962524e-05,
|
| 1024 |
+
"loss": 1.2548,
|
| 1025 |
+
"step": 7250
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.6496974012103952,
|
| 1029 |
+
"grad_norm": 2.5126068592071533,
|
| 1030 |
+
"learning_rate": 1.9676908042839355e-05,
|
| 1031 |
+
"loss": 1.0031,
|
| 1032 |
+
"step": 7300
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.6541473834104664,
|
| 1036 |
+
"grad_norm": 0.7228437662124634,
|
| 1037 |
+
"learning_rate": 1.9672487115672594e-05,
|
| 1038 |
+
"loss": 1.1321,
|
| 1039 |
+
"step": 7350
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.6585973656105376,
|
| 1043 |
+
"grad_norm": 1.3764936923980713,
|
| 1044 |
+
"learning_rate": 1.966803665096273e-05,
|
| 1045 |
+
"loss": 0.9916,
|
| 1046 |
+
"step": 7400
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.6630473478106088,
|
| 1050 |
+
"grad_norm": 1.3645603656768799,
|
| 1051 |
+
"learning_rate": 1.9663556662300454e-05,
|
| 1052 |
+
"loss": 1.0035,
|
| 1053 |
+
"step": 7450
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.66749733001068,
|
| 1057 |
+
"grad_norm": 0.848249077796936,
|
| 1058 |
+
"learning_rate": 1.9659047163366622e-05,
|
| 1059 |
+
"loss": 1.1513,
|
| 1060 |
+
"step": 7500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.6719473122107511,
|
| 1064 |
+
"grad_norm": 1.5419740676879883,
|
| 1065 |
+
"learning_rate": 1.9654508167932195e-05,
|
| 1066 |
+
"loss": 1.163,
|
| 1067 |
+
"step": 7550
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.6763972944108223,
|
| 1071 |
+
"grad_norm": 22.703840255737305,
|
| 1072 |
+
"learning_rate": 1.9649939689858225e-05,
|
| 1073 |
+
"loss": 1.3058,
|
| 1074 |
+
"step": 7600
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.6808472766108935,
|
| 1078 |
+
"grad_norm": 0.5974789261817932,
|
| 1079 |
+
"learning_rate": 1.9645341743095786e-05,
|
| 1080 |
+
"loss": 0.9678,
|
| 1081 |
+
"step": 7650
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.6852972588109647,
|
| 1085 |
+
"grad_norm": 1.0212652683258057,
|
| 1086 |
+
"learning_rate": 1.9640714341685947e-05,
|
| 1087 |
+
"loss": 1.1219,
|
| 1088 |
+
"step": 7700
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.6897472410110359,
|
| 1092 |
+
"grad_norm": 46.52585983276367,
|
| 1093 |
+
"learning_rate": 1.9636057499759724e-05,
|
| 1094 |
+
"loss": 1.0244,
|
| 1095 |
+
"step": 7750
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.6941972232111071,
|
| 1099 |
+
"grad_norm": 1.4065423011779785,
|
| 1100 |
+
"learning_rate": 1.9631371231538035e-05,
|
| 1101 |
+
"loss": 1.0998,
|
| 1102 |
+
"step": 7800
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.6986472054111783,
|
| 1106 |
+
"grad_norm": 0.6876867413520813,
|
| 1107 |
+
"learning_rate": 1.9626655551331665e-05,
|
| 1108 |
+
"loss": 1.2191,
|
| 1109 |
+
"step": 7850
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.7030971876112495,
|
| 1113 |
+
"grad_norm": 1.2235878705978394,
|
| 1114 |
+
"learning_rate": 1.962191047354121e-05,
|
| 1115 |
+
"loss": 1.1293,
|
| 1116 |
+
"step": 7900
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.7075471698113207,
|
| 1120 |
+
"grad_norm": 1.5235185623168945,
|
| 1121 |
+
"learning_rate": 1.9617136012657045e-05,
|
| 1122 |
+
"loss": 1.0222,
|
| 1123 |
+
"step": 7950
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.7119971520113919,
|
| 1127 |
+
"grad_norm": 2.0007951259613037,
|
| 1128 |
+
"learning_rate": 1.9612332183259267e-05,
|
| 1129 |
+
"loss": 1.0209,
|
| 1130 |
+
"step": 8000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.7164471342114631,
|
| 1134 |
+
"grad_norm": 0.7732981443405151,
|
| 1135 |
+
"learning_rate": 1.9607499000017668e-05,
|
| 1136 |
+
"loss": 1.1007,
|
| 1137 |
+
"step": 8050
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.7208971164115343,
|
| 1141 |
+
"grad_norm": 3.4698424339294434,
|
| 1142 |
+
"learning_rate": 1.9602636477691674e-05,
|
| 1143 |
+
"loss": 1.253,
|
| 1144 |
+
"step": 8100
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.7253470986116055,
|
| 1148 |
+
"grad_norm": 0.8018836379051208,
|
| 1149 |
+
"learning_rate": 1.9597744631130298e-05,
|
| 1150 |
+
"loss": 1.186,
|
| 1151 |
+
"step": 8150
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.7297970808116767,
|
| 1155 |
+
"grad_norm": 1.1866015195846558,
|
| 1156 |
+
"learning_rate": 1.9592823475272117e-05,
|
| 1157 |
+
"loss": 1.1985,
|
| 1158 |
+
"step": 8200
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.7342470630117479,
|
| 1162 |
+
"grad_norm": 1.5124443769454956,
|
| 1163 |
+
"learning_rate": 1.9587873025145202e-05,
|
| 1164 |
+
"loss": 0.9594,
|
| 1165 |
+
"step": 8250
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.7386970452118191,
|
| 1169 |
+
"grad_norm": 10.030634880065918,
|
| 1170 |
+
"learning_rate": 1.958289329586709e-05,
|
| 1171 |
+
"loss": 1.4065,
|
| 1172 |
+
"step": 8300
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.7431470274118903,
|
| 1176 |
+
"grad_norm": 1.049864411354065,
|
| 1177 |
+
"learning_rate": 1.957788430264472e-05,
|
| 1178 |
+
"loss": 1.0799,
|
| 1179 |
+
"step": 8350
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.7475970096119615,
|
| 1183 |
+
"grad_norm": 0.6957271695137024,
|
| 1184 |
+
"learning_rate": 1.9572846060774403e-05,
|
| 1185 |
+
"loss": 1.1008,
|
| 1186 |
+
"step": 8400
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.7520469918120327,
|
| 1190 |
+
"grad_norm": 1.6415716409683228,
|
| 1191 |
+
"learning_rate": 1.9567880221530444e-05,
|
| 1192 |
+
"loss": 1.1157,
|
| 1193 |
+
"step": 8450
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.7564969740121039,
|
| 1197 |
+
"grad_norm": 5.416161060333252,
|
| 1198 |
+
"learning_rate": 1.9562784112813907e-05,
|
| 1199 |
+
"loss": 1.156,
|
| 1200 |
+
"step": 8500
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.7609469562121751,
|
| 1204 |
+
"grad_norm": 22.172027587890625,
|
| 1205 |
+
"learning_rate": 1.955765880156191e-05,
|
| 1206 |
+
"loss": 1.3024,
|
| 1207 |
+
"step": 8550
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.7653969384122463,
|
| 1211 |
+
"grad_norm": 1.2330561876296997,
|
| 1212 |
+
"learning_rate": 1.9552504303425986e-05,
|
| 1213 |
+
"loss": 1.1647,
|
| 1214 |
+
"step": 8600
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.7698469206123175,
|
| 1218 |
+
"grad_norm": 1.1770780086517334,
|
| 1219 |
+
"learning_rate": 1.9547320634146767e-05,
|
| 1220 |
+
"loss": 0.9177,
|
| 1221 |
+
"step": 8650
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.7742969028123887,
|
| 1225 |
+
"grad_norm": 3.6036808490753174,
|
| 1226 |
+
"learning_rate": 1.9542107809553995e-05,
|
| 1227 |
+
"loss": 1.147,
|
| 1228 |
+
"step": 8700
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.7787468850124599,
|
| 1232 |
+
"grad_norm": 0.9867936968803406,
|
| 1233 |
+
"learning_rate": 1.9536865845566425e-05,
|
| 1234 |
+
"loss": 0.9828,
|
| 1235 |
+
"step": 8750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.7831968672125311,
|
| 1239 |
+
"grad_norm": 17.20427894592285,
|
| 1240 |
+
"learning_rate": 1.953159475819181e-05,
|
| 1241 |
+
"loss": 1.127,
|
| 1242 |
+
"step": 8800
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.7876468494126023,
|
| 1246 |
+
"grad_norm": 0.6954526305198669,
|
| 1247 |
+
"learning_rate": 1.952629456352683e-05,
|
| 1248 |
+
"loss": 0.8992,
|
| 1249 |
+
"step": 8850
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.7920968316126735,
|
| 1253 |
+
"grad_norm": 0.7507011890411377,
|
| 1254 |
+
"learning_rate": 1.9520965277757054e-05,
|
| 1255 |
+
"loss": 1.2564,
|
| 1256 |
+
"step": 8900
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.7965468138127447,
|
| 1260 |
+
"grad_norm": 2.2453718185424805,
|
| 1261 |
+
"learning_rate": 1.9515606917156904e-05,
|
| 1262 |
+
"loss": 0.984,
|
| 1263 |
+
"step": 8950
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.8009967960128159,
|
| 1267 |
+
"grad_norm": 1.342645287513733,
|
| 1268 |
+
"learning_rate": 1.9510219498089563e-05,
|
| 1269 |
+
"loss": 1.1199,
|
| 1270 |
+
"step": 9000
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.8054467782128871,
|
| 1274 |
+
"grad_norm": 1.5172566175460815,
|
| 1275 |
+
"learning_rate": 1.950480303700697e-05,
|
| 1276 |
+
"loss": 0.9538,
|
| 1277 |
+
"step": 9050
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.8098967604129583,
|
| 1281 |
+
"grad_norm": 1.8109244108200073,
|
| 1282 |
+
"learning_rate": 1.9499357550449745e-05,
|
| 1283 |
+
"loss": 1.0505,
|
| 1284 |
+
"step": 9100
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.8143467426130295,
|
| 1288 |
+
"grad_norm": 14.07536792755127,
|
| 1289 |
+
"learning_rate": 1.949388305504715e-05,
|
| 1290 |
+
"loss": 1.1659,
|
| 1291 |
+
"step": 9150
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.8187967248131007,
|
| 1295 |
+
"grad_norm": 0.8219563364982605,
|
| 1296 |
+
"learning_rate": 1.9488379567517032e-05,
|
| 1297 |
+
"loss": 1.1572,
|
| 1298 |
+
"step": 9200
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.8232467070131719,
|
| 1302 |
+
"grad_norm": 0.7456687688827515,
|
| 1303 |
+
"learning_rate": 1.9482847104665765e-05,
|
| 1304 |
+
"loss": 1.0114,
|
| 1305 |
+
"step": 9250
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.8276966892132431,
|
| 1309 |
+
"grad_norm": 2.4477434158325195,
|
| 1310 |
+
"learning_rate": 1.9477285683388218e-05,
|
| 1311 |
+
"loss": 1.1338,
|
| 1312 |
+
"step": 9300
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.8321466714133143,
|
| 1316 |
+
"grad_norm": 1.7693390846252441,
|
| 1317 |
+
"learning_rate": 1.947169532066769e-05,
|
| 1318 |
+
"loss": 0.9649,
|
| 1319 |
+
"step": 9350
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.8365966536133855,
|
| 1323 |
+
"grad_norm": 13.62708568572998,
|
| 1324 |
+
"learning_rate": 1.946607603357585e-05,
|
| 1325 |
+
"loss": 1.0521,
|
| 1326 |
+
"step": 9400
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.8410466358134567,
|
| 1330 |
+
"grad_norm": 2.1173110008239746,
|
| 1331 |
+
"learning_rate": 1.9460427839272714e-05,
|
| 1332 |
+
"loss": 1.4169,
|
| 1333 |
+
"step": 9450
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.8454966180135279,
|
| 1337 |
+
"grad_norm": 0.8660404682159424,
|
| 1338 |
+
"learning_rate": 1.9454750755006557e-05,
|
| 1339 |
+
"loss": 0.8661,
|
| 1340 |
+
"step": 9500
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.8499466002135991,
|
| 1344 |
+
"grad_norm": 9.612180709838867,
|
| 1345 |
+
"learning_rate": 1.9449044798113888e-05,
|
| 1346 |
+
"loss": 1.1864,
|
| 1347 |
+
"step": 9550
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.8543965824136703,
|
| 1351 |
+
"grad_norm": 0.7924606204032898,
|
| 1352 |
+
"learning_rate": 1.9443309986019377e-05,
|
| 1353 |
+
"loss": 1.1295,
|
| 1354 |
+
"step": 9600
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.8588465646137415,
|
| 1358 |
+
"grad_norm": 0.5419692397117615,
|
| 1359 |
+
"learning_rate": 1.9437546336235824e-05,
|
| 1360 |
+
"loss": 0.9944,
|
| 1361 |
+
"step": 9650
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.8632965468138127,
|
| 1365 |
+
"grad_norm": 2.778602123260498,
|
| 1366 |
+
"learning_rate": 1.943175386636408e-05,
|
| 1367 |
+
"loss": 1.3265,
|
| 1368 |
+
"step": 9700
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.8677465290138839,
|
| 1372 |
+
"grad_norm": 2.985241413116455,
|
| 1373 |
+
"learning_rate": 1.942593259409301e-05,
|
| 1374 |
+
"loss": 1.0673,
|
| 1375 |
+
"step": 9750
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.8721965112139551,
|
| 1379 |
+
"grad_norm": 3.0507829189300537,
|
| 1380 |
+
"learning_rate": 1.9420082537199437e-05,
|
| 1381 |
+
"loss": 1.1267,
|
| 1382 |
+
"step": 9800
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.8766464934140263,
|
| 1386 |
+
"grad_norm": 1.0891329050064087,
|
| 1387 |
+
"learning_rate": 1.9414203713548086e-05,
|
| 1388 |
+
"loss": 1.1279,
|
| 1389 |
+
"step": 9850
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.8810964756140975,
|
| 1393 |
+
"grad_norm": 2.639254570007324,
|
| 1394 |
+
"learning_rate": 1.9408296141091533e-05,
|
| 1395 |
+
"loss": 1.3157,
|
| 1396 |
+
"step": 9900
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.8855464578141687,
|
| 1400 |
+
"grad_norm": 2.320467710494995,
|
| 1401 |
+
"learning_rate": 1.9402359837870128e-05,
|
| 1402 |
+
"loss": 0.9687,
|
| 1403 |
+
"step": 9950
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.8899964400142399,
|
| 1407 |
+
"grad_norm": 1.3457088470458984,
|
| 1408 |
+
"learning_rate": 1.939639482201198e-05,
|
| 1409 |
+
"loss": 0.8925,
|
| 1410 |
+
"step": 10000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.8944464222143111,
|
| 1414 |
+
"grad_norm": 1.1230852603912354,
|
| 1415 |
+
"learning_rate": 1.9390401111732868e-05,
|
| 1416 |
+
"loss": 1.0535,
|
| 1417 |
+
"step": 10050
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.8988964044143823,
|
| 1421 |
+
"grad_norm": 2.784928798675537,
|
| 1422 |
+
"learning_rate": 1.93843787253362e-05,
|
| 1423 |
+
"loss": 1.1733,
|
| 1424 |
+
"step": 10100
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.9033463866144535,
|
| 1428 |
+
"grad_norm": 1.3313930034637451,
|
| 1429 |
+
"learning_rate": 1.9378327681212954e-05,
|
| 1430 |
+
"loss": 1.0189,
|
| 1431 |
+
"step": 10150
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.9077963688145247,
|
| 1435 |
+
"grad_norm": 1.4785683155059814,
|
| 1436 |
+
"learning_rate": 1.9372247997841623e-05,
|
| 1437 |
+
"loss": 1.1516,
|
| 1438 |
+
"step": 10200
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.912246351014596,
|
| 1442 |
+
"grad_norm": 4.558147430419922,
|
| 1443 |
+
"learning_rate": 1.936613969378815e-05,
|
| 1444 |
+
"loss": 1.3025,
|
| 1445 |
+
"step": 10250
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.9166963332146671,
|
| 1449 |
+
"grad_norm": 1.1733040809631348,
|
| 1450 |
+
"learning_rate": 1.93600027877059e-05,
|
| 1451 |
+
"loss": 1.1425,
|
| 1452 |
+
"step": 10300
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.9211463154147383,
|
| 1456 |
+
"grad_norm": 11.623977661132812,
|
| 1457 |
+
"learning_rate": 1.935383729833555e-05,
|
| 1458 |
+
"loss": 1.0945,
|
| 1459 |
+
"step": 10350
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.9255962976148095,
|
| 1463 |
+
"grad_norm": 2.0317745208740234,
|
| 1464 |
+
"learning_rate": 1.9347643244505098e-05,
|
| 1465 |
+
"loss": 0.9415,
|
| 1466 |
+
"step": 10400
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.9300462798148807,
|
| 1470 |
+
"grad_norm": 1.0777006149291992,
|
| 1471 |
+
"learning_rate": 1.934142064512974e-05,
|
| 1472 |
+
"loss": 0.9,
|
| 1473 |
+
"step": 10450
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.934496262014952,
|
| 1477 |
+
"grad_norm": 0.9465547800064087,
|
| 1478 |
+
"learning_rate": 1.9335169519211873e-05,
|
| 1479 |
+
"loss": 1.1661,
|
| 1480 |
+
"step": 10500
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.9389462442150232,
|
| 1484 |
+
"grad_norm": 3.3057515621185303,
|
| 1485 |
+
"learning_rate": 1.9328889885840982e-05,
|
| 1486 |
+
"loss": 1.0773,
|
| 1487 |
+
"step": 10550
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.9433962264150944,
|
| 1491 |
+
"grad_norm": 1.0848942995071411,
|
| 1492 |
+
"learning_rate": 1.932258176419362e-05,
|
| 1493 |
+
"loss": 0.9374,
|
| 1494 |
+
"step": 10600
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.9478462086151656,
|
| 1498 |
+
"grad_norm": 0.6923954486846924,
|
| 1499 |
+
"learning_rate": 1.931624517353334e-05,
|
| 1500 |
+
"loss": 0.8315,
|
| 1501 |
+
"step": 10650
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.9522961908152368,
|
| 1505 |
+
"grad_norm": 0.835031270980835,
|
| 1506 |
+
"learning_rate": 1.930988013321062e-05,
|
| 1507 |
+
"loss": 1.1184,
|
| 1508 |
+
"step": 10700
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.956746173015308,
|
| 1512 |
+
"grad_norm": 0.8372194170951843,
|
| 1513 |
+
"learning_rate": 1.9303486662662824e-05,
|
| 1514 |
+
"loss": 0.8965,
|
| 1515 |
+
"step": 10750
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.9611961552153792,
|
| 1519 |
+
"grad_norm": 1.5202910900115967,
|
| 1520 |
+
"learning_rate": 1.9297064781414142e-05,
|
| 1521 |
+
"loss": 1.1413,
|
| 1522 |
+
"step": 10800
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.9656461374154504,
|
| 1526 |
+
"grad_norm": 17.712987899780273,
|
| 1527 |
+
"learning_rate": 1.929061450907551e-05,
|
| 1528 |
+
"loss": 0.9889,
|
| 1529 |
+
"step": 10850
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.9700961196155216,
|
| 1533 |
+
"grad_norm": 0.6960763931274414,
|
| 1534 |
+
"learning_rate": 1.9284135865344576e-05,
|
| 1535 |
+
"loss": 1.2101,
|
| 1536 |
+
"step": 10900
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.9745461018155928,
|
| 1540 |
+
"grad_norm": 0.6224497556686401,
|
| 1541 |
+
"learning_rate": 1.927762887000562e-05,
|
| 1542 |
+
"loss": 0.853,
|
| 1543 |
+
"step": 10950
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.978996084015664,
|
| 1547 |
+
"grad_norm": 2.1982674598693848,
|
| 1548 |
+
"learning_rate": 1.9271093542929508e-05,
|
| 1549 |
+
"loss": 1.2139,
|
| 1550 |
+
"step": 11000
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.9834460662157352,
|
| 1554 |
+
"grad_norm": 3.0297718048095703,
|
| 1555 |
+
"learning_rate": 1.9264529904073614e-05,
|
| 1556 |
+
"loss": 1.201,
|
| 1557 |
+
"step": 11050
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.9878960484158064,
|
| 1561 |
+
"grad_norm": 1.381274938583374,
|
| 1562 |
+
"learning_rate": 1.9257937973481778e-05,
|
| 1563 |
+
"loss": 1.1065,
|
| 1564 |
+
"step": 11100
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.9923460306158776,
|
| 1568 |
+
"grad_norm": 20.468204498291016,
|
| 1569 |
+
"learning_rate": 1.925131777128424e-05,
|
| 1570 |
+
"loss": 1.3885,
|
| 1571 |
+
"step": 11150
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.9967960128159488,
|
| 1575 |
+
"grad_norm": 0.8038458824157715,
|
| 1576 |
+
"learning_rate": 1.9244669317697563e-05,
|
| 1577 |
+
"loss": 1.4847,
|
| 1578 |
+
"step": 11200
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.0,
|
| 1582 |
+
"eval_f1_homophobe": 0.7517241379310344,
|
| 1583 |
+
"eval_f1_macro": 0.5682024245488293,
|
| 1584 |
+
"eval_f1_micro": 0.6462405673243022,
|
| 1585 |
+
"eval_f1_otherhate": 0.5995331777259086,
|
| 1586 |
+
"eval_f1_racist": 0.6786310517529215,
|
| 1587 |
+
"eval_f1_religion": 0.20270270270270271,
|
| 1588 |
+
"eval_f1_sexist": 0.608421052631579,
|
| 1589 |
+
"eval_loss": 1.4235976934432983,
|
| 1590 |
+
"eval_roc_homophobe": 0.8922838430419266,
|
| 1591 |
+
"eval_roc_macro": 0.7886598443962021,
|
| 1592 |
+
"eval_roc_otherhate": 0.8324156169761214,
|
| 1593 |
+
"eval_roc_racist": 0.7609558549233864,
|
| 1594 |
+
"eval_roc_religion": 0.635975612667281,
|
| 1595 |
+
"eval_roc_sexist": 0.8216682943722944,
|
| 1596 |
+
"eval_runtime": 20.8847,
|
| 1597 |
+
"eval_samples_per_second": 239.41,
|
| 1598 |
+
"eval_steps_per_second": 7.517,
|
| 1599 |
+
"step": 11236
|
| 1600 |
+
}
|
| 1601 |
+
],
|
| 1602 |
+
"logging_steps": 50,
|
| 1603 |
+
"max_steps": 89888,
|
| 1604 |
+
"num_input_tokens_seen": 0,
|
| 1605 |
+
"num_train_epochs": 8,
|
| 1606 |
+
"save_steps": 500,
|
| 1607 |
+
"stateful_callbacks": {
|
| 1608 |
+
"EarlyStoppingCallback": {
|
| 1609 |
+
"args": {
|
| 1610 |
+
"early_stopping_patience": 3,
|
| 1611 |
+
"early_stopping_threshold": 0.0
|
| 1612 |
+
},
|
| 1613 |
+
"attributes": {
|
| 1614 |
+
"early_stopping_patience_counter": 0
|
| 1615 |
+
}
|
| 1616 |
+
},
|
| 1617 |
+
"TrainerControl": {
|
| 1618 |
+
"args": {
|
| 1619 |
+
"should_epoch_stop": false,
|
| 1620 |
+
"should_evaluate": false,
|
| 1621 |
+
"should_log": false,
|
| 1622 |
+
"should_save": true,
|
| 1623 |
+
"should_training_stop": false
|
| 1624 |
+
},
|
| 1625 |
+
"attributes": {}
|
| 1626 |
+
}
|
| 1627 |
+
},
|
| 1628 |
+
"total_flos": 0.0,
|
| 1629 |
+
"train_batch_size": 12,
|
| 1630 |
+
"trial_name": null,
|
| 1631 |
+
"trial_params": null
|
| 1632 |
+
}
|