Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,89 @@
----
-license: apache-2.0
----
+---
+library_name: LLaMA-3.1-8B-AGNews-SFT
+license: apache-2.0
+datasets:
+- sentence-transformers/agnews
+language:
+- en
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+base_model:
+- meta-llama/Llama-3.1-8B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: LLaMA-3.1-8B-AGNews-SFT
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# train_2024-12-03-21-04-03
+
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the ag_news_train_num dataset.
+
+## Model description
+
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the ag_news_train_num dataset. The model is a transformer-based model that was trained on a large corpus of text data and fine-tuned on the ag_news_train_num dataset. The model is capable of performing text classification tasks and can be used to classify text into one of four categories: World, Sports, Business, and Sci/Tech.
+
+## Intended uses & limitations
+
+### How to use
+
+You can use this model to classify text into one of four categories: World, Sports, Business, and Sci/Tech. To use the model, you can load it using the `transformers` library and pass the text you want to classify to the model. The model will return the predicted category for the text.
+
+### Limitations and bias
+
+The model may not perform well on text that is outside the domain of the training data. The model may also exhibit bias in its predictions based on the biases present in the training data. It is important to be aware of these limitations when using the model and to evaluate its performance on your specific use case.
+
+## Training and evaluation data
+
+### Dataset
+
+The model was fine-tuned on the ag_news_train_num dataset, which is a subset of the AG News dataset. The AG News dataset is a collection of news articles from the AG's corpus of news articles on the web. The ag_news_train_num dataset contains 120,000 news articles from the AG News dataset, with 30,000 articles in each of the four categories: World, Sports, Business, and Sci/Tech.
+
+### Data preprocessing
+
+The data was preprocessed by tokenizing the text using the `transformers` library's tokenizer for the LLaMA-3.1-8B model. The text was tokenized into subword tokens, and the tokens were converted into input features for the model. The input features were then used to train the model on the classification task.
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 256
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 1.0
+
+### Training results
+
+| Class     | Accuracy | Precision | Recall  | F1 Score |
+|-----------|----------|-----------|---------|----------|
+| World     | 95.95%   | 96.87%    | 95.95%  | 96.40%   |
+| Sports    | 99.42%   | 99.00%    | 99.42%  | 99.21%   |
+| Business  | 91.53%   | 93.95%    | 91.53%  | 92.72%   |
+| Sci/Tech  | 94.84%   | 91.99%    | 94.84%  | 93.39%   |
+| Overall (Macro Avg) | 95.43% | 95.45% | 95.43% | 95.43% |
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.4.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.20.1

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9984,
+    "total_flos": 24715131617280.0,
+    "train_loss": 0.19915007105351895,
+    "train_runtime": 2797.252,
+    "train_samples_per_second": 42.899,
+    "train_steps_per_second": 0.167
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "/mnt/petrelfs/tangzinan/LLaMA-Factory/models/LLama3.1-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f0f398785e2d7d83eb7f5d6f2de93e43edea74c85d7722464f18dbbb06cb18d
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb9b9b82e9fdcb762698a4ac84f8a4fa86dc12b7188e6c3c0f4b431b43cf2e3f
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fafde16175d3c624dab4902e6d873ef2bb7ae76d94e1e3a22c91929864bbc2ca
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8037229d1f435004691231989828fd79d4b5046ef83166de3276a443fab02df6
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -0,0 +1,2064 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9984,
+    "total_flos": 24715131617280.0,
+    "train_loss": 0.19915007105351895,
+    "train_runtime": 2797.252,
+    "train_samples_per_second": 42.899,
+    "train_steps_per_second": 0.167
+}

trainer_log.jsonl

@@ -0,0 +1,469 @@
+{"current_steps": 1, "total_steps": 468, "loss": 7.3237, "learning_rate": 1.3333333333333334e-06, "epoch": 0.0021333333333333334, "percentage": 0.21, "elapsed_time": "0:00:14", "remaining_time": "1:49:18"}
+{"current_steps": 2, "total_steps": 468, "loss": 7.1998, "learning_rate": 2.666666666666667e-06, "epoch": 0.004266666666666667, "percentage": 0.43, "elapsed_time": "0:00:19", "remaining_time": "1:15:54"}
+{"current_steps": 3, "total_steps": 468, "loss": 7.036, "learning_rate": 4.000000000000001e-06, "epoch": 0.0064, "percentage": 0.64, "elapsed_time": "0:00:25", "remaining_time": "1:04:38"}
+{"current_steps": 4, "total_steps": 468, "loss": 6.3763, "learning_rate": 5.333333333333334e-06, "epoch": 0.008533333333333334, "percentage": 0.85, "elapsed_time": "0:00:30", "remaining_time": "0:58:51"}
+{"current_steps": 5, "total_steps": 468, "loss": 4.6166, "learning_rate": 6.666666666666667e-06, "epoch": 0.010666666666666666, "percentage": 1.07, "elapsed_time": "0:00:36", "remaining_time": "0:55:49"}
+{"current_steps": 6, "total_steps": 468, "loss": 3.1298, "learning_rate": 8.000000000000001e-06, "epoch": 0.0128, "percentage": 1.28, "elapsed_time": "0:00:41", "remaining_time": "0:53:17"}
+{"current_steps": 7, "total_steps": 468, "loss": 2.4499, "learning_rate": 9.333333333333334e-06, "epoch": 0.014933333333333333, "percentage": 1.5, "elapsed_time": "0:00:46", "remaining_time": "0:51:24"}
+{"current_steps": 8, "total_steps": 468, "loss": 2.1396, "learning_rate": 1.0666666666666667e-05, "epoch": 0.017066666666666667, "percentage": 1.71, "elapsed_time": "0:00:52", "remaining_time": "0:50:00"}
+{"current_steps": 9, "total_steps": 468, "loss": 2.1943, "learning_rate": 1.2e-05, "epoch": 0.0192, "percentage": 1.92, "elapsed_time": "0:00:57", "remaining_time": "0:48:51"}
+{"current_steps": 10, "total_steps": 468, "loss": 2.0228, "learning_rate": 1.3333333333333333e-05, "epoch": 0.021333333333333333, "percentage": 2.14, "elapsed_time": "0:01:02", "remaining_time": "0:47:54"}
+{"current_steps": 11, "total_steps": 468, "loss": 1.8804, "learning_rate": 1.4666666666666666e-05, "epoch": 0.023466666666666667, "percentage": 2.35, "elapsed_time": "0:01:08", "remaining_time": "0:47:07"}
+{"current_steps": 12, "total_steps": 468, "loss": 1.8405, "learning_rate": 1.6000000000000003e-05, "epoch": 0.0256, "percentage": 2.56, "elapsed_time": "0:01:13", "remaining_time": "0:46:27"}
+{"current_steps": 13, "total_steps": 468, "loss": 1.6634, "learning_rate": 1.7333333333333336e-05, "epoch": 0.027733333333333332, "percentage": 2.78, "elapsed_time": "0:01:18", "remaining_time": "0:45:52"}
+{"current_steps": 14, "total_steps": 468, "loss": 1.585, "learning_rate": 1.866666666666667e-05, "epoch": 0.029866666666666666, "percentage": 2.99, "elapsed_time": "0:01:23", "remaining_time": "0:45:22"}
+{"current_steps": 15, "total_steps": 468, "loss": 1.5327, "learning_rate": 2e-05, "epoch": 0.032, "percentage": 3.21, "elapsed_time": "0:01:29", "remaining_time": "0:44:55"}
+{"current_steps": 16, "total_steps": 468, "loss": 1.6873, "learning_rate": 1.9999759524074374e-05, "epoch": 0.034133333333333335, "percentage": 3.42, "elapsed_time": "0:01:34", "remaining_time": "0:44:30"}
+{"current_steps": 17, "total_steps": 468, "loss": 2.1603, "learning_rate": 1.999903810786324e-05, "epoch": 0.03626666666666667, "percentage": 3.63, "elapsed_time": "0:01:39", "remaining_time": "0:44:07"}
+{"current_steps": 18, "total_steps": 468, "loss": 1.5881, "learning_rate": 1.999783578606323e-05, "epoch": 0.0384, "percentage": 3.85, "elapsed_time": "0:01:45", "remaining_time": "0:43:47"}
+{"current_steps": 19, "total_steps": 468, "loss": 3.0391, "learning_rate": 1.9996152616500244e-05, "epoch": 0.04053333333333333, "percentage": 4.06, "elapsed_time": "0:01:50", "remaining_time": "0:43:28"}
+{"current_steps": 20, "total_steps": 468, "loss": 2.35, "learning_rate": 1.999398868012663e-05, "epoch": 0.042666666666666665, "percentage": 4.27, "elapsed_time": "0:01:55", "remaining_time": "0:43:10"}
+{"current_steps": 21, "total_steps": 468, "loss": 1.385, "learning_rate": 1.9991344081017312e-05, "epoch": 0.0448, "percentage": 4.49, "elapsed_time": "0:02:00", "remaining_time": "0:42:53"}
+{"current_steps": 22, "total_steps": 468, "loss": 2.4298, "learning_rate": 1.998821894636477e-05, "epoch": 0.046933333333333334, "percentage": 4.7, "elapsed_time": "0:02:06", "remaining_time": "0:42:38"}
+{"current_steps": 23, "total_steps": 468, "loss": 1.1715, "learning_rate": 1.9984613426472934e-05, "epoch": 0.04906666666666667, "percentage": 4.91, "elapsed_time": "0:02:11", "remaining_time": "0:42:23"}
+{"current_steps": 24, "total_steps": 468, "loss": 1.0305, "learning_rate": 1.9980527694749952e-05, "epoch": 0.0512, "percentage": 5.13, "elapsed_time": "0:02:16", "remaining_time": "0:42:09"}
+{"current_steps": 25, "total_steps": 468, "loss": 0.8896, "learning_rate": 1.9975961947699848e-05, "epoch": 0.05333333333333334, "percentage": 5.34, "elapsed_time": "0:02:21", "remaining_time": "0:41:56"}
+{"current_steps": 26, "total_steps": 468, "loss": 1.3138, "learning_rate": 1.9970916404913068e-05, "epoch": 0.055466666666666664, "percentage": 5.56, "elapsed_time": "0:02:27", "remaining_time": "0:41:43"}
+{"current_steps": 27, "total_steps": 468, "loss": 0.7626, "learning_rate": 1.996539130905593e-05, "epoch": 0.0576, "percentage": 5.77, "elapsed_time": "0:02:32", "remaining_time": "0:41:30"}
+{"current_steps": 28, "total_steps": 468, "loss": 0.6847, "learning_rate": 1.9959386925858944e-05, "epoch": 0.05973333333333333, "percentage": 5.98, "elapsed_time": "0:02:37", "remaining_time": "0:41:19"}
+{"current_steps": 29, "total_steps": 468, "loss": 0.5946, "learning_rate": 1.9952903544104026e-05, "epoch": 0.06186666666666667, "percentage": 6.2, "elapsed_time": "0:02:43", "remaining_time": "0:41:08"}
+{"current_steps": 30, "total_steps": 468, "loss": 0.5467, "learning_rate": 1.9945941475610623e-05, "epoch": 0.064, "percentage": 6.41, "elapsed_time": "0:02:48", "remaining_time": "0:40:58"}
+{"current_steps": 31, "total_steps": 468, "loss": 0.4314, "learning_rate": 1.9938501055220712e-05, "epoch": 0.06613333333333334, "percentage": 6.62, "elapsed_time": "0:02:53", "remaining_time": "0:40:48"}
+{"current_steps": 32, "total_steps": 468, "loss": 0.3731, "learning_rate": 1.9930582640782684e-05, "epoch": 0.06826666666666667, "percentage": 6.84, "elapsed_time": "0:02:59", "remaining_time": "0:40:40"}
+{"current_steps": 33, "total_steps": 468, "loss": 0.3163, "learning_rate": 1.9922186613134152e-05, "epoch": 0.0704, "percentage": 7.05, "elapsed_time": "0:03:04", "remaining_time": "0:40:30"}
+{"current_steps": 34, "total_steps": 468, "loss": 0.2417, "learning_rate": 1.9913313376083615e-05, "epoch": 0.07253333333333334, "percentage": 7.26, "elapsed_time": "0:03:09", "remaining_time": "0:40:21"}
+{"current_steps": 35, "total_steps": 468, "loss": 0.2095, "learning_rate": 1.9903963356391057e-05, "epoch": 0.07466666666666667, "percentage": 7.48, "elapsed_time": "0:03:15", "remaining_time": "0:40:14"}
+{"current_steps": 36, "total_steps": 468, "loss": 0.1806, "learning_rate": 1.9894137003747404e-05, "epoch": 0.0768, "percentage": 7.69, "elapsed_time": "0:03:20", "remaining_time": "0:40:05"}
+{"current_steps": 37, "total_steps": 468, "loss": 0.1429, "learning_rate": 1.9883834790752904e-05, "epoch": 0.07893333333333333, "percentage": 7.91, "elapsed_time": "0:03:25", "remaining_time": "0:39:57"}
+{"current_steps": 38, "total_steps": 468, "loss": 0.1052, "learning_rate": 1.98730572128944e-05, "epoch": 0.08106666666666666, "percentage": 8.12, "elapsed_time": "0:03:31", "remaining_time": "0:39:50"}
+{"current_steps": 39, "total_steps": 468, "loss": 0.0877, "learning_rate": 1.986180478852149e-05, "epoch": 0.0832, "percentage": 8.33, "elapsed_time": "0:03:36", "remaining_time": "0:39:43"}
+{"current_steps": 40, "total_steps": 468, "loss": 0.1171, "learning_rate": 1.9850078058821615e-05, "epoch": 0.08533333333333333, "percentage": 8.55, "elapsed_time": "0:03:42", "remaining_time": "0:39:35"}
+{"current_steps": 41, "total_steps": 468, "loss": 0.1014, "learning_rate": 1.9837877587794003e-05, "epoch": 0.08746666666666666, "percentage": 8.76, "elapsed_time": "0:03:47", "remaining_time": "0:39:28"}
+{"current_steps": 42, "total_steps": 468, "loss": 0.0509, "learning_rate": 1.9825203962222573e-05, "epoch": 0.0896, "percentage": 8.97, "elapsed_time": "0:03:52", "remaining_time": "0:39:20"}
+{"current_steps": 43, "total_steps": 468, "loss": 0.0976, "learning_rate": 1.9812057791647687e-05, "epoch": 0.09173333333333333, "percentage": 9.19, "elapsed_time": "0:03:58", "remaining_time": "0:39:13"}
+{"current_steps": 44, "total_steps": 468, "loss": 0.0723, "learning_rate": 1.979843970833686e-05, "epoch": 0.09386666666666667, "percentage": 9.4, "elapsed_time": "0:04:03", "remaining_time": "0:39:05"}
+{"current_steps": 45, "total_steps": 468, "loss": 0.0565, "learning_rate": 1.9784350367254322e-05, "epoch": 0.096, "percentage": 9.62, "elapsed_time": "0:04:08", "remaining_time": "0:38:58"}
+{"current_steps": 46, "total_steps": 468, "loss": 0.0622, "learning_rate": 1.9769790446029543e-05, "epoch": 0.09813333333333334, "percentage": 9.83, "elapsed_time": "0:04:14", "remaining_time": "0:38:51"}
+{"current_steps": 47, "total_steps": 468, "loss": 0.0994, "learning_rate": 1.9754760644924635e-05, "epoch": 0.10026666666666667, "percentage": 10.04, "elapsed_time": "0:04:19", "remaining_time": "0:38:44"}
+{"current_steps": 48, "total_steps": 468, "loss": 0.0682, "learning_rate": 1.9739261686800662e-05, "epoch": 0.1024, "percentage": 10.26, "elapsed_time": "0:04:24", "remaining_time": "0:38:37"}
+{"current_steps": 49, "total_steps": 468, "loss": 0.0703, "learning_rate": 1.9723294317082876e-05, "epoch": 0.10453333333333334, "percentage": 10.47, "elapsed_time": "0:04:30", "remaining_time": "0:38:30"}
+{"current_steps": 50, "total_steps": 468, "loss": 0.0706, "learning_rate": 1.970685930372489e-05, "epoch": 0.10666666666666667, "percentage": 10.68, "elapsed_time": "0:04:35", "remaining_time": "0:38:23"}
+{"current_steps": 51, "total_steps": 468, "loss": 0.0593, "learning_rate": 1.968995743717171e-05, "epoch": 0.1088, "percentage": 10.9, "elapsed_time": "0:04:40", "remaining_time": "0:38:15"}
+{"current_steps": 52, "total_steps": 468, "loss": 0.0935, "learning_rate": 1.967258953032174e-05, "epoch": 0.11093333333333333, "percentage": 11.11, "elapsed_time": "0:04:46", "remaining_time": "0:38:09"}
+{"current_steps": 53, "total_steps": 468, "loss": 0.0859, "learning_rate": 1.965475641848767e-05, "epoch": 0.11306666666666666, "percentage": 11.32, "elapsed_time": "0:04:51", "remaining_time": "0:38:03"}
+{"current_steps": 54, "total_steps": 468, "loss": 0.0838, "learning_rate": 1.963645895935632e-05, "epoch": 0.1152, "percentage": 11.54, "elapsed_time": "0:04:56", "remaining_time": "0:37:56"}
+{"current_steps": 55, "total_steps": 468, "loss": 0.0575, "learning_rate": 1.9617698032947364e-05, "epoch": 0.11733333333333333, "percentage": 11.75, "elapsed_time": "0:05:02", "remaining_time": "0:37:49"}
+{"current_steps": 56, "total_steps": 468, "loss": 0.0494, "learning_rate": 1.9598474541571045e-05, "epoch": 0.11946666666666667, "percentage": 11.97, "elapsed_time": "0:05:07", "remaining_time": "0:37:42"}
+{"current_steps": 57, "total_steps": 468, "loss": 0.059, "learning_rate": 1.9578789409784727e-05, "epoch": 0.1216, "percentage": 12.18, "elapsed_time": "0:05:12", "remaining_time": "0:37:36"}
+{"current_steps": 58, "total_steps": 468, "loss": 0.0468, "learning_rate": 1.9558643584348478e-05, "epoch": 0.12373333333333333, "percentage": 12.39, "elapsed_time": "0:05:18", "remaining_time": "0:37:29"}
+{"current_steps": 59, "total_steps": 468, "loss": 0.0277, "learning_rate": 1.9538038034179496e-05, "epoch": 0.12586666666666665, "percentage": 12.61, "elapsed_time": "0:05:23", "remaining_time": "0:37:23"}
+{"current_steps": 60, "total_steps": 468, "loss": 0.0551, "learning_rate": 1.951697375030553e-05, "epoch": 0.128, "percentage": 12.82, "elapsed_time": "0:05:28", "remaining_time": "0:37:16"}
+{"current_steps": 61, "total_steps": 468, "loss": 0.0583, "learning_rate": 1.949545174581722e-05, "epoch": 0.13013333333333332, "percentage": 13.03, "elapsed_time": "0:05:34", "remaining_time": "0:37:10"}
+{"current_steps": 62, "total_steps": 468, "loss": 0.0552, "learning_rate": 1.9473473055819348e-05, "epoch": 0.13226666666666667, "percentage": 13.25, "elapsed_time": "0:05:39", "remaining_time": "0:37:03"}
+{"current_steps": 63, "total_steps": 468, "loss": 0.0448, "learning_rate": 1.9451038737381078e-05, "epoch": 0.1344, "percentage": 13.46, "elapsed_time": "0:05:44", "remaining_time": "0:36:56"}
+{"current_steps": 64, "total_steps": 468, "loss": 0.0701, "learning_rate": 1.9428149869485113e-05, "epoch": 0.13653333333333334, "percentage": 13.68, "elapsed_time": "0:05:50", "remaining_time": "0:36:50"}
+{"current_steps": 65, "total_steps": 468, "loss": 0.0426, "learning_rate": 1.940480755297579e-05, "epoch": 0.13866666666666666, "percentage": 13.89, "elapsed_time": "0:05:55", "remaining_time": "0:36:43"}
+{"current_steps": 66, "total_steps": 468, "loss": 0.0586, "learning_rate": 1.9381012910506146e-05, "epoch": 0.1408, "percentage": 14.1, "elapsed_time": "0:06:00", "remaining_time": "0:36:37"}
+{"current_steps": 67, "total_steps": 468, "loss": 0.065, "learning_rate": 1.9356767086483908e-05, "epoch": 0.14293333333333333, "percentage": 14.32, "elapsed_time": "0:06:06", "remaining_time": "0:36:30"}
+{"current_steps": 68, "total_steps": 468, "loss": 0.0585, "learning_rate": 1.9332071247016476e-05, "epoch": 0.14506666666666668, "percentage": 14.53, "elapsed_time": "0:06:11", "remaining_time": "0:36:24"}
+{"current_steps": 69, "total_steps": 468, "loss": 0.0444, "learning_rate": 1.930692657985482e-05, "epoch": 0.1472, "percentage": 14.74, "elapsed_time": "0:06:16", "remaining_time": "0:36:17"}
+{"current_steps": 70, "total_steps": 468, "loss": 0.0499, "learning_rate": 1.9281334294336364e-05, "epoch": 0.14933333333333335, "percentage": 14.96, "elapsed_time": "0:06:21", "remaining_time": "0:36:11"}
+{"current_steps": 71, "total_steps": 468, "loss": 0.5615, "learning_rate": 1.9255295621326813e-05, "epoch": 0.15146666666666667, "percentage": 15.17, "elapsed_time": "0:06:27", "remaining_time": "0:36:05"}
+{"current_steps": 72, "total_steps": 468, "loss": 0.0492, "learning_rate": 1.9228811813160972e-05, "epoch": 0.1536, "percentage": 15.38, "elapsed_time": "0:06:32", "remaining_time": "0:35:59"}
+{"current_steps": 73, "total_steps": 468, "loss": 0.0416, "learning_rate": 1.9201884143582496e-05, "epoch": 0.15573333333333333, "percentage": 15.6, "elapsed_time": "0:06:38", "remaining_time": "0:35:53"}
+{"current_steps": 74, "total_steps": 468, "loss": 0.0583, "learning_rate": 1.9174513907682634e-05, "epoch": 0.15786666666666666, "percentage": 15.81, "elapsed_time": "0:06:43", "remaining_time": "0:35:47"}
+{"current_steps": 75, "total_steps": 468, "loss": 0.0522, "learning_rate": 1.9146702421837952e-05, "epoch": 0.16, "percentage": 16.03, "elapsed_time": "0:06:48", "remaining_time": "0:35:41"}
+{"current_steps": 76, "total_steps": 468, "loss": 0.0509, "learning_rate": 1.9118451023647008e-05, "epoch": 0.16213333333333332, "percentage": 16.24, "elapsed_time": "0:06:54", "remaining_time": "0:35:35"}
+{"current_steps": 77, "total_steps": 468, "loss": 0.0424, "learning_rate": 1.908976107186603e-05, "epoch": 0.16426666666666667, "percentage": 16.45, "elapsed_time": "0:06:59", "remaining_time": "0:35:29"}
+{"current_steps": 78, "total_steps": 468, "loss": 0.0605, "learning_rate": 1.906063394634356e-05, "epoch": 0.1664, "percentage": 16.67, "elapsed_time": "0:07:04", "remaining_time": "0:35:23"}
+{"current_steps": 79, "total_steps": 468, "loss": 0.0514, "learning_rate": 1.9031071047954095e-05, "epoch": 0.16853333333333334, "percentage": 16.88, "elapsed_time": "0:07:10", "remaining_time": "0:35:17"}
+{"current_steps": 80, "total_steps": 468, "loss": 0.0526, "learning_rate": 1.90010737985307e-05, "epoch": 0.17066666666666666, "percentage": 17.09, "elapsed_time": "0:07:15", "remaining_time": "0:35:12"}
+{"current_steps": 81, "total_steps": 468, "loss": 0.0565, "learning_rate": 1.8970643640796642e-05, "epoch": 0.1728, "percentage": 17.31, "elapsed_time": "0:07:20", "remaining_time": "0:35:05"}
+{"current_steps": 82, "total_steps": 468, "loss": 0.0596, "learning_rate": 1.893978203829599e-05, "epoch": 0.17493333333333333, "percentage": 17.52, "elapsed_time": "0:07:26", "remaining_time": "0:34:59"}
+{"current_steps": 83, "total_steps": 468, "loss": 0.0528, "learning_rate": 1.8908490475323234e-05, "epoch": 0.17706666666666668, "percentage": 17.74, "elapsed_time": "0:07:31", "remaining_time": "0:34:53"}
+{"current_steps": 84, "total_steps": 468, "loss": 0.0285, "learning_rate": 1.887677045685188e-05, "epoch": 0.1792, "percentage": 17.95, "elapsed_time": "0:07:36", "remaining_time": "0:34:47"}
+{"current_steps": 85, "total_steps": 468, "loss": 0.0575, "learning_rate": 1.8844623508462093e-05, "epoch": 0.18133333333333335, "percentage": 18.16, "elapsed_time": "0:07:42", "remaining_time": "0:34:41"}
+{"current_steps": 86, "total_steps": 468, "loss": 0.0539, "learning_rate": 1.8812051176267307e-05, "epoch": 0.18346666666666667, "percentage": 18.38, "elapsed_time": "0:07:47", "remaining_time": "0:34:35"}
+{"current_steps": 87, "total_steps": 468, "loss": 0.0343, "learning_rate": 1.877905502683987e-05, "epoch": 0.1856, "percentage": 18.59, "elapsed_time": "0:07:52", "remaining_time": "0:34:30"}
+{"current_steps": 88, "total_steps": 468, "loss": 0.0438, "learning_rate": 1.8745636647135693e-05, "epoch": 0.18773333333333334, "percentage": 18.8, "elapsed_time": "0:07:58", "remaining_time": "0:34:24"}
+{"current_steps": 89, "total_steps": 468, "loss": 0.0495, "learning_rate": 1.871179764441794e-05, "epoch": 0.18986666666666666, "percentage": 19.02, "elapsed_time": "0:08:03", "remaining_time": "0:34:18"}
+{"current_steps": 90, "total_steps": 468, "loss": 0.0572, "learning_rate": 1.8677539646179706e-05, "epoch": 0.192, "percentage": 19.23, "elapsed_time": "0:08:08", "remaining_time": "0:34:12"}
+{"current_steps": 91, "total_steps": 468, "loss": 0.049, "learning_rate": 1.8642864300065767e-05, "epoch": 0.19413333333333332, "percentage": 19.44, "elapsed_time": "0:08:13", "remaining_time": "0:34:05"}
+{"current_steps": 92, "total_steps": 468, "loss": 0.0447, "learning_rate": 1.8607773273793298e-05, "epoch": 0.19626666666666667, "percentage": 19.66, "elapsed_time": "0:08:19", "remaining_time": "0:34:00"}
+{"current_steps": 93, "total_steps": 468, "loss": 0.057, "learning_rate": 1.8572268255071718e-05, "epoch": 0.1984, "percentage": 19.87, "elapsed_time": "0:08:24", "remaining_time": "0:33:54"}
+{"current_steps": 94, "total_steps": 468, "loss": 0.0391, "learning_rate": 1.853635095152147e-05, "epoch": 0.20053333333333334, "percentage": 20.09, "elapsed_time": "0:08:29", "remaining_time": "0:33:48"}
+{"current_steps": 95, "total_steps": 468, "loss": 0.0377, "learning_rate": 1.8500023090591917e-05, "epoch": 0.20266666666666666, "percentage": 20.3, "elapsed_time": "0:08:35", "remaining_time": "0:33:42"}
+{"current_steps": 96, "total_steps": 468, "loss": 0.0515, "learning_rate": 1.8463286419478256e-05, "epoch": 0.2048, "percentage": 20.51, "elapsed_time": "0:08:40", "remaining_time": "0:33:36"}
+{"current_steps": 97, "total_steps": 468, "loss": 0.0422, "learning_rate": 1.8426142705037487e-05, "epoch": 0.20693333333333333, "percentage": 20.73, "elapsed_time": "0:08:45", "remaining_time": "0:33:29"}
+{"current_steps": 98, "total_steps": 468, "loss": 0.0521, "learning_rate": 1.8388593733703428e-05, "epoch": 0.20906666666666668, "percentage": 20.94, "elapsed_time": "0:08:50", "remaining_time": "0:33:23"}
+{"current_steps": 99, "total_steps": 468, "loss": 0.0602, "learning_rate": 1.8350641311400813e-05, "epoch": 0.2112, "percentage": 21.15, "elapsed_time": "0:08:56", "remaining_time": "0:33:17"}
+{"current_steps": 100, "total_steps": 468, "loss": 0.0588, "learning_rate": 1.831228726345841e-05, "epoch": 0.21333333333333335, "percentage": 21.37, "elapsed_time": "0:09:01", "remaining_time": "0:33:11"}
+{"current_steps": 101, "total_steps": 468, "loss": 0.0564, "learning_rate": 1.8273533434521262e-05, "epoch": 0.21546666666666667, "percentage": 21.58, "elapsed_time": "0:09:06", "remaining_time": "0:33:05"}
+{"current_steps": 102, "total_steps": 468, "loss": 0.0506, "learning_rate": 1.8234381688461943e-05, "epoch": 0.2176, "percentage": 21.79, "elapsed_time": "0:09:11", "remaining_time": "0:33:00"}
+{"current_steps": 103, "total_steps": 468, "loss": 0.044, "learning_rate": 1.8194833908290933e-05, "epoch": 0.21973333333333334, "percentage": 22.01, "elapsed_time": "0:09:17", "remaining_time": "0:32:54"}
+{"current_steps": 104, "total_steps": 468, "loss": 0.059, "learning_rate": 1.815489199606603e-05, "epoch": 0.22186666666666666, "percentage": 22.22, "elapsed_time": "0:09:22", "remaining_time": "0:32:48"}
+{"current_steps": 105, "total_steps": 468, "loss": 0.0476, "learning_rate": 1.8114557872800906e-05, "epoch": 0.224, "percentage": 22.44, "elapsed_time": "0:09:27", "remaining_time": "0:32:42"}
+{"current_steps": 106, "total_steps": 468, "loss": 0.0314, "learning_rate": 1.8073833478372682e-05, "epoch": 0.22613333333333333, "percentage": 22.65, "elapsed_time": "0:09:33", "remaining_time": "0:32:36"}
+{"current_steps": 107, "total_steps": 468, "loss": 0.0444, "learning_rate": 1.803272077142865e-05, "epoch": 0.22826666666666667, "percentage": 22.86, "elapsed_time": "0:09:38", "remaining_time": "0:32:31"}
+{"current_steps": 108, "total_steps": 468, "loss": 0.0486, "learning_rate": 1.799122172929206e-05, "epoch": 0.2304, "percentage": 23.08, "elapsed_time": "0:09:43", "remaining_time": "0:32:25"}
+{"current_steps": 109, "total_steps": 468, "loss": 0.0311, "learning_rate": 1.794933834786702e-05, "epoch": 0.23253333333333334, "percentage": 23.29, "elapsed_time": "0:09:48", "remaining_time": "0:32:19"}
+{"current_steps": 110, "total_steps": 468, "loss": 0.0665, "learning_rate": 1.7907072641542527e-05, "epoch": 0.23466666666666666, "percentage": 23.5, "elapsed_time": "0:09:54", "remaining_time": "0:32:13"}
+{"current_steps": 111, "total_steps": 468, "loss": 0.0351, "learning_rate": 1.7864426643095537e-05, "epoch": 0.2368, "percentage": 23.72, "elapsed_time": "0:09:59", "remaining_time": "0:32:08"}
+{"current_steps": 112, "total_steps": 468, "loss": 0.0355, "learning_rate": 1.782140240359325e-05, "epoch": 0.23893333333333333, "percentage": 23.93, "elapsed_time": "0:10:04", "remaining_time": "0:32:02"}
+{"current_steps": 113, "total_steps": 468, "loss": 0.0408, "learning_rate": 1.7778001992294426e-05, "epoch": 0.24106666666666668, "percentage": 24.15, "elapsed_time": "0:10:10", "remaining_time": "0:31:56"}
+{"current_steps": 114, "total_steps": 468, "loss": 0.0477, "learning_rate": 1.773422749654988e-05, "epoch": 0.2432, "percentage": 24.36, "elapsed_time": "0:10:15", "remaining_time": "0:31:51"}
+{"current_steps": 115, "total_steps": 468, "loss": 0.037, "learning_rate": 1.769008102170209e-05, "epoch": 0.24533333333333332, "percentage": 24.57, "elapsed_time": "0:10:20", "remaining_time": "0:31:45"}
+{"current_steps": 116, "total_steps": 468, "loss": 0.0356, "learning_rate": 1.7645564690983936e-05, "epoch": 0.24746666666666667, "percentage": 24.79, "elapsed_time": "0:10:26", "remaining_time": "0:31:40"}
+{"current_steps": 117, "total_steps": 468, "loss": 0.0397, "learning_rate": 1.7600680645416583e-05, "epoch": 0.2496, "percentage": 25.0, "elapsed_time": "0:10:31", "remaining_time": "0:31:35"}
+{"current_steps": 118, "total_steps": 468, "loss": 0.0388, "learning_rate": 1.7555431043706517e-05, "epoch": 0.2517333333333333, "percentage": 25.21, "elapsed_time": "0:10:37", "remaining_time": "0:31:29"}
+{"current_steps": 119, "total_steps": 468, "loss": 0.0447, "learning_rate": 1.7509818062141704e-05, "epoch": 0.2538666666666667, "percentage": 25.43, "elapsed_time": "0:10:42", "remaining_time": "0:31:23"}
+{"current_steps": 120, "total_steps": 468, "loss": 0.0265, "learning_rate": 1.746384389448694e-05, "epoch": 0.256, "percentage": 25.64, "elapsed_time": "0:10:47", "remaining_time": "0:31:18"}
+{"current_steps": 121, "total_steps": 468, "loss": 0.0571, "learning_rate": 1.7417510751878324e-05, "epoch": 0.2581333333333333, "percentage": 25.85, "elapsed_time": "0:10:53", "remaining_time": "0:31:12"}
+{"current_steps": 122, "total_steps": 468, "loss": 0.0501, "learning_rate": 1.737082086271693e-05, "epoch": 0.26026666666666665, "percentage": 26.07, "elapsed_time": "0:10:58", "remaining_time": "0:31:07"}
+{"current_steps": 123, "total_steps": 468, "loss": 0.0281, "learning_rate": 1.7323776472561625e-05, "epoch": 0.2624, "percentage": 26.28, "elapsed_time": "0:11:03", "remaining_time": "0:31:01"}
+{"current_steps": 124, "total_steps": 468, "loss": 0.0354, "learning_rate": 1.727637984402106e-05, "epoch": 0.26453333333333334, "percentage": 26.5, "elapsed_time": "0:11:08", "remaining_time": "0:30:55"}
+{"current_steps": 125, "total_steps": 468, "loss": 0.0301, "learning_rate": 1.7228633256644854e-05, "epoch": 0.26666666666666666, "percentage": 26.71, "elapsed_time": "0:11:14", "remaining_time": "0:30:49"}
+{"current_steps": 126, "total_steps": 468, "loss": 0.042, "learning_rate": 1.7180539006813973e-05, "epoch": 0.2688, "percentage": 26.92, "elapsed_time": "0:11:19", "remaining_time": "0:30:44"}
+{"current_steps": 127, "total_steps": 468, "loss": 0.0414, "learning_rate": 1.713209940763026e-05, "epoch": 0.27093333333333336, "percentage": 27.14, "elapsed_time": "0:11:24", "remaining_time": "0:30:38"}
+{"current_steps": 128, "total_steps": 468, "loss": 0.0367, "learning_rate": 1.7083316788805212e-05, "epoch": 0.2730666666666667, "percentage": 27.35, "elapsed_time": "0:11:30", "remaining_time": "0:30:33"}
+{"current_steps": 129, "total_steps": 468, "loss": 0.0384, "learning_rate": 1.7034193496547903e-05, "epoch": 0.2752, "percentage": 27.56, "elapsed_time": "0:11:35", "remaining_time": "0:30:27"}
+{"current_steps": 130, "total_steps": 468, "loss": 0.0687, "learning_rate": 1.6984731893452174e-05, "epoch": 0.2773333333333333, "percentage": 27.78, "elapsed_time": "0:11:40", "remaining_time": "0:30:22"}
+{"current_steps": 131, "total_steps": 468, "loss": 0.0506, "learning_rate": 1.6934934358382987e-05, "epoch": 0.27946666666666664, "percentage": 27.99, "elapsed_time": "0:11:46", "remaining_time": "0:30:16"}
+{"current_steps": 132, "total_steps": 468, "loss": 0.0448, "learning_rate": 1.6884803286362e-05, "epoch": 0.2816, "percentage": 28.21, "elapsed_time": "0:11:51", "remaining_time": "0:30:10"}
+{"current_steps": 133, "total_steps": 468, "loss": 0.0504, "learning_rate": 1.683434108845241e-05, "epoch": 0.28373333333333334, "percentage": 28.42, "elapsed_time": "0:11:56", "remaining_time": "0:30:05"}
+{"current_steps": 134, "total_steps": 468, "loss": 0.0289, "learning_rate": 1.6783550191642962e-05, "epoch": 0.28586666666666666, "percentage": 28.63, "elapsed_time": "0:12:01", "remaining_time": "0:29:59"}
+{"current_steps": 135, "total_steps": 468, "loss": 0.0413, "learning_rate": 1.6732433038731245e-05, "epoch": 0.288, "percentage": 28.85, "elapsed_time": "0:12:07", "remaining_time": "0:29:53"}
+{"current_steps": 136, "total_steps": 468, "loss": 0.0568, "learning_rate": 1.668099208820619e-05, "epoch": 0.29013333333333335, "percentage": 29.06, "elapsed_time": "0:12:12", "remaining_time": "0:29:48"}
+{"current_steps": 137, "total_steps": 468, "loss": 0.0529, "learning_rate": 1.662922981412983e-05, "epoch": 0.2922666666666667, "percentage": 29.27, "elapsed_time": "0:12:17", "remaining_time": "0:29:43"}
+{"current_steps": 138, "total_steps": 468, "loss": 0.0582, "learning_rate": 1.657714870601833e-05, "epoch": 0.2944, "percentage": 29.49, "elapsed_time": "0:12:23", "remaining_time": "0:29:37"}
+{"current_steps": 139, "total_steps": 468, "loss": 0.0501, "learning_rate": 1.6524751268722216e-05, "epoch": 0.2965333333333333, "percentage": 29.7, "elapsed_time": "0:12:28", "remaining_time": "0:29:32"}
+{"current_steps": 140, "total_steps": 468, "loss": 0.0341, "learning_rate": 1.647204002230594e-05, "epoch": 0.2986666666666667, "percentage": 29.91, "elapsed_time": "0:12:34", "remaining_time": "0:29:26"}
+{"current_steps": 141, "total_steps": 468, "loss": 0.0317, "learning_rate": 1.641901750192666e-05, "epoch": 0.3008, "percentage": 30.13, "elapsed_time": "0:12:39", "remaining_time": "0:29:21"}
+{"current_steps": 142, "total_steps": 468, "loss": 0.0391, "learning_rate": 1.63656862577123e-05, "epoch": 0.30293333333333333, "percentage": 30.34, "elapsed_time": "0:12:44", "remaining_time": "0:29:15"}
+{"current_steps": 143, "total_steps": 468, "loss": 0.0499, "learning_rate": 1.6312048854638927e-05, "epoch": 0.30506666666666665, "percentage": 30.56, "elapsed_time": "0:12:49", "remaining_time": "0:29:09"}
+{"current_steps": 144, "total_steps": 468, "loss": 0.0529, "learning_rate": 1.6258107872407376e-05, "epoch": 0.3072, "percentage": 30.77, "elapsed_time": "0:12:55", "remaining_time": "0:29:04"}
+{"current_steps": 145, "total_steps": 468, "loss": 0.0324, "learning_rate": 1.620386590531917e-05, "epoch": 0.30933333333333335, "percentage": 30.98, "elapsed_time": "0:13:00", "remaining_time": "0:28:58"}
+{"current_steps": 146, "total_steps": 468, "loss": 0.0365, "learning_rate": 1.614932556215176e-05, "epoch": 0.31146666666666667, "percentage": 31.2, "elapsed_time": "0:13:05", "remaining_time": "0:28:53"}
+{"current_steps": 147, "total_steps": 468, "loss": 0.0453, "learning_rate": 1.609448946603304e-05, "epoch": 0.3136, "percentage": 31.41, "elapsed_time": "0:13:11", "remaining_time": "0:28:47"}
+{"current_steps": 148, "total_steps": 468, "loss": 0.0334, "learning_rate": 1.6039360254315213e-05, "epoch": 0.3157333333333333, "percentage": 31.62, "elapsed_time": "0:13:16", "remaining_time": "0:28:41"}
+{"current_steps": 149, "total_steps": 468, "loss": 0.0294, "learning_rate": 1.598394057844792e-05, "epoch": 0.3178666666666667, "percentage": 31.84, "elapsed_time": "0:13:21", "remaining_time": "0:28:36"}
+{"current_steps": 150, "total_steps": 468, "loss": 0.0409, "learning_rate": 1.592823310385073e-05, "epoch": 0.32, "percentage": 32.05, "elapsed_time": "0:13:27", "remaining_time": "0:28:30"}
+{"current_steps": 151, "total_steps": 468, "loss": 0.0585, "learning_rate": 1.5872240509784943e-05, "epoch": 0.3221333333333333, "percentage": 32.26, "elapsed_time": "0:13:32", "remaining_time": "0:28:25"}
+{"current_steps": 152, "total_steps": 468, "loss": 0.0376, "learning_rate": 1.5815965489224746e-05, "epoch": 0.32426666666666665, "percentage": 32.48, "elapsed_time": "0:13:37", "remaining_time": "0:28:19"}
+{"current_steps": 153, "total_steps": 468, "loss": 0.0338, "learning_rate": 1.5759410748727663e-05, "epoch": 0.3264, "percentage": 32.69, "elapsed_time": "0:13:42", "remaining_time": "0:28:14"}
+{"current_steps": 154, "total_steps": 468, "loss": 0.0614, "learning_rate": 1.5702579008304403e-05, "epoch": 0.32853333333333334, "percentage": 32.91, "elapsed_time": "0:13:48", "remaining_time": "0:28:08"}
+{"current_steps": 155, "total_steps": 468, "loss": 0.0312, "learning_rate": 1.5645473001288057e-05, "epoch": 0.33066666666666666, "percentage": 33.12, "elapsed_time": "0:13:53", "remaining_time": "0:28:03"}
+{"current_steps": 156, "total_steps": 468, "loss": 0.0353, "learning_rate": 1.5588095474202597e-05, "epoch": 0.3328, "percentage": 33.33, "elapsed_time": "0:13:58", "remaining_time": "0:27:57"}
+{"current_steps": 157, "total_steps": 468, "loss": 0.0318, "learning_rate": 1.5530449186630805e-05, "epoch": 0.33493333333333336, "percentage": 33.55, "elapsed_time": "0:14:04", "remaining_time": "0:27:52"}
+{"current_steps": 158, "total_steps": 468, "loss": 0.0377, "learning_rate": 1.547253691108156e-05, "epoch": 0.3370666666666667, "percentage": 33.76, "elapsed_time": "0:14:09", "remaining_time": "0:27:46"}
+{"current_steps": 159, "total_steps": 468, "loss": 0.0433, "learning_rate": 1.5414361432856475e-05, "epoch": 0.3392, "percentage": 33.97, "elapsed_time": "0:14:14", "remaining_time": "0:27:40"}
+{"current_steps": 160, "total_steps": 468, "loss": 0.0476, "learning_rate": 1.5355925549915943e-05, "epoch": 0.3413333333333333, "percentage": 34.19, "elapsed_time": "0:14:19", "remaining_time": "0:27:35"}
+{"current_steps": 161, "total_steps": 468, "loss": 0.0425, "learning_rate": 1.5297232072744576e-05, "epoch": 0.34346666666666664, "percentage": 34.4, "elapsed_time": "0:14:25", "remaining_time": "0:27:29"}
+{"current_steps": 162, "total_steps": 468, "loss": 0.0496, "learning_rate": 1.5238283824216015e-05, "epoch": 0.3456, "percentage": 34.62, "elapsed_time": "0:14:30", "remaining_time": "0:27:24"}
+{"current_steps": 163, "total_steps": 468, "loss": 0.0246, "learning_rate": 1.5179083639457193e-05, "epoch": 0.34773333333333334, "percentage": 34.83, "elapsed_time": "0:14:35", "remaining_time": "0:27:18"}
+{"current_steps": 164, "total_steps": 468, "loss": 0.0394, "learning_rate": 1.5119634365711955e-05, "epoch": 0.34986666666666666, "percentage": 35.04, "elapsed_time": "0:14:41", "remaining_time": "0:27:13"}
+{"current_steps": 165, "total_steps": 468, "loss": 0.046, "learning_rate": 1.5059938862204126e-05, "epoch": 0.352, "percentage": 35.26, "elapsed_time": "0:14:46", "remaining_time": "0:27:07"}
+{"current_steps": 166, "total_steps": 468, "loss": 0.037, "learning_rate": 1.5000000000000002e-05, "epoch": 0.35413333333333336, "percentage": 35.47, "elapsed_time": "0:14:51", "remaining_time": "0:27:02"}
+{"current_steps": 167, "total_steps": 468, "loss": 0.0594, "learning_rate": 1.4939820661870253e-05, "epoch": 0.3562666666666667, "percentage": 35.68, "elapsed_time": "0:14:56", "remaining_time": "0:26:56"}
+{"current_steps": 168, "total_steps": 468, "loss": 0.0437, "learning_rate": 1.4879403742151283e-05, "epoch": 0.3584, "percentage": 35.9, "elapsed_time": "0:15:02", "remaining_time": "0:26:51"}
+{"current_steps": 169, "total_steps": 468, "loss": 0.041, "learning_rate": 1.481875214660604e-05, "epoch": 0.3605333333333333, "percentage": 36.11, "elapsed_time": "0:15:07", "remaining_time": "0:26:45"}
+{"current_steps": 170, "total_steps": 468, "loss": 0.0435, "learning_rate": 1.4757868792284231e-05, "epoch": 0.3626666666666667, "percentage": 36.32, "elapsed_time": "0:15:12", "remaining_time": "0:26:39"}
+{"current_steps": 171, "total_steps": 468, "loss": 0.0362, "learning_rate": 1.469675660738206e-05, "epoch": 0.3648, "percentage": 36.54, "elapsed_time": "0:15:17", "remaining_time": "0:26:34"}
+{"current_steps": 172, "total_steps": 468, "loss": 0.0301, "learning_rate": 1.463541853110137e-05, "epoch": 0.36693333333333333, "percentage": 36.75, "elapsed_time": "0:15:23", "remaining_time": "0:26:28"}
+{"current_steps": 173, "total_steps": 468, "loss": 0.0353, "learning_rate": 1.4573857513508297e-05, "epoch": 0.36906666666666665, "percentage": 36.97, "elapsed_time": "0:15:28", "remaining_time": "0:26:23"}
+{"current_steps": 174, "total_steps": 468, "loss": 0.0263, "learning_rate": 1.4512076515391375e-05, "epoch": 0.3712, "percentage": 37.18, "elapsed_time": "0:15:33", "remaining_time": "0:26:17"}
+{"current_steps": 175, "total_steps": 468, "loss": 0.0484, "learning_rate": 1.4450078508119148e-05, "epoch": 0.37333333333333335, "percentage": 37.39, "elapsed_time": "0:15:39", "remaining_time": "0:26:12"}
+{"current_steps": 176, "total_steps": 468, "loss": 0.077, "learning_rate": 1.4387866473497254e-05, "epoch": 0.37546666666666667, "percentage": 37.61, "elapsed_time": "0:15:44", "remaining_time": "0:26:06"}
+{"current_steps": 177, "total_steps": 468, "loss": 0.0555, "learning_rate": 1.4325443403625012e-05, "epoch": 0.3776, "percentage": 37.82, "elapsed_time": "0:15:49", "remaining_time": "0:26:01"}
+{"current_steps": 178, "total_steps": 468, "loss": 0.0398, "learning_rate": 1.4262812300751528e-05, "epoch": 0.3797333333333333, "percentage": 38.03, "elapsed_time": "0:15:55", "remaining_time": "0:25:56"}
+{"current_steps": 179, "total_steps": 468, "loss": 0.02, "learning_rate": 1.4199976177131283e-05, "epoch": 0.3818666666666667, "percentage": 38.25, "elapsed_time": "0:16:00", "remaining_time": "0:25:50"}
+{"current_steps": 180, "total_steps": 468, "loss": 0.0396, "learning_rate": 1.4136938054879284e-05, "epoch": 0.384, "percentage": 38.46, "elapsed_time": "0:16:05", "remaining_time": "0:25:45"}
+{"current_steps": 181, "total_steps": 468, "loss": 0.036, "learning_rate": 1.4073700965825681e-05, "epoch": 0.38613333333333333, "percentage": 38.68, "elapsed_time": "0:16:11", "remaining_time": "0:25:40"}
+{"current_steps": 182, "total_steps": 468, "loss": 0.0525, "learning_rate": 1.4010267951369985e-05, "epoch": 0.38826666666666665, "percentage": 38.89, "elapsed_time": "0:16:16", "remaining_time": "0:25:34"}
+{"current_steps": 183, "total_steps": 468, "loss": 0.0444, "learning_rate": 1.3946642062334765e-05, "epoch": 0.3904, "percentage": 39.1, "elapsed_time": "0:16:21", "remaining_time": "0:25:29"}
+{"current_steps": 184, "total_steps": 468, "loss": 0.0436, "learning_rate": 1.3882826358818936e-05, "epoch": 0.39253333333333335, "percentage": 39.32, "elapsed_time": "0:16:27", "remaining_time": "0:25:23"}
+{"current_steps": 185, "total_steps": 468, "loss": 0.04, "learning_rate": 1.381882391005058e-05, "epoch": 0.39466666666666667, "percentage": 39.53, "elapsed_time": "0:16:32", "remaining_time": "0:25:18"}
+{"current_steps": 186, "total_steps": 468, "loss": 0.0334, "learning_rate": 1.3754637794239303e-05, "epoch": 0.3968, "percentage": 39.74, "elapsed_time": "0:16:37", "remaining_time": "0:25:13"}
+{"current_steps": 187, "total_steps": 468, "loss": 0.0511, "learning_rate": 1.3690271098428234e-05, "epoch": 0.3989333333333333, "percentage": 39.96, "elapsed_time": "0:16:43", "remaining_time": "0:25:07"}
+{"current_steps": 188, "total_steps": 468, "loss": 0.0362, "learning_rate": 1.362572691834553e-05, "epoch": 0.4010666666666667, "percentage": 40.17, "elapsed_time": "0:16:48", "remaining_time": "0:25:02"}
+{"current_steps": 189, "total_steps": 468, "loss": 0.0318, "learning_rate": 1.356100835825547e-05, "epoch": 0.4032, "percentage": 40.38, "elapsed_time": "0:16:54", "remaining_time": "0:24:56"}
+{"current_steps": 190, "total_steps": 468, "loss": 0.0351, "learning_rate": 1.3496118530809195e-05, "epoch": 0.4053333333333333, "percentage": 40.6, "elapsed_time": "0:16:59", "remaining_time": "0:24:51"}
+{"current_steps": 191, "total_steps": 468, "loss": 0.0431, "learning_rate": 1.3431060556894959e-05, "epoch": 0.40746666666666664, "percentage": 40.81, "elapsed_time": "0:17:04", "remaining_time": "0:24:46"}
+{"current_steps": 192, "total_steps": 468, "loss": 0.036, "learning_rate": 1.3365837565488065e-05, "epoch": 0.4096, "percentage": 41.03, "elapsed_time": "0:17:09", "remaining_time": "0:24:40"}
+{"current_steps": 193, "total_steps": 468, "loss": 0.0267, "learning_rate": 1.3300452693500358e-05, "epoch": 0.41173333333333334, "percentage": 41.24, "elapsed_time": "0:17:15", "remaining_time": "0:24:35"}
+{"current_steps": 194, "total_steps": 468, "loss": 0.0315, "learning_rate": 1.3234909085629362e-05, "epoch": 0.41386666666666666, "percentage": 41.45, "elapsed_time": "0:17:20", "remaining_time": "0:24:29"}
+{"current_steps": 195, "total_steps": 468, "loss": 0.0238, "learning_rate": 1.316920989420703e-05, "epoch": 0.416, "percentage": 41.67, "elapsed_time": "0:17:25", "remaining_time": "0:24:24"}
+{"current_steps": 196, "total_steps": 468, "loss": 0.0235, "learning_rate": 1.3103358279048136e-05, "epoch": 0.41813333333333336, "percentage": 41.88, "elapsed_time": "0:17:31", "remaining_time": "0:24:18"}
+{"current_steps": 197, "total_steps": 468, "loss": 0.0399, "learning_rate": 1.30373574072983e-05, "epoch": 0.4202666666666667, "percentage": 42.09, "elapsed_time": "0:17:36", "remaining_time": "0:24:13"}
+{"current_steps": 198, "total_steps": 468, "loss": 0.0326, "learning_rate": 1.2971210453281675e-05, "epoch": 0.4224, "percentage": 42.31, "elapsed_time": "0:17:41", "remaining_time": "0:24:08"}
+{"current_steps": 199, "total_steps": 468, "loss": 0.0343, "learning_rate": 1.2904920598348252e-05, "epoch": 0.4245333333333333, "percentage": 42.52, "elapsed_time": "0:17:47", "remaining_time": "0:24:02"}
+{"current_steps": 200, "total_steps": 468, "loss": 0.04, "learning_rate": 1.2838491030720882e-05, "epoch": 0.4266666666666667, "percentage": 42.74, "elapsed_time": "0:17:52", "remaining_time": "0:23:57"}
+{"current_steps": 201, "total_steps": 468, "loss": 0.0389, "learning_rate": 1.2771924945341906e-05, "epoch": 0.4288, "percentage": 42.95, "elapsed_time": "0:19:40", "remaining_time": "0:26:08"}
+{"current_steps": 202, "total_steps": 468, "loss": 0.0469, "learning_rate": 1.2705225543719537e-05, "epoch": 0.43093333333333333, "percentage": 43.16, "elapsed_time": "0:19:46", "remaining_time": "0:26:01"}
+{"current_steps": 203, "total_steps": 468, "loss": 0.0294, "learning_rate": 1.2638396033773836e-05, "epoch": 0.43306666666666666, "percentage": 43.38, "elapsed_time": "0:19:51", "remaining_time": "0:25:55"}
+{"current_steps": 204, "total_steps": 468, "loss": 0.028, "learning_rate": 1.257143962968246e-05, "epoch": 0.4352, "percentage": 43.59, "elapsed_time": "0:19:56", "remaining_time": "0:25:48"}
+{"current_steps": 205, "total_steps": 468, "loss": 0.0257, "learning_rate": 1.250435955172606e-05, "epoch": 0.43733333333333335, "percentage": 43.8, "elapsed_time": "0:20:02", "remaining_time": "0:25:42"}
+{"current_steps": 206, "total_steps": 468, "loss": 0.036, "learning_rate": 1.2437159026133397e-05, "epoch": 0.43946666666666667, "percentage": 44.02, "elapsed_time": "0:20:07", "remaining_time": "0:25:35"}
+{"current_steps": 207, "total_steps": 468, "loss": 0.0424, "learning_rate": 1.236984128492619e-05, "epoch": 0.4416, "percentage": 44.23, "elapsed_time": "0:20:12", "remaining_time": "0:25:28"}
+{"current_steps": 208, "total_steps": 468, "loss": 0.0268, "learning_rate": 1.230240956576367e-05, "epoch": 0.4437333333333333, "percentage": 44.44, "elapsed_time": "0:20:17", "remaining_time": "0:25:22"}
+{"current_steps": 209, "total_steps": 468, "loss": 0.0374, "learning_rate": 1.2234867111786851e-05, "epoch": 0.4458666666666667, "percentage": 44.66, "elapsed_time": "0:20:23", "remaining_time": "0:25:15"}
+{"current_steps": 210, "total_steps": 468, "loss": 0.0318, "learning_rate": 1.2167217171462566e-05, "epoch": 0.448, "percentage": 44.87, "elapsed_time": "0:20:28", "remaining_time": "0:25:09"}
+{"current_steps": 211, "total_steps": 468, "loss": 0.0296, "learning_rate": 1.2099462998427211e-05, "epoch": 0.45013333333333333, "percentage": 45.09, "elapsed_time": "0:20:33", "remaining_time": "0:25:02"}
+{"current_steps": 212, "total_steps": 468, "loss": 0.0192, "learning_rate": 1.2031607851330282e-05, "epoch": 0.45226666666666665, "percentage": 45.3, "elapsed_time": "0:20:38", "remaining_time": "0:24:56"}
+{"current_steps": 213, "total_steps": 468, "loss": 0.039, "learning_rate": 1.1963654993677645e-05, "epoch": 0.4544, "percentage": 45.51, "elapsed_time": "0:20:44", "remaining_time": "0:24:49"}
+{"current_steps": 214, "total_steps": 468, "loss": 0.0428, "learning_rate": 1.189560769367456e-05, "epoch": 0.45653333333333335, "percentage": 45.73, "elapsed_time": "0:20:49", "remaining_time": "0:24:43"}
+{"current_steps": 215, "total_steps": 468, "loss": 0.0558, "learning_rate": 1.1827469224068531e-05, "epoch": 0.45866666666666667, "percentage": 45.94, "elapsed_time": "0:20:54", "remaining_time": "0:24:36"}
+{"current_steps": 216, "total_steps": 468, "loss": 0.0529, "learning_rate": 1.1759242861991855e-05, "epoch": 0.4608, "percentage": 46.15, "elapsed_time": "0:21:00", "remaining_time": "0:24:30"}
+{"current_steps": 217, "total_steps": 468, "loss": 0.0342, "learning_rate": 1.1690931888804055e-05, "epoch": 0.4629333333333333, "percentage": 46.37, "elapsed_time": "0:21:05", "remaining_time": "0:24:23"}
+{"current_steps": 218, "total_steps": 468, "loss": 0.0391, "learning_rate": 1.1622539589934027e-05, "epoch": 0.4650666666666667, "percentage": 46.58, "elapsed_time": "0:21:10", "remaining_time": "0:24:17"}
+{"current_steps": 219, "total_steps": 468, "loss": 0.0227, "learning_rate": 1.155406925472205e-05, "epoch": 0.4672, "percentage": 46.79, "elapsed_time": "0:21:16", "remaining_time": "0:24:10"}
+{"current_steps": 220, "total_steps": 468, "loss": 0.0351, "learning_rate": 1.148552417626157e-05, "epoch": 0.4693333333333333, "percentage": 47.01, "elapsed_time": "0:21:21", "remaining_time": "0:24:04"}
+{"current_steps": 221, "total_steps": 468, "loss": 0.0465, "learning_rate": 1.1416907651240826e-05, "epoch": 0.47146666666666665, "percentage": 47.22, "elapsed_time": "0:21:26", "remaining_time": "0:23:58"}
+{"current_steps": 222, "total_steps": 468, "loss": 0.0407, "learning_rate": 1.1348222979784289e-05, "epoch": 0.4736, "percentage": 47.44, "elapsed_time": "0:21:32", "remaining_time": "0:23:51"}
+{"current_steps": 223, "total_steps": 468, "loss": 0.0373, "learning_rate": 1.1279473465293953e-05, "epoch": 0.47573333333333334, "percentage": 47.65, "elapsed_time": "0:21:37", "remaining_time": "0:23:45"}
+{"current_steps": 224, "total_steps": 468, "loss": 0.0482, "learning_rate": 1.1210662414290439e-05, "epoch": 0.47786666666666666, "percentage": 47.86, "elapsed_time": "0:21:42", "remaining_time": "0:23:39"}
+{"current_steps": 225, "total_steps": 468, "loss": 0.0405, "learning_rate": 1.1141793136253987e-05, "epoch": 0.48, "percentage": 48.08, "elapsed_time": "0:21:48", "remaining_time": "0:23:32"}
+{"current_steps": 226, "total_steps": 468, "loss": 0.0313, "learning_rate": 1.107286894346527e-05, "epoch": 0.48213333333333336, "percentage": 48.29, "elapsed_time": "0:21:53", "remaining_time": "0:23:26"}
+{"current_steps": 227, "total_steps": 468, "loss": 0.0332, "learning_rate": 1.1003893150846103e-05, "epoch": 0.4842666666666667, "percentage": 48.5, "elapsed_time": "0:21:58", "remaining_time": "0:23:20"}
+{"current_steps": 228, "total_steps": 468, "loss": 0.0444, "learning_rate": 1.09348690758e-05, "epoch": 0.4864, "percentage": 48.72, "elapsed_time": "0:22:04", "remaining_time": "0:23:13"}
+{"current_steps": 229, "total_steps": 468, "loss": 0.0301, "learning_rate": 1.0865800038052632e-05, "epoch": 0.4885333333333333, "percentage": 48.93, "elapsed_time": "0:22:09", "remaining_time": "0:23:07"}
+{"current_steps": 230, "total_steps": 468, "loss": 0.031, "learning_rate": 1.0796689359492154e-05, "epoch": 0.49066666666666664, "percentage": 49.15, "elapsed_time": "0:22:14", "remaining_time": "0:23:00"}
+{"current_steps": 231, "total_steps": 468, "loss": 0.0347, "learning_rate": 1.072754036400944e-05, "epoch": 0.4928, "percentage": 49.36, "elapsed_time": "0:22:19", "remaining_time": "0:22:54"}
+{"current_steps": 232, "total_steps": 468, "loss": 0.0301, "learning_rate": 1.0658356377338235e-05, "epoch": 0.49493333333333334, "percentage": 49.57, "elapsed_time": "0:22:25", "remaining_time": "0:22:48"}
+{"current_steps": 233, "total_steps": 468, "loss": 0.0346, "learning_rate": 1.0589140726895179e-05, "epoch": 0.49706666666666666, "percentage": 49.79, "elapsed_time": "0:22:30", "remaining_time": "0:22:41"}
+{"current_steps": 234, "total_steps": 468, "loss": 0.0383, "learning_rate": 1.0519896741619803e-05, "epoch": 0.4992, "percentage": 50.0, "elapsed_time": "0:22:35", "remaining_time": "0:22:35"}
+{"current_steps": 235, "total_steps": 468, "loss": 0.0365, "learning_rate": 1.0450627751814396e-05, "epoch": 0.5013333333333333, "percentage": 50.21, "elapsed_time": "0:22:41", "remaining_time": "0:22:29"}
+{"current_steps": 236, "total_steps": 468, "loss": 0.0495, "learning_rate": 1.0381337088983838e-05, "epoch": 0.5034666666666666, "percentage": 50.43, "elapsed_time": "0:22:46", "remaining_time": "0:22:23"}
+{"current_steps": 237, "total_steps": 468, "loss": 0.0376, "learning_rate": 1.0312028085675393e-05, "epoch": 0.5056, "percentage": 50.64, "elapsed_time": "0:22:51", "remaining_time": "0:22:17"}
+{"current_steps": 238, "total_steps": 468, "loss": 0.0256, "learning_rate": 1.0242704075318402e-05, "epoch": 0.5077333333333334, "percentage": 50.85, "elapsed_time": "0:22:57", "remaining_time": "0:22:10"}
+{"current_steps": 239, "total_steps": 468, "loss": 0.0368, "learning_rate": 1.0173368392063978e-05, "epoch": 0.5098666666666667, "percentage": 51.07, "elapsed_time": "0:23:02", "remaining_time": "0:22:04"}
+{"current_steps": 240, "total_steps": 468, "loss": 0.0331, "learning_rate": 1.0104024370624644e-05, "epoch": 0.512, "percentage": 51.28, "elapsed_time": "0:23:07", "remaining_time": "0:21:58"}
+{"current_steps": 241, "total_steps": 468, "loss": 0.032, "learning_rate": 1.0034675346113945e-05, "epoch": 0.5141333333333333, "percentage": 51.5, "elapsed_time": "0:23:13", "remaining_time": "0:21:52"}
+{"current_steps": 242, "total_steps": 468, "loss": 0.0372, "learning_rate": 9.965324653886057e-06, "epoch": 0.5162666666666667, "percentage": 51.71, "elapsed_time": "0:23:18", "remaining_time": "0:21:46"}
+{"current_steps": 243, "total_steps": 468, "loss": 0.0333, "learning_rate": 9.89597562937536e-06, "epoch": 0.5184, "percentage": 51.92, "elapsed_time": "0:23:23", "remaining_time": "0:21:39"}
+{"current_steps": 244, "total_steps": 468, "loss": 0.0467, "learning_rate": 9.826631607936024e-06, "epoch": 0.5205333333333333, "percentage": 52.14, "elapsed_time": "0:23:29", "remaining_time": "0:21:33"}
+{"current_steps": 245, "total_steps": 468, "loss": 0.0425, "learning_rate": 9.757295924681601e-06, "epoch": 0.5226666666666666, "percentage": 52.35, "elapsed_time": "0:23:34", "remaining_time": "0:21:27"}
+{"current_steps": 246, "total_steps": 468, "loss": 0.0447, "learning_rate": 9.687971914324607e-06, "epoch": 0.5248, "percentage": 52.56, "elapsed_time": "0:23:39", "remaining_time": "0:21:21"}
+{"current_steps": 247, "total_steps": 468, "loss": 0.0319, "learning_rate": 9.618662911016165e-06, "epoch": 0.5269333333333334, "percentage": 52.78, "elapsed_time": "0:23:44", "remaining_time": "0:21:14"}
+{"current_steps": 248, "total_steps": 468, "loss": 0.0328, "learning_rate": 9.54937224818561e-06, "epoch": 0.5290666666666667, "percentage": 52.99, "elapsed_time": "0:23:50", "remaining_time": "0:21:08"}
+{"current_steps": 249, "total_steps": 468, "loss": 0.0478, "learning_rate": 9.480103258380198e-06, "epoch": 0.5312, "percentage": 53.21, "elapsed_time": "0:23:55", "remaining_time": "0:21:02"}
+{"current_steps": 250, "total_steps": 468, "loss": 0.0302, "learning_rate": 9.410859273104823e-06, "epoch": 0.5333333333333333, "percentage": 53.42, "elapsed_time": "0:24:00", "remaining_time": "0:20:56"}
+{"current_steps": 251, "total_steps": 468, "loss": 0.029, "learning_rate": 9.341643622661768e-06, "epoch": 0.5354666666666666, "percentage": 53.63, "elapsed_time": "0:24:06", "remaining_time": "0:20:50"}
+{"current_steps": 252, "total_steps": 468, "loss": 0.0248, "learning_rate": 9.272459635990563e-06, "epoch": 0.5376, "percentage": 53.85, "elapsed_time": "0:24:11", "remaining_time": "0:20:44"}
+{"current_steps": 253, "total_steps": 468, "loss": 0.0213, "learning_rate": 9.20331064050785e-06, "epoch": 0.5397333333333333, "percentage": 54.06, "elapsed_time": "0:24:16", "remaining_time": "0:20:38"}
+{"current_steps": 254, "total_steps": 468, "loss": 0.0422, "learning_rate": 9.134199961947368e-06, "epoch": 0.5418666666666667, "percentage": 54.27, "elapsed_time": "0:24:22", "remaining_time": "0:20:32"}
+{"current_steps": 255, "total_steps": 468, "loss": 0.0381, "learning_rate": 9.065130924199998e-06, "epoch": 0.544, "percentage": 54.49, "elapsed_time": "0:24:28", "remaining_time": "0:20:26"}
+{"current_steps": 256, "total_steps": 468, "loss": 0.0361, "learning_rate": 8.996106849153897e-06, "epoch": 0.5461333333333334, "percentage": 54.7, "elapsed_time": "0:24:33", "remaining_time": "0:20:20"}
+{"current_steps": 257, "total_steps": 468, "loss": 0.0316, "learning_rate": 8.927131056534734e-06, "epoch": 0.5482666666666667, "percentage": 54.91, "elapsed_time": "0:24:38", "remaining_time": "0:20:14"}
+{"current_steps": 258, "total_steps": 468, "loss": 0.0395, "learning_rate": 8.858206863746018e-06, "epoch": 0.5504, "percentage": 55.13, "elapsed_time": "0:24:44", "remaining_time": "0:20:08"}
+{"current_steps": 259, "total_steps": 468, "loss": 0.0373, "learning_rate": 8.789337585709565e-06, "epoch": 0.5525333333333333, "percentage": 55.34, "elapsed_time": "0:24:49", "remaining_time": "0:20:01"}
+{"current_steps": 260, "total_steps": 468, "loss": 0.0297, "learning_rate": 8.720526534706052e-06, "epoch": 0.5546666666666666, "percentage": 55.56, "elapsed_time": "0:24:54", "remaining_time": "0:19:55"}
+{"current_steps": 261, "total_steps": 468, "loss": 0.0302, "learning_rate": 8.651777020215713e-06, "epoch": 0.5568, "percentage": 55.77, "elapsed_time": "0:25:00", "remaining_time": "0:19:49"}
+{"current_steps": 262, "total_steps": 468, "loss": 0.033, "learning_rate": 8.583092348759176e-06, "epoch": 0.5589333333333333, "percentage": 55.98, "elapsed_time": "0:25:05", "remaining_time": "0:19:43"}
+{"current_steps": 263, "total_steps": 468, "loss": 0.0346, "learning_rate": 8.514475823738431e-06, "epoch": 0.5610666666666667, "percentage": 56.2, "elapsed_time": "0:25:10", "remaining_time": "0:19:37"}
+{"current_steps": 264, "total_steps": 468, "loss": 0.0233, "learning_rate": 8.445930745277953e-06, "epoch": 0.5632, "percentage": 56.41, "elapsed_time": "0:25:16", "remaining_time": "0:19:31"}
+{"current_steps": 265, "total_steps": 468, "loss": 0.0252, "learning_rate": 8.377460410065973e-06, "epoch": 0.5653333333333334, "percentage": 56.62, "elapsed_time": "0:25:21", "remaining_time": "0:19:25"}
+{"current_steps": 266, "total_steps": 468, "loss": 0.0328, "learning_rate": 8.309068111195947e-06, "epoch": 0.5674666666666667, "percentage": 56.84, "elapsed_time": "0:25:26", "remaining_time": "0:19:19"}
+{"current_steps": 267, "total_steps": 468, "loss": 0.0283, "learning_rate": 8.240757138008149e-06, "epoch": 0.5696, "percentage": 57.05, "elapsed_time": "0:25:32", "remaining_time": "0:19:13"}
+{"current_steps": 268, "total_steps": 468, "loss": 0.0436, "learning_rate": 8.172530775931476e-06, "epoch": 0.5717333333333333, "percentage": 57.26, "elapsed_time": "0:25:37", "remaining_time": "0:19:07"}
+{"current_steps": 269, "total_steps": 468, "loss": 0.0359, "learning_rate": 8.104392306325442e-06, "epoch": 0.5738666666666666, "percentage": 57.48, "elapsed_time": "0:25:42", "remaining_time": "0:19:01"}
+{"current_steps": 270, "total_steps": 468, "loss": 0.0364, "learning_rate": 8.036345006322358e-06, "epoch": 0.576, "percentage": 57.69, "elapsed_time": "0:25:48", "remaining_time": "0:18:55"}
+{"current_steps": 271, "total_steps": 468, "loss": 0.0221, "learning_rate": 7.96839214866972e-06, "epoch": 0.5781333333333334, "percentage": 57.91, "elapsed_time": "0:25:53", "remaining_time": "0:18:49"}
+{"current_steps": 272, "total_steps": 468, "loss": 0.0309, "learning_rate": 7.900537001572792e-06, "epoch": 0.5802666666666667, "percentage": 58.12, "elapsed_time": "0:25:58", "remaining_time": "0:18:43"}
+{"current_steps": 273, "total_steps": 468, "loss": 0.0412, "learning_rate": 7.832782828537437e-06, "epoch": 0.5824, "percentage": 58.33, "elapsed_time": "0:26:04", "remaining_time": "0:18:37"}
+{"current_steps": 274, "total_steps": 468, "loss": 0.0384, "learning_rate": 7.765132888213147e-06, "epoch": 0.5845333333333333, "percentage": 58.55, "elapsed_time": "0:26:09", "remaining_time": "0:18:31"}
+{"current_steps": 275, "total_steps": 468, "loss": 0.0501, "learning_rate": 7.697590434236331e-06, "epoch": 0.5866666666666667, "percentage": 58.76, "elapsed_time": "0:26:14", "remaining_time": "0:18:25"}
+{"current_steps": 276, "total_steps": 468, "loss": 0.0215, "learning_rate": 7.630158715073813e-06, "epoch": 0.5888, "percentage": 58.97, "elapsed_time": "0:26:20", "remaining_time": "0:18:19"}
+{"current_steps": 277, "total_steps": 468, "loss": 0.0195, "learning_rate": 7.56284097386661e-06, "epoch": 0.5909333333333333, "percentage": 59.19, "elapsed_time": "0:26:25", "remaining_time": "0:18:13"}
+{"current_steps": 278, "total_steps": 468, "loss": 0.0288, "learning_rate": 7.495640448273947e-06, "epoch": 0.5930666666666666, "percentage": 59.4, "elapsed_time": "0:26:30", "remaining_time": "0:18:07"}
+{"current_steps": 279, "total_steps": 468, "loss": 0.0186, "learning_rate": 7.428560370317542e-06, "epoch": 0.5952, "percentage": 59.62, "elapsed_time": "0:26:36", "remaining_time": "0:18:01"}
+{"current_steps": 280, "total_steps": 468, "loss": 0.0294, "learning_rate": 7.361603966226165e-06, "epoch": 0.5973333333333334, "percentage": 59.83, "elapsed_time": "0:26:41", "remaining_time": "0:17:55"}
+{"current_steps": 281, "total_steps": 468, "loss": 0.0282, "learning_rate": 7.294774456280466e-06, "epoch": 0.5994666666666667, "percentage": 60.04, "elapsed_time": "0:26:46", "remaining_time": "0:17:49"}
+{"current_steps": 282, "total_steps": 468, "loss": 0.0409, "learning_rate": 7.228075054658096e-06, "epoch": 0.6016, "percentage": 60.26, "elapsed_time": "0:26:51", "remaining_time": "0:17:43"}
+{"current_steps": 283, "total_steps": 468, "loss": 0.0276, "learning_rate": 7.1615089692791225e-06, "epoch": 0.6037333333333333, "percentage": 60.47, "elapsed_time": "0:26:57", "remaining_time": "0:17:37"}
+{"current_steps": 284, "total_steps": 468, "loss": 0.0257, "learning_rate": 7.095079401651749e-06, "epoch": 0.6058666666666667, "percentage": 60.68, "elapsed_time": "0:27:02", "remaining_time": "0:17:31"}
+{"current_steps": 285, "total_steps": 468, "loss": 0.022, "learning_rate": 7.028789546718327e-06, "epoch": 0.608, "percentage": 60.9, "elapsed_time": "0:27:07", "remaining_time": "0:17:25"}
+{"current_steps": 286, "total_steps": 468, "loss": 0.0398, "learning_rate": 6.962642592701703e-06, "epoch": 0.6101333333333333, "percentage": 61.11, "elapsed_time": "0:27:12", "remaining_time": "0:17:19"}
+{"current_steps": 287, "total_steps": 468, "loss": 0.0319, "learning_rate": 6.896641720951868e-06, "epoch": 0.6122666666666666, "percentage": 61.32, "elapsed_time": "0:27:18", "remaining_time": "0:17:13"}
+{"current_steps": 288, "total_steps": 468, "loss": 0.0301, "learning_rate": 6.8307901057929735e-06, "epoch": 0.6144, "percentage": 61.54, "elapsed_time": "0:27:23", "remaining_time": "0:17:07"}
+{"current_steps": 289, "total_steps": 468, "loss": 0.0316, "learning_rate": 6.765090914370643e-06, "epoch": 0.6165333333333334, "percentage": 61.75, "elapsed_time": "0:27:28", "remaining_time": "0:17:01"}
+{"current_steps": 290, "total_steps": 468, "loss": 0.036, "learning_rate": 6.6995473064996455e-06, "epoch": 0.6186666666666667, "percentage": 61.97, "elapsed_time": "0:27:33", "remaining_time": "0:16:55"}
+{"current_steps": 291, "total_steps": 468, "loss": 0.0256, "learning_rate": 6.634162434511939e-06, "epoch": 0.6208, "percentage": 62.18, "elapsed_time": "0:27:39", "remaining_time": "0:16:49"}
+{"current_steps": 292, "total_steps": 468, "loss": 0.0458, "learning_rate": 6.568939443105045e-06, "epoch": 0.6229333333333333, "percentage": 62.39, "elapsed_time": "0:27:44", "remaining_time": "0:16:43"}
+{"current_steps": 293, "total_steps": 468, "loss": 0.0292, "learning_rate": 6.5038814691908095e-06, "epoch": 0.6250666666666667, "percentage": 62.61, "elapsed_time": "0:27:49", "remaining_time": "0:16:37"}
+{"current_steps": 294, "total_steps": 468, "loss": 0.0251, "learning_rate": 6.438991641744531e-06, "epoch": 0.6272, "percentage": 62.82, "elapsed_time": "0:27:54", "remaining_time": "0:16:31"}
+{"current_steps": 295, "total_steps": 468, "loss": 0.0301, "learning_rate": 6.374273081654474e-06, "epoch": 0.6293333333333333, "percentage": 63.03, "elapsed_time": "0:28:00", "remaining_time": "0:16:25"}
+{"current_steps": 296, "total_steps": 468, "loss": 0.0224, "learning_rate": 6.30972890157177e-06, "epoch": 0.6314666666666666, "percentage": 63.25, "elapsed_time": "0:28:05", "remaining_time": "0:16:19"}
+{"current_steps": 297, "total_steps": 468, "loss": 0.0273, "learning_rate": 6.245362205760703e-06, "epoch": 0.6336, "percentage": 63.46, "elapsed_time": "0:28:10", "remaining_time": "0:16:13"}
+{"current_steps": 298, "total_steps": 468, "loss": 0.0347, "learning_rate": 6.1811760899494276e-06, "epoch": 0.6357333333333334, "percentage": 63.68, "elapsed_time": "0:28:16", "remaining_time": "0:16:07"}
+{"current_steps": 299, "total_steps": 468, "loss": 0.0468, "learning_rate": 6.117173641181064e-06, "epoch": 0.6378666666666667, "percentage": 63.89, "elapsed_time": "0:28:21", "remaining_time": "0:16:01"}
+{"current_steps": 300, "total_steps": 468, "loss": 0.0473, "learning_rate": 6.053357937665237e-06, "epoch": 0.64, "percentage": 64.1, "elapsed_time": "0:28:26", "remaining_time": "0:15:55"}
+{"current_steps": 301, "total_steps": 468, "loss": 0.0212, "learning_rate": 5.9897320486300195e-06, "epoch": 0.6421333333333333, "percentage": 64.32, "elapsed_time": "0:28:32", "remaining_time": "0:15:49"}
+{"current_steps": 302, "total_steps": 468, "loss": 0.0323, "learning_rate": 5.926299034174321e-06, "epoch": 0.6442666666666667, "percentage": 64.53, "elapsed_time": "0:28:37", "remaining_time": "0:15:43"}
+{"current_steps": 303, "total_steps": 468, "loss": 0.0361, "learning_rate": 5.863061945120719e-06, "epoch": 0.6464, "percentage": 64.74, "elapsed_time": "0:28:42", "remaining_time": "0:15:38"}
+{"current_steps": 304, "total_steps": 468, "loss": 0.0271, "learning_rate": 5.800023822868717e-06, "epoch": 0.6485333333333333, "percentage": 64.96, "elapsed_time": "0:28:48", "remaining_time": "0:15:32"}
+{"current_steps": 305, "total_steps": 468, "loss": 0.0277, "learning_rate": 5.737187699248474e-06, "epoch": 0.6506666666666666, "percentage": 65.17, "elapsed_time": "0:28:53", "remaining_time": "0:15:26"}
+{"current_steps": 306, "total_steps": 468, "loss": 0.0348, "learning_rate": 5.674556596374993e-06, "epoch": 0.6528, "percentage": 65.38, "elapsed_time": "0:28:58", "remaining_time": "0:15:20"}
+{"current_steps": 307, "total_steps": 468, "loss": 0.0378, "learning_rate": 5.612133526502752e-06, "epoch": 0.6549333333333334, "percentage": 65.6, "elapsed_time": "0:29:04", "remaining_time": "0:15:14"}
+{"current_steps": 308, "total_steps": 468, "loss": 0.0358, "learning_rate": 5.549921491880856e-06, "epoch": 0.6570666666666667, "percentage": 65.81, "elapsed_time": "0:29:09", "remaining_time": "0:15:08"}
+{"current_steps": 309, "total_steps": 468, "loss": 0.0326, "learning_rate": 5.487923484608629e-06, "epoch": 0.6592, "percentage": 66.03, "elapsed_time": "0:29:14", "remaining_time": "0:15:02"}
+{"current_steps": 310, "total_steps": 468, "loss": 0.0199, "learning_rate": 5.4261424864917075e-06, "epoch": 0.6613333333333333, "percentage": 66.24, "elapsed_time": "0:29:20", "remaining_time": "0:14:57"}
+{"current_steps": 311, "total_steps": 468, "loss": 0.0313, "learning_rate": 5.364581468898629e-06, "epoch": 0.6634666666666666, "percentage": 66.45, "elapsed_time": "0:29:25", "remaining_time": "0:14:51"}
+{"current_steps": 312, "total_steps": 468, "loss": 0.0227, "learning_rate": 5.3032433926179395e-06, "epoch": 0.6656, "percentage": 66.67, "elapsed_time": "0:29:30", "remaining_time": "0:14:45"}
+{"current_steps": 313, "total_steps": 468, "loss": 0.0351, "learning_rate": 5.242131207715768e-06, "epoch": 0.6677333333333333, "percentage": 66.88, "elapsed_time": "0:29:35", "remaining_time": "0:14:39"}
+{"current_steps": 314, "total_steps": 468, "loss": 0.0357, "learning_rate": 5.181247853393961e-06, "epoch": 0.6698666666666667, "percentage": 67.09, "elapsed_time": "0:29:41", "remaining_time": "0:14:33"}
+{"current_steps": 315, "total_steps": 468, "loss": 0.0245, "learning_rate": 5.120596257848716e-06, "epoch": 0.672, "percentage": 67.31, "elapsed_time": "0:29:46", "remaining_time": "0:14:27"}
+{"current_steps": 316, "total_steps": 468, "loss": 0.0282, "learning_rate": 5.060179338129754e-06, "epoch": 0.6741333333333334, "percentage": 67.52, "elapsed_time": "0:29:51", "remaining_time": "0:14:21"}
+{"current_steps": 317, "total_steps": 468, "loss": 0.0304, "learning_rate": 5.000000000000003e-06, "epoch": 0.6762666666666667, "percentage": 67.74, "elapsed_time": "0:29:56", "remaining_time": "0:14:15"}
+{"current_steps": 318, "total_steps": 468, "loss": 0.0353, "learning_rate": 4.940061137795876e-06, "epoch": 0.6784, "percentage": 67.95, "elapsed_time": "0:30:02", "remaining_time": "0:14:10"}
+{"current_steps": 319, "total_steps": 468, "loss": 0.0231, "learning_rate": 4.8803656342880475e-06, "epoch": 0.6805333333333333, "percentage": 68.16, "elapsed_time": "0:30:07", "remaining_time": "0:14:04"}
+{"current_steps": 320, "total_steps": 468, "loss": 0.0275, "learning_rate": 4.82091636054281e-06, "epoch": 0.6826666666666666, "percentage": 68.38, "elapsed_time": "0:30:12", "remaining_time": "0:13:58"}
+{"current_steps": 321, "total_steps": 468, "loss": 0.0216, "learning_rate": 4.7617161757839895e-06, "epoch": 0.6848, "percentage": 68.59, "elapsed_time": "0:30:17", "remaining_time": "0:13:52"}
+{"current_steps": 322, "total_steps": 468, "loss": 0.0405, "learning_rate": 4.702767927255432e-06, "epoch": 0.6869333333333333, "percentage": 68.8, "elapsed_time": "0:30:22", "remaining_time": "0:13:46"}
+{"current_steps": 323, "total_steps": 468, "loss": 0.0256, "learning_rate": 4.644074450084061e-06, "epoch": 0.6890666666666667, "percentage": 69.02, "elapsed_time": "0:30:28", "remaining_time": "0:13:40"}
+{"current_steps": 324, "total_steps": 468, "loss": 0.0234, "learning_rate": 4.5856385671435285e-06, "epoch": 0.6912, "percentage": 69.23, "elapsed_time": "0:30:33", "remaining_time": "0:13:34"}
+{"current_steps": 325, "total_steps": 468, "loss": 0.0208, "learning_rate": 4.527463088918439e-06, "epoch": 0.6933333333333334, "percentage": 69.44, "elapsed_time": "0:30:38", "remaining_time": "0:13:28"}
+{"current_steps": 326, "total_steps": 468, "loss": 0.0264, "learning_rate": 4.469550813369198e-06, "epoch": 0.6954666666666667, "percentage": 69.66, "elapsed_time": "0:30:43", "remaining_time": "0:13:23"}
+{"current_steps": 327, "total_steps": 468, "loss": 0.0228, "learning_rate": 4.411904525797408e-06, "epoch": 0.6976, "percentage": 69.87, "elapsed_time": "0:30:48", "remaining_time": "0:13:17"}
+{"current_steps": 328, "total_steps": 468, "loss": 0.0339, "learning_rate": 4.354526998711945e-06, "epoch": 0.6997333333333333, "percentage": 70.09, "elapsed_time": "0:30:54", "remaining_time": "0:13:11"}
+{"current_steps": 329, "total_steps": 468, "loss": 0.029, "learning_rate": 4.297420991695598e-06, "epoch": 0.7018666666666666, "percentage": 70.3, "elapsed_time": "0:30:59", "remaining_time": "0:13:05"}
+{"current_steps": 330, "total_steps": 468, "loss": 0.0218, "learning_rate": 4.240589251272342e-06, "epoch": 0.704, "percentage": 70.51, "elapsed_time": "0:31:04", "remaining_time": "0:12:59"}
+{"current_steps": 331, "total_steps": 468, "loss": 0.0206, "learning_rate": 4.184034510775258e-06, "epoch": 0.7061333333333333, "percentage": 70.73, "elapsed_time": "0:31:09", "remaining_time": "0:12:53"}
+{"current_steps": 332, "total_steps": 468, "loss": 0.0318, "learning_rate": 4.127759490215057e-06, "epoch": 0.7082666666666667, "percentage": 70.94, "elapsed_time": "0:31:15", "remaining_time": "0:12:48"}
+{"current_steps": 333, "total_steps": 468, "loss": 0.019, "learning_rate": 4.0717668961492725e-06, "epoch": 0.7104, "percentage": 71.15, "elapsed_time": "0:31:20", "remaining_time": "0:12:42"}
+{"current_steps": 334, "total_steps": 468, "loss": 0.0377, "learning_rate": 4.016059421552082e-06, "epoch": 0.7125333333333334, "percentage": 71.37, "elapsed_time": "0:31:25", "remaining_time": "0:12:36"}
+{"current_steps": 335, "total_steps": 468, "loss": 0.0207, "learning_rate": 3.9606397456847875e-06, "epoch": 0.7146666666666667, "percentage": 71.58, "elapsed_time": "0:31:30", "remaining_time": "0:12:30"}
+{"current_steps": 336, "total_steps": 468, "loss": 0.0298, "learning_rate": 3.905510533966959e-06, "epoch": 0.7168, "percentage": 71.79, "elapsed_time": "0:31:36", "remaining_time": "0:12:24"}
+{"current_steps": 337, "total_steps": 468, "loss": 0.0153, "learning_rate": 3.850674437848243e-06, "epoch": 0.7189333333333333, "percentage": 72.01, "elapsed_time": "0:31:41", "remaining_time": "0:12:19"}
+{"current_steps": 338, "total_steps": 468, "loss": 0.0531, "learning_rate": 3.79613409468083e-06, "epoch": 0.7210666666666666, "percentage": 72.22, "elapsed_time": "0:31:46", "remaining_time": "0:12:13"}
+{"current_steps": 339, "total_steps": 468, "loss": 0.0328, "learning_rate": 3.7418921275926245e-06, "epoch": 0.7232, "percentage": 72.44, "elapsed_time": "0:31:51", "remaining_time": "0:12:07"}
+{"current_steps": 340, "total_steps": 468, "loss": 0.0393, "learning_rate": 3.687951145361073e-06, "epoch": 0.7253333333333334, "percentage": 72.65, "elapsed_time": "0:31:56", "remaining_time": "0:12:01"}
+{"current_steps": 341, "total_steps": 468, "loss": 0.0468, "learning_rate": 3.634313742287703e-06, "epoch": 0.7274666666666667, "percentage": 72.86, "elapsed_time": "0:32:02", "remaining_time": "0:11:55"}
+{"current_steps": 342, "total_steps": 468, "loss": 0.0299, "learning_rate": 3.5809824980733445e-06, "epoch": 0.7296, "percentage": 73.08, "elapsed_time": "0:32:07", "remaining_time": "0:11:50"}
+{"current_steps": 343, "total_steps": 468, "loss": 0.0251, "learning_rate": 3.527959977694061e-06, "epoch": 0.7317333333333333, "percentage": 73.29, "elapsed_time": "0:32:12", "remaining_time": "0:11:44"}
+{"current_steps": 344, "total_steps": 468, "loss": 0.0243, "learning_rate": 3.475248731277785e-06, "epoch": 0.7338666666666667, "percentage": 73.5, "elapsed_time": "0:32:18", "remaining_time": "0:11:38"}
+{"current_steps": 345, "total_steps": 468, "loss": 0.0251, "learning_rate": 3.422851293981676e-06, "epoch": 0.736, "percentage": 73.72, "elapsed_time": "0:32:23", "remaining_time": "0:11:32"}
+{"current_steps": 346, "total_steps": 468, "loss": 0.0211, "learning_rate": 3.3707701858701736e-06, "epoch": 0.7381333333333333, "percentage": 73.93, "elapsed_time": "0:32:28", "remaining_time": "0:11:27"}
+{"current_steps": 347, "total_steps": 468, "loss": 0.0384, "learning_rate": 3.3190079117938167e-06, "epoch": 0.7402666666666666, "percentage": 74.15, "elapsed_time": "0:32:33", "remaining_time": "0:11:21"}
+{"current_steps": 348, "total_steps": 468, "loss": 0.0482, "learning_rate": 3.2675669612687565e-06, "epoch": 0.7424, "percentage": 74.36, "elapsed_time": "0:32:39", "remaining_time": "0:11:15"}
+{"current_steps": 349, "total_steps": 468, "loss": 0.0307, "learning_rate": 3.2164498083570393e-06, "epoch": 0.7445333333333334, "percentage": 74.57, "elapsed_time": "0:32:44", "remaining_time": "0:11:09"}
+{"current_steps": 350, "total_steps": 468, "loss": 0.0339, "learning_rate": 3.165658911547592e-06, "epoch": 0.7466666666666667, "percentage": 74.79, "elapsed_time": "0:32:49", "remaining_time": "0:11:04"}
+{"current_steps": 351, "total_steps": 468, "loss": 0.0413, "learning_rate": 3.115196713638e-06, "epoch": 0.7488, "percentage": 75.0, "elapsed_time": "0:32:55", "remaining_time": "0:10:58"}
+{"current_steps": 352, "total_steps": 468, "loss": 0.0321, "learning_rate": 3.0650656416170155e-06, "epoch": 0.7509333333333333, "percentage": 75.21, "elapsed_time": "0:33:00", "remaining_time": "0:10:52"}
+{"current_steps": 353, "total_steps": 468, "loss": 0.0308, "learning_rate": 3.0152681065478252e-06, "epoch": 0.7530666666666667, "percentage": 75.43, "elapsed_time": "0:33:06", "remaining_time": "0:10:47"}
+{"current_steps": 354, "total_steps": 468, "loss": 0.0336, "learning_rate": 2.965806503452098e-06, "epoch": 0.7552, "percentage": 75.64, "elapsed_time": "0:33:11", "remaining_time": "0:10:41"}
+{"current_steps": 355, "total_steps": 468, "loss": 0.026, "learning_rate": 2.9166832111947953e-06, "epoch": 0.7573333333333333, "percentage": 75.85, "elapsed_time": "0:33:16", "remaining_time": "0:10:35"}
+{"current_steps": 356, "total_steps": 468, "loss": 0.0274, "learning_rate": 2.8679005923697444e-06, "epoch": 0.7594666666666666, "percentage": 76.07, "elapsed_time": "0:33:22", "remaining_time": "0:10:29"}
+{"current_steps": 357, "total_steps": 468, "loss": 0.0256, "learning_rate": 2.819460993186032e-06, "epoch": 0.7616, "percentage": 76.28, "elapsed_time": "0:33:27", "remaining_time": "0:10:24"}
+{"current_steps": 358, "total_steps": 468, "loss": 0.0252, "learning_rate": 2.7713667433551495e-06, "epoch": 0.7637333333333334, "percentage": 76.5, "elapsed_time": "0:33:32", "remaining_time": "0:10:18"}
+{"current_steps": 359, "total_steps": 468, "loss": 0.0208, "learning_rate": 2.7236201559789456e-06, "epoch": 0.7658666666666667, "percentage": 76.71, "elapsed_time": "0:33:37", "remaining_time": "0:10:12"}
+{"current_steps": 360, "total_steps": 468, "loss": 0.0253, "learning_rate": 2.6762235274383775e-06, "epoch": 0.768, "percentage": 76.92, "elapsed_time": "0:33:42", "remaining_time": "0:10:06"}
+{"current_steps": 361, "total_steps": 468, "loss": 0.0209, "learning_rate": 2.629179137283071e-06, "epoch": 0.7701333333333333, "percentage": 77.14, "elapsed_time": "0:33:48", "remaining_time": "0:10:01"}
+{"current_steps": 362, "total_steps": 468, "loss": 0.0284, "learning_rate": 2.582489248121677e-06, "epoch": 0.7722666666666667, "percentage": 77.35, "elapsed_time": "0:33:53", "remaining_time": "0:09:55"}
+{"current_steps": 363, "total_steps": 468, "loss": 0.028, "learning_rate": 2.5361561055130625e-06, "epoch": 0.7744, "percentage": 77.56, "elapsed_time": "0:33:58", "remaining_time": "0:09:49"}
+{"current_steps": 364, "total_steps": 468, "loss": 0.0257, "learning_rate": 2.490181937858296e-06, "epoch": 0.7765333333333333, "percentage": 77.78, "elapsed_time": "0:34:04", "remaining_time": "0:09:44"}
+{"current_steps": 365, "total_steps": 468, "loss": 0.0341, "learning_rate": 2.444568956293486e-06, "epoch": 0.7786666666666666, "percentage": 77.99, "elapsed_time": "0:34:09", "remaining_time": "0:09:38"}
+{"current_steps": 366, "total_steps": 468, "loss": 0.0234, "learning_rate": 2.3993193545834182e-06, "epoch": 0.7808, "percentage": 78.21, "elapsed_time": "0:34:14", "remaining_time": "0:09:32"}
+{"current_steps": 367, "total_steps": 468, "loss": 0.0143, "learning_rate": 2.3544353090160664e-06, "epoch": 0.7829333333333334, "percentage": 78.42, "elapsed_time": "0:34:19", "remaining_time": "0:09:26"}
+{"current_steps": 368, "total_steps": 468, "loss": 0.0227, "learning_rate": 2.3099189782979126e-06, "epoch": 0.7850666666666667, "percentage": 78.63, "elapsed_time": "0:34:25", "remaining_time": "0:09:21"}
+{"current_steps": 369, "total_steps": 468, "loss": 0.0153, "learning_rate": 2.265772503450122e-06, "epoch": 0.7872, "percentage": 78.85, "elapsed_time": "0:34:30", "remaining_time": "0:09:15"}
+{"current_steps": 370, "total_steps": 468, "loss": 0.0268, "learning_rate": 2.2219980077055756e-06, "epoch": 0.7893333333333333, "percentage": 79.06, "elapsed_time": "0:34:35", "remaining_time": "0:09:09"}
+{"current_steps": 371, "total_steps": 468, "loss": 0.018, "learning_rate": 2.178597596406752e-06, "epoch": 0.7914666666666667, "percentage": 79.27, "elapsed_time": "0:34:40", "remaining_time": "0:09:04"}
+{"current_steps": 372, "total_steps": 468, "loss": 0.042, "learning_rate": 2.1355733569044633e-06, "epoch": 0.7936, "percentage": 79.49, "elapsed_time": "0:34:46", "remaining_time": "0:08:58"}
+{"current_steps": 373, "total_steps": 468, "loss": 0.0242, "learning_rate": 2.092927358457476e-06, "epoch": 0.7957333333333333, "percentage": 79.7, "elapsed_time": "0:34:51", "remaining_time": "0:08:52"}
+{"current_steps": 374, "total_steps": 468, "loss": 0.0346, "learning_rate": 2.0506616521329803e-06, "epoch": 0.7978666666666666, "percentage": 79.91, "elapsed_time": "0:34:56", "remaining_time": "0:08:46"}
+{"current_steps": 375, "total_steps": 468, "loss": 0.0236, "learning_rate": 2.008778270707944e-06, "epoch": 0.8, "percentage": 80.13, "elapsed_time": "0:35:01", "remaining_time": "0:08:41"}
+{"current_steps": 376, "total_steps": 468, "loss": 0.0353, "learning_rate": 1.9672792285713528e-06, "epoch": 0.8021333333333334, "percentage": 80.34, "elapsed_time": "0:35:06", "remaining_time": "0:08:35"}
+{"current_steps": 377, "total_steps": 468, "loss": 0.0165, "learning_rate": 1.9261665216273197e-06, "epoch": 0.8042666666666667, "percentage": 80.56, "elapsed_time": "0:35:11", "remaining_time": "0:08:29"}
+{"current_steps": 378, "total_steps": 468, "loss": 0.0342, "learning_rate": 1.8854421271990964e-06, "epoch": 0.8064, "percentage": 80.77, "elapsed_time": "0:35:16", "remaining_time": "0:08:24"}
+{"current_steps": 379, "total_steps": 468, "loss": 0.0262, "learning_rate": 1.845108003933972e-06, "epoch": 0.8085333333333333, "percentage": 80.98, "elapsed_time": "0:35:22", "remaining_time": "0:08:18"}
+{"current_steps": 380, "total_steps": 468, "loss": 0.0412, "learning_rate": 1.8051660917090718e-06, "epoch": 0.8106666666666666, "percentage": 81.2, "elapsed_time": "0:35:27", "remaining_time": "0:08:12"}
+{"current_steps": 381, "total_steps": 468, "loss": 0.0328, "learning_rate": 1.7656183115380577e-06, "epoch": 0.8128, "percentage": 81.41, "elapsed_time": "0:35:32", "remaining_time": "0:08:06"}
+{"current_steps": 382, "total_steps": 468, "loss": 0.0237, "learning_rate": 1.7264665654787405e-06, "epoch": 0.8149333333333333, "percentage": 81.62, "elapsed_time": "0:35:37", "remaining_time": "0:08:01"}
+{"current_steps": 383, "total_steps": 468, "loss": 0.0214, "learning_rate": 1.6877127365415924e-06, "epoch": 0.8170666666666667, "percentage": 81.84, "elapsed_time": "0:35:42", "remaining_time": "0:07:55"}
+{"current_steps": 384, "total_steps": 468, "loss": 0.0387, "learning_rate": 1.6493586885991908e-06, "epoch": 0.8192, "percentage": 82.05, "elapsed_time": "0:35:47", "remaining_time": "0:07:49"}
+{"current_steps": 385, "total_steps": 468, "loss": 0.0317, "learning_rate": 1.6114062662965757e-06, "epoch": 0.8213333333333334, "percentage": 82.26, "elapsed_time": "0:35:52", "remaining_time": "0:07:44"}
+{"current_steps": 386, "total_steps": 468, "loss": 0.0347, "learning_rate": 1.5738572949625163e-06, "epoch": 0.8234666666666667, "percentage": 82.48, "elapsed_time": "0:35:58", "remaining_time": "0:07:38"}
+{"current_steps": 387, "total_steps": 468, "loss": 0.0384, "learning_rate": 1.536713580521746e-06, "epoch": 0.8256, "percentage": 82.69, "elapsed_time": "0:36:03", "remaining_time": "0:07:32"}
+{"current_steps": 388, "total_steps": 468, "loss": 0.0173, "learning_rate": 1.4999769094080853e-06, "epoch": 0.8277333333333333, "percentage": 82.91, "elapsed_time": "0:36:08", "remaining_time": "0:07:27"}
+{"current_steps": 389, "total_steps": 468, "loss": 0.0335, "learning_rate": 1.4636490484785316e-06, "epoch": 0.8298666666666666, "percentage": 83.12, "elapsed_time": "0:36:13", "remaining_time": "0:07:21"}
+{"current_steps": 390, "total_steps": 468, "loss": 0.0475, "learning_rate": 1.4277317449282834e-06, "epoch": 0.832, "percentage": 83.33, "elapsed_time": "0:36:18", "remaining_time": "0:07:15"}
+{"current_steps": 391, "total_steps": 468, "loss": 0.0212, "learning_rate": 1.3922267262067025e-06, "epoch": 0.8341333333333333, "percentage": 83.55, "elapsed_time": "0:36:23", "remaining_time": "0:07:10"}
+{"current_steps": 392, "total_steps": 468, "loss": 0.0223, "learning_rate": 1.3571356999342366e-06, "epoch": 0.8362666666666667, "percentage": 83.76, "elapsed_time": "0:36:28", "remaining_time": "0:07:04"}
+{"current_steps": 393, "total_steps": 468, "loss": 0.0288, "learning_rate": 1.3224603538202929e-06, "epoch": 0.8384, "percentage": 83.97, "elapsed_time": "0:36:34", "remaining_time": "0:06:58"}
+{"current_steps": 394, "total_steps": 468, "loss": 0.0309, "learning_rate": 1.28820235558206e-06, "epoch": 0.8405333333333334, "percentage": 84.19, "elapsed_time": "0:36:39", "remaining_time": "0:06:53"}
+{"current_steps": 395, "total_steps": 468, "loss": 0.025, "learning_rate": 1.2543633528643084e-06, "epoch": 0.8426666666666667, "percentage": 84.4, "elapsed_time": "0:36:44", "remaining_time": "0:06:47"}
+{"current_steps": 396, "total_steps": 468, "loss": 0.0303, "learning_rate": 1.220944973160133e-06, "epoch": 0.8448, "percentage": 84.62, "elapsed_time": "0:36:49", "remaining_time": "0:06:41"}
+{"current_steps": 397, "total_steps": 468, "loss": 0.0275, "learning_rate": 1.1879488237326952e-06, "epoch": 0.8469333333333333, "percentage": 84.83, "elapsed_time": "0:36:54", "remaining_time": "0:06:36"}
+{"current_steps": 398, "total_steps": 468, "loss": 0.0258, "learning_rate": 1.1553764915379095e-06, "epoch": 0.8490666666666666, "percentage": 85.04, "elapsed_time": "0:36:59", "remaining_time": "0:06:30"}
+{"current_steps": 399, "total_steps": 468, "loss": 0.042, "learning_rate": 1.1232295431481222e-06, "epoch": 0.8512, "percentage": 85.26, "elapsed_time": "0:37:04", "remaining_time": "0:06:24"}
+{"current_steps": 400, "total_steps": 468, "loss": 0.0391, "learning_rate": 1.0915095246767692e-06, "epoch": 0.8533333333333334, "percentage": 85.47, "elapsed_time": "0:37:10", "remaining_time": "0:06:19"}
+{"current_steps": 401, "total_steps": 468, "loss": 0.0178, "learning_rate": 1.0602179617040098e-06, "epoch": 0.8554666666666667, "percentage": 85.68, "elapsed_time": "0:38:59", "remaining_time": "0:06:30"}
+{"current_steps": 402, "total_steps": 468, "loss": 0.0213, "learning_rate": 1.0293563592033595e-06, "epoch": 0.8576, "percentage": 85.9, "elapsed_time": "0:39:04", "remaining_time": "0:06:24"}
+{"current_steps": 403, "total_steps": 468, "loss": 0.0323, "learning_rate": 9.989262014693013e-07, "epoch": 0.8597333333333333, "percentage": 86.11, "elapsed_time": "0:39:10", "remaining_time": "0:06:19"}
+{"current_steps": 404, "total_steps": 468, "loss": 0.0319, "learning_rate": 9.68928952045909e-07, "epoch": 0.8618666666666667, "percentage": 86.32, "elapsed_time": "0:39:15", "remaining_time": "0:06:13"}
+{"current_steps": 405, "total_steps": 468, "loss": 0.0293, "learning_rate": 9.393660536564408e-07, "epoch": 0.864, "percentage": 86.54, "elapsed_time": "0:39:20", "remaining_time": "0:06:07"}
+{"current_steps": 406, "total_steps": 468, "loss": 0.0347, "learning_rate": 9.102389281339719e-07, "epoch": 0.8661333333333333, "percentage": 86.75, "elapsed_time": "0:39:25", "remaining_time": "0:06:01"}
+{"current_steps": 407, "total_steps": 468, "loss": 0.0412, "learning_rate": 8.815489763529938e-07, "epoch": 0.8682666666666666, "percentage": 86.97, "elapsed_time": "0:39:30", "remaining_time": "0:05:55"}
+{"current_steps": 408, "total_steps": 468, "loss": 0.0345, "learning_rate": 8.532975781620511e-07, "epoch": 0.8704, "percentage": 87.18, "elapsed_time": "0:39:36", "remaining_time": "0:05:49"}
+{"current_steps": 409, "total_steps": 468, "loss": 0.0272, "learning_rate": 8.254860923173691e-07, "epoch": 0.8725333333333334, "percentage": 87.39, "elapsed_time": "0:39:41", "remaining_time": "0:05:43"}
+{"current_steps": 410, "total_steps": 468, "loss": 0.0201, "learning_rate": 7.981158564175074e-07, "epoch": 0.8746666666666667, "percentage": 87.61, "elapsed_time": "0:39:46", "remaining_time": "0:05:37"}
+{"current_steps": 411, "total_steps": 468, "loss": 0.0268, "learning_rate": 7.711881868390292e-07, "epoch": 0.8768, "percentage": 87.82, "elapsed_time": "0:39:51", "remaining_time": "0:05:31"}
+{"current_steps": 412, "total_steps": 468, "loss": 0.0328, "learning_rate": 7.447043786731867e-07, "epoch": 0.8789333333333333, "percentage": 88.03, "elapsed_time": "0:39:56", "remaining_time": "0:05:25"}
+{"current_steps": 413, "total_steps": 468, "loss": 0.021, "learning_rate": 7.18665705663637e-07, "epoch": 0.8810666666666667, "percentage": 88.25, "elapsed_time": "0:40:01", "remaining_time": "0:05:19"}
+{"current_steps": 414, "total_steps": 468, "loss": 0.0313, "learning_rate": 6.930734201451817e-07, "epoch": 0.8832, "percentage": 88.46, "elapsed_time": "0:40:07", "remaining_time": "0:05:13"}
+{"current_steps": 415, "total_steps": 468, "loss": 0.0344, "learning_rate": 6.679287529835266e-07, "epoch": 0.8853333333333333, "percentage": 88.68, "elapsed_time": "0:40:12", "remaining_time": "0:05:08"}
+{"current_steps": 416, "total_steps": 468, "loss": 0.0287, "learning_rate": 6.432329135160953e-07, "epoch": 0.8874666666666666, "percentage": 88.89, "elapsed_time": "0:40:17", "remaining_time": "0:05:02"}
+{"current_steps": 417, "total_steps": 468, "loss": 0.0303, "learning_rate": 6.189870894938587e-07, "epoch": 0.8896, "percentage": 89.1, "elapsed_time": "0:40:23", "remaining_time": "0:04:56"}
+{"current_steps": 418, "total_steps": 468, "loss": 0.0327, "learning_rate": 5.951924470242121e-07, "epoch": 0.8917333333333334, "percentage": 89.32, "elapsed_time": "0:40:28", "remaining_time": "0:04:50"}
+{"current_steps": 419, "total_steps": 468, "loss": 0.0243, "learning_rate": 5.718501305148893e-07, "epoch": 0.8938666666666667, "percentage": 89.53, "elapsed_time": "0:40:33", "remaining_time": "0:04:44"}
+{"current_steps": 420, "total_steps": 468, "loss": 0.0331, "learning_rate": 5.489612626189245e-07, "epoch": 0.896, "percentage": 89.74, "elapsed_time": "0:40:39", "remaining_time": "0:04:38"}
+{"current_steps": 421, "total_steps": 468, "loss": 0.0363, "learning_rate": 5.265269441806564e-07, "epoch": 0.8981333333333333, "percentage": 89.96, "elapsed_time": "0:40:44", "remaining_time": "0:04:32"}
+{"current_steps": 422, "total_steps": 468, "loss": 0.0244, "learning_rate": 5.045482541827828e-07, "epoch": 0.9002666666666667, "percentage": 90.17, "elapsed_time": "0:40:49", "remaining_time": "0:04:27"}
+{"current_steps": 423, "total_steps": 468, "loss": 0.029, "learning_rate": 4.830262496944693e-07, "epoch": 0.9024, "percentage": 90.38, "elapsed_time": "0:40:54", "remaining_time": "0:04:21"}
+{"current_steps": 424, "total_steps": 468, "loss": 0.0147, "learning_rate": 4.6196196582050543e-07, "epoch": 0.9045333333333333, "percentage": 90.6, "elapsed_time": "0:41:00", "remaining_time": "0:04:15"}
+{"current_steps": 425, "total_steps": 468, "loss": 0.0264, "learning_rate": 4.4135641565152265e-07, "epoch": 0.9066666666666666, "percentage": 90.81, "elapsed_time": "0:41:05", "remaining_time": "0:04:09"}
+{"current_steps": 426, "total_steps": 468, "loss": 0.0229, "learning_rate": 4.21210590215273e-07, "epoch": 0.9088, "percentage": 91.03, "elapsed_time": "0:41:10", "remaining_time": "0:04:03"}
+{"current_steps": 427, "total_steps": 468, "loss": 0.0284, "learning_rate": 4.015254584289585e-07, "epoch": 0.9109333333333334, "percentage": 91.24, "elapsed_time": "0:41:16", "remaining_time": "0:03:57"}
+{"current_steps": 428, "total_steps": 468, "loss": 0.0314, "learning_rate": 3.8230196705263734e-07, "epoch": 0.9130666666666667, "percentage": 91.45, "elapsed_time": "0:41:21", "remaining_time": "0:03:51"}
+{"current_steps": 429, "total_steps": 468, "loss": 0.0285, "learning_rate": 3.635410406436857e-07, "epoch": 0.9152, "percentage": 91.67, "elapsed_time": "0:41:26", "remaining_time": "0:03:46"}
+{"current_steps": 430, "total_steps": 468, "loss": 0.0242, "learning_rate": 3.452435815123323e-07, "epoch": 0.9173333333333333, "percentage": 91.88, "elapsed_time": "0:41:31", "remaining_time": "0:03:40"}
+{"current_steps": 431, "total_steps": 468, "loss": 0.0295, "learning_rate": 3.2741046967826205e-07, "epoch": 0.9194666666666667, "percentage": 92.09, "elapsed_time": "0:41:37", "remaining_time": "0:03:34"}
+{"current_steps": 432, "total_steps": 468, "loss": 0.0249, "learning_rate": 3.100425628282899e-07, "epoch": 0.9216, "percentage": 92.31, "elapsed_time": "0:41:42", "remaining_time": "0:03:28"}
+{"current_steps": 433, "total_steps": 468, "loss": 0.0177, "learning_rate": 2.9314069627511045e-07, "epoch": 0.9237333333333333, "percentage": 92.52, "elapsed_time": "0:41:47", "remaining_time": "0:03:22"}
+{"current_steps": 434, "total_steps": 468, "loss": 0.0288, "learning_rate": 2.767056829171255e-07, "epoch": 0.9258666666666666, "percentage": 92.74, "elapsed_time": "0:41:52", "remaining_time": "0:03:16"}
+{"current_steps": 435, "total_steps": 468, "loss": 0.0129, "learning_rate": 2.607383131993424e-07, "epoch": 0.928, "percentage": 92.95, "elapsed_time": "0:41:58", "remaining_time": "0:03:11"}
+{"current_steps": 436, "total_steps": 468, "loss": 0.0322, "learning_rate": 2.452393550753662e-07, "epoch": 0.9301333333333334, "percentage": 93.16, "elapsed_time": "0:42:03", "remaining_time": "0:03:05"}
+{"current_steps": 437, "total_steps": 468, "loss": 0.0291, "learning_rate": 2.302095539704563e-07, "epoch": 0.9322666666666667, "percentage": 93.38, "elapsed_time": "0:42:08", "remaining_time": "0:02:59"}
+{"current_steps": 438, "total_steps": 468, "loss": 0.0187, "learning_rate": 2.1564963274568028e-07, "epoch": 0.9344, "percentage": 93.59, "elapsed_time": "0:42:13", "remaining_time": "0:02:53"}
+{"current_steps": 439, "total_steps": 468, "loss": 0.0196, "learning_rate": 2.0156029166314316e-07, "epoch": 0.9365333333333333, "percentage": 93.8, "elapsed_time": "0:42:18", "remaining_time": "0:02:47"}
+{"current_steps": 440, "total_steps": 468, "loss": 0.0369, "learning_rate": 1.8794220835231413e-07, "epoch": 0.9386666666666666, "percentage": 94.02, "elapsed_time": "0:42:24", "remaining_time": "0:02:41"}
+{"current_steps": 441, "total_steps": 468, "loss": 0.043, "learning_rate": 1.7479603777742937e-07, "epoch": 0.9408, "percentage": 94.23, "elapsed_time": "0:42:29", "remaining_time": "0:02:36"}
+{"current_steps": 442, "total_steps": 468, "loss": 0.0167, "learning_rate": 1.6212241220599835e-07, "epoch": 0.9429333333333333, "percentage": 94.44, "elapsed_time": "0:42:34", "remaining_time": "0:02:30"}
+{"current_steps": 443, "total_steps": 468, "loss": 0.0387, "learning_rate": 1.49921941178387e-07, "epoch": 0.9450666666666667, "percentage": 94.66, "elapsed_time": "0:42:39", "remaining_time": "0:02:24"}
+{"current_steps": 444, "total_steps": 468, "loss": 0.0167, "learning_rate": 1.3819521147851122e-07, "epoch": 0.9472, "percentage": 94.87, "elapsed_time": "0:42:45", "remaining_time": "0:02:18"}
+{"current_steps": 445, "total_steps": 468, "loss": 0.0147, "learning_rate": 1.2694278710560282e-07, "epoch": 0.9493333333333334, "percentage": 95.09, "elapsed_time": "0:42:50", "remaining_time": "0:02:12"}
+{"current_steps": 446, "total_steps": 468, "loss": 0.0405, "learning_rate": 1.1616520924709773e-07, "epoch": 0.9514666666666667, "percentage": 95.3, "elapsed_time": "0:42:55", "remaining_time": "0:02:07"}
+{"current_steps": 447, "total_steps": 468, "loss": 0.0335, "learning_rate": 1.0586299625259699e-07, "epoch": 0.9536, "percentage": 95.51, "elapsed_time": "0:43:00", "remaining_time": "0:02:01"}
+{"current_steps": 448, "total_steps": 468, "loss": 0.0265, "learning_rate": 9.603664360894327e-08, "epoch": 0.9557333333333333, "percentage": 95.73, "elapsed_time": "0:43:06", "remaining_time": "0:01:55"}
+{"current_steps": 449, "total_steps": 468, "loss": 0.0248, "learning_rate": 8.668662391638439e-08, "epoch": 0.9578666666666666, "percentage": 95.94, "elapsed_time": "0:43:11", "remaining_time": "0:01:49"}
+{"current_steps": 450, "total_steps": 468, "loss": 0.0185, "learning_rate": 7.781338686584928e-08, "epoch": 0.96, "percentage": 96.15, "elapsed_time": "0:43:16", "remaining_time": "0:01:43"}
+{"current_steps": 451, "total_steps": 468, "loss": 0.0341, "learning_rate": 6.94173592173164e-08, "epoch": 0.9621333333333333, "percentage": 96.37, "elapsed_time": "0:43:22", "remaining_time": "0:01:38"}
+{"current_steps": 452, "total_steps": 468, "loss": 0.0316, "learning_rate": 6.149894477928909e-08, "epoch": 0.9642666666666667, "percentage": 96.58, "elapsed_time": "0:43:27", "remaining_time": "0:01:32"}
+{"current_steps": 453, "total_steps": 468, "loss": 0.0259, "learning_rate": 5.405852438937764e-08, "epoch": 0.9664, "percentage": 96.79, "elapsed_time": "0:43:32", "remaining_time": "0:01:26"}
+{"current_steps": 454, "total_steps": 468, "loss": 0.0221, "learning_rate": 4.7096455895976334e-08, "epoch": 0.9685333333333334, "percentage": 97.01, "elapsed_time": "0:43:38", "remaining_time": "0:01:20"}
+{"current_steps": 455, "total_steps": 468, "loss": 0.0463, "learning_rate": 4.0613074141059307e-08, "epoch": 0.9706666666666667, "percentage": 97.22, "elapsed_time": "0:43:43", "remaining_time": "0:01:14"}
+{"current_steps": 456, "total_steps": 468, "loss": 0.0463, "learning_rate": 3.460869094407127e-08, "epoch": 0.9728, "percentage": 97.44, "elapsed_time": "0:43:48", "remaining_time": "0:01:09"}
+{"current_steps": 457, "total_steps": 468, "loss": 0.0328, "learning_rate": 2.9083595086933924e-08, "epoch": 0.9749333333333333, "percentage": 97.65, "elapsed_time": "0:43:54", "remaining_time": "0:01:03"}
+{"current_steps": 458, "total_steps": 468, "loss": 0.0316, "learning_rate": 2.403805230015488e-08, "epoch": 0.9770666666666666, "percentage": 97.86, "elapsed_time": "0:43:59", "remaining_time": "0:00:57"}
+{"current_steps": 459, "total_steps": 468, "loss": 0.0279, "learning_rate": 1.947230525005006e-08, "epoch": 0.9792, "percentage": 98.08, "elapsed_time": "0:44:04", "remaining_time": "0:00:51"}
+{"current_steps": 460, "total_steps": 468, "loss": 0.0207, "learning_rate": 1.5386573527067516e-08, "epoch": 0.9813333333333333, "percentage": 98.29, "elapsed_time": "0:44:10", "remaining_time": "0:00:46"}
+{"current_steps": 461, "total_steps": 468, "loss": 0.0341, "learning_rate": 1.178105363523252e-08, "epoch": 0.9834666666666667, "percentage": 98.5, "elapsed_time": "0:44:15", "remaining_time": "0:00:40"}
+{"current_steps": 462, "total_steps": 468, "loss": 0.0374, "learning_rate": 8.655918982689582e-09, "epoch": 0.9856, "percentage": 98.72, "elapsed_time": "0:44:20", "remaining_time": "0:00:34"}
+{"current_steps": 463, "total_steps": 468, "loss": 0.0337, "learning_rate": 6.011319873370225e-09, "epoch": 0.9877333333333334, "percentage": 98.93, "elapsed_time": "0:44:26", "remaining_time": "0:00:28"}
+{"current_steps": 464, "total_steps": 468, "loss": 0.0233, "learning_rate": 3.847383499756552e-09, "epoch": 0.9898666666666667, "percentage": 99.15, "elapsed_time": "0:44:31", "remaining_time": "0:00:23"}
+{"current_steps": 465, "total_steps": 468, "loss": 0.0316, "learning_rate": 2.164213936770576e-09, "epoch": 0.992, "percentage": 99.36, "elapsed_time": "0:44:36", "remaining_time": "0:00:17"}
+{"current_steps": 466, "total_steps": 468, "loss": 0.0418, "learning_rate": 9.618921367637869e-10, "epoch": 0.9941333333333333, "percentage": 99.57, "elapsed_time": "0:44:41", "remaining_time": "0:00:11"}
+{"current_steps": 467, "total_steps": 468, "loss": 0.0284, "learning_rate": 2.404759256247058e-10, "epoch": 0.9962666666666666, "percentage": 99.79, "elapsed_time": "0:44:47", "remaining_time": "0:00:05"}
+{"current_steps": 468, "total_steps": 468, "loss": 0.0306, "learning_rate": 0.0, "epoch": 0.9984, "percentage": 100.0, "elapsed_time": "0:44:52", "remaining_time": "0:00:00"}
+{"current_steps": 468, "total_steps": 468, "epoch": 0.9984, "percentage": 100.0, "elapsed_time": "0:46:34", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,3318 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9984,
+  "eval_steps": 500,
+  "global_step": 468,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0021333333333333334,
+      "grad_norm": 303.16577329572664,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 7.3237,
+      "step": 1
+    },
+    {
+      "epoch": 0.004266666666666667,
+      "grad_norm": 353.2271149443972,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 7.1998,
+      "step": 2
+    },
+    {
+      "epoch": 0.0064,
+      "grad_norm": 3775.8753863697425,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 7.036,
+      "step": 3
+    },
+    {
+      "epoch": 0.008533333333333334,
+      "grad_norm": 12766.706200003042,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 6.3763,
+      "step": 4
+    },
+    {
+      "epoch": 0.010666666666666666,
+      "grad_norm": 4561.3079788029345,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 4.6166,
+      "step": 5
+    },
+    {
+      "epoch": 0.0128,
+      "grad_norm": 329.75463018445424,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 3.1298,
+      "step": 6
+    },
+    {
+      "epoch": 0.014933333333333333,
+      "grad_norm": 150.3073575839664,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 2.4499,
+      "step": 7
+    },
+    {
+      "epoch": 0.017066666666666667,
+      "grad_norm": 120.22030185769444,
+      "learning_rate": 1.0666666666666667e-05,
+      "loss": 2.1396,
+      "step": 8
+    },
+    {
+      "epoch": 0.0192,
+      "grad_norm": 2801.279095013984,
+      "learning_rate": 1.2e-05,
+      "loss": 2.1943,
+      "step": 9
+    },
+    {
+      "epoch": 0.021333333333333333,
+      "grad_norm": 857.3832692985438,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.0228,
+      "step": 10
+    },
+    {
+      "epoch": 0.023466666666666667,
+      "grad_norm": 104.0268024732774,
+      "learning_rate": 1.4666666666666666e-05,
+      "loss": 1.8804,
+      "step": 11
+    },
+    {
+      "epoch": 0.0256,
+      "grad_norm": 274.73978833765904,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.8405,
+      "step": 12
+    },
+    {
+      "epoch": 0.027733333333333332,
+      "grad_norm": 50.3942946849501,
+      "learning_rate": 1.7333333333333336e-05,
+      "loss": 1.6634,
+      "step": 13
+    },
+    {
+      "epoch": 0.029866666666666666,
+      "grad_norm": 35.72029667887262,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 1.585,
+      "step": 14
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 57.98881512188265,
+      "learning_rate": 2e-05,
+      "loss": 1.5327,
+      "step": 15
+    },
+    {
+      "epoch": 0.034133333333333335,
+      "grad_norm": 51.88325176813403,
+      "learning_rate": 1.9999759524074374e-05,
+      "loss": 1.6873,
+      "step": 16
+    },
+    {
+      "epoch": 0.03626666666666667,
+      "grad_norm": 111.8209187578997,
+      "learning_rate": 1.999903810786324e-05,
+      "loss": 2.1603,
+      "step": 17
+    },
+    {
+      "epoch": 0.0384,
+      "grad_norm": 61.500262882767906,
+      "learning_rate": 1.999783578606323e-05,
+      "loss": 1.5881,
+      "step": 18
+    },
+    {
+      "epoch": 0.04053333333333333,
+      "grad_norm": 195.3438645543274,
+      "learning_rate": 1.9996152616500244e-05,
+      "loss": 3.0391,
+      "step": 19
+    },
+    {
+      "epoch": 0.042666666666666665,
+      "grad_norm": 582.3526037490119,
+      "learning_rate": 1.999398868012663e-05,
+      "loss": 2.35,
+      "step": 20
+    },
+    {
+      "epoch": 0.0448,
+      "grad_norm": 37.40410071254404,
+      "learning_rate": 1.9991344081017312e-05,
+      "loss": 1.385,
+      "step": 21
+    },
+    {
+      "epoch": 0.046933333333333334,
+      "grad_norm": 440.3513371697739,
+      "learning_rate": 1.998821894636477e-05,
+      "loss": 2.4298,
+      "step": 22
+    },
+    {
+      "epoch": 0.04906666666666667,
+      "grad_norm": 43.08235812759601,
+      "learning_rate": 1.9984613426472934e-05,
+      "loss": 1.1715,
+      "step": 23
+    },
+    {
+      "epoch": 0.0512,
+      "grad_norm": 31.488094572141176,
+      "learning_rate": 1.9980527694749952e-05,
+      "loss": 1.0305,
+      "step": 24
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 31.160498386253675,
+      "learning_rate": 1.9975961947699848e-05,
+      "loss": 0.8896,
+      "step": 25
+    },
+    {
+      "epoch": 0.055466666666666664,
+      "grad_norm": 737.782711558036,
+      "learning_rate": 1.9970916404913068e-05,
+      "loss": 1.3138,
+      "step": 26
+    },
+    {
+      "epoch": 0.0576,
+      "grad_norm": 66.20369948568924,
+      "learning_rate": 1.996539130905593e-05,
+      "loss": 0.7626,
+      "step": 27
+    },
+    {
+      "epoch": 0.05973333333333333,
+      "grad_norm": 30.812436073170076,
+      "learning_rate": 1.9959386925858944e-05,
+      "loss": 0.6847,
+      "step": 28
+    },
+    {
+      "epoch": 0.06186666666666667,
+      "grad_norm": 29.298876849093364,
+      "learning_rate": 1.9952903544104026e-05,
+      "loss": 0.5946,
+      "step": 29
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 28.08736432130866,
+      "learning_rate": 1.9945941475610623e-05,
+      "loss": 0.5467,
+      "step": 30
+    },
+    {
+      "epoch": 0.06613333333333334,
+      "grad_norm": 26.806093797987,
+      "learning_rate": 1.9938501055220712e-05,
+      "loss": 0.4314,
+      "step": 31
+    },
+    {
+      "epoch": 0.06826666666666667,
+      "grad_norm": 25.39897533634086,
+      "learning_rate": 1.9930582640782684e-05,
+      "loss": 0.3731,
+      "step": 32
+    },
+    {
+      "epoch": 0.0704,
+      "grad_norm": 22.19029542164766,
+      "learning_rate": 1.9922186613134152e-05,
+      "loss": 0.3163,
+      "step": 33
+    },
+    {
+      "epoch": 0.07253333333333334,
+      "grad_norm": 18.989501274513696,
+      "learning_rate": 1.9913313376083615e-05,
+      "loss": 0.2417,
+      "step": 34
+    },
+    {
+      "epoch": 0.07466666666666667,
+      "grad_norm": 15.535323827258397,
+      "learning_rate": 1.9903963356391057e-05,
+      "loss": 0.2095,
+      "step": 35
+    },
+    {
+      "epoch": 0.0768,
+      "grad_norm": 12.202379826721002,
+      "learning_rate": 1.9894137003747404e-05,
+      "loss": 0.1806,
+      "step": 36
+    },
+    {
+      "epoch": 0.07893333333333333,
+      "grad_norm": 9.743647016337594,
+      "learning_rate": 1.9883834790752904e-05,
+      "loss": 0.1429,
+      "step": 37
+    },
+    {
+      "epoch": 0.08106666666666666,
+      "grad_norm": 7.040896957885027,
+      "learning_rate": 1.98730572128944e-05,
+      "loss": 0.1052,
+      "step": 38
+    },
+    {
+      "epoch": 0.0832,
+      "grad_norm": 5.850481150614585,
+      "learning_rate": 1.986180478852149e-05,
+      "loss": 0.0877,
+      "step": 39
+    },
+    {
+      "epoch": 0.08533333333333333,
+      "grad_norm": 6.351944359015419,
+      "learning_rate": 1.9850078058821615e-05,
+      "loss": 0.1171,
+      "step": 40
+    },
+    {
+      "epoch": 0.08746666666666666,
+      "grad_norm": 4.0127764316578345,
+      "learning_rate": 1.9837877587794003e-05,
+      "loss": 0.1014,
+      "step": 41
+    },
+    {
+      "epoch": 0.0896,
+      "grad_norm": 2.4450558074878153,
+      "learning_rate": 1.9825203962222573e-05,
+      "loss": 0.0509,
+      "step": 42
+    },
+    {
+      "epoch": 0.09173333333333333,
+      "grad_norm": 3.6199437343560463,
+      "learning_rate": 1.9812057791647687e-05,
+      "loss": 0.0976,
+      "step": 43
+    },
+    {
+      "epoch": 0.09386666666666667,
+      "grad_norm": 1.804585356085605,
+      "learning_rate": 1.979843970833686e-05,
+      "loss": 0.0723,
+      "step": 44
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 2.3278790243286953,
+      "learning_rate": 1.9784350367254322e-05,
+      "loss": 0.0565,
+      "step": 45
+    },
+    {
+      "epoch": 0.09813333333333334,
+      "grad_norm": 1.6700332259009343,
+      "learning_rate": 1.9769790446029543e-05,
+      "loss": 0.0622,
+      "step": 46
+    },
+    {
+      "epoch": 0.10026666666666667,
+      "grad_norm": 5.262573042857478,
+      "learning_rate": 1.9754760644924635e-05,
+      "loss": 0.0994,
+      "step": 47
+    },
+    {
+      "epoch": 0.1024,
+      "grad_norm": 2.9582266408641753,
+      "learning_rate": 1.9739261686800662e-05,
+      "loss": 0.0682,
+      "step": 48
+    },
+    {
+      "epoch": 0.10453333333333334,
+      "grad_norm": 1.8583246123127024,
+      "learning_rate": 1.9723294317082876e-05,
+      "loss": 0.0703,
+      "step": 49
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 2.223404034041097,
+      "learning_rate": 1.970685930372489e-05,
+      "loss": 0.0706,
+      "step": 50
+    },
+    {
+      "epoch": 0.1088,
+      "grad_norm": 1.7370846310374337,
+      "learning_rate": 1.968995743717171e-05,
+      "loss": 0.0593,
+      "step": 51
+    },
+    {
+      "epoch": 0.11093333333333333,
+      "grad_norm": 2.1069245641895367,
+      "learning_rate": 1.967258953032174e-05,
+      "loss": 0.0935,
+      "step": 52
+    },
+    {
+      "epoch": 0.11306666666666666,
+      "grad_norm": 3.611309521220031,
+      "learning_rate": 1.965475641848767e-05,
+      "loss": 0.0859,
+      "step": 53
+    },
+    {
+      "epoch": 0.1152,
+      "grad_norm": 3.0134636967786848,
+      "learning_rate": 1.963645895935632e-05,
+      "loss": 0.0838,
+      "step": 54
+    },
+    {
+      "epoch": 0.11733333333333333,
+      "grad_norm": 1.1765247077783991,
+      "learning_rate": 1.9617698032947364e-05,
+      "loss": 0.0575,
+      "step": 55
+    },
+    {
+      "epoch": 0.11946666666666667,
+      "grad_norm": 1.413419636552233,
+      "learning_rate": 1.9598474541571045e-05,
+      "loss": 0.0494,
+      "step": 56
+    },
+    {
+      "epoch": 0.1216,
+      "grad_norm": 3.049218145912724,
+      "learning_rate": 1.9578789409784727e-05,
+      "loss": 0.059,
+      "step": 57
+    },
+    {
+      "epoch": 0.12373333333333333,
+      "grad_norm": 2.319072694901923,
+      "learning_rate": 1.9558643584348478e-05,
+      "loss": 0.0468,
+      "step": 58
+    },
+    {
+      "epoch": 0.12586666666666665,
+      "grad_norm": 0.8811274880218757,
+      "learning_rate": 1.9538038034179496e-05,
+      "loss": 0.0277,
+      "step": 59
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 1.2915088490192281,
+      "learning_rate": 1.951697375030553e-05,
+      "loss": 0.0551,
+      "step": 60
+    },
+    {
+      "epoch": 0.13013333333333332,
+      "grad_norm": 1.9735975352508464,
+      "learning_rate": 1.949545174581722e-05,
+      "loss": 0.0583,
+      "step": 61
+    },
+    {
+      "epoch": 0.13226666666666667,
+      "grad_norm": 1.192344855848184,
+      "learning_rate": 1.9473473055819348e-05,
+      "loss": 0.0552,
+      "step": 62
+    },
+    {
+      "epoch": 0.1344,
+      "grad_norm": 1.2966313742109048,
+      "learning_rate": 1.9451038737381078e-05,
+      "loss": 0.0448,
+      "step": 63
+    },
+    {
+      "epoch": 0.13653333333333334,
+      "grad_norm": 1.3825160157020073,
+      "learning_rate": 1.9428149869485113e-05,
+      "loss": 0.0701,
+      "step": 64
+    },
+    {
+      "epoch": 0.13866666666666666,
+      "grad_norm": 1.9541094599422788,
+      "learning_rate": 1.940480755297579e-05,
+      "loss": 0.0426,
+      "step": 65
+    },
+    {
+      "epoch": 0.1408,
+      "grad_norm": 1.8302152703129704,
+      "learning_rate": 1.9381012910506146e-05,
+      "loss": 0.0586,
+      "step": 66
+    },
+    {
+      "epoch": 0.14293333333333333,
+      "grad_norm": 3.0075784502203073,
+      "learning_rate": 1.9356767086483908e-05,
+      "loss": 0.065,
+      "step": 67
+    },
+    {
+      "epoch": 0.14506666666666668,
+      "grad_norm": 2.8176882799696488,
+      "learning_rate": 1.9332071247016476e-05,
+      "loss": 0.0585,
+      "step": 68
+    },
+    {
+      "epoch": 0.1472,
+      "grad_norm": 1.5885593151199713,
+      "learning_rate": 1.930692657985482e-05,
+      "loss": 0.0444,
+      "step": 69
+    },
+    {
+      "epoch": 0.14933333333333335,
+      "grad_norm": 1.6744129803042231,
+      "learning_rate": 1.9281334294336364e-05,
+      "loss": 0.0499,
+      "step": 70
+    },
+    {
+      "epoch": 0.15146666666666667,
+      "grad_norm": 722.093964558362,
+      "learning_rate": 1.9255295621326813e-05,
+      "loss": 0.5615,
+      "step": 71
+    },
+    {
+      "epoch": 0.1536,
+      "grad_norm": 1.021775336442788,
+      "learning_rate": 1.9228811813160972e-05,
+      "loss": 0.0492,
+      "step": 72
+    },
+    {
+      "epoch": 0.15573333333333333,
+      "grad_norm": 1.719180732110971,
+      "learning_rate": 1.9201884143582496e-05,
+      "loss": 0.0416,
+      "step": 73
+    },
+    {
+      "epoch": 0.15786666666666666,
+      "grad_norm": 0.801300515899985,
+      "learning_rate": 1.9174513907682634e-05,
+      "loss": 0.0583,
+      "step": 74
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.8934798304001422,
+      "learning_rate": 1.9146702421837952e-05,
+      "loss": 0.0522,
+      "step": 75
+    },
+    {
+      "epoch": 0.16213333333333332,
+      "grad_norm": 2.8554464022350388,
+      "learning_rate": 1.9118451023647008e-05,
+      "loss": 0.0509,
+      "step": 76
+    },
+    {
+      "epoch": 0.16426666666666667,
+      "grad_norm": 2.016229542572464,
+      "learning_rate": 1.908976107186603e-05,
+      "loss": 0.0424,
+      "step": 77
+    },
+    {
+      "epoch": 0.1664,
+      "grad_norm": 1.1387239138997594,
+      "learning_rate": 1.906063394634356e-05,
+      "loss": 0.0605,
+      "step": 78
+    },
+    {
+      "epoch": 0.16853333333333334,
+      "grad_norm": 2.333170908799125,
+      "learning_rate": 1.9031071047954095e-05,
+      "loss": 0.0514,
+      "step": 79
+    },
+    {
+      "epoch": 0.17066666666666666,
+      "grad_norm": 3.148123690246876,
+      "learning_rate": 1.90010737985307e-05,
+      "loss": 0.0526,
+      "step": 80
+    },
+    {
+      "epoch": 0.1728,
+      "grad_norm": 0.9306331994487845,
+      "learning_rate": 1.8970643640796642e-05,
+      "loss": 0.0565,
+      "step": 81
+    },
+    {
+      "epoch": 0.17493333333333333,
+      "grad_norm": 1.4757932187911904,
+      "learning_rate": 1.893978203829599e-05,
+      "loss": 0.0596,
+      "step": 82
+    },
+    {
+      "epoch": 0.17706666666666668,
+      "grad_norm": 1.5406104511542824,
+      "learning_rate": 1.8908490475323234e-05,
+      "loss": 0.0528,
+      "step": 83
+    },
+    {
+      "epoch": 0.1792,
+      "grad_norm": 1.4782922193683028,
+      "learning_rate": 1.887677045685188e-05,
+      "loss": 0.0285,
+      "step": 84
+    },
+    {
+      "epoch": 0.18133333333333335,
+      "grad_norm": 1.0965496042734815,
+      "learning_rate": 1.8844623508462093e-05,
+      "loss": 0.0575,
+      "step": 85
+    },
+    {
+      "epoch": 0.18346666666666667,
+      "grad_norm": 1.546939219676516,
+      "learning_rate": 1.8812051176267307e-05,
+      "loss": 0.0539,
+      "step": 86
+    },
+    {
+      "epoch": 0.1856,
+      "grad_norm": 0.8044353550104301,
+      "learning_rate": 1.877905502683987e-05,
+      "loss": 0.0343,
+      "step": 87
+    },
+    {
+      "epoch": 0.18773333333333334,
+      "grad_norm": 1.4879064675453955,
+      "learning_rate": 1.8745636647135693e-05,
+      "loss": 0.0438,
+      "step": 88
+    },
+    {
+      "epoch": 0.18986666666666666,
+      "grad_norm": 1.577173528471535,
+      "learning_rate": 1.871179764441794e-05,
+      "loss": 0.0495,
+      "step": 89
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 1.3084663493341901,
+      "learning_rate": 1.8677539646179706e-05,
+      "loss": 0.0572,
+      "step": 90
+    },
+    {
+      "epoch": 0.19413333333333332,
+      "grad_norm": 1.1197066743705792,
+      "learning_rate": 1.8642864300065767e-05,
+      "loss": 0.049,
+      "step": 91
+    },
+    {
+      "epoch": 0.19626666666666667,
+      "grad_norm": 2.151010541075887,
+      "learning_rate": 1.8607773273793298e-05,
+      "loss": 0.0447,
+      "step": 92
+    },
+    {
+      "epoch": 0.1984,
+      "grad_norm": 2.2954457431315887,
+      "learning_rate": 1.8572268255071718e-05,
+      "loss": 0.057,
+      "step": 93
+    },
+    {
+      "epoch": 0.20053333333333334,
+      "grad_norm": 1.5354278499932348,
+      "learning_rate": 1.853635095152147e-05,
+      "loss": 0.0391,
+      "step": 94
+    },
+    {
+      "epoch": 0.20266666666666666,
+      "grad_norm": 0.9465445667881486,
+      "learning_rate": 1.8500023090591917e-05,
+      "loss": 0.0377,
+      "step": 95
+    },
+    {
+      "epoch": 0.2048,
+      "grad_norm": 1.5138653926594017,
+      "learning_rate": 1.8463286419478256e-05,
+      "loss": 0.0515,
+      "step": 96
+    },
+    {
+      "epoch": 0.20693333333333333,
+      "grad_norm": 0.6636533900983109,
+      "learning_rate": 1.8426142705037487e-05,
+      "loss": 0.0422,
+      "step": 97
+    },
+    {
+      "epoch": 0.20906666666666668,
+      "grad_norm": 1.8423438762388482,
+      "learning_rate": 1.8388593733703428e-05,
+      "loss": 0.0521,
+      "step": 98
+    },
+    {
+      "epoch": 0.2112,
+      "grad_norm": 1.323868663775525,
+      "learning_rate": 1.8350641311400813e-05,
+      "loss": 0.0602,
+      "step": 99
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.8098522474981942,
+      "learning_rate": 1.831228726345841e-05,
+      "loss": 0.0588,
+      "step": 100
+    },
+    {
+      "epoch": 0.21546666666666667,
+      "grad_norm": 2.0211786324636223,
+      "learning_rate": 1.8273533434521262e-05,
+      "loss": 0.0564,
+      "step": 101
+    },
+    {
+      "epoch": 0.2176,
+      "grad_norm": 2.2994083937662713,
+      "learning_rate": 1.8234381688461943e-05,
+      "loss": 0.0506,
+      "step": 102
+    },
+    {
+      "epoch": 0.21973333333333334,
+      "grad_norm": 1.9959590414766974,
+      "learning_rate": 1.8194833908290933e-05,
+      "loss": 0.044,
+      "step": 103
+    },
+    {
+      "epoch": 0.22186666666666666,
+      "grad_norm": 2.360882638356312,
+      "learning_rate": 1.815489199606603e-05,
+      "loss": 0.059,
+      "step": 104
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 2.1351366348440677,
+      "learning_rate": 1.8114557872800906e-05,
+      "loss": 0.0476,
+      "step": 105
+    },
+    {
+      "epoch": 0.22613333333333333,
+      "grad_norm": 1.3665576177215513,
+      "learning_rate": 1.8073833478372682e-05,
+      "loss": 0.0314,
+      "step": 106
+    },
+    {
+      "epoch": 0.22826666666666667,
+      "grad_norm": 0.9922981526651514,
+      "learning_rate": 1.803272077142865e-05,
+      "loss": 0.0444,
+      "step": 107
+    },
+    {
+      "epoch": 0.2304,
+      "grad_norm": 1.8075072368975036,
+      "learning_rate": 1.799122172929206e-05,
+      "loss": 0.0486,
+      "step": 108
+    },
+    {
+      "epoch": 0.23253333333333334,
+      "grad_norm": 1.5561443820733862,
+      "learning_rate": 1.794933834786702e-05,
+      "loss": 0.0311,
+      "step": 109
+    },
+    {
+      "epoch": 0.23466666666666666,
+      "grad_norm": 1.3632115314913158,
+      "learning_rate": 1.7907072641542527e-05,
+      "loss": 0.0665,
+      "step": 110
+    },
+    {
+      "epoch": 0.2368,
+      "grad_norm": 1.3537787582097376,
+      "learning_rate": 1.7864426643095537e-05,
+      "loss": 0.0351,
+      "step": 111
+    },
+    {
+      "epoch": 0.23893333333333333,
+      "grad_norm": 0.8104851815221553,
+      "learning_rate": 1.782140240359325e-05,
+      "loss": 0.0355,
+      "step": 112
+    },
+    {
+      "epoch": 0.24106666666666668,
+      "grad_norm": 1.4449720031557718,
+      "learning_rate": 1.7778001992294426e-05,
+      "loss": 0.0408,
+      "step": 113
+    },
+    {
+      "epoch": 0.2432,
+      "grad_norm": 2.1980401957547766,
+      "learning_rate": 1.773422749654988e-05,
+      "loss": 0.0477,
+      "step": 114
+    },
+    {
+      "epoch": 0.24533333333333332,
+      "grad_norm": 1.5235705975724492,
+      "learning_rate": 1.769008102170209e-05,
+      "loss": 0.037,
+      "step": 115
+    },
+    {
+      "epoch": 0.24746666666666667,
+      "grad_norm": 0.8773714281299343,
+      "learning_rate": 1.7645564690983936e-05,
+      "loss": 0.0356,
+      "step": 116
+    },
+    {
+      "epoch": 0.2496,
+      "grad_norm": 0.8857344133803974,
+      "learning_rate": 1.7600680645416583e-05,
+      "loss": 0.0397,
+      "step": 117
+    },
+    {
+      "epoch": 0.2517333333333333,
+      "grad_norm": 1.1765135397832847,
+      "learning_rate": 1.7555431043706517e-05,
+      "loss": 0.0388,
+      "step": 118
+    },
+    {
+      "epoch": 0.2538666666666667,
+      "grad_norm": 0.7787965832495356,
+      "learning_rate": 1.7509818062141704e-05,
+      "loss": 0.0447,
+      "step": 119
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 1.1558727376844886,
+      "learning_rate": 1.746384389448694e-05,
+      "loss": 0.0265,
+      "step": 120
+    },
+    {
+      "epoch": 0.2581333333333333,
+      "grad_norm": 1.5531094412288022,
+      "learning_rate": 1.7417510751878324e-05,
+      "loss": 0.0571,
+      "step": 121
+    },
+    {
+      "epoch": 0.26026666666666665,
+      "grad_norm": 0.740788808106007,
+      "learning_rate": 1.737082086271693e-05,
+      "loss": 0.0501,
+      "step": 122
+    },
+    {
+      "epoch": 0.2624,
+      "grad_norm": 0.7886321146252248,
+      "learning_rate": 1.7323776472561625e-05,
+      "loss": 0.0281,
+      "step": 123
+    },
+    {
+      "epoch": 0.26453333333333334,
+      "grad_norm": 0.7006144368893459,
+      "learning_rate": 1.727637984402106e-05,
+      "loss": 0.0354,
+      "step": 124
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.4967524533271434,
+      "learning_rate": 1.7228633256644854e-05,
+      "loss": 0.0301,
+      "step": 125
+    },
+    {
+      "epoch": 0.2688,
+      "grad_norm": 0.9992119536121632,
+      "learning_rate": 1.7180539006813973e-05,
+      "loss": 0.042,
+      "step": 126
+    },
+    {
+      "epoch": 0.27093333333333336,
+      "grad_norm": 1.2582964924849702,
+      "learning_rate": 1.713209940763026e-05,
+      "loss": 0.0414,
+      "step": 127
+    },
+    {
+      "epoch": 0.2730666666666667,
+      "grad_norm": 0.5320627853997396,
+      "learning_rate": 1.7083316788805212e-05,
+      "loss": 0.0367,
+      "step": 128
+    },
+    {
+      "epoch": 0.2752,
+      "grad_norm": 0.5378330469500274,
+      "learning_rate": 1.7034193496547903e-05,
+      "loss": 0.0384,
+      "step": 129
+    },
+    {
+      "epoch": 0.2773333333333333,
+      "grad_norm": 9.259419235523216,
+      "learning_rate": 1.6984731893452174e-05,
+      "loss": 0.0687,
+      "step": 130
+    },
+    {
+      "epoch": 0.27946666666666664,
+      "grad_norm": 0.7752489260828755,
+      "learning_rate": 1.6934934358382987e-05,
+      "loss": 0.0506,
+      "step": 131
+    },
+    {
+      "epoch": 0.2816,
+      "grad_norm": 1.2333741857296412,
+      "learning_rate": 1.6884803286362e-05,
+      "loss": 0.0448,
+      "step": 132
+    },
+    {
+      "epoch": 0.28373333333333334,
+      "grad_norm": 1.1992240730463735,
+      "learning_rate": 1.683434108845241e-05,
+      "loss": 0.0504,
+      "step": 133
+    },
+    {
+      "epoch": 0.28586666666666666,
+      "grad_norm": 0.7154947006132196,
+      "learning_rate": 1.6783550191642962e-05,
+      "loss": 0.0289,
+      "step": 134
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.6763298081951205,
+      "learning_rate": 1.6732433038731245e-05,
+      "loss": 0.0413,
+      "step": 135
+    },
+    {
+      "epoch": 0.29013333333333335,
+      "grad_norm": 1.5327709400902307,
+      "learning_rate": 1.668099208820619e-05,
+      "loss": 0.0568,
+      "step": 136
+    },
+    {
+      "epoch": 0.2922666666666667,
+      "grad_norm": 1.413241850948284,
+      "learning_rate": 1.662922981412983e-05,
+      "loss": 0.0529,
+      "step": 137
+    },
+    {
+      "epoch": 0.2944,
+      "grad_norm": 1.1244304252976907,
+      "learning_rate": 1.657714870601833e-05,
+      "loss": 0.0582,
+      "step": 138
+    },
+    {
+      "epoch": 0.2965333333333333,
+      "grad_norm": 0.5118964217117021,
+      "learning_rate": 1.6524751268722216e-05,
+      "loss": 0.0501,
+      "step": 139
+    },
+    {
+      "epoch": 0.2986666666666667,
+      "grad_norm": 0.6930134535710681,
+      "learning_rate": 1.647204002230594e-05,
+      "loss": 0.0341,
+      "step": 140
+    },
+    {
+      "epoch": 0.3008,
+      "grad_norm": 0.8574574146847935,
+      "learning_rate": 1.641901750192666e-05,
+      "loss": 0.0317,
+      "step": 141
+    },
+    {
+      "epoch": 0.30293333333333333,
+      "grad_norm": 1.253852016789459,
+      "learning_rate": 1.63656862577123e-05,
+      "loss": 0.0391,
+      "step": 142
+    },
+    {
+      "epoch": 0.30506666666666665,
+      "grad_norm": 0.6980045449988571,
+      "learning_rate": 1.6312048854638927e-05,
+      "loss": 0.0499,
+      "step": 143
+    },
+    {
+      "epoch": 0.3072,
+      "grad_norm": 0.8184777310682656,
+      "learning_rate": 1.6258107872407376e-05,
+      "loss": 0.0529,
+      "step": 144
+    },
+    {
+      "epoch": 0.30933333333333335,
+      "grad_norm": 0.5971927997338532,
+      "learning_rate": 1.620386590531917e-05,
+      "loss": 0.0324,
+      "step": 145
+    },
+    {
+      "epoch": 0.31146666666666667,
+      "grad_norm": 0.6899390205325759,
+      "learning_rate": 1.614932556215176e-05,
+      "loss": 0.0365,
+      "step": 146
+    },
+    {
+      "epoch": 0.3136,
+      "grad_norm": 0.7151754854547785,
+      "learning_rate": 1.609448946603304e-05,
+      "loss": 0.0453,
+      "step": 147
+    },
+    {
+      "epoch": 0.3157333333333333,
+      "grad_norm": 0.8834546138842408,
+      "learning_rate": 1.6039360254315213e-05,
+      "loss": 0.0334,
+      "step": 148
+    },
+    {
+      "epoch": 0.3178666666666667,
+      "grad_norm": 0.4792748032844571,
+      "learning_rate": 1.598394057844792e-05,
+      "loss": 0.0294,
+      "step": 149
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.0322554725620747,
+      "learning_rate": 1.592823310385073e-05,
+      "loss": 0.0409,
+      "step": 150
+    },
+    {
+      "epoch": 0.3221333333333333,
+      "grad_norm": 1.4230091486157987,
+      "learning_rate": 1.5872240509784943e-05,
+      "loss": 0.0585,
+      "step": 151
+    },
+    {
+      "epoch": 0.32426666666666665,
+      "grad_norm": 1.2041324899062362,
+      "learning_rate": 1.5815965489224746e-05,
+      "loss": 0.0376,
+      "step": 152
+    },
+    {
+      "epoch": 0.3264,
+      "grad_norm": 0.970755585175824,
+      "learning_rate": 1.5759410748727663e-05,
+      "loss": 0.0338,
+      "step": 153
+    },
+    {
+      "epoch": 0.32853333333333334,
+      "grad_norm": 1.5293971676249898,
+      "learning_rate": 1.5702579008304403e-05,
+      "loss": 0.0614,
+      "step": 154
+    },
+    {
+      "epoch": 0.33066666666666666,
+      "grad_norm": 0.6110517060457243,
+      "learning_rate": 1.5645473001288057e-05,
+      "loss": 0.0312,
+      "step": 155
+    },
+    {
+      "epoch": 0.3328,
+      "grad_norm": 1.4352762538394752,
+      "learning_rate": 1.5588095474202597e-05,
+      "loss": 0.0353,
+      "step": 156
+    },
+    {
+      "epoch": 0.33493333333333336,
+      "grad_norm": 0.7125171125043145,
+      "learning_rate": 1.5530449186630805e-05,
+      "loss": 0.0318,
+      "step": 157
+    },
+    {
+      "epoch": 0.3370666666666667,
+      "grad_norm": 2.2795462202235535,
+      "learning_rate": 1.547253691108156e-05,
+      "loss": 0.0377,
+      "step": 158
+    },
+    {
+      "epoch": 0.3392,
+      "grad_norm": 1.0909024623264403,
+      "learning_rate": 1.5414361432856475e-05,
+      "loss": 0.0433,
+      "step": 159
+    },
+    {
+      "epoch": 0.3413333333333333,
+      "grad_norm": 0.686857734775932,
+      "learning_rate": 1.5355925549915943e-05,
+      "loss": 0.0476,
+      "step": 160
+    },
+    {
+      "epoch": 0.34346666666666664,
+      "grad_norm": 1.0424894974104526,
+      "learning_rate": 1.5297232072744576e-05,
+      "loss": 0.0425,
+      "step": 161
+    },
+    {
+      "epoch": 0.3456,
+      "grad_norm": 0.9418678518587029,
+      "learning_rate": 1.5238283824216015e-05,
+      "loss": 0.0496,
+      "step": 162
+    },
+    {
+      "epoch": 0.34773333333333334,
+      "grad_norm": 0.5423092727091834,
+      "learning_rate": 1.5179083639457193e-05,
+      "loss": 0.0246,
+      "step": 163
+    },
+    {
+      "epoch": 0.34986666666666666,
+      "grad_norm": 0.5755202146273961,
+      "learning_rate": 1.5119634365711955e-05,
+      "loss": 0.0394,
+      "step": 164
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.8124862344582832,
+      "learning_rate": 1.5059938862204126e-05,
+      "loss": 0.046,
+      "step": 165
+    },
+    {
+      "epoch": 0.35413333333333336,
+      "grad_norm": 1.289150746306003,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.037,
+      "step": 166
+    },
+    {
+      "epoch": 0.3562666666666667,
+      "grad_norm": 0.9372621548024846,
+      "learning_rate": 1.4939820661870253e-05,
+      "loss": 0.0594,
+      "step": 167
+    },
+    {
+      "epoch": 0.3584,
+      "grad_norm": 0.7231113547887756,
+      "learning_rate": 1.4879403742151283e-05,
+      "loss": 0.0437,
+      "step": 168
+    },
+    {
+      "epoch": 0.3605333333333333,
+      "grad_norm": 0.922243162100279,
+      "learning_rate": 1.481875214660604e-05,
+      "loss": 0.041,
+      "step": 169
+    },
+    {
+      "epoch": 0.3626666666666667,
+      "grad_norm": 0.42231387384182395,
+      "learning_rate": 1.4757868792284231e-05,
+      "loss": 0.0435,
+      "step": 170
+    },
+    {
+      "epoch": 0.3648,
+      "grad_norm": 0.7695794091239532,
+      "learning_rate": 1.469675660738206e-05,
+      "loss": 0.0362,
+      "step": 171
+    },
+    {
+      "epoch": 0.36693333333333333,
+      "grad_norm": 0.5572037371599261,
+      "learning_rate": 1.463541853110137e-05,
+      "loss": 0.0301,
+      "step": 172
+    },
+    {
+      "epoch": 0.36906666666666665,
+      "grad_norm": 0.8890223856167749,
+      "learning_rate": 1.4573857513508297e-05,
+      "loss": 0.0353,
+      "step": 173
+    },
+    {
+      "epoch": 0.3712,
+      "grad_norm": 0.5300608334896313,
+      "learning_rate": 1.4512076515391375e-05,
+      "loss": 0.0263,
+      "step": 174
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 0.8762162718993954,
+      "learning_rate": 1.4450078508119148e-05,
+      "loss": 0.0484,
+      "step": 175
+    },
+    {
+      "epoch": 0.37546666666666667,
+      "grad_norm": 1.3346645193363964,
+      "learning_rate": 1.4387866473497254e-05,
+      "loss": 0.077,
+      "step": 176
+    },
+    {
+      "epoch": 0.3776,
+      "grad_norm": 0.9954685207628413,
+      "learning_rate": 1.4325443403625012e-05,
+      "loss": 0.0555,
+      "step": 177
+    },
+    {
+      "epoch": 0.3797333333333333,
+      "grad_norm": 1.8127871372398991,
+      "learning_rate": 1.4262812300751528e-05,
+      "loss": 0.0398,
+      "step": 178
+    },
+    {
+      "epoch": 0.3818666666666667,
+      "grad_norm": 0.7047656843698573,
+      "learning_rate": 1.4199976177131283e-05,
+      "loss": 0.02,
+      "step": 179
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.9290073704051591,
+      "learning_rate": 1.4136938054879284e-05,
+      "loss": 0.0396,
+      "step": 180
+    },
+    {
+      "epoch": 0.38613333333333333,
+      "grad_norm": 1.2764226119948145,
+      "learning_rate": 1.4073700965825681e-05,
+      "loss": 0.036,
+      "step": 181
+    },
+    {
+      "epoch": 0.38826666666666665,
+      "grad_norm": 0.9587223008540513,
+      "learning_rate": 1.4010267951369985e-05,
+      "loss": 0.0525,
+      "step": 182
+    },
+    {
+      "epoch": 0.3904,
+      "grad_norm": 0.9618631428283729,
+      "learning_rate": 1.3946642062334765e-05,
+      "loss": 0.0444,
+      "step": 183
+    },
+    {
+      "epoch": 0.39253333333333335,
+      "grad_norm": 2.0100658679288435,
+      "learning_rate": 1.3882826358818936e-05,
+      "loss": 0.0436,
+      "step": 184
+    },
+    {
+      "epoch": 0.39466666666666667,
+      "grad_norm": 0.9954379375299915,
+      "learning_rate": 1.381882391005058e-05,
+      "loss": 0.04,
+      "step": 185
+    },
+    {
+      "epoch": 0.3968,
+      "grad_norm": 1.3141896148114316,
+      "learning_rate": 1.3754637794239303e-05,
+      "loss": 0.0334,
+      "step": 186
+    },
+    {
+      "epoch": 0.3989333333333333,
+      "grad_norm": 0.90730269049163,
+      "learning_rate": 1.3690271098428234e-05,
+      "loss": 0.0511,
+      "step": 187
+    },
+    {
+      "epoch": 0.4010666666666667,
+      "grad_norm": 1.2414394032444556,
+      "learning_rate": 1.362572691834553e-05,
+      "loss": 0.0362,
+      "step": 188
+    },
+    {
+      "epoch": 0.4032,
+      "grad_norm": 1.0097746588180307,
+      "learning_rate": 1.356100835825547e-05,
+      "loss": 0.0318,
+      "step": 189
+    },
+    {
+      "epoch": 0.4053333333333333,
+      "grad_norm": 0.9233850635774495,
+      "learning_rate": 1.3496118530809195e-05,
+      "loss": 0.0351,
+      "step": 190
+    },
+    {
+      "epoch": 0.40746666666666664,
+      "grad_norm": 0.5816593448374567,
+      "learning_rate": 1.3431060556894959e-05,
+      "loss": 0.0431,
+      "step": 191
+    },
+    {
+      "epoch": 0.4096,
+      "grad_norm": 1.405582350574752,
+      "learning_rate": 1.3365837565488065e-05,
+      "loss": 0.036,
+      "step": 192
+    },
+    {
+      "epoch": 0.41173333333333334,
+      "grad_norm": 0.7483065796170301,
+      "learning_rate": 1.3300452693500358e-05,
+      "loss": 0.0267,
+      "step": 193
+    },
+    {
+      "epoch": 0.41386666666666666,
+      "grad_norm": 0.708426732185897,
+      "learning_rate": 1.3234909085629362e-05,
+      "loss": 0.0315,
+      "step": 194
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.7844907601400196,
+      "learning_rate": 1.316920989420703e-05,
+      "loss": 0.0238,
+      "step": 195
+    },
+    {
+      "epoch": 0.41813333333333336,
+      "grad_norm": 0.45772582218203484,
+      "learning_rate": 1.3103358279048136e-05,
+      "loss": 0.0235,
+      "step": 196
+    },
+    {
+      "epoch": 0.4202666666666667,
+      "grad_norm": 2.0369880222798344,
+      "learning_rate": 1.30373574072983e-05,
+      "loss": 0.0399,
+      "step": 197
+    },
+    {
+      "epoch": 0.4224,
+      "grad_norm": 1.0442049886874567,
+      "learning_rate": 1.2971210453281675e-05,
+      "loss": 0.0326,
+      "step": 198
+    },
+    {
+      "epoch": 0.4245333333333333,
+      "grad_norm": 0.8079361297617966,
+      "learning_rate": 1.2904920598348252e-05,
+      "loss": 0.0343,
+      "step": 199
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.5328227683903852,
+      "learning_rate": 1.2838491030720882e-05,
+      "loss": 0.04,
+      "step": 200
+    },
+    {
+      "epoch": 0.4288,
+      "grad_norm": 1.0351850053207556,
+      "learning_rate": 1.2771924945341906e-05,
+      "loss": 0.0389,
+      "step": 201
+    },
+    {
+      "epoch": 0.43093333333333333,
+      "grad_norm": 1.6420563344834735,
+      "learning_rate": 1.2705225543719537e-05,
+      "loss": 0.0469,
+      "step": 202
+    },
+    {
+      "epoch": 0.43306666666666666,
+      "grad_norm": 0.8756136800321246,
+      "learning_rate": 1.2638396033773836e-05,
+      "loss": 0.0294,
+      "step": 203
+    },
+    {
+      "epoch": 0.4352,
+      "grad_norm": 0.5048390094407171,
+      "learning_rate": 1.257143962968246e-05,
+      "loss": 0.028,
+      "step": 204
+    },
+    {
+      "epoch": 0.43733333333333335,
+      "grad_norm": 0.5062705845684266,
+      "learning_rate": 1.250435955172606e-05,
+      "loss": 0.0257,
+      "step": 205
+    },
+    {
+      "epoch": 0.43946666666666667,
+      "grad_norm": 0.6946077596533794,
+      "learning_rate": 1.2437159026133397e-05,
+      "loss": 0.036,
+      "step": 206
+    },
+    {
+      "epoch": 0.4416,
+      "grad_norm": 0.4955713113749287,
+      "learning_rate": 1.236984128492619e-05,
+      "loss": 0.0424,
+      "step": 207
+    },
+    {
+      "epoch": 0.4437333333333333,
+      "grad_norm": 0.5002990969185134,
+      "learning_rate": 1.230240956576367e-05,
+      "loss": 0.0268,
+      "step": 208
+    },
+    {
+      "epoch": 0.4458666666666667,
+      "grad_norm": 0.6499936859427997,
+      "learning_rate": 1.2234867111786851e-05,
+      "loss": 0.0374,
+      "step": 209
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.796943745498357,
+      "learning_rate": 1.2167217171462566e-05,
+      "loss": 0.0318,
+      "step": 210
+    },
+    {
+      "epoch": 0.45013333333333333,
+      "grad_norm": 0.8497064365798689,
+      "learning_rate": 1.2099462998427211e-05,
+      "loss": 0.0296,
+      "step": 211
+    },
+    {
+      "epoch": 0.45226666666666665,
+      "grad_norm": 0.5517348061773629,
+      "learning_rate": 1.2031607851330282e-05,
+      "loss": 0.0192,
+      "step": 212
+    },
+    {
+      "epoch": 0.4544,
+      "grad_norm": 0.9985729561704767,
+      "learning_rate": 1.1963654993677645e-05,
+      "loss": 0.039,
+      "step": 213
+    },
+    {
+      "epoch": 0.45653333333333335,
+      "grad_norm": 0.6670151650802995,
+      "learning_rate": 1.189560769367456e-05,
+      "loss": 0.0428,
+      "step": 214
+    },
+    {
+      "epoch": 0.45866666666666667,
+      "grad_norm": 1.6000545490530746,
+      "learning_rate": 1.1827469224068531e-05,
+      "loss": 0.0558,
+      "step": 215
+    },
+    {
+      "epoch": 0.4608,
+      "grad_norm": 1.1784477994642049,
+      "learning_rate": 1.1759242861991855e-05,
+      "loss": 0.0529,
+      "step": 216
+    },
+    {
+      "epoch": 0.4629333333333333,
+      "grad_norm": 0.9235561072658854,
+      "learning_rate": 1.1690931888804055e-05,
+      "loss": 0.0342,
+      "step": 217
+    },
+    {
+      "epoch": 0.4650666666666667,
+      "grad_norm": 0.604794183600379,
+      "learning_rate": 1.1622539589934027e-05,
+      "loss": 0.0391,
+      "step": 218
+    },
+    {
+      "epoch": 0.4672,
+      "grad_norm": 0.4633332588771442,
+      "learning_rate": 1.155406925472205e-05,
+      "loss": 0.0227,
+      "step": 219
+    },
+    {
+      "epoch": 0.4693333333333333,
+      "grad_norm": 0.7264835488117962,
+      "learning_rate": 1.148552417626157e-05,
+      "loss": 0.0351,
+      "step": 220
+    },
+    {
+      "epoch": 0.47146666666666665,
+      "grad_norm": 0.733659081652025,
+      "learning_rate": 1.1416907651240826e-05,
+      "loss": 0.0465,
+      "step": 221
+    },
+    {
+      "epoch": 0.4736,
+      "grad_norm": 0.8049147485126275,
+      "learning_rate": 1.1348222979784289e-05,
+      "loss": 0.0407,
+      "step": 222
+    },
+    {
+      "epoch": 0.47573333333333334,
+      "grad_norm": 0.775576870952529,
+      "learning_rate": 1.1279473465293953e-05,
+      "loss": 0.0373,
+      "step": 223
+    },
+    {
+      "epoch": 0.47786666666666666,
+      "grad_norm": 1.237283998006661,
+      "learning_rate": 1.1210662414290439e-05,
+      "loss": 0.0482,
+      "step": 224
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.6740351828565961,
+      "learning_rate": 1.1141793136253987e-05,
+      "loss": 0.0405,
+      "step": 225
+    },
+    {
+      "epoch": 0.48213333333333336,
+      "grad_norm": 1.2497678974651796,
+      "learning_rate": 1.107286894346527e-05,
+      "loss": 0.0313,
+      "step": 226
+    },
+    {
+      "epoch": 0.4842666666666667,
+      "grad_norm": 0.6220316755005454,
+      "learning_rate": 1.1003893150846103e-05,
+      "loss": 0.0332,
+      "step": 227
+    },
+    {
+      "epoch": 0.4864,
+      "grad_norm": 0.6899190802375788,
+      "learning_rate": 1.09348690758e-05,
+      "loss": 0.0444,
+      "step": 228
+    },
+    {
+      "epoch": 0.4885333333333333,
+      "grad_norm": 0.8788424905334975,
+      "learning_rate": 1.0865800038052632e-05,
+      "loss": 0.0301,
+      "step": 229
+    },
+    {
+      "epoch": 0.49066666666666664,
+      "grad_norm": 0.9525057607599884,
+      "learning_rate": 1.0796689359492154e-05,
+      "loss": 0.031,
+      "step": 230
+    },
+    {
+      "epoch": 0.4928,
+      "grad_norm": 0.45365011027832236,
+      "learning_rate": 1.072754036400944e-05,
+      "loss": 0.0347,
+      "step": 231
+    },
+    {
+      "epoch": 0.49493333333333334,
+      "grad_norm": 0.5783847690812823,
+      "learning_rate": 1.0658356377338235e-05,
+      "loss": 0.0301,
+      "step": 232
+    },
+    {
+      "epoch": 0.49706666666666666,
+      "grad_norm": 0.6938862695154436,
+      "learning_rate": 1.0589140726895179e-05,
+      "loss": 0.0346,
+      "step": 233
+    },
+    {
+      "epoch": 0.4992,
+      "grad_norm": 0.5696171257838482,
+      "learning_rate": 1.0519896741619803e-05,
+      "loss": 0.0383,
+      "step": 234
+    },
+    {
+      "epoch": 0.5013333333333333,
+      "grad_norm": 0.9730739034465179,
+      "learning_rate": 1.0450627751814396e-05,
+      "loss": 0.0365,
+      "step": 235
+    },
+    {
+      "epoch": 0.5034666666666666,
+      "grad_norm": 0.6738632209266081,
+      "learning_rate": 1.0381337088983838e-05,
+      "loss": 0.0495,
+      "step": 236
+    },
+    {
+      "epoch": 0.5056,
+      "grad_norm": 0.9293769576273838,
+      "learning_rate": 1.0312028085675393e-05,
+      "loss": 0.0376,
+      "step": 237
+    },
+    {
+      "epoch": 0.5077333333333334,
+      "grad_norm": 0.7730901514446904,
+      "learning_rate": 1.0242704075318402e-05,
+      "loss": 0.0256,
+      "step": 238
+    },
+    {
+      "epoch": 0.5098666666666667,
+      "grad_norm": 0.9243576819662022,
+      "learning_rate": 1.0173368392063978e-05,
+      "loss": 0.0368,
+      "step": 239
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.6106740685878067,
+      "learning_rate": 1.0104024370624644e-05,
+      "loss": 0.0331,
+      "step": 240
+    },
+    {
+      "epoch": 0.5141333333333333,
+      "grad_norm": 0.5471807046738713,
+      "learning_rate": 1.0034675346113945e-05,
+      "loss": 0.032,
+      "step": 241
+    },
+    {
+      "epoch": 0.5162666666666667,
+      "grad_norm": 1.0112509834033534,
+      "learning_rate": 9.965324653886057e-06,
+      "loss": 0.0372,
+      "step": 242
+    },
+    {
+      "epoch": 0.5184,
+      "grad_norm": 1.22816810696457,
+      "learning_rate": 9.89597562937536e-06,
+      "loss": 0.0333,
+      "step": 243
+    },
+    {
+      "epoch": 0.5205333333333333,
+      "grad_norm": 0.7037349725664515,
+      "learning_rate": 9.826631607936024e-06,
+      "loss": 0.0467,
+      "step": 244
+    },
+    {
+      "epoch": 0.5226666666666666,
+      "grad_norm": 1.2241925260548945,
+      "learning_rate": 9.757295924681601e-06,
+      "loss": 0.0425,
+      "step": 245
+    },
+    {
+      "epoch": 0.5248,
+      "grad_norm": 0.5625363217551341,
+      "learning_rate": 9.687971914324607e-06,
+      "loss": 0.0447,
+      "step": 246
+    },
+    {
+      "epoch": 0.5269333333333334,
+      "grad_norm": 0.5699653225245445,
+      "learning_rate": 9.618662911016165e-06,
+      "loss": 0.0319,
+      "step": 247
+    },
+    {
+      "epoch": 0.5290666666666667,
+      "grad_norm": 0.7314163846872603,
+      "learning_rate": 9.54937224818561e-06,
+      "loss": 0.0328,
+      "step": 248
+    },
+    {
+      "epoch": 0.5312,
+      "grad_norm": 1.3643278717817504,
+      "learning_rate": 9.480103258380198e-06,
+      "loss": 0.0478,
+      "step": 249
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.4918918706062453,
+      "learning_rate": 9.410859273104823e-06,
+      "loss": 0.0302,
+      "step": 250
+    },
+    {
+      "epoch": 0.5354666666666666,
+      "grad_norm": 0.6721247059889798,
+      "learning_rate": 9.341643622661768e-06,
+      "loss": 0.029,
+      "step": 251
+    },
+    {
+      "epoch": 0.5376,
+      "grad_norm": 0.9810888072611974,
+      "learning_rate": 9.272459635990563e-06,
+      "loss": 0.0248,
+      "step": 252
+    },
+    {
+      "epoch": 0.5397333333333333,
+      "grad_norm": 0.4876155527039283,
+      "learning_rate": 9.20331064050785e-06,
+      "loss": 0.0213,
+      "step": 253
+    },
+    {
+      "epoch": 0.5418666666666667,
+      "grad_norm": 0.8358072464072603,
+      "learning_rate": 9.134199961947368e-06,
+      "loss": 0.0422,
+      "step": 254
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.7506843334438347,
+      "learning_rate": 9.065130924199998e-06,
+      "loss": 0.0381,
+      "step": 255
+    },
+    {
+      "epoch": 0.5461333333333334,
+      "grad_norm": 0.3536923477560136,
+      "learning_rate": 8.996106849153897e-06,
+      "loss": 0.0361,
+      "step": 256
+    },
+    {
+      "epoch": 0.5482666666666667,
+      "grad_norm": 0.5200796089003477,
+      "learning_rate": 8.927131056534734e-06,
+      "loss": 0.0316,
+      "step": 257
+    },
+    {
+      "epoch": 0.5504,
+      "grad_norm": 1.0411697648370726,
+      "learning_rate": 8.858206863746018e-06,
+      "loss": 0.0395,
+      "step": 258
+    },
+    {
+      "epoch": 0.5525333333333333,
+      "grad_norm": 0.5824473409964944,
+      "learning_rate": 8.789337585709565e-06,
+      "loss": 0.0373,
+      "step": 259
+    },
+    {
+      "epoch": 0.5546666666666666,
+      "grad_norm": 0.511942343514825,
+      "learning_rate": 8.720526534706052e-06,
+      "loss": 0.0297,
+      "step": 260
+    },
+    {
+      "epoch": 0.5568,
+      "grad_norm": 0.5081243142225651,
+      "learning_rate": 8.651777020215713e-06,
+      "loss": 0.0302,
+      "step": 261
+    },
+    {
+      "epoch": 0.5589333333333333,
+      "grad_norm": 0.5106721938666013,
+      "learning_rate": 8.583092348759176e-06,
+      "loss": 0.033,
+      "step": 262
+    },
+    {
+      "epoch": 0.5610666666666667,
+      "grad_norm": 0.5956281593151138,
+      "learning_rate": 8.514475823738431e-06,
+      "loss": 0.0346,
+      "step": 263
+    },
+    {
+      "epoch": 0.5632,
+      "grad_norm": 0.47917214228596317,
+      "learning_rate": 8.445930745277953e-06,
+      "loss": 0.0233,
+      "step": 264
+    },
+    {
+      "epoch": 0.5653333333333334,
+      "grad_norm": 0.9189179502445622,
+      "learning_rate": 8.377460410065973e-06,
+      "loss": 0.0252,
+      "step": 265
+    },
+    {
+      "epoch": 0.5674666666666667,
+      "grad_norm": 0.7043369220639759,
+      "learning_rate": 8.309068111195947e-06,
+      "loss": 0.0328,
+      "step": 266
+    },
+    {
+      "epoch": 0.5696,
+      "grad_norm": 0.5510595724210231,
+      "learning_rate": 8.240757138008149e-06,
+      "loss": 0.0283,
+      "step": 267
+    },
+    {
+      "epoch": 0.5717333333333333,
+      "grad_norm": 0.8496711751164575,
+      "learning_rate": 8.172530775931476e-06,
+      "loss": 0.0436,
+      "step": 268
+    },
+    {
+      "epoch": 0.5738666666666666,
+      "grad_norm": 0.4503694242791863,
+      "learning_rate": 8.104392306325442e-06,
+      "loss": 0.0359,
+      "step": 269
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.7732096548912992,
+      "learning_rate": 8.036345006322358e-06,
+      "loss": 0.0364,
+      "step": 270
+    },
+    {
+      "epoch": 0.5781333333333334,
+      "grad_norm": 0.4599733594804368,
+      "learning_rate": 7.96839214866972e-06,
+      "loss": 0.0221,
+      "step": 271
+    },
+    {
+      "epoch": 0.5802666666666667,
+      "grad_norm": 1.336428863557948,
+      "learning_rate": 7.900537001572792e-06,
+      "loss": 0.0309,
+      "step": 272
+    },
+    {
+      "epoch": 0.5824,
+      "grad_norm": 0.5843504500873555,
+      "learning_rate": 7.832782828537437e-06,
+      "loss": 0.0412,
+      "step": 273
+    },
+    {
+      "epoch": 0.5845333333333333,
+      "grad_norm": 1.0789524676382762,
+      "learning_rate": 7.765132888213147e-06,
+      "loss": 0.0384,
+      "step": 274
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.737096776428912,
+      "learning_rate": 7.697590434236331e-06,
+      "loss": 0.0501,
+      "step": 275
+    },
+    {
+      "epoch": 0.5888,
+      "grad_norm": 0.8043391582754201,
+      "learning_rate": 7.630158715073813e-06,
+      "loss": 0.0215,
+      "step": 276
+    },
+    {
+      "epoch": 0.5909333333333333,
+      "grad_norm": 0.635341870485607,
+      "learning_rate": 7.56284097386661e-06,
+      "loss": 0.0195,
+      "step": 277
+    },
+    {
+      "epoch": 0.5930666666666666,
+      "grad_norm": 0.593058090471716,
+      "learning_rate": 7.495640448273947e-06,
+      "loss": 0.0288,
+      "step": 278
+    },
+    {
+      "epoch": 0.5952,
+      "grad_norm": 0.8510673331441703,
+      "learning_rate": 7.428560370317542e-06,
+      "loss": 0.0186,
+      "step": 279
+    },
+    {
+      "epoch": 0.5973333333333334,
+      "grad_norm": 0.9565592779805303,
+      "learning_rate": 7.361603966226165e-06,
+      "loss": 0.0294,
+      "step": 280
+    },
+    {
+      "epoch": 0.5994666666666667,
+      "grad_norm": 0.7591784894186213,
+      "learning_rate": 7.294774456280466e-06,
+      "loss": 0.0282,
+      "step": 281
+    },
+    {
+      "epoch": 0.6016,
+      "grad_norm": 0.42677489159298454,
+      "learning_rate": 7.228075054658096e-06,
+      "loss": 0.0409,
+      "step": 282
+    },
+    {
+      "epoch": 0.6037333333333333,
+      "grad_norm": 0.5627212818811943,
+      "learning_rate": 7.1615089692791225e-06,
+      "loss": 0.0276,
+      "step": 283
+    },
+    {
+      "epoch": 0.6058666666666667,
+      "grad_norm": 0.39183013002706013,
+      "learning_rate": 7.095079401651749e-06,
+      "loss": 0.0257,
+      "step": 284
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.4106091763231696,
+      "learning_rate": 7.028789546718327e-06,
+      "loss": 0.022,
+      "step": 285
+    },
+    {
+      "epoch": 0.6101333333333333,
+      "grad_norm": 0.7820664969598445,
+      "learning_rate": 6.962642592701703e-06,
+      "loss": 0.0398,
+      "step": 286
+    },
+    {
+      "epoch": 0.6122666666666666,
+      "grad_norm": 0.6711734140968976,
+      "learning_rate": 6.896641720951868e-06,
+      "loss": 0.0319,
+      "step": 287
+    },
+    {
+      "epoch": 0.6144,
+      "grad_norm": 0.8036347103770932,
+      "learning_rate": 6.8307901057929735e-06,
+      "loss": 0.0301,
+      "step": 288
+    },
+    {
+      "epoch": 0.6165333333333334,
+      "grad_norm": 0.4343557664695177,
+      "learning_rate": 6.765090914370643e-06,
+      "loss": 0.0316,
+      "step": 289
+    },
+    {
+      "epoch": 0.6186666666666667,
+      "grad_norm": 0.9799509282210106,
+      "learning_rate": 6.6995473064996455e-06,
+      "loss": 0.036,
+      "step": 290
+    },
+    {
+      "epoch": 0.6208,
+      "grad_norm": 0.44518139913001936,
+      "learning_rate": 6.634162434511939e-06,
+      "loss": 0.0256,
+      "step": 291
+    },
+    {
+      "epoch": 0.6229333333333333,
+      "grad_norm": 0.6499908491163479,
+      "learning_rate": 6.568939443105045e-06,
+      "loss": 0.0458,
+      "step": 292
+    },
+    {
+      "epoch": 0.6250666666666667,
+      "grad_norm": 0.8496501466573976,
+      "learning_rate": 6.5038814691908095e-06,
+      "loss": 0.0292,
+      "step": 293
+    },
+    {
+      "epoch": 0.6272,
+      "grad_norm": 0.5981028686330536,
+      "learning_rate": 6.438991641744531e-06,
+      "loss": 0.0251,
+      "step": 294
+    },
+    {
+      "epoch": 0.6293333333333333,
+      "grad_norm": 0.8110400012909722,
+      "learning_rate": 6.374273081654474e-06,
+      "loss": 0.0301,
+      "step": 295
+    },
+    {
+      "epoch": 0.6314666666666666,
+      "grad_norm": 0.4891292127480029,
+      "learning_rate": 6.30972890157177e-06,
+      "loss": 0.0224,
+      "step": 296
+    },
+    {
+      "epoch": 0.6336,
+      "grad_norm": 0.598714016686363,
+      "learning_rate": 6.245362205760703e-06,
+      "loss": 0.0273,
+      "step": 297
+    },
+    {
+      "epoch": 0.6357333333333334,
+      "grad_norm": 1.117871466722133,
+      "learning_rate": 6.1811760899494276e-06,
+      "loss": 0.0347,
+      "step": 298
+    },
+    {
+      "epoch": 0.6378666666666667,
+      "grad_norm": 1.098050969004808,
+      "learning_rate": 6.117173641181064e-06,
+      "loss": 0.0468,
+      "step": 299
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.8704162336865564,
+      "learning_rate": 6.053357937665237e-06,
+      "loss": 0.0473,
+      "step": 300
+    },
+    {
+      "epoch": 0.6421333333333333,
+      "grad_norm": 0.26723758613522036,
+      "learning_rate": 5.9897320486300195e-06,
+      "loss": 0.0212,
+      "step": 301
+    },
+    {
+      "epoch": 0.6442666666666667,
+      "grad_norm": 0.793058594700282,
+      "learning_rate": 5.926299034174321e-06,
+      "loss": 0.0323,
+      "step": 302
+    },
+    {
+      "epoch": 0.6464,
+      "grad_norm": 0.8106520095015479,
+      "learning_rate": 5.863061945120719e-06,
+      "loss": 0.0361,
+      "step": 303
+    },
+    {
+      "epoch": 0.6485333333333333,
+      "grad_norm": 0.7749475240302227,
+      "learning_rate": 5.800023822868717e-06,
+      "loss": 0.0271,
+      "step": 304
+    },
+    {
+      "epoch": 0.6506666666666666,
+      "grad_norm": 0.6182100559731326,
+      "learning_rate": 5.737187699248474e-06,
+      "loss": 0.0277,
+      "step": 305
+    },
+    {
+      "epoch": 0.6528,
+      "grad_norm": 0.7280936837269392,
+      "learning_rate": 5.674556596374993e-06,
+      "loss": 0.0348,
+      "step": 306
+    },
+    {
+      "epoch": 0.6549333333333334,
+      "grad_norm": 0.49499465678540155,
+      "learning_rate": 5.612133526502752e-06,
+      "loss": 0.0378,
+      "step": 307
+    },
+    {
+      "epoch": 0.6570666666666667,
+      "grad_norm": 0.48581236356550417,
+      "learning_rate": 5.549921491880856e-06,
+      "loss": 0.0358,
+      "step": 308
+    },
+    {
+      "epoch": 0.6592,
+      "grad_norm": 0.9174556713312179,
+      "learning_rate": 5.487923484608629e-06,
+      "loss": 0.0326,
+      "step": 309
+    },
+    {
+      "epoch": 0.6613333333333333,
+      "grad_norm": 0.566499446081699,
+      "learning_rate": 5.4261424864917075e-06,
+      "loss": 0.0199,
+      "step": 310
+    },
+    {
+      "epoch": 0.6634666666666666,
+      "grad_norm": 1.137197461480215,
+      "learning_rate": 5.364581468898629e-06,
+      "loss": 0.0313,
+      "step": 311
+    },
+    {
+      "epoch": 0.6656,
+      "grad_norm": 0.4475893108260262,
+      "learning_rate": 5.3032433926179395e-06,
+      "loss": 0.0227,
+      "step": 312
+    },
+    {
+      "epoch": 0.6677333333333333,
+      "grad_norm": 0.5095854555003005,
+      "learning_rate": 5.242131207715768e-06,
+      "loss": 0.0351,
+      "step": 313
+    },
+    {
+      "epoch": 0.6698666666666667,
+      "grad_norm": 0.5322845841523259,
+      "learning_rate": 5.181247853393961e-06,
+      "loss": 0.0357,
+      "step": 314
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.8355127340278774,
+      "learning_rate": 5.120596257848716e-06,
+      "loss": 0.0245,
+      "step": 315
+    },
+    {
+      "epoch": 0.6741333333333334,
+      "grad_norm": 1.198148615361382,
+      "learning_rate": 5.060179338129754e-06,
+      "loss": 0.0282,
+      "step": 316
+    },
+    {
+      "epoch": 0.6762666666666667,
+      "grad_norm": 0.77281962005305,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.0304,
+      "step": 317
+    },
+    {
+      "epoch": 0.6784,
+      "grad_norm": 0.6062452489615262,
+      "learning_rate": 4.940061137795876e-06,
+      "loss": 0.0353,
+      "step": 318
+    },
+    {
+      "epoch": 0.6805333333333333,
+      "grad_norm": 0.43421611052260756,
+      "learning_rate": 4.8803656342880475e-06,
+      "loss": 0.0231,
+      "step": 319
+    },
+    {
+      "epoch": 0.6826666666666666,
+      "grad_norm": 0.4402644027282258,
+      "learning_rate": 4.82091636054281e-06,
+      "loss": 0.0275,
+      "step": 320
+    },
+    {
+      "epoch": 0.6848,
+      "grad_norm": 0.4135727836547369,
+      "learning_rate": 4.7617161757839895e-06,
+      "loss": 0.0216,
+      "step": 321
+    },
+    {
+      "epoch": 0.6869333333333333,
+      "grad_norm": 0.5474933678166377,
+      "learning_rate": 4.702767927255432e-06,
+      "loss": 0.0405,
+      "step": 322
+    },
+    {
+      "epoch": 0.6890666666666667,
+      "grad_norm": 0.477609432901859,
+      "learning_rate": 4.644074450084061e-06,
+      "loss": 0.0256,
+      "step": 323
+    },
+    {
+      "epoch": 0.6912,
+      "grad_norm": 0.3001594877169152,
+      "learning_rate": 4.5856385671435285e-06,
+      "loss": 0.0234,
+      "step": 324
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 0.45904329239585984,
+      "learning_rate": 4.527463088918439e-06,
+      "loss": 0.0208,
+      "step": 325
+    },
+    {
+      "epoch": 0.6954666666666667,
+      "grad_norm": 0.8288269971471939,
+      "learning_rate": 4.469550813369198e-06,
+      "loss": 0.0264,
+      "step": 326
+    },
+    {
+      "epoch": 0.6976,
+      "grad_norm": 0.610033984986427,
+      "learning_rate": 4.411904525797408e-06,
+      "loss": 0.0228,
+      "step": 327
+    },
+    {
+      "epoch": 0.6997333333333333,
+      "grad_norm": 0.45459905485331176,
+      "learning_rate": 4.354526998711945e-06,
+      "loss": 0.0339,
+      "step": 328
+    },
+    {
+      "epoch": 0.7018666666666666,
+      "grad_norm": 0.6530795623366433,
+      "learning_rate": 4.297420991695598e-06,
+      "loss": 0.029,
+      "step": 329
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.7765482306498186,
+      "learning_rate": 4.240589251272342e-06,
+      "loss": 0.0218,
+      "step": 330
+    },
+    {
+      "epoch": 0.7061333333333333,
+      "grad_norm": 0.43966478027928985,
+      "learning_rate": 4.184034510775258e-06,
+      "loss": 0.0206,
+      "step": 331
+    },
+    {
+      "epoch": 0.7082666666666667,
+      "grad_norm": 1.3894283227382265,
+      "learning_rate": 4.127759490215057e-06,
+      "loss": 0.0318,
+      "step": 332
+    },
+    {
+      "epoch": 0.7104,
+      "grad_norm": 0.37331468443451093,
+      "learning_rate": 4.0717668961492725e-06,
+      "loss": 0.019,
+      "step": 333
+    },
+    {
+      "epoch": 0.7125333333333334,
+      "grad_norm": 0.673458235705654,
+      "learning_rate": 4.016059421552082e-06,
+      "loss": 0.0377,
+      "step": 334
+    },
+    {
+      "epoch": 0.7146666666666667,
+      "grad_norm": 0.6467225984317707,
+      "learning_rate": 3.9606397456847875e-06,
+      "loss": 0.0207,
+      "step": 335
+    },
+    {
+      "epoch": 0.7168,
+      "grad_norm": 0.9111713839294915,
+      "learning_rate": 3.905510533966959e-06,
+      "loss": 0.0298,
+      "step": 336
+    },
+    {
+      "epoch": 0.7189333333333333,
+      "grad_norm": 0.3640453441847698,
+      "learning_rate": 3.850674437848243e-06,
+      "loss": 0.0153,
+      "step": 337
+    },
+    {
+      "epoch": 0.7210666666666666,
+      "grad_norm": 0.6775424314273997,
+      "learning_rate": 3.79613409468083e-06,
+      "loss": 0.0531,
+      "step": 338
+    },
+    {
+      "epoch": 0.7232,
+      "grad_norm": 0.45312781292115256,
+      "learning_rate": 3.7418921275926245e-06,
+      "loss": 0.0328,
+      "step": 339
+    },
+    {
+      "epoch": 0.7253333333333334,
+      "grad_norm": 0.6234872313783427,
+      "learning_rate": 3.687951145361073e-06,
+      "loss": 0.0393,
+      "step": 340
+    },
+    {
+      "epoch": 0.7274666666666667,
+      "grad_norm": 1.2061170185300967,
+      "learning_rate": 3.634313742287703e-06,
+      "loss": 0.0468,
+      "step": 341
+    },
+    {
+      "epoch": 0.7296,
+      "grad_norm": 0.5833352463057135,
+      "learning_rate": 3.5809824980733445e-06,
+      "loss": 0.0299,
+      "step": 342
+    },
+    {
+      "epoch": 0.7317333333333333,
+      "grad_norm": 0.36837294327024817,
+      "learning_rate": 3.527959977694061e-06,
+      "loss": 0.0251,
+      "step": 343
+    },
+    {
+      "epoch": 0.7338666666666667,
+      "grad_norm": 0.4810227916945505,
+      "learning_rate": 3.475248731277785e-06,
+      "loss": 0.0243,
+      "step": 344
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.5574408320117392,
+      "learning_rate": 3.422851293981676e-06,
+      "loss": 0.0251,
+      "step": 345
+    },
+    {
+      "epoch": 0.7381333333333333,
+      "grad_norm": 0.6214665684822743,
+      "learning_rate": 3.3707701858701736e-06,
+      "loss": 0.0211,
+      "step": 346
+    },
+    {
+      "epoch": 0.7402666666666666,
+      "grad_norm": 0.7289466503971875,
+      "learning_rate": 3.3190079117938167e-06,
+      "loss": 0.0384,
+      "step": 347
+    },
+    {
+      "epoch": 0.7424,
+      "grad_norm": 0.7749220871898594,
+      "learning_rate": 3.2675669612687565e-06,
+      "loss": 0.0482,
+      "step": 348
+    },
+    {
+      "epoch": 0.7445333333333334,
+      "grad_norm": 0.5621519345620897,
+      "learning_rate": 3.2164498083570393e-06,
+      "loss": 0.0307,
+      "step": 349
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.6129914976186284,
+      "learning_rate": 3.165658911547592e-06,
+      "loss": 0.0339,
+      "step": 350
+    },
+    {
+      "epoch": 0.7488,
+      "grad_norm": 0.7792497128436966,
+      "learning_rate": 3.115196713638e-06,
+      "loss": 0.0413,
+      "step": 351
+    },
+    {
+      "epoch": 0.7509333333333333,
+      "grad_norm": 0.8058659414208739,
+      "learning_rate": 3.0650656416170155e-06,
+      "loss": 0.0321,
+      "step": 352
+    },
+    {
+      "epoch": 0.7530666666666667,
+      "grad_norm": 1.0381062746549443,
+      "learning_rate": 3.0152681065478252e-06,
+      "loss": 0.0308,
+      "step": 353
+    },
+    {
+      "epoch": 0.7552,
+      "grad_norm": 1.0129245619456944,
+      "learning_rate": 2.965806503452098e-06,
+      "loss": 0.0336,
+      "step": 354
+    },
+    {
+      "epoch": 0.7573333333333333,
+      "grad_norm": 0.47151923583442085,
+      "learning_rate": 2.9166832111947953e-06,
+      "loss": 0.026,
+      "step": 355
+    },
+    {
+      "epoch": 0.7594666666666666,
+      "grad_norm": 0.5933910542638863,
+      "learning_rate": 2.8679005923697444e-06,
+      "loss": 0.0274,
+      "step": 356
+    },
+    {
+      "epoch": 0.7616,
+      "grad_norm": 0.6226875227172493,
+      "learning_rate": 2.819460993186032e-06,
+      "loss": 0.0256,
+      "step": 357
+    },
+    {
+      "epoch": 0.7637333333333334,
+      "grad_norm": 0.6679506328900092,
+      "learning_rate": 2.7713667433551495e-06,
+      "loss": 0.0252,
+      "step": 358
+    },
+    {
+      "epoch": 0.7658666666666667,
+      "grad_norm": 0.2635830672351724,
+      "learning_rate": 2.7236201559789456e-06,
+      "loss": 0.0208,
+      "step": 359
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.3835186718580681,
+      "learning_rate": 2.6762235274383775e-06,
+      "loss": 0.0253,
+      "step": 360
+    },
+    {
+      "epoch": 0.7701333333333333,
+      "grad_norm": 0.6251532094302285,
+      "learning_rate": 2.629179137283071e-06,
+      "loss": 0.0209,
+      "step": 361
+    },
+    {
+      "epoch": 0.7722666666666667,
+      "grad_norm": 0.6846444745004698,
+      "learning_rate": 2.582489248121677e-06,
+      "loss": 0.0284,
+      "step": 362
+    },
+    {
+      "epoch": 0.7744,
+      "grad_norm": 0.5713976117645878,
+      "learning_rate": 2.5361561055130625e-06,
+      "loss": 0.028,
+      "step": 363
+    },
+    {
+      "epoch": 0.7765333333333333,
+      "grad_norm": 0.5026126924117239,
+      "learning_rate": 2.490181937858296e-06,
+      "loss": 0.0257,
+      "step": 364
+    },
+    {
+      "epoch": 0.7786666666666666,
+      "grad_norm": 0.6122792257804385,
+      "learning_rate": 2.444568956293486e-06,
+      "loss": 0.0341,
+      "step": 365
+    },
+    {
+      "epoch": 0.7808,
+      "grad_norm": 0.40370556320553413,
+      "learning_rate": 2.3993193545834182e-06,
+      "loss": 0.0234,
+      "step": 366
+    },
+    {
+      "epoch": 0.7829333333333334,
+      "grad_norm": 0.2777995491899089,
+      "learning_rate": 2.3544353090160664e-06,
+      "loss": 0.0143,
+      "step": 367
+    },
+    {
+      "epoch": 0.7850666666666667,
+      "grad_norm": 0.602757764248379,
+      "learning_rate": 2.3099189782979126e-06,
+      "loss": 0.0227,
+      "step": 368
+    },
+    {
+      "epoch": 0.7872,
+      "grad_norm": 0.5876930591519407,
+      "learning_rate": 2.265772503450122e-06,
+      "loss": 0.0153,
+      "step": 369
+    },
+    {
+      "epoch": 0.7893333333333333,
+      "grad_norm": 0.6846826034507567,
+      "learning_rate": 2.2219980077055756e-06,
+      "loss": 0.0268,
+      "step": 370
+    },
+    {
+      "epoch": 0.7914666666666667,
+      "grad_norm": 0.5162086979233491,
+      "learning_rate": 2.178597596406752e-06,
+      "loss": 0.018,
+      "step": 371
+    },
+    {
+      "epoch": 0.7936,
+      "grad_norm": 0.5698113191934069,
+      "learning_rate": 2.1355733569044633e-06,
+      "loss": 0.042,
+      "step": 372
+    },
+    {
+      "epoch": 0.7957333333333333,
+      "grad_norm": 0.5331086272206527,
+      "learning_rate": 2.092927358457476e-06,
+      "loss": 0.0242,
+      "step": 373
+    },
+    {
+      "epoch": 0.7978666666666666,
+      "grad_norm": 0.7833847471910158,
+      "learning_rate": 2.0506616521329803e-06,
+      "loss": 0.0346,
+      "step": 374
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.35346719003372534,
+      "learning_rate": 2.008778270707944e-06,
+      "loss": 0.0236,
+      "step": 375
+    },
+    {
+      "epoch": 0.8021333333333334,
+      "grad_norm": 0.7443011312344207,
+      "learning_rate": 1.9672792285713528e-06,
+      "loss": 0.0353,
+      "step": 376
+    },
+    {
+      "epoch": 0.8042666666666667,
+      "grad_norm": 0.2802287306818556,
+      "learning_rate": 1.9261665216273197e-06,
+      "loss": 0.0165,
+      "step": 377
+    },
+    {
+      "epoch": 0.8064,
+      "grad_norm": 0.4158465877007506,
+      "learning_rate": 1.8854421271990964e-06,
+      "loss": 0.0342,
+      "step": 378
+    },
+    {
+      "epoch": 0.8085333333333333,
+      "grad_norm": 0.6518427178413402,
+      "learning_rate": 1.845108003933972e-06,
+      "loss": 0.0262,
+      "step": 379
+    },
+    {
+      "epoch": 0.8106666666666666,
+      "grad_norm": 0.6027500567203649,
+      "learning_rate": 1.8051660917090718e-06,
+      "loss": 0.0412,
+      "step": 380
+    },
+    {
+      "epoch": 0.8128,
+      "grad_norm": 0.757207440052833,
+      "learning_rate": 1.7656183115380577e-06,
+      "loss": 0.0328,
+      "step": 381
+    },
+    {
+      "epoch": 0.8149333333333333,
+      "grad_norm": 0.8293533798251376,
+      "learning_rate": 1.7264665654787405e-06,
+      "loss": 0.0237,
+      "step": 382
+    },
+    {
+      "epoch": 0.8170666666666667,
+      "grad_norm": 0.7509669455316721,
+      "learning_rate": 1.6877127365415924e-06,
+      "loss": 0.0214,
+      "step": 383
+    },
+    {
+      "epoch": 0.8192,
+      "grad_norm": 0.5014248712232455,
+      "learning_rate": 1.6493586885991908e-06,
+      "loss": 0.0387,
+      "step": 384
+    },
+    {
+      "epoch": 0.8213333333333334,
+      "grad_norm": 0.8748237393912051,
+      "learning_rate": 1.6114062662965757e-06,
+      "loss": 0.0317,
+      "step": 385
+    },
+    {
+      "epoch": 0.8234666666666667,
+      "grad_norm": 0.7770936634683773,
+      "learning_rate": 1.5738572949625163e-06,
+      "loss": 0.0347,
+      "step": 386
+    },
+    {
+      "epoch": 0.8256,
+      "grad_norm": 0.722834887813668,
+      "learning_rate": 1.536713580521746e-06,
+      "loss": 0.0384,
+      "step": 387
+    },
+    {
+      "epoch": 0.8277333333333333,
+      "grad_norm": 0.5381479186787534,
+      "learning_rate": 1.4999769094080853e-06,
+      "loss": 0.0173,
+      "step": 388
+    },
+    {
+      "epoch": 0.8298666666666666,
+      "grad_norm": 0.5633652545130038,
+      "learning_rate": 1.4636490484785316e-06,
+      "loss": 0.0335,
+      "step": 389
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.7401945131898912,
+      "learning_rate": 1.4277317449282834e-06,
+      "loss": 0.0475,
+      "step": 390
+    },
+    {
+      "epoch": 0.8341333333333333,
+      "grad_norm": 0.5573956901387076,
+      "learning_rate": 1.3922267262067025e-06,
+      "loss": 0.0212,
+      "step": 391
+    },
+    {
+      "epoch": 0.8362666666666667,
+      "grad_norm": 0.6594976014910652,
+      "learning_rate": 1.3571356999342366e-06,
+      "loss": 0.0223,
+      "step": 392
+    },
+    {
+      "epoch": 0.8384,
+      "grad_norm": 0.39444202398047057,
+      "learning_rate": 1.3224603538202929e-06,
+      "loss": 0.0288,
+      "step": 393
+    },
+    {
+      "epoch": 0.8405333333333334,
+      "grad_norm": 0.6517753855436424,
+      "learning_rate": 1.28820235558206e-06,
+      "loss": 0.0309,
+      "step": 394
+    },
+    {
+      "epoch": 0.8426666666666667,
+      "grad_norm": 0.47554735483988925,
+      "learning_rate": 1.2543633528643084e-06,
+      "loss": 0.025,
+      "step": 395
+    },
+    {
+      "epoch": 0.8448,
+      "grad_norm": 0.5200189273763404,
+      "learning_rate": 1.220944973160133e-06,
+      "loss": 0.0303,
+      "step": 396
+    },
+    {
+      "epoch": 0.8469333333333333,
+      "grad_norm": 0.3773966895641283,
+      "learning_rate": 1.1879488237326952e-06,
+      "loss": 0.0275,
+      "step": 397
+    },
+    {
+      "epoch": 0.8490666666666666,
+      "grad_norm": 0.41251238052334416,
+      "learning_rate": 1.1553764915379095e-06,
+      "loss": 0.0258,
+      "step": 398
+    },
+    {
+      "epoch": 0.8512,
+      "grad_norm": 0.44234356074912834,
+      "learning_rate": 1.1232295431481222e-06,
+      "loss": 0.042,
+      "step": 399
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.7976202514589322,
+      "learning_rate": 1.0915095246767692e-06,
+      "loss": 0.0391,
+      "step": 400
+    },
+    {
+      "epoch": 0.8554666666666667,
+      "grad_norm": 0.4590402183287072,
+      "learning_rate": 1.0602179617040098e-06,
+      "loss": 0.0178,
+      "step": 401
+    },
+    {
+      "epoch": 0.8576,
+      "grad_norm": 0.349604164391915,
+      "learning_rate": 1.0293563592033595e-06,
+      "loss": 0.0213,
+      "step": 402
+    },
+    {
+      "epoch": 0.8597333333333333,
+      "grad_norm": 0.4171534401807337,
+      "learning_rate": 9.989262014693013e-07,
+      "loss": 0.0323,
+      "step": 403
+    },
+    {
+      "epoch": 0.8618666666666667,
+      "grad_norm": 0.9525998577214346,
+      "learning_rate": 9.68928952045909e-07,
+      "loss": 0.0319,
+      "step": 404
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.43387713958853175,
+      "learning_rate": 9.393660536564408e-07,
+      "loss": 0.0293,
+      "step": 405
+    },
+    {
+      "epoch": 0.8661333333333333,
+      "grad_norm": 0.6181788637585869,
+      "learning_rate": 9.102389281339719e-07,
+      "loss": 0.0347,
+      "step": 406
+    },
+    {
+      "epoch": 0.8682666666666666,
+      "grad_norm": 0.4112245482675152,
+      "learning_rate": 8.815489763529938e-07,
+      "loss": 0.0412,
+      "step": 407
+    },
+    {
+      "epoch": 0.8704,
+      "grad_norm": 1.0019704272603145,
+      "learning_rate": 8.532975781620511e-07,
+      "loss": 0.0345,
+      "step": 408
+    },
+    {
+      "epoch": 0.8725333333333334,
+      "grad_norm": 0.3985340312946,
+      "learning_rate": 8.254860923173691e-07,
+      "loss": 0.0272,
+      "step": 409
+    },
+    {
+      "epoch": 0.8746666666666667,
+      "grad_norm": 0.6815670712875654,
+      "learning_rate": 7.981158564175074e-07,
+      "loss": 0.0201,
+      "step": 410
+    },
+    {
+      "epoch": 0.8768,
+      "grad_norm": 0.5010003162281399,
+      "learning_rate": 7.711881868390292e-07,
+      "loss": 0.0268,
+      "step": 411
+    },
+    {
+      "epoch": 0.8789333333333333,
+      "grad_norm": 0.587930435219023,
+      "learning_rate": 7.447043786731867e-07,
+      "loss": 0.0328,
+      "step": 412
+    },
+    {
+      "epoch": 0.8810666666666667,
+      "grad_norm": 0.7385703191912768,
+      "learning_rate": 7.18665705663637e-07,
+      "loss": 0.021,
+      "step": 413
+    },
+    {
+      "epoch": 0.8832,
+      "grad_norm": 0.802872057617413,
+      "learning_rate": 6.930734201451817e-07,
+      "loss": 0.0313,
+      "step": 414
+    },
+    {
+      "epoch": 0.8853333333333333,
+      "grad_norm": 0.3652437091029865,
+      "learning_rate": 6.679287529835266e-07,
+      "loss": 0.0344,
+      "step": 415
+    },
+    {
+      "epoch": 0.8874666666666666,
+      "grad_norm": 0.5639889944551809,
+      "learning_rate": 6.432329135160953e-07,
+      "loss": 0.0287,
+      "step": 416
+    },
+    {
+      "epoch": 0.8896,
+      "grad_norm": 0.3392340924912007,
+      "learning_rate": 6.189870894938587e-07,
+      "loss": 0.0303,
+      "step": 417
+    },
+    {
+      "epoch": 0.8917333333333334,
+      "grad_norm": 0.5293387418247875,
+      "learning_rate": 5.951924470242121e-07,
+      "loss": 0.0327,
+      "step": 418
+    },
+    {
+      "epoch": 0.8938666666666667,
+      "grad_norm": 0.5664320263461886,
+      "learning_rate": 5.718501305148893e-07,
+      "loss": 0.0243,
+      "step": 419
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.5847456818189899,
+      "learning_rate": 5.489612626189245e-07,
+      "loss": 0.0331,
+      "step": 420
+    },
+    {
+      "epoch": 0.8981333333333333,
+      "grad_norm": 1.1828319003570638,
+      "learning_rate": 5.265269441806564e-07,
+      "loss": 0.0363,
+      "step": 421
+    },
+    {
+      "epoch": 0.9002666666666667,
+      "grad_norm": 0.4354584930844899,
+      "learning_rate": 5.045482541827828e-07,
+      "loss": 0.0244,
+      "step": 422
+    },
+    {
+      "epoch": 0.9024,
+      "grad_norm": 0.8949661565466129,
+      "learning_rate": 4.830262496944693e-07,
+      "loss": 0.029,
+      "step": 423
+    },
+    {
+      "epoch": 0.9045333333333333,
+      "grad_norm": 0.4384020038288744,
+      "learning_rate": 4.6196196582050543e-07,
+      "loss": 0.0147,
+      "step": 424
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 0.4674711677217029,
+      "learning_rate": 4.4135641565152265e-07,
+      "loss": 0.0264,
+      "step": 425
+    },
+    {
+      "epoch": 0.9088,
+      "grad_norm": 1.496033281566512,
+      "learning_rate": 4.21210590215273e-07,
+      "loss": 0.0229,
+      "step": 426
+    },
+    {
+      "epoch": 0.9109333333333334,
+      "grad_norm": 0.6444510658740636,
+      "learning_rate": 4.015254584289585e-07,
+      "loss": 0.0284,
+      "step": 427
+    },
+    {
+      "epoch": 0.9130666666666667,
+      "grad_norm": 0.3821784310816325,
+      "learning_rate": 3.8230196705263734e-07,
+      "loss": 0.0314,
+      "step": 428
+    },
+    {
+      "epoch": 0.9152,
+      "grad_norm": 0.4285412525833733,
+      "learning_rate": 3.635410406436857e-07,
+      "loss": 0.0285,
+      "step": 429
+    },
+    {
+      "epoch": 0.9173333333333333,
+      "grad_norm": 0.47164766917478057,
+      "learning_rate": 3.452435815123323e-07,
+      "loss": 0.0242,
+      "step": 430
+    },
+    {
+      "epoch": 0.9194666666666667,
+      "grad_norm": 0.49041783990243004,
+      "learning_rate": 3.2741046967826205e-07,
+      "loss": 0.0295,
+      "step": 431
+    },
+    {
+      "epoch": 0.9216,
+      "grad_norm": 0.6397446017314912,
+      "learning_rate": 3.100425628282899e-07,
+      "loss": 0.0249,
+      "step": 432
+    },
+    {
+      "epoch": 0.9237333333333333,
+      "grad_norm": 0.4970070709773908,
+      "learning_rate": 2.9314069627511045e-07,
+      "loss": 0.0177,
+      "step": 433
+    },
+    {
+      "epoch": 0.9258666666666666,
+      "grad_norm": 0.4670315801826843,
+      "learning_rate": 2.767056829171255e-07,
+      "loss": 0.0288,
+      "step": 434
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.5046915562077479,
+      "learning_rate": 2.607383131993424e-07,
+      "loss": 0.0129,
+      "step": 435
+    },
+    {
+      "epoch": 0.9301333333333334,
+      "grad_norm": 0.8275284725819219,
+      "learning_rate": 2.452393550753662e-07,
+      "loss": 0.0322,
+      "step": 436
+    },
+    {
+      "epoch": 0.9322666666666667,
+      "grad_norm": 0.5330578134222311,
+      "learning_rate": 2.302095539704563e-07,
+      "loss": 0.0291,
+      "step": 437
+    },
+    {
+      "epoch": 0.9344,
+      "grad_norm": 0.4043839746249479,
+      "learning_rate": 2.1564963274568028e-07,
+      "loss": 0.0187,
+      "step": 438
+    },
+    {
+      "epoch": 0.9365333333333333,
+      "grad_norm": 2.1237883356620095,
+      "learning_rate": 2.0156029166314316e-07,
+      "loss": 0.0196,
+      "step": 439
+    },
+    {
+      "epoch": 0.9386666666666666,
+      "grad_norm": 0.9091991546647338,
+      "learning_rate": 1.8794220835231413e-07,
+      "loss": 0.0369,
+      "step": 440
+    },
+    {
+      "epoch": 0.9408,
+      "grad_norm": 1.2279587859330783,
+      "learning_rate": 1.7479603777742937e-07,
+      "loss": 0.043,
+      "step": 441
+    },
+    {
+      "epoch": 0.9429333333333333,
+      "grad_norm": 0.4701919068863411,
+      "learning_rate": 1.6212241220599835e-07,
+      "loss": 0.0167,
+      "step": 442
+    },
+    {
+      "epoch": 0.9450666666666667,
+      "grad_norm": 0.6567820766521014,
+      "learning_rate": 1.49921941178387e-07,
+      "loss": 0.0387,
+      "step": 443
+    },
+    {
+      "epoch": 0.9472,
+      "grad_norm": 0.6387442727751721,
+      "learning_rate": 1.3819521147851122e-07,
+      "loss": 0.0167,
+      "step": 444
+    },
+    {
+      "epoch": 0.9493333333333334,
+      "grad_norm": 0.6453478387521295,
+      "learning_rate": 1.2694278710560282e-07,
+      "loss": 0.0147,
+      "step": 445
+    },
+    {
+      "epoch": 0.9514666666666667,
+      "grad_norm": 0.45942473171463294,
+      "learning_rate": 1.1616520924709773e-07,
+      "loss": 0.0405,
+      "step": 446
+    },
+    {
+      "epoch": 0.9536,
+      "grad_norm": 0.6556176206084849,
+      "learning_rate": 1.0586299625259699e-07,
+      "loss": 0.0335,
+      "step": 447
+    },
+    {
+      "epoch": 0.9557333333333333,
+      "grad_norm": 0.7060471932864678,
+      "learning_rate": 9.603664360894327e-08,
+      "loss": 0.0265,
+      "step": 448
+    },
+    {
+      "epoch": 0.9578666666666666,
+      "grad_norm": 0.6260109644095994,
+      "learning_rate": 8.668662391638439e-08,
+      "loss": 0.0248,
+      "step": 449
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.36731082098951995,
+      "learning_rate": 7.781338686584928e-08,
+      "loss": 0.0185,
+      "step": 450
+    },
+    {
+      "epoch": 0.9621333333333333,
+      "grad_norm": 0.8139729310196088,
+      "learning_rate": 6.94173592173164e-08,
+      "loss": 0.0341,
+      "step": 451
+    },
+    {
+      "epoch": 0.9642666666666667,
+      "grad_norm": 1.6216939031071436,
+      "learning_rate": 6.149894477928909e-08,
+      "loss": 0.0316,
+      "step": 452
+    },
+    {
+      "epoch": 0.9664,
+      "grad_norm": 0.5150067530894208,
+      "learning_rate": 5.405852438937764e-08,
+      "loss": 0.0259,
+      "step": 453
+    },
+    {
+      "epoch": 0.9685333333333334,
+      "grad_norm": 0.8841513107446011,
+      "learning_rate": 4.7096455895976334e-08,
+      "loss": 0.0221,
+      "step": 454
+    },
+    {
+      "epoch": 0.9706666666666667,
+      "grad_norm": 0.6370913091082288,
+      "learning_rate": 4.0613074141059307e-08,
+      "loss": 0.0463,
+      "step": 455
+    },
+    {
+      "epoch": 0.9728,
+      "grad_norm": 0.7085376308611622,
+      "learning_rate": 3.460869094407127e-08,
+      "loss": 0.0463,
+      "step": 456
+    },
+    {
+      "epoch": 0.9749333333333333,
+      "grad_norm": 3.220232340341537,
+      "learning_rate": 2.9083595086933924e-08,
+      "loss": 0.0328,
+      "step": 457
+    },
+    {
+      "epoch": 0.9770666666666666,
+      "grad_norm": 0.5424367863848012,
+      "learning_rate": 2.403805230015488e-08,
+      "loss": 0.0316,
+      "step": 458
+    },
+    {
+      "epoch": 0.9792,
+      "grad_norm": 0.36392784412465723,
+      "learning_rate": 1.947230525005006e-08,
+      "loss": 0.0279,
+      "step": 459
+    },
+    {
+      "epoch": 0.9813333333333333,
+      "grad_norm": 0.6181427229243145,
+      "learning_rate": 1.5386573527067516e-08,
+      "loss": 0.0207,
+      "step": 460
+    },
+    {
+      "epoch": 0.9834666666666667,
+      "grad_norm": 1.0432099564460677,
+      "learning_rate": 1.178105363523252e-08,
+      "loss": 0.0341,
+      "step": 461
+    },
+    {
+      "epoch": 0.9856,
+      "grad_norm": 0.6805191457294142,
+      "learning_rate": 8.655918982689582e-09,
+      "loss": 0.0374,
+      "step": 462
+    },
+    {
+      "epoch": 0.9877333333333334,
+      "grad_norm": 0.7140231951371093,
+      "learning_rate": 6.011319873370225e-09,
+      "loss": 0.0337,
+      "step": 463
+    },
+    {
+      "epoch": 0.9898666666666667,
+      "grad_norm": 0.4539980505144493,
+      "learning_rate": 3.847383499756552e-09,
+      "loss": 0.0233,
+      "step": 464
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.639929310768322,
+      "learning_rate": 2.164213936770576e-09,
+      "loss": 0.0316,
+      "step": 465
+    },
+    {
+      "epoch": 0.9941333333333333,
+      "grad_norm": 0.3734946598281521,
+      "learning_rate": 9.618921367637869e-10,
+      "loss": 0.0418,
+      "step": 466
+    },
+    {
+      "epoch": 0.9962666666666666,
+      "grad_norm": 0.4711246157830267,
+      "learning_rate": 2.404759256247058e-10,
+      "loss": 0.0284,
+      "step": 467
+    },
+    {
+      "epoch": 0.9984,
+      "grad_norm": 0.5677887625377763,
+      "learning_rate": 0.0,
+      "loss": 0.0306,
+      "step": 468
+    },
+    {
+      "epoch": 0.9984,
+      "step": 468,
+      "total_flos": 24715131617280.0,
+      "train_loss": 0.19915007105351895,
+      "train_runtime": 2797.252,
+      "train_samples_per_second": 42.899,
+      "train_steps_per_second": 0.167
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 468,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 24715131617280.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8122ce9766f4c8c84381f15a813e641568bcc0c5b7e17f0e5e2ac6c6f5c093b
+size 7224

upload.py

@@ -0,0 +1,9 @@
+from huggingface_hub import HfApi
+
+api = HfApi()
+
+api.upload_folder(
+    folder_path="/mnt/petrelfs/tangzinan/LLaMA-Factory/saves/LLama3.1-8B/full/train_2024-12-03-21-04-03",
+    repo_id="Word2Li/LLaMA-3.1-8B-AGNews-SFT",
+    repo_type="model",
+)