Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+checkpoint-330/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,60 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: qwen_output_v3
+  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. -->
+
+# qwen_output_v3
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the final_modified_script dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 30.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.48.3
+- Pytorch 2.1.0+cu118
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff617a0825ac42eb44e7e58c33a7feeebe0f654f0fe31eb4a0c31eaaf2dbda4
+size 10107280

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 27.533333333333335,
+    "total_flos": 1.1131745240245862e+17,
+    "train_loss": 0.9375696651863329,
+    "train_runtime": 851.6955,
+    "train_samples_per_second": 6.34,
+    "train_steps_per_second": 0.387
+}

checkpoint-330/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-330/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-330/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff617a0825ac42eb44e7e58c33a7feeebe0f654f0fe31eb4a0c31eaaf2dbda4
+size 10107280

checkpoint-330/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-330/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:520b59e758567a58d40078cdedbbb4bfb2425f03919314f80537f4bc0dc7af79
+size 20279354

checkpoint-330/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb72f599d1027b925d55faf9bd966c3c639994729da3f87b5fcc1655df3e6613
+size 14244

checkpoint-330/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:271ba4f5144f1f534eebe728d49e6aebee535f6c8e5c7ffd197d30099b536c9c
+size 1064

checkpoint-330/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-330/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-330/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-330/trainer_state.json

@@ -0,0 +1,2343 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 27.533333333333335,
+  "eval_steps": 500,
+  "global_step": 330,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.19567996263504028,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 0.94,
+      "step": 1
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.2986994683742523,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 1.0076,
+      "step": 2
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.28921350836753845,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 0.9695,
+      "step": 3
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.30233919620513916,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 0.8687,
+      "step": 4
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.36907249689102173,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 1.099,
+      "step": 5
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.38191747665405273,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 1.2947,
+      "step": 6
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.2860971689224243,
+      "learning_rate": 3.5000000000000004e-07,
+      "loss": 0.9469,
+      "step": 7
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.2793874442577362,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 1.032,
+      "step": 8
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.28660792112350464,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 1.0493,
+      "step": 9
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.23447971045970917,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 1.051,
+      "step": 10
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.5307306051254272,
+      "learning_rate": 5.5e-07,
+      "loss": 1.0976,
+      "step": 11
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.49731138348579407,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 0.9379,
+      "step": 12
+    },
+    {
+      "epoch": 1.0888888888888888,
+      "grad_norm": 0.2752147614955902,
+      "learning_rate": 6.5e-07,
+      "loss": 0.9381,
+      "step": 13
+    },
+    {
+      "epoch": 1.1777777777777778,
+      "grad_norm": 0.34284281730651855,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 0.9569,
+      "step": 14
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.25561222434043884,
+      "learning_rate": 7.5e-07,
+      "loss": 1.0227,
+      "step": 15
+    },
+    {
+      "epoch": 1.3555555555555556,
+      "grad_norm": 0.2456677258014679,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 1.0438,
+      "step": 16
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.29848751425743103,
+      "learning_rate": 8.500000000000001e-07,
+      "loss": 1.1062,
+      "step": 17
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.28204187750816345,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 0.8878,
+      "step": 18
+    },
+    {
+      "epoch": 1.6222222222222222,
+      "grad_norm": 0.26430532336235046,
+      "learning_rate": 9.500000000000001e-07,
+      "loss": 1.0275,
+      "step": 19
+    },
+    {
+      "epoch": 1.7111111111111112,
+      "grad_norm": 0.26862281560897827,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.9946,
+      "step": 20
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.36035194993019104,
+      "learning_rate": 1.0500000000000001e-06,
+      "loss": 1.0708,
+      "step": 21
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.23725222051143646,
+      "learning_rate": 1.1e-06,
+      "loss": 1.101,
+      "step": 22
+    },
+    {
+      "epoch": 1.9777777777777779,
+      "grad_norm": 0.3509962856769562,
+      "learning_rate": 1.1500000000000002e-06,
+      "loss": 0.9893,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.26212382316589355,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.1786,
+      "step": 24
+    },
+    {
+      "epoch": 2.088888888888889,
+      "grad_norm": 0.32545071840286255,
+      "learning_rate": 1.25e-06,
+      "loss": 1.0819,
+      "step": 25
+    },
+    {
+      "epoch": 2.1777777777777776,
+      "grad_norm": 0.23323898017406464,
+      "learning_rate": 1.3e-06,
+      "loss": 1.0393,
+      "step": 26
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.2809179723262787,
+      "learning_rate": 1.3500000000000002e-06,
+      "loss": 1.1029,
+      "step": 27
+    },
+    {
+      "epoch": 2.3555555555555556,
+      "grad_norm": 0.28984516859054565,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 1.0597,
+      "step": 28
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.3196355402469635,
+      "learning_rate": 1.45e-06,
+      "loss": 0.9494,
+      "step": 29
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 0.2864663600921631,
+      "learning_rate": 1.5e-06,
+      "loss": 0.944,
+      "step": 30
+    },
+    {
+      "epoch": 2.6222222222222222,
+      "grad_norm": 0.24206970632076263,
+      "learning_rate": 1.5500000000000002e-06,
+      "loss": 1.023,
+      "step": 31
+    },
+    {
+      "epoch": 2.7111111111111112,
+      "grad_norm": 0.2996947765350342,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.9772,
+      "step": 32
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.28879255056381226,
+      "learning_rate": 1.6500000000000003e-06,
+      "loss": 1.0928,
+      "step": 33
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.27944567799568176,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 0.9012,
+      "step": 34
+    },
+    {
+      "epoch": 2.977777777777778,
+      "grad_norm": 0.2939954400062561,
+      "learning_rate": 1.75e-06,
+      "loss": 1.0461,
+      "step": 35
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.5568829774856567,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 0.9155,
+      "step": 36
+    },
+    {
+      "epoch": 3.088888888888889,
+      "grad_norm": 0.3321582078933716,
+      "learning_rate": 1.85e-06,
+      "loss": 1.0048,
+      "step": 37
+    },
+    {
+      "epoch": 3.1777777777777776,
+      "grad_norm": 0.29956573247909546,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 0.9085,
+      "step": 38
+    },
+    {
+      "epoch": 3.2666666666666666,
+      "grad_norm": 0.2925553023815155,
+      "learning_rate": 1.9500000000000004e-06,
+      "loss": 0.8711,
+      "step": 39
+    },
+    {
+      "epoch": 3.3555555555555556,
+      "grad_norm": 0.32938718795776367,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.0397,
+      "step": 40
+    },
+    {
+      "epoch": 3.4444444444444446,
+      "grad_norm": 0.37126410007476807,
+      "learning_rate": 2.05e-06,
+      "loss": 1.0436,
+      "step": 41
+    },
+    {
+      "epoch": 3.533333333333333,
+      "grad_norm": 0.30750295519828796,
+      "learning_rate": 2.1000000000000002e-06,
+      "loss": 1.1212,
+      "step": 42
+    },
+    {
+      "epoch": 3.6222222222222222,
+      "grad_norm": 0.27158430218696594,
+      "learning_rate": 2.15e-06,
+      "loss": 1.0738,
+      "step": 43
+    },
+    {
+      "epoch": 3.7111111111111112,
+      "grad_norm": 0.19385884702205658,
+      "learning_rate": 2.2e-06,
+      "loss": 0.9962,
+      "step": 44
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.3193662464618683,
+      "learning_rate": 2.25e-06,
+      "loss": 1.121,
+      "step": 45
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 0.30041366815567017,
+      "learning_rate": 2.3000000000000004e-06,
+      "loss": 1.0232,
+      "step": 46
+    },
+    {
+      "epoch": 3.977777777777778,
+      "grad_norm": 0.3569968640804291,
+      "learning_rate": 2.35e-06,
+      "loss": 1.0396,
+      "step": 47
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.0826685428619385,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.0178,
+      "step": 48
+    },
+    {
+      "epoch": 4.088888888888889,
+      "grad_norm": 0.3048429787158966,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 1.0127,
+      "step": 49
+    },
+    {
+      "epoch": 4.177777777777778,
+      "grad_norm": 0.6735008955001831,
+      "learning_rate": 2.5e-06,
+      "loss": 1.0034,
+      "step": 50
+    },
+    {
+      "epoch": 4.266666666666667,
+      "grad_norm": 0.28620263934135437,
+      "learning_rate": 2.55e-06,
+      "loss": 1.0821,
+      "step": 51
+    },
+    {
+      "epoch": 4.355555555555555,
+      "grad_norm": 0.2925148904323578,
+      "learning_rate": 2.6e-06,
+      "loss": 0.8747,
+      "step": 52
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.28806746006011963,
+      "learning_rate": 2.6500000000000005e-06,
+      "loss": 1.0981,
+      "step": 53
+    },
+    {
+      "epoch": 4.533333333333333,
+      "grad_norm": 0.2822423279285431,
+      "learning_rate": 2.7000000000000004e-06,
+      "loss": 0.8774,
+      "step": 54
+    },
+    {
+      "epoch": 4.622222222222222,
+      "grad_norm": 0.30998173356056213,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 1.0841,
+      "step": 55
+    },
+    {
+      "epoch": 4.711111111111111,
+      "grad_norm": 0.3339422047138214,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 1.0752,
+      "step": 56
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.3425965905189514,
+      "learning_rate": 2.85e-06,
+      "loss": 1.087,
+      "step": 57
+    },
+    {
+      "epoch": 4.888888888888889,
+      "grad_norm": 0.2678565979003906,
+      "learning_rate": 2.9e-06,
+      "loss": 1.0578,
+      "step": 58
+    },
+    {
+      "epoch": 4.977777777777778,
+      "grad_norm": 0.3225661516189575,
+      "learning_rate": 2.95e-06,
+      "loss": 0.9329,
+      "step": 59
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.5934492945671082,
+      "learning_rate": 3e-06,
+      "loss": 0.9952,
+      "step": 60
+    },
+    {
+      "epoch": 5.088888888888889,
+      "grad_norm": 0.41927722096443176,
+      "learning_rate": 3.05e-06,
+      "loss": 1.2386,
+      "step": 61
+    },
+    {
+      "epoch": 5.177777777777778,
+      "grad_norm": 0.3196963667869568,
+      "learning_rate": 3.1000000000000004e-06,
+      "loss": 0.9,
+      "step": 62
+    },
+    {
+      "epoch": 5.266666666666667,
+      "grad_norm": 0.31587812304496765,
+      "learning_rate": 3.1500000000000003e-06,
+      "loss": 1.0832,
+      "step": 63
+    },
+    {
+      "epoch": 5.355555555555555,
+      "grad_norm": 0.34145388007164,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.9822,
+      "step": 64
+    },
+    {
+      "epoch": 5.444444444444445,
+      "grad_norm": 0.302914023399353,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.9968,
+      "step": 65
+    },
+    {
+      "epoch": 5.533333333333333,
+      "grad_norm": 0.22116686403751373,
+      "learning_rate": 3.3000000000000006e-06,
+      "loss": 0.9124,
+      "step": 66
+    },
+    {
+      "epoch": 5.622222222222222,
+      "grad_norm": 0.3197582960128784,
+      "learning_rate": 3.3500000000000005e-06,
+      "loss": 1.1134,
+      "step": 67
+    },
+    {
+      "epoch": 5.711111111111111,
+      "grad_norm": 0.31704509258270264,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.879,
+      "step": 68
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 0.35378602147102356,
+      "learning_rate": 3.45e-06,
+      "loss": 1.103,
+      "step": 69
+    },
+    {
+      "epoch": 5.888888888888889,
+      "grad_norm": 0.33167579770088196,
+      "learning_rate": 3.5e-06,
+      "loss": 1.0124,
+      "step": 70
+    },
+    {
+      "epoch": 5.977777777777778,
+      "grad_norm": 0.30484288930892944,
+      "learning_rate": 3.5500000000000003e-06,
+      "loss": 1.001,
+      "step": 71
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.4108036458492279,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 1.0199,
+      "step": 72
+    },
+    {
+      "epoch": 6.088888888888889,
+      "grad_norm": 0.3657933175563812,
+      "learning_rate": 3.65e-06,
+      "loss": 1.1584,
+      "step": 73
+    },
+    {
+      "epoch": 6.177777777777778,
+      "grad_norm": 0.6758050918579102,
+      "learning_rate": 3.7e-06,
+      "loss": 1.0419,
+      "step": 74
+    },
+    {
+      "epoch": 6.266666666666667,
+      "grad_norm": 0.35230952501296997,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.856,
+      "step": 75
+    },
+    {
+      "epoch": 6.355555555555555,
+      "grad_norm": 0.38534823060035706,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.9925,
+      "step": 76
+    },
+    {
+      "epoch": 6.444444444444445,
+      "grad_norm": 0.32009822130203247,
+      "learning_rate": 3.85e-06,
+      "loss": 1.0069,
+      "step": 77
+    },
+    {
+      "epoch": 6.533333333333333,
+      "grad_norm": 0.32822826504707336,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 0.953,
+      "step": 78
+    },
+    {
+      "epoch": 6.622222222222222,
+      "grad_norm": 0.36539173126220703,
+      "learning_rate": 3.95e-06,
+      "loss": 1.1169,
+      "step": 79
+    },
+    {
+      "epoch": 6.711111111111111,
+      "grad_norm": 0.3481679856777191,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.9554,
+      "step": 80
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 0.4089198410511017,
+      "learning_rate": 4.05e-06,
+      "loss": 1.0723,
+      "step": 81
+    },
+    {
+      "epoch": 6.888888888888889,
+      "grad_norm": 0.3250631093978882,
+      "learning_rate": 4.1e-06,
+      "loss": 1.0264,
+      "step": 82
+    },
+    {
+      "epoch": 6.977777777777778,
+      "grad_norm": 0.26394304633140564,
+      "learning_rate": 4.15e-06,
+      "loss": 0.9445,
+      "step": 83
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.5080349445343018,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 1.1842,
+      "step": 84
+    },
+    {
+      "epoch": 7.088888888888889,
+      "grad_norm": 0.349873811006546,
+      "learning_rate": 4.25e-06,
+      "loss": 1.0707,
+      "step": 85
+    },
+    {
+      "epoch": 7.177777777777778,
+      "grad_norm": 0.4573216140270233,
+      "learning_rate": 4.3e-06,
+      "loss": 1.116,
+      "step": 86
+    },
+    {
+      "epoch": 7.266666666666667,
+      "grad_norm": 0.32420143485069275,
+      "learning_rate": 4.350000000000001e-06,
+      "loss": 0.8747,
+      "step": 87
+    },
+    {
+      "epoch": 7.355555555555555,
+      "grad_norm": 0.3515697717666626,
+      "learning_rate": 4.4e-06,
+      "loss": 0.9918,
+      "step": 88
+    },
+    {
+      "epoch": 7.444444444444445,
+      "grad_norm": 0.404070645570755,
+      "learning_rate": 4.450000000000001e-06,
+      "loss": 1.1398,
+      "step": 89
+    },
+    {
+      "epoch": 7.533333333333333,
+      "grad_norm": 0.3488151729106903,
+      "learning_rate": 4.5e-06,
+      "loss": 0.9042,
+      "step": 90
+    },
+    {
+      "epoch": 7.622222222222222,
+      "grad_norm": 0.3190948963165283,
+      "learning_rate": 4.5500000000000005e-06,
+      "loss": 0.9608,
+      "step": 91
+    },
+    {
+      "epoch": 7.711111111111111,
+      "grad_norm": 0.3400370478630066,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 0.9085,
+      "step": 92
+    },
+    {
+      "epoch": 7.8,
+      "grad_norm": 0.3799091577529907,
+      "learning_rate": 4.65e-06,
+      "loss": 1.0053,
+      "step": 93
+    },
+    {
+      "epoch": 7.888888888888889,
+      "grad_norm": 0.31531545519828796,
+      "learning_rate": 4.7e-06,
+      "loss": 1.1269,
+      "step": 94
+    },
+    {
+      "epoch": 7.977777777777778,
+      "grad_norm": 0.540896475315094,
+      "learning_rate": 4.75e-06,
+      "loss": 1.1115,
+      "step": 95
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.4667949080467224,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.8602,
+      "step": 96
+    },
+    {
+      "epoch": 8.088888888888889,
+      "grad_norm": 0.29491057991981506,
+      "learning_rate": 4.85e-06,
+      "loss": 1.0071,
+      "step": 97
+    },
+    {
+      "epoch": 8.177777777777777,
+      "grad_norm": 0.4064798355102539,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 0.847,
+      "step": 98
+    },
+    {
+      "epoch": 8.266666666666667,
+      "grad_norm": 0.35105201601982117,
+      "learning_rate": 4.95e-06,
+      "loss": 0.9321,
+      "step": 99
+    },
+    {
+      "epoch": 8.355555555555556,
+      "grad_norm": 0.42249858379364014,
+      "learning_rate": 5e-06,
+      "loss": 0.9997,
+      "step": 100
+    },
+    {
+      "epoch": 8.444444444444445,
+      "grad_norm": 0.46596774458885193,
+      "learning_rate": 4.9997667899113055e-06,
+      "loss": 0.9206,
+      "step": 101
+    },
+    {
+      "epoch": 8.533333333333333,
+      "grad_norm": 0.4481567442417145,
+      "learning_rate": 4.999067203154777e-06,
+      "loss": 1.0383,
+      "step": 102
+    },
+    {
+      "epoch": 8.622222222222222,
+      "grad_norm": 0.389378160238266,
+      "learning_rate": 4.997901370250966e-06,
+      "loss": 1.2077,
+      "step": 103
+    },
+    {
+      "epoch": 8.71111111111111,
+      "grad_norm": 0.386259526014328,
+      "learning_rate": 4.99626950870707e-06,
+      "loss": 0.9617,
+      "step": 104
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 0.38413456082344055,
+      "learning_rate": 4.994171922976349e-06,
+      "loss": 0.9182,
+      "step": 105
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 0.4302501082420349,
+      "learning_rate": 4.991609004401324e-06,
+      "loss": 1.1561,
+      "step": 106
+    },
+    {
+      "epoch": 8.977777777777778,
+      "grad_norm": 0.4424130320549011,
+      "learning_rate": 4.988581231140772e-06,
+      "loss": 1.135,
+      "step": 107
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.3800254762172699,
+      "learning_rate": 4.985089168080509e-06,
+      "loss": 0.7612,
+      "step": 108
+    },
+    {
+      "epoch": 9.088888888888889,
+      "grad_norm": 0.46646955609321594,
+      "learning_rate": 4.981133466728004e-06,
+      "loss": 0.9991,
+      "step": 109
+    },
+    {
+      "epoch": 9.177777777777777,
+      "grad_norm": 0.4952200949192047,
+      "learning_rate": 4.976714865090827e-06,
+      "loss": 0.9779,
+      "step": 110
+    },
+    {
+      "epoch": 9.266666666666667,
+      "grad_norm": 0.4172927737236023,
+      "learning_rate": 4.971834187538963e-06,
+      "loss": 0.9449,
+      "step": 111
+    },
+    {
+      "epoch": 9.355555555555556,
+      "grad_norm": 0.4364710748195648,
+      "learning_rate": 4.966492344651006e-06,
+      "loss": 0.8786,
+      "step": 112
+    },
+    {
+      "epoch": 9.444444444444445,
+      "grad_norm": 0.4623521566390991,
+      "learning_rate": 4.960690333044279e-06,
+      "loss": 1.0798,
+      "step": 113
+    },
+    {
+      "epoch": 9.533333333333333,
+      "grad_norm": 0.4485428035259247,
+      "learning_rate": 4.954429235188897e-06,
+      "loss": 1.182,
+      "step": 114
+    },
+    {
+      "epoch": 9.622222222222222,
+      "grad_norm": 0.38542506098747253,
+      "learning_rate": 4.947710219205808e-06,
+      "loss": 0.9882,
+      "step": 115
+    },
+    {
+      "epoch": 9.71111111111111,
+      "grad_norm": 0.35373494029045105,
+      "learning_rate": 4.940534538648862e-06,
+      "loss": 0.9649,
+      "step": 116
+    },
+    {
+      "epoch": 9.8,
+      "grad_norm": 0.5160645246505737,
+      "learning_rate": 4.932903532270939e-06,
+      "loss": 1.0484,
+      "step": 117
+    },
+    {
+      "epoch": 9.88888888888889,
+      "grad_norm": 0.3412460684776306,
+      "learning_rate": 4.924818623774178e-06,
+      "loss": 0.8972,
+      "step": 118
+    },
+    {
+      "epoch": 9.977777777777778,
+      "grad_norm": 0.4623534083366394,
+      "learning_rate": 4.916281321544362e-06,
+      "loss": 0.9265,
+      "step": 119
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.4575502872467041,
+      "learning_rate": 4.907293218369499e-06,
+      "loss": 1.1764,
+      "step": 120
+    },
+    {
+      "epoch": 10.088888888888889,
+      "grad_norm": 0.4604892134666443,
+      "learning_rate": 4.897855991142658e-06,
+      "loss": 0.9429,
+      "step": 121
+    },
+    {
+      "epoch": 10.177777777777777,
+      "grad_norm": 0.4723954200744629,
+      "learning_rate": 4.8879714005491205e-06,
+      "loss": 1.0113,
+      "step": 122
+    },
+    {
+      "epoch": 10.266666666666667,
+      "grad_norm": 0.419286847114563,
+      "learning_rate": 4.8776412907378845e-06,
+      "loss": 1.0417,
+      "step": 123
+    },
+    {
+      "epoch": 10.355555555555556,
+      "grad_norm": 0.33823734521865845,
+      "learning_rate": 4.8668675889776095e-06,
+      "loss": 0.9355,
+      "step": 124
+    },
+    {
+      "epoch": 10.444444444444445,
+      "grad_norm": 0.5317716598510742,
+      "learning_rate": 4.855652305297052e-06,
+      "loss": 0.829,
+      "step": 125
+    },
+    {
+      "epoch": 10.533333333333333,
+      "grad_norm": 0.5897918343544006,
+      "learning_rate": 4.843997532110051e-06,
+      "loss": 1.003,
+      "step": 126
+    },
+    {
+      "epoch": 10.622222222222222,
+      "grad_norm": 0.4935283064842224,
+      "learning_rate": 4.83190544382516e-06,
+      "loss": 1.0789,
+      "step": 127
+    },
+    {
+      "epoch": 10.71111111111111,
+      "grad_norm": 0.575020432472229,
+      "learning_rate": 4.819378296439962e-06,
+      "loss": 1.0207,
+      "step": 128
+    },
+    {
+      "epoch": 10.8,
+      "grad_norm": 0.7120870351791382,
+      "learning_rate": 4.80641842712018e-06,
+      "loss": 0.8893,
+      "step": 129
+    },
+    {
+      "epoch": 10.88888888888889,
+      "grad_norm": 0.445549875497818,
+      "learning_rate": 4.793028253763633e-06,
+      "loss": 1.0629,
+      "step": 130
+    },
+    {
+      "epoch": 10.977777777777778,
+      "grad_norm": 0.372715026140213,
+      "learning_rate": 4.7792102745491345e-06,
+      "loss": 0.986,
+      "step": 131
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 0.6868900656700134,
+      "learning_rate": 4.764967067470409e-06,
+      "loss": 1.2309,
+      "step": 132
+    },
+    {
+      "epoch": 11.088888888888889,
+      "grad_norm": 0.47809746861457825,
+      "learning_rate": 4.750301289855128e-06,
+      "loss": 1.0157,
+      "step": 133
+    },
+    {
+      "epoch": 11.177777777777777,
+      "grad_norm": 0.4651176631450653,
+      "learning_rate": 4.735215677869129e-06,
+      "loss": 1.0521,
+      "step": 134
+    },
+    {
+      "epoch": 11.266666666666667,
+      "grad_norm": 0.4832024574279785,
+      "learning_rate": 4.7197130460059385e-06,
+      "loss": 0.861,
+      "step": 135
+    },
+    {
+      "epoch": 11.355555555555556,
+      "grad_norm": 0.508399486541748,
+      "learning_rate": 4.7037962865616795e-06,
+      "loss": 1.0256,
+      "step": 136
+    },
+    {
+      "epoch": 11.444444444444445,
+      "grad_norm": 0.5031757950782776,
+      "learning_rate": 4.687468369095457e-06,
+      "loss": 1.0302,
+      "step": 137
+    },
+    {
+      "epoch": 11.533333333333333,
+      "grad_norm": 0.4271880090236664,
+      "learning_rate": 4.6707323398753346e-06,
+      "loss": 0.9272,
+      "step": 138
+    },
+    {
+      "epoch": 11.622222222222222,
+      "grad_norm": 0.41679927706718445,
+      "learning_rate": 4.6535913213100005e-06,
+      "loss": 0.9849,
+      "step": 139
+    },
+    {
+      "epoch": 11.71111111111111,
+      "grad_norm": 0.4784274995326996,
+      "learning_rate": 4.636048511366222e-06,
+      "loss": 0.7549,
+      "step": 140
+    },
+    {
+      "epoch": 11.8,
+      "grad_norm": 0.5748984217643738,
+      "learning_rate": 4.618107182972209e-06,
+      "loss": 0.9387,
+      "step": 141
+    },
+    {
+      "epoch": 11.88888888888889,
+      "grad_norm": 0.5074996948242188,
+      "learning_rate": 4.599770683406992e-06,
+      "loss": 1.1931,
+      "step": 142
+    },
+    {
+      "epoch": 11.977777777777778,
+      "grad_norm": 0.46601927280426025,
+      "learning_rate": 4.58104243367592e-06,
+      "loss": 0.8533,
+      "step": 143
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.8853896260261536,
+      "learning_rate": 4.561925927872421e-06,
+      "loss": 1.2318,
+      "step": 144
+    },
+    {
+      "epoch": 12.088888888888889,
+      "grad_norm": 0.4770624041557312,
+      "learning_rate": 4.542424732526105e-06,
+      "loss": 0.877,
+      "step": 145
+    },
+    {
+      "epoch": 12.177777777777777,
+      "grad_norm": 0.5245800018310547,
+      "learning_rate": 4.522542485937369e-06,
+      "loss": 0.9198,
+      "step": 146
+    },
+    {
+      "epoch": 12.266666666666667,
+      "grad_norm": 0.8387463092803955,
+      "learning_rate": 4.5022828974986044e-06,
+      "loss": 0.9225,
+      "step": 147
+    },
+    {
+      "epoch": 12.355555555555556,
+      "grad_norm": 0.4439677596092224,
+      "learning_rate": 4.481649747002146e-06,
+      "loss": 1.0818,
+      "step": 148
+    },
+    {
+      "epoch": 12.444444444444445,
+      "grad_norm": 0.4621722996234894,
+      "learning_rate": 4.460646883935079e-06,
+      "loss": 0.9635,
+      "step": 149
+    },
+    {
+      "epoch": 12.533333333333333,
+      "grad_norm": 0.4656592607498169,
+      "learning_rate": 4.43927822676105e-06,
+      "loss": 0.8971,
+      "step": 150
+    },
+    {
+      "epoch": 12.622222222222222,
+      "grad_norm": 0.4961630702018738,
+      "learning_rate": 4.417547762189207e-06,
+      "loss": 0.9474,
+      "step": 151
+    },
+    {
+      "epoch": 12.71111111111111,
+      "grad_norm": 0.5954545736312866,
+      "learning_rate": 4.395459544430407e-06,
+      "loss": 1.0403,
+      "step": 152
+    },
+    {
+      "epoch": 12.8,
+      "grad_norm": 0.7063807249069214,
+      "learning_rate": 4.373017694440828e-06,
+      "loss": 1.0076,
+      "step": 153
+    },
+    {
+      "epoch": 12.88888888888889,
+      "grad_norm": 0.48963138461112976,
+      "learning_rate": 4.35022639915313e-06,
+      "loss": 0.9405,
+      "step": 154
+    },
+    {
+      "epoch": 12.977777777777778,
+      "grad_norm": 0.6047050952911377,
+      "learning_rate": 4.32708991069531e-06,
+      "loss": 0.9689,
+      "step": 155
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 0.779731273651123,
+      "learning_rate": 4.30361254559739e-06,
+      "loss": 0.8877,
+      "step": 156
+    },
+    {
+      "epoch": 13.088888888888889,
+      "grad_norm": 0.6274661421775818,
+      "learning_rate": 4.279798683986084e-06,
+      "loss": 0.9697,
+      "step": 157
+    },
+    {
+      "epoch": 13.177777777777777,
+      "grad_norm": 0.5181424021720886,
+      "learning_rate": 4.255652768767619e-06,
+      "loss": 0.8949,
+      "step": 158
+    },
+    {
+      "epoch": 13.266666666666667,
+      "grad_norm": 0.4889301657676697,
+      "learning_rate": 4.2311793047988145e-06,
+      "loss": 0.941,
+      "step": 159
+    },
+    {
+      "epoch": 13.355555555555556,
+      "grad_norm": 0.5373956561088562,
+      "learning_rate": 4.206382858046636e-06,
+      "loss": 0.792,
+      "step": 160
+    },
+    {
+      "epoch": 13.444444444444445,
+      "grad_norm": 0.4251907765865326,
+      "learning_rate": 4.181268054736319e-06,
+      "loss": 0.9622,
+      "step": 161
+    },
+    {
+      "epoch": 13.533333333333333,
+      "grad_norm": 0.3853691518306732,
+      "learning_rate": 4.15583958048827e-06,
+      "loss": 0.8678,
+      "step": 162
+    },
+    {
+      "epoch": 13.622222222222222,
+      "grad_norm": 0.5543946027755737,
+      "learning_rate": 4.130102179443877e-06,
+      "loss": 0.8901,
+      "step": 163
+    },
+    {
+      "epoch": 13.71111111111111,
+      "grad_norm": 0.6818388104438782,
+      "learning_rate": 4.104060653380403e-06,
+      "loss": 0.9957,
+      "step": 164
+    },
+    {
+      "epoch": 13.8,
+      "grad_norm": 0.6395586729049683,
+      "learning_rate": 4.077719860815132e-06,
+      "loss": 1.0817,
+      "step": 165
+    },
+    {
+      "epoch": 13.88888888888889,
+      "grad_norm": 0.6789353489875793,
+      "learning_rate": 4.051084716098921e-06,
+      "loss": 1.1538,
+      "step": 166
+    },
+    {
+      "epoch": 13.977777777777778,
+      "grad_norm": 0.4569081664085388,
+      "learning_rate": 4.024160188499337e-06,
+      "loss": 0.9047,
+      "step": 167
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 1.7882684469223022,
+      "learning_rate": 3.996951301273556e-06,
+      "loss": 0.9499,
+      "step": 168
+    },
+    {
+      "epoch": 14.088888888888889,
+      "grad_norm": 0.6156724691390991,
+      "learning_rate": 3.969463130731183e-06,
+      "loss": 0.9101,
+      "step": 169
+    },
+    {
+      "epoch": 14.177777777777777,
+      "grad_norm": 0.5264705419540405,
+      "learning_rate": 3.941700805287169e-06,
+      "loss": 1.0762,
+      "step": 170
+    },
+    {
+      "epoch": 14.266666666666667,
+      "grad_norm": 0.5197077989578247,
+      "learning_rate": 3.913669504505015e-06,
+      "loss": 1.0859,
+      "step": 171
+    },
+    {
+      "epoch": 14.355555555555556,
+      "grad_norm": 0.5074746608734131,
+      "learning_rate": 3.8853744581304376e-06,
+      "loss": 0.8807,
+      "step": 172
+    },
+    {
+      "epoch": 14.444444444444445,
+      "grad_norm": 0.5885288119316101,
+      "learning_rate": 3.856820945115655e-06,
+      "loss": 0.7543,
+      "step": 173
+    },
+    {
+      "epoch": 14.533333333333333,
+      "grad_norm": 0.5903788805007935,
+      "learning_rate": 3.828014292634508e-06,
+      "loss": 0.8641,
+      "step": 174
+    },
+    {
+      "epoch": 14.622222222222222,
+      "grad_norm": 0.5170984268188477,
+      "learning_rate": 3.798959875088584e-06,
+      "loss": 0.8557,
+      "step": 175
+    },
+    {
+      "epoch": 14.71111111111111,
+      "grad_norm": 0.4823358356952667,
+      "learning_rate": 3.769663113104516e-06,
+      "loss": 0.8084,
+      "step": 176
+    },
+    {
+      "epoch": 14.8,
+      "grad_norm": 0.5628538131713867,
+      "learning_rate": 3.7401294725226707e-06,
+      "loss": 1.0103,
+      "step": 177
+    },
+    {
+      "epoch": 14.88888888888889,
+      "grad_norm": 0.575435221195221,
+      "learning_rate": 3.7103644633774015e-06,
+      "loss": 0.9011,
+      "step": 178
+    },
+    {
+      "epoch": 14.977777777777778,
+      "grad_norm": 0.7047615051269531,
+      "learning_rate": 3.680373638869047e-06,
+      "loss": 0.9671,
+      "step": 179
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.747231125831604,
+      "learning_rate": 3.650162594327881e-06,
+      "loss": 1.1957,
+      "step": 180
+    },
+    {
+      "epoch": 15.088888888888889,
+      "grad_norm": 0.6477513313293457,
+      "learning_rate": 3.6197369661702052e-06,
+      "loss": 1.0547,
+      "step": 181
+    },
+    {
+      "epoch": 15.177777777777777,
+      "grad_norm": 0.44793015718460083,
+      "learning_rate": 3.589102430846773e-06,
+      "loss": 0.8339,
+      "step": 182
+    },
+    {
+      "epoch": 15.266666666666667,
+      "grad_norm": 0.4845152199268341,
+      "learning_rate": 3.5582647037837446e-06,
+      "loss": 0.933,
+      "step": 183
+    },
+    {
+      "epoch": 15.355555555555556,
+      "grad_norm": 0.5620778203010559,
+      "learning_rate": 3.527229538316371e-06,
+      "loss": 0.8677,
+      "step": 184
+    },
+    {
+      "epoch": 15.444444444444445,
+      "grad_norm": 1.1254522800445557,
+      "learning_rate": 3.4960027246156043e-06,
+      "loss": 0.9953,
+      "step": 185
+    },
+    {
+      "epoch": 15.533333333333333,
+      "grad_norm": 0.5396095514297485,
+      "learning_rate": 3.4645900886078388e-06,
+      "loss": 0.9982,
+      "step": 186
+    },
+    {
+      "epoch": 15.622222222222222,
+      "grad_norm": 0.6709286570549011,
+      "learning_rate": 3.432997490887979e-06,
+      "loss": 0.8604,
+      "step": 187
+    },
+    {
+      "epoch": 15.71111111111111,
+      "grad_norm": 0.655689001083374,
+      "learning_rate": 3.4012308256260366e-06,
+      "loss": 0.7839,
+      "step": 188
+    },
+    {
+      "epoch": 15.8,
+      "grad_norm": 0.6764020323753357,
+      "learning_rate": 3.369296019467473e-06,
+      "loss": 0.8544,
+      "step": 189
+    },
+    {
+      "epoch": 15.88888888888889,
+      "grad_norm": 0.5892664194107056,
+      "learning_rate": 3.3371990304274654e-06,
+      "loss": 0.8877,
+      "step": 190
+    },
+    {
+      "epoch": 15.977777777777778,
+      "grad_norm": 0.5942324995994568,
+      "learning_rate": 3.304945846779346e-06,
+      "loss": 0.9024,
+      "step": 191
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 0.7737208008766174,
+      "learning_rate": 3.272542485937369e-06,
+      "loss": 1.1495,
+      "step": 192
+    },
+    {
+      "epoch": 16.08888888888889,
+      "grad_norm": 0.6798277497291565,
+      "learning_rate": 3.239994993334059e-06,
+      "loss": 0.9458,
+      "step": 193
+    },
+    {
+      "epoch": 16.177777777777777,
+      "grad_norm": 0.5800243020057678,
+      "learning_rate": 3.207309441292325e-06,
+      "loss": 0.881,
+      "step": 194
+    },
+    {
+      "epoch": 16.266666666666666,
+      "grad_norm": 0.626613438129425,
+      "learning_rate": 3.174491927892561e-06,
+      "loss": 0.9062,
+      "step": 195
+    },
+    {
+      "epoch": 16.355555555555554,
+      "grad_norm": 0.6165486574172974,
+      "learning_rate": 3.1415485758349344e-06,
+      "loss": 1.002,
+      "step": 196
+    },
+    {
+      "epoch": 16.444444444444443,
+      "grad_norm": 0.6354159116744995,
+      "learning_rate": 3.1084855312970897e-06,
+      "loss": 0.9224,
+      "step": 197
+    },
+    {
+      "epoch": 16.533333333333335,
+      "grad_norm": 0.6106343865394592,
+      "learning_rate": 3.0753089627874668e-06,
+      "loss": 0.8111,
+      "step": 198
+    },
+    {
+      "epoch": 16.622222222222224,
+      "grad_norm": 0.5856066346168518,
+      "learning_rate": 3.0420250599944525e-06,
+      "loss": 1.1155,
+      "step": 199
+    },
+    {
+      "epoch": 16.711111111111112,
+      "grad_norm": 0.6578230857849121,
+      "learning_rate": 3.0086400326315853e-06,
+      "loss": 0.7782,
+      "step": 200
+    },
+    {
+      "epoch": 16.8,
+      "grad_norm": 0.5129030346870422,
+      "learning_rate": 2.9751601092790185e-06,
+      "loss": 0.8999,
+      "step": 201
+    },
+    {
+      "epoch": 16.88888888888889,
+      "grad_norm": 0.5636340975761414,
+      "learning_rate": 2.941591536221469e-06,
+      "loss": 0.8363,
+      "step": 202
+    },
+    {
+      "epoch": 16.977777777777778,
+      "grad_norm": 0.6733406186103821,
+      "learning_rate": 2.907940576282856e-06,
+      "loss": 0.8183,
+      "step": 203
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 1.0829391479492188,
+      "learning_rate": 2.8742135076578608e-06,
+      "loss": 1.1636,
+      "step": 204
+    },
+    {
+      "epoch": 17.08888888888889,
+      "grad_norm": 0.5469006299972534,
+      "learning_rate": 2.840416622740617e-06,
+      "loss": 0.8142,
+      "step": 205
+    },
+    {
+      "epoch": 17.177777777777777,
+      "grad_norm": 0.6195508241653442,
+      "learning_rate": 2.8065562269507464e-06,
+      "loss": 0.8903,
+      "step": 206
+    },
+    {
+      "epoch": 17.266666666666666,
+      "grad_norm": 0.5448200702667236,
+      "learning_rate": 2.7726386375569748e-06,
+      "loss": 0.9834,
+      "step": 207
+    },
+    {
+      "epoch": 17.355555555555554,
+      "grad_norm": 0.667235791683197,
+      "learning_rate": 2.7386701824985257e-06,
+      "loss": 0.6709,
+      "step": 208
+    },
+    {
+      "epoch": 17.444444444444443,
+      "grad_norm": 0.48227953910827637,
+      "learning_rate": 2.7046571992045334e-06,
+      "loss": 0.8927,
+      "step": 209
+    },
+    {
+      "epoch": 17.533333333333335,
+      "grad_norm": 1.3036866188049316,
+      "learning_rate": 2.670606033411678e-06,
+      "loss": 0.9977,
+      "step": 210
+    },
+    {
+      "epoch": 17.622222222222224,
+      "grad_norm": 0.7368432879447937,
+      "learning_rate": 2.636523037980275e-06,
+      "loss": 0.9036,
+      "step": 211
+    },
+    {
+      "epoch": 17.711111111111112,
+      "grad_norm": 0.49763280153274536,
+      "learning_rate": 2.602414571709036e-06,
+      "loss": 0.9087,
+      "step": 212
+    },
+    {
+      "epoch": 17.8,
+      "grad_norm": 0.7820340394973755,
+      "learning_rate": 2.5682869981487154e-06,
+      "loss": 0.9693,
+      "step": 213
+    },
+    {
+      "epoch": 17.88888888888889,
+      "grad_norm": 0.6577602624893188,
+      "learning_rate": 2.5341466844148775e-06,
+      "loss": 0.8481,
+      "step": 214
+    },
+    {
+      "epoch": 17.977777777777778,
+      "grad_norm": 0.8875017166137695,
+      "learning_rate": 2.5e-06,
+      "loss": 1.0045,
+      "step": 215
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 2.128192663192749,
+      "learning_rate": 2.465853315585123e-06,
+      "loss": 1.0231,
+      "step": 216
+    },
+    {
+      "epoch": 18.08888888888889,
+      "grad_norm": 0.5647242665290833,
+      "learning_rate": 2.431713001851286e-06,
+      "loss": 0.8498,
+      "step": 217
+    },
+    {
+      "epoch": 18.177777777777777,
+      "grad_norm": 0.6913108825683594,
+      "learning_rate": 2.3975854282909645e-06,
+      "loss": 1.0558,
+      "step": 218
+    },
+    {
+      "epoch": 18.266666666666666,
+      "grad_norm": 0.5946425795555115,
+      "learning_rate": 2.3634769620197253e-06,
+      "loss": 0.8356,
+      "step": 219
+    },
+    {
+      "epoch": 18.355555555555554,
+      "grad_norm": 0.9023786187171936,
+      "learning_rate": 2.3293939665883233e-06,
+      "loss": 0.959,
+      "step": 220
+    },
+    {
+      "epoch": 18.444444444444443,
+      "grad_norm": 0.6683367490768433,
+      "learning_rate": 2.2953428007954682e-06,
+      "loss": 0.7641,
+      "step": 221
+    },
+    {
+      "epoch": 18.533333333333335,
+      "grad_norm": 0.7781148552894592,
+      "learning_rate": 2.261329817501475e-06,
+      "loss": 0.9507,
+      "step": 222
+    },
+    {
+      "epoch": 18.622222222222224,
+      "grad_norm": 0.5396183133125305,
+      "learning_rate": 2.2273613624430256e-06,
+      "loss": 0.9078,
+      "step": 223
+    },
+    {
+      "epoch": 18.711111111111112,
+      "grad_norm": 0.6765702962875366,
+      "learning_rate": 2.1934437730492544e-06,
+      "loss": 0.8616,
+      "step": 224
+    },
+    {
+      "epoch": 18.8,
+      "grad_norm": 0.6181918978691101,
+      "learning_rate": 2.159583377259384e-06,
+      "loss": 0.7377,
+      "step": 225
+    },
+    {
+      "epoch": 18.88888888888889,
+      "grad_norm": 0.7162302732467651,
+      "learning_rate": 2.1257864923421405e-06,
+      "loss": 0.9405,
+      "step": 226
+    },
+    {
+      "epoch": 18.977777777777778,
+      "grad_norm": 0.6811490654945374,
+      "learning_rate": 2.092059423717145e-06,
+      "loss": 0.874,
+      "step": 227
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 0.6545157432556152,
+      "learning_rate": 2.0584084637785316e-06,
+      "loss": 0.6244,
+      "step": 228
+    },
+    {
+      "epoch": 19.08888888888889,
+      "grad_norm": 0.5392009615898132,
+      "learning_rate": 2.0248398907209827e-06,
+      "loss": 0.8523,
+      "step": 229
+    },
+    {
+      "epoch": 19.177777777777777,
+      "grad_norm": 0.5963950157165527,
+      "learning_rate": 1.991359967368416e-06,
+      "loss": 0.6882,
+      "step": 230
+    },
+    {
+      "epoch": 19.266666666666666,
+      "grad_norm": 0.6452714204788208,
+      "learning_rate": 1.957974940005548e-06,
+      "loss": 0.7386,
+      "step": 231
+    },
+    {
+      "epoch": 19.355555555555554,
+      "grad_norm": 0.6710150241851807,
+      "learning_rate": 1.9246910372125345e-06,
+      "loss": 0.9825,
+      "step": 232
+    },
+    {
+      "epoch": 19.444444444444443,
+      "grad_norm": 0.5551663637161255,
+      "learning_rate": 1.8915144687029107e-06,
+      "loss": 0.9288,
+      "step": 233
+    },
+    {
+      "epoch": 19.533333333333335,
+      "grad_norm": 0.7859821319580078,
+      "learning_rate": 1.8584514241650667e-06,
+      "loss": 1.0302,
+      "step": 234
+    },
+    {
+      "epoch": 19.622222222222224,
+      "grad_norm": 0.580791175365448,
+      "learning_rate": 1.8255080721074391e-06,
+      "loss": 0.9244,
+      "step": 235
+    },
+    {
+      "epoch": 19.711111111111112,
+      "grad_norm": 0.7111539244651794,
+      "learning_rate": 1.792690558707675e-06,
+      "loss": 0.8465,
+      "step": 236
+    },
+    {
+      "epoch": 19.8,
+      "grad_norm": 0.8440479636192322,
+      "learning_rate": 1.7600050066659418e-06,
+      "loss": 0.9308,
+      "step": 237
+    },
+    {
+      "epoch": 19.88888888888889,
+      "grad_norm": 0.7431160807609558,
+      "learning_rate": 1.7274575140626318e-06,
+      "loss": 0.9417,
+      "step": 238
+    },
+    {
+      "epoch": 19.977777777777778,
+      "grad_norm": 0.8644082546234131,
+      "learning_rate": 1.695054153220655e-06,
+      "loss": 0.8363,
+      "step": 239
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.8472647666931152,
+      "learning_rate": 1.6628009695725348e-06,
+      "loss": 0.5418,
+      "step": 240
+    },
+    {
+      "epoch": 20.08888888888889,
+      "grad_norm": 0.8104817867279053,
+      "learning_rate": 1.630703980532528e-06,
+      "loss": 0.7425,
+      "step": 241
+    },
+    {
+      "epoch": 20.177777777777777,
+      "grad_norm": 0.6427087187767029,
+      "learning_rate": 1.5987691743739636e-06,
+      "loss": 0.7761,
+      "step": 242
+    },
+    {
+      "epoch": 20.266666666666666,
+      "grad_norm": 0.8927726745605469,
+      "learning_rate": 1.5670025091120219e-06,
+      "loss": 0.8807,
+      "step": 243
+    },
+    {
+      "epoch": 20.355555555555554,
+      "grad_norm": 0.5097454786300659,
+      "learning_rate": 1.5354099113921614e-06,
+      "loss": 0.875,
+      "step": 244
+    },
+    {
+      "epoch": 20.444444444444443,
+      "grad_norm": 0.5797455310821533,
+      "learning_rate": 1.5039972753843966e-06,
+      "loss": 0.8312,
+      "step": 245
+    },
+    {
+      "epoch": 20.533333333333335,
+      "grad_norm": 0.7658204436302185,
+      "learning_rate": 1.4727704616836297e-06,
+      "loss": 0.8858,
+      "step": 246
+    },
+    {
+      "epoch": 20.622222222222224,
+      "grad_norm": 0.7070634365081787,
+      "learning_rate": 1.441735296216256e-06,
+      "loss": 0.9683,
+      "step": 247
+    },
+    {
+      "epoch": 20.711111111111112,
+      "grad_norm": 0.5789161920547485,
+      "learning_rate": 1.4108975691532273e-06,
+      "loss": 0.9102,
+      "step": 248
+    },
+    {
+      "epoch": 20.8,
+      "grad_norm": 0.8189324736595154,
+      "learning_rate": 1.3802630338297956e-06,
+      "loss": 0.96,
+      "step": 249
+    },
+    {
+      "epoch": 20.88888888888889,
+      "grad_norm": 0.7410324215888977,
+      "learning_rate": 1.3498374056721198e-06,
+      "loss": 0.9536,
+      "step": 250
+    },
+    {
+      "epoch": 20.977777777777778,
+      "grad_norm": 0.9396767616271973,
+      "learning_rate": 1.3196263611309539e-06,
+      "loss": 0.8433,
+      "step": 251
+    },
+    {
+      "epoch": 21.0,
+      "grad_norm": 0.7975627779960632,
+      "learning_rate": 1.2896355366226e-06,
+      "loss": 0.4761,
+      "step": 252
+    },
+    {
+      "epoch": 21.08888888888889,
+      "grad_norm": 0.7357563972473145,
+      "learning_rate": 1.2598705274773299e-06,
+      "loss": 0.8871,
+      "step": 253
+    },
+    {
+      "epoch": 21.177777777777777,
+      "grad_norm": 0.7067966461181641,
+      "learning_rate": 1.2303368868954848e-06,
+      "loss": 0.773,
+      "step": 254
+    },
+    {
+      "epoch": 21.266666666666666,
+      "grad_norm": 0.593105137348175,
+      "learning_rate": 1.2010401249114166e-06,
+      "loss": 0.8273,
+      "step": 255
+    },
+    {
+      "epoch": 21.355555555555554,
+      "grad_norm": 0.707051157951355,
+      "learning_rate": 1.1719857073654923e-06,
+      "loss": 0.8088,
+      "step": 256
+    },
+    {
+      "epoch": 21.444444444444443,
+      "grad_norm": 0.7845866084098816,
+      "learning_rate": 1.1431790548843464e-06,
+      "loss": 0.9616,
+      "step": 257
+    },
+    {
+      "epoch": 21.533333333333335,
+      "grad_norm": 0.481231689453125,
+      "learning_rate": 1.1146255418695635e-06,
+      "loss": 0.8371,
+      "step": 258
+    },
+    {
+      "epoch": 21.622222222222224,
+      "grad_norm": 1.1225308179855347,
+      "learning_rate": 1.0863304954949856e-06,
+      "loss": 0.802,
+      "step": 259
+    },
+    {
+      "epoch": 21.711111111111112,
+      "grad_norm": 0.6318144798278809,
+      "learning_rate": 1.0582991947128324e-06,
+      "loss": 0.8741,
+      "step": 260
+    },
+    {
+      "epoch": 21.8,
+      "grad_norm": 0.7717880010604858,
+      "learning_rate": 1.0305368692688175e-06,
+      "loss": 0.7535,
+      "step": 261
+    },
+    {
+      "epoch": 21.88888888888889,
+      "grad_norm": 0.6893540024757385,
+      "learning_rate": 1.0030486987264436e-06,
+      "loss": 0.894,
+      "step": 262
+    },
+    {
+      "epoch": 21.977777777777778,
+      "grad_norm": 0.6379507184028625,
+      "learning_rate": 9.758398115006637e-07,
+      "loss": 0.9623,
+      "step": 263
+    },
+    {
+      "epoch": 22.0,
+      "grad_norm": 0.9665340781211853,
+      "learning_rate": 9.489152839010799e-07,
+      "loss": 0.9206,
+      "step": 264
+    },
+    {
+      "epoch": 22.08888888888889,
+      "grad_norm": 0.6625165343284607,
+      "learning_rate": 9.222801391848688e-07,
+      "loss": 0.696,
+      "step": 265
+    },
+    {
+      "epoch": 22.177777777777777,
+      "grad_norm": 0.6619503498077393,
+      "learning_rate": 8.959393466195973e-07,
+      "loss": 0.8825,
+      "step": 266
+    },
+    {
+      "epoch": 22.266666666666666,
+      "grad_norm": 0.5958104133605957,
+      "learning_rate": 8.69897820556124e-07,
+      "loss": 0.9445,
+      "step": 267
+    },
+    {
+      "epoch": 22.355555555555554,
+      "grad_norm": 0.7491523027420044,
+      "learning_rate": 8.441604195117315e-07,
+      "loss": 0.8024,
+      "step": 268
+    },
+    {
+      "epoch": 22.444444444444443,
+      "grad_norm": 0.6927403211593628,
+      "learning_rate": 8.187319452636821e-07,
+      "loss": 0.7532,
+      "step": 269
+    },
+    {
+      "epoch": 22.533333333333335,
+      "grad_norm": 0.7777316570281982,
+      "learning_rate": 7.936171419533653e-07,
+      "loss": 0.949,
+      "step": 270
+    },
+    {
+      "epoch": 22.622222222222224,
+      "grad_norm": 0.5703297257423401,
+      "learning_rate": 7.688206952011862e-07,
+      "loss": 0.7882,
+      "step": 271
+    },
+    {
+      "epoch": 22.711111111111112,
+      "grad_norm": 0.717693030834198,
+      "learning_rate": 7.443472312323824e-07,
+      "loss": 0.7254,
+      "step": 272
+    },
+    {
+      "epoch": 22.8,
+      "grad_norm": 0.6906650066375732,
+      "learning_rate": 7.202013160139159e-07,
+      "loss": 1.1334,
+      "step": 273
+    },
+    {
+      "epoch": 22.88888888888889,
+      "grad_norm": 0.7221674919128418,
+      "learning_rate": 6.963874544026109e-07,
+      "loss": 0.7708,
+      "step": 274
+    },
+    {
+      "epoch": 22.977777777777778,
+      "grad_norm": 0.7417134642601013,
+      "learning_rate": 6.729100893046897e-07,
+      "loss": 0.8617,
+      "step": 275
+    },
+    {
+      "epoch": 23.0,
+      "grad_norm": 0.7064130306243896,
+      "learning_rate": 6.497736008468703e-07,
+      "loss": 0.7606,
+      "step": 276
+    },
+    {
+      "epoch": 23.08888888888889,
+      "grad_norm": 0.741130530834198,
+      "learning_rate": 6.269823055591726e-07,
+      "loss": 0.7765,
+      "step": 277
+    },
+    {
+      "epoch": 23.177777777777777,
+      "grad_norm": 1.3605138063430786,
+      "learning_rate": 6.045404555695935e-07,
+      "loss": 0.907,
+      "step": 278
+    },
+    {
+      "epoch": 23.266666666666666,
+      "grad_norm": 0.6725257635116577,
+      "learning_rate": 5.824522378107936e-07,
+      "loss": 1.0291,
+      "step": 279
+    },
+    {
+      "epoch": 23.355555555555554,
+      "grad_norm": 0.5731009840965271,
+      "learning_rate": 5.607217732389503e-07,
+      "loss": 0.8876,
+      "step": 280
+    },
+    {
+      "epoch": 23.444444444444443,
+      "grad_norm": 0.8626798391342163,
+      "learning_rate": 5.393531160649221e-07,
+      "loss": 0.9152,
+      "step": 281
+    },
+    {
+      "epoch": 23.533333333333335,
+      "grad_norm": 0.6386983394622803,
+      "learning_rate": 5.183502529978548e-07,
+      "loss": 0.9826,
+      "step": 282
+    },
+    {
+      "epoch": 23.622222222222224,
+      "grad_norm": 0.9047194719314575,
+      "learning_rate": 4.977171025013961e-07,
+      "loss": 0.7636,
+      "step": 283
+    },
+    {
+      "epoch": 23.711111111111112,
+      "grad_norm": 0.671303927898407,
+      "learning_rate": 4.774575140626317e-07,
+      "loss": 0.6843,
+      "step": 284
+    },
+    {
+      "epoch": 23.8,
+      "grad_norm": 0.5185788869857788,
+      "learning_rate": 4.5757526747389506e-07,
+      "loss": 0.8194,
+      "step": 285
+    },
+    {
+      "epoch": 23.88888888888889,
+      "grad_norm": 0.673641562461853,
+      "learning_rate": 4.380740721275786e-07,
+      "loss": 0.8164,
+      "step": 286
+    },
+    {
+      "epoch": 23.977777777777778,
+      "grad_norm": 0.7130348086357117,
+      "learning_rate": 4.189575663240794e-07,
+      "loss": 0.7278,
+      "step": 287
+    },
+    {
+      "epoch": 24.0,
+      "grad_norm": 0.894011914730072,
+      "learning_rate": 4.002293165930088e-07,
+      "loss": 0.7292,
+      "step": 288
+    },
+    {
+      "epoch": 24.08888888888889,
+      "grad_norm": 0.7084284424781799,
+      "learning_rate": 3.818928170277911e-07,
+      "loss": 0.6609,
+      "step": 289
+    },
+    {
+      "epoch": 24.177777777777777,
+      "grad_norm": 0.7356826066970825,
+      "learning_rate": 3.639514886337786e-07,
+      "loss": 0.8054,
+      "step": 290
+    },
+    {
+      "epoch": 24.266666666666666,
+      "grad_norm": 0.6582125425338745,
+      "learning_rate": 3.4640867869000036e-07,
+      "loss": 0.869,
+      "step": 291
+    },
+    {
+      "epoch": 24.355555555555554,
+      "grad_norm": 0.6234636306762695,
+      "learning_rate": 3.292676601246661e-07,
+      "loss": 1.0296,
+      "step": 292
+    },
+    {
+      "epoch": 24.444444444444443,
+      "grad_norm": 1.0210919380187988,
+      "learning_rate": 3.125316309045434e-07,
+      "loss": 0.9983,
+      "step": 293
+    },
+    {
+      "epoch": 24.533333333333335,
+      "grad_norm": 0.5547788143157959,
+      "learning_rate": 2.962037134383211e-07,
+      "loss": 0.8998,
+      "step": 294
+    },
+    {
+      "epoch": 24.622222222222224,
+      "grad_norm": 0.6771321296691895,
+      "learning_rate": 2.80286953994062e-07,
+      "loss": 0.805,
+      "step": 295
+    },
+    {
+      "epoch": 24.711111111111112,
+      "grad_norm": 0.6345370411872864,
+      "learning_rate": 2.647843221308721e-07,
+      "loss": 0.6883,
+      "step": 296
+    },
+    {
+      "epoch": 24.8,
+      "grad_norm": 0.6311068534851074,
+      "learning_rate": 2.496987101448728e-07,
+      "loss": 0.8913,
+      "step": 297
+    },
+    {
+      "epoch": 24.88888888888889,
+      "grad_norm": 0.7895520925521851,
+      "learning_rate": 2.3503293252959136e-07,
+      "loss": 0.938,
+      "step": 298
+    },
+    {
+      "epoch": 24.977777777777778,
+      "grad_norm": 0.7793102860450745,
+      "learning_rate": 2.2078972545086647e-07,
+      "loss": 0.8841,
+      "step": 299
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.6420133709907532,
+      "learning_rate": 2.0697174623636795e-07,
+      "loss": 0.556,
+      "step": 300
+    },
+    {
+      "epoch": 25.08888888888889,
+      "grad_norm": 0.6089626550674438,
+      "learning_rate": 1.9358157287982099e-07,
+      "loss": 0.8709,
+      "step": 301
+    },
+    {
+      "epoch": 25.177777777777777,
+      "grad_norm": 1.60710871219635,
+      "learning_rate": 1.8062170356003854e-07,
+      "loss": 0.6853,
+      "step": 302
+    },
+    {
+      "epoch": 25.266666666666666,
+      "grad_norm": 0.678098738193512,
+      "learning_rate": 1.680945561748412e-07,
+      "loss": 0.995,
+      "step": 303
+    },
+    {
+      "epoch": 25.355555555555554,
+      "grad_norm": 0.5670207738876343,
+      "learning_rate": 1.5600246788994938e-07,
+      "loss": 0.8167,
+      "step": 304
+    },
+    {
+      "epoch": 25.444444444444443,
+      "grad_norm": 0.6996327638626099,
+      "learning_rate": 1.44347694702949e-07,
+      "loss": 0.9414,
+      "step": 305
+    },
+    {
+      "epoch": 25.533333333333335,
+      "grad_norm": 0.7256758213043213,
+      "learning_rate": 1.3313241102239056e-07,
+      "loss": 0.9439,
+      "step": 306
+    },
+    {
+      "epoch": 25.622222222222224,
+      "grad_norm": 0.5879709124565125,
+      "learning_rate": 1.223587092621162e-07,
+      "loss": 0.6697,
+      "step": 307
+    },
+    {
+      "epoch": 25.711111111111112,
+      "grad_norm": 0.7841221690177917,
+      "learning_rate": 1.120285994508799e-07,
+      "loss": 0.9173,
+      "step": 308
+    },
+    {
+      "epoch": 25.8,
+      "grad_norm": 0.6498060822486877,
+      "learning_rate": 1.0214400885734194e-07,
+      "loss": 0.8086,
+      "step": 309
+    },
+    {
+      "epoch": 25.88888888888889,
+      "grad_norm": 0.740508496761322,
+      "learning_rate": 9.270678163050218e-08,
+      "loss": 0.8424,
+      "step": 310
+    },
+    {
+      "epoch": 25.977777777777778,
+      "grad_norm": 0.6314177513122559,
+      "learning_rate": 8.371867845563819e-08,
+      "loss": 0.8007,
+      "step": 311
+    },
+    {
+      "epoch": 26.0,
+      "grad_norm": 0.8741561770439148,
+      "learning_rate": 7.518137622582189e-08,
+      "loss": 0.8582,
+      "step": 312
+    },
+    {
+      "epoch": 26.08888888888889,
+      "grad_norm": 0.7642889022827148,
+      "learning_rate": 6.70964677290617e-08,
+      "loss": 0.767,
+      "step": 313
+    },
+    {
+      "epoch": 26.177777777777777,
+      "grad_norm": 0.5676147937774658,
+      "learning_rate": 5.946546135113862e-08,
+      "loss": 0.8953,
+      "step": 314
+    },
+    {
+      "epoch": 26.266666666666666,
+      "grad_norm": 0.6517917513847351,
+      "learning_rate": 5.2289780794192726e-08,
+      "loss": 0.7334,
+      "step": 315
+    },
+    {
+      "epoch": 26.355555555555554,
+      "grad_norm": 0.8068559169769287,
+      "learning_rate": 4.557076481110367e-08,
+      "loss": 0.9373,
+      "step": 316
+    },
+    {
+      "epoch": 26.444444444444443,
+      "grad_norm": 0.5517790913581848,
+      "learning_rate": 3.930966695572136e-08,
+      "loss": 0.884,
+      "step": 317
+    },
+    {
+      "epoch": 26.533333333333335,
+      "grad_norm": 0.6840013861656189,
+      "learning_rate": 3.3507655348995194e-08,
+      "loss": 0.7411,
+      "step": 318
+    },
+    {
+      "epoch": 26.622222222222224,
+      "grad_norm": 1.3431508541107178,
+      "learning_rate": 2.8165812461038166e-08,
+      "loss": 0.7748,
+      "step": 319
+    },
+    {
+      "epoch": 26.711111111111112,
+      "grad_norm": 0.7526693940162659,
+      "learning_rate": 2.3285134909173113e-08,
+      "loss": 0.8678,
+      "step": 320
+    },
+    {
+      "epoch": 26.8,
+      "grad_norm": 0.7261110544204712,
+      "learning_rate": 1.886653327199617e-08,
+      "loss": 0.8908,
+      "step": 321
+    },
+    {
+      "epoch": 26.88888888888889,
+      "grad_norm": 0.6295614242553711,
+      "learning_rate": 1.4910831919490997e-08,
+      "loss": 0.8878,
+      "step": 322
+    },
+    {
+      "epoch": 26.977777777777778,
+      "grad_norm": 0.8621529936790466,
+      "learning_rate": 1.1418768859227935e-08,
+      "loss": 0.895,
+      "step": 323
+    },
+    {
+      "epoch": 27.0,
+      "grad_norm": 0.7991691827774048,
+      "learning_rate": 8.390995598676067e-09,
+      "loss": 0.802,
+      "step": 324
+    },
+    {
+      "epoch": 27.08888888888889,
+      "grad_norm": 0.551089882850647,
+      "learning_rate": 5.828077023651846e-09,
+      "loss": 0.6027,
+      "step": 325
+    },
+    {
+      "epoch": 27.177777777777777,
+      "grad_norm": 0.6393262147903442,
+      "learning_rate": 3.730491292930072e-09,
+      "loss": 0.7449,
+      "step": 326
+    },
+    {
+      "epoch": 27.266666666666666,
+      "grad_norm": 0.7486969232559204,
+      "learning_rate": 2.0986297490338536e-09,
+      "loss": 0.9378,
+      "step": 327
+    },
+    {
+      "epoch": 27.355555555555554,
+      "grad_norm": 0.5878354907035828,
+      "learning_rate": 9.32796845223294e-10,
+      "loss": 0.8487,
+      "step": 328
+    },
+    {
+      "epoch": 27.444444444444443,
+      "grad_norm": 0.7258017659187317,
+      "learning_rate": 2.3321008869481296e-10,
+      "loss": 0.9618,
+      "step": 329
+    },
+    {
+      "epoch": 27.533333333333335,
+      "grad_norm": 0.6953983902931213,
+      "learning_rate": 0.0,
+      "loss": 1.0057,
+      "step": 330
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 330,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1131745240245862e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-330/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74c6e9337569ab897f68ed8f72668ff4adcd96380dade86a6035389284287720
+size 5624

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 27.533333333333335,
+    "total_flos": 1.1131745240245862e+17,
+    "train_loss": 0.9375696651863329,
+    "train_runtime": 851.6955,
+    "train_samples_per_second": 6.34,
+    "train_steps_per_second": 0.387
+}

trainer_log.jsonl

@@ -0,0 +1,331 @@
+{"current_steps": 1, "total_steps": 330, "loss": 0.94, "lr": 5.0000000000000004e-08, "epoch": 0.08888888888888889, "percentage": 0.3, "elapsed_time": "0:00:03", "remaining_time": "0:18:38"}
+{"current_steps": 2, "total_steps": 330, "loss": 1.0076, "lr": 1.0000000000000001e-07, "epoch": 0.17777777777777778, "percentage": 0.61, "elapsed_time": "0:00:05", "remaining_time": "0:15:36"}
+{"current_steps": 3, "total_steps": 330, "loss": 0.9695, "lr": 1.5000000000000002e-07, "epoch": 0.26666666666666666, "percentage": 0.91, "elapsed_time": "0:00:08", "remaining_time": "0:14:32"}
+{"current_steps": 4, "total_steps": 330, "loss": 0.8687, "lr": 2.0000000000000002e-07, "epoch": 0.35555555555555557, "percentage": 1.21, "elapsed_time": "0:00:10", "remaining_time": "0:13:45"}
+{"current_steps": 5, "total_steps": 330, "loss": 1.099, "lr": 2.5000000000000004e-07, "epoch": 0.4444444444444444, "percentage": 1.52, "elapsed_time": "0:00:12", "remaining_time": "0:13:08"}
+{"current_steps": 6, "total_steps": 330, "loss": 1.2947, "lr": 3.0000000000000004e-07, "epoch": 0.5333333333333333, "percentage": 1.82, "elapsed_time": "0:00:14", "remaining_time": "0:12:40"}
+{"current_steps": 7, "total_steps": 330, "loss": 0.9469, "lr": 3.5000000000000004e-07, "epoch": 0.6222222222222222, "percentage": 2.12, "elapsed_time": "0:00:16", "remaining_time": "0:12:26"}
+{"current_steps": 8, "total_steps": 330, "loss": 1.032, "lr": 4.0000000000000003e-07, "epoch": 0.7111111111111111, "percentage": 2.42, "elapsed_time": "0:00:18", "remaining_time": "0:12:26"}
+{"current_steps": 9, "total_steps": 330, "loss": 1.0493, "lr": 4.5000000000000003e-07, "epoch": 0.8, "percentage": 2.73, "elapsed_time": "0:00:21", "remaining_time": "0:12:31"}
+{"current_steps": 10, "total_steps": 330, "loss": 1.051, "lr": 5.000000000000001e-07, "epoch": 0.8888888888888888, "percentage": 3.03, "elapsed_time": "0:00:24", "remaining_time": "0:12:49"}
+{"current_steps": 11, "total_steps": 330, "loss": 1.0976, "lr": 5.5e-07, "epoch": 0.9777777777777777, "percentage": 3.33, "elapsed_time": "0:00:26", "remaining_time": "0:12:47"}
+{"current_steps": 12, "total_steps": 330, "loss": 0.9379, "lr": 6.000000000000001e-07, "epoch": 1.0, "percentage": 3.64, "elapsed_time": "0:00:26", "remaining_time": "0:11:55"}
+{"current_steps": 13, "total_steps": 330, "loss": 0.9381, "lr": 6.5e-07, "epoch": 1.0888888888888888, "percentage": 3.94, "elapsed_time": "0:00:29", "remaining_time": "0:11:54"}
+{"current_steps": 14, "total_steps": 330, "loss": 0.9569, "lr": 7.000000000000001e-07, "epoch": 1.1777777777777778, "percentage": 4.24, "elapsed_time": "0:00:31", "remaining_time": "0:11:52"}
+{"current_steps": 15, "total_steps": 330, "loss": 1.0227, "lr": 7.5e-07, "epoch": 1.2666666666666666, "percentage": 4.55, "elapsed_time": "0:00:34", "remaining_time": "0:11:54"}
+{"current_steps": 16, "total_steps": 330, "loss": 1.0438, "lr": 8.000000000000001e-07, "epoch": 1.3555555555555556, "percentage": 4.85, "elapsed_time": "0:00:36", "remaining_time": "0:11:58"}
+{"current_steps": 17, "total_steps": 330, "loss": 1.1062, "lr": 8.500000000000001e-07, "epoch": 1.4444444444444444, "percentage": 5.15, "elapsed_time": "0:00:38", "remaining_time": "0:11:56"}
+{"current_steps": 18, "total_steps": 330, "loss": 0.8878, "lr": 9.000000000000001e-07, "epoch": 1.5333333333333332, "percentage": 5.45, "elapsed_time": "0:00:41", "remaining_time": "0:11:52"}
+{"current_steps": 19, "total_steps": 330, "loss": 1.0275, "lr": 9.500000000000001e-07, "epoch": 1.6222222222222222, "percentage": 5.76, "elapsed_time": "0:00:43", "remaining_time": "0:11:47"}
+{"current_steps": 20, "total_steps": 330, "loss": 0.9946, "lr": 1.0000000000000002e-06, "epoch": 1.7111111111111112, "percentage": 6.06, "elapsed_time": "0:00:45", "remaining_time": "0:11:42"}
+{"current_steps": 21, "total_steps": 330, "loss": 1.0708, "lr": 1.0500000000000001e-06, "epoch": 1.8, "percentage": 6.36, "elapsed_time": "0:00:47", "remaining_time": "0:11:42"}
+{"current_steps": 22, "total_steps": 330, "loss": 1.101, "lr": 1.1e-06, "epoch": 1.8888888888888888, "percentage": 6.67, "elapsed_time": "0:00:50", "remaining_time": "0:11:47"}
+{"current_steps": 23, "total_steps": 330, "loss": 0.9893, "lr": 1.1500000000000002e-06, "epoch": 1.9777777777777779, "percentage": 6.97, "elapsed_time": "0:00:52", "remaining_time": "0:11:44"}
+{"current_steps": 24, "total_steps": 330, "loss": 1.1786, "lr": 1.2000000000000002e-06, "epoch": 2.0, "percentage": 7.27, "elapsed_time": "0:00:53", "remaining_time": "0:11:22"}
+{"current_steps": 25, "total_steps": 330, "loss": 1.0819, "lr": 1.25e-06, "epoch": 2.088888888888889, "percentage": 7.58, "elapsed_time": "0:00:55", "remaining_time": "0:11:16"}
+{"current_steps": 26, "total_steps": 330, "loss": 1.0393, "lr": 1.3e-06, "epoch": 2.1777777777777776, "percentage": 7.88, "elapsed_time": "0:00:57", "remaining_time": "0:11:17"}
+{"current_steps": 27, "total_steps": 330, "loss": 1.1029, "lr": 1.3500000000000002e-06, "epoch": 2.2666666666666666, "percentage": 8.18, "elapsed_time": "0:01:00", "remaining_time": "0:11:18"}
+{"current_steps": 28, "total_steps": 330, "loss": 1.0597, "lr": 1.4000000000000001e-06, "epoch": 2.3555555555555556, "percentage": 8.48, "elapsed_time": "0:01:02", "remaining_time": "0:11:17"}
+{"current_steps": 29, "total_steps": 330, "loss": 0.9494, "lr": 1.45e-06, "epoch": 2.4444444444444446, "percentage": 8.79, "elapsed_time": "0:01:05", "remaining_time": "0:11:16"}
+{"current_steps": 30, "total_steps": 330, "loss": 0.944, "lr": 1.5e-06, "epoch": 2.533333333333333, "percentage": 9.09, "elapsed_time": "0:01:07", "remaining_time": "0:11:13"}
+{"current_steps": 31, "total_steps": 330, "loss": 1.023, "lr": 1.5500000000000002e-06, "epoch": 2.6222222222222222, "percentage": 9.39, "elapsed_time": "0:01:09", "remaining_time": "0:11:12"}
+{"current_steps": 32, "total_steps": 330, "loss": 0.9772, "lr": 1.6000000000000001e-06, "epoch": 2.7111111111111112, "percentage": 9.7, "elapsed_time": "0:01:12", "remaining_time": "0:11:14"}
+{"current_steps": 33, "total_steps": 330, "loss": 1.0928, "lr": 1.6500000000000003e-06, "epoch": 2.8, "percentage": 10.0, "elapsed_time": "0:01:15", "remaining_time": "0:11:16"}
+{"current_steps": 34, "total_steps": 330, "loss": 0.9012, "lr": 1.7000000000000002e-06, "epoch": 2.888888888888889, "percentage": 10.3, "elapsed_time": "0:01:17", "remaining_time": "0:11:14"}
+{"current_steps": 35, "total_steps": 330, "loss": 1.0461, "lr": 1.75e-06, "epoch": 2.977777777777778, "percentage": 10.61, "elapsed_time": "0:01:19", "remaining_time": "0:11:10"}
+{"current_steps": 36, "total_steps": 330, "loss": 0.9155, "lr": 1.8000000000000001e-06, "epoch": 3.0, "percentage": 10.91, "elapsed_time": "0:01:20", "remaining_time": "0:10:54"}
+{"current_steps": 37, "total_steps": 330, "loss": 1.0048, "lr": 1.85e-06, "epoch": 3.088888888888889, "percentage": 11.21, "elapsed_time": "0:01:22", "remaining_time": "0:10:55"}
+{"current_steps": 38, "total_steps": 330, "loss": 0.9085, "lr": 1.9000000000000002e-06, "epoch": 3.1777777777777776, "percentage": 11.52, "elapsed_time": "0:01:24", "remaining_time": "0:10:52"}
+{"current_steps": 39, "total_steps": 330, "loss": 0.8711, "lr": 1.9500000000000004e-06, "epoch": 3.2666666666666666, "percentage": 11.82, "elapsed_time": "0:01:27", "remaining_time": "0:10:50"}
+{"current_steps": 40, "total_steps": 330, "loss": 1.0397, "lr": 2.0000000000000003e-06, "epoch": 3.3555555555555556, "percentage": 12.12, "elapsed_time": "0:01:29", "remaining_time": "0:10:48"}
+{"current_steps": 41, "total_steps": 330, "loss": 1.0436, "lr": 2.05e-06, "epoch": 3.4444444444444446, "percentage": 12.42, "elapsed_time": "0:01:31", "remaining_time": "0:10:43"}
+{"current_steps": 42, "total_steps": 330, "loss": 1.1212, "lr": 2.1000000000000002e-06, "epoch": 3.533333333333333, "percentage": 12.73, "elapsed_time": "0:01:33", "remaining_time": "0:10:41"}
+{"current_steps": 43, "total_steps": 330, "loss": 1.0738, "lr": 2.15e-06, "epoch": 3.6222222222222222, "percentage": 13.03, "elapsed_time": "0:01:35", "remaining_time": "0:10:39"}
+{"current_steps": 44, "total_steps": 330, "loss": 0.9962, "lr": 2.2e-06, "epoch": 3.7111111111111112, "percentage": 13.33, "elapsed_time": "0:01:39", "remaining_time": "0:10:45"}
+{"current_steps": 45, "total_steps": 330, "loss": 1.121, "lr": 2.25e-06, "epoch": 3.8, "percentage": 13.64, "elapsed_time": "0:01:41", "remaining_time": "0:10:43"}
+{"current_steps": 46, "total_steps": 330, "loss": 1.0232, "lr": 2.3000000000000004e-06, "epoch": 3.888888888888889, "percentage": 13.94, "elapsed_time": "0:01:43", "remaining_time": "0:10:39"}
+{"current_steps": 47, "total_steps": 330, "loss": 1.0396, "lr": 2.35e-06, "epoch": 3.977777777777778, "percentage": 14.24, "elapsed_time": "0:01:46", "remaining_time": "0:10:40"}
+{"current_steps": 48, "total_steps": 330, "loss": 1.0178, "lr": 2.4000000000000003e-06, "epoch": 4.0, "percentage": 14.55, "elapsed_time": "0:01:46", "remaining_time": "0:10:26"}
+{"current_steps": 49, "total_steps": 330, "loss": 1.0127, "lr": 2.4500000000000003e-06, "epoch": 4.088888888888889, "percentage": 14.85, "elapsed_time": "0:01:49", "remaining_time": "0:10:26"}
+{"current_steps": 50, "total_steps": 330, "loss": 1.0034, "lr": 2.5e-06, "epoch": 4.177777777777778, "percentage": 15.15, "elapsed_time": "0:01:51", "remaining_time": "0:10:22"}
+{"current_steps": 51, "total_steps": 330, "loss": 1.0821, "lr": 2.55e-06, "epoch": 4.266666666666667, "percentage": 15.45, "elapsed_time": "0:01:54", "remaining_time": "0:10:24"}
+{"current_steps": 52, "total_steps": 330, "loss": 0.8747, "lr": 2.6e-06, "epoch": 4.355555555555555, "percentage": 15.76, "elapsed_time": "0:01:56", "remaining_time": "0:10:23"}
+{"current_steps": 53, "total_steps": 330, "loss": 1.0981, "lr": 2.6500000000000005e-06, "epoch": 4.444444444444445, "percentage": 16.06, "elapsed_time": "0:01:59", "remaining_time": "0:10:22"}
+{"current_steps": 54, "total_steps": 330, "loss": 0.8774, "lr": 2.7000000000000004e-06, "epoch": 4.533333333333333, "percentage": 16.36, "elapsed_time": "0:02:01", "remaining_time": "0:10:19"}
+{"current_steps": 55, "total_steps": 330, "loss": 1.0841, "lr": 2.7500000000000004e-06, "epoch": 4.622222222222222, "percentage": 16.67, "elapsed_time": "0:02:03", "remaining_time": "0:10:17"}
+{"current_steps": 56, "total_steps": 330, "loss": 1.0752, "lr": 2.8000000000000003e-06, "epoch": 4.711111111111111, "percentage": 16.97, "elapsed_time": "0:02:05", "remaining_time": "0:10:14"}
+{"current_steps": 57, "total_steps": 330, "loss": 1.087, "lr": 2.85e-06, "epoch": 4.8, "percentage": 17.27, "elapsed_time": "0:02:07", "remaining_time": "0:10:12"}
+{"current_steps": 58, "total_steps": 330, "loss": 1.0578, "lr": 2.9e-06, "epoch": 4.888888888888889, "percentage": 17.58, "elapsed_time": "0:02:10", "remaining_time": "0:10:13"}
+{"current_steps": 59, "total_steps": 330, "loss": 0.9329, "lr": 2.95e-06, "epoch": 4.977777777777778, "percentage": 17.88, "elapsed_time": "0:02:13", "remaining_time": "0:10:11"}
+{"current_steps": 60, "total_steps": 330, "loss": 0.9952, "lr": 3e-06, "epoch": 5.0, "percentage": 18.18, "elapsed_time": "0:02:13", "remaining_time": "0:10:01"}
+{"current_steps": 61, "total_steps": 330, "loss": 1.2386, "lr": 3.05e-06, "epoch": 5.088888888888889, "percentage": 18.48, "elapsed_time": "0:02:15", "remaining_time": "0:09:58"}
+{"current_steps": 62, "total_steps": 330, "loss": 0.9, "lr": 3.1000000000000004e-06, "epoch": 5.177777777777778, "percentage": 18.79, "elapsed_time": "0:02:18", "remaining_time": "0:09:56"}
+{"current_steps": 63, "total_steps": 330, "loss": 1.0832, "lr": 3.1500000000000003e-06, "epoch": 5.266666666666667, "percentage": 19.09, "elapsed_time": "0:02:20", "remaining_time": "0:09:54"}
+{"current_steps": 64, "total_steps": 330, "loss": 0.9822, "lr": 3.2000000000000003e-06, "epoch": 5.355555555555555, "percentage": 19.39, "elapsed_time": "0:02:22", "remaining_time": "0:09:52"}
+{"current_steps": 65, "total_steps": 330, "loss": 0.9968, "lr": 3.2500000000000002e-06, "epoch": 5.444444444444445, "percentage": 19.7, "elapsed_time": "0:02:25", "remaining_time": "0:09:51"}
+{"current_steps": 66, "total_steps": 330, "loss": 0.9124, "lr": 3.3000000000000006e-06, "epoch": 5.533333333333333, "percentage": 20.0, "elapsed_time": "0:02:28", "remaining_time": "0:09:53"}
+{"current_steps": 67, "total_steps": 330, "loss": 1.1134, "lr": 3.3500000000000005e-06, "epoch": 5.622222222222222, "percentage": 20.3, "elapsed_time": "0:02:30", "remaining_time": "0:09:51"}
+{"current_steps": 68, "total_steps": 330, "loss": 0.879, "lr": 3.4000000000000005e-06, "epoch": 5.711111111111111, "percentage": 20.61, "elapsed_time": "0:02:32", "remaining_time": "0:09:49"}
+{"current_steps": 69, "total_steps": 330, "loss": 1.103, "lr": 3.45e-06, "epoch": 5.8, "percentage": 20.91, "elapsed_time": "0:02:35", "remaining_time": "0:09:48"}
+{"current_steps": 70, "total_steps": 330, "loss": 1.0124, "lr": 3.5e-06, "epoch": 5.888888888888889, "percentage": 21.21, "elapsed_time": "0:02:37", "remaining_time": "0:09:46"}
+{"current_steps": 71, "total_steps": 330, "loss": 1.001, "lr": 3.5500000000000003e-06, "epoch": 5.977777777777778, "percentage": 21.52, "elapsed_time": "0:02:40", "remaining_time": "0:09:46"}
+{"current_steps": 72, "total_steps": 330, "loss": 1.0199, "lr": 3.6000000000000003e-06, "epoch": 6.0, "percentage": 21.82, "elapsed_time": "0:02:41", "remaining_time": "0:09:37"}
+{"current_steps": 73, "total_steps": 330, "loss": 1.1584, "lr": 3.65e-06, "epoch": 6.088888888888889, "percentage": 22.12, "elapsed_time": "0:02:43", "remaining_time": "0:09:35"}
+{"current_steps": 74, "total_steps": 330, "loss": 1.0419, "lr": 3.7e-06, "epoch": 6.177777777777778, "percentage": 22.42, "elapsed_time": "0:02:45", "remaining_time": "0:09:33"}
+{"current_steps": 75, "total_steps": 330, "loss": 0.856, "lr": 3.7500000000000005e-06, "epoch": 6.266666666666667, "percentage": 22.73, "elapsed_time": "0:02:48", "remaining_time": "0:09:33"}
+{"current_steps": 76, "total_steps": 330, "loss": 0.9925, "lr": 3.8000000000000005e-06, "epoch": 6.355555555555555, "percentage": 23.03, "elapsed_time": "0:02:50", "remaining_time": "0:09:30"}
+{"current_steps": 77, "total_steps": 330, "loss": 1.0069, "lr": 3.85e-06, "epoch": 6.444444444444445, "percentage": 23.33, "elapsed_time": "0:02:53", "remaining_time": "0:09:29"}
+{"current_steps": 78, "total_steps": 330, "loss": 0.953, "lr": 3.900000000000001e-06, "epoch": 6.533333333333333, "percentage": 23.64, "elapsed_time": "0:02:55", "remaining_time": "0:09:26"}
+{"current_steps": 79, "total_steps": 330, "loss": 1.1169, "lr": 3.95e-06, "epoch": 6.622222222222222, "percentage": 23.94, "elapsed_time": "0:02:57", "remaining_time": "0:09:24"}
+{"current_steps": 80, "total_steps": 330, "loss": 0.9554, "lr": 4.000000000000001e-06, "epoch": 6.711111111111111, "percentage": 24.24, "elapsed_time": "0:02:59", "remaining_time": "0:09:21"}
+{"current_steps": 81, "total_steps": 330, "loss": 1.0723, "lr": 4.05e-06, "epoch": 6.8, "percentage": 24.55, "elapsed_time": "0:03:02", "remaining_time": "0:09:21"}
+{"current_steps": 82, "total_steps": 330, "loss": 1.0264, "lr": 4.1e-06, "epoch": 6.888888888888889, "percentage": 24.85, "elapsed_time": "0:03:04", "remaining_time": "0:09:19"}
+{"current_steps": 83, "total_steps": 330, "loss": 0.9445, "lr": 4.15e-06, "epoch": 6.977777777777778, "percentage": 25.15, "elapsed_time": "0:03:07", "remaining_time": "0:09:18"}
+{"current_steps": 84, "total_steps": 330, "loss": 1.1842, "lr": 4.2000000000000004e-06, "epoch": 7.0, "percentage": 25.45, "elapsed_time": "0:03:08", "remaining_time": "0:09:11"}
+{"current_steps": 85, "total_steps": 330, "loss": 1.0707, "lr": 4.25e-06, "epoch": 7.088888888888889, "percentage": 25.76, "elapsed_time": "0:03:10", "remaining_time": "0:09:09"}
+{"current_steps": 86, "total_steps": 330, "loss": 1.116, "lr": 4.3e-06, "epoch": 7.177777777777778, "percentage": 26.06, "elapsed_time": "0:03:13", "remaining_time": "0:09:07"}
+{"current_steps": 87, "total_steps": 330, "loss": 0.8747, "lr": 4.350000000000001e-06, "epoch": 7.266666666666667, "percentage": 26.36, "elapsed_time": "0:03:15", "remaining_time": "0:09:06"}
+{"current_steps": 88, "total_steps": 330, "loss": 0.9918, "lr": 4.4e-06, "epoch": 7.355555555555555, "percentage": 26.67, "elapsed_time": "0:03:18", "remaining_time": "0:09:05"}
+{"current_steps": 89, "total_steps": 330, "loss": 1.1398, "lr": 4.450000000000001e-06, "epoch": 7.444444444444445, "percentage": 26.97, "elapsed_time": "0:03:21", "remaining_time": "0:09:04"}
+{"current_steps": 90, "total_steps": 330, "loss": 0.9042, "lr": 4.5e-06, "epoch": 7.533333333333333, "percentage": 27.27, "elapsed_time": "0:03:23", "remaining_time": "0:09:03"}
+{"current_steps": 91, "total_steps": 330, "loss": 0.9608, "lr": 4.5500000000000005e-06, "epoch": 7.622222222222222, "percentage": 27.58, "elapsed_time": "0:03:26", "remaining_time": "0:09:02"}
+{"current_steps": 92, "total_steps": 330, "loss": 0.9085, "lr": 4.600000000000001e-06, "epoch": 7.711111111111111, "percentage": 27.88, "elapsed_time": "0:03:28", "remaining_time": "0:09:00"}
+{"current_steps": 93, "total_steps": 330, "loss": 1.0053, "lr": 4.65e-06, "epoch": 7.8, "percentage": 28.18, "elapsed_time": "0:03:31", "remaining_time": "0:08:58"}
+{"current_steps": 94, "total_steps": 330, "loss": 1.1269, "lr": 4.7e-06, "epoch": 7.888888888888889, "percentage": 28.48, "elapsed_time": "0:03:34", "remaining_time": "0:08:57"}
+{"current_steps": 95, "total_steps": 330, "loss": 1.1115, "lr": 4.75e-06, "epoch": 7.977777777777778, "percentage": 28.79, "elapsed_time": "0:03:36", "remaining_time": "0:08:54"}
+{"current_steps": 96, "total_steps": 330, "loss": 0.8602, "lr": 4.800000000000001e-06, "epoch": 8.0, "percentage": 29.09, "elapsed_time": "0:03:36", "remaining_time": "0:08:47"}
+{"current_steps": 97, "total_steps": 330, "loss": 1.0071, "lr": 4.85e-06, "epoch": 8.088888888888889, "percentage": 29.39, "elapsed_time": "0:03:39", "remaining_time": "0:08:47"}
+{"current_steps": 98, "total_steps": 330, "loss": 0.847, "lr": 4.9000000000000005e-06, "epoch": 8.177777777777777, "percentage": 29.7, "elapsed_time": "0:03:41", "remaining_time": "0:08:44"}
+{"current_steps": 99, "total_steps": 330, "loss": 0.9321, "lr": 4.95e-06, "epoch": 8.266666666666667, "percentage": 30.0, "elapsed_time": "0:03:44", "remaining_time": "0:08:42"}
+{"current_steps": 100, "total_steps": 330, "loss": 0.9997, "lr": 5e-06, "epoch": 8.355555555555556, "percentage": 30.3, "elapsed_time": "0:03:46", "remaining_time": "0:08:40"}
+{"current_steps": 101, "total_steps": 330, "loss": 0.9206, "lr": 4.9997667899113055e-06, "epoch": 8.444444444444445, "percentage": 30.61, "elapsed_time": "0:03:48", "remaining_time": "0:08:37"}
+{"current_steps": 102, "total_steps": 330, "loss": 1.0383, "lr": 4.999067203154777e-06, "epoch": 8.533333333333333, "percentage": 30.91, "elapsed_time": "0:03:50", "remaining_time": "0:08:36"}
+{"current_steps": 103, "total_steps": 330, "loss": 1.2077, "lr": 4.997901370250966e-06, "epoch": 8.622222222222222, "percentage": 31.21, "elapsed_time": "0:03:53", "remaining_time": "0:08:34"}
+{"current_steps": 104, "total_steps": 330, "loss": 0.9617, "lr": 4.99626950870707e-06, "epoch": 8.71111111111111, "percentage": 31.52, "elapsed_time": "0:03:55", "remaining_time": "0:08:32"}
+{"current_steps": 105, "total_steps": 330, "loss": 0.9182, "lr": 4.994171922976349e-06, "epoch": 8.8, "percentage": 31.82, "elapsed_time": "0:03:58", "remaining_time": "0:08:30"}
+{"current_steps": 106, "total_steps": 330, "loss": 1.1561, "lr": 4.991609004401324e-06, "epoch": 8.88888888888889, "percentage": 32.12, "elapsed_time": "0:04:00", "remaining_time": "0:08:28"}
+{"current_steps": 107, "total_steps": 330, "loss": 1.135, "lr": 4.988581231140772e-06, "epoch": 8.977777777777778, "percentage": 32.42, "elapsed_time": "0:04:03", "remaining_time": "0:08:26"}
+{"current_steps": 108, "total_steps": 330, "loss": 0.7612, "lr": 4.985089168080509e-06, "epoch": 9.0, "percentage": 32.73, "elapsed_time": "0:04:03", "remaining_time": "0:08:20"}
+{"current_steps": 109, "total_steps": 330, "loss": 0.9991, "lr": 4.981133466728004e-06, "epoch": 9.088888888888889, "percentage": 33.03, "elapsed_time": "0:04:05", "remaining_time": "0:08:18"}
+{"current_steps": 110, "total_steps": 330, "loss": 0.9779, "lr": 4.976714865090827e-06, "epoch": 9.177777777777777, "percentage": 33.33, "elapsed_time": "0:04:07", "remaining_time": "0:08:15"}
+{"current_steps": 111, "total_steps": 330, "loss": 0.9449, "lr": 4.971834187538963e-06, "epoch": 9.266666666666667, "percentage": 33.64, "elapsed_time": "0:04:10", "remaining_time": "0:08:13"}
+{"current_steps": 112, "total_steps": 330, "loss": 0.8786, "lr": 4.966492344651006e-06, "epoch": 9.355555555555556, "percentage": 33.94, "elapsed_time": "0:04:12", "remaining_time": "0:08:11"}
+{"current_steps": 113, "total_steps": 330, "loss": 1.0798, "lr": 4.960690333044279e-06, "epoch": 9.444444444444445, "percentage": 34.24, "elapsed_time": "0:04:14", "remaining_time": "0:08:08"}
+{"current_steps": 114, "total_steps": 330, "loss": 1.182, "lr": 4.954429235188897e-06, "epoch": 9.533333333333333, "percentage": 34.55, "elapsed_time": "0:04:16", "remaining_time": "0:08:06"}
+{"current_steps": 115, "total_steps": 330, "loss": 0.9882, "lr": 4.947710219205808e-06, "epoch": 9.622222222222222, "percentage": 34.85, "elapsed_time": "0:04:19", "remaining_time": "0:08:05"}
+{"current_steps": 116, "total_steps": 330, "loss": 0.9649, "lr": 4.940534538648862e-06, "epoch": 9.71111111111111, "percentage": 35.15, "elapsed_time": "0:04:22", "remaining_time": "0:08:04"}
+{"current_steps": 117, "total_steps": 330, "loss": 1.0484, "lr": 4.932903532270939e-06, "epoch": 9.8, "percentage": 35.45, "elapsed_time": "0:04:24", "remaining_time": "0:08:01"}
+{"current_steps": 118, "total_steps": 330, "loss": 0.8972, "lr": 4.924818623774178e-06, "epoch": 9.88888888888889, "percentage": 35.76, "elapsed_time": "0:04:27", "remaining_time": "0:08:00"}
+{"current_steps": 119, "total_steps": 330, "loss": 0.9265, "lr": 4.916281321544362e-06, "epoch": 9.977777777777778, "percentage": 36.06, "elapsed_time": "0:04:29", "remaining_time": "0:07:58"}
+{"current_steps": 120, "total_steps": 330, "loss": 1.1764, "lr": 4.907293218369499e-06, "epoch": 10.0, "percentage": 36.36, "elapsed_time": "0:04:30", "remaining_time": "0:07:53"}
+{"current_steps": 121, "total_steps": 330, "loss": 0.9429, "lr": 4.897855991142658e-06, "epoch": 10.088888888888889, "percentage": 36.67, "elapsed_time": "0:04:32", "remaining_time": "0:07:51"}
+{"current_steps": 122, "total_steps": 330, "loss": 1.0113, "lr": 4.8879714005491205e-06, "epoch": 10.177777777777777, "percentage": 36.97, "elapsed_time": "0:04:34", "remaining_time": "0:07:48"}
+{"current_steps": 123, "total_steps": 330, "loss": 1.0417, "lr": 4.8776412907378845e-06, "epoch": 10.266666666666667, "percentage": 37.27, "elapsed_time": "0:04:37", "remaining_time": "0:07:47"}
+{"current_steps": 124, "total_steps": 330, "loss": 0.9355, "lr": 4.8668675889776095e-06, "epoch": 10.355555555555556, "percentage": 37.58, "elapsed_time": "0:04:40", "remaining_time": "0:07:45"}
+{"current_steps": 125, "total_steps": 330, "loss": 0.829, "lr": 4.855652305297052e-06, "epoch": 10.444444444444445, "percentage": 37.88, "elapsed_time": "0:04:42", "remaining_time": "0:07:43"}
+{"current_steps": 126, "total_steps": 330, "loss": 1.003, "lr": 4.843997532110051e-06, "epoch": 10.533333333333333, "percentage": 38.18, "elapsed_time": "0:04:45", "remaining_time": "0:07:41"}
+{"current_steps": 127, "total_steps": 330, "loss": 1.0789, "lr": 4.83190544382516e-06, "epoch": 10.622222222222222, "percentage": 38.48, "elapsed_time": "0:04:47", "remaining_time": "0:07:39"}
+{"current_steps": 128, "total_steps": 330, "loss": 1.0207, "lr": 4.819378296439962e-06, "epoch": 10.71111111111111, "percentage": 38.79, "elapsed_time": "0:04:50", "remaining_time": "0:07:37"}
+{"current_steps": 129, "total_steps": 330, "loss": 0.8893, "lr": 4.80641842712018e-06, "epoch": 10.8, "percentage": 39.09, "elapsed_time": "0:04:52", "remaining_time": "0:07:36"}
+{"current_steps": 130, "total_steps": 330, "loss": 1.0629, "lr": 4.793028253763633e-06, "epoch": 10.88888888888889, "percentage": 39.39, "elapsed_time": "0:04:56", "remaining_time": "0:07:35"}
+{"current_steps": 131, "total_steps": 330, "loss": 0.986, "lr": 4.7792102745491345e-06, "epoch": 10.977777777777778, "percentage": 39.7, "elapsed_time": "0:04:59", "remaining_time": "0:07:35"}
+{"current_steps": 132, "total_steps": 330, "loss": 1.2309, "lr": 4.764967067470409e-06, "epoch": 11.0, "percentage": 40.0, "elapsed_time": "0:05:00", "remaining_time": "0:07:30"}
+{"current_steps": 133, "total_steps": 330, "loss": 1.0157, "lr": 4.750301289855128e-06, "epoch": 11.088888888888889, "percentage": 40.3, "elapsed_time": "0:05:03", "remaining_time": "0:07:29"}
+{"current_steps": 134, "total_steps": 330, "loss": 1.0521, "lr": 4.735215677869129e-06, "epoch": 11.177777777777777, "percentage": 40.61, "elapsed_time": "0:05:06", "remaining_time": "0:07:28"}
+{"current_steps": 135, "total_steps": 330, "loss": 0.861, "lr": 4.7197130460059385e-06, "epoch": 11.266666666666667, "percentage": 40.91, "elapsed_time": "0:05:09", "remaining_time": "0:07:26"}
+{"current_steps": 136, "total_steps": 330, "loss": 1.0256, "lr": 4.7037962865616795e-06, "epoch": 11.355555555555556, "percentage": 41.21, "elapsed_time": "0:05:12", "remaining_time": "0:07:25"}
+{"current_steps": 137, "total_steps": 330, "loss": 1.0302, "lr": 4.687468369095457e-06, "epoch": 11.444444444444445, "percentage": 41.52, "elapsed_time": "0:05:15", "remaining_time": "0:07:24"}
+{"current_steps": 138, "total_steps": 330, "loss": 0.9272, "lr": 4.6707323398753346e-06, "epoch": 11.533333333333333, "percentage": 41.82, "elapsed_time": "0:05:18", "remaining_time": "0:07:23"}
+{"current_steps": 139, "total_steps": 330, "loss": 0.9849, "lr": 4.6535913213100005e-06, "epoch": 11.622222222222222, "percentage": 42.12, "elapsed_time": "0:05:22", "remaining_time": "0:07:23"}
+{"current_steps": 140, "total_steps": 330, "loss": 0.7549, "lr": 4.636048511366222e-06, "epoch": 11.71111111111111, "percentage": 42.42, "elapsed_time": "0:05:26", "remaining_time": "0:07:22"}
+{"current_steps": 141, "total_steps": 330, "loss": 0.9387, "lr": 4.618107182972209e-06, "epoch": 11.8, "percentage": 42.73, "elapsed_time": "0:05:29", "remaining_time": "0:07:22"}
+{"current_steps": 142, "total_steps": 330, "loss": 1.1931, "lr": 4.599770683406992e-06, "epoch": 11.88888888888889, "percentage": 43.03, "elapsed_time": "0:05:32", "remaining_time": "0:07:20"}
+{"current_steps": 143, "total_steps": 330, "loss": 0.8533, "lr": 4.58104243367592e-06, "epoch": 11.977777777777778, "percentage": 43.33, "elapsed_time": "0:05:36", "remaining_time": "0:07:19"}
+{"current_steps": 144, "total_steps": 330, "loss": 1.2318, "lr": 4.561925927872421e-06, "epoch": 12.0, "percentage": 43.64, "elapsed_time": "0:05:36", "remaining_time": "0:07:14"}
+{"current_steps": 145, "total_steps": 330, "loss": 0.877, "lr": 4.542424732526105e-06, "epoch": 12.088888888888889, "percentage": 43.94, "elapsed_time": "0:05:39", "remaining_time": "0:07:13"}
+{"current_steps": 146, "total_steps": 330, "loss": 0.9198, "lr": 4.522542485937369e-06, "epoch": 12.177777777777777, "percentage": 44.24, "elapsed_time": "0:05:43", "remaining_time": "0:07:12"}
+{"current_steps": 147, "total_steps": 330, "loss": 0.9225, "lr": 4.5022828974986044e-06, "epoch": 12.266666666666667, "percentage": 44.55, "elapsed_time": "0:05:46", "remaining_time": "0:07:11"}
+{"current_steps": 148, "total_steps": 330, "loss": 1.0818, "lr": 4.481649747002146e-06, "epoch": 12.355555555555556, "percentage": 44.85, "elapsed_time": "0:05:50", "remaining_time": "0:07:11"}
+{"current_steps": 149, "total_steps": 330, "loss": 0.9635, "lr": 4.460646883935079e-06, "epoch": 12.444444444444445, "percentage": 45.15, "elapsed_time": "0:05:53", "remaining_time": "0:07:09"}
+{"current_steps": 150, "total_steps": 330, "loss": 0.8971, "lr": 4.43927822676105e-06, "epoch": 12.533333333333333, "percentage": 45.45, "elapsed_time": "0:05:57", "remaining_time": "0:07:08"}
+{"current_steps": 151, "total_steps": 330, "loss": 0.9474, "lr": 4.417547762189207e-06, "epoch": 12.622222222222222, "percentage": 45.76, "elapsed_time": "0:05:59", "remaining_time": "0:07:06"}
+{"current_steps": 152, "total_steps": 330, "loss": 1.0403, "lr": 4.395459544430407e-06, "epoch": 12.71111111111111, "percentage": 46.06, "elapsed_time": "0:06:02", "remaining_time": "0:07:04"}
+{"current_steps": 153, "total_steps": 330, "loss": 1.0076, "lr": 4.373017694440828e-06, "epoch": 12.8, "percentage": 46.36, "elapsed_time": "0:06:05", "remaining_time": "0:07:02"}
+{"current_steps": 154, "total_steps": 330, "loss": 0.9405, "lr": 4.35022639915313e-06, "epoch": 12.88888888888889, "percentage": 46.67, "elapsed_time": "0:06:09", "remaining_time": "0:07:02"}
+{"current_steps": 155, "total_steps": 330, "loss": 0.9689, "lr": 4.32708991069531e-06, "epoch": 12.977777777777778, "percentage": 46.97, "elapsed_time": "0:06:13", "remaining_time": "0:07:01"}
+{"current_steps": 156, "total_steps": 330, "loss": 0.8877, "lr": 4.30361254559739e-06, "epoch": 13.0, "percentage": 47.27, "elapsed_time": "0:06:14", "remaining_time": "0:06:57"}
+{"current_steps": 157, "total_steps": 330, "loss": 0.9697, "lr": 4.279798683986084e-06, "epoch": 13.088888888888889, "percentage": 47.58, "elapsed_time": "0:06:17", "remaining_time": "0:06:56"}
+{"current_steps": 158, "total_steps": 330, "loss": 0.8949, "lr": 4.255652768767619e-06, "epoch": 13.177777777777777, "percentage": 47.88, "elapsed_time": "0:06:20", "remaining_time": "0:06:54"}
+{"current_steps": 159, "total_steps": 330, "loss": 0.941, "lr": 4.2311793047988145e-06, "epoch": 13.266666666666667, "percentage": 48.18, "elapsed_time": "0:06:23", "remaining_time": "0:06:52"}
+{"current_steps": 160, "total_steps": 330, "loss": 0.792, "lr": 4.206382858046636e-06, "epoch": 13.355555555555556, "percentage": 48.48, "elapsed_time": "0:06:26", "remaining_time": "0:06:50"}
+{"current_steps": 161, "total_steps": 330, "loss": 0.9622, "lr": 4.181268054736319e-06, "epoch": 13.444444444444445, "percentage": 48.79, "elapsed_time": "0:06:29", "remaining_time": "0:06:49"}
+{"current_steps": 162, "total_steps": 330, "loss": 0.8678, "lr": 4.15583958048827e-06, "epoch": 13.533333333333333, "percentage": 49.09, "elapsed_time": "0:06:33", "remaining_time": "0:06:47"}
+{"current_steps": 163, "total_steps": 330, "loss": 0.8901, "lr": 4.130102179443877e-06, "epoch": 13.622222222222222, "percentage": 49.39, "elapsed_time": "0:06:36", "remaining_time": "0:06:46"}
+{"current_steps": 164, "total_steps": 330, "loss": 0.9957, "lr": 4.104060653380403e-06, "epoch": 13.71111111111111, "percentage": 49.7, "elapsed_time": "0:06:39", "remaining_time": "0:06:43"}
+{"current_steps": 165, "total_steps": 330, "loss": 1.0817, "lr": 4.077719860815132e-06, "epoch": 13.8, "percentage": 50.0, "elapsed_time": "0:06:43", "remaining_time": "0:06:43"}
+{"current_steps": 166, "total_steps": 330, "loss": 1.1538, "lr": 4.051084716098921e-06, "epoch": 13.88888888888889, "percentage": 50.3, "elapsed_time": "0:06:46", "remaining_time": "0:06:41"}
+{"current_steps": 167, "total_steps": 330, "loss": 0.9047, "lr": 4.024160188499337e-06, "epoch": 13.977777777777778, "percentage": 50.61, "elapsed_time": "0:06:49", "remaining_time": "0:06:40"}
+{"current_steps": 168, "total_steps": 330, "loss": 0.9499, "lr": 3.996951301273556e-06, "epoch": 14.0, "percentage": 50.91, "elapsed_time": "0:06:50", "remaining_time": "0:06:35"}
+{"current_steps": 169, "total_steps": 330, "loss": 0.9101, "lr": 3.969463130731183e-06, "epoch": 14.088888888888889, "percentage": 51.21, "elapsed_time": "0:06:53", "remaining_time": "0:06:33"}
+{"current_steps": 170, "total_steps": 330, "loss": 1.0762, "lr": 3.941700805287169e-06, "epoch": 14.177777777777777, "percentage": 51.52, "elapsed_time": "0:06:56", "remaining_time": "0:06:32"}
+{"current_steps": 171, "total_steps": 330, "loss": 1.0859, "lr": 3.913669504505015e-06, "epoch": 14.266666666666667, "percentage": 51.82, "elapsed_time": "0:06:59", "remaining_time": "0:06:30"}
+{"current_steps": 172, "total_steps": 330, "loss": 0.8807, "lr": 3.8853744581304376e-06, "epoch": 14.355555555555556, "percentage": 52.12, "elapsed_time": "0:07:02", "remaining_time": "0:06:28"}
+{"current_steps": 173, "total_steps": 330, "loss": 0.7543, "lr": 3.856820945115655e-06, "epoch": 14.444444444444445, "percentage": 52.42, "elapsed_time": "0:07:06", "remaining_time": "0:06:26"}
+{"current_steps": 174, "total_steps": 330, "loss": 0.8641, "lr": 3.828014292634508e-06, "epoch": 14.533333333333333, "percentage": 52.73, "elapsed_time": "0:07:09", "remaining_time": "0:06:24"}
+{"current_steps": 175, "total_steps": 330, "loss": 0.8557, "lr": 3.798959875088584e-06, "epoch": 14.622222222222222, "percentage": 53.03, "elapsed_time": "0:07:12", "remaining_time": "0:06:23"}
+{"current_steps": 176, "total_steps": 330, "loss": 0.8084, "lr": 3.769663113104516e-06, "epoch": 14.71111111111111, "percentage": 53.33, "elapsed_time": "0:07:16", "remaining_time": "0:06:21"}
+{"current_steps": 177, "total_steps": 330, "loss": 1.0103, "lr": 3.7401294725226707e-06, "epoch": 14.8, "percentage": 53.64, "elapsed_time": "0:07:19", "remaining_time": "0:06:19"}
+{"current_steps": 178, "total_steps": 330, "loss": 0.9011, "lr": 3.7103644633774015e-06, "epoch": 14.88888888888889, "percentage": 53.94, "elapsed_time": "0:07:22", "remaining_time": "0:06:17"}
+{"current_steps": 179, "total_steps": 330, "loss": 0.9671, "lr": 3.680373638869047e-06, "epoch": 14.977777777777778, "percentage": 54.24, "elapsed_time": "0:07:25", "remaining_time": "0:06:15"}
+{"current_steps": 180, "total_steps": 330, "loss": 1.1957, "lr": 3.650162594327881e-06, "epoch": 15.0, "percentage": 54.55, "elapsed_time": "0:07:26", "remaining_time": "0:06:11"}
+{"current_steps": 181, "total_steps": 330, "loss": 1.0547, "lr": 3.6197369661702052e-06, "epoch": 15.088888888888889, "percentage": 54.85, "elapsed_time": "0:07:29", "remaining_time": "0:06:09"}
+{"current_steps": 182, "total_steps": 330, "loss": 0.8339, "lr": 3.589102430846773e-06, "epoch": 15.177777777777777, "percentage": 55.15, "elapsed_time": "0:07:33", "remaining_time": "0:06:08"}
+{"current_steps": 183, "total_steps": 330, "loss": 0.933, "lr": 3.5582647037837446e-06, "epoch": 15.266666666666667, "percentage": 55.45, "elapsed_time": "0:07:36", "remaining_time": "0:06:06"}
+{"current_steps": 184, "total_steps": 330, "loss": 0.8677, "lr": 3.527229538316371e-06, "epoch": 15.355555555555556, "percentage": 55.76, "elapsed_time": "0:07:39", "remaining_time": "0:06:04"}
+{"current_steps": 185, "total_steps": 330, "loss": 0.9953, "lr": 3.4960027246156043e-06, "epoch": 15.444444444444445, "percentage": 56.06, "elapsed_time": "0:07:43", "remaining_time": "0:06:02"}
+{"current_steps": 186, "total_steps": 330, "loss": 0.9982, "lr": 3.4645900886078388e-06, "epoch": 15.533333333333333, "percentage": 56.36, "elapsed_time": "0:07:46", "remaining_time": "0:06:01"}
+{"current_steps": 187, "total_steps": 330, "loss": 0.8604, "lr": 3.432997490887979e-06, "epoch": 15.622222222222222, "percentage": 56.67, "elapsed_time": "0:07:49", "remaining_time": "0:05:58"}
+{"current_steps": 188, "total_steps": 330, "loss": 0.7839, "lr": 3.4012308256260366e-06, "epoch": 15.71111111111111, "percentage": 56.97, "elapsed_time": "0:07:52", "remaining_time": "0:05:56"}
+{"current_steps": 189, "total_steps": 330, "loss": 0.8544, "lr": 3.369296019467473e-06, "epoch": 15.8, "percentage": 57.27, "elapsed_time": "0:07:55", "remaining_time": "0:05:54"}
+{"current_steps": 190, "total_steps": 330, "loss": 0.8877, "lr": 3.3371990304274654e-06, "epoch": 15.88888888888889, "percentage": 57.58, "elapsed_time": "0:07:58", "remaining_time": "0:05:52"}
+{"current_steps": 191, "total_steps": 330, "loss": 0.9024, "lr": 3.304945846779346e-06, "epoch": 15.977777777777778, "percentage": 57.88, "elapsed_time": "0:08:01", "remaining_time": "0:05:50"}
+{"current_steps": 192, "total_steps": 330, "loss": 1.1495, "lr": 3.272542485937369e-06, "epoch": 16.0, "percentage": 58.18, "elapsed_time": "0:08:02", "remaining_time": "0:05:46"}
+{"current_steps": 193, "total_steps": 330, "loss": 0.9458, "lr": 3.239994993334059e-06, "epoch": 16.08888888888889, "percentage": 58.48, "elapsed_time": "0:08:05", "remaining_time": "0:05:44"}
+{"current_steps": 194, "total_steps": 330, "loss": 0.881, "lr": 3.207309441292325e-06, "epoch": 16.177777777777777, "percentage": 58.79, "elapsed_time": "0:08:08", "remaining_time": "0:05:42"}
+{"current_steps": 195, "total_steps": 330, "loss": 0.9062, "lr": 3.174491927892561e-06, "epoch": 16.266666666666666, "percentage": 59.09, "elapsed_time": "0:08:11", "remaining_time": "0:05:40"}
+{"current_steps": 196, "total_steps": 330, "loss": 1.002, "lr": 3.1415485758349344e-06, "epoch": 16.355555555555554, "percentage": 59.39, "elapsed_time": "0:08:14", "remaining_time": "0:05:37"}
+{"current_steps": 197, "total_steps": 330, "loss": 0.9224, "lr": 3.1084855312970897e-06, "epoch": 16.444444444444443, "percentage": 59.7, "elapsed_time": "0:08:17", "remaining_time": "0:05:35"}
+{"current_steps": 198, "total_steps": 330, "loss": 0.8111, "lr": 3.0753089627874668e-06, "epoch": 16.533333333333335, "percentage": 60.0, "elapsed_time": "0:08:20", "remaining_time": "0:05:33"}
+{"current_steps": 199, "total_steps": 330, "loss": 1.1155, "lr": 3.0420250599944525e-06, "epoch": 16.622222222222224, "percentage": 60.3, "elapsed_time": "0:08:23", "remaining_time": "0:05:31"}
+{"current_steps": 200, "total_steps": 330, "loss": 0.7782, "lr": 3.0086400326315853e-06, "epoch": 16.711111111111112, "percentage": 60.61, "elapsed_time": "0:08:26", "remaining_time": "0:05:29"}
+{"current_steps": 201, "total_steps": 330, "loss": 0.8999, "lr": 2.9751601092790185e-06, "epoch": 16.8, "percentage": 60.91, "elapsed_time": "0:08:29", "remaining_time": "0:05:27"}
+{"current_steps": 202, "total_steps": 330, "loss": 0.8363, "lr": 2.941591536221469e-06, "epoch": 16.88888888888889, "percentage": 61.21, "elapsed_time": "0:08:33", "remaining_time": "0:05:25"}
+{"current_steps": 203, "total_steps": 330, "loss": 0.8183, "lr": 2.907940576282856e-06, "epoch": 16.977777777777778, "percentage": 61.52, "elapsed_time": "0:08:37", "remaining_time": "0:05:23"}
+{"current_steps": 204, "total_steps": 330, "loss": 1.1636, "lr": 2.8742135076578608e-06, "epoch": 17.0, "percentage": 61.82, "elapsed_time": "0:08:37", "remaining_time": "0:05:19"}
+{"current_steps": 205, "total_steps": 330, "loss": 0.8142, "lr": 2.840416622740617e-06, "epoch": 17.08888888888889, "percentage": 62.12, "elapsed_time": "0:08:41", "remaining_time": "0:05:17"}
+{"current_steps": 206, "total_steps": 330, "loss": 0.8903, "lr": 2.8065562269507464e-06, "epoch": 17.177777777777777, "percentage": 62.42, "elapsed_time": "0:08:44", "remaining_time": "0:05:15"}
+{"current_steps": 207, "total_steps": 330, "loss": 0.9834, "lr": 2.7726386375569748e-06, "epoch": 17.266666666666666, "percentage": 62.73, "elapsed_time": "0:08:48", "remaining_time": "0:05:13"}
+{"current_steps": 208, "total_steps": 330, "loss": 0.6709, "lr": 2.7386701824985257e-06, "epoch": 17.355555555555554, "percentage": 63.03, "elapsed_time": "0:08:51", "remaining_time": "0:05:11"}
+{"current_steps": 209, "total_steps": 330, "loss": 0.8927, "lr": 2.7046571992045334e-06, "epoch": 17.444444444444443, "percentage": 63.33, "elapsed_time": "0:08:55", "remaining_time": "0:05:09"}
+{"current_steps": 210, "total_steps": 330, "loss": 0.9977, "lr": 2.670606033411678e-06, "epoch": 17.533333333333335, "percentage": 63.64, "elapsed_time": "0:08:57", "remaining_time": "0:05:07"}
+{"current_steps": 211, "total_steps": 330, "loss": 0.9036, "lr": 2.636523037980275e-06, "epoch": 17.622222222222224, "percentage": 63.94, "elapsed_time": "0:09:00", "remaining_time": "0:05:05"}
+{"current_steps": 212, "total_steps": 330, "loss": 0.9087, "lr": 2.602414571709036e-06, "epoch": 17.711111111111112, "percentage": 64.24, "elapsed_time": "0:09:03", "remaining_time": "0:05:02"}
+{"current_steps": 213, "total_steps": 330, "loss": 0.9693, "lr": 2.5682869981487154e-06, "epoch": 17.8, "percentage": 64.55, "elapsed_time": "0:09:06", "remaining_time": "0:05:00"}
+{"current_steps": 214, "total_steps": 330, "loss": 0.8481, "lr": 2.5341466844148775e-06, "epoch": 17.88888888888889, "percentage": 64.85, "elapsed_time": "0:09:09", "remaining_time": "0:04:57"}
+{"current_steps": 215, "total_steps": 330, "loss": 1.0045, "lr": 2.5e-06, "epoch": 17.977777777777778, "percentage": 65.15, "elapsed_time": "0:09:11", "remaining_time": "0:04:55"}
+{"current_steps": 216, "total_steps": 330, "loss": 1.0231, "lr": 2.465853315585123e-06, "epoch": 18.0, "percentage": 65.45, "elapsed_time": "0:09:12", "remaining_time": "0:04:51"}
+{"current_steps": 217, "total_steps": 330, "loss": 0.8498, "lr": 2.431713001851286e-06, "epoch": 18.08888888888889, "percentage": 65.76, "elapsed_time": "0:09:15", "remaining_time": "0:04:49"}
+{"current_steps": 218, "total_steps": 330, "loss": 1.0558, "lr": 2.3975854282909645e-06, "epoch": 18.177777777777777, "percentage": 66.06, "elapsed_time": "0:09:18", "remaining_time": "0:04:46"}
+{"current_steps": 219, "total_steps": 330, "loss": 0.8356, "lr": 2.3634769620197253e-06, "epoch": 18.266666666666666, "percentage": 66.36, "elapsed_time": "0:09:21", "remaining_time": "0:04:44"}
+{"current_steps": 220, "total_steps": 330, "loss": 0.959, "lr": 2.3293939665883233e-06, "epoch": 18.355555555555554, "percentage": 66.67, "elapsed_time": "0:09:24", "remaining_time": "0:04:42"}
+{"current_steps": 221, "total_steps": 330, "loss": 0.7641, "lr": 2.2953428007954682e-06, "epoch": 18.444444444444443, "percentage": 66.97, "elapsed_time": "0:09:26", "remaining_time": "0:04:39"}
+{"current_steps": 222, "total_steps": 330, "loss": 0.9507, "lr": 2.261329817501475e-06, "epoch": 18.533333333333335, "percentage": 67.27, "elapsed_time": "0:09:29", "remaining_time": "0:04:37"}
+{"current_steps": 223, "total_steps": 330, "loss": 0.9078, "lr": 2.2273613624430256e-06, "epoch": 18.622222222222224, "percentage": 67.58, "elapsed_time": "0:09:32", "remaining_time": "0:04:34"}
+{"current_steps": 224, "total_steps": 330, "loss": 0.8616, "lr": 2.1934437730492544e-06, "epoch": 18.711111111111112, "percentage": 67.88, "elapsed_time": "0:09:35", "remaining_time": "0:04:32"}
+{"current_steps": 225, "total_steps": 330, "loss": 0.7377, "lr": 2.159583377259384e-06, "epoch": 18.8, "percentage": 68.18, "elapsed_time": "0:09:38", "remaining_time": "0:04:29"}
+{"current_steps": 226, "total_steps": 330, "loss": 0.9405, "lr": 2.1257864923421405e-06, "epoch": 18.88888888888889, "percentage": 68.48, "elapsed_time": "0:09:42", "remaining_time": "0:04:27"}
+{"current_steps": 227, "total_steps": 330, "loss": 0.874, "lr": 2.092059423717145e-06, "epoch": 18.977777777777778, "percentage": 68.79, "elapsed_time": "0:09:45", "remaining_time": "0:04:25"}
+{"current_steps": 228, "total_steps": 330, "loss": 0.6244, "lr": 2.0584084637785316e-06, "epoch": 19.0, "percentage": 69.09, "elapsed_time": "0:09:45", "remaining_time": "0:04:22"}
+{"current_steps": 229, "total_steps": 330, "loss": 0.8523, "lr": 2.0248398907209827e-06, "epoch": 19.08888888888889, "percentage": 69.39, "elapsed_time": "0:09:48", "remaining_time": "0:04:19"}
+{"current_steps": 230, "total_steps": 330, "loss": 0.6882, "lr": 1.991359967368416e-06, "epoch": 19.177777777777777, "percentage": 69.7, "elapsed_time": "0:09:51", "remaining_time": "0:04:17"}
+{"current_steps": 231, "total_steps": 330, "loss": 0.7386, "lr": 1.957974940005548e-06, "epoch": 19.266666666666666, "percentage": 70.0, "elapsed_time": "0:09:55", "remaining_time": "0:04:15"}
+{"current_steps": 232, "total_steps": 330, "loss": 0.9825, "lr": 1.9246910372125345e-06, "epoch": 19.355555555555554, "percentage": 70.3, "elapsed_time": "0:09:58", "remaining_time": "0:04:12"}
+{"current_steps": 233, "total_steps": 330, "loss": 0.9288, "lr": 1.8915144687029107e-06, "epoch": 19.444444444444443, "percentage": 70.61, "elapsed_time": "0:10:02", "remaining_time": "0:04:10"}
+{"current_steps": 234, "total_steps": 330, "loss": 1.0302, "lr": 1.8584514241650667e-06, "epoch": 19.533333333333335, "percentage": 70.91, "elapsed_time": "0:10:05", "remaining_time": "0:04:08"}
+{"current_steps": 235, "total_steps": 330, "loss": 0.9244, "lr": 1.8255080721074391e-06, "epoch": 19.622222222222224, "percentage": 71.21, "elapsed_time": "0:10:07", "remaining_time": "0:04:05"}
+{"current_steps": 236, "total_steps": 330, "loss": 0.8465, "lr": 1.792690558707675e-06, "epoch": 19.711111111111112, "percentage": 71.52, "elapsed_time": "0:10:10", "remaining_time": "0:04:03"}
+{"current_steps": 237, "total_steps": 330, "loss": 0.9308, "lr": 1.7600050066659418e-06, "epoch": 19.8, "percentage": 71.82, "elapsed_time": "0:10:12", "remaining_time": "0:04:00"}
+{"current_steps": 238, "total_steps": 330, "loss": 0.9417, "lr": 1.7274575140626318e-06, "epoch": 19.88888888888889, "percentage": 72.12, "elapsed_time": "0:10:14", "remaining_time": "0:03:57"}
+{"current_steps": 239, "total_steps": 330, "loss": 0.8363, "lr": 1.695054153220655e-06, "epoch": 19.977777777777778, "percentage": 72.42, "elapsed_time": "0:10:16", "remaining_time": "0:03:54"}
+{"current_steps": 240, "total_steps": 330, "loss": 0.5418, "lr": 1.6628009695725348e-06, "epoch": 20.0, "percentage": 72.73, "elapsed_time": "0:10:17", "remaining_time": "0:03:51"}
+{"current_steps": 241, "total_steps": 330, "loss": 0.7425, "lr": 1.630703980532528e-06, "epoch": 20.08888888888889, "percentage": 73.03, "elapsed_time": "0:10:19", "remaining_time": "0:03:48"}
+{"current_steps": 242, "total_steps": 330, "loss": 0.7761, "lr": 1.5987691743739636e-06, "epoch": 20.177777777777777, "percentage": 73.33, "elapsed_time": "0:10:21", "remaining_time": "0:03:46"}
+{"current_steps": 243, "total_steps": 330, "loss": 0.8807, "lr": 1.5670025091120219e-06, "epoch": 20.266666666666666, "percentage": 73.64, "elapsed_time": "0:10:23", "remaining_time": "0:03:43"}
+{"current_steps": 244, "total_steps": 330, "loss": 0.875, "lr": 1.5354099113921614e-06, "epoch": 20.355555555555554, "percentage": 73.94, "elapsed_time": "0:10:26", "remaining_time": "0:03:40"}
+{"current_steps": 245, "total_steps": 330, "loss": 0.8312, "lr": 1.5039972753843966e-06, "epoch": 20.444444444444443, "percentage": 74.24, "elapsed_time": "0:10:29", "remaining_time": "0:03:38"}
+{"current_steps": 246, "total_steps": 330, "loss": 0.8858, "lr": 1.4727704616836297e-06, "epoch": 20.533333333333335, "percentage": 74.55, "elapsed_time": "0:10:31", "remaining_time": "0:03:35"}
+{"current_steps": 247, "total_steps": 330, "loss": 0.9683, "lr": 1.441735296216256e-06, "epoch": 20.622222222222224, "percentage": 74.85, "elapsed_time": "0:10:34", "remaining_time": "0:03:33"}
+{"current_steps": 248, "total_steps": 330, "loss": 0.9102, "lr": 1.4108975691532273e-06, "epoch": 20.711111111111112, "percentage": 75.15, "elapsed_time": "0:10:37", "remaining_time": "0:03:30"}
+{"current_steps": 249, "total_steps": 330, "loss": 0.96, "lr": 1.3802630338297956e-06, "epoch": 20.8, "percentage": 75.45, "elapsed_time": "0:10:39", "remaining_time": "0:03:27"}
+{"current_steps": 250, "total_steps": 330, "loss": 0.9536, "lr": 1.3498374056721198e-06, "epoch": 20.88888888888889, "percentage": 75.76, "elapsed_time": "0:10:41", "remaining_time": "0:03:25"}
+{"current_steps": 251, "total_steps": 330, "loss": 0.8433, "lr": 1.3196263611309539e-06, "epoch": 20.977777777777778, "percentage": 76.06, "elapsed_time": "0:10:43", "remaining_time": "0:03:22"}
+{"current_steps": 252, "total_steps": 330, "loss": 0.4761, "lr": 1.2896355366226e-06, "epoch": 21.0, "percentage": 76.36, "elapsed_time": "0:10:43", "remaining_time": "0:03:19"}
+{"current_steps": 253, "total_steps": 330, "loss": 0.8871, "lr": 1.2598705274773299e-06, "epoch": 21.08888888888889, "percentage": 76.67, "elapsed_time": "0:10:46", "remaining_time": "0:03:16"}
+{"current_steps": 254, "total_steps": 330, "loss": 0.773, "lr": 1.2303368868954848e-06, "epoch": 21.177777777777777, "percentage": 76.97, "elapsed_time": "0:10:48", "remaining_time": "0:03:14"}
+{"current_steps": 255, "total_steps": 330, "loss": 0.8273, "lr": 1.2010401249114166e-06, "epoch": 21.266666666666666, "percentage": 77.27, "elapsed_time": "0:10:51", "remaining_time": "0:03:11"}
+{"current_steps": 256, "total_steps": 330, "loss": 0.8088, "lr": 1.1719857073654923e-06, "epoch": 21.355555555555554, "percentage": 77.58, "elapsed_time": "0:10:53", "remaining_time": "0:03:08"}
+{"current_steps": 257, "total_steps": 330, "loss": 0.9616, "lr": 1.1431790548843464e-06, "epoch": 21.444444444444443, "percentage": 77.88, "elapsed_time": "0:10:55", "remaining_time": "0:03:06"}
+{"current_steps": 258, "total_steps": 330, "loss": 0.8371, "lr": 1.1146255418695635e-06, "epoch": 21.533333333333335, "percentage": 78.18, "elapsed_time": "0:10:58", "remaining_time": "0:03:03"}
+{"current_steps": 259, "total_steps": 330, "loss": 0.802, "lr": 1.0863304954949856e-06, "epoch": 21.622222222222224, "percentage": 78.48, "elapsed_time": "0:11:00", "remaining_time": "0:03:01"}
+{"current_steps": 260, "total_steps": 330, "loss": 0.8741, "lr": 1.0582991947128324e-06, "epoch": 21.711111111111112, "percentage": 78.79, "elapsed_time": "0:11:03", "remaining_time": "0:02:58"}
+{"current_steps": 261, "total_steps": 330, "loss": 0.7535, "lr": 1.0305368692688175e-06, "epoch": 21.8, "percentage": 79.09, "elapsed_time": "0:11:05", "remaining_time": "0:02:55"}
+{"current_steps": 262, "total_steps": 330, "loss": 0.894, "lr": 1.0030486987264436e-06, "epoch": 21.88888888888889, "percentage": 79.39, "elapsed_time": "0:11:08", "remaining_time": "0:02:53"}
+{"current_steps": 263, "total_steps": 330, "loss": 0.9623, "lr": 9.758398115006637e-07, "epoch": 21.977777777777778, "percentage": 79.7, "elapsed_time": "0:11:10", "remaining_time": "0:02:50"}
+{"current_steps": 264, "total_steps": 330, "loss": 0.9206, "lr": 9.489152839010799e-07, "epoch": 22.0, "percentage": 80.0, "elapsed_time": "0:11:11", "remaining_time": "0:02:47"}
+{"current_steps": 265, "total_steps": 330, "loss": 0.696, "lr": 9.222801391848688e-07, "epoch": 22.08888888888889, "percentage": 80.3, "elapsed_time": "0:11:13", "remaining_time": "0:02:45"}
+{"current_steps": 266, "total_steps": 330, "loss": 0.8825, "lr": 8.959393466195973e-07, "epoch": 22.177777777777777, "percentage": 80.61, "elapsed_time": "0:11:16", "remaining_time": "0:02:42"}
+{"current_steps": 267, "total_steps": 330, "loss": 0.9445, "lr": 8.69897820556124e-07, "epoch": 22.266666666666666, "percentage": 80.91, "elapsed_time": "0:11:19", "remaining_time": "0:02:40"}
+{"current_steps": 268, "total_steps": 330, "loss": 0.8024, "lr": 8.441604195117315e-07, "epoch": 22.355555555555554, "percentage": 81.21, "elapsed_time": "0:11:21", "remaining_time": "0:02:37"}
+{"current_steps": 269, "total_steps": 330, "loss": 0.7532, "lr": 8.187319452636821e-07, "epoch": 22.444444444444443, "percentage": 81.52, "elapsed_time": "0:11:23", "remaining_time": "0:02:35"}
+{"current_steps": 270, "total_steps": 330, "loss": 0.949, "lr": 7.936171419533653e-07, "epoch": 22.533333333333335, "percentage": 81.82, "elapsed_time": "0:11:26", "remaining_time": "0:02:32"}
+{"current_steps": 271, "total_steps": 330, "loss": 0.7882, "lr": 7.688206952011862e-07, "epoch": 22.622222222222224, "percentage": 82.12, "elapsed_time": "0:11:28", "remaining_time": "0:02:29"}
+{"current_steps": 272, "total_steps": 330, "loss": 0.7254, "lr": 7.443472312323824e-07, "epoch": 22.711111111111112, "percentage": 82.42, "elapsed_time": "0:11:30", "remaining_time": "0:02:27"}
+{"current_steps": 273, "total_steps": 330, "loss": 1.1334, "lr": 7.202013160139159e-07, "epoch": 22.8, "percentage": 82.73, "elapsed_time": "0:11:33", "remaining_time": "0:02:24"}
+{"current_steps": 274, "total_steps": 330, "loss": 0.7708, "lr": 6.963874544026109e-07, "epoch": 22.88888888888889, "percentage": 83.03, "elapsed_time": "0:11:35", "remaining_time": "0:02:22"}
+{"current_steps": 275, "total_steps": 330, "loss": 0.8617, "lr": 6.729100893046897e-07, "epoch": 22.977777777777778, "percentage": 83.33, "elapsed_time": "0:11:38", "remaining_time": "0:02:19"}
+{"current_steps": 276, "total_steps": 330, "loss": 0.7606, "lr": 6.497736008468703e-07, "epoch": 23.0, "percentage": 83.64, "elapsed_time": "0:11:39", "remaining_time": "0:02:16"}
+{"current_steps": 277, "total_steps": 330, "loss": 0.7765, "lr": 6.269823055591726e-07, "epoch": 23.08888888888889, "percentage": 83.94, "elapsed_time": "0:11:42", "remaining_time": "0:02:14"}
+{"current_steps": 278, "total_steps": 330, "loss": 0.907, "lr": 6.045404555695935e-07, "epoch": 23.177777777777777, "percentage": 84.24, "elapsed_time": "0:11:44", "remaining_time": "0:02:11"}
+{"current_steps": 279, "total_steps": 330, "loss": 1.0291, "lr": 5.824522378107936e-07, "epoch": 23.266666666666666, "percentage": 84.55, "elapsed_time": "0:11:49", "remaining_time": "0:02:09"}
+{"current_steps": 280, "total_steps": 330, "loss": 0.8876, "lr": 5.607217732389503e-07, "epoch": 23.355555555555554, "percentage": 84.85, "elapsed_time": "0:11:52", "remaining_time": "0:02:07"}
+{"current_steps": 281, "total_steps": 330, "loss": 0.9152, "lr": 5.393531160649221e-07, "epoch": 23.444444444444443, "percentage": 85.15, "elapsed_time": "0:11:55", "remaining_time": "0:02:04"}
+{"current_steps": 282, "total_steps": 330, "loss": 0.9826, "lr": 5.183502529978548e-07, "epoch": 23.533333333333335, "percentage": 85.45, "elapsed_time": "0:11:59", "remaining_time": "0:02:02"}
+{"current_steps": 283, "total_steps": 330, "loss": 0.7636, "lr": 4.977171025013961e-07, "epoch": 23.622222222222224, "percentage": 85.76, "elapsed_time": "0:12:01", "remaining_time": "0:01:59"}
+{"current_steps": 284, "total_steps": 330, "loss": 0.6843, "lr": 4.774575140626317e-07, "epoch": 23.711111111111112, "percentage": 86.06, "elapsed_time": "0:12:05", "remaining_time": "0:01:57"}
+{"current_steps": 285, "total_steps": 330, "loss": 0.8194, "lr": 4.5757526747389506e-07, "epoch": 23.8, "percentage": 86.36, "elapsed_time": "0:12:08", "remaining_time": "0:01:54"}
+{"current_steps": 286, "total_steps": 330, "loss": 0.8164, "lr": 4.380740721275786e-07, "epoch": 23.88888888888889, "percentage": 86.67, "elapsed_time": "0:12:11", "remaining_time": "0:01:52"}
+{"current_steps": 287, "total_steps": 330, "loss": 0.7278, "lr": 4.189575663240794e-07, "epoch": 23.977777777777778, "percentage": 86.97, "elapsed_time": "0:12:14", "remaining_time": "0:01:50"}
+{"current_steps": 288, "total_steps": 330, "loss": 0.7292, "lr": 4.002293165930088e-07, "epoch": 24.0, "percentage": 87.27, "elapsed_time": "0:12:15", "remaining_time": "0:01:47"}
+{"current_steps": 289, "total_steps": 330, "loss": 0.6609, "lr": 3.818928170277911e-07, "epoch": 24.08888888888889, "percentage": 87.58, "elapsed_time": "0:12:18", "remaining_time": "0:01:44"}
+{"current_steps": 290, "total_steps": 330, "loss": 0.8054, "lr": 3.639514886337786e-07, "epoch": 24.177777777777777, "percentage": 87.88, "elapsed_time": "0:12:21", "remaining_time": "0:01:42"}
+{"current_steps": 291, "total_steps": 330, "loss": 0.869, "lr": 3.4640867869000036e-07, "epoch": 24.266666666666666, "percentage": 88.18, "elapsed_time": "0:12:23", "remaining_time": "0:01:39"}
+{"current_steps": 292, "total_steps": 330, "loss": 1.0296, "lr": 3.292676601246661e-07, "epoch": 24.355555555555554, "percentage": 88.48, "elapsed_time": "0:12:27", "remaining_time": "0:01:37"}
+{"current_steps": 293, "total_steps": 330, "loss": 0.9983, "lr": 3.125316309045434e-07, "epoch": 24.444444444444443, "percentage": 88.79, "elapsed_time": "0:12:29", "remaining_time": "0:01:34"}
+{"current_steps": 294, "total_steps": 330, "loss": 0.8998, "lr": 2.962037134383211e-07, "epoch": 24.533333333333335, "percentage": 89.09, "elapsed_time": "0:12:33", "remaining_time": "0:01:32"}
+{"current_steps": 295, "total_steps": 330, "loss": 0.805, "lr": 2.80286953994062e-07, "epoch": 24.622222222222224, "percentage": 89.39, "elapsed_time": "0:12:36", "remaining_time": "0:01:29"}
+{"current_steps": 296, "total_steps": 330, "loss": 0.6883, "lr": 2.647843221308721e-07, "epoch": 24.711111111111112, "percentage": 89.7, "elapsed_time": "0:12:39", "remaining_time": "0:01:27"}
+{"current_steps": 297, "total_steps": 330, "loss": 0.8913, "lr": 2.496987101448728e-07, "epoch": 24.8, "percentage": 90.0, "elapsed_time": "0:12:43", "remaining_time": "0:01:24"}
+{"current_steps": 298, "total_steps": 330, "loss": 0.938, "lr": 2.3503293252959136e-07, "epoch": 24.88888888888889, "percentage": 90.3, "elapsed_time": "0:12:46", "remaining_time": "0:01:22"}
+{"current_steps": 299, "total_steps": 330, "loss": 0.8841, "lr": 2.2078972545086647e-07, "epoch": 24.977777777777778, "percentage": 90.61, "elapsed_time": "0:12:49", "remaining_time": "0:01:19"}
+{"current_steps": 300, "total_steps": 330, "loss": 0.556, "lr": 2.0697174623636795e-07, "epoch": 25.0, "percentage": 90.91, "elapsed_time": "0:12:50", "remaining_time": "0:01:17"}
+{"current_steps": 301, "total_steps": 330, "loss": 0.8709, "lr": 1.9358157287982099e-07, "epoch": 25.08888888888889, "percentage": 91.21, "elapsed_time": "0:12:52", "remaining_time": "0:01:14"}
+{"current_steps": 302, "total_steps": 330, "loss": 0.6853, "lr": 1.8062170356003854e-07, "epoch": 25.177777777777777, "percentage": 91.52, "elapsed_time": "0:12:54", "remaining_time": "0:01:11"}
+{"current_steps": 303, "total_steps": 330, "loss": 0.995, "lr": 1.680945561748412e-07, "epoch": 25.266666666666666, "percentage": 91.82, "elapsed_time": "0:12:57", "remaining_time": "0:01:09"}
+{"current_steps": 304, "total_steps": 330, "loss": 0.8167, "lr": 1.5600246788994938e-07, "epoch": 25.355555555555554, "percentage": 92.12, "elapsed_time": "0:12:59", "remaining_time": "0:01:06"}
+{"current_steps": 305, "total_steps": 330, "loss": 0.9414, "lr": 1.44347694702949e-07, "epoch": 25.444444444444443, "percentage": 92.42, "elapsed_time": "0:13:01", "remaining_time": "0:01:04"}
+{"current_steps": 306, "total_steps": 330, "loss": 0.9439, "lr": 1.3313241102239056e-07, "epoch": 25.533333333333335, "percentage": 92.73, "elapsed_time": "0:13:04", "remaining_time": "0:01:01"}
+{"current_steps": 307, "total_steps": 330, "loss": 0.6697, "lr": 1.223587092621162e-07, "epoch": 25.622222222222224, "percentage": 93.03, "elapsed_time": "0:13:07", "remaining_time": "0:00:58"}
+{"current_steps": 308, "total_steps": 330, "loss": 0.9173, "lr": 1.120285994508799e-07, "epoch": 25.711111111111112, "percentage": 93.33, "elapsed_time": "0:13:09", "remaining_time": "0:00:56"}
+{"current_steps": 309, "total_steps": 330, "loss": 0.8086, "lr": 1.0214400885734194e-07, "epoch": 25.8, "percentage": 93.64, "elapsed_time": "0:13:11", "remaining_time": "0:00:53"}
+{"current_steps": 310, "total_steps": 330, "loss": 0.8424, "lr": 9.270678163050218e-08, "epoch": 25.88888888888889, "percentage": 93.94, "elapsed_time": "0:13:14", "remaining_time": "0:00:51"}
+{"current_steps": 311, "total_steps": 330, "loss": 0.8007, "lr": 8.371867845563819e-08, "epoch": 25.977777777777778, "percentage": 94.24, "elapsed_time": "0:13:16", "remaining_time": "0:00:48"}
+{"current_steps": 312, "total_steps": 330, "loss": 0.8582, "lr": 7.518137622582189e-08, "epoch": 26.0, "percentage": 94.55, "elapsed_time": "0:13:17", "remaining_time": "0:00:46"}
+{"current_steps": 313, "total_steps": 330, "loss": 0.767, "lr": 6.70964677290617e-08, "epoch": 26.08888888888889, "percentage": 94.85, "elapsed_time": "0:13:19", "remaining_time": "0:00:43"}
+{"current_steps": 314, "total_steps": 330, "loss": 0.8953, "lr": 5.946546135113862e-08, "epoch": 26.177777777777777, "percentage": 95.15, "elapsed_time": "0:13:24", "remaining_time": "0:00:40"}
+{"current_steps": 315, "total_steps": 330, "loss": 0.7334, "lr": 5.2289780794192726e-08, "epoch": 26.266666666666666, "percentage": 95.45, "elapsed_time": "0:13:29", "remaining_time": "0:00:38"}
+{"current_steps": 316, "total_steps": 330, "loss": 0.9373, "lr": 4.557076481110367e-08, "epoch": 26.355555555555554, "percentage": 95.76, "elapsed_time": "0:13:33", "remaining_time": "0:00:36"}
+{"current_steps": 317, "total_steps": 330, "loss": 0.884, "lr": 3.930966695572136e-08, "epoch": 26.444444444444443, "percentage": 96.06, "elapsed_time": "0:13:39", "remaining_time": "0:00:33"}
+{"current_steps": 318, "total_steps": 330, "loss": 0.7411, "lr": 3.3507655348995194e-08, "epoch": 26.533333333333335, "percentage": 96.36, "elapsed_time": "0:13:43", "remaining_time": "0:00:31"}
+{"current_steps": 319, "total_steps": 330, "loss": 0.7748, "lr": 2.8165812461038166e-08, "epoch": 26.622222222222224, "percentage": 96.67, "elapsed_time": "0:13:46", "remaining_time": "0:00:28"}
+{"current_steps": 320, "total_steps": 330, "loss": 0.8678, "lr": 2.3285134909173113e-08, "epoch": 26.711111111111112, "percentage": 96.97, "elapsed_time": "0:13:48", "remaining_time": "0:00:25"}
+{"current_steps": 321, "total_steps": 330, "loss": 0.8908, "lr": 1.886653327199617e-08, "epoch": 26.8, "percentage": 97.27, "elapsed_time": "0:13:51", "remaining_time": "0:00:23"}
+{"current_steps": 322, "total_steps": 330, "loss": 0.8878, "lr": 1.4910831919490997e-08, "epoch": 26.88888888888889, "percentage": 97.58, "elapsed_time": "0:13:53", "remaining_time": "0:00:20"}
+{"current_steps": 323, "total_steps": 330, "loss": 0.895, "lr": 1.1418768859227935e-08, "epoch": 26.977777777777778, "percentage": 97.88, "elapsed_time": "0:13:56", "remaining_time": "0:00:18"}
+{"current_steps": 324, "total_steps": 330, "loss": 0.802, "lr": 8.390995598676067e-09, "epoch": 27.0, "percentage": 98.18, "elapsed_time": "0:13:56", "remaining_time": "0:00:15"}
+{"current_steps": 325, "total_steps": 330, "loss": 0.6027, "lr": 5.828077023651846e-09, "epoch": 27.08888888888889, "percentage": 98.48, "elapsed_time": "0:13:59", "remaining_time": "0:00:12"}
+{"current_steps": 326, "total_steps": 330, "loss": 0.7449, "lr": 3.730491292930072e-09, "epoch": 27.177777777777777, "percentage": 98.79, "elapsed_time": "0:14:01", "remaining_time": "0:00:10"}
+{"current_steps": 327, "total_steps": 330, "loss": 0.9378, "lr": 2.0986297490338536e-09, "epoch": 27.266666666666666, "percentage": 99.09, "elapsed_time": "0:14:03", "remaining_time": "0:00:07"}
+{"current_steps": 328, "total_steps": 330, "loss": 0.8487, "lr": 9.32796845223294e-10, "epoch": 27.355555555555554, "percentage": 99.39, "elapsed_time": "0:14:06", "remaining_time": "0:00:05"}
+{"current_steps": 329, "total_steps": 330, "loss": 0.9618, "lr": 2.3321008869481296e-10, "epoch": 27.444444444444443, "percentage": 99.7, "elapsed_time": "0:14:08", "remaining_time": "0:00:02"}
+{"current_steps": 330, "total_steps": 330, "loss": 1.0057, "lr": 0.0, "epoch": 27.533333333333335, "percentage": 100.0, "elapsed_time": "0:14:11", "remaining_time": "0:00:00"}
+{"current_steps": 330, "total_steps": 330, "epoch": 27.533333333333335, "percentage": 100.0, "elapsed_time": "0:14:11", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2352 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 27.533333333333335,
+  "eval_steps": 500,
+  "global_step": 330,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.19567996263504028,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 0.94,
+      "step": 1
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.2986994683742523,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 1.0076,
+      "step": 2
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.28921350836753845,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 0.9695,
+      "step": 3
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.30233919620513916,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 0.8687,
+      "step": 4
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.36907249689102173,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 1.099,
+      "step": 5
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.38191747665405273,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 1.2947,
+      "step": 6
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.2860971689224243,
+      "learning_rate": 3.5000000000000004e-07,
+      "loss": 0.9469,
+      "step": 7
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.2793874442577362,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 1.032,
+      "step": 8
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.28660792112350464,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 1.0493,
+      "step": 9
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.23447971045970917,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 1.051,
+      "step": 10
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.5307306051254272,
+      "learning_rate": 5.5e-07,
+      "loss": 1.0976,
+      "step": 11
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.49731138348579407,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 0.9379,
+      "step": 12
+    },
+    {
+      "epoch": 1.0888888888888888,
+      "grad_norm": 0.2752147614955902,
+      "learning_rate": 6.5e-07,
+      "loss": 0.9381,
+      "step": 13
+    },
+    {
+      "epoch": 1.1777777777777778,
+      "grad_norm": 0.34284281730651855,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 0.9569,
+      "step": 14
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.25561222434043884,
+      "learning_rate": 7.5e-07,
+      "loss": 1.0227,
+      "step": 15
+    },
+    {
+      "epoch": 1.3555555555555556,
+      "grad_norm": 0.2456677258014679,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 1.0438,
+      "step": 16
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.29848751425743103,
+      "learning_rate": 8.500000000000001e-07,
+      "loss": 1.1062,
+      "step": 17
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.28204187750816345,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 0.8878,
+      "step": 18
+    },
+    {
+      "epoch": 1.6222222222222222,
+      "grad_norm": 0.26430532336235046,
+      "learning_rate": 9.500000000000001e-07,
+      "loss": 1.0275,
+      "step": 19
+    },
+    {
+      "epoch": 1.7111111111111112,
+      "grad_norm": 0.26862281560897827,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.9946,
+      "step": 20
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.36035194993019104,
+      "learning_rate": 1.0500000000000001e-06,
+      "loss": 1.0708,
+      "step": 21
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.23725222051143646,
+      "learning_rate": 1.1e-06,
+      "loss": 1.101,
+      "step": 22
+    },
+    {
+      "epoch": 1.9777777777777779,
+      "grad_norm": 0.3509962856769562,
+      "learning_rate": 1.1500000000000002e-06,
+      "loss": 0.9893,
+      "step": 23
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.26212382316589355,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.1786,
+      "step": 24
+    },
+    {
+      "epoch": 2.088888888888889,
+      "grad_norm": 0.32545071840286255,
+      "learning_rate": 1.25e-06,
+      "loss": 1.0819,
+      "step": 25
+    },
+    {
+      "epoch": 2.1777777777777776,
+      "grad_norm": 0.23323898017406464,
+      "learning_rate": 1.3e-06,
+      "loss": 1.0393,
+      "step": 26
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.2809179723262787,
+      "learning_rate": 1.3500000000000002e-06,
+      "loss": 1.1029,
+      "step": 27
+    },
+    {
+      "epoch": 2.3555555555555556,
+      "grad_norm": 0.28984516859054565,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 1.0597,
+      "step": 28
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.3196355402469635,
+      "learning_rate": 1.45e-06,
+      "loss": 0.9494,
+      "step": 29
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 0.2864663600921631,
+      "learning_rate": 1.5e-06,
+      "loss": 0.944,
+      "step": 30
+    },
+    {
+      "epoch": 2.6222222222222222,
+      "grad_norm": 0.24206970632076263,
+      "learning_rate": 1.5500000000000002e-06,
+      "loss": 1.023,
+      "step": 31
+    },
+    {
+      "epoch": 2.7111111111111112,
+      "grad_norm": 0.2996947765350342,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.9772,
+      "step": 32
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.28879255056381226,
+      "learning_rate": 1.6500000000000003e-06,
+      "loss": 1.0928,
+      "step": 33
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.27944567799568176,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 0.9012,
+      "step": 34
+    },
+    {
+      "epoch": 2.977777777777778,
+      "grad_norm": 0.2939954400062561,
+      "learning_rate": 1.75e-06,
+      "loss": 1.0461,
+      "step": 35
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.5568829774856567,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 0.9155,
+      "step": 36
+    },
+    {
+      "epoch": 3.088888888888889,
+      "grad_norm": 0.3321582078933716,
+      "learning_rate": 1.85e-06,
+      "loss": 1.0048,
+      "step": 37
+    },
+    {
+      "epoch": 3.1777777777777776,
+      "grad_norm": 0.29956573247909546,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 0.9085,
+      "step": 38
+    },
+    {
+      "epoch": 3.2666666666666666,
+      "grad_norm": 0.2925553023815155,
+      "learning_rate": 1.9500000000000004e-06,
+      "loss": 0.8711,
+      "step": 39
+    },
+    {
+      "epoch": 3.3555555555555556,
+      "grad_norm": 0.32938718795776367,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.0397,
+      "step": 40
+    },
+    {
+      "epoch": 3.4444444444444446,
+      "grad_norm": 0.37126410007476807,
+      "learning_rate": 2.05e-06,
+      "loss": 1.0436,
+      "step": 41
+    },
+    {
+      "epoch": 3.533333333333333,
+      "grad_norm": 0.30750295519828796,
+      "learning_rate": 2.1000000000000002e-06,
+      "loss": 1.1212,
+      "step": 42
+    },
+    {
+      "epoch": 3.6222222222222222,
+      "grad_norm": 0.27158430218696594,
+      "learning_rate": 2.15e-06,
+      "loss": 1.0738,
+      "step": 43
+    },
+    {
+      "epoch": 3.7111111111111112,
+      "grad_norm": 0.19385884702205658,
+      "learning_rate": 2.2e-06,
+      "loss": 0.9962,
+      "step": 44
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.3193662464618683,
+      "learning_rate": 2.25e-06,
+      "loss": 1.121,
+      "step": 45
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 0.30041366815567017,
+      "learning_rate": 2.3000000000000004e-06,
+      "loss": 1.0232,
+      "step": 46
+    },
+    {
+      "epoch": 3.977777777777778,
+      "grad_norm": 0.3569968640804291,
+      "learning_rate": 2.35e-06,
+      "loss": 1.0396,
+      "step": 47
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.0826685428619385,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.0178,
+      "step": 48
+    },
+    {
+      "epoch": 4.088888888888889,
+      "grad_norm": 0.3048429787158966,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 1.0127,
+      "step": 49
+    },
+    {
+      "epoch": 4.177777777777778,
+      "grad_norm": 0.6735008955001831,
+      "learning_rate": 2.5e-06,
+      "loss": 1.0034,
+      "step": 50
+    },
+    {
+      "epoch": 4.266666666666667,
+      "grad_norm": 0.28620263934135437,
+      "learning_rate": 2.55e-06,
+      "loss": 1.0821,
+      "step": 51
+    },
+    {
+      "epoch": 4.355555555555555,
+      "grad_norm": 0.2925148904323578,
+      "learning_rate": 2.6e-06,
+      "loss": 0.8747,
+      "step": 52
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.28806746006011963,
+      "learning_rate": 2.6500000000000005e-06,
+      "loss": 1.0981,
+      "step": 53
+    },
+    {
+      "epoch": 4.533333333333333,
+      "grad_norm": 0.2822423279285431,
+      "learning_rate": 2.7000000000000004e-06,
+      "loss": 0.8774,
+      "step": 54
+    },
+    {
+      "epoch": 4.622222222222222,
+      "grad_norm": 0.30998173356056213,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 1.0841,
+      "step": 55
+    },
+    {
+      "epoch": 4.711111111111111,
+      "grad_norm": 0.3339422047138214,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 1.0752,
+      "step": 56
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.3425965905189514,
+      "learning_rate": 2.85e-06,
+      "loss": 1.087,
+      "step": 57
+    },
+    {
+      "epoch": 4.888888888888889,
+      "grad_norm": 0.2678565979003906,
+      "learning_rate": 2.9e-06,
+      "loss": 1.0578,
+      "step": 58
+    },
+    {
+      "epoch": 4.977777777777778,
+      "grad_norm": 0.3225661516189575,
+      "learning_rate": 2.95e-06,
+      "loss": 0.9329,
+      "step": 59
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.5934492945671082,
+      "learning_rate": 3e-06,
+      "loss": 0.9952,
+      "step": 60
+    },
+    {
+      "epoch": 5.088888888888889,
+      "grad_norm": 0.41927722096443176,
+      "learning_rate": 3.05e-06,
+      "loss": 1.2386,
+      "step": 61
+    },
+    {
+      "epoch": 5.177777777777778,
+      "grad_norm": 0.3196963667869568,
+      "learning_rate": 3.1000000000000004e-06,
+      "loss": 0.9,
+      "step": 62
+    },
+    {
+      "epoch": 5.266666666666667,
+      "grad_norm": 0.31587812304496765,
+      "learning_rate": 3.1500000000000003e-06,
+      "loss": 1.0832,
+      "step": 63
+    },
+    {
+      "epoch": 5.355555555555555,
+      "grad_norm": 0.34145388007164,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.9822,
+      "step": 64
+    },
+    {
+      "epoch": 5.444444444444445,
+      "grad_norm": 0.302914023399353,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.9968,
+      "step": 65
+    },
+    {
+      "epoch": 5.533333333333333,
+      "grad_norm": 0.22116686403751373,
+      "learning_rate": 3.3000000000000006e-06,
+      "loss": 0.9124,
+      "step": 66
+    },
+    {
+      "epoch": 5.622222222222222,
+      "grad_norm": 0.3197582960128784,
+      "learning_rate": 3.3500000000000005e-06,
+      "loss": 1.1134,
+      "step": 67
+    },
+    {
+      "epoch": 5.711111111111111,
+      "grad_norm": 0.31704509258270264,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.879,
+      "step": 68
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 0.35378602147102356,
+      "learning_rate": 3.45e-06,
+      "loss": 1.103,
+      "step": 69
+    },
+    {
+      "epoch": 5.888888888888889,
+      "grad_norm": 0.33167579770088196,
+      "learning_rate": 3.5e-06,
+      "loss": 1.0124,
+      "step": 70
+    },
+    {
+      "epoch": 5.977777777777778,
+      "grad_norm": 0.30484288930892944,
+      "learning_rate": 3.5500000000000003e-06,
+      "loss": 1.001,
+      "step": 71
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.4108036458492279,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 1.0199,
+      "step": 72
+    },
+    {
+      "epoch": 6.088888888888889,
+      "grad_norm": 0.3657933175563812,
+      "learning_rate": 3.65e-06,
+      "loss": 1.1584,
+      "step": 73
+    },
+    {
+      "epoch": 6.177777777777778,
+      "grad_norm": 0.6758050918579102,
+      "learning_rate": 3.7e-06,
+      "loss": 1.0419,
+      "step": 74
+    },
+    {
+      "epoch": 6.266666666666667,
+      "grad_norm": 0.35230952501296997,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.856,
+      "step": 75
+    },
+    {
+      "epoch": 6.355555555555555,
+      "grad_norm": 0.38534823060035706,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.9925,
+      "step": 76
+    },
+    {
+      "epoch": 6.444444444444445,
+      "grad_norm": 0.32009822130203247,
+      "learning_rate": 3.85e-06,
+      "loss": 1.0069,
+      "step": 77
+    },
+    {
+      "epoch": 6.533333333333333,
+      "grad_norm": 0.32822826504707336,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 0.953,
+      "step": 78
+    },
+    {
+      "epoch": 6.622222222222222,
+      "grad_norm": 0.36539173126220703,
+      "learning_rate": 3.95e-06,
+      "loss": 1.1169,
+      "step": 79
+    },
+    {
+      "epoch": 6.711111111111111,
+      "grad_norm": 0.3481679856777191,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.9554,
+      "step": 80
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 0.4089198410511017,
+      "learning_rate": 4.05e-06,
+      "loss": 1.0723,
+      "step": 81
+    },
+    {
+      "epoch": 6.888888888888889,
+      "grad_norm": 0.3250631093978882,
+      "learning_rate": 4.1e-06,
+      "loss": 1.0264,
+      "step": 82
+    },
+    {
+      "epoch": 6.977777777777778,
+      "grad_norm": 0.26394304633140564,
+      "learning_rate": 4.15e-06,
+      "loss": 0.9445,
+      "step": 83
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.5080349445343018,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 1.1842,
+      "step": 84
+    },
+    {
+      "epoch": 7.088888888888889,
+      "grad_norm": 0.349873811006546,
+      "learning_rate": 4.25e-06,
+      "loss": 1.0707,
+      "step": 85
+    },
+    {
+      "epoch": 7.177777777777778,
+      "grad_norm": 0.4573216140270233,
+      "learning_rate": 4.3e-06,
+      "loss": 1.116,
+      "step": 86
+    },
+    {
+      "epoch": 7.266666666666667,
+      "grad_norm": 0.32420143485069275,
+      "learning_rate": 4.350000000000001e-06,
+      "loss": 0.8747,
+      "step": 87
+    },
+    {
+      "epoch": 7.355555555555555,
+      "grad_norm": 0.3515697717666626,
+      "learning_rate": 4.4e-06,
+      "loss": 0.9918,
+      "step": 88
+    },
+    {
+      "epoch": 7.444444444444445,
+      "grad_norm": 0.404070645570755,
+      "learning_rate": 4.450000000000001e-06,
+      "loss": 1.1398,
+      "step": 89
+    },
+    {
+      "epoch": 7.533333333333333,
+      "grad_norm": 0.3488151729106903,
+      "learning_rate": 4.5e-06,
+      "loss": 0.9042,
+      "step": 90
+    },
+    {
+      "epoch": 7.622222222222222,
+      "grad_norm": 0.3190948963165283,
+      "learning_rate": 4.5500000000000005e-06,
+      "loss": 0.9608,
+      "step": 91
+    },
+    {
+      "epoch": 7.711111111111111,
+      "grad_norm": 0.3400370478630066,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 0.9085,
+      "step": 92
+    },
+    {
+      "epoch": 7.8,
+      "grad_norm": 0.3799091577529907,
+      "learning_rate": 4.65e-06,
+      "loss": 1.0053,
+      "step": 93
+    },
+    {
+      "epoch": 7.888888888888889,
+      "grad_norm": 0.31531545519828796,
+      "learning_rate": 4.7e-06,
+      "loss": 1.1269,
+      "step": 94
+    },
+    {
+      "epoch": 7.977777777777778,
+      "grad_norm": 0.540896475315094,
+      "learning_rate": 4.75e-06,
+      "loss": 1.1115,
+      "step": 95
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.4667949080467224,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.8602,
+      "step": 96
+    },
+    {
+      "epoch": 8.088888888888889,
+      "grad_norm": 0.29491057991981506,
+      "learning_rate": 4.85e-06,
+      "loss": 1.0071,
+      "step": 97
+    },
+    {
+      "epoch": 8.177777777777777,
+      "grad_norm": 0.4064798355102539,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 0.847,
+      "step": 98
+    },
+    {
+      "epoch": 8.266666666666667,
+      "grad_norm": 0.35105201601982117,
+      "learning_rate": 4.95e-06,
+      "loss": 0.9321,
+      "step": 99
+    },
+    {
+      "epoch": 8.355555555555556,
+      "grad_norm": 0.42249858379364014,
+      "learning_rate": 5e-06,
+      "loss": 0.9997,
+      "step": 100
+    },
+    {
+      "epoch": 8.444444444444445,
+      "grad_norm": 0.46596774458885193,
+      "learning_rate": 4.9997667899113055e-06,
+      "loss": 0.9206,
+      "step": 101
+    },
+    {
+      "epoch": 8.533333333333333,
+      "grad_norm": 0.4481567442417145,
+      "learning_rate": 4.999067203154777e-06,
+      "loss": 1.0383,
+      "step": 102
+    },
+    {
+      "epoch": 8.622222222222222,
+      "grad_norm": 0.389378160238266,
+      "learning_rate": 4.997901370250966e-06,
+      "loss": 1.2077,
+      "step": 103
+    },
+    {
+      "epoch": 8.71111111111111,
+      "grad_norm": 0.386259526014328,
+      "learning_rate": 4.99626950870707e-06,
+      "loss": 0.9617,
+      "step": 104
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 0.38413456082344055,
+      "learning_rate": 4.994171922976349e-06,
+      "loss": 0.9182,
+      "step": 105
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 0.4302501082420349,
+      "learning_rate": 4.991609004401324e-06,
+      "loss": 1.1561,
+      "step": 106
+    },
+    {
+      "epoch": 8.977777777777778,
+      "grad_norm": 0.4424130320549011,
+      "learning_rate": 4.988581231140772e-06,
+      "loss": 1.135,
+      "step": 107
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.3800254762172699,
+      "learning_rate": 4.985089168080509e-06,
+      "loss": 0.7612,
+      "step": 108
+    },
+    {
+      "epoch": 9.088888888888889,
+      "grad_norm": 0.46646955609321594,
+      "learning_rate": 4.981133466728004e-06,
+      "loss": 0.9991,
+      "step": 109
+    },
+    {
+      "epoch": 9.177777777777777,
+      "grad_norm": 0.4952200949192047,
+      "learning_rate": 4.976714865090827e-06,
+      "loss": 0.9779,
+      "step": 110
+    },
+    {
+      "epoch": 9.266666666666667,
+      "grad_norm": 0.4172927737236023,
+      "learning_rate": 4.971834187538963e-06,
+      "loss": 0.9449,
+      "step": 111
+    },
+    {
+      "epoch": 9.355555555555556,
+      "grad_norm": 0.4364710748195648,
+      "learning_rate": 4.966492344651006e-06,
+      "loss": 0.8786,
+      "step": 112
+    },
+    {
+      "epoch": 9.444444444444445,
+      "grad_norm": 0.4623521566390991,
+      "learning_rate": 4.960690333044279e-06,
+      "loss": 1.0798,
+      "step": 113
+    },
+    {
+      "epoch": 9.533333333333333,
+      "grad_norm": 0.4485428035259247,
+      "learning_rate": 4.954429235188897e-06,
+      "loss": 1.182,
+      "step": 114
+    },
+    {
+      "epoch": 9.622222222222222,
+      "grad_norm": 0.38542506098747253,
+      "learning_rate": 4.947710219205808e-06,
+      "loss": 0.9882,
+      "step": 115
+    },
+    {
+      "epoch": 9.71111111111111,
+      "grad_norm": 0.35373494029045105,
+      "learning_rate": 4.940534538648862e-06,
+      "loss": 0.9649,
+      "step": 116
+    },
+    {
+      "epoch": 9.8,
+      "grad_norm": 0.5160645246505737,
+      "learning_rate": 4.932903532270939e-06,
+      "loss": 1.0484,
+      "step": 117
+    },
+    {
+      "epoch": 9.88888888888889,
+      "grad_norm": 0.3412460684776306,
+      "learning_rate": 4.924818623774178e-06,
+      "loss": 0.8972,
+      "step": 118
+    },
+    {
+      "epoch": 9.977777777777778,
+      "grad_norm": 0.4623534083366394,
+      "learning_rate": 4.916281321544362e-06,
+      "loss": 0.9265,
+      "step": 119
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.4575502872467041,
+      "learning_rate": 4.907293218369499e-06,
+      "loss": 1.1764,
+      "step": 120
+    },
+    {
+      "epoch": 10.088888888888889,
+      "grad_norm": 0.4604892134666443,
+      "learning_rate": 4.897855991142658e-06,
+      "loss": 0.9429,
+      "step": 121
+    },
+    {
+      "epoch": 10.177777777777777,
+      "grad_norm": 0.4723954200744629,
+      "learning_rate": 4.8879714005491205e-06,
+      "loss": 1.0113,
+      "step": 122
+    },
+    {
+      "epoch": 10.266666666666667,
+      "grad_norm": 0.419286847114563,
+      "learning_rate": 4.8776412907378845e-06,
+      "loss": 1.0417,
+      "step": 123
+    },
+    {
+      "epoch": 10.355555555555556,
+      "grad_norm": 0.33823734521865845,
+      "learning_rate": 4.8668675889776095e-06,
+      "loss": 0.9355,
+      "step": 124
+    },
+    {
+      "epoch": 10.444444444444445,
+      "grad_norm": 0.5317716598510742,
+      "learning_rate": 4.855652305297052e-06,
+      "loss": 0.829,
+      "step": 125
+    },
+    {
+      "epoch": 10.533333333333333,
+      "grad_norm": 0.5897918343544006,
+      "learning_rate": 4.843997532110051e-06,
+      "loss": 1.003,
+      "step": 126
+    },
+    {
+      "epoch": 10.622222222222222,
+      "grad_norm": 0.4935283064842224,
+      "learning_rate": 4.83190544382516e-06,
+      "loss": 1.0789,
+      "step": 127
+    },
+    {
+      "epoch": 10.71111111111111,
+      "grad_norm": 0.575020432472229,
+      "learning_rate": 4.819378296439962e-06,
+      "loss": 1.0207,
+      "step": 128
+    },
+    {
+      "epoch": 10.8,
+      "grad_norm": 0.7120870351791382,
+      "learning_rate": 4.80641842712018e-06,
+      "loss": 0.8893,
+      "step": 129
+    },
+    {
+      "epoch": 10.88888888888889,
+      "grad_norm": 0.445549875497818,
+      "learning_rate": 4.793028253763633e-06,
+      "loss": 1.0629,
+      "step": 130
+    },
+    {
+      "epoch": 10.977777777777778,
+      "grad_norm": 0.372715026140213,
+      "learning_rate": 4.7792102745491345e-06,
+      "loss": 0.986,
+      "step": 131
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 0.6868900656700134,
+      "learning_rate": 4.764967067470409e-06,
+      "loss": 1.2309,
+      "step": 132
+    },
+    {
+      "epoch": 11.088888888888889,
+      "grad_norm": 0.47809746861457825,
+      "learning_rate": 4.750301289855128e-06,
+      "loss": 1.0157,
+      "step": 133
+    },
+    {
+      "epoch": 11.177777777777777,
+      "grad_norm": 0.4651176631450653,
+      "learning_rate": 4.735215677869129e-06,
+      "loss": 1.0521,
+      "step": 134
+    },
+    {
+      "epoch": 11.266666666666667,
+      "grad_norm": 0.4832024574279785,
+      "learning_rate": 4.7197130460059385e-06,
+      "loss": 0.861,
+      "step": 135
+    },
+    {
+      "epoch": 11.355555555555556,
+      "grad_norm": 0.508399486541748,
+      "learning_rate": 4.7037962865616795e-06,
+      "loss": 1.0256,
+      "step": 136
+    },
+    {
+      "epoch": 11.444444444444445,
+      "grad_norm": 0.5031757950782776,
+      "learning_rate": 4.687468369095457e-06,
+      "loss": 1.0302,
+      "step": 137
+    },
+    {
+      "epoch": 11.533333333333333,
+      "grad_norm": 0.4271880090236664,
+      "learning_rate": 4.6707323398753346e-06,
+      "loss": 0.9272,
+      "step": 138
+    },
+    {
+      "epoch": 11.622222222222222,
+      "grad_norm": 0.41679927706718445,
+      "learning_rate": 4.6535913213100005e-06,
+      "loss": 0.9849,
+      "step": 139
+    },
+    {
+      "epoch": 11.71111111111111,
+      "grad_norm": 0.4784274995326996,
+      "learning_rate": 4.636048511366222e-06,
+      "loss": 0.7549,
+      "step": 140
+    },
+    {
+      "epoch": 11.8,
+      "grad_norm": 0.5748984217643738,
+      "learning_rate": 4.618107182972209e-06,
+      "loss": 0.9387,
+      "step": 141
+    },
+    {
+      "epoch": 11.88888888888889,
+      "grad_norm": 0.5074996948242188,
+      "learning_rate": 4.599770683406992e-06,
+      "loss": 1.1931,
+      "step": 142
+    },
+    {
+      "epoch": 11.977777777777778,
+      "grad_norm": 0.46601927280426025,
+      "learning_rate": 4.58104243367592e-06,
+      "loss": 0.8533,
+      "step": 143
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.8853896260261536,
+      "learning_rate": 4.561925927872421e-06,
+      "loss": 1.2318,
+      "step": 144
+    },
+    {
+      "epoch": 12.088888888888889,
+      "grad_norm": 0.4770624041557312,
+      "learning_rate": 4.542424732526105e-06,
+      "loss": 0.877,
+      "step": 145
+    },
+    {
+      "epoch": 12.177777777777777,
+      "grad_norm": 0.5245800018310547,
+      "learning_rate": 4.522542485937369e-06,
+      "loss": 0.9198,
+      "step": 146
+    },
+    {
+      "epoch": 12.266666666666667,
+      "grad_norm": 0.8387463092803955,
+      "learning_rate": 4.5022828974986044e-06,
+      "loss": 0.9225,
+      "step": 147
+    },
+    {
+      "epoch": 12.355555555555556,
+      "grad_norm": 0.4439677596092224,
+      "learning_rate": 4.481649747002146e-06,
+      "loss": 1.0818,
+      "step": 148
+    },
+    {
+      "epoch": 12.444444444444445,
+      "grad_norm": 0.4621722996234894,
+      "learning_rate": 4.460646883935079e-06,
+      "loss": 0.9635,
+      "step": 149
+    },
+    {
+      "epoch": 12.533333333333333,
+      "grad_norm": 0.4656592607498169,
+      "learning_rate": 4.43927822676105e-06,
+      "loss": 0.8971,
+      "step": 150
+    },
+    {
+      "epoch": 12.622222222222222,
+      "grad_norm": 0.4961630702018738,
+      "learning_rate": 4.417547762189207e-06,
+      "loss": 0.9474,
+      "step": 151
+    },
+    {
+      "epoch": 12.71111111111111,
+      "grad_norm": 0.5954545736312866,
+      "learning_rate": 4.395459544430407e-06,
+      "loss": 1.0403,
+      "step": 152
+    },
+    {
+      "epoch": 12.8,
+      "grad_norm": 0.7063807249069214,
+      "learning_rate": 4.373017694440828e-06,
+      "loss": 1.0076,
+      "step": 153
+    },
+    {
+      "epoch": 12.88888888888889,
+      "grad_norm": 0.48963138461112976,
+      "learning_rate": 4.35022639915313e-06,
+      "loss": 0.9405,
+      "step": 154
+    },
+    {
+      "epoch": 12.977777777777778,
+      "grad_norm": 0.6047050952911377,
+      "learning_rate": 4.32708991069531e-06,
+      "loss": 0.9689,
+      "step": 155
+    },
+    {
+      "epoch": 13.0,
+      "grad_norm": 0.779731273651123,
+      "learning_rate": 4.30361254559739e-06,
+      "loss": 0.8877,
+      "step": 156
+    },
+    {
+      "epoch": 13.088888888888889,
+      "grad_norm": 0.6274661421775818,
+      "learning_rate": 4.279798683986084e-06,
+      "loss": 0.9697,
+      "step": 157
+    },
+    {
+      "epoch": 13.177777777777777,
+      "grad_norm": 0.5181424021720886,
+      "learning_rate": 4.255652768767619e-06,
+      "loss": 0.8949,
+      "step": 158
+    },
+    {
+      "epoch": 13.266666666666667,
+      "grad_norm": 0.4889301657676697,
+      "learning_rate": 4.2311793047988145e-06,
+      "loss": 0.941,
+      "step": 159
+    },
+    {
+      "epoch": 13.355555555555556,
+      "grad_norm": 0.5373956561088562,
+      "learning_rate": 4.206382858046636e-06,
+      "loss": 0.792,
+      "step": 160
+    },
+    {
+      "epoch": 13.444444444444445,
+      "grad_norm": 0.4251907765865326,
+      "learning_rate": 4.181268054736319e-06,
+      "loss": 0.9622,
+      "step": 161
+    },
+    {
+      "epoch": 13.533333333333333,
+      "grad_norm": 0.3853691518306732,
+      "learning_rate": 4.15583958048827e-06,
+      "loss": 0.8678,
+      "step": 162
+    },
+    {
+      "epoch": 13.622222222222222,
+      "grad_norm": 0.5543946027755737,
+      "learning_rate": 4.130102179443877e-06,
+      "loss": 0.8901,
+      "step": 163
+    },
+    {
+      "epoch": 13.71111111111111,
+      "grad_norm": 0.6818388104438782,
+      "learning_rate": 4.104060653380403e-06,
+      "loss": 0.9957,
+      "step": 164
+    },
+    {
+      "epoch": 13.8,
+      "grad_norm": 0.6395586729049683,
+      "learning_rate": 4.077719860815132e-06,
+      "loss": 1.0817,
+      "step": 165
+    },
+    {
+      "epoch": 13.88888888888889,
+      "grad_norm": 0.6789353489875793,
+      "learning_rate": 4.051084716098921e-06,
+      "loss": 1.1538,
+      "step": 166
+    },
+    {
+      "epoch": 13.977777777777778,
+      "grad_norm": 0.4569081664085388,
+      "learning_rate": 4.024160188499337e-06,
+      "loss": 0.9047,
+      "step": 167
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 1.7882684469223022,
+      "learning_rate": 3.996951301273556e-06,
+      "loss": 0.9499,
+      "step": 168
+    },
+    {
+      "epoch": 14.088888888888889,
+      "grad_norm": 0.6156724691390991,
+      "learning_rate": 3.969463130731183e-06,
+      "loss": 0.9101,
+      "step": 169
+    },
+    {
+      "epoch": 14.177777777777777,
+      "grad_norm": 0.5264705419540405,
+      "learning_rate": 3.941700805287169e-06,
+      "loss": 1.0762,
+      "step": 170
+    },
+    {
+      "epoch": 14.266666666666667,
+      "grad_norm": 0.5197077989578247,
+      "learning_rate": 3.913669504505015e-06,
+      "loss": 1.0859,
+      "step": 171
+    },
+    {
+      "epoch": 14.355555555555556,
+      "grad_norm": 0.5074746608734131,
+      "learning_rate": 3.8853744581304376e-06,
+      "loss": 0.8807,
+      "step": 172
+    },
+    {
+      "epoch": 14.444444444444445,
+      "grad_norm": 0.5885288119316101,
+      "learning_rate": 3.856820945115655e-06,
+      "loss": 0.7543,
+      "step": 173
+    },
+    {
+      "epoch": 14.533333333333333,
+      "grad_norm": 0.5903788805007935,
+      "learning_rate": 3.828014292634508e-06,
+      "loss": 0.8641,
+      "step": 174
+    },
+    {
+      "epoch": 14.622222222222222,
+      "grad_norm": 0.5170984268188477,
+      "learning_rate": 3.798959875088584e-06,
+      "loss": 0.8557,
+      "step": 175
+    },
+    {
+      "epoch": 14.71111111111111,
+      "grad_norm": 0.4823358356952667,
+      "learning_rate": 3.769663113104516e-06,
+      "loss": 0.8084,
+      "step": 176
+    },
+    {
+      "epoch": 14.8,
+      "grad_norm": 0.5628538131713867,
+      "learning_rate": 3.7401294725226707e-06,
+      "loss": 1.0103,
+      "step": 177
+    },
+    {
+      "epoch": 14.88888888888889,
+      "grad_norm": 0.575435221195221,
+      "learning_rate": 3.7103644633774015e-06,
+      "loss": 0.9011,
+      "step": 178
+    },
+    {
+      "epoch": 14.977777777777778,
+      "grad_norm": 0.7047615051269531,
+      "learning_rate": 3.680373638869047e-06,
+      "loss": 0.9671,
+      "step": 179
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.747231125831604,
+      "learning_rate": 3.650162594327881e-06,
+      "loss": 1.1957,
+      "step": 180
+    },
+    {
+      "epoch": 15.088888888888889,
+      "grad_norm": 0.6477513313293457,
+      "learning_rate": 3.6197369661702052e-06,
+      "loss": 1.0547,
+      "step": 181
+    },
+    {
+      "epoch": 15.177777777777777,
+      "grad_norm": 0.44793015718460083,
+      "learning_rate": 3.589102430846773e-06,
+      "loss": 0.8339,
+      "step": 182
+    },
+    {
+      "epoch": 15.266666666666667,
+      "grad_norm": 0.4845152199268341,
+      "learning_rate": 3.5582647037837446e-06,
+      "loss": 0.933,
+      "step": 183
+    },
+    {
+      "epoch": 15.355555555555556,
+      "grad_norm": 0.5620778203010559,
+      "learning_rate": 3.527229538316371e-06,
+      "loss": 0.8677,
+      "step": 184
+    },
+    {
+      "epoch": 15.444444444444445,
+      "grad_norm": 1.1254522800445557,
+      "learning_rate": 3.4960027246156043e-06,
+      "loss": 0.9953,
+      "step": 185
+    },
+    {
+      "epoch": 15.533333333333333,
+      "grad_norm": 0.5396095514297485,
+      "learning_rate": 3.4645900886078388e-06,
+      "loss": 0.9982,
+      "step": 186
+    },
+    {
+      "epoch": 15.622222222222222,
+      "grad_norm": 0.6709286570549011,
+      "learning_rate": 3.432997490887979e-06,
+      "loss": 0.8604,
+      "step": 187
+    },
+    {
+      "epoch": 15.71111111111111,
+      "grad_norm": 0.655689001083374,
+      "learning_rate": 3.4012308256260366e-06,
+      "loss": 0.7839,
+      "step": 188
+    },
+    {
+      "epoch": 15.8,
+      "grad_norm": 0.6764020323753357,
+      "learning_rate": 3.369296019467473e-06,
+      "loss": 0.8544,
+      "step": 189
+    },
+    {
+      "epoch": 15.88888888888889,
+      "grad_norm": 0.5892664194107056,
+      "learning_rate": 3.3371990304274654e-06,
+      "loss": 0.8877,
+      "step": 190
+    },
+    {
+      "epoch": 15.977777777777778,
+      "grad_norm": 0.5942324995994568,
+      "learning_rate": 3.304945846779346e-06,
+      "loss": 0.9024,
+      "step": 191
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 0.7737208008766174,
+      "learning_rate": 3.272542485937369e-06,
+      "loss": 1.1495,
+      "step": 192
+    },
+    {
+      "epoch": 16.08888888888889,
+      "grad_norm": 0.6798277497291565,
+      "learning_rate": 3.239994993334059e-06,
+      "loss": 0.9458,
+      "step": 193
+    },
+    {
+      "epoch": 16.177777777777777,
+      "grad_norm": 0.5800243020057678,
+      "learning_rate": 3.207309441292325e-06,
+      "loss": 0.881,
+      "step": 194
+    },
+    {
+      "epoch": 16.266666666666666,
+      "grad_norm": 0.626613438129425,
+      "learning_rate": 3.174491927892561e-06,
+      "loss": 0.9062,
+      "step": 195
+    },
+    {
+      "epoch": 16.355555555555554,
+      "grad_norm": 0.6165486574172974,
+      "learning_rate": 3.1415485758349344e-06,
+      "loss": 1.002,
+      "step": 196
+    },
+    {
+      "epoch": 16.444444444444443,
+      "grad_norm": 0.6354159116744995,
+      "learning_rate": 3.1084855312970897e-06,
+      "loss": 0.9224,
+      "step": 197
+    },
+    {
+      "epoch": 16.533333333333335,
+      "grad_norm": 0.6106343865394592,
+      "learning_rate": 3.0753089627874668e-06,
+      "loss": 0.8111,
+      "step": 198
+    },
+    {
+      "epoch": 16.622222222222224,
+      "grad_norm": 0.5856066346168518,
+      "learning_rate": 3.0420250599944525e-06,
+      "loss": 1.1155,
+      "step": 199
+    },
+    {
+      "epoch": 16.711111111111112,
+      "grad_norm": 0.6578230857849121,
+      "learning_rate": 3.0086400326315853e-06,
+      "loss": 0.7782,
+      "step": 200
+    },
+    {
+      "epoch": 16.8,
+      "grad_norm": 0.5129030346870422,
+      "learning_rate": 2.9751601092790185e-06,
+      "loss": 0.8999,
+      "step": 201
+    },
+    {
+      "epoch": 16.88888888888889,
+      "grad_norm": 0.5636340975761414,
+      "learning_rate": 2.941591536221469e-06,
+      "loss": 0.8363,
+      "step": 202
+    },
+    {
+      "epoch": 16.977777777777778,
+      "grad_norm": 0.6733406186103821,
+      "learning_rate": 2.907940576282856e-06,
+      "loss": 0.8183,
+      "step": 203
+    },
+    {
+      "epoch": 17.0,
+      "grad_norm": 1.0829391479492188,
+      "learning_rate": 2.8742135076578608e-06,
+      "loss": 1.1636,
+      "step": 204
+    },
+    {
+      "epoch": 17.08888888888889,
+      "grad_norm": 0.5469006299972534,
+      "learning_rate": 2.840416622740617e-06,
+      "loss": 0.8142,
+      "step": 205
+    },
+    {
+      "epoch": 17.177777777777777,
+      "grad_norm": 0.6195508241653442,
+      "learning_rate": 2.8065562269507464e-06,
+      "loss": 0.8903,
+      "step": 206
+    },
+    {
+      "epoch": 17.266666666666666,
+      "grad_norm": 0.5448200702667236,
+      "learning_rate": 2.7726386375569748e-06,
+      "loss": 0.9834,
+      "step": 207
+    },
+    {
+      "epoch": 17.355555555555554,
+      "grad_norm": 0.667235791683197,
+      "learning_rate": 2.7386701824985257e-06,
+      "loss": 0.6709,
+      "step": 208
+    },
+    {
+      "epoch": 17.444444444444443,
+      "grad_norm": 0.48227953910827637,
+      "learning_rate": 2.7046571992045334e-06,
+      "loss": 0.8927,
+      "step": 209
+    },
+    {
+      "epoch": 17.533333333333335,
+      "grad_norm": 1.3036866188049316,
+      "learning_rate": 2.670606033411678e-06,
+      "loss": 0.9977,
+      "step": 210
+    },
+    {
+      "epoch": 17.622222222222224,
+      "grad_norm": 0.7368432879447937,
+      "learning_rate": 2.636523037980275e-06,
+      "loss": 0.9036,
+      "step": 211
+    },
+    {
+      "epoch": 17.711111111111112,
+      "grad_norm": 0.49763280153274536,
+      "learning_rate": 2.602414571709036e-06,
+      "loss": 0.9087,
+      "step": 212
+    },
+    {
+      "epoch": 17.8,
+      "grad_norm": 0.7820340394973755,
+      "learning_rate": 2.5682869981487154e-06,
+      "loss": 0.9693,
+      "step": 213
+    },
+    {
+      "epoch": 17.88888888888889,
+      "grad_norm": 0.6577602624893188,
+      "learning_rate": 2.5341466844148775e-06,
+      "loss": 0.8481,
+      "step": 214
+    },
+    {
+      "epoch": 17.977777777777778,
+      "grad_norm": 0.8875017166137695,
+      "learning_rate": 2.5e-06,
+      "loss": 1.0045,
+      "step": 215
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 2.128192663192749,
+      "learning_rate": 2.465853315585123e-06,
+      "loss": 1.0231,
+      "step": 216
+    },
+    {
+      "epoch": 18.08888888888889,
+      "grad_norm": 0.5647242665290833,
+      "learning_rate": 2.431713001851286e-06,
+      "loss": 0.8498,
+      "step": 217
+    },
+    {
+      "epoch": 18.177777777777777,
+      "grad_norm": 0.6913108825683594,
+      "learning_rate": 2.3975854282909645e-06,
+      "loss": 1.0558,
+      "step": 218
+    },
+    {
+      "epoch": 18.266666666666666,
+      "grad_norm": 0.5946425795555115,
+      "learning_rate": 2.3634769620197253e-06,
+      "loss": 0.8356,
+      "step": 219
+    },
+    {
+      "epoch": 18.355555555555554,
+      "grad_norm": 0.9023786187171936,
+      "learning_rate": 2.3293939665883233e-06,
+      "loss": 0.959,
+      "step": 220
+    },
+    {
+      "epoch": 18.444444444444443,
+      "grad_norm": 0.6683367490768433,
+      "learning_rate": 2.2953428007954682e-06,
+      "loss": 0.7641,
+      "step": 221
+    },
+    {
+      "epoch": 18.533333333333335,
+      "grad_norm": 0.7781148552894592,
+      "learning_rate": 2.261329817501475e-06,
+      "loss": 0.9507,
+      "step": 222
+    },
+    {
+      "epoch": 18.622222222222224,
+      "grad_norm": 0.5396183133125305,
+      "learning_rate": 2.2273613624430256e-06,
+      "loss": 0.9078,
+      "step": 223
+    },
+    {
+      "epoch": 18.711111111111112,
+      "grad_norm": 0.6765702962875366,
+      "learning_rate": 2.1934437730492544e-06,
+      "loss": 0.8616,
+      "step": 224
+    },
+    {
+      "epoch": 18.8,
+      "grad_norm": 0.6181918978691101,
+      "learning_rate": 2.159583377259384e-06,
+      "loss": 0.7377,
+      "step": 225
+    },
+    {
+      "epoch": 18.88888888888889,
+      "grad_norm": 0.7162302732467651,
+      "learning_rate": 2.1257864923421405e-06,
+      "loss": 0.9405,
+      "step": 226
+    },
+    {
+      "epoch": 18.977777777777778,
+      "grad_norm": 0.6811490654945374,
+      "learning_rate": 2.092059423717145e-06,
+      "loss": 0.874,
+      "step": 227
+    },
+    {
+      "epoch": 19.0,
+      "grad_norm": 0.6545157432556152,
+      "learning_rate": 2.0584084637785316e-06,
+      "loss": 0.6244,
+      "step": 228
+    },
+    {
+      "epoch": 19.08888888888889,
+      "grad_norm": 0.5392009615898132,
+      "learning_rate": 2.0248398907209827e-06,
+      "loss": 0.8523,
+      "step": 229
+    },
+    {
+      "epoch": 19.177777777777777,
+      "grad_norm": 0.5963950157165527,
+      "learning_rate": 1.991359967368416e-06,
+      "loss": 0.6882,
+      "step": 230
+    },
+    {
+      "epoch": 19.266666666666666,
+      "grad_norm": 0.6452714204788208,
+      "learning_rate": 1.957974940005548e-06,
+      "loss": 0.7386,
+      "step": 231
+    },
+    {
+      "epoch": 19.355555555555554,
+      "grad_norm": 0.6710150241851807,
+      "learning_rate": 1.9246910372125345e-06,
+      "loss": 0.9825,
+      "step": 232
+    },
+    {
+      "epoch": 19.444444444444443,
+      "grad_norm": 0.5551663637161255,
+      "learning_rate": 1.8915144687029107e-06,
+      "loss": 0.9288,
+      "step": 233
+    },
+    {
+      "epoch": 19.533333333333335,
+      "grad_norm": 0.7859821319580078,
+      "learning_rate": 1.8584514241650667e-06,
+      "loss": 1.0302,
+      "step": 234
+    },
+    {
+      "epoch": 19.622222222222224,
+      "grad_norm": 0.580791175365448,
+      "learning_rate": 1.8255080721074391e-06,
+      "loss": 0.9244,
+      "step": 235
+    },
+    {
+      "epoch": 19.711111111111112,
+      "grad_norm": 0.7111539244651794,
+      "learning_rate": 1.792690558707675e-06,
+      "loss": 0.8465,
+      "step": 236
+    },
+    {
+      "epoch": 19.8,
+      "grad_norm": 0.8440479636192322,
+      "learning_rate": 1.7600050066659418e-06,
+      "loss": 0.9308,
+      "step": 237
+    },
+    {
+      "epoch": 19.88888888888889,
+      "grad_norm": 0.7431160807609558,
+      "learning_rate": 1.7274575140626318e-06,
+      "loss": 0.9417,
+      "step": 238
+    },
+    {
+      "epoch": 19.977777777777778,
+      "grad_norm": 0.8644082546234131,
+      "learning_rate": 1.695054153220655e-06,
+      "loss": 0.8363,
+      "step": 239
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.8472647666931152,
+      "learning_rate": 1.6628009695725348e-06,
+      "loss": 0.5418,
+      "step": 240
+    },
+    {
+      "epoch": 20.08888888888889,
+      "grad_norm": 0.8104817867279053,
+      "learning_rate": 1.630703980532528e-06,
+      "loss": 0.7425,
+      "step": 241
+    },
+    {
+      "epoch": 20.177777777777777,
+      "grad_norm": 0.6427087187767029,
+      "learning_rate": 1.5987691743739636e-06,
+      "loss": 0.7761,
+      "step": 242
+    },
+    {
+      "epoch": 20.266666666666666,
+      "grad_norm": 0.8927726745605469,
+      "learning_rate": 1.5670025091120219e-06,
+      "loss": 0.8807,
+      "step": 243
+    },
+    {
+      "epoch": 20.355555555555554,
+      "grad_norm": 0.5097454786300659,
+      "learning_rate": 1.5354099113921614e-06,
+      "loss": 0.875,
+      "step": 244
+    },
+    {
+      "epoch": 20.444444444444443,
+      "grad_norm": 0.5797455310821533,
+      "learning_rate": 1.5039972753843966e-06,
+      "loss": 0.8312,
+      "step": 245
+    },
+    {
+      "epoch": 20.533333333333335,
+      "grad_norm": 0.7658204436302185,
+      "learning_rate": 1.4727704616836297e-06,
+      "loss": 0.8858,
+      "step": 246
+    },
+    {
+      "epoch": 20.622222222222224,
+      "grad_norm": 0.7070634365081787,
+      "learning_rate": 1.441735296216256e-06,
+      "loss": 0.9683,
+      "step": 247
+    },
+    {
+      "epoch": 20.711111111111112,
+      "grad_norm": 0.5789161920547485,
+      "learning_rate": 1.4108975691532273e-06,
+      "loss": 0.9102,
+      "step": 248
+    },
+    {
+      "epoch": 20.8,
+      "grad_norm": 0.8189324736595154,
+      "learning_rate": 1.3802630338297956e-06,
+      "loss": 0.96,
+      "step": 249
+    },
+    {
+      "epoch": 20.88888888888889,
+      "grad_norm": 0.7410324215888977,
+      "learning_rate": 1.3498374056721198e-06,
+      "loss": 0.9536,
+      "step": 250
+    },
+    {
+      "epoch": 20.977777777777778,
+      "grad_norm": 0.9396767616271973,
+      "learning_rate": 1.3196263611309539e-06,
+      "loss": 0.8433,
+      "step": 251
+    },
+    {
+      "epoch": 21.0,
+      "grad_norm": 0.7975627779960632,
+      "learning_rate": 1.2896355366226e-06,
+      "loss": 0.4761,
+      "step": 252
+    },
+    {
+      "epoch": 21.08888888888889,
+      "grad_norm": 0.7357563972473145,
+      "learning_rate": 1.2598705274773299e-06,
+      "loss": 0.8871,
+      "step": 253
+    },
+    {
+      "epoch": 21.177777777777777,
+      "grad_norm": 0.7067966461181641,
+      "learning_rate": 1.2303368868954848e-06,
+      "loss": 0.773,
+      "step": 254
+    },
+    {
+      "epoch": 21.266666666666666,
+      "grad_norm": 0.593105137348175,
+      "learning_rate": 1.2010401249114166e-06,
+      "loss": 0.8273,
+      "step": 255
+    },
+    {
+      "epoch": 21.355555555555554,
+      "grad_norm": 0.707051157951355,
+      "learning_rate": 1.1719857073654923e-06,
+      "loss": 0.8088,
+      "step": 256
+    },
+    {
+      "epoch": 21.444444444444443,
+      "grad_norm": 0.7845866084098816,
+      "learning_rate": 1.1431790548843464e-06,
+      "loss": 0.9616,
+      "step": 257
+    },
+    {
+      "epoch": 21.533333333333335,
+      "grad_norm": 0.481231689453125,
+      "learning_rate": 1.1146255418695635e-06,
+      "loss": 0.8371,
+      "step": 258
+    },
+    {
+      "epoch": 21.622222222222224,
+      "grad_norm": 1.1225308179855347,
+      "learning_rate": 1.0863304954949856e-06,
+      "loss": 0.802,
+      "step": 259
+    },
+    {
+      "epoch": 21.711111111111112,
+      "grad_norm": 0.6318144798278809,
+      "learning_rate": 1.0582991947128324e-06,
+      "loss": 0.8741,
+      "step": 260
+    },
+    {
+      "epoch": 21.8,
+      "grad_norm": 0.7717880010604858,
+      "learning_rate": 1.0305368692688175e-06,
+      "loss": 0.7535,
+      "step": 261
+    },
+    {
+      "epoch": 21.88888888888889,
+      "grad_norm": 0.6893540024757385,
+      "learning_rate": 1.0030486987264436e-06,
+      "loss": 0.894,
+      "step": 262
+    },
+    {
+      "epoch": 21.977777777777778,
+      "grad_norm": 0.6379507184028625,
+      "learning_rate": 9.758398115006637e-07,
+      "loss": 0.9623,
+      "step": 263
+    },
+    {
+      "epoch": 22.0,
+      "grad_norm": 0.9665340781211853,
+      "learning_rate": 9.489152839010799e-07,
+      "loss": 0.9206,
+      "step": 264
+    },
+    {
+      "epoch": 22.08888888888889,
+      "grad_norm": 0.6625165343284607,
+      "learning_rate": 9.222801391848688e-07,
+      "loss": 0.696,
+      "step": 265
+    },
+    {
+      "epoch": 22.177777777777777,
+      "grad_norm": 0.6619503498077393,
+      "learning_rate": 8.959393466195973e-07,
+      "loss": 0.8825,
+      "step": 266
+    },
+    {
+      "epoch": 22.266666666666666,
+      "grad_norm": 0.5958104133605957,
+      "learning_rate": 8.69897820556124e-07,
+      "loss": 0.9445,
+      "step": 267
+    },
+    {
+      "epoch": 22.355555555555554,
+      "grad_norm": 0.7491523027420044,
+      "learning_rate": 8.441604195117315e-07,
+      "loss": 0.8024,
+      "step": 268
+    },
+    {
+      "epoch": 22.444444444444443,
+      "grad_norm": 0.6927403211593628,
+      "learning_rate": 8.187319452636821e-07,
+      "loss": 0.7532,
+      "step": 269
+    },
+    {
+      "epoch": 22.533333333333335,
+      "grad_norm": 0.7777316570281982,
+      "learning_rate": 7.936171419533653e-07,
+      "loss": 0.949,
+      "step": 270
+    },
+    {
+      "epoch": 22.622222222222224,
+      "grad_norm": 0.5703297257423401,
+      "learning_rate": 7.688206952011862e-07,
+      "loss": 0.7882,
+      "step": 271
+    },
+    {
+      "epoch": 22.711111111111112,
+      "grad_norm": 0.717693030834198,
+      "learning_rate": 7.443472312323824e-07,
+      "loss": 0.7254,
+      "step": 272
+    },
+    {
+      "epoch": 22.8,
+      "grad_norm": 0.6906650066375732,
+      "learning_rate": 7.202013160139159e-07,
+      "loss": 1.1334,
+      "step": 273
+    },
+    {
+      "epoch": 22.88888888888889,
+      "grad_norm": 0.7221674919128418,
+      "learning_rate": 6.963874544026109e-07,
+      "loss": 0.7708,
+      "step": 274
+    },
+    {
+      "epoch": 22.977777777777778,
+      "grad_norm": 0.7417134642601013,
+      "learning_rate": 6.729100893046897e-07,
+      "loss": 0.8617,
+      "step": 275
+    },
+    {
+      "epoch": 23.0,
+      "grad_norm": 0.7064130306243896,
+      "learning_rate": 6.497736008468703e-07,
+      "loss": 0.7606,
+      "step": 276
+    },
+    {
+      "epoch": 23.08888888888889,
+      "grad_norm": 0.741130530834198,
+      "learning_rate": 6.269823055591726e-07,
+      "loss": 0.7765,
+      "step": 277
+    },
+    {
+      "epoch": 23.177777777777777,
+      "grad_norm": 1.3605138063430786,
+      "learning_rate": 6.045404555695935e-07,
+      "loss": 0.907,
+      "step": 278
+    },
+    {
+      "epoch": 23.266666666666666,
+      "grad_norm": 0.6725257635116577,
+      "learning_rate": 5.824522378107936e-07,
+      "loss": 1.0291,
+      "step": 279
+    },
+    {
+      "epoch": 23.355555555555554,
+      "grad_norm": 0.5731009840965271,
+      "learning_rate": 5.607217732389503e-07,
+      "loss": 0.8876,
+      "step": 280
+    },
+    {
+      "epoch": 23.444444444444443,
+      "grad_norm": 0.8626798391342163,
+      "learning_rate": 5.393531160649221e-07,
+      "loss": 0.9152,
+      "step": 281
+    },
+    {
+      "epoch": 23.533333333333335,
+      "grad_norm": 0.6386983394622803,
+      "learning_rate": 5.183502529978548e-07,
+      "loss": 0.9826,
+      "step": 282
+    },
+    {
+      "epoch": 23.622222222222224,
+      "grad_norm": 0.9047194719314575,
+      "learning_rate": 4.977171025013961e-07,
+      "loss": 0.7636,
+      "step": 283
+    },
+    {
+      "epoch": 23.711111111111112,
+      "grad_norm": 0.671303927898407,
+      "learning_rate": 4.774575140626317e-07,
+      "loss": 0.6843,
+      "step": 284
+    },
+    {
+      "epoch": 23.8,
+      "grad_norm": 0.5185788869857788,
+      "learning_rate": 4.5757526747389506e-07,
+      "loss": 0.8194,
+      "step": 285
+    },
+    {
+      "epoch": 23.88888888888889,
+      "grad_norm": 0.673641562461853,
+      "learning_rate": 4.380740721275786e-07,
+      "loss": 0.8164,
+      "step": 286
+    },
+    {
+      "epoch": 23.977777777777778,
+      "grad_norm": 0.7130348086357117,
+      "learning_rate": 4.189575663240794e-07,
+      "loss": 0.7278,
+      "step": 287
+    },
+    {
+      "epoch": 24.0,
+      "grad_norm": 0.894011914730072,
+      "learning_rate": 4.002293165930088e-07,
+      "loss": 0.7292,
+      "step": 288
+    },
+    {
+      "epoch": 24.08888888888889,
+      "grad_norm": 0.7084284424781799,
+      "learning_rate": 3.818928170277911e-07,
+      "loss": 0.6609,
+      "step": 289
+    },
+    {
+      "epoch": 24.177777777777777,
+      "grad_norm": 0.7356826066970825,
+      "learning_rate": 3.639514886337786e-07,
+      "loss": 0.8054,
+      "step": 290
+    },
+    {
+      "epoch": 24.266666666666666,
+      "grad_norm": 0.6582125425338745,
+      "learning_rate": 3.4640867869000036e-07,
+      "loss": 0.869,
+      "step": 291
+    },
+    {
+      "epoch": 24.355555555555554,
+      "grad_norm": 0.6234636306762695,
+      "learning_rate": 3.292676601246661e-07,
+      "loss": 1.0296,
+      "step": 292
+    },
+    {
+      "epoch": 24.444444444444443,
+      "grad_norm": 1.0210919380187988,
+      "learning_rate": 3.125316309045434e-07,
+      "loss": 0.9983,
+      "step": 293
+    },
+    {
+      "epoch": 24.533333333333335,
+      "grad_norm": 0.5547788143157959,
+      "learning_rate": 2.962037134383211e-07,
+      "loss": 0.8998,
+      "step": 294
+    },
+    {
+      "epoch": 24.622222222222224,
+      "grad_norm": 0.6771321296691895,
+      "learning_rate": 2.80286953994062e-07,
+      "loss": 0.805,
+      "step": 295
+    },
+    {
+      "epoch": 24.711111111111112,
+      "grad_norm": 0.6345370411872864,
+      "learning_rate": 2.647843221308721e-07,
+      "loss": 0.6883,
+      "step": 296
+    },
+    {
+      "epoch": 24.8,
+      "grad_norm": 0.6311068534851074,
+      "learning_rate": 2.496987101448728e-07,
+      "loss": 0.8913,
+      "step": 297
+    },
+    {
+      "epoch": 24.88888888888889,
+      "grad_norm": 0.7895520925521851,
+      "learning_rate": 2.3503293252959136e-07,
+      "loss": 0.938,
+      "step": 298
+    },
+    {
+      "epoch": 24.977777777777778,
+      "grad_norm": 0.7793102860450745,
+      "learning_rate": 2.2078972545086647e-07,
+      "loss": 0.8841,
+      "step": 299
+    },
+    {
+      "epoch": 25.0,
+      "grad_norm": 0.6420133709907532,
+      "learning_rate": 2.0697174623636795e-07,
+      "loss": 0.556,
+      "step": 300
+    },
+    {
+      "epoch": 25.08888888888889,
+      "grad_norm": 0.6089626550674438,
+      "learning_rate": 1.9358157287982099e-07,
+      "loss": 0.8709,
+      "step": 301
+    },
+    {
+      "epoch": 25.177777777777777,
+      "grad_norm": 1.60710871219635,
+      "learning_rate": 1.8062170356003854e-07,
+      "loss": 0.6853,
+      "step": 302
+    },
+    {
+      "epoch": 25.266666666666666,
+      "grad_norm": 0.678098738193512,
+      "learning_rate": 1.680945561748412e-07,
+      "loss": 0.995,
+      "step": 303
+    },
+    {
+      "epoch": 25.355555555555554,
+      "grad_norm": 0.5670207738876343,
+      "learning_rate": 1.5600246788994938e-07,
+      "loss": 0.8167,
+      "step": 304
+    },
+    {
+      "epoch": 25.444444444444443,
+      "grad_norm": 0.6996327638626099,
+      "learning_rate": 1.44347694702949e-07,
+      "loss": 0.9414,
+      "step": 305
+    },
+    {
+      "epoch": 25.533333333333335,
+      "grad_norm": 0.7256758213043213,
+      "learning_rate": 1.3313241102239056e-07,
+      "loss": 0.9439,
+      "step": 306
+    },
+    {
+      "epoch": 25.622222222222224,
+      "grad_norm": 0.5879709124565125,
+      "learning_rate": 1.223587092621162e-07,
+      "loss": 0.6697,
+      "step": 307
+    },
+    {
+      "epoch": 25.711111111111112,
+      "grad_norm": 0.7841221690177917,
+      "learning_rate": 1.120285994508799e-07,
+      "loss": 0.9173,
+      "step": 308
+    },
+    {
+      "epoch": 25.8,
+      "grad_norm": 0.6498060822486877,
+      "learning_rate": 1.0214400885734194e-07,
+      "loss": 0.8086,
+      "step": 309
+    },
+    {
+      "epoch": 25.88888888888889,
+      "grad_norm": 0.740508496761322,
+      "learning_rate": 9.270678163050218e-08,
+      "loss": 0.8424,
+      "step": 310
+    },
+    {
+      "epoch": 25.977777777777778,
+      "grad_norm": 0.6314177513122559,
+      "learning_rate": 8.371867845563819e-08,
+      "loss": 0.8007,
+      "step": 311
+    },
+    {
+      "epoch": 26.0,
+      "grad_norm": 0.8741561770439148,
+      "learning_rate": 7.518137622582189e-08,
+      "loss": 0.8582,
+      "step": 312
+    },
+    {
+      "epoch": 26.08888888888889,
+      "grad_norm": 0.7642889022827148,
+      "learning_rate": 6.70964677290617e-08,
+      "loss": 0.767,
+      "step": 313
+    },
+    {
+      "epoch": 26.177777777777777,
+      "grad_norm": 0.5676147937774658,
+      "learning_rate": 5.946546135113862e-08,
+      "loss": 0.8953,
+      "step": 314
+    },
+    {
+      "epoch": 26.266666666666666,
+      "grad_norm": 0.6517917513847351,
+      "learning_rate": 5.2289780794192726e-08,
+      "loss": 0.7334,
+      "step": 315
+    },
+    {
+      "epoch": 26.355555555555554,
+      "grad_norm": 0.8068559169769287,
+      "learning_rate": 4.557076481110367e-08,
+      "loss": 0.9373,
+      "step": 316
+    },
+    {
+      "epoch": 26.444444444444443,
+      "grad_norm": 0.5517790913581848,
+      "learning_rate": 3.930966695572136e-08,
+      "loss": 0.884,
+      "step": 317
+    },
+    {
+      "epoch": 26.533333333333335,
+      "grad_norm": 0.6840013861656189,
+      "learning_rate": 3.3507655348995194e-08,
+      "loss": 0.7411,
+      "step": 318
+    },
+    {
+      "epoch": 26.622222222222224,
+      "grad_norm": 1.3431508541107178,
+      "learning_rate": 2.8165812461038166e-08,
+      "loss": 0.7748,
+      "step": 319
+    },
+    {
+      "epoch": 26.711111111111112,
+      "grad_norm": 0.7526693940162659,
+      "learning_rate": 2.3285134909173113e-08,
+      "loss": 0.8678,
+      "step": 320
+    },
+    {
+      "epoch": 26.8,
+      "grad_norm": 0.7261110544204712,
+      "learning_rate": 1.886653327199617e-08,
+      "loss": 0.8908,
+      "step": 321
+    },
+    {
+      "epoch": 26.88888888888889,
+      "grad_norm": 0.6295614242553711,
+      "learning_rate": 1.4910831919490997e-08,
+      "loss": 0.8878,
+      "step": 322
+    },
+    {
+      "epoch": 26.977777777777778,
+      "grad_norm": 0.8621529936790466,
+      "learning_rate": 1.1418768859227935e-08,
+      "loss": 0.895,
+      "step": 323
+    },
+    {
+      "epoch": 27.0,
+      "grad_norm": 0.7991691827774048,
+      "learning_rate": 8.390995598676067e-09,
+      "loss": 0.802,
+      "step": 324
+    },
+    {
+      "epoch": 27.08888888888889,
+      "grad_norm": 0.551089882850647,
+      "learning_rate": 5.828077023651846e-09,
+      "loss": 0.6027,
+      "step": 325
+    },
+    {
+      "epoch": 27.177777777777777,
+      "grad_norm": 0.6393262147903442,
+      "learning_rate": 3.730491292930072e-09,
+      "loss": 0.7449,
+      "step": 326
+    },
+    {
+      "epoch": 27.266666666666666,
+      "grad_norm": 0.7486969232559204,
+      "learning_rate": 2.0986297490338536e-09,
+      "loss": 0.9378,
+      "step": 327
+    },
+    {
+      "epoch": 27.355555555555554,
+      "grad_norm": 0.5878354907035828,
+      "learning_rate": 9.32796845223294e-10,
+      "loss": 0.8487,
+      "step": 328
+    },
+    {
+      "epoch": 27.444444444444443,
+      "grad_norm": 0.7258017659187317,
+      "learning_rate": 2.3321008869481296e-10,
+      "loss": 0.9618,
+      "step": 329
+    },
+    {
+      "epoch": 27.533333333333335,
+      "grad_norm": 0.6953983902931213,
+      "learning_rate": 0.0,
+      "loss": 1.0057,
+      "step": 330
+    },
+    {
+      "epoch": 27.533333333333335,
+      "step": 330,
+      "total_flos": 1.1131745240245862e+17,
+      "train_loss": 0.9375696651863329,
+      "train_runtime": 851.6955,
+      "train_samples_per_second": 6.34,
+      "train_steps_per_second": 0.387
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 330,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1131745240245862e+17,
+  "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 sha256:74c6e9337569ab897f68ed8f72668ff4adcd96380dade86a6035389284287720
+size 5624