Add files using upload-large-folder tool

.gitattributes

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

README.md

@@ -0,0 +1,66 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2.5-32B-Instruct
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: MATH_training_response_Qwen2.5_32B
+  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. -->
+
+# MATH_training_response_Qwen2.5_32B
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) on the MATH_training_response_Qwen2.5_32B dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0296
+
+## 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 4
+- total_eval_batch_size: 4
+- 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_ratio: 0.1
+- num_epochs: 2.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.0258        | 1.5038 | 200  | 0.0297          |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.46.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-32B-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",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "up_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 sha256:6219e9a63ad5f05268ce26d51bacc4012cebe9edc72a7512d663031a71ab59a4
+size 134337704

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 +1,12 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.029648179188370705,
+    "eval_runtime": 6.4826,
+    "eval_samples_per_second": 0.926,
+    "eval_steps_per_second": 0.309,
+    "total_flos": 673614818967552.0,
+    "train_loss": 0.039493271835932604,
+    "train_runtime": 2026.6163,
+    "train_samples_per_second": 0.522,
+    "train_steps_per_second": 0.131
+}

checkpoint-266/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-32B-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-266/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-32B-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",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-266/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6219e9a63ad5f05268ce26d51bacc4012cebe9edc72a7512d663031a71ab59a4
+size 134337704

checkpoint-266/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-266/global_step266/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b130e5262b172aeddd48022a5dc081acbef2d7631c6bc7287dfe2d653f3f81f
+size 201330416

checkpoint-266/global_step266/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eaeca8e30bdbd76f3da7676f14d7b5f4bf9b40db7aa75cb740993bd7a7e4a5a
+size 201330416

checkpoint-266/global_step266/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d127eb07f96623a39b3913d624a877da068d63f47ec47f7395786ecd3fb52a69
+size 201330416

checkpoint-266/global_step266/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:133bff1007d33c4aad62619eaa9d0b16e6862a5e38b4bd26281b8c5a122b286a
+size 201330416

checkpoint-266/global_step266/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16b58e7ac09bf6383a946bbea6cfa00458f662c2c7fa7a19ae7e1faefe73fb4a
+size 890990

checkpoint-266/global_step266/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b819168dcf9c095b589be291321612e12e7e4031a024866eace73a8e7f895450
+size 890990

checkpoint-266/global_step266/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2276b369a601b00d89276dd1380626387021362527de4bfbaedd3c84797d0a2
+size 890990

checkpoint-266/global_step266/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b384caae261db631be7509bfd26514d4f685dd5ae6b30bef44ac3647300fa9fd
+size 890990

checkpoint-266/latest

@@ -0,0 +1 @@
+global_step266

checkpoint-266/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:308f94f9a5c24e1bad5c393d56ae7af7782600f4e791d9c6ac35b22fff2105b6
+size 15024

checkpoint-266/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b056f3c23cb32dc77a2ec9e7651e0b64e4440e21f0fdf969b86bfc56a1cbdf06
+size 15024

checkpoint-266/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3f8a05714bc528f4885a2816181652f2303b3e8150f89b56aaee6bec56aa520
+size 15024

checkpoint-266/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f755bd3c330281961e5c03af9d10ce8c1e1678619d384f6f1fd5fd7dce2ff50
+size 15024

checkpoint-266/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf4da5bd6a6ee404b7afdcdde78eaa3c48c2bdac694e70095236c413424be5b9
+size 1064

checkpoint-266/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-266/tokenizer.json

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

checkpoint-266/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-266/trainer_state.json

@@ -0,0 +1,1903 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 200,
+  "global_step": 266,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007518796992481203,
+      "grad_norm": 0.08289683091006875,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 0.2087,
+      "step": 1
+    },
+    {
+      "epoch": 0.015037593984962405,
+      "grad_norm": 0.03030546873337256,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.1045,
+      "step": 2
+    },
+    {
+      "epoch": 0.022556390977443608,
+      "grad_norm": 0.04340875250649354,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 0.1291,
+      "step": 3
+    },
+    {
+      "epoch": 0.03007518796992481,
+      "grad_norm": 0.04223285184390201,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 0.1263,
+      "step": 4
+    },
+    {
+      "epoch": 0.03759398496240601,
+      "grad_norm": 0.04894801143939966,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 0.1409,
+      "step": 5
+    },
+    {
+      "epoch": 0.045112781954887216,
+      "grad_norm": 0.22261274174154347,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.2362,
+      "step": 6
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 0.043978295203653116,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 0.1195,
+      "step": 7
+    },
+    {
+      "epoch": 0.06015037593984962,
+      "grad_norm": 0.04381964595602848,
+      "learning_rate": 2.962962962962963e-05,
+      "loss": 0.1215,
+      "step": 8
+    },
+    {
+      "epoch": 0.06766917293233082,
+      "grad_norm": 0.03290036083527209,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.0881,
+      "step": 9
+    },
+    {
+      "epoch": 0.07518796992481203,
+      "grad_norm": 0.03303553719000837,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.0923,
+      "step": 10
+    },
+    {
+      "epoch": 0.08270676691729323,
+      "grad_norm": 0.12832751130733108,
+      "learning_rate": 4.074074074074074e-05,
+      "loss": 0.218,
+      "step": 11
+    },
+    {
+      "epoch": 0.09022556390977443,
+      "grad_norm": 0.08479076437214379,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.149,
+      "step": 12
+    },
+    {
+      "epoch": 0.09774436090225563,
+      "grad_norm": 0.13534422076541278,
+      "learning_rate": 4.814814814814815e-05,
+      "loss": 0.1835,
+      "step": 13
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 0.10341781138952844,
+      "learning_rate": 5.185185185185185e-05,
+      "loss": 0.1573,
+      "step": 14
+    },
+    {
+      "epoch": 0.11278195488721804,
+      "grad_norm": 0.12256701286625035,
+      "learning_rate": 5.555555555555556e-05,
+      "loss": 0.1701,
+      "step": 15
+    },
+    {
+      "epoch": 0.12030075187969924,
+      "grad_norm": 0.05708144315846648,
+      "learning_rate": 5.925925925925926e-05,
+      "loss": 0.0938,
+      "step": 16
+    },
+    {
+      "epoch": 0.12781954887218044,
+      "grad_norm": 0.0813311914428683,
+      "learning_rate": 6.296296296296296e-05,
+      "loss": 0.1221,
+      "step": 17
+    },
+    {
+      "epoch": 0.13533834586466165,
+      "grad_norm": 0.07670248585638807,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.1068,
+      "step": 18
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.12777013083805186,
+      "learning_rate": 7.037037037037038e-05,
+      "loss": 0.1183,
+      "step": 19
+    },
+    {
+      "epoch": 0.15037593984962405,
+      "grad_norm": 0.07203864112993859,
+      "learning_rate": 7.407407407407407e-05,
+      "loss": 0.0941,
+      "step": 20
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 0.06622495246697525,
+      "learning_rate": 7.777777777777778e-05,
+      "loss": 0.0851,
+      "step": 21
+    },
+    {
+      "epoch": 0.16541353383458646,
+      "grad_norm": 0.05064660711733651,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.0672,
+      "step": 22
+    },
+    {
+      "epoch": 0.17293233082706766,
+      "grad_norm": 0.05569880144395339,
+      "learning_rate": 8.518518518518518e-05,
+      "loss": 0.0692,
+      "step": 23
+    },
+    {
+      "epoch": 0.18045112781954886,
+      "grad_norm": 0.06341922542018791,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 0.0719,
+      "step": 24
+    },
+    {
+      "epoch": 0.18796992481203006,
+      "grad_norm": 0.09483517480751269,
+      "learning_rate": 9.25925925925926e-05,
+      "loss": 0.1039,
+      "step": 25
+    },
+    {
+      "epoch": 0.19548872180451127,
+      "grad_norm": 0.06345422292566975,
+      "learning_rate": 9.62962962962963e-05,
+      "loss": 0.0642,
+      "step": 26
+    },
+    {
+      "epoch": 0.20300751879699247,
+      "grad_norm": 0.06565559978972503,
+      "learning_rate": 0.0001,
+      "loss": 0.0806,
+      "step": 27
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.07234940226716612,
+      "learning_rate": 9.999568045802217e-05,
+      "loss": 0.0699,
+      "step": 28
+    },
+    {
+      "epoch": 0.21804511278195488,
+      "grad_norm": 0.09174614011055109,
+      "learning_rate": 9.998272257842641e-05,
+      "loss": 0.0797,
+      "step": 29
+    },
+    {
+      "epoch": 0.22556390977443608,
+      "grad_norm": 0.0799372037045221,
+      "learning_rate": 9.996112860009688e-05,
+      "loss": 0.0599,
+      "step": 30
+    },
+    {
+      "epoch": 0.23308270676691728,
+      "grad_norm": 0.07650243821697233,
+      "learning_rate": 9.993090225407743e-05,
+      "loss": 0.0673,
+      "step": 31
+    },
+    {
+      "epoch": 0.24060150375939848,
+      "grad_norm": 0.07437978624039222,
+      "learning_rate": 9.989204876292688e-05,
+      "loss": 0.063,
+      "step": 32
+    },
+    {
+      "epoch": 0.24812030075187969,
+      "grad_norm": 0.05826090837310029,
+      "learning_rate": 9.984457483981669e-05,
+      "loss": 0.0563,
+      "step": 33
+    },
+    {
+      "epoch": 0.2556390977443609,
+      "grad_norm": 0.046830358894256296,
+      "learning_rate": 9.978848868737098e-05,
+      "loss": 0.0449,
+      "step": 34
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 0.059942032653184,
+      "learning_rate": 9.972379999624936e-05,
+      "loss": 0.0492,
+      "step": 35
+    },
+    {
+      "epoch": 0.2706766917293233,
+      "grad_norm": 0.04559622889503948,
+      "learning_rate": 9.96505199434725e-05,
+      "loss": 0.0384,
+      "step": 36
+    },
+    {
+      "epoch": 0.2781954887218045,
+      "grad_norm": 0.08582556953299057,
+      "learning_rate": 9.956866119049095e-05,
+      "loss": 0.052,
+      "step": 37
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.05879365562753825,
+      "learning_rate": 9.947823788099753e-05,
+      "loss": 0.0499,
+      "step": 38
+    },
+    {
+      "epoch": 0.2932330827067669,
+      "grad_norm": 0.07725729979493687,
+      "learning_rate": 9.937926563848346e-05,
+      "loss": 0.0382,
+      "step": 39
+    },
+    {
+      "epoch": 0.3007518796992481,
+      "grad_norm": 0.06791365316815774,
+      "learning_rate": 9.927176156353899e-05,
+      "loss": 0.0424,
+      "step": 40
+    },
+    {
+      "epoch": 0.3082706766917293,
+      "grad_norm": 0.06835456363607172,
+      "learning_rate": 9.91557442308987e-05,
+      "loss": 0.0477,
+      "step": 41
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.06785706541381617,
+      "learning_rate": 9.903123368623216e-05,
+      "loss": 0.0423,
+      "step": 42
+    },
+    {
+      "epoch": 0.3233082706766917,
+      "grad_norm": 0.037822284484082716,
+      "learning_rate": 9.889825144268029e-05,
+      "loss": 0.0373,
+      "step": 43
+    },
+    {
+      "epoch": 0.3308270676691729,
+      "grad_norm": 0.09335172889811039,
+      "learning_rate": 9.875682047713846e-05,
+      "loss": 0.0532,
+      "step": 44
+    },
+    {
+      "epoch": 0.3383458646616541,
+      "grad_norm": 0.03552601591664148,
+      "learning_rate": 9.860696522628639e-05,
+      "loss": 0.0302,
+      "step": 45
+    },
+    {
+      "epoch": 0.3458646616541353,
+      "grad_norm": 0.06792399841238587,
+      "learning_rate": 9.844871158236591e-05,
+      "loss": 0.043,
+      "step": 46
+    },
+    {
+      "epoch": 0.3533834586466165,
+      "grad_norm": 0.07394708716985816,
+      "learning_rate": 9.828208688870735e-05,
+      "loss": 0.0414,
+      "step": 47
+    },
+    {
+      "epoch": 0.3609022556390977,
+      "grad_norm": 0.07644206071621325,
+      "learning_rate": 9.810711993500507e-05,
+      "loss": 0.0442,
+      "step": 48
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 0.04448780324279346,
+      "learning_rate": 9.792384095234313e-05,
+      "loss": 0.0397,
+      "step": 49
+    },
+    {
+      "epoch": 0.37593984962406013,
+      "grad_norm": 0.040299146373067786,
+      "learning_rate": 9.773228160797188e-05,
+      "loss": 0.0294,
+      "step": 50
+    },
+    {
+      "epoch": 0.38345864661654133,
+      "grad_norm": 0.04600091352431098,
+      "learning_rate": 9.753247499983649e-05,
+      "loss": 0.0388,
+      "step": 51
+    },
+    {
+      "epoch": 0.39097744360902253,
+      "grad_norm": 0.05174024689025062,
+      "learning_rate": 9.732445565085824e-05,
+      "loss": 0.0464,
+      "step": 52
+    },
+    {
+      "epoch": 0.39849624060150374,
+      "grad_norm": 0.06048290755695799,
+      "learning_rate": 9.71082595029695e-05,
+      "loss": 0.0441,
+      "step": 53
+    },
+    {
+      "epoch": 0.40601503759398494,
+      "grad_norm": 0.06909111905381797,
+      "learning_rate": 9.688392391090373e-05,
+      "loss": 0.0403,
+      "step": 54
+    },
+    {
+      "epoch": 0.41353383458646614,
+      "grad_norm": 0.10580098842980783,
+      "learning_rate": 9.665148763574123e-05,
+      "loss": 0.0414,
+      "step": 55
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.06004492721880413,
+      "learning_rate": 9.64109908382119e-05,
+      "loss": 0.0348,
+      "step": 56
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.05616302785838828,
+      "learning_rate": 9.616247507175623e-05,
+      "loss": 0.0353,
+      "step": 57
+    },
+    {
+      "epoch": 0.43609022556390975,
+      "grad_norm": 0.04963402332052172,
+      "learning_rate": 9.590598327534564e-05,
+      "loss": 0.0354,
+      "step": 58
+    },
+    {
+      "epoch": 0.44360902255639095,
+      "grad_norm": 0.09520890937208057,
+      "learning_rate": 9.564155976606339e-05,
+      "loss": 0.0436,
+      "step": 59
+    },
+    {
+      "epoch": 0.45112781954887216,
+      "grad_norm": 0.07317691578763187,
+      "learning_rate": 9.536925023144742e-05,
+      "loss": 0.0448,
+      "step": 60
+    },
+    {
+      "epoch": 0.45864661654135336,
+      "grad_norm": 0.0653903652099525,
+      "learning_rate": 9.508910172159635e-05,
+      "loss": 0.0456,
+      "step": 61
+    },
+    {
+      "epoch": 0.46616541353383456,
+      "grad_norm": 0.08533000644485912,
+      "learning_rate": 9.480116264104011e-05,
+      "loss": 0.0417,
+      "step": 62
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.07477194348090598,
+      "learning_rate": 9.450548274037653e-05,
+      "loss": 0.0427,
+      "step": 63
+    },
+    {
+      "epoch": 0.48120300751879697,
+      "grad_norm": 0.040320894825821886,
+      "learning_rate": 9.420211310767533e-05,
+      "loss": 0.0317,
+      "step": 64
+    },
+    {
+      "epoch": 0.48872180451127817,
+      "grad_norm": 0.04204333897095501,
+      "learning_rate": 9.389110615965102e-05,
+      "loss": 0.0308,
+      "step": 65
+    },
+    {
+      "epoch": 0.49624060150375937,
+      "grad_norm": 0.06435209558835227,
+      "learning_rate": 9.35725156326063e-05,
+      "loss": 0.0404,
+      "step": 66
+    },
+    {
+      "epoch": 0.5037593984962406,
+      "grad_norm": 0.05292300086818655,
+      "learning_rate": 9.324639657314742e-05,
+      "loss": 0.0383,
+      "step": 67
+    },
+    {
+      "epoch": 0.5112781954887218,
+      "grad_norm": 0.0533359959006372,
+      "learning_rate": 9.291280532867302e-05,
+      "loss": 0.0419,
+      "step": 68
+    },
+    {
+      "epoch": 0.518796992481203,
+      "grad_norm": 0.0421677134855151,
+      "learning_rate": 9.257179953763845e-05,
+      "loss": 0.0301,
+      "step": 69
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.047396091527240565,
+      "learning_rate": 9.222343811959693e-05,
+      "loss": 0.0355,
+      "step": 70
+    },
+    {
+      "epoch": 0.5338345864661654,
+      "grad_norm": 0.05055865206409256,
+      "learning_rate": 9.186778126501916e-05,
+      "loss": 0.0379,
+      "step": 71
+    },
+    {
+      "epoch": 0.5413533834586466,
+      "grad_norm": 0.03922328494549794,
+      "learning_rate": 9.150489042489367e-05,
+      "loss": 0.03,
+      "step": 72
+    },
+    {
+      "epoch": 0.5488721804511278,
+      "grad_norm": 0.08580904921861318,
+      "learning_rate": 9.113482830010918e-05,
+      "loss": 0.038,
+      "step": 73
+    },
+    {
+      "epoch": 0.556390977443609,
+      "grad_norm": 0.04615991149700515,
+      "learning_rate": 9.075765883062093e-05,
+      "loss": 0.0321,
+      "step": 74
+    },
+    {
+      "epoch": 0.5639097744360902,
+      "grad_norm": 0.21688152384611062,
+      "learning_rate": 9.037344718440322e-05,
+      "loss": 0.0369,
+      "step": 75
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.06709856743156827,
+      "learning_rate": 8.99822597461894e-05,
+      "loss": 0.0429,
+      "step": 76
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.07300506123989278,
+      "learning_rate": 8.958416410600187e-05,
+      "loss": 0.0351,
+      "step": 77
+    },
+    {
+      "epoch": 0.5864661654135338,
+      "grad_norm": 0.08415403445437179,
+      "learning_rate": 8.917922904747384e-05,
+      "loss": 0.0425,
+      "step": 78
+    },
+    {
+      "epoch": 0.5939849624060151,
+      "grad_norm": 0.043734956942212244,
+      "learning_rate": 8.876752453596462e-05,
+      "loss": 0.0322,
+      "step": 79
+    },
+    {
+      "epoch": 0.6015037593984962,
+      "grad_norm": 0.11340147288766998,
+      "learning_rate": 8.834912170647101e-05,
+      "loss": 0.0446,
+      "step": 80
+    },
+    {
+      "epoch": 0.6090225563909775,
+      "grad_norm": 0.061288991507609664,
+      "learning_rate": 8.792409285133642e-05,
+      "loss": 0.0424,
+      "step": 81
+    },
+    {
+      "epoch": 0.6165413533834586,
+      "grad_norm": 0.043805649893633086,
+      "learning_rate": 8.749251140776016e-05,
+      "loss": 0.0342,
+      "step": 82
+    },
+    {
+      "epoch": 0.6240601503759399,
+      "grad_norm": 0.05953059965877648,
+      "learning_rate": 8.705445194510868e-05,
+      "loss": 0.0321,
+      "step": 83
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.07945205955271631,
+      "learning_rate": 8.66099901520315e-05,
+      "loss": 0.0371,
+      "step": 84
+    },
+    {
+      "epoch": 0.6390977443609023,
+      "grad_norm": 0.04453806753518928,
+      "learning_rate": 8.615920282338355e-05,
+      "loss": 0.0349,
+      "step": 85
+    },
+    {
+      "epoch": 0.6466165413533834,
+      "grad_norm": 0.05196927124976879,
+      "learning_rate": 8.570216784695637e-05,
+      "loss": 0.0287,
+      "step": 86
+    },
+    {
+      "epoch": 0.6541353383458647,
+      "grad_norm": 0.08901603801098872,
+      "learning_rate": 8.52389641900206e-05,
+      "loss": 0.0379,
+      "step": 87
+    },
+    {
+      "epoch": 0.6616541353383458,
+      "grad_norm": 0.04173009472070016,
+      "learning_rate": 8.476967188568188e-05,
+      "loss": 0.0264,
+      "step": 88
+    },
+    {
+      "epoch": 0.6691729323308271,
+      "grad_norm": 0.06191267416598679,
+      "learning_rate": 8.429437201905254e-05,
+      "loss": 0.028,
+      "step": 89
+    },
+    {
+      "epoch": 0.6766917293233082,
+      "grad_norm": 0.05938205491417802,
+      "learning_rate": 8.381314671324159e-05,
+      "loss": 0.0353,
+      "step": 90
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.06594155945203996,
+      "learning_rate": 8.332607911516545e-05,
+      "loss": 0.0423,
+      "step": 91
+    },
+    {
+      "epoch": 0.6917293233082706,
+      "grad_norm": 0.03727901580427709,
+      "learning_rate": 8.283325338118153e-05,
+      "loss": 0.0288,
+      "step": 92
+    },
+    {
+      "epoch": 0.6992481203007519,
+      "grad_norm": 0.039506792129091334,
+      "learning_rate": 8.233475466254765e-05,
+      "loss": 0.0319,
+      "step": 93
+    },
+    {
+      "epoch": 0.706766917293233,
+      "grad_norm": 0.10114676138905467,
+      "learning_rate": 8.183066909070947e-05,
+      "loss": 0.0413,
+      "step": 94
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.0519720254987392,
+      "learning_rate": 8.132108376241849e-05,
+      "loss": 0.0319,
+      "step": 95
+    },
+    {
+      "epoch": 0.7218045112781954,
+      "grad_norm": 0.06828535688055823,
+      "learning_rate": 8.08060867246834e-05,
+      "loss": 0.0415,
+      "step": 96
+    },
+    {
+      "epoch": 0.7293233082706767,
+      "grad_norm": 0.04423778552147402,
+      "learning_rate": 8.028576695955711e-05,
+      "loss": 0.0307,
+      "step": 97
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.04301708267503238,
+      "learning_rate": 7.97602143687623e-05,
+      "loss": 0.0292,
+      "step": 98
+    },
+    {
+      "epoch": 0.7443609022556391,
+      "grad_norm": 0.07557692217243188,
+      "learning_rate": 7.922951975815811e-05,
+      "loss": 0.0304,
+      "step": 99
+    },
+    {
+      "epoch": 0.7518796992481203,
+      "grad_norm": 0.061041885279450855,
+      "learning_rate": 7.869377482205042e-05,
+      "loss": 0.0318,
+      "step": 100
+    },
+    {
+      "epoch": 0.7593984962406015,
+      "grad_norm": 0.040342152719196084,
+      "learning_rate": 7.815307212734888e-05,
+      "loss": 0.027,
+      "step": 101
+    },
+    {
+      "epoch": 0.7669172932330827,
+      "grad_norm": 0.07790755826343725,
+      "learning_rate": 7.760750509757298e-05,
+      "loss": 0.0339,
+      "step": 102
+    },
+    {
+      "epoch": 0.7744360902255639,
+      "grad_norm": 0.05210408795431101,
+      "learning_rate": 7.705716799671019e-05,
+      "loss": 0.0228,
+      "step": 103
+    },
+    {
+      "epoch": 0.7819548872180451,
+      "grad_norm": 0.08000736959421384,
+      "learning_rate": 7.650215591292888e-05,
+      "loss": 0.0357,
+      "step": 104
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.05843028390975531,
+      "learning_rate": 7.594256474214882e-05,
+      "loss": 0.0285,
+      "step": 105
+    },
+    {
+      "epoch": 0.7969924812030075,
+      "grad_norm": 0.13537509841914472,
+      "learning_rate": 7.537849117147212e-05,
+      "loss": 0.0359,
+      "step": 106
+    },
+    {
+      "epoch": 0.8045112781954887,
+      "grad_norm": 0.08230566866298178,
+      "learning_rate": 7.481003266247744e-05,
+      "loss": 0.0367,
+      "step": 107
+    },
+    {
+      "epoch": 0.8120300751879699,
+      "grad_norm": 0.09678557492723187,
+      "learning_rate": 7.423728743438048e-05,
+      "loss": 0.0358,
+      "step": 108
+    },
+    {
+      "epoch": 0.8195488721804511,
+      "grad_norm": 0.049541914871144996,
+      "learning_rate": 7.366035444706347e-05,
+      "loss": 0.0329,
+      "step": 109
+    },
+    {
+      "epoch": 0.8270676691729323,
+      "grad_norm": 0.08823757922929092,
+      "learning_rate": 7.307933338397667e-05,
+      "loss": 0.0364,
+      "step": 110
+    },
+    {
+      "epoch": 0.8345864661654135,
+      "grad_norm": 0.044744299992948704,
+      "learning_rate": 7.249432463491498e-05,
+      "loss": 0.0328,
+      "step": 111
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.03814585189064516,
+      "learning_rate": 7.190542927867234e-05,
+      "loss": 0.0242,
+      "step": 112
+    },
+    {
+      "epoch": 0.849624060150376,
+      "grad_norm": 0.03553642928460275,
+      "learning_rate": 7.131274906557725e-05,
+      "loss": 0.0277,
+      "step": 113
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.044176381361140944,
+      "learning_rate": 7.071638639991207e-05,
+      "loss": 0.0282,
+      "step": 114
+    },
+    {
+      "epoch": 0.8646616541353384,
+      "grad_norm": 0.04113727259330019,
+      "learning_rate": 7.011644432221958e-05,
+      "loss": 0.0311,
+      "step": 115
+    },
+    {
+      "epoch": 0.8721804511278195,
+      "grad_norm": 0.060773829286428965,
+      "learning_rate": 6.95130264914993e-05,
+      "loss": 0.0414,
+      "step": 116
+    },
+    {
+      "epoch": 0.8796992481203008,
+      "grad_norm": 0.05757846085257315,
+      "learning_rate": 6.890623716729724e-05,
+      "loss": 0.0279,
+      "step": 117
+    },
+    {
+      "epoch": 0.8872180451127819,
+      "grad_norm": 0.08428255259620104,
+      "learning_rate": 6.82961811916917e-05,
+      "loss": 0.0298,
+      "step": 118
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.04529601746123181,
+      "learning_rate": 6.768296397117848e-05,
+      "loss": 0.0263,
+      "step": 119
+    },
+    {
+      "epoch": 0.9022556390977443,
+      "grad_norm": 0.0559976345746786,
+      "learning_rate": 6.706669145845863e-05,
+      "loss": 0.0331,
+      "step": 120
+    },
+    {
+      "epoch": 0.9097744360902256,
+      "grad_norm": 0.046985300077111235,
+      "learning_rate": 6.644747013413168e-05,
+      "loss": 0.0323,
+      "step": 121
+    },
+    {
+      "epoch": 0.9172932330827067,
+      "grad_norm": 0.06973194335422163,
+      "learning_rate": 6.582540698829781e-05,
+      "loss": 0.0356,
+      "step": 122
+    },
+    {
+      "epoch": 0.924812030075188,
+      "grad_norm": 0.0550307651636393,
+      "learning_rate": 6.520060950207185e-05,
+      "loss": 0.0374,
+      "step": 123
+    },
+    {
+      "epoch": 0.9323308270676691,
+      "grad_norm": 0.04136098377224926,
+      "learning_rate": 6.457318562901256e-05,
+      "loss": 0.0281,
+      "step": 124
+    },
+    {
+      "epoch": 0.9398496240601504,
+      "grad_norm": 0.04471839673788357,
+      "learning_rate": 6.394324377647028e-05,
+      "loss": 0.0344,
+      "step": 125
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.04057335071418551,
+      "learning_rate": 6.331089278685599e-05,
+      "loss": 0.0289,
+      "step": 126
+    },
+    {
+      "epoch": 0.9548872180451128,
+      "grad_norm": 0.036632585834280834,
+      "learning_rate": 6.26762419188355e-05,
+      "loss": 0.0254,
+      "step": 127
+    },
+    {
+      "epoch": 0.9624060150375939,
+      "grad_norm": 0.05253467833143005,
+      "learning_rate": 6.203940082845144e-05,
+      "loss": 0.0423,
+      "step": 128
+    },
+    {
+      "epoch": 0.9699248120300752,
+      "grad_norm": 0.05828434847478486,
+      "learning_rate": 6.140047955017671e-05,
+      "loss": 0.0331,
+      "step": 129
+    },
+    {
+      "epoch": 0.9774436090225563,
+      "grad_norm": 0.052528332979290625,
+      "learning_rate": 6.075958847790262e-05,
+      "loss": 0.0344,
+      "step": 130
+    },
+    {
+      "epoch": 0.9849624060150376,
+      "grad_norm": 0.039125799054480936,
+      "learning_rate": 6.011683834586473e-05,
+      "loss": 0.0264,
+      "step": 131
+    },
+    {
+      "epoch": 0.9924812030075187,
+      "grad_norm": 0.03707157930189228,
+      "learning_rate": 5.947234020951015e-05,
+      "loss": 0.0237,
+      "step": 132
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.054189982183542575,
+      "learning_rate": 5.882620542630901e-05,
+      "loss": 0.0317,
+      "step": 133
+    },
+    {
+      "epoch": 1.0075187969924813,
+      "grad_norm": 0.04357846265860899,
+      "learning_rate": 5.8178545636514145e-05,
+      "loss": 0.0268,
+      "step": 134
+    },
+    {
+      "epoch": 1.0150375939849625,
+      "grad_norm": 0.056012933476124856,
+      "learning_rate": 5.752947274387147e-05,
+      "loss": 0.0223,
+      "step": 135
+    },
+    {
+      "epoch": 1.0225563909774436,
+      "grad_norm": 0.049689439936320044,
+      "learning_rate": 5.687909889628529e-05,
+      "loss": 0.0304,
+      "step": 136
+    },
+    {
+      "epoch": 1.0300751879699248,
+      "grad_norm": 0.04830994322048754,
+      "learning_rate": 5.622753646644102e-05,
+      "loss": 0.0278,
+      "step": 137
+    },
+    {
+      "epoch": 1.037593984962406,
+      "grad_norm": 0.04418639970975713,
+      "learning_rate": 5.557489803238933e-05,
+      "loss": 0.0259,
+      "step": 138
+    },
+    {
+      "epoch": 1.045112781954887,
+      "grad_norm": 0.042738363591787835,
+      "learning_rate": 5.492129635809473e-05,
+      "loss": 0.0198,
+      "step": 139
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.03885713180148723,
+      "learning_rate": 5.426684437395196e-05,
+      "loss": 0.0191,
+      "step": 140
+    },
+    {
+      "epoch": 1.0601503759398496,
+      "grad_norm": 0.04951650926676435,
+      "learning_rate": 5.361165515727374e-05,
+      "loss": 0.0214,
+      "step": 141
+    },
+    {
+      "epoch": 1.0676691729323309,
+      "grad_norm": 0.059968470212708236,
+      "learning_rate": 5.295584191275308e-05,
+      "loss": 0.0243,
+      "step": 142
+    },
+    {
+      "epoch": 1.0751879699248121,
+      "grad_norm": 0.0676386940224187,
+      "learning_rate": 5.229951795290353e-05,
+      "loss": 0.029,
+      "step": 143
+    },
+    {
+      "epoch": 1.0827067669172932,
+      "grad_norm": 0.04250436122379926,
+      "learning_rate": 5.164279667848094e-05,
+      "loss": 0.0204,
+      "step": 144
+    },
+    {
+      "epoch": 1.0902255639097744,
+      "grad_norm": 0.04124846102938738,
+      "learning_rate": 5.0985791558889785e-05,
+      "loss": 0.0209,
+      "step": 145
+    },
+    {
+      "epoch": 1.0977443609022557,
+      "grad_norm": 0.05914558229310168,
+      "learning_rate": 5.032861611257783e-05,
+      "loss": 0.0285,
+      "step": 146
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.0465029543723527,
+      "learning_rate": 4.967138388742218e-05,
+      "loss": 0.0204,
+      "step": 147
+    },
+    {
+      "epoch": 1.112781954887218,
+      "grad_norm": 0.06469458945659604,
+      "learning_rate": 4.901420844111021e-05,
+      "loss": 0.0314,
+      "step": 148
+    },
+    {
+      "epoch": 1.1203007518796992,
+      "grad_norm": 0.06440915952496404,
+      "learning_rate": 4.835720332151907e-05,
+      "loss": 0.0281,
+      "step": 149
+    },
+    {
+      "epoch": 1.1278195488721805,
+      "grad_norm": 0.0571757163158284,
+      "learning_rate": 4.770048204709648e-05,
+      "loss": 0.0248,
+      "step": 150
+    },
+    {
+      "epoch": 1.1353383458646618,
+      "grad_norm": 0.05910301690921271,
+      "learning_rate": 4.7044158087246926e-05,
+      "loss": 0.0311,
+      "step": 151
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.04613839631194596,
+      "learning_rate": 4.6388344842726264e-05,
+      "loss": 0.0218,
+      "step": 152
+    },
+    {
+      "epoch": 1.150375939849624,
+      "grad_norm": 0.05741866552084954,
+      "learning_rate": 4.5733155626048036e-05,
+      "loss": 0.0271,
+      "step": 153
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 0.04682544810113655,
+      "learning_rate": 4.507870364190527e-05,
+      "loss": 0.0264,
+      "step": 154
+    },
+    {
+      "epoch": 1.1654135338345863,
+      "grad_norm": 0.06282838577083374,
+      "learning_rate": 4.4425101967610674e-05,
+      "loss": 0.024,
+      "step": 155
+    },
+    {
+      "epoch": 1.1729323308270676,
+      "grad_norm": 0.05388737782363021,
+      "learning_rate": 4.377246353355899e-05,
+      "loss": 0.0271,
+      "step": 156
+    },
+    {
+      "epoch": 1.1804511278195489,
+      "grad_norm": 0.05086578069156835,
+      "learning_rate": 4.312090110371473e-05,
+      "loss": 0.0278,
+      "step": 157
+    },
+    {
+      "epoch": 1.1879699248120301,
+      "grad_norm": 0.05863572980738164,
+      "learning_rate": 4.247052725612852e-05,
+      "loss": 0.0292,
+      "step": 158
+    },
+    {
+      "epoch": 1.1954887218045114,
+      "grad_norm": 0.04227523648124146,
+      "learning_rate": 4.1821454363485866e-05,
+      "loss": 0.0234,
+      "step": 159
+    },
+    {
+      "epoch": 1.2030075187969924,
+      "grad_norm": 0.04268704545270105,
+      "learning_rate": 4.1173794573690996e-05,
+      "loss": 0.0206,
+      "step": 160
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.04778787432486908,
+      "learning_rate": 4.052765979048986e-05,
+      "loss": 0.0227,
+      "step": 161
+    },
+    {
+      "epoch": 1.218045112781955,
+      "grad_norm": 0.0459311125342993,
+      "learning_rate": 3.988316165413528e-05,
+      "loss": 0.0205,
+      "step": 162
+    },
+    {
+      "epoch": 1.225563909774436,
+      "grad_norm": 0.05603215690118315,
+      "learning_rate": 3.924041152209739e-05,
+      "loss": 0.029,
+      "step": 163
+    },
+    {
+      "epoch": 1.2330827067669172,
+      "grad_norm": 0.060179119443112154,
+      "learning_rate": 3.859952044982329e-05,
+      "loss": 0.0271,
+      "step": 164
+    },
+    {
+      "epoch": 1.2406015037593985,
+      "grad_norm": 0.04740279415347567,
+      "learning_rate": 3.7960599171548574e-05,
+      "loss": 0.0213,
+      "step": 165
+    },
+    {
+      "epoch": 1.2481203007518797,
+      "grad_norm": 0.052482110362426594,
+      "learning_rate": 3.732375808116451e-05,
+      "loss": 0.0258,
+      "step": 166
+    },
+    {
+      "epoch": 1.255639097744361,
+      "grad_norm": 0.04835120393099329,
+      "learning_rate": 3.668910721314402e-05,
+      "loss": 0.0229,
+      "step": 167
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.08311507045185516,
+      "learning_rate": 3.605675622352973e-05,
+      "loss": 0.0265,
+      "step": 168
+    },
+    {
+      "epoch": 1.2706766917293233,
+      "grad_norm": 0.053563077833150494,
+      "learning_rate": 3.542681437098745e-05,
+      "loss": 0.0256,
+      "step": 169
+    },
+    {
+      "epoch": 1.2781954887218046,
+      "grad_norm": 0.05567682482783888,
+      "learning_rate": 3.479939049792817e-05,
+      "loss": 0.0213,
+      "step": 170
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.054588031712222006,
+      "learning_rate": 3.417459301170219e-05,
+      "loss": 0.0266,
+      "step": 171
+    },
+    {
+      "epoch": 1.2932330827067668,
+      "grad_norm": 0.07694344232267265,
+      "learning_rate": 3.355252986586832e-05,
+      "loss": 0.0193,
+      "step": 172
+    },
+    {
+      "epoch": 1.300751879699248,
+      "grad_norm": 0.05943952613035603,
+      "learning_rate": 3.293330854154136e-05,
+      "loss": 0.0258,
+      "step": 173
+    },
+    {
+      "epoch": 1.3082706766917294,
+      "grad_norm": 0.038766556860819104,
+      "learning_rate": 3.2317036028821523e-05,
+      "loss": 0.0159,
+      "step": 174
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.05092188135687549,
+      "learning_rate": 3.1703818808308324e-05,
+      "loss": 0.0215,
+      "step": 175
+    },
+    {
+      "epoch": 1.3233082706766917,
+      "grad_norm": 0.04779789780883562,
+      "learning_rate": 3.109376283270277e-05,
+      "loss": 0.0268,
+      "step": 176
+    },
+    {
+      "epoch": 1.330827067669173,
+      "grad_norm": 0.04433720319245774,
+      "learning_rate": 3.0486973508500727e-05,
+      "loss": 0.0238,
+      "step": 177
+    },
+    {
+      "epoch": 1.3383458646616542,
+      "grad_norm": 0.049878475563895956,
+      "learning_rate": 2.988355567778043e-05,
+      "loss": 0.0259,
+      "step": 178
+    },
+    {
+      "epoch": 1.3458646616541352,
+      "grad_norm": 0.05962755604807658,
+      "learning_rate": 2.9283613600087933e-05,
+      "loss": 0.025,
+      "step": 179
+    },
+    {
+      "epoch": 1.3533834586466165,
+      "grad_norm": 0.04955718527923681,
+      "learning_rate": 2.8687250934422772e-05,
+      "loss": 0.0194,
+      "step": 180
+    },
+    {
+      "epoch": 1.3609022556390977,
+      "grad_norm": 0.03676456890831394,
+      "learning_rate": 2.8094570721327662e-05,
+      "loss": 0.0189,
+      "step": 181
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.04868946152583533,
+      "learning_rate": 2.750567536508504e-05,
+      "loss": 0.0243,
+      "step": 182
+    },
+    {
+      "epoch": 1.3759398496240602,
+      "grad_norm": 0.0555305400721802,
+      "learning_rate": 2.6920666616023327e-05,
+      "loss": 0.0257,
+      "step": 183
+    },
+    {
+      "epoch": 1.3834586466165413,
+      "grad_norm": 0.04963192556183434,
+      "learning_rate": 2.6339645552936536e-05,
+      "loss": 0.0275,
+      "step": 184
+    },
+    {
+      "epoch": 1.3909774436090225,
+      "grad_norm": 0.05542091349920839,
+      "learning_rate": 2.5762712565619528e-05,
+      "loss": 0.023,
+      "step": 185
+    },
+    {
+      "epoch": 1.3984962406015038,
+      "grad_norm": 0.0426183120843919,
+      "learning_rate": 2.5189967337522573e-05,
+      "loss": 0.0206,
+      "step": 186
+    },
+    {
+      "epoch": 1.4060150375939848,
+      "grad_norm": 0.05205246245376388,
+      "learning_rate": 2.46215088285279e-05,
+      "loss": 0.0229,
+      "step": 187
+    },
+    {
+      "epoch": 1.413533834586466,
+      "grad_norm": 0.04337666332691105,
+      "learning_rate": 2.4057435257851175e-05,
+      "loss": 0.019,
+      "step": 188
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.05985729489503263,
+      "learning_rate": 2.349784408707112e-05,
+      "loss": 0.0274,
+      "step": 189
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.062032022184375604,
+      "learning_rate": 2.2942832003289823e-05,
+      "loss": 0.0271,
+      "step": 190
+    },
+    {
+      "epoch": 1.4360902255639099,
+      "grad_norm": 0.05773389436675615,
+      "learning_rate": 2.2392494902427025e-05,
+      "loss": 0.0263,
+      "step": 191
+    },
+    {
+      "epoch": 1.443609022556391,
+      "grad_norm": 0.048522536078850126,
+      "learning_rate": 2.1846927872651137e-05,
+      "loss": 0.0242,
+      "step": 192
+    },
+    {
+      "epoch": 1.4511278195488722,
+      "grad_norm": 0.05010560342148772,
+      "learning_rate": 2.1306225177949585e-05,
+      "loss": 0.024,
+      "step": 193
+    },
+    {
+      "epoch": 1.4586466165413534,
+      "grad_norm": 0.058011679310299026,
+      "learning_rate": 2.07704802418419e-05,
+      "loss": 0.0301,
+      "step": 194
+    },
+    {
+      "epoch": 1.4661654135338344,
+      "grad_norm": 0.052695628737558814,
+      "learning_rate": 2.0239785631237705e-05,
+      "loss": 0.0262,
+      "step": 195
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.0397195089948912,
+      "learning_rate": 1.9714233040442915e-05,
+      "loss": 0.0179,
+      "step": 196
+    },
+    {
+      "epoch": 1.481203007518797,
+      "grad_norm": 0.05532938780742867,
+      "learning_rate": 1.9193913275316626e-05,
+      "loss": 0.0234,
+      "step": 197
+    },
+    {
+      "epoch": 1.4887218045112782,
+      "grad_norm": 0.07349266479809795,
+      "learning_rate": 1.8678916237581522e-05,
+      "loss": 0.0236,
+      "step": 198
+    },
+    {
+      "epoch": 1.4962406015037595,
+      "grad_norm": 0.03995824607041351,
+      "learning_rate": 1.816933090929055e-05,
+      "loss": 0.0176,
+      "step": 199
+    },
+    {
+      "epoch": 1.5037593984962405,
+      "grad_norm": 0.07166373724308431,
+      "learning_rate": 1.7665245337452368e-05,
+      "loss": 0.0258,
+      "step": 200
+    },
+    {
+      "epoch": 1.5037593984962405,
+      "eval_loss": 0.029665347188711166,
+      "eval_runtime": 6.5066,
+      "eval_samples_per_second": 0.922,
+      "eval_steps_per_second": 0.307,
+      "step": 200
+    },
+    {
+      "epoch": 1.5112781954887218,
+      "grad_norm": 0.048692577901512116,
+      "learning_rate": 1.716674661881848e-05,
+      "loss": 0.0224,
+      "step": 201
+    },
+    {
+      "epoch": 1.518796992481203,
+      "grad_norm": 0.04675059057360818,
+      "learning_rate": 1.667392088483456e-05,
+      "loss": 0.0223,
+      "step": 202
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.05459458244813264,
+      "learning_rate": 1.6186853286758397e-05,
+      "loss": 0.0242,
+      "step": 203
+    },
+    {
+      "epoch": 1.5338345864661656,
+      "grad_norm": 0.051543551392068274,
+      "learning_rate": 1.570562798094747e-05,
+      "loss": 0.025,
+      "step": 204
+    },
+    {
+      "epoch": 1.5413533834586466,
+      "grad_norm": 0.14671926401344376,
+      "learning_rate": 1.5230328114318127e-05,
+      "loss": 0.0241,
+      "step": 205
+    },
+    {
+      "epoch": 1.5488721804511278,
+      "grad_norm": 0.058979726559234814,
+      "learning_rate": 1.4761035809979395e-05,
+      "loss": 0.0253,
+      "step": 206
+    },
+    {
+      "epoch": 1.556390977443609,
+      "grad_norm": 0.06494643885270886,
+      "learning_rate": 1.4297832153043656e-05,
+      "loss": 0.0236,
+      "step": 207
+    },
+    {
+      "epoch": 1.5639097744360901,
+      "grad_norm": 0.06627104647345526,
+      "learning_rate": 1.3840797176616466e-05,
+      "loss": 0.0278,
+      "step": 208
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.06190650675134399,
+      "learning_rate": 1.3390009847968504e-05,
+      "loss": 0.0255,
+      "step": 209
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.06250699899282167,
+      "learning_rate": 1.2945548054891321e-05,
+      "loss": 0.0254,
+      "step": 210
+    },
+    {
+      "epoch": 1.5864661654135337,
+      "grad_norm": 0.06214391708977836,
+      "learning_rate": 1.2507488592239847e-05,
+      "loss": 0.0233,
+      "step": 211
+    },
+    {
+      "epoch": 1.5939849624060152,
+      "grad_norm": 0.054608347620115995,
+      "learning_rate": 1.2075907148663579e-05,
+      "loss": 0.024,
+      "step": 212
+    },
+    {
+      "epoch": 1.6015037593984962,
+      "grad_norm": 0.05333683650123989,
+      "learning_rate": 1.1650878293528994e-05,
+      "loss": 0.0261,
+      "step": 213
+    },
+    {
+      "epoch": 1.6090225563909775,
+      "grad_norm": 0.047407562918454,
+      "learning_rate": 1.1232475464035385e-05,
+      "loss": 0.0192,
+      "step": 214
+    },
+    {
+      "epoch": 1.6165413533834587,
+      "grad_norm": 0.06549580580637923,
+      "learning_rate": 1.0820770952526155e-05,
+      "loss": 0.0192,
+      "step": 215
+    },
+    {
+      "epoch": 1.6240601503759398,
+      "grad_norm": 0.0582730317262946,
+      "learning_rate": 1.0415835893998116e-05,
+      "loss": 0.0267,
+      "step": 216
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.06724858724013988,
+      "learning_rate": 1.0017740253810609e-05,
+      "loss": 0.0244,
+      "step": 217
+    },
+    {
+      "epoch": 1.6390977443609023,
+      "grad_norm": 0.07353126997097047,
+      "learning_rate": 9.62655281559679e-06,
+      "loss": 0.0265,
+      "step": 218
+    },
+    {
+      "epoch": 1.6466165413533833,
+      "grad_norm": 0.057567868642984674,
+      "learning_rate": 9.242341169379076e-06,
+      "loss": 0.0239,
+      "step": 219
+    },
+    {
+      "epoch": 1.6541353383458648,
+      "grad_norm": 0.06325334373179048,
+      "learning_rate": 8.865171699890834e-06,
+      "loss": 0.023,
+      "step": 220
+    },
+    {
+      "epoch": 1.6616541353383458,
+      "grad_norm": 0.057849806459398294,
+      "learning_rate": 8.49510957510633e-06,
+      "loss": 0.0286,
+      "step": 221
+    },
+    {
+      "epoch": 1.669172932330827,
+      "grad_norm": 0.06257054012996921,
+      "learning_rate": 8.132218734980852e-06,
+      "loss": 0.0205,
+      "step": 222
+    },
+    {
+      "epoch": 1.6766917293233083,
+      "grad_norm": 0.053291552200528655,
+      "learning_rate": 7.776561880403072e-06,
+      "loss": 0.0222,
+      "step": 223
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.055884993872003165,
+      "learning_rate": 7.4282004623615396e-06,
+      "loss": 0.0257,
+      "step": 224
+    },
+    {
+      "epoch": 1.6917293233082706,
+      "grad_norm": 0.04781226703104293,
+      "learning_rate": 7.0871946713269856e-06,
+      "loss": 0.021,
+      "step": 225
+    },
+    {
+      "epoch": 1.699248120300752,
+      "grad_norm": 0.04617454207758738,
+      "learning_rate": 6.753603426852589e-06,
+      "loss": 0.0206,
+      "step": 226
+    },
+    {
+      "epoch": 1.706766917293233,
+      "grad_norm": 0.05934488856386534,
+      "learning_rate": 6.427484367393699e-06,
+      "loss": 0.0221,
+      "step": 227
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.0563063349000768,
+      "learning_rate": 6.108893840348995e-06,
+      "loss": 0.0217,
+      "step": 228
+    },
+    {
+      "epoch": 1.7218045112781954,
+      "grad_norm": 0.058919681414065804,
+      "learning_rate": 5.797886892324694e-06,
+      "loss": 0.0241,
+      "step": 229
+    },
+    {
+      "epoch": 1.7293233082706767,
+      "grad_norm": 0.04652279001651371,
+      "learning_rate": 5.494517259623477e-06,
+      "loss": 0.023,
+      "step": 230
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.05206753304811755,
+      "learning_rate": 5.198837358959901e-06,
+      "loss": 0.0247,
+      "step": 231
+    },
+    {
+      "epoch": 1.744360902255639,
+      "grad_norm": 0.05759411719610633,
+      "learning_rate": 4.910898278403669e-06,
+      "loss": 0.0275,
+      "step": 232
+    },
+    {
+      "epoch": 1.7518796992481203,
+      "grad_norm": 0.05493938568305548,
+      "learning_rate": 4.630749768552589e-06,
+      "loss": 0.0236,
+      "step": 233
+    },
+    {
+      "epoch": 1.7593984962406015,
+      "grad_norm": 0.045214515268897214,
+      "learning_rate": 4.358440233936617e-06,
+      "loss": 0.0196,
+      "step": 234
+    },
+    {
+      "epoch": 1.7669172932330826,
+      "grad_norm": 0.08670874372319154,
+      "learning_rate": 4.094016724654359e-06,
+      "loss": 0.0292,
+      "step": 235
+    },
+    {
+      "epoch": 1.774436090225564,
+      "grad_norm": 0.049117351787292686,
+      "learning_rate": 3.837524928243774e-06,
+      "loss": 0.0224,
+      "step": 236
+    },
+    {
+      "epoch": 1.781954887218045,
+      "grad_norm": 0.058397389390063136,
+      "learning_rate": 3.589009161788104e-06,
+      "loss": 0.0278,
+      "step": 237
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 0.05422155962388968,
+      "learning_rate": 3.3485123642587658e-06,
+      "loss": 0.0243,
+      "step": 238
+    },
+    {
+      "epoch": 1.7969924812030076,
+      "grad_norm": 0.07090059571835504,
+      "learning_rate": 3.116076089096265e-06,
+      "loss": 0.027,
+      "step": 239
+    },
+    {
+      "epoch": 1.8045112781954886,
+      "grad_norm": 0.05963059250846481,
+      "learning_rate": 2.8917404970305097e-06,
+      "loss": 0.0288,
+      "step": 240
+    },
+    {
+      "epoch": 1.8120300751879699,
+      "grad_norm": 0.06946365704174999,
+      "learning_rate": 2.675544349141779e-06,
+      "loss": 0.0259,
+      "step": 241
+    },
+    {
+      "epoch": 1.8195488721804511,
+      "grad_norm": 0.06143740644726876,
+      "learning_rate": 2.4675250001635232e-06,
+      "loss": 0.0247,
+      "step": 242
+    },
+    {
+      "epoch": 1.8270676691729322,
+      "grad_norm": 0.04728168437977354,
+      "learning_rate": 2.2677183920281343e-06,
+      "loss": 0.0193,
+      "step": 243
+    },
+    {
+      "epoch": 1.8345864661654137,
+      "grad_norm": 0.07042127314230426,
+      "learning_rate": 2.076159047656889e-06,
+      "loss": 0.0227,
+      "step": 244
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.05266415047166696,
+      "learning_rate": 1.892880064994934e-06,
+      "loss": 0.0256,
+      "step": 245
+    },
+    {
+      "epoch": 1.849624060150376,
+      "grad_norm": 0.05204878417509025,
+      "learning_rate": 1.7179131112926627e-06,
+      "loss": 0.024,
+      "step": 246
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.04727065912696429,
+      "learning_rate": 1.551288417634106e-06,
+      "loss": 0.0159,
+      "step": 247
+    },
+    {
+      "epoch": 1.8646616541353382,
+      "grad_norm": 0.049637487718030344,
+      "learning_rate": 1.3930347737136196e-06,
+      "loss": 0.0209,
+      "step": 248
+    },
+    {
+      "epoch": 1.8721804511278195,
+      "grad_norm": 0.0505669836884092,
+      "learning_rate": 1.2431795228615372e-06,
+      "loss": 0.0206,
+      "step": 249
+    },
+    {
+      "epoch": 1.8796992481203008,
+      "grad_norm": 0.07557073448805833,
+      "learning_rate": 1.101748557319715e-06,
+      "loss": 0.0315,
+      "step": 250
+    },
+    {
+      "epoch": 1.8872180451127818,
+      "grad_norm": 0.04855407299966349,
+      "learning_rate": 9.687663137678604e-07,
+      "loss": 0.0193,
+      "step": 251
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.05981871688003821,
+      "learning_rate": 8.442557691013043e-07,
+      "loss": 0.0245,
+      "step": 252
+    },
+    {
+      "epoch": 1.9022556390977443,
+      "grad_norm": 0.055297053623164526,
+      "learning_rate": 7.282384364610206e-07,
+      "loss": 0.0242,
+      "step": 253
+    },
+    {
+      "epoch": 1.9097744360902256,
+      "grad_norm": 0.05097924138111233,
+      "learning_rate": 6.207343615165561e-07,
+      "loss": 0.0207,
+      "step": 254
+    },
+    {
+      "epoch": 1.9172932330827068,
+      "grad_norm": 0.05870296620626846,
+      "learning_rate": 5.217621190024779e-07,
+      "loss": 0.0259,
+      "step": 255
+    },
+    {
+      "epoch": 1.9248120300751879,
+      "grad_norm": 0.05289043509456049,
+      "learning_rate": 4.3133880950905205e-07,
+      "loss": 0.0217,
+      "step": 256
+    },
+    {
+      "epoch": 1.9323308270676691,
+      "grad_norm": 0.05040687502136238,
+      "learning_rate": 3.494800565275125e-07,
+      "loss": 0.0226,
+      "step": 257
+    },
+    {
+      "epoch": 1.9398496240601504,
+      "grad_norm": 0.05483598628420617,
+      "learning_rate": 2.762000037506485e-07,
+      "loss": 0.0226,
+      "step": 258
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.052171052589092846,
+      "learning_rate": 2.115113126290258e-07,
+      "loss": 0.0224,
+      "step": 259
+    },
+    {
+      "epoch": 1.954887218045113,
+      "grad_norm": 0.060066029686361856,
+      "learning_rate": 1.554251601833201e-07,
+      "loss": 0.0242,
+      "step": 260
+    },
+    {
+      "epoch": 1.962406015037594,
+      "grad_norm": 0.04560282840465627,
+      "learning_rate": 1.0795123707312283e-07,
+      "loss": 0.0199,
+      "step": 261
+    },
+    {
+      "epoch": 1.9699248120300752,
+      "grad_norm": 0.055943707431487216,
+      "learning_rate": 6.909774592258056e-08,
+      "loss": 0.0218,
+      "step": 262
+    },
+    {
+      "epoch": 1.9774436090225564,
+      "grad_norm": 0.057987573660367824,
+      "learning_rate": 3.8871399903134265e-08,
+      "loss": 0.0242,
+      "step": 263
+    },
+    {
+      "epoch": 1.9849624060150375,
+      "grad_norm": 0.05438020219150765,
+      "learning_rate": 1.7277421573608232e-08,
+      "loss": 0.0278,
+      "step": 264
+    },
+    {
+      "epoch": 1.9924812030075187,
+      "grad_norm": 0.05442881774912085,
+      "learning_rate": 4.319541977831909e-09,
+      "loss": 0.0193,
+      "step": 265
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.059490023866208885,
+      "learning_rate": 0.0,
+      "loss": 0.0224,
+      "step": 266
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 266,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 673614818967552.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-266/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d6847f9e87919055227d9c8018b28017980a14d70646aaf178f757b9a503d6f
+size 7224

checkpoint-266/zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.029648179188370705,
+    "eval_runtime": 6.4826,
+    "eval_samples_per_second": 0.926,
+    "eval_steps_per_second": 0.309
+}

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 +1,208 @@
+{
+  "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",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 673614818967552.0,
+    "train_loss": 0.039493271835932604,
+    "train_runtime": 2026.6163,
+    "train_samples_per_second": 0.522,
+    "train_steps_per_second": 0.131
+}

trainer_log.jsonl

@@ -0,0 +1,268 @@
+{"current_steps": 1, "total_steps": 266, "loss": 0.2087, "lr": 3.7037037037037037e-06, "epoch": 0.007518796992481203, "percentage": 0.38, "elapsed_time": "0:00:13", "remaining_time": "0:57:45"}
+{"current_steps": 2, "total_steps": 266, "loss": 0.1045, "lr": 7.4074074074074075e-06, "epoch": 0.015037593984962405, "percentage": 0.75, "elapsed_time": "0:00:22", "remaining_time": "0:50:07"}
+{"current_steps": 3, "total_steps": 266, "loss": 0.1291, "lr": 1.1111111111111112e-05, "epoch": 0.022556390977443608, "percentage": 1.13, "elapsed_time": "0:00:30", "remaining_time": "0:44:04"}
+{"current_steps": 4, "total_steps": 266, "loss": 0.1263, "lr": 1.4814814814814815e-05, "epoch": 0.03007518796992481, "percentage": 1.5, "elapsed_time": "0:00:37", "remaining_time": "0:40:59"}
+{"current_steps": 5, "total_steps": 266, "loss": 0.1409, "lr": 1.8518518518518518e-05, "epoch": 0.03759398496240601, "percentage": 1.88, "elapsed_time": "0:00:44", "remaining_time": "0:39:05"}
+{"current_steps": 6, "total_steps": 266, "loss": 0.2362, "lr": 2.2222222222222223e-05, "epoch": 0.045112781954887216, "percentage": 2.26, "elapsed_time": "0:00:52", "remaining_time": "0:37:46"}
+{"current_steps": 7, "total_steps": 266, "loss": 0.1195, "lr": 2.5925925925925925e-05, "epoch": 0.05263157894736842, "percentage": 2.63, "elapsed_time": "0:00:59", "remaining_time": "0:36:49"}
+{"current_steps": 8, "total_steps": 266, "loss": 0.1215, "lr": 2.962962962962963e-05, "epoch": 0.06015037593984962, "percentage": 3.01, "elapsed_time": "0:01:07", "remaining_time": "0:36:05"}
+{"current_steps": 9, "total_steps": 266, "loss": 0.0881, "lr": 3.3333333333333335e-05, "epoch": 0.06766917293233082, "percentage": 3.38, "elapsed_time": "0:01:14", "remaining_time": "0:35:29"}
+{"current_steps": 10, "total_steps": 266, "loss": 0.0923, "lr": 3.7037037037037037e-05, "epoch": 0.07518796992481203, "percentage": 3.76, "elapsed_time": "0:01:22", "remaining_time": "0:34:59"}
+{"current_steps": 11, "total_steps": 266, "loss": 0.218, "lr": 4.074074074074074e-05, "epoch": 0.08270676691729323, "percentage": 4.14, "elapsed_time": "0:01:29", "remaining_time": "0:34:32"}
+{"current_steps": 12, "total_steps": 266, "loss": 0.149, "lr": 4.4444444444444447e-05, "epoch": 0.09022556390977443, "percentage": 4.51, "elapsed_time": "0:01:36", "remaining_time": "0:34:09"}
+{"current_steps": 13, "total_steps": 266, "loss": 0.1835, "lr": 4.814814814814815e-05, "epoch": 0.09774436090225563, "percentage": 4.89, "elapsed_time": "0:01:44", "remaining_time": "0:33:49"}
+{"current_steps": 14, "total_steps": 266, "loss": 0.1573, "lr": 5.185185185185185e-05, "epoch": 0.10526315789473684, "percentage": 5.26, "elapsed_time": "0:01:51", "remaining_time": "0:33:30"}
+{"current_steps": 15, "total_steps": 266, "loss": 0.1701, "lr": 5.555555555555556e-05, "epoch": 0.11278195488721804, "percentage": 5.64, "elapsed_time": "0:01:59", "remaining_time": "0:33:13"}
+{"current_steps": 16, "total_steps": 266, "loss": 0.0938, "lr": 5.925925925925926e-05, "epoch": 0.12030075187969924, "percentage": 6.02, "elapsed_time": "0:02:06", "remaining_time": "0:32:57"}
+{"current_steps": 17, "total_steps": 266, "loss": 0.1221, "lr": 6.296296296296296e-05, "epoch": 0.12781954887218044, "percentage": 6.39, "elapsed_time": "0:02:13", "remaining_time": "0:32:42"}
+{"current_steps": 18, "total_steps": 266, "loss": 0.1068, "lr": 6.666666666666667e-05, "epoch": 0.13533834586466165, "percentage": 6.77, "elapsed_time": "0:02:21", "remaining_time": "0:32:28"}
+{"current_steps": 19, "total_steps": 266, "loss": 0.1183, "lr": 7.037037037037038e-05, "epoch": 0.14285714285714285, "percentage": 7.14, "elapsed_time": "0:02:28", "remaining_time": "0:32:15"}
+{"current_steps": 20, "total_steps": 266, "loss": 0.0941, "lr": 7.407407407407407e-05, "epoch": 0.15037593984962405, "percentage": 7.52, "elapsed_time": "0:02:36", "remaining_time": "0:32:01"}
+{"current_steps": 21, "total_steps": 266, "loss": 0.0851, "lr": 7.777777777777778e-05, "epoch": 0.15789473684210525, "percentage": 7.89, "elapsed_time": "0:02:43", "remaining_time": "0:31:49"}
+{"current_steps": 22, "total_steps": 266, "loss": 0.0672, "lr": 8.148148148148148e-05, "epoch": 0.16541353383458646, "percentage": 8.27, "elapsed_time": "0:02:51", "remaining_time": "0:31:37"}
+{"current_steps": 23, "total_steps": 266, "loss": 0.0692, "lr": 8.518518518518518e-05, "epoch": 0.17293233082706766, "percentage": 8.65, "elapsed_time": "0:02:58", "remaining_time": "0:31:26"}
+{"current_steps": 24, "total_steps": 266, "loss": 0.0719, "lr": 8.888888888888889e-05, "epoch": 0.18045112781954886, "percentage": 9.02, "elapsed_time": "0:03:05", "remaining_time": "0:31:15"}
+{"current_steps": 25, "total_steps": 266, "loss": 0.1039, "lr": 9.25925925925926e-05, "epoch": 0.18796992481203006, "percentage": 9.4, "elapsed_time": "0:03:13", "remaining_time": "0:31:04"}
+{"current_steps": 26, "total_steps": 266, "loss": 0.0642, "lr": 9.62962962962963e-05, "epoch": 0.19548872180451127, "percentage": 9.77, "elapsed_time": "0:03:20", "remaining_time": "0:30:53"}
+{"current_steps": 27, "total_steps": 266, "loss": 0.0806, "lr": 0.0001, "epoch": 0.20300751879699247, "percentage": 10.15, "elapsed_time": "0:03:28", "remaining_time": "0:30:42"}
+{"current_steps": 28, "total_steps": 266, "loss": 0.0699, "lr": 9.999568045802217e-05, "epoch": 0.21052631578947367, "percentage": 10.53, "elapsed_time": "0:03:35", "remaining_time": "0:30:32"}
+{"current_steps": 29, "total_steps": 266, "loss": 0.0797, "lr": 9.998272257842641e-05, "epoch": 0.21804511278195488, "percentage": 10.9, "elapsed_time": "0:03:42", "remaining_time": "0:30:22"}
+{"current_steps": 30, "total_steps": 266, "loss": 0.0599, "lr": 9.996112860009688e-05, "epoch": 0.22556390977443608, "percentage": 11.28, "elapsed_time": "0:03:50", "remaining_time": "0:30:12"}
+{"current_steps": 31, "total_steps": 266, "loss": 0.0673, "lr": 9.993090225407743e-05, "epoch": 0.23308270676691728, "percentage": 11.65, "elapsed_time": "0:03:57", "remaining_time": "0:30:02"}
+{"current_steps": 32, "total_steps": 266, "loss": 0.063, "lr": 9.989204876292688e-05, "epoch": 0.24060150375939848, "percentage": 12.03, "elapsed_time": "0:04:05", "remaining_time": "0:29:55"}
+{"current_steps": 33, "total_steps": 266, "loss": 0.0563, "lr": 9.984457483981669e-05, "epoch": 0.24812030075187969, "percentage": 12.41, "elapsed_time": "0:04:12", "remaining_time": "0:29:45"}
+{"current_steps": 34, "total_steps": 266, "loss": 0.0449, "lr": 9.978848868737098e-05, "epoch": 0.2556390977443609, "percentage": 12.78, "elapsed_time": "0:04:20", "remaining_time": "0:29:36"}
+{"current_steps": 35, "total_steps": 266, "loss": 0.0492, "lr": 9.972379999624936e-05, "epoch": 0.2631578947368421, "percentage": 13.16, "elapsed_time": "0:04:27", "remaining_time": "0:29:26"}
+{"current_steps": 36, "total_steps": 266, "loss": 0.0384, "lr": 9.96505199434725e-05, "epoch": 0.2706766917293233, "percentage": 13.53, "elapsed_time": "0:04:35", "remaining_time": "0:29:17"}
+{"current_steps": 37, "total_steps": 266, "loss": 0.052, "lr": 9.956866119049095e-05, "epoch": 0.2781954887218045, "percentage": 13.91, "elapsed_time": "0:04:42", "remaining_time": "0:29:08"}
+{"current_steps": 38, "total_steps": 266, "loss": 0.0499, "lr": 9.947823788099753e-05, "epoch": 0.2857142857142857, "percentage": 14.29, "elapsed_time": "0:04:49", "remaining_time": "0:28:59"}
+{"current_steps": 39, "total_steps": 266, "loss": 0.0382, "lr": 9.937926563848346e-05, "epoch": 0.2932330827067669, "percentage": 14.66, "elapsed_time": "0:04:57", "remaining_time": "0:28:52"}
+{"current_steps": 40, "total_steps": 266, "loss": 0.0424, "lr": 9.927176156353899e-05, "epoch": 0.3007518796992481, "percentage": 15.04, "elapsed_time": "0:05:05", "remaining_time": "0:28:43"}
+{"current_steps": 41, "total_steps": 266, "loss": 0.0477, "lr": 9.91557442308987e-05, "epoch": 0.3082706766917293, "percentage": 15.41, "elapsed_time": "0:05:12", "remaining_time": "0:28:34"}
+{"current_steps": 42, "total_steps": 266, "loss": 0.0423, "lr": 9.903123368623216e-05, "epoch": 0.3157894736842105, "percentage": 15.79, "elapsed_time": "0:05:19", "remaining_time": "0:28:25"}
+{"current_steps": 43, "total_steps": 266, "loss": 0.0373, "lr": 9.889825144268029e-05, "epoch": 0.3233082706766917, "percentage": 16.17, "elapsed_time": "0:05:27", "remaining_time": "0:28:17"}
+{"current_steps": 44, "total_steps": 266, "loss": 0.0532, "lr": 9.875682047713846e-05, "epoch": 0.3308270676691729, "percentage": 16.54, "elapsed_time": "0:05:34", "remaining_time": "0:28:08"}
+{"current_steps": 45, "total_steps": 266, "loss": 0.0302, "lr": 9.860696522628639e-05, "epoch": 0.3383458646616541, "percentage": 16.92, "elapsed_time": "0:05:42", "remaining_time": "0:28:00"}
+{"current_steps": 46, "total_steps": 266, "loss": 0.043, "lr": 9.844871158236591e-05, "epoch": 0.3458646616541353, "percentage": 17.29, "elapsed_time": "0:05:49", "remaining_time": "0:27:51"}
+{"current_steps": 47, "total_steps": 266, "loss": 0.0414, "lr": 9.828208688870735e-05, "epoch": 0.3533834586466165, "percentage": 17.67, "elapsed_time": "0:05:56", "remaining_time": "0:27:43"}
+{"current_steps": 48, "total_steps": 266, "loss": 0.0442, "lr": 9.810711993500507e-05, "epoch": 0.3609022556390977, "percentage": 18.05, "elapsed_time": "0:06:04", "remaining_time": "0:27:34"}
+{"current_steps": 49, "total_steps": 266, "loss": 0.0397, "lr": 9.792384095234313e-05, "epoch": 0.3684210526315789, "percentage": 18.42, "elapsed_time": "0:06:11", "remaining_time": "0:27:26"}
+{"current_steps": 50, "total_steps": 266, "loss": 0.0294, "lr": 9.773228160797188e-05, "epoch": 0.37593984962406013, "percentage": 18.8, "elapsed_time": "0:06:19", "remaining_time": "0:27:18"}
+{"current_steps": 51, "total_steps": 266, "loss": 0.0388, "lr": 9.753247499983649e-05, "epoch": 0.38345864661654133, "percentage": 19.17, "elapsed_time": "0:06:26", "remaining_time": "0:27:09"}
+{"current_steps": 52, "total_steps": 266, "loss": 0.0464, "lr": 9.732445565085824e-05, "epoch": 0.39097744360902253, "percentage": 19.55, "elapsed_time": "0:06:33", "remaining_time": "0:27:01"}
+{"current_steps": 53, "total_steps": 266, "loss": 0.0441, "lr": 9.71082595029695e-05, "epoch": 0.39849624060150374, "percentage": 19.92, "elapsed_time": "0:06:41", "remaining_time": "0:26:53"}
+{"current_steps": 54, "total_steps": 266, "loss": 0.0403, "lr": 9.688392391090373e-05, "epoch": 0.40601503759398494, "percentage": 20.3, "elapsed_time": "0:06:48", "remaining_time": "0:26:45"}
+{"current_steps": 55, "total_steps": 266, "loss": 0.0414, "lr": 9.665148763574123e-05, "epoch": 0.41353383458646614, "percentage": 20.68, "elapsed_time": "0:06:56", "remaining_time": "0:26:36"}
+{"current_steps": 56, "total_steps": 266, "loss": 0.0348, "lr": 9.64109908382119e-05, "epoch": 0.42105263157894735, "percentage": 21.05, "elapsed_time": "0:07:03", "remaining_time": "0:26:28"}
+{"current_steps": 57, "total_steps": 266, "loss": 0.0353, "lr": 9.616247507175623e-05, "epoch": 0.42857142857142855, "percentage": 21.43, "elapsed_time": "0:07:11", "remaining_time": "0:26:20"}
+{"current_steps": 58, "total_steps": 266, "loss": 0.0354, "lr": 9.590598327534564e-05, "epoch": 0.43609022556390975, "percentage": 21.8, "elapsed_time": "0:07:18", "remaining_time": "0:26:12"}
+{"current_steps": 59, "total_steps": 266, "loss": 0.0436, "lr": 9.564155976606339e-05, "epoch": 0.44360902255639095, "percentage": 22.18, "elapsed_time": "0:07:25", "remaining_time": "0:26:04"}
+{"current_steps": 60, "total_steps": 266, "loss": 0.0448, "lr": 9.536925023144742e-05, "epoch": 0.45112781954887216, "percentage": 22.56, "elapsed_time": "0:07:33", "remaining_time": "0:25:56"}
+{"current_steps": 61, "total_steps": 266, "loss": 0.0456, "lr": 9.508910172159635e-05, "epoch": 0.45864661654135336, "percentage": 22.93, "elapsed_time": "0:07:40", "remaining_time": "0:25:48"}
+{"current_steps": 62, "total_steps": 266, "loss": 0.0417, "lr": 9.480116264104011e-05, "epoch": 0.46616541353383456, "percentage": 23.31, "elapsed_time": "0:07:48", "remaining_time": "0:25:40"}
+{"current_steps": 63, "total_steps": 266, "loss": 0.0427, "lr": 9.450548274037653e-05, "epoch": 0.47368421052631576, "percentage": 23.68, "elapsed_time": "0:07:55", "remaining_time": "0:25:32"}
+{"current_steps": 64, "total_steps": 266, "loss": 0.0317, "lr": 9.420211310767533e-05, "epoch": 0.48120300751879697, "percentage": 24.06, "elapsed_time": "0:08:02", "remaining_time": "0:25:24"}
+{"current_steps": 65, "total_steps": 266, "loss": 0.0308, "lr": 9.389110615965102e-05, "epoch": 0.48872180451127817, "percentage": 24.44, "elapsed_time": "0:08:10", "remaining_time": "0:25:16"}
+{"current_steps": 66, "total_steps": 266, "loss": 0.0404, "lr": 9.35725156326063e-05, "epoch": 0.49624060150375937, "percentage": 24.81, "elapsed_time": "0:08:17", "remaining_time": "0:25:08"}
+{"current_steps": 67, "total_steps": 266, "loss": 0.0383, "lr": 9.324639657314742e-05, "epoch": 0.5037593984962406, "percentage": 25.19, "elapsed_time": "0:08:25", "remaining_time": "0:25:00"}
+{"current_steps": 68, "total_steps": 266, "loss": 0.0419, "lr": 9.291280532867302e-05, "epoch": 0.5112781954887218, "percentage": 25.56, "elapsed_time": "0:08:32", "remaining_time": "0:24:52"}
+{"current_steps": 69, "total_steps": 266, "loss": 0.0301, "lr": 9.257179953763845e-05, "epoch": 0.518796992481203, "percentage": 25.94, "elapsed_time": "0:08:39", "remaining_time": "0:24:44"}
+{"current_steps": 70, "total_steps": 266, "loss": 0.0355, "lr": 9.222343811959693e-05, "epoch": 0.5263157894736842, "percentage": 26.32, "elapsed_time": "0:08:47", "remaining_time": "0:24:36"}
+{"current_steps": 71, "total_steps": 266, "loss": 0.0379, "lr": 9.186778126501916e-05, "epoch": 0.5338345864661654, "percentage": 26.69, "elapsed_time": "0:08:54", "remaining_time": "0:24:28"}
+{"current_steps": 72, "total_steps": 266, "loss": 0.03, "lr": 9.150489042489367e-05, "epoch": 0.5413533834586466, "percentage": 27.07, "elapsed_time": "0:09:02", "remaining_time": "0:24:20"}
+{"current_steps": 73, "total_steps": 266, "loss": 0.038, "lr": 9.113482830010918e-05, "epoch": 0.5488721804511278, "percentage": 27.44, "elapsed_time": "0:09:09", "remaining_time": "0:24:12"}
+{"current_steps": 74, "total_steps": 266, "loss": 0.0321, "lr": 9.075765883062093e-05, "epoch": 0.556390977443609, "percentage": 27.82, "elapsed_time": "0:09:16", "remaining_time": "0:24:05"}
+{"current_steps": 75, "total_steps": 266, "loss": 0.0369, "lr": 9.037344718440322e-05, "epoch": 0.5639097744360902, "percentage": 28.2, "elapsed_time": "0:09:24", "remaining_time": "0:23:57"}
+{"current_steps": 76, "total_steps": 266, "loss": 0.0429, "lr": 8.99822597461894e-05, "epoch": 0.5714285714285714, "percentage": 28.57, "elapsed_time": "0:09:31", "remaining_time": "0:23:49"}
+{"current_steps": 77, "total_steps": 266, "loss": 0.0351, "lr": 8.958416410600187e-05, "epoch": 0.5789473684210527, "percentage": 28.95, "elapsed_time": "0:09:39", "remaining_time": "0:23:41"}
+{"current_steps": 78, "total_steps": 266, "loss": 0.0425, "lr": 8.917922904747384e-05, "epoch": 0.5864661654135338, "percentage": 29.32, "elapsed_time": "0:09:46", "remaining_time": "0:23:33"}
+{"current_steps": 79, "total_steps": 266, "loss": 0.0322, "lr": 8.876752453596462e-05, "epoch": 0.5939849624060151, "percentage": 29.7, "elapsed_time": "0:09:53", "remaining_time": "0:23:25"}
+{"current_steps": 80, "total_steps": 266, "loss": 0.0446, "lr": 8.834912170647101e-05, "epoch": 0.6015037593984962, "percentage": 30.08, "elapsed_time": "0:10:01", "remaining_time": "0:23:18"}
+{"current_steps": 81, "total_steps": 266, "loss": 0.0424, "lr": 8.792409285133642e-05, "epoch": 0.6090225563909775, "percentage": 30.45, "elapsed_time": "0:10:08", "remaining_time": "0:23:10"}
+{"current_steps": 82, "total_steps": 266, "loss": 0.0342, "lr": 8.749251140776016e-05, "epoch": 0.6165413533834586, "percentage": 30.83, "elapsed_time": "0:10:16", "remaining_time": "0:23:02"}
+{"current_steps": 83, "total_steps": 266, "loss": 0.0321, "lr": 8.705445194510868e-05, "epoch": 0.6240601503759399, "percentage": 31.2, "elapsed_time": "0:10:23", "remaining_time": "0:22:54"}
+{"current_steps": 84, "total_steps": 266, "loss": 0.0371, "lr": 8.66099901520315e-05, "epoch": 0.631578947368421, "percentage": 31.58, "elapsed_time": "0:10:30", "remaining_time": "0:22:47"}
+{"current_steps": 85, "total_steps": 266, "loss": 0.0349, "lr": 8.615920282338355e-05, "epoch": 0.6390977443609023, "percentage": 31.95, "elapsed_time": "0:10:38", "remaining_time": "0:22:39"}
+{"current_steps": 86, "total_steps": 266, "loss": 0.0287, "lr": 8.570216784695637e-05, "epoch": 0.6466165413533834, "percentage": 32.33, "elapsed_time": "0:10:45", "remaining_time": "0:22:31"}
+{"current_steps": 87, "total_steps": 266, "loss": 0.0379, "lr": 8.52389641900206e-05, "epoch": 0.6541353383458647, "percentage": 32.71, "elapsed_time": "0:10:53", "remaining_time": "0:22:23"}
+{"current_steps": 88, "total_steps": 266, "loss": 0.0264, "lr": 8.476967188568188e-05, "epoch": 0.6616541353383458, "percentage": 33.08, "elapsed_time": "0:11:00", "remaining_time": "0:22:16"}
+{"current_steps": 89, "total_steps": 266, "loss": 0.028, "lr": 8.429437201905254e-05, "epoch": 0.6691729323308271, "percentage": 33.46, "elapsed_time": "0:11:08", "remaining_time": "0:22:08"}
+{"current_steps": 90, "total_steps": 266, "loss": 0.0353, "lr": 8.381314671324159e-05, "epoch": 0.6766917293233082, "percentage": 33.83, "elapsed_time": "0:11:15", "remaining_time": "0:22:00"}
+{"current_steps": 91, "total_steps": 266, "loss": 0.0423, "lr": 8.332607911516545e-05, "epoch": 0.6842105263157895, "percentage": 34.21, "elapsed_time": "0:11:22", "remaining_time": "0:21:53"}
+{"current_steps": 92, "total_steps": 266, "loss": 0.0288, "lr": 8.283325338118153e-05, "epoch": 0.6917293233082706, "percentage": 34.59, "elapsed_time": "0:11:30", "remaining_time": "0:21:45"}
+{"current_steps": 93, "total_steps": 266, "loss": 0.0319, "lr": 8.233475466254765e-05, "epoch": 0.6992481203007519, "percentage": 34.96, "elapsed_time": "0:11:37", "remaining_time": "0:21:37"}
+{"current_steps": 94, "total_steps": 266, "loss": 0.0413, "lr": 8.183066909070947e-05, "epoch": 0.706766917293233, "percentage": 35.34, "elapsed_time": "0:11:45", "remaining_time": "0:21:30"}
+{"current_steps": 95, "total_steps": 266, "loss": 0.0319, "lr": 8.132108376241849e-05, "epoch": 0.7142857142857143, "percentage": 35.71, "elapsed_time": "0:11:52", "remaining_time": "0:21:22"}
+{"current_steps": 96, "total_steps": 266, "loss": 0.0415, "lr": 8.08060867246834e-05, "epoch": 0.7218045112781954, "percentage": 36.09, "elapsed_time": "0:11:59", "remaining_time": "0:21:14"}
+{"current_steps": 97, "total_steps": 266, "loss": 0.0307, "lr": 8.028576695955711e-05, "epoch": 0.7293233082706767, "percentage": 36.47, "elapsed_time": "0:12:07", "remaining_time": "0:21:07"}
+{"current_steps": 98, "total_steps": 266, "loss": 0.0292, "lr": 7.97602143687623e-05, "epoch": 0.7368421052631579, "percentage": 36.84, "elapsed_time": "0:12:14", "remaining_time": "0:20:59"}
+{"current_steps": 99, "total_steps": 266, "loss": 0.0304, "lr": 7.922951975815811e-05, "epoch": 0.7443609022556391, "percentage": 37.22, "elapsed_time": "0:12:22", "remaining_time": "0:20:51"}
+{"current_steps": 100, "total_steps": 266, "loss": 0.0318, "lr": 7.869377482205042e-05, "epoch": 0.7518796992481203, "percentage": 37.59, "elapsed_time": "0:12:29", "remaining_time": "0:20:44"}
+{"current_steps": 101, "total_steps": 266, "loss": 0.027, "lr": 7.815307212734888e-05, "epoch": 0.7593984962406015, "percentage": 37.97, "elapsed_time": "0:12:36", "remaining_time": "0:20:36"}
+{"current_steps": 102, "total_steps": 266, "loss": 0.0339, "lr": 7.760750509757298e-05, "epoch": 0.7669172932330827, "percentage": 38.35, "elapsed_time": "0:12:44", "remaining_time": "0:20:28"}
+{"current_steps": 103, "total_steps": 266, "loss": 0.0228, "lr": 7.705716799671019e-05, "epoch": 0.7744360902255639, "percentage": 38.72, "elapsed_time": "0:12:51", "remaining_time": "0:20:21"}
+{"current_steps": 104, "total_steps": 266, "loss": 0.0357, "lr": 7.650215591292888e-05, "epoch": 0.7819548872180451, "percentage": 39.1, "elapsed_time": "0:12:59", "remaining_time": "0:20:13"}
+{"current_steps": 105, "total_steps": 266, "loss": 0.0285, "lr": 7.594256474214882e-05, "epoch": 0.7894736842105263, "percentage": 39.47, "elapsed_time": "0:13:06", "remaining_time": "0:20:06"}
+{"current_steps": 106, "total_steps": 266, "loss": 0.0359, "lr": 7.537849117147212e-05, "epoch": 0.7969924812030075, "percentage": 39.85, "elapsed_time": "0:13:13", "remaining_time": "0:19:58"}
+{"current_steps": 107, "total_steps": 266, "loss": 0.0367, "lr": 7.481003266247744e-05, "epoch": 0.8045112781954887, "percentage": 40.23, "elapsed_time": "0:13:21", "remaining_time": "0:19:50"}
+{"current_steps": 108, "total_steps": 266, "loss": 0.0358, "lr": 7.423728743438048e-05, "epoch": 0.8120300751879699, "percentage": 40.6, "elapsed_time": "0:13:28", "remaining_time": "0:19:43"}
+{"current_steps": 109, "total_steps": 266, "loss": 0.0329, "lr": 7.366035444706347e-05, "epoch": 0.8195488721804511, "percentage": 40.98, "elapsed_time": "0:13:36", "remaining_time": "0:19:35"}
+{"current_steps": 110, "total_steps": 266, "loss": 0.0364, "lr": 7.307933338397667e-05, "epoch": 0.8270676691729323, "percentage": 41.35, "elapsed_time": "0:13:43", "remaining_time": "0:19:28"}
+{"current_steps": 111, "total_steps": 266, "loss": 0.0328, "lr": 7.249432463491498e-05, "epoch": 0.8345864661654135, "percentage": 41.73, "elapsed_time": "0:13:51", "remaining_time": "0:19:20"}
+{"current_steps": 112, "total_steps": 266, "loss": 0.0242, "lr": 7.190542927867234e-05, "epoch": 0.8421052631578947, "percentage": 42.11, "elapsed_time": "0:13:58", "remaining_time": "0:19:12"}
+{"current_steps": 113, "total_steps": 266, "loss": 0.0277, "lr": 7.131274906557725e-05, "epoch": 0.849624060150376, "percentage": 42.48, "elapsed_time": "0:14:05", "remaining_time": "0:19:05"}
+{"current_steps": 114, "total_steps": 266, "loss": 0.0282, "lr": 7.071638639991207e-05, "epoch": 0.8571428571428571, "percentage": 42.86, "elapsed_time": "0:14:13", "remaining_time": "0:18:57"}
+{"current_steps": 115, "total_steps": 266, "loss": 0.0311, "lr": 7.011644432221958e-05, "epoch": 0.8646616541353384, "percentage": 43.23, "elapsed_time": "0:14:20", "remaining_time": "0:18:50"}
+{"current_steps": 116, "total_steps": 266, "loss": 0.0414, "lr": 6.95130264914993e-05, "epoch": 0.8721804511278195, "percentage": 43.61, "elapsed_time": "0:14:28", "remaining_time": "0:18:42"}
+{"current_steps": 117, "total_steps": 266, "loss": 0.0279, "lr": 6.890623716729724e-05, "epoch": 0.8796992481203008, "percentage": 43.98, "elapsed_time": "0:14:35", "remaining_time": "0:18:34"}
+{"current_steps": 118, "total_steps": 266, "loss": 0.0298, "lr": 6.82961811916917e-05, "epoch": 0.8872180451127819, "percentage": 44.36, "elapsed_time": "0:14:42", "remaining_time": "0:18:27"}
+{"current_steps": 119, "total_steps": 266, "loss": 0.0263, "lr": 6.768296397117848e-05, "epoch": 0.8947368421052632, "percentage": 44.74, "elapsed_time": "0:14:50", "remaining_time": "0:18:19"}
+{"current_steps": 120, "total_steps": 266, "loss": 0.0331, "lr": 6.706669145845863e-05, "epoch": 0.9022556390977443, "percentage": 45.11, "elapsed_time": "0:14:57", "remaining_time": "0:18:12"}
+{"current_steps": 121, "total_steps": 266, "loss": 0.0323, "lr": 6.644747013413168e-05, "epoch": 0.9097744360902256, "percentage": 45.49, "elapsed_time": "0:15:05", "remaining_time": "0:18:04"}
+{"current_steps": 122, "total_steps": 266, "loss": 0.0356, "lr": 6.582540698829781e-05, "epoch": 0.9172932330827067, "percentage": 45.86, "elapsed_time": "0:15:12", "remaining_time": "0:17:57"}
+{"current_steps": 123, "total_steps": 266, "loss": 0.0374, "lr": 6.520060950207185e-05, "epoch": 0.924812030075188, "percentage": 46.24, "elapsed_time": "0:15:19", "remaining_time": "0:17:49"}
+{"current_steps": 124, "total_steps": 266, "loss": 0.0281, "lr": 6.457318562901256e-05, "epoch": 0.9323308270676691, "percentage": 46.62, "elapsed_time": "0:15:27", "remaining_time": "0:17:42"}
+{"current_steps": 125, "total_steps": 266, "loss": 0.0344, "lr": 6.394324377647028e-05, "epoch": 0.9398496240601504, "percentage": 46.99, "elapsed_time": "0:15:34", "remaining_time": "0:17:34"}
+{"current_steps": 126, "total_steps": 266, "loss": 0.0289, "lr": 6.331089278685599e-05, "epoch": 0.9473684210526315, "percentage": 47.37, "elapsed_time": "0:15:42", "remaining_time": "0:17:26"}
+{"current_steps": 127, "total_steps": 266, "loss": 0.0254, "lr": 6.26762419188355e-05, "epoch": 0.9548872180451128, "percentage": 47.74, "elapsed_time": "0:15:49", "remaining_time": "0:17:19"}
+{"current_steps": 128, "total_steps": 266, "loss": 0.0423, "lr": 6.203940082845144e-05, "epoch": 0.9624060150375939, "percentage": 48.12, "elapsed_time": "0:15:57", "remaining_time": "0:17:11"}
+{"current_steps": 129, "total_steps": 266, "loss": 0.0331, "lr": 6.140047955017671e-05, "epoch": 0.9699248120300752, "percentage": 48.5, "elapsed_time": "0:16:04", "remaining_time": "0:17:04"}
+{"current_steps": 130, "total_steps": 266, "loss": 0.0344, "lr": 6.075958847790262e-05, "epoch": 0.9774436090225563, "percentage": 48.87, "elapsed_time": "0:16:11", "remaining_time": "0:16:56"}
+{"current_steps": 131, "total_steps": 266, "loss": 0.0264, "lr": 6.011683834586473e-05, "epoch": 0.9849624060150376, "percentage": 49.25, "elapsed_time": "0:16:19", "remaining_time": "0:16:49"}
+{"current_steps": 132, "total_steps": 266, "loss": 0.0237, "lr": 5.947234020951015e-05, "epoch": 0.9924812030075187, "percentage": 49.62, "elapsed_time": "0:16:26", "remaining_time": "0:16:41"}
+{"current_steps": 133, "total_steps": 266, "loss": 0.0317, "lr": 5.882620542630901e-05, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:16:34", "remaining_time": "0:16:34"}
+{"current_steps": 134, "total_steps": 266, "loss": 0.0268, "lr": 5.8178545636514145e-05, "epoch": 1.0075187969924813, "percentage": 50.38, "elapsed_time": "0:16:41", "remaining_time": "0:16:26"}
+{"current_steps": 135, "total_steps": 266, "loss": 0.0223, "lr": 5.752947274387147e-05, "epoch": 1.0150375939849625, "percentage": 50.75, "elapsed_time": "0:16:48", "remaining_time": "0:16:19"}
+{"current_steps": 136, "total_steps": 266, "loss": 0.0304, "lr": 5.687909889628529e-05, "epoch": 1.0225563909774436, "percentage": 51.13, "elapsed_time": "0:16:56", "remaining_time": "0:16:11"}
+{"current_steps": 137, "total_steps": 266, "loss": 0.0278, "lr": 5.622753646644102e-05, "epoch": 1.0300751879699248, "percentage": 51.5, "elapsed_time": "0:17:03", "remaining_time": "0:16:03"}
+{"current_steps": 138, "total_steps": 266, "loss": 0.0259, "lr": 5.557489803238933e-05, "epoch": 1.037593984962406, "percentage": 51.88, "elapsed_time": "0:17:11", "remaining_time": "0:15:56"}
+{"current_steps": 139, "total_steps": 266, "loss": 0.0198, "lr": 5.492129635809473e-05, "epoch": 1.045112781954887, "percentage": 52.26, "elapsed_time": "0:17:18", "remaining_time": "0:15:48"}
+{"current_steps": 140, "total_steps": 266, "loss": 0.0191, "lr": 5.426684437395196e-05, "epoch": 1.0526315789473684, "percentage": 52.63, "elapsed_time": "0:17:25", "remaining_time": "0:15:41"}
+{"current_steps": 141, "total_steps": 266, "loss": 0.0214, "lr": 5.361165515727374e-05, "epoch": 1.0601503759398496, "percentage": 53.01, "elapsed_time": "0:17:33", "remaining_time": "0:15:33"}
+{"current_steps": 142, "total_steps": 266, "loss": 0.0243, "lr": 5.295584191275308e-05, "epoch": 1.0676691729323309, "percentage": 53.38, "elapsed_time": "0:17:40", "remaining_time": "0:15:26"}
+{"current_steps": 143, "total_steps": 266, "loss": 0.029, "lr": 5.229951795290353e-05, "epoch": 1.0751879699248121, "percentage": 53.76, "elapsed_time": "0:17:48", "remaining_time": "0:15:18"}
+{"current_steps": 144, "total_steps": 266, "loss": 0.0204, "lr": 5.164279667848094e-05, "epoch": 1.0827067669172932, "percentage": 54.14, "elapsed_time": "0:17:55", "remaining_time": "0:15:11"}
+{"current_steps": 145, "total_steps": 266, "loss": 0.0209, "lr": 5.0985791558889785e-05, "epoch": 1.0902255639097744, "percentage": 54.51, "elapsed_time": "0:18:03", "remaining_time": "0:15:03"}
+{"current_steps": 146, "total_steps": 266, "loss": 0.0285, "lr": 5.032861611257783e-05, "epoch": 1.0977443609022557, "percentage": 54.89, "elapsed_time": "0:18:10", "remaining_time": "0:14:56"}
+{"current_steps": 147, "total_steps": 266, "loss": 0.0204, "lr": 4.967138388742218e-05, "epoch": 1.1052631578947367, "percentage": 55.26, "elapsed_time": "0:18:17", "remaining_time": "0:14:48"}
+{"current_steps": 148, "total_steps": 266, "loss": 0.0314, "lr": 4.901420844111021e-05, "epoch": 1.112781954887218, "percentage": 55.64, "elapsed_time": "0:18:25", "remaining_time": "0:14:41"}
+{"current_steps": 149, "total_steps": 266, "loss": 0.0281, "lr": 4.835720332151907e-05, "epoch": 1.1203007518796992, "percentage": 56.02, "elapsed_time": "0:18:32", "remaining_time": "0:14:33"}
+{"current_steps": 150, "total_steps": 266, "loss": 0.0248, "lr": 4.770048204709648e-05, "epoch": 1.1278195488721805, "percentage": 56.39, "elapsed_time": "0:18:40", "remaining_time": "0:14:26"}
+{"current_steps": 151, "total_steps": 266, "loss": 0.0311, "lr": 4.7044158087246926e-05, "epoch": 1.1353383458646618, "percentage": 56.77, "elapsed_time": "0:18:47", "remaining_time": "0:14:18"}
+{"current_steps": 152, "total_steps": 266, "loss": 0.0218, "lr": 4.6388344842726264e-05, "epoch": 1.1428571428571428, "percentage": 57.14, "elapsed_time": "0:18:54", "remaining_time": "0:14:11"}
+{"current_steps": 153, "total_steps": 266, "loss": 0.0271, "lr": 4.5733155626048036e-05, "epoch": 1.150375939849624, "percentage": 57.52, "elapsed_time": "0:19:02", "remaining_time": "0:14:03"}
+{"current_steps": 154, "total_steps": 266, "loss": 0.0264, "lr": 4.507870364190527e-05, "epoch": 1.1578947368421053, "percentage": 57.89, "elapsed_time": "0:19:09", "remaining_time": "0:13:56"}
+{"current_steps": 155, "total_steps": 266, "loss": 0.024, "lr": 4.4425101967610674e-05, "epoch": 1.1654135338345863, "percentage": 58.27, "elapsed_time": "0:19:17", "remaining_time": "0:13:48"}
+{"current_steps": 156, "total_steps": 266, "loss": 0.0271, "lr": 4.377246353355899e-05, "epoch": 1.1729323308270676, "percentage": 58.65, "elapsed_time": "0:19:24", "remaining_time": "0:13:41"}
+{"current_steps": 157, "total_steps": 266, "loss": 0.0278, "lr": 4.312090110371473e-05, "epoch": 1.1804511278195489, "percentage": 59.02, "elapsed_time": "0:19:31", "remaining_time": "0:13:33"}
+{"current_steps": 158, "total_steps": 266, "loss": 0.0292, "lr": 4.247052725612852e-05, "epoch": 1.1879699248120301, "percentage": 59.4, "elapsed_time": "0:19:39", "remaining_time": "0:13:26"}
+{"current_steps": 159, "total_steps": 266, "loss": 0.0234, "lr": 4.1821454363485866e-05, "epoch": 1.1954887218045114, "percentage": 59.77, "elapsed_time": "0:19:47", "remaining_time": "0:13:18"}
+{"current_steps": 160, "total_steps": 266, "loss": 0.0206, "lr": 4.1173794573690996e-05, "epoch": 1.2030075187969924, "percentage": 60.15, "elapsed_time": "0:19:54", "remaining_time": "0:13:11"}
+{"current_steps": 161, "total_steps": 266, "loss": 0.0227, "lr": 4.052765979048986e-05, "epoch": 1.2105263157894737, "percentage": 60.53, "elapsed_time": "0:20:02", "remaining_time": "0:13:04"}
+{"current_steps": 162, "total_steps": 266, "loss": 0.0205, "lr": 3.988316165413528e-05, "epoch": 1.218045112781955, "percentage": 60.9, "elapsed_time": "0:20:09", "remaining_time": "0:12:56"}
+{"current_steps": 163, "total_steps": 266, "loss": 0.029, "lr": 3.924041152209739e-05, "epoch": 1.225563909774436, "percentage": 61.28, "elapsed_time": "0:20:17", "remaining_time": "0:12:49"}
+{"current_steps": 164, "total_steps": 266, "loss": 0.0271, "lr": 3.859952044982329e-05, "epoch": 1.2330827067669172, "percentage": 61.65, "elapsed_time": "0:20:24", "remaining_time": "0:12:41"}
+{"current_steps": 165, "total_steps": 266, "loss": 0.0213, "lr": 3.7960599171548574e-05, "epoch": 1.2406015037593985, "percentage": 62.03, "elapsed_time": "0:20:32", "remaining_time": "0:12:34"}
+{"current_steps": 166, "total_steps": 266, "loss": 0.0258, "lr": 3.732375808116451e-05, "epoch": 1.2481203007518797, "percentage": 62.41, "elapsed_time": "0:20:39", "remaining_time": "0:12:26"}
+{"current_steps": 167, "total_steps": 266, "loss": 0.0229, "lr": 3.668910721314402e-05, "epoch": 1.255639097744361, "percentage": 62.78, "elapsed_time": "0:20:46", "remaining_time": "0:12:19"}
+{"current_steps": 168, "total_steps": 266, "loss": 0.0265, "lr": 3.605675622352973e-05, "epoch": 1.263157894736842, "percentage": 63.16, "elapsed_time": "0:20:54", "remaining_time": "0:12:11"}
+{"current_steps": 169, "total_steps": 266, "loss": 0.0256, "lr": 3.542681437098745e-05, "epoch": 1.2706766917293233, "percentage": 63.53, "elapsed_time": "0:21:01", "remaining_time": "0:12:04"}
+{"current_steps": 170, "total_steps": 266, "loss": 0.0213, "lr": 3.479939049792817e-05, "epoch": 1.2781954887218046, "percentage": 63.91, "elapsed_time": "0:21:09", "remaining_time": "0:11:56"}
+{"current_steps": 171, "total_steps": 266, "loss": 0.0266, "lr": 3.417459301170219e-05, "epoch": 1.2857142857142856, "percentage": 64.29, "elapsed_time": "0:21:16", "remaining_time": "0:11:49"}
+{"current_steps": 172, "total_steps": 266, "loss": 0.0193, "lr": 3.355252986586832e-05, "epoch": 1.2932330827067668, "percentage": 64.66, "elapsed_time": "0:21:23", "remaining_time": "0:11:41"}
+{"current_steps": 173, "total_steps": 266, "loss": 0.0258, "lr": 3.293330854154136e-05, "epoch": 1.300751879699248, "percentage": 65.04, "elapsed_time": "0:21:31", "remaining_time": "0:11:34"}
+{"current_steps": 174, "total_steps": 266, "loss": 0.0159, "lr": 3.2317036028821523e-05, "epoch": 1.3082706766917294, "percentage": 65.41, "elapsed_time": "0:21:38", "remaining_time": "0:11:26"}
+{"current_steps": 175, "total_steps": 266, "loss": 0.0215, "lr": 3.1703818808308324e-05, "epoch": 1.3157894736842106, "percentage": 65.79, "elapsed_time": "0:21:46", "remaining_time": "0:11:19"}
+{"current_steps": 176, "total_steps": 266, "loss": 0.0268, "lr": 3.109376283270277e-05, "epoch": 1.3233082706766917, "percentage": 66.17, "elapsed_time": "0:21:53", "remaining_time": "0:11:11"}
+{"current_steps": 177, "total_steps": 266, "loss": 0.0238, "lr": 3.0486973508500727e-05, "epoch": 1.330827067669173, "percentage": 66.54, "elapsed_time": "0:22:00", "remaining_time": "0:11:04"}
+{"current_steps": 178, "total_steps": 266, "loss": 0.0259, "lr": 2.988355567778043e-05, "epoch": 1.3383458646616542, "percentage": 66.92, "elapsed_time": "0:22:08", "remaining_time": "0:10:56"}
+{"current_steps": 179, "total_steps": 266, "loss": 0.025, "lr": 2.9283613600087933e-05, "epoch": 1.3458646616541352, "percentage": 67.29, "elapsed_time": "0:22:15", "remaining_time": "0:10:49"}
+{"current_steps": 180, "total_steps": 266, "loss": 0.0194, "lr": 2.8687250934422772e-05, "epoch": 1.3533834586466165, "percentage": 67.67, "elapsed_time": "0:22:23", "remaining_time": "0:10:41"}
+{"current_steps": 181, "total_steps": 266, "loss": 0.0189, "lr": 2.8094570721327662e-05, "epoch": 1.3609022556390977, "percentage": 68.05, "elapsed_time": "0:22:30", "remaining_time": "0:10:34"}
+{"current_steps": 182, "total_steps": 266, "loss": 0.0243, "lr": 2.750567536508504e-05, "epoch": 1.368421052631579, "percentage": 68.42, "elapsed_time": "0:22:38", "remaining_time": "0:10:26"}
+{"current_steps": 183, "total_steps": 266, "loss": 0.0257, "lr": 2.6920666616023327e-05, "epoch": 1.3759398496240602, "percentage": 68.8, "elapsed_time": "0:22:45", "remaining_time": "0:10:19"}
+{"current_steps": 184, "total_steps": 266, "loss": 0.0275, "lr": 2.6339645552936536e-05, "epoch": 1.3834586466165413, "percentage": 69.17, "elapsed_time": "0:22:52", "remaining_time": "0:10:11"}
+{"current_steps": 185, "total_steps": 266, "loss": 0.023, "lr": 2.5762712565619528e-05, "epoch": 1.3909774436090225, "percentage": 69.55, "elapsed_time": "0:23:00", "remaining_time": "0:10:04"}
+{"current_steps": 186, "total_steps": 266, "loss": 0.0206, "lr": 2.5189967337522573e-05, "epoch": 1.3984962406015038, "percentage": 69.92, "elapsed_time": "0:23:07", "remaining_time": "0:09:56"}
+{"current_steps": 187, "total_steps": 266, "loss": 0.0229, "lr": 2.46215088285279e-05, "epoch": 1.4060150375939848, "percentage": 70.3, "elapsed_time": "0:23:15", "remaining_time": "0:09:49"}
+{"current_steps": 188, "total_steps": 266, "loss": 0.019, "lr": 2.4057435257851175e-05, "epoch": 1.413533834586466, "percentage": 70.68, "elapsed_time": "0:23:22", "remaining_time": "0:09:41"}
+{"current_steps": 189, "total_steps": 266, "loss": 0.0274, "lr": 2.349784408707112e-05, "epoch": 1.4210526315789473, "percentage": 71.05, "elapsed_time": "0:23:29", "remaining_time": "0:09:34"}
+{"current_steps": 190, "total_steps": 266, "loss": 0.0271, "lr": 2.2942832003289823e-05, "epoch": 1.4285714285714286, "percentage": 71.43, "elapsed_time": "0:23:37", "remaining_time": "0:09:26"}
+{"current_steps": 191, "total_steps": 266, "loss": 0.0263, "lr": 2.2392494902427025e-05, "epoch": 1.4360902255639099, "percentage": 71.8, "elapsed_time": "0:23:44", "remaining_time": "0:09:19"}
+{"current_steps": 192, "total_steps": 266, "loss": 0.0242, "lr": 2.1846927872651137e-05, "epoch": 1.443609022556391, "percentage": 72.18, "elapsed_time": "0:23:52", "remaining_time": "0:09:12"}
+{"current_steps": 193, "total_steps": 266, "loss": 0.024, "lr": 2.1306225177949585e-05, "epoch": 1.4511278195488722, "percentage": 72.56, "elapsed_time": "0:23:59", "remaining_time": "0:09:04"}
+{"current_steps": 194, "total_steps": 266, "loss": 0.0301, "lr": 2.07704802418419e-05, "epoch": 1.4586466165413534, "percentage": 72.93, "elapsed_time": "0:24:07", "remaining_time": "0:08:57"}
+{"current_steps": 195, "total_steps": 266, "loss": 0.0262, "lr": 2.0239785631237705e-05, "epoch": 1.4661654135338344, "percentage": 73.31, "elapsed_time": "0:24:14", "remaining_time": "0:08:49"}
+{"current_steps": 196, "total_steps": 266, "loss": 0.0179, "lr": 1.9714233040442915e-05, "epoch": 1.4736842105263157, "percentage": 73.68, "elapsed_time": "0:24:21", "remaining_time": "0:08:42"}
+{"current_steps": 197, "total_steps": 266, "loss": 0.0234, "lr": 1.9193913275316626e-05, "epoch": 1.481203007518797, "percentage": 74.06, "elapsed_time": "0:24:29", "remaining_time": "0:08:34"}
+{"current_steps": 198, "total_steps": 266, "loss": 0.0236, "lr": 1.8678916237581522e-05, "epoch": 1.4887218045112782, "percentage": 74.44, "elapsed_time": "0:24:36", "remaining_time": "0:08:27"}
+{"current_steps": 199, "total_steps": 266, "loss": 0.0176, "lr": 1.816933090929055e-05, "epoch": 1.4962406015037595, "percentage": 74.81, "elapsed_time": "0:24:44", "remaining_time": "0:08:19"}
+{"current_steps": 200, "total_steps": 266, "loss": 0.0258, "lr": 1.7665245337452368e-05, "epoch": 1.5037593984962405, "percentage": 75.19, "elapsed_time": "0:24:51", "remaining_time": "0:08:12"}
+{"current_steps": 200, "total_steps": 266, "eval_loss": 0.029665347188711166, "epoch": 1.5037593984962405, "percentage": 75.19, "elapsed_time": "0:24:58", "remaining_time": "0:08:14"}
+{"current_steps": 201, "total_steps": 266, "loss": 0.0224, "lr": 1.716674661881848e-05, "epoch": 1.5112781954887218, "percentage": 75.56, "elapsed_time": "0:25:05", "remaining_time": "0:08:06"}
+{"current_steps": 202, "total_steps": 266, "loss": 0.0223, "lr": 1.667392088483456e-05, "epoch": 1.518796992481203, "percentage": 75.94, "elapsed_time": "0:25:12", "remaining_time": "0:07:59"}
+{"current_steps": 203, "total_steps": 266, "loss": 0.0242, "lr": 1.6186853286758397e-05, "epoch": 1.526315789473684, "percentage": 76.32, "elapsed_time": "0:25:20", "remaining_time": "0:07:51"}
+{"current_steps": 204, "total_steps": 266, "loss": 0.025, "lr": 1.570562798094747e-05, "epoch": 1.5338345864661656, "percentage": 76.69, "elapsed_time": "0:25:27", "remaining_time": "0:07:44"}
+{"current_steps": 205, "total_steps": 266, "loss": 0.0241, "lr": 1.5230328114318127e-05, "epoch": 1.5413533834586466, "percentage": 77.07, "elapsed_time": "0:25:34", "remaining_time": "0:07:36"}
+{"current_steps": 206, "total_steps": 266, "loss": 0.0253, "lr": 1.4761035809979395e-05, "epoch": 1.5488721804511278, "percentage": 77.44, "elapsed_time": "0:25:42", "remaining_time": "0:07:29"}
+{"current_steps": 207, "total_steps": 266, "loss": 0.0236, "lr": 1.4297832153043656e-05, "epoch": 1.556390977443609, "percentage": 77.82, "elapsed_time": "0:25:49", "remaining_time": "0:07:21"}
+{"current_steps": 208, "total_steps": 266, "loss": 0.0278, "lr": 1.3840797176616466e-05, "epoch": 1.5639097744360901, "percentage": 78.2, "elapsed_time": "0:25:57", "remaining_time": "0:07:14"}
+{"current_steps": 209, "total_steps": 266, "loss": 0.0255, "lr": 1.3390009847968504e-05, "epoch": 1.5714285714285714, "percentage": 78.57, "elapsed_time": "0:26:04", "remaining_time": "0:07:06"}
+{"current_steps": 210, "total_steps": 266, "loss": 0.0254, "lr": 1.2945548054891321e-05, "epoch": 1.5789473684210527, "percentage": 78.95, "elapsed_time": "0:26:12", "remaining_time": "0:06:59"}
+{"current_steps": 211, "total_steps": 266, "loss": 0.0233, "lr": 1.2507488592239847e-05, "epoch": 1.5864661654135337, "percentage": 79.32, "elapsed_time": "0:26:19", "remaining_time": "0:06:51"}
+{"current_steps": 212, "total_steps": 266, "loss": 0.024, "lr": 1.2075907148663579e-05, "epoch": 1.5939849624060152, "percentage": 79.7, "elapsed_time": "0:26:26", "remaining_time": "0:06:44"}
+{"current_steps": 213, "total_steps": 266, "loss": 0.0261, "lr": 1.1650878293528994e-05, "epoch": 1.6015037593984962, "percentage": 80.08, "elapsed_time": "0:26:34", "remaining_time": "0:06:36"}
+{"current_steps": 214, "total_steps": 266, "loss": 0.0192, "lr": 1.1232475464035385e-05, "epoch": 1.6090225563909775, "percentage": 80.45, "elapsed_time": "0:26:41", "remaining_time": "0:06:29"}
+{"current_steps": 215, "total_steps": 266, "loss": 0.0192, "lr": 1.0820770952526155e-05, "epoch": 1.6165413533834587, "percentage": 80.83, "elapsed_time": "0:26:49", "remaining_time": "0:06:21"}
+{"current_steps": 216, "total_steps": 266, "loss": 0.0267, "lr": 1.0415835893998116e-05, "epoch": 1.6240601503759398, "percentage": 81.2, "elapsed_time": "0:26:56", "remaining_time": "0:06:14"}
+{"current_steps": 217, "total_steps": 266, "loss": 0.0244, "lr": 1.0017740253810609e-05, "epoch": 1.631578947368421, "percentage": 81.58, "elapsed_time": "0:27:03", "remaining_time": "0:06:06"}
+{"current_steps": 218, "total_steps": 266, "loss": 0.0265, "lr": 9.62655281559679e-06, "epoch": 1.6390977443609023, "percentage": 81.95, "elapsed_time": "0:27:11", "remaining_time": "0:05:59"}
+{"current_steps": 219, "total_steps": 266, "loss": 0.0239, "lr": 9.242341169379076e-06, "epoch": 1.6466165413533833, "percentage": 82.33, "elapsed_time": "0:27:18", "remaining_time": "0:05:51"}
+{"current_steps": 220, "total_steps": 266, "loss": 0.023, "lr": 8.865171699890834e-06, "epoch": 1.6541353383458648, "percentage": 82.71, "elapsed_time": "0:27:26", "remaining_time": "0:05:44"}
+{"current_steps": 221, "total_steps": 266, "loss": 0.0286, "lr": 8.49510957510633e-06, "epoch": 1.6616541353383458, "percentage": 83.08, "elapsed_time": "0:27:33", "remaining_time": "0:05:36"}
+{"current_steps": 222, "total_steps": 266, "loss": 0.0205, "lr": 8.132218734980852e-06, "epoch": 1.669172932330827, "percentage": 83.46, "elapsed_time": "0:27:41", "remaining_time": "0:05:29"}
+{"current_steps": 223, "total_steps": 266, "loss": 0.0222, "lr": 7.776561880403072e-06, "epoch": 1.6766917293233083, "percentage": 83.83, "elapsed_time": "0:27:48", "remaining_time": "0:05:21"}
+{"current_steps": 224, "total_steps": 266, "loss": 0.0257, "lr": 7.4282004623615396e-06, "epoch": 1.6842105263157894, "percentage": 84.21, "elapsed_time": "0:27:55", "remaining_time": "0:05:14"}
+{"current_steps": 225, "total_steps": 266, "loss": 0.021, "lr": 7.0871946713269856e-06, "epoch": 1.6917293233082706, "percentage": 84.59, "elapsed_time": "0:28:03", "remaining_time": "0:05:06"}
+{"current_steps": 226, "total_steps": 266, "loss": 0.0206, "lr": 6.753603426852589e-06, "epoch": 1.699248120300752, "percentage": 84.96, "elapsed_time": "0:28:10", "remaining_time": "0:04:59"}
+{"current_steps": 227, "total_steps": 266, "loss": 0.0221, "lr": 6.427484367393699e-06, "epoch": 1.706766917293233, "percentage": 85.34, "elapsed_time": "0:28:18", "remaining_time": "0:04:51"}
+{"current_steps": 228, "total_steps": 266, "loss": 0.0217, "lr": 6.108893840348995e-06, "epoch": 1.7142857142857144, "percentage": 85.71, "elapsed_time": "0:28:25", "remaining_time": "0:04:44"}
+{"current_steps": 229, "total_steps": 266, "loss": 0.0241, "lr": 5.797886892324694e-06, "epoch": 1.7218045112781954, "percentage": 86.09, "elapsed_time": "0:28:32", "remaining_time": "0:04:36"}
+{"current_steps": 230, "total_steps": 266, "loss": 0.023, "lr": 5.494517259623477e-06, "epoch": 1.7293233082706767, "percentage": 86.47, "elapsed_time": "0:28:40", "remaining_time": "0:04:29"}
+{"current_steps": 231, "total_steps": 266, "loss": 0.0247, "lr": 5.198837358959901e-06, "epoch": 1.736842105263158, "percentage": 86.84, "elapsed_time": "0:28:47", "remaining_time": "0:04:21"}
+{"current_steps": 232, "total_steps": 266, "loss": 0.0275, "lr": 4.910898278403669e-06, "epoch": 1.744360902255639, "percentage": 87.22, "elapsed_time": "0:28:55", "remaining_time": "0:04:14"}
+{"current_steps": 233, "total_steps": 266, "loss": 0.0236, "lr": 4.630749768552589e-06, "epoch": 1.7518796992481203, "percentage": 87.59, "elapsed_time": "0:29:02", "remaining_time": "0:04:06"}
+{"current_steps": 234, "total_steps": 266, "loss": 0.0196, "lr": 4.358440233936617e-06, "epoch": 1.7593984962406015, "percentage": 87.97, "elapsed_time": "0:29:09", "remaining_time": "0:03:59"}
+{"current_steps": 235, "total_steps": 266, "loss": 0.0292, "lr": 4.094016724654359e-06, "epoch": 1.7669172932330826, "percentage": 88.35, "elapsed_time": "0:29:17", "remaining_time": "0:03:51"}
+{"current_steps": 236, "total_steps": 266, "loss": 0.0224, "lr": 3.837524928243774e-06, "epoch": 1.774436090225564, "percentage": 88.72, "elapsed_time": "0:29:24", "remaining_time": "0:03:44"}
+{"current_steps": 237, "total_steps": 266, "loss": 0.0278, "lr": 3.589009161788104e-06, "epoch": 1.781954887218045, "percentage": 89.1, "elapsed_time": "0:29:32", "remaining_time": "0:03:36"}
+{"current_steps": 238, "total_steps": 266, "loss": 0.0243, "lr": 3.3485123642587658e-06, "epoch": 1.7894736842105263, "percentage": 89.47, "elapsed_time": "0:29:39", "remaining_time": "0:03:29"}
+{"current_steps": 239, "total_steps": 266, "loss": 0.027, "lr": 3.116076089096265e-06, "epoch": 1.7969924812030076, "percentage": 89.85, "elapsed_time": "0:29:46", "remaining_time": "0:03:21"}
+{"current_steps": 240, "total_steps": 266, "loss": 0.0288, "lr": 2.8917404970305097e-06, "epoch": 1.8045112781954886, "percentage": 90.23, "elapsed_time": "0:29:54", "remaining_time": "0:03:14"}
+{"current_steps": 241, "total_steps": 266, "loss": 0.0259, "lr": 2.675544349141779e-06, "epoch": 1.8120300751879699, "percentage": 90.6, "elapsed_time": "0:30:01", "remaining_time": "0:03:06"}
+{"current_steps": 242, "total_steps": 266, "loss": 0.0247, "lr": 2.4675250001635232e-06, "epoch": 1.8195488721804511, "percentage": 90.98, "elapsed_time": "0:30:09", "remaining_time": "0:02:59"}
+{"current_steps": 243, "total_steps": 266, "loss": 0.0193, "lr": 2.2677183920281343e-06, "epoch": 1.8270676691729322, "percentage": 91.35, "elapsed_time": "0:30:16", "remaining_time": "0:02:51"}
+{"current_steps": 244, "total_steps": 266, "loss": 0.0227, "lr": 2.076159047656889e-06, "epoch": 1.8345864661654137, "percentage": 91.73, "elapsed_time": "0:30:23", "remaining_time": "0:02:44"}
+{"current_steps": 245, "total_steps": 266, "loss": 0.0256, "lr": 1.892880064994934e-06, "epoch": 1.8421052631578947, "percentage": 92.11, "elapsed_time": "0:30:31", "remaining_time": "0:02:36"}
+{"current_steps": 246, "total_steps": 266, "loss": 0.024, "lr": 1.7179131112926627e-06, "epoch": 1.849624060150376, "percentage": 92.48, "elapsed_time": "0:30:38", "remaining_time": "0:02:29"}
+{"current_steps": 247, "total_steps": 266, "loss": 0.0159, "lr": 1.551288417634106e-06, "epoch": 1.8571428571428572, "percentage": 92.86, "elapsed_time": "0:30:46", "remaining_time": "0:02:22"}
+{"current_steps": 248, "total_steps": 266, "loss": 0.0209, "lr": 1.3930347737136196e-06, "epoch": 1.8646616541353382, "percentage": 93.23, "elapsed_time": "0:30:53", "remaining_time": "0:02:14"}
+{"current_steps": 249, "total_steps": 266, "loss": 0.0206, "lr": 1.2431795228615372e-06, "epoch": 1.8721804511278195, "percentage": 93.61, "elapsed_time": "0:31:00", "remaining_time": "0:02:07"}
+{"current_steps": 250, "total_steps": 266, "loss": 0.0315, "lr": 1.101748557319715e-06, "epoch": 1.8796992481203008, "percentage": 93.98, "elapsed_time": "0:31:08", "remaining_time": "0:01:59"}
+{"current_steps": 251, "total_steps": 266, "loss": 0.0193, "lr": 9.687663137678604e-07, "epoch": 1.8872180451127818, "percentage": 94.36, "elapsed_time": "0:31:15", "remaining_time": "0:01:52"}
+{"current_steps": 252, "total_steps": 266, "loss": 0.0245, "lr": 8.442557691013043e-07, "epoch": 1.8947368421052633, "percentage": 94.74, "elapsed_time": "0:31:23", "remaining_time": "0:01:44"}
+{"current_steps": 253, "total_steps": 266, "loss": 0.0242, "lr": 7.282384364610206e-07, "epoch": 1.9022556390977443, "percentage": 95.11, "elapsed_time": "0:31:30", "remaining_time": "0:01:37"}
+{"current_steps": 254, "total_steps": 266, "loss": 0.0207, "lr": 6.207343615165561e-07, "epoch": 1.9097744360902256, "percentage": 95.49, "elapsed_time": "0:31:37", "remaining_time": "0:01:29"}
+{"current_steps": 255, "total_steps": 266, "loss": 0.0259, "lr": 5.217621190024779e-07, "epoch": 1.9172932330827068, "percentage": 95.86, "elapsed_time": "0:31:45", "remaining_time": "0:01:22"}
+{"current_steps": 256, "total_steps": 266, "loss": 0.0217, "lr": 4.3133880950905205e-07, "epoch": 1.9248120300751879, "percentage": 96.24, "elapsed_time": "0:31:52", "remaining_time": "0:01:14"}
+{"current_steps": 257, "total_steps": 266, "loss": 0.0226, "lr": 3.494800565275125e-07, "epoch": 1.9323308270676691, "percentage": 96.62, "elapsed_time": "0:32:00", "remaining_time": "0:01:07"}
+{"current_steps": 258, "total_steps": 266, "loss": 0.0226, "lr": 2.762000037506485e-07, "epoch": 1.9398496240601504, "percentage": 96.99, "elapsed_time": "0:32:07", "remaining_time": "0:00:59"}
+{"current_steps": 259, "total_steps": 266, "loss": 0.0224, "lr": 2.115113126290258e-07, "epoch": 1.9473684210526314, "percentage": 97.37, "elapsed_time": "0:32:14", "remaining_time": "0:00:52"}
+{"current_steps": 260, "total_steps": 266, "loss": 0.0242, "lr": 1.554251601833201e-07, "epoch": 1.954887218045113, "percentage": 97.74, "elapsed_time": "0:32:22", "remaining_time": "0:00:44"}
+{"current_steps": 261, "total_steps": 266, "loss": 0.0199, "lr": 1.0795123707312283e-07, "epoch": 1.962406015037594, "percentage": 98.12, "elapsed_time": "0:32:29", "remaining_time": "0:00:37"}
+{"current_steps": 262, "total_steps": 266, "loss": 0.0218, "lr": 6.909774592258056e-08, "epoch": 1.9699248120300752, "percentage": 98.5, "elapsed_time": "0:32:37", "remaining_time": "0:00:29"}
+{"current_steps": 263, "total_steps": 266, "loss": 0.0242, "lr": 3.8871399903134265e-08, "epoch": 1.9774436090225564, "percentage": 98.87, "elapsed_time": "0:32:44", "remaining_time": "0:00:22"}
+{"current_steps": 264, "total_steps": 266, "loss": 0.0278, "lr": 1.7277421573608232e-08, "epoch": 1.9849624060150375, "percentage": 99.25, "elapsed_time": "0:32:52", "remaining_time": "0:00:14"}
+{"current_steps": 265, "total_steps": 266, "loss": 0.0193, "lr": 4.319541977831909e-09, "epoch": 1.9924812030075187, "percentage": 99.62, "elapsed_time": "0:32:59", "remaining_time": "0:00:07"}
+{"current_steps": 266, "total_steps": 266, "loss": 0.0224, "lr": 0.0, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:33:06", "remaining_time": "0:00:00"}
+{"current_steps": 266, "total_steps": 266, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:33:46", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1912 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 200,
+  "global_step": 266,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007518796992481203,
+      "grad_norm": 0.08289683091006875,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 0.2087,
+      "step": 1
+    },
+    {
+      "epoch": 0.015037593984962405,
+      "grad_norm": 0.03030546873337256,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.1045,
+      "step": 2
+    },
+    {
+      "epoch": 0.022556390977443608,
+      "grad_norm": 0.04340875250649354,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 0.1291,
+      "step": 3
+    },
+    {
+      "epoch": 0.03007518796992481,
+      "grad_norm": 0.04223285184390201,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 0.1263,
+      "step": 4
+    },
+    {
+      "epoch": 0.03759398496240601,
+      "grad_norm": 0.04894801143939966,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 0.1409,
+      "step": 5
+    },
+    {
+      "epoch": 0.045112781954887216,
+      "grad_norm": 0.22261274174154347,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.2362,
+      "step": 6
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 0.043978295203653116,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 0.1195,
+      "step": 7
+    },
+    {
+      "epoch": 0.06015037593984962,
+      "grad_norm": 0.04381964595602848,
+      "learning_rate": 2.962962962962963e-05,
+      "loss": 0.1215,
+      "step": 8
+    },
+    {
+      "epoch": 0.06766917293233082,
+      "grad_norm": 0.03290036083527209,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.0881,
+      "step": 9
+    },
+    {
+      "epoch": 0.07518796992481203,
+      "grad_norm": 0.03303553719000837,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.0923,
+      "step": 10
+    },
+    {
+      "epoch": 0.08270676691729323,
+      "grad_norm": 0.12832751130733108,
+      "learning_rate": 4.074074074074074e-05,
+      "loss": 0.218,
+      "step": 11
+    },
+    {
+      "epoch": 0.09022556390977443,
+      "grad_norm": 0.08479076437214379,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.149,
+      "step": 12
+    },
+    {
+      "epoch": 0.09774436090225563,
+      "grad_norm": 0.13534422076541278,
+      "learning_rate": 4.814814814814815e-05,
+      "loss": 0.1835,
+      "step": 13
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 0.10341781138952844,
+      "learning_rate": 5.185185185185185e-05,
+      "loss": 0.1573,
+      "step": 14
+    },
+    {
+      "epoch": 0.11278195488721804,
+      "grad_norm": 0.12256701286625035,
+      "learning_rate": 5.555555555555556e-05,
+      "loss": 0.1701,
+      "step": 15
+    },
+    {
+      "epoch": 0.12030075187969924,
+      "grad_norm": 0.05708144315846648,
+      "learning_rate": 5.925925925925926e-05,
+      "loss": 0.0938,
+      "step": 16
+    },
+    {
+      "epoch": 0.12781954887218044,
+      "grad_norm": 0.0813311914428683,
+      "learning_rate": 6.296296296296296e-05,
+      "loss": 0.1221,
+      "step": 17
+    },
+    {
+      "epoch": 0.13533834586466165,
+      "grad_norm": 0.07670248585638807,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.1068,
+      "step": 18
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.12777013083805186,
+      "learning_rate": 7.037037037037038e-05,
+      "loss": 0.1183,
+      "step": 19
+    },
+    {
+      "epoch": 0.15037593984962405,
+      "grad_norm": 0.07203864112993859,
+      "learning_rate": 7.407407407407407e-05,
+      "loss": 0.0941,
+      "step": 20
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 0.06622495246697525,
+      "learning_rate": 7.777777777777778e-05,
+      "loss": 0.0851,
+      "step": 21
+    },
+    {
+      "epoch": 0.16541353383458646,
+      "grad_norm": 0.05064660711733651,
+      "learning_rate": 8.148148148148148e-05,
+      "loss": 0.0672,
+      "step": 22
+    },
+    {
+      "epoch": 0.17293233082706766,
+      "grad_norm": 0.05569880144395339,
+      "learning_rate": 8.518518518518518e-05,
+      "loss": 0.0692,
+      "step": 23
+    },
+    {
+      "epoch": 0.18045112781954886,
+      "grad_norm": 0.06341922542018791,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 0.0719,
+      "step": 24
+    },
+    {
+      "epoch": 0.18796992481203006,
+      "grad_norm": 0.09483517480751269,
+      "learning_rate": 9.25925925925926e-05,
+      "loss": 0.1039,
+      "step": 25
+    },
+    {
+      "epoch": 0.19548872180451127,
+      "grad_norm": 0.06345422292566975,
+      "learning_rate": 9.62962962962963e-05,
+      "loss": 0.0642,
+      "step": 26
+    },
+    {
+      "epoch": 0.20300751879699247,
+      "grad_norm": 0.06565559978972503,
+      "learning_rate": 0.0001,
+      "loss": 0.0806,
+      "step": 27
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.07234940226716612,
+      "learning_rate": 9.999568045802217e-05,
+      "loss": 0.0699,
+      "step": 28
+    },
+    {
+      "epoch": 0.21804511278195488,
+      "grad_norm": 0.09174614011055109,
+      "learning_rate": 9.998272257842641e-05,
+      "loss": 0.0797,
+      "step": 29
+    },
+    {
+      "epoch": 0.22556390977443608,
+      "grad_norm": 0.0799372037045221,
+      "learning_rate": 9.996112860009688e-05,
+      "loss": 0.0599,
+      "step": 30
+    },
+    {
+      "epoch": 0.23308270676691728,
+      "grad_norm": 0.07650243821697233,
+      "learning_rate": 9.993090225407743e-05,
+      "loss": 0.0673,
+      "step": 31
+    },
+    {
+      "epoch": 0.24060150375939848,
+      "grad_norm": 0.07437978624039222,
+      "learning_rate": 9.989204876292688e-05,
+      "loss": 0.063,
+      "step": 32
+    },
+    {
+      "epoch": 0.24812030075187969,
+      "grad_norm": 0.05826090837310029,
+      "learning_rate": 9.984457483981669e-05,
+      "loss": 0.0563,
+      "step": 33
+    },
+    {
+      "epoch": 0.2556390977443609,
+      "grad_norm": 0.046830358894256296,
+      "learning_rate": 9.978848868737098e-05,
+      "loss": 0.0449,
+      "step": 34
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 0.059942032653184,
+      "learning_rate": 9.972379999624936e-05,
+      "loss": 0.0492,
+      "step": 35
+    },
+    {
+      "epoch": 0.2706766917293233,
+      "grad_norm": 0.04559622889503948,
+      "learning_rate": 9.96505199434725e-05,
+      "loss": 0.0384,
+      "step": 36
+    },
+    {
+      "epoch": 0.2781954887218045,
+      "grad_norm": 0.08582556953299057,
+      "learning_rate": 9.956866119049095e-05,
+      "loss": 0.052,
+      "step": 37
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.05879365562753825,
+      "learning_rate": 9.947823788099753e-05,
+      "loss": 0.0499,
+      "step": 38
+    },
+    {
+      "epoch": 0.2932330827067669,
+      "grad_norm": 0.07725729979493687,
+      "learning_rate": 9.937926563848346e-05,
+      "loss": 0.0382,
+      "step": 39
+    },
+    {
+      "epoch": 0.3007518796992481,
+      "grad_norm": 0.06791365316815774,
+      "learning_rate": 9.927176156353899e-05,
+      "loss": 0.0424,
+      "step": 40
+    },
+    {
+      "epoch": 0.3082706766917293,
+      "grad_norm": 0.06835456363607172,
+      "learning_rate": 9.91557442308987e-05,
+      "loss": 0.0477,
+      "step": 41
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.06785706541381617,
+      "learning_rate": 9.903123368623216e-05,
+      "loss": 0.0423,
+      "step": 42
+    },
+    {
+      "epoch": 0.3233082706766917,
+      "grad_norm": 0.037822284484082716,
+      "learning_rate": 9.889825144268029e-05,
+      "loss": 0.0373,
+      "step": 43
+    },
+    {
+      "epoch": 0.3308270676691729,
+      "grad_norm": 0.09335172889811039,
+      "learning_rate": 9.875682047713846e-05,
+      "loss": 0.0532,
+      "step": 44
+    },
+    {
+      "epoch": 0.3383458646616541,
+      "grad_norm": 0.03552601591664148,
+      "learning_rate": 9.860696522628639e-05,
+      "loss": 0.0302,
+      "step": 45
+    },
+    {
+      "epoch": 0.3458646616541353,
+      "grad_norm": 0.06792399841238587,
+      "learning_rate": 9.844871158236591e-05,
+      "loss": 0.043,
+      "step": 46
+    },
+    {
+      "epoch": 0.3533834586466165,
+      "grad_norm": 0.07394708716985816,
+      "learning_rate": 9.828208688870735e-05,
+      "loss": 0.0414,
+      "step": 47
+    },
+    {
+      "epoch": 0.3609022556390977,
+      "grad_norm": 0.07644206071621325,
+      "learning_rate": 9.810711993500507e-05,
+      "loss": 0.0442,
+      "step": 48
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 0.04448780324279346,
+      "learning_rate": 9.792384095234313e-05,
+      "loss": 0.0397,
+      "step": 49
+    },
+    {
+      "epoch": 0.37593984962406013,
+      "grad_norm": 0.040299146373067786,
+      "learning_rate": 9.773228160797188e-05,
+      "loss": 0.0294,
+      "step": 50
+    },
+    {
+      "epoch": 0.38345864661654133,
+      "grad_norm": 0.04600091352431098,
+      "learning_rate": 9.753247499983649e-05,
+      "loss": 0.0388,
+      "step": 51
+    },
+    {
+      "epoch": 0.39097744360902253,
+      "grad_norm": 0.05174024689025062,
+      "learning_rate": 9.732445565085824e-05,
+      "loss": 0.0464,
+      "step": 52
+    },
+    {
+      "epoch": 0.39849624060150374,
+      "grad_norm": 0.06048290755695799,
+      "learning_rate": 9.71082595029695e-05,
+      "loss": 0.0441,
+      "step": 53
+    },
+    {
+      "epoch": 0.40601503759398494,
+      "grad_norm": 0.06909111905381797,
+      "learning_rate": 9.688392391090373e-05,
+      "loss": 0.0403,
+      "step": 54
+    },
+    {
+      "epoch": 0.41353383458646614,
+      "grad_norm": 0.10580098842980783,
+      "learning_rate": 9.665148763574123e-05,
+      "loss": 0.0414,
+      "step": 55
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.06004492721880413,
+      "learning_rate": 9.64109908382119e-05,
+      "loss": 0.0348,
+      "step": 56
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.05616302785838828,
+      "learning_rate": 9.616247507175623e-05,
+      "loss": 0.0353,
+      "step": 57
+    },
+    {
+      "epoch": 0.43609022556390975,
+      "grad_norm": 0.04963402332052172,
+      "learning_rate": 9.590598327534564e-05,
+      "loss": 0.0354,
+      "step": 58
+    },
+    {
+      "epoch": 0.44360902255639095,
+      "grad_norm": 0.09520890937208057,
+      "learning_rate": 9.564155976606339e-05,
+      "loss": 0.0436,
+      "step": 59
+    },
+    {
+      "epoch": 0.45112781954887216,
+      "grad_norm": 0.07317691578763187,
+      "learning_rate": 9.536925023144742e-05,
+      "loss": 0.0448,
+      "step": 60
+    },
+    {
+      "epoch": 0.45864661654135336,
+      "grad_norm": 0.0653903652099525,
+      "learning_rate": 9.508910172159635e-05,
+      "loss": 0.0456,
+      "step": 61
+    },
+    {
+      "epoch": 0.46616541353383456,
+      "grad_norm": 0.08533000644485912,
+      "learning_rate": 9.480116264104011e-05,
+      "loss": 0.0417,
+      "step": 62
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.07477194348090598,
+      "learning_rate": 9.450548274037653e-05,
+      "loss": 0.0427,
+      "step": 63
+    },
+    {
+      "epoch": 0.48120300751879697,
+      "grad_norm": 0.040320894825821886,
+      "learning_rate": 9.420211310767533e-05,
+      "loss": 0.0317,
+      "step": 64
+    },
+    {
+      "epoch": 0.48872180451127817,
+      "grad_norm": 0.04204333897095501,
+      "learning_rate": 9.389110615965102e-05,
+      "loss": 0.0308,
+      "step": 65
+    },
+    {
+      "epoch": 0.49624060150375937,
+      "grad_norm": 0.06435209558835227,
+      "learning_rate": 9.35725156326063e-05,
+      "loss": 0.0404,
+      "step": 66
+    },
+    {
+      "epoch": 0.5037593984962406,
+      "grad_norm": 0.05292300086818655,
+      "learning_rate": 9.324639657314742e-05,
+      "loss": 0.0383,
+      "step": 67
+    },
+    {
+      "epoch": 0.5112781954887218,
+      "grad_norm": 0.0533359959006372,
+      "learning_rate": 9.291280532867302e-05,
+      "loss": 0.0419,
+      "step": 68
+    },
+    {
+      "epoch": 0.518796992481203,
+      "grad_norm": 0.0421677134855151,
+      "learning_rate": 9.257179953763845e-05,
+      "loss": 0.0301,
+      "step": 69
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.047396091527240565,
+      "learning_rate": 9.222343811959693e-05,
+      "loss": 0.0355,
+      "step": 70
+    },
+    {
+      "epoch": 0.5338345864661654,
+      "grad_norm": 0.05055865206409256,
+      "learning_rate": 9.186778126501916e-05,
+      "loss": 0.0379,
+      "step": 71
+    },
+    {
+      "epoch": 0.5413533834586466,
+      "grad_norm": 0.03922328494549794,
+      "learning_rate": 9.150489042489367e-05,
+      "loss": 0.03,
+      "step": 72
+    },
+    {
+      "epoch": 0.5488721804511278,
+      "grad_norm": 0.08580904921861318,
+      "learning_rate": 9.113482830010918e-05,
+      "loss": 0.038,
+      "step": 73
+    },
+    {
+      "epoch": 0.556390977443609,
+      "grad_norm": 0.04615991149700515,
+      "learning_rate": 9.075765883062093e-05,
+      "loss": 0.0321,
+      "step": 74
+    },
+    {
+      "epoch": 0.5639097744360902,
+      "grad_norm": 0.21688152384611062,
+      "learning_rate": 9.037344718440322e-05,
+      "loss": 0.0369,
+      "step": 75
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.06709856743156827,
+      "learning_rate": 8.99822597461894e-05,
+      "loss": 0.0429,
+      "step": 76
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.07300506123989278,
+      "learning_rate": 8.958416410600187e-05,
+      "loss": 0.0351,
+      "step": 77
+    },
+    {
+      "epoch": 0.5864661654135338,
+      "grad_norm": 0.08415403445437179,
+      "learning_rate": 8.917922904747384e-05,
+      "loss": 0.0425,
+      "step": 78
+    },
+    {
+      "epoch": 0.5939849624060151,
+      "grad_norm": 0.043734956942212244,
+      "learning_rate": 8.876752453596462e-05,
+      "loss": 0.0322,
+      "step": 79
+    },
+    {
+      "epoch": 0.6015037593984962,
+      "grad_norm": 0.11340147288766998,
+      "learning_rate": 8.834912170647101e-05,
+      "loss": 0.0446,
+      "step": 80
+    },
+    {
+      "epoch": 0.6090225563909775,
+      "grad_norm": 0.061288991507609664,
+      "learning_rate": 8.792409285133642e-05,
+      "loss": 0.0424,
+      "step": 81
+    },
+    {
+      "epoch": 0.6165413533834586,
+      "grad_norm": 0.043805649893633086,
+      "learning_rate": 8.749251140776016e-05,
+      "loss": 0.0342,
+      "step": 82
+    },
+    {
+      "epoch": 0.6240601503759399,
+      "grad_norm": 0.05953059965877648,
+      "learning_rate": 8.705445194510868e-05,
+      "loss": 0.0321,
+      "step": 83
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.07945205955271631,
+      "learning_rate": 8.66099901520315e-05,
+      "loss": 0.0371,
+      "step": 84
+    },
+    {
+      "epoch": 0.6390977443609023,
+      "grad_norm": 0.04453806753518928,
+      "learning_rate": 8.615920282338355e-05,
+      "loss": 0.0349,
+      "step": 85
+    },
+    {
+      "epoch": 0.6466165413533834,
+      "grad_norm": 0.05196927124976879,
+      "learning_rate": 8.570216784695637e-05,
+      "loss": 0.0287,
+      "step": 86
+    },
+    {
+      "epoch": 0.6541353383458647,
+      "grad_norm": 0.08901603801098872,
+      "learning_rate": 8.52389641900206e-05,
+      "loss": 0.0379,
+      "step": 87
+    },
+    {
+      "epoch": 0.6616541353383458,
+      "grad_norm": 0.04173009472070016,
+      "learning_rate": 8.476967188568188e-05,
+      "loss": 0.0264,
+      "step": 88
+    },
+    {
+      "epoch": 0.6691729323308271,
+      "grad_norm": 0.06191267416598679,
+      "learning_rate": 8.429437201905254e-05,
+      "loss": 0.028,
+      "step": 89
+    },
+    {
+      "epoch": 0.6766917293233082,
+      "grad_norm": 0.05938205491417802,
+      "learning_rate": 8.381314671324159e-05,
+      "loss": 0.0353,
+      "step": 90
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.06594155945203996,
+      "learning_rate": 8.332607911516545e-05,
+      "loss": 0.0423,
+      "step": 91
+    },
+    {
+      "epoch": 0.6917293233082706,
+      "grad_norm": 0.03727901580427709,
+      "learning_rate": 8.283325338118153e-05,
+      "loss": 0.0288,
+      "step": 92
+    },
+    {
+      "epoch": 0.6992481203007519,
+      "grad_norm": 0.039506792129091334,
+      "learning_rate": 8.233475466254765e-05,
+      "loss": 0.0319,
+      "step": 93
+    },
+    {
+      "epoch": 0.706766917293233,
+      "grad_norm": 0.10114676138905467,
+      "learning_rate": 8.183066909070947e-05,
+      "loss": 0.0413,
+      "step": 94
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.0519720254987392,
+      "learning_rate": 8.132108376241849e-05,
+      "loss": 0.0319,
+      "step": 95
+    },
+    {
+      "epoch": 0.7218045112781954,
+      "grad_norm": 0.06828535688055823,
+      "learning_rate": 8.08060867246834e-05,
+      "loss": 0.0415,
+      "step": 96
+    },
+    {
+      "epoch": 0.7293233082706767,
+      "grad_norm": 0.04423778552147402,
+      "learning_rate": 8.028576695955711e-05,
+      "loss": 0.0307,
+      "step": 97
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.04301708267503238,
+      "learning_rate": 7.97602143687623e-05,
+      "loss": 0.0292,
+      "step": 98
+    },
+    {
+      "epoch": 0.7443609022556391,
+      "grad_norm": 0.07557692217243188,
+      "learning_rate": 7.922951975815811e-05,
+      "loss": 0.0304,
+      "step": 99
+    },
+    {
+      "epoch": 0.7518796992481203,
+      "grad_norm": 0.061041885279450855,
+      "learning_rate": 7.869377482205042e-05,
+      "loss": 0.0318,
+      "step": 100
+    },
+    {
+      "epoch": 0.7593984962406015,
+      "grad_norm": 0.040342152719196084,
+      "learning_rate": 7.815307212734888e-05,
+      "loss": 0.027,
+      "step": 101
+    },
+    {
+      "epoch": 0.7669172932330827,
+      "grad_norm": 0.07790755826343725,
+      "learning_rate": 7.760750509757298e-05,
+      "loss": 0.0339,
+      "step": 102
+    },
+    {
+      "epoch": 0.7744360902255639,
+      "grad_norm": 0.05210408795431101,
+      "learning_rate": 7.705716799671019e-05,
+      "loss": 0.0228,
+      "step": 103
+    },
+    {
+      "epoch": 0.7819548872180451,
+      "grad_norm": 0.08000736959421384,
+      "learning_rate": 7.650215591292888e-05,
+      "loss": 0.0357,
+      "step": 104
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.05843028390975531,
+      "learning_rate": 7.594256474214882e-05,
+      "loss": 0.0285,
+      "step": 105
+    },
+    {
+      "epoch": 0.7969924812030075,
+      "grad_norm": 0.13537509841914472,
+      "learning_rate": 7.537849117147212e-05,
+      "loss": 0.0359,
+      "step": 106
+    },
+    {
+      "epoch": 0.8045112781954887,
+      "grad_norm": 0.08230566866298178,
+      "learning_rate": 7.481003266247744e-05,
+      "loss": 0.0367,
+      "step": 107
+    },
+    {
+      "epoch": 0.8120300751879699,
+      "grad_norm": 0.09678557492723187,
+      "learning_rate": 7.423728743438048e-05,
+      "loss": 0.0358,
+      "step": 108
+    },
+    {
+      "epoch": 0.8195488721804511,
+      "grad_norm": 0.049541914871144996,
+      "learning_rate": 7.366035444706347e-05,
+      "loss": 0.0329,
+      "step": 109
+    },
+    {
+      "epoch": 0.8270676691729323,
+      "grad_norm": 0.08823757922929092,
+      "learning_rate": 7.307933338397667e-05,
+      "loss": 0.0364,
+      "step": 110
+    },
+    {
+      "epoch": 0.8345864661654135,
+      "grad_norm": 0.044744299992948704,
+      "learning_rate": 7.249432463491498e-05,
+      "loss": 0.0328,
+      "step": 111
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.03814585189064516,
+      "learning_rate": 7.190542927867234e-05,
+      "loss": 0.0242,
+      "step": 112
+    },
+    {
+      "epoch": 0.849624060150376,
+      "grad_norm": 0.03553642928460275,
+      "learning_rate": 7.131274906557725e-05,
+      "loss": 0.0277,
+      "step": 113
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.044176381361140944,
+      "learning_rate": 7.071638639991207e-05,
+      "loss": 0.0282,
+      "step": 114
+    },
+    {
+      "epoch": 0.8646616541353384,
+      "grad_norm": 0.04113727259330019,
+      "learning_rate": 7.011644432221958e-05,
+      "loss": 0.0311,
+      "step": 115
+    },
+    {
+      "epoch": 0.8721804511278195,
+      "grad_norm": 0.060773829286428965,
+      "learning_rate": 6.95130264914993e-05,
+      "loss": 0.0414,
+      "step": 116
+    },
+    {
+      "epoch": 0.8796992481203008,
+      "grad_norm": 0.05757846085257315,
+      "learning_rate": 6.890623716729724e-05,
+      "loss": 0.0279,
+      "step": 117
+    },
+    {
+      "epoch": 0.8872180451127819,
+      "grad_norm": 0.08428255259620104,
+      "learning_rate": 6.82961811916917e-05,
+      "loss": 0.0298,
+      "step": 118
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.04529601746123181,
+      "learning_rate": 6.768296397117848e-05,
+      "loss": 0.0263,
+      "step": 119
+    },
+    {
+      "epoch": 0.9022556390977443,
+      "grad_norm": 0.0559976345746786,
+      "learning_rate": 6.706669145845863e-05,
+      "loss": 0.0331,
+      "step": 120
+    },
+    {
+      "epoch": 0.9097744360902256,
+      "grad_norm": 0.046985300077111235,
+      "learning_rate": 6.644747013413168e-05,
+      "loss": 0.0323,
+      "step": 121
+    },
+    {
+      "epoch": 0.9172932330827067,
+      "grad_norm": 0.06973194335422163,
+      "learning_rate": 6.582540698829781e-05,
+      "loss": 0.0356,
+      "step": 122
+    },
+    {
+      "epoch": 0.924812030075188,
+      "grad_norm": 0.0550307651636393,
+      "learning_rate": 6.520060950207185e-05,
+      "loss": 0.0374,
+      "step": 123
+    },
+    {
+      "epoch": 0.9323308270676691,
+      "grad_norm": 0.04136098377224926,
+      "learning_rate": 6.457318562901256e-05,
+      "loss": 0.0281,
+      "step": 124
+    },
+    {
+      "epoch": 0.9398496240601504,
+      "grad_norm": 0.04471839673788357,
+      "learning_rate": 6.394324377647028e-05,
+      "loss": 0.0344,
+      "step": 125
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.04057335071418551,
+      "learning_rate": 6.331089278685599e-05,
+      "loss": 0.0289,
+      "step": 126
+    },
+    {
+      "epoch": 0.9548872180451128,
+      "grad_norm": 0.036632585834280834,
+      "learning_rate": 6.26762419188355e-05,
+      "loss": 0.0254,
+      "step": 127
+    },
+    {
+      "epoch": 0.9624060150375939,
+      "grad_norm": 0.05253467833143005,
+      "learning_rate": 6.203940082845144e-05,
+      "loss": 0.0423,
+      "step": 128
+    },
+    {
+      "epoch": 0.9699248120300752,
+      "grad_norm": 0.05828434847478486,
+      "learning_rate": 6.140047955017671e-05,
+      "loss": 0.0331,
+      "step": 129
+    },
+    {
+      "epoch": 0.9774436090225563,
+      "grad_norm": 0.052528332979290625,
+      "learning_rate": 6.075958847790262e-05,
+      "loss": 0.0344,
+      "step": 130
+    },
+    {
+      "epoch": 0.9849624060150376,
+      "grad_norm": 0.039125799054480936,
+      "learning_rate": 6.011683834586473e-05,
+      "loss": 0.0264,
+      "step": 131
+    },
+    {
+      "epoch": 0.9924812030075187,
+      "grad_norm": 0.03707157930189228,
+      "learning_rate": 5.947234020951015e-05,
+      "loss": 0.0237,
+      "step": 132
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.054189982183542575,
+      "learning_rate": 5.882620542630901e-05,
+      "loss": 0.0317,
+      "step": 133
+    },
+    {
+      "epoch": 1.0075187969924813,
+      "grad_norm": 0.04357846265860899,
+      "learning_rate": 5.8178545636514145e-05,
+      "loss": 0.0268,
+      "step": 134
+    },
+    {
+      "epoch": 1.0150375939849625,
+      "grad_norm": 0.056012933476124856,
+      "learning_rate": 5.752947274387147e-05,
+      "loss": 0.0223,
+      "step": 135
+    },
+    {
+      "epoch": 1.0225563909774436,
+      "grad_norm": 0.049689439936320044,
+      "learning_rate": 5.687909889628529e-05,
+      "loss": 0.0304,
+      "step": 136
+    },
+    {
+      "epoch": 1.0300751879699248,
+      "grad_norm": 0.04830994322048754,
+      "learning_rate": 5.622753646644102e-05,
+      "loss": 0.0278,
+      "step": 137
+    },
+    {
+      "epoch": 1.037593984962406,
+      "grad_norm": 0.04418639970975713,
+      "learning_rate": 5.557489803238933e-05,
+      "loss": 0.0259,
+      "step": 138
+    },
+    {
+      "epoch": 1.045112781954887,
+      "grad_norm": 0.042738363591787835,
+      "learning_rate": 5.492129635809473e-05,
+      "loss": 0.0198,
+      "step": 139
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.03885713180148723,
+      "learning_rate": 5.426684437395196e-05,
+      "loss": 0.0191,
+      "step": 140
+    },
+    {
+      "epoch": 1.0601503759398496,
+      "grad_norm": 0.04951650926676435,
+      "learning_rate": 5.361165515727374e-05,
+      "loss": 0.0214,
+      "step": 141
+    },
+    {
+      "epoch": 1.0676691729323309,
+      "grad_norm": 0.059968470212708236,
+      "learning_rate": 5.295584191275308e-05,
+      "loss": 0.0243,
+      "step": 142
+    },
+    {
+      "epoch": 1.0751879699248121,
+      "grad_norm": 0.0676386940224187,
+      "learning_rate": 5.229951795290353e-05,
+      "loss": 0.029,
+      "step": 143
+    },
+    {
+      "epoch": 1.0827067669172932,
+      "grad_norm": 0.04250436122379926,
+      "learning_rate": 5.164279667848094e-05,
+      "loss": 0.0204,
+      "step": 144
+    },
+    {
+      "epoch": 1.0902255639097744,
+      "grad_norm": 0.04124846102938738,
+      "learning_rate": 5.0985791558889785e-05,
+      "loss": 0.0209,
+      "step": 145
+    },
+    {
+      "epoch": 1.0977443609022557,
+      "grad_norm": 0.05914558229310168,
+      "learning_rate": 5.032861611257783e-05,
+      "loss": 0.0285,
+      "step": 146
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.0465029543723527,
+      "learning_rate": 4.967138388742218e-05,
+      "loss": 0.0204,
+      "step": 147
+    },
+    {
+      "epoch": 1.112781954887218,
+      "grad_norm": 0.06469458945659604,
+      "learning_rate": 4.901420844111021e-05,
+      "loss": 0.0314,
+      "step": 148
+    },
+    {
+      "epoch": 1.1203007518796992,
+      "grad_norm": 0.06440915952496404,
+      "learning_rate": 4.835720332151907e-05,
+      "loss": 0.0281,
+      "step": 149
+    },
+    {
+      "epoch": 1.1278195488721805,
+      "grad_norm": 0.0571757163158284,
+      "learning_rate": 4.770048204709648e-05,
+      "loss": 0.0248,
+      "step": 150
+    },
+    {
+      "epoch": 1.1353383458646618,
+      "grad_norm": 0.05910301690921271,
+      "learning_rate": 4.7044158087246926e-05,
+      "loss": 0.0311,
+      "step": 151
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.04613839631194596,
+      "learning_rate": 4.6388344842726264e-05,
+      "loss": 0.0218,
+      "step": 152
+    },
+    {
+      "epoch": 1.150375939849624,
+      "grad_norm": 0.05741866552084954,
+      "learning_rate": 4.5733155626048036e-05,
+      "loss": 0.0271,
+      "step": 153
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 0.04682544810113655,
+      "learning_rate": 4.507870364190527e-05,
+      "loss": 0.0264,
+      "step": 154
+    },
+    {
+      "epoch": 1.1654135338345863,
+      "grad_norm": 0.06282838577083374,
+      "learning_rate": 4.4425101967610674e-05,
+      "loss": 0.024,
+      "step": 155
+    },
+    {
+      "epoch": 1.1729323308270676,
+      "grad_norm": 0.05388737782363021,
+      "learning_rate": 4.377246353355899e-05,
+      "loss": 0.0271,
+      "step": 156
+    },
+    {
+      "epoch": 1.1804511278195489,
+      "grad_norm": 0.05086578069156835,
+      "learning_rate": 4.312090110371473e-05,
+      "loss": 0.0278,
+      "step": 157
+    },
+    {
+      "epoch": 1.1879699248120301,
+      "grad_norm": 0.05863572980738164,
+      "learning_rate": 4.247052725612852e-05,
+      "loss": 0.0292,
+      "step": 158
+    },
+    {
+      "epoch": 1.1954887218045114,
+      "grad_norm": 0.04227523648124146,
+      "learning_rate": 4.1821454363485866e-05,
+      "loss": 0.0234,
+      "step": 159
+    },
+    {
+      "epoch": 1.2030075187969924,
+      "grad_norm": 0.04268704545270105,
+      "learning_rate": 4.1173794573690996e-05,
+      "loss": 0.0206,
+      "step": 160
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.04778787432486908,
+      "learning_rate": 4.052765979048986e-05,
+      "loss": 0.0227,
+      "step": 161
+    },
+    {
+      "epoch": 1.218045112781955,
+      "grad_norm": 0.0459311125342993,
+      "learning_rate": 3.988316165413528e-05,
+      "loss": 0.0205,
+      "step": 162
+    },
+    {
+      "epoch": 1.225563909774436,
+      "grad_norm": 0.05603215690118315,
+      "learning_rate": 3.924041152209739e-05,
+      "loss": 0.029,
+      "step": 163
+    },
+    {
+      "epoch": 1.2330827067669172,
+      "grad_norm": 0.060179119443112154,
+      "learning_rate": 3.859952044982329e-05,
+      "loss": 0.0271,
+      "step": 164
+    },
+    {
+      "epoch": 1.2406015037593985,
+      "grad_norm": 0.04740279415347567,
+      "learning_rate": 3.7960599171548574e-05,
+      "loss": 0.0213,
+      "step": 165
+    },
+    {
+      "epoch": 1.2481203007518797,
+      "grad_norm": 0.052482110362426594,
+      "learning_rate": 3.732375808116451e-05,
+      "loss": 0.0258,
+      "step": 166
+    },
+    {
+      "epoch": 1.255639097744361,
+      "grad_norm": 0.04835120393099329,
+      "learning_rate": 3.668910721314402e-05,
+      "loss": 0.0229,
+      "step": 167
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.08311507045185516,
+      "learning_rate": 3.605675622352973e-05,
+      "loss": 0.0265,
+      "step": 168
+    },
+    {
+      "epoch": 1.2706766917293233,
+      "grad_norm": 0.053563077833150494,
+      "learning_rate": 3.542681437098745e-05,
+      "loss": 0.0256,
+      "step": 169
+    },
+    {
+      "epoch": 1.2781954887218046,
+      "grad_norm": 0.05567682482783888,
+      "learning_rate": 3.479939049792817e-05,
+      "loss": 0.0213,
+      "step": 170
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.054588031712222006,
+      "learning_rate": 3.417459301170219e-05,
+      "loss": 0.0266,
+      "step": 171
+    },
+    {
+      "epoch": 1.2932330827067668,
+      "grad_norm": 0.07694344232267265,
+      "learning_rate": 3.355252986586832e-05,
+      "loss": 0.0193,
+      "step": 172
+    },
+    {
+      "epoch": 1.300751879699248,
+      "grad_norm": 0.05943952613035603,
+      "learning_rate": 3.293330854154136e-05,
+      "loss": 0.0258,
+      "step": 173
+    },
+    {
+      "epoch": 1.3082706766917294,
+      "grad_norm": 0.038766556860819104,
+      "learning_rate": 3.2317036028821523e-05,
+      "loss": 0.0159,
+      "step": 174
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.05092188135687549,
+      "learning_rate": 3.1703818808308324e-05,
+      "loss": 0.0215,
+      "step": 175
+    },
+    {
+      "epoch": 1.3233082706766917,
+      "grad_norm": 0.04779789780883562,
+      "learning_rate": 3.109376283270277e-05,
+      "loss": 0.0268,
+      "step": 176
+    },
+    {
+      "epoch": 1.330827067669173,
+      "grad_norm": 0.04433720319245774,
+      "learning_rate": 3.0486973508500727e-05,
+      "loss": 0.0238,
+      "step": 177
+    },
+    {
+      "epoch": 1.3383458646616542,
+      "grad_norm": 0.049878475563895956,
+      "learning_rate": 2.988355567778043e-05,
+      "loss": 0.0259,
+      "step": 178
+    },
+    {
+      "epoch": 1.3458646616541352,
+      "grad_norm": 0.05962755604807658,
+      "learning_rate": 2.9283613600087933e-05,
+      "loss": 0.025,
+      "step": 179
+    },
+    {
+      "epoch": 1.3533834586466165,
+      "grad_norm": 0.04955718527923681,
+      "learning_rate": 2.8687250934422772e-05,
+      "loss": 0.0194,
+      "step": 180
+    },
+    {
+      "epoch": 1.3609022556390977,
+      "grad_norm": 0.03676456890831394,
+      "learning_rate": 2.8094570721327662e-05,
+      "loss": 0.0189,
+      "step": 181
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.04868946152583533,
+      "learning_rate": 2.750567536508504e-05,
+      "loss": 0.0243,
+      "step": 182
+    },
+    {
+      "epoch": 1.3759398496240602,
+      "grad_norm": 0.0555305400721802,
+      "learning_rate": 2.6920666616023327e-05,
+      "loss": 0.0257,
+      "step": 183
+    },
+    {
+      "epoch": 1.3834586466165413,
+      "grad_norm": 0.04963192556183434,
+      "learning_rate": 2.6339645552936536e-05,
+      "loss": 0.0275,
+      "step": 184
+    },
+    {
+      "epoch": 1.3909774436090225,
+      "grad_norm": 0.05542091349920839,
+      "learning_rate": 2.5762712565619528e-05,
+      "loss": 0.023,
+      "step": 185
+    },
+    {
+      "epoch": 1.3984962406015038,
+      "grad_norm": 0.0426183120843919,
+      "learning_rate": 2.5189967337522573e-05,
+      "loss": 0.0206,
+      "step": 186
+    },
+    {
+      "epoch": 1.4060150375939848,
+      "grad_norm": 0.05205246245376388,
+      "learning_rate": 2.46215088285279e-05,
+      "loss": 0.0229,
+      "step": 187
+    },
+    {
+      "epoch": 1.413533834586466,
+      "grad_norm": 0.04337666332691105,
+      "learning_rate": 2.4057435257851175e-05,
+      "loss": 0.019,
+      "step": 188
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.05985729489503263,
+      "learning_rate": 2.349784408707112e-05,
+      "loss": 0.0274,
+      "step": 189
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.062032022184375604,
+      "learning_rate": 2.2942832003289823e-05,
+      "loss": 0.0271,
+      "step": 190
+    },
+    {
+      "epoch": 1.4360902255639099,
+      "grad_norm": 0.05773389436675615,
+      "learning_rate": 2.2392494902427025e-05,
+      "loss": 0.0263,
+      "step": 191
+    },
+    {
+      "epoch": 1.443609022556391,
+      "grad_norm": 0.048522536078850126,
+      "learning_rate": 2.1846927872651137e-05,
+      "loss": 0.0242,
+      "step": 192
+    },
+    {
+      "epoch": 1.4511278195488722,
+      "grad_norm": 0.05010560342148772,
+      "learning_rate": 2.1306225177949585e-05,
+      "loss": 0.024,
+      "step": 193
+    },
+    {
+      "epoch": 1.4586466165413534,
+      "grad_norm": 0.058011679310299026,
+      "learning_rate": 2.07704802418419e-05,
+      "loss": 0.0301,
+      "step": 194
+    },
+    {
+      "epoch": 1.4661654135338344,
+      "grad_norm": 0.052695628737558814,
+      "learning_rate": 2.0239785631237705e-05,
+      "loss": 0.0262,
+      "step": 195
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.0397195089948912,
+      "learning_rate": 1.9714233040442915e-05,
+      "loss": 0.0179,
+      "step": 196
+    },
+    {
+      "epoch": 1.481203007518797,
+      "grad_norm": 0.05532938780742867,
+      "learning_rate": 1.9193913275316626e-05,
+      "loss": 0.0234,
+      "step": 197
+    },
+    {
+      "epoch": 1.4887218045112782,
+      "grad_norm": 0.07349266479809795,
+      "learning_rate": 1.8678916237581522e-05,
+      "loss": 0.0236,
+      "step": 198
+    },
+    {
+      "epoch": 1.4962406015037595,
+      "grad_norm": 0.03995824607041351,
+      "learning_rate": 1.816933090929055e-05,
+      "loss": 0.0176,
+      "step": 199
+    },
+    {
+      "epoch": 1.5037593984962405,
+      "grad_norm": 0.07166373724308431,
+      "learning_rate": 1.7665245337452368e-05,
+      "loss": 0.0258,
+      "step": 200
+    },
+    {
+      "epoch": 1.5037593984962405,
+      "eval_loss": 0.029665347188711166,
+      "eval_runtime": 6.5066,
+      "eval_samples_per_second": 0.922,
+      "eval_steps_per_second": 0.307,
+      "step": 200
+    },
+    {
+      "epoch": 1.5112781954887218,
+      "grad_norm": 0.048692577901512116,
+      "learning_rate": 1.716674661881848e-05,
+      "loss": 0.0224,
+      "step": 201
+    },
+    {
+      "epoch": 1.518796992481203,
+      "grad_norm": 0.04675059057360818,
+      "learning_rate": 1.667392088483456e-05,
+      "loss": 0.0223,
+      "step": 202
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.05459458244813264,
+      "learning_rate": 1.6186853286758397e-05,
+      "loss": 0.0242,
+      "step": 203
+    },
+    {
+      "epoch": 1.5338345864661656,
+      "grad_norm": 0.051543551392068274,
+      "learning_rate": 1.570562798094747e-05,
+      "loss": 0.025,
+      "step": 204
+    },
+    {
+      "epoch": 1.5413533834586466,
+      "grad_norm": 0.14671926401344376,
+      "learning_rate": 1.5230328114318127e-05,
+      "loss": 0.0241,
+      "step": 205
+    },
+    {
+      "epoch": 1.5488721804511278,
+      "grad_norm": 0.058979726559234814,
+      "learning_rate": 1.4761035809979395e-05,
+      "loss": 0.0253,
+      "step": 206
+    },
+    {
+      "epoch": 1.556390977443609,
+      "grad_norm": 0.06494643885270886,
+      "learning_rate": 1.4297832153043656e-05,
+      "loss": 0.0236,
+      "step": 207
+    },
+    {
+      "epoch": 1.5639097744360901,
+      "grad_norm": 0.06627104647345526,
+      "learning_rate": 1.3840797176616466e-05,
+      "loss": 0.0278,
+      "step": 208
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.06190650675134399,
+      "learning_rate": 1.3390009847968504e-05,
+      "loss": 0.0255,
+      "step": 209
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.06250699899282167,
+      "learning_rate": 1.2945548054891321e-05,
+      "loss": 0.0254,
+      "step": 210
+    },
+    {
+      "epoch": 1.5864661654135337,
+      "grad_norm": 0.06214391708977836,
+      "learning_rate": 1.2507488592239847e-05,
+      "loss": 0.0233,
+      "step": 211
+    },
+    {
+      "epoch": 1.5939849624060152,
+      "grad_norm": 0.054608347620115995,
+      "learning_rate": 1.2075907148663579e-05,
+      "loss": 0.024,
+      "step": 212
+    },
+    {
+      "epoch": 1.6015037593984962,
+      "grad_norm": 0.05333683650123989,
+      "learning_rate": 1.1650878293528994e-05,
+      "loss": 0.0261,
+      "step": 213
+    },
+    {
+      "epoch": 1.6090225563909775,
+      "grad_norm": 0.047407562918454,
+      "learning_rate": 1.1232475464035385e-05,
+      "loss": 0.0192,
+      "step": 214
+    },
+    {
+      "epoch": 1.6165413533834587,
+      "grad_norm": 0.06549580580637923,
+      "learning_rate": 1.0820770952526155e-05,
+      "loss": 0.0192,
+      "step": 215
+    },
+    {
+      "epoch": 1.6240601503759398,
+      "grad_norm": 0.0582730317262946,
+      "learning_rate": 1.0415835893998116e-05,
+      "loss": 0.0267,
+      "step": 216
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.06724858724013988,
+      "learning_rate": 1.0017740253810609e-05,
+      "loss": 0.0244,
+      "step": 217
+    },
+    {
+      "epoch": 1.6390977443609023,
+      "grad_norm": 0.07353126997097047,
+      "learning_rate": 9.62655281559679e-06,
+      "loss": 0.0265,
+      "step": 218
+    },
+    {
+      "epoch": 1.6466165413533833,
+      "grad_norm": 0.057567868642984674,
+      "learning_rate": 9.242341169379076e-06,
+      "loss": 0.0239,
+      "step": 219
+    },
+    {
+      "epoch": 1.6541353383458648,
+      "grad_norm": 0.06325334373179048,
+      "learning_rate": 8.865171699890834e-06,
+      "loss": 0.023,
+      "step": 220
+    },
+    {
+      "epoch": 1.6616541353383458,
+      "grad_norm": 0.057849806459398294,
+      "learning_rate": 8.49510957510633e-06,
+      "loss": 0.0286,
+      "step": 221
+    },
+    {
+      "epoch": 1.669172932330827,
+      "grad_norm": 0.06257054012996921,
+      "learning_rate": 8.132218734980852e-06,
+      "loss": 0.0205,
+      "step": 222
+    },
+    {
+      "epoch": 1.6766917293233083,
+      "grad_norm": 0.053291552200528655,
+      "learning_rate": 7.776561880403072e-06,
+      "loss": 0.0222,
+      "step": 223
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.055884993872003165,
+      "learning_rate": 7.4282004623615396e-06,
+      "loss": 0.0257,
+      "step": 224
+    },
+    {
+      "epoch": 1.6917293233082706,
+      "grad_norm": 0.04781226703104293,
+      "learning_rate": 7.0871946713269856e-06,
+      "loss": 0.021,
+      "step": 225
+    },
+    {
+      "epoch": 1.699248120300752,
+      "grad_norm": 0.04617454207758738,
+      "learning_rate": 6.753603426852589e-06,
+      "loss": 0.0206,
+      "step": 226
+    },
+    {
+      "epoch": 1.706766917293233,
+      "grad_norm": 0.05934488856386534,
+      "learning_rate": 6.427484367393699e-06,
+      "loss": 0.0221,
+      "step": 227
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.0563063349000768,
+      "learning_rate": 6.108893840348995e-06,
+      "loss": 0.0217,
+      "step": 228
+    },
+    {
+      "epoch": 1.7218045112781954,
+      "grad_norm": 0.058919681414065804,
+      "learning_rate": 5.797886892324694e-06,
+      "loss": 0.0241,
+      "step": 229
+    },
+    {
+      "epoch": 1.7293233082706767,
+      "grad_norm": 0.04652279001651371,
+      "learning_rate": 5.494517259623477e-06,
+      "loss": 0.023,
+      "step": 230
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.05206753304811755,
+      "learning_rate": 5.198837358959901e-06,
+      "loss": 0.0247,
+      "step": 231
+    },
+    {
+      "epoch": 1.744360902255639,
+      "grad_norm": 0.05759411719610633,
+      "learning_rate": 4.910898278403669e-06,
+      "loss": 0.0275,
+      "step": 232
+    },
+    {
+      "epoch": 1.7518796992481203,
+      "grad_norm": 0.05493938568305548,
+      "learning_rate": 4.630749768552589e-06,
+      "loss": 0.0236,
+      "step": 233
+    },
+    {
+      "epoch": 1.7593984962406015,
+      "grad_norm": 0.045214515268897214,
+      "learning_rate": 4.358440233936617e-06,
+      "loss": 0.0196,
+      "step": 234
+    },
+    {
+      "epoch": 1.7669172932330826,
+      "grad_norm": 0.08670874372319154,
+      "learning_rate": 4.094016724654359e-06,
+      "loss": 0.0292,
+      "step": 235
+    },
+    {
+      "epoch": 1.774436090225564,
+      "grad_norm": 0.049117351787292686,
+      "learning_rate": 3.837524928243774e-06,
+      "loss": 0.0224,
+      "step": 236
+    },
+    {
+      "epoch": 1.781954887218045,
+      "grad_norm": 0.058397389390063136,
+      "learning_rate": 3.589009161788104e-06,
+      "loss": 0.0278,
+      "step": 237
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 0.05422155962388968,
+      "learning_rate": 3.3485123642587658e-06,
+      "loss": 0.0243,
+      "step": 238
+    },
+    {
+      "epoch": 1.7969924812030076,
+      "grad_norm": 0.07090059571835504,
+      "learning_rate": 3.116076089096265e-06,
+      "loss": 0.027,
+      "step": 239
+    },
+    {
+      "epoch": 1.8045112781954886,
+      "grad_norm": 0.05963059250846481,
+      "learning_rate": 2.8917404970305097e-06,
+      "loss": 0.0288,
+      "step": 240
+    },
+    {
+      "epoch": 1.8120300751879699,
+      "grad_norm": 0.06946365704174999,
+      "learning_rate": 2.675544349141779e-06,
+      "loss": 0.0259,
+      "step": 241
+    },
+    {
+      "epoch": 1.8195488721804511,
+      "grad_norm": 0.06143740644726876,
+      "learning_rate": 2.4675250001635232e-06,
+      "loss": 0.0247,
+      "step": 242
+    },
+    {
+      "epoch": 1.8270676691729322,
+      "grad_norm": 0.04728168437977354,
+      "learning_rate": 2.2677183920281343e-06,
+      "loss": 0.0193,
+      "step": 243
+    },
+    {
+      "epoch": 1.8345864661654137,
+      "grad_norm": 0.07042127314230426,
+      "learning_rate": 2.076159047656889e-06,
+      "loss": 0.0227,
+      "step": 244
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.05266415047166696,
+      "learning_rate": 1.892880064994934e-06,
+      "loss": 0.0256,
+      "step": 245
+    },
+    {
+      "epoch": 1.849624060150376,
+      "grad_norm": 0.05204878417509025,
+      "learning_rate": 1.7179131112926627e-06,
+      "loss": 0.024,
+      "step": 246
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.04727065912696429,
+      "learning_rate": 1.551288417634106e-06,
+      "loss": 0.0159,
+      "step": 247
+    },
+    {
+      "epoch": 1.8646616541353382,
+      "grad_norm": 0.049637487718030344,
+      "learning_rate": 1.3930347737136196e-06,
+      "loss": 0.0209,
+      "step": 248
+    },
+    {
+      "epoch": 1.8721804511278195,
+      "grad_norm": 0.0505669836884092,
+      "learning_rate": 1.2431795228615372e-06,
+      "loss": 0.0206,
+      "step": 249
+    },
+    {
+      "epoch": 1.8796992481203008,
+      "grad_norm": 0.07557073448805833,
+      "learning_rate": 1.101748557319715e-06,
+      "loss": 0.0315,
+      "step": 250
+    },
+    {
+      "epoch": 1.8872180451127818,
+      "grad_norm": 0.04855407299966349,
+      "learning_rate": 9.687663137678604e-07,
+      "loss": 0.0193,
+      "step": 251
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.05981871688003821,
+      "learning_rate": 8.442557691013043e-07,
+      "loss": 0.0245,
+      "step": 252
+    },
+    {
+      "epoch": 1.9022556390977443,
+      "grad_norm": 0.055297053623164526,
+      "learning_rate": 7.282384364610206e-07,
+      "loss": 0.0242,
+      "step": 253
+    },
+    {
+      "epoch": 1.9097744360902256,
+      "grad_norm": 0.05097924138111233,
+      "learning_rate": 6.207343615165561e-07,
+      "loss": 0.0207,
+      "step": 254
+    },
+    {
+      "epoch": 1.9172932330827068,
+      "grad_norm": 0.05870296620626846,
+      "learning_rate": 5.217621190024779e-07,
+      "loss": 0.0259,
+      "step": 255
+    },
+    {
+      "epoch": 1.9248120300751879,
+      "grad_norm": 0.05289043509456049,
+      "learning_rate": 4.3133880950905205e-07,
+      "loss": 0.0217,
+      "step": 256
+    },
+    {
+      "epoch": 1.9323308270676691,
+      "grad_norm": 0.05040687502136238,
+      "learning_rate": 3.494800565275125e-07,
+      "loss": 0.0226,
+      "step": 257
+    },
+    {
+      "epoch": 1.9398496240601504,
+      "grad_norm": 0.05483598628420617,
+      "learning_rate": 2.762000037506485e-07,
+      "loss": 0.0226,
+      "step": 258
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.052171052589092846,
+      "learning_rate": 2.115113126290258e-07,
+      "loss": 0.0224,
+      "step": 259
+    },
+    {
+      "epoch": 1.954887218045113,
+      "grad_norm": 0.060066029686361856,
+      "learning_rate": 1.554251601833201e-07,
+      "loss": 0.0242,
+      "step": 260
+    },
+    {
+      "epoch": 1.962406015037594,
+      "grad_norm": 0.04560282840465627,
+      "learning_rate": 1.0795123707312283e-07,
+      "loss": 0.0199,
+      "step": 261
+    },
+    {
+      "epoch": 1.9699248120300752,
+      "grad_norm": 0.055943707431487216,
+      "learning_rate": 6.909774592258056e-08,
+      "loss": 0.0218,
+      "step": 262
+    },
+    {
+      "epoch": 1.9774436090225564,
+      "grad_norm": 0.057987573660367824,
+      "learning_rate": 3.8871399903134265e-08,
+      "loss": 0.0242,
+      "step": 263
+    },
+    {
+      "epoch": 1.9849624060150375,
+      "grad_norm": 0.05438020219150765,
+      "learning_rate": 1.7277421573608232e-08,
+      "loss": 0.0278,
+      "step": 264
+    },
+    {
+      "epoch": 1.9924812030075187,
+      "grad_norm": 0.05442881774912085,
+      "learning_rate": 4.319541977831909e-09,
+      "loss": 0.0193,
+      "step": 265
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.059490023866208885,
+      "learning_rate": 0.0,
+      "loss": 0.0224,
+      "step": 266
+    },
+    {
+      "epoch": 2.0,
+      "step": 266,
+      "total_flos": 673614818967552.0,
+      "train_loss": 0.039493271835932604,
+      "train_runtime": 2026.6163,
+      "train_samples_per_second": 0.522,
+      "train_steps_per_second": 0.131
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 266,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 673614818967552.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d6847f9e87919055227d9c8018b28017980a14d70646aaf178f757b9a503d6f
+size 7224