Add fine-tuned model

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 0.15.1

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-32B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2386ed9f1dcbeae3fa6ec9b9635f215535973376661ed870ec655fd093383b5
+size 2147605960

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
+}

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:a8506e7111b80c6d8635951a02eab0f4e1a8e4e5772da83846579e97b16f61bf
+size 7031673

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1610 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 224,
+  "global_step": 224,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004464285714285714,
+      "grad_norm": 0.2761818468570709,
+      "learning_rate": 1e-05,
+      "loss": 1.9335,
+      "step": 1
+    },
+    {
+      "epoch": 0.008928571428571428,
+      "grad_norm": 0.2839259207248688,
+      "learning_rate": 9.955357142857143e-06,
+      "loss": 1.9572,
+      "step": 2
+    },
+    {
+      "epoch": 0.013392857142857142,
+      "grad_norm": 0.27978816628456116,
+      "learning_rate": 9.910714285714288e-06,
+      "loss": 1.9055,
+      "step": 3
+    },
+    {
+      "epoch": 0.017857142857142856,
+      "grad_norm": 0.29557615518569946,
+      "learning_rate": 9.86607142857143e-06,
+      "loss": 1.9802,
+      "step": 4
+    },
+    {
+      "epoch": 0.022321428571428572,
+      "grad_norm": 0.28455209732055664,
+      "learning_rate": 9.821428571428573e-06,
+      "loss": 1.8339,
+      "step": 5
+    },
+    {
+      "epoch": 0.026785714285714284,
+      "grad_norm": 0.29499706625938416,
+      "learning_rate": 9.776785714285715e-06,
+      "loss": 1.9119,
+      "step": 6
+    },
+    {
+      "epoch": 0.03125,
+      "grad_norm": 0.2904488444328308,
+      "learning_rate": 9.732142857142858e-06,
+      "loss": 1.8801,
+      "step": 7
+    },
+    {
+      "epoch": 0.03571428571428571,
+      "grad_norm": 0.3096090853214264,
+      "learning_rate": 9.6875e-06,
+      "loss": 1.9382,
+      "step": 8
+    },
+    {
+      "epoch": 0.04017857142857143,
+      "grad_norm": 0.28679272532463074,
+      "learning_rate": 9.642857142857144e-06,
+      "loss": 1.8691,
+      "step": 9
+    },
+    {
+      "epoch": 0.044642857142857144,
+      "grad_norm": 0.2840006947517395,
+      "learning_rate": 9.598214285714287e-06,
+      "loss": 1.8146,
+      "step": 10
+    },
+    {
+      "epoch": 0.049107142857142856,
+      "grad_norm": 0.28163135051727295,
+      "learning_rate": 9.55357142857143e-06,
+      "loss": 1.8451,
+      "step": 11
+    },
+    {
+      "epoch": 0.05357142857142857,
+      "grad_norm": 0.2710447609424591,
+      "learning_rate": 9.508928571428572e-06,
+      "loss": 1.8102,
+      "step": 12
+    },
+    {
+      "epoch": 0.05803571428571429,
+      "grad_norm": 0.28104639053344727,
+      "learning_rate": 9.464285714285714e-06,
+      "loss": 1.8514,
+      "step": 13
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 0.27071282267570496,
+      "learning_rate": 9.419642857142858e-06,
+      "loss": 1.7856,
+      "step": 14
+    },
+    {
+      "epoch": 0.06696428571428571,
+      "grad_norm": 0.26851388812065125,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 1.7548,
+      "step": 15
+    },
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 0.26807543635368347,
+      "learning_rate": 9.330357142857143e-06,
+      "loss": 1.7333,
+      "step": 16
+    },
+    {
+      "epoch": 0.07589285714285714,
+      "grad_norm": 0.2696438729763031,
+      "learning_rate": 9.285714285714288e-06,
+      "loss": 1.718,
+      "step": 17
+    },
+    {
+      "epoch": 0.08035714285714286,
+      "grad_norm": 0.25405392050743103,
+      "learning_rate": 9.24107142857143e-06,
+      "loss": 1.71,
+      "step": 18
+    },
+    {
+      "epoch": 0.08482142857142858,
+      "grad_norm": 0.2596004903316498,
+      "learning_rate": 9.196428571428571e-06,
+      "loss": 1.6927,
+      "step": 19
+    },
+    {
+      "epoch": 0.08928571428571429,
+      "grad_norm": 0.2591722011566162,
+      "learning_rate": 9.151785714285715e-06,
+      "loss": 1.6633,
+      "step": 20
+    },
+    {
+      "epoch": 0.09375,
+      "grad_norm": 0.25017333030700684,
+      "learning_rate": 9.107142857142858e-06,
+      "loss": 1.6717,
+      "step": 21
+    },
+    {
+      "epoch": 0.09821428571428571,
+      "grad_norm": 0.24752862751483917,
+      "learning_rate": 9.0625e-06,
+      "loss": 1.69,
+      "step": 22
+    },
+    {
+      "epoch": 0.10267857142857142,
+      "grad_norm": 0.24346745014190674,
+      "learning_rate": 9.017857142857144e-06,
+      "loss": 1.6627,
+      "step": 23
+    },
+    {
+      "epoch": 0.10714285714285714,
+      "grad_norm": 0.242690771818161,
+      "learning_rate": 8.973214285714287e-06,
+      "loss": 1.6503,
+      "step": 24
+    },
+    {
+      "epoch": 0.11160714285714286,
+      "grad_norm": 0.2382921576499939,
+      "learning_rate": 8.92857142857143e-06,
+      "loss": 1.6372,
+      "step": 25
+    },
+    {
+      "epoch": 0.11607142857142858,
+      "grad_norm": 0.22940175235271454,
+      "learning_rate": 8.883928571428572e-06,
+      "loss": 1.5877,
+      "step": 26
+    },
+    {
+      "epoch": 0.12053571428571429,
+      "grad_norm": 0.23437069356441498,
+      "learning_rate": 8.839285714285714e-06,
+      "loss": 1.6385,
+      "step": 27
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.2343682050704956,
+      "learning_rate": 8.794642857142858e-06,
+      "loss": 1.6232,
+      "step": 28
+    },
+    {
+      "epoch": 0.12946428571428573,
+      "grad_norm": 0.22419074177742004,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 1.5601,
+      "step": 29
+    },
+    {
+      "epoch": 0.13392857142857142,
+      "grad_norm": 0.22903244197368622,
+      "learning_rate": 8.705357142857143e-06,
+      "loss": 1.5862,
+      "step": 30
+    },
+    {
+      "epoch": 0.13839285714285715,
+      "grad_norm": 0.2142716646194458,
+      "learning_rate": 8.660714285714286e-06,
+      "loss": 1.5567,
+      "step": 31
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.2121979147195816,
+      "learning_rate": 8.61607142857143e-06,
+      "loss": 1.5239,
+      "step": 32
+    },
+    {
+      "epoch": 0.14732142857142858,
+      "grad_norm": 0.20913730561733246,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 1.5147,
+      "step": 33
+    },
+    {
+      "epoch": 0.15178571428571427,
+      "grad_norm": 0.20845234394073486,
+      "learning_rate": 8.526785714285715e-06,
+      "loss": 1.489,
+      "step": 34
+    },
+    {
+      "epoch": 0.15625,
+      "grad_norm": 0.21410076320171356,
+      "learning_rate": 8.482142857142858e-06,
+      "loss": 1.5326,
+      "step": 35
+    },
+    {
+      "epoch": 0.16071428571428573,
+      "grad_norm": 0.20321586728096008,
+      "learning_rate": 8.4375e-06,
+      "loss": 1.5242,
+      "step": 36
+    },
+    {
+      "epoch": 0.16517857142857142,
+      "grad_norm": 0.2035406529903412,
+      "learning_rate": 8.392857142857144e-06,
+      "loss": 1.4907,
+      "step": 37
+    },
+    {
+      "epoch": 0.16964285714285715,
+      "grad_norm": 0.2062457650899887,
+      "learning_rate": 8.348214285714287e-06,
+      "loss": 1.5084,
+      "step": 38
+    },
+    {
+      "epoch": 0.17410714285714285,
+      "grad_norm": 0.18952934443950653,
+      "learning_rate": 8.30357142857143e-06,
+      "loss": 1.4762,
+      "step": 39
+    },
+    {
+      "epoch": 0.17857142857142858,
+      "grad_norm": 0.2010241597890854,
+      "learning_rate": 8.258928571428572e-06,
+      "loss": 1.4962,
+      "step": 40
+    },
+    {
+      "epoch": 0.18303571428571427,
+      "grad_norm": 0.18677328526973724,
+      "learning_rate": 8.214285714285714e-06,
+      "loss": 1.4495,
+      "step": 41
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 0.19814759492874146,
+      "learning_rate": 8.169642857142858e-06,
+      "loss": 1.4932,
+      "step": 42
+    },
+    {
+      "epoch": 0.19196428571428573,
+      "grad_norm": 0.18671900033950806,
+      "learning_rate": 8.125000000000001e-06,
+      "loss": 1.4715,
+      "step": 43
+    },
+    {
+      "epoch": 0.19642857142857142,
+      "grad_norm": 0.1806054562330246,
+      "learning_rate": 8.080357142857143e-06,
+      "loss": 1.3962,
+      "step": 44
+    },
+    {
+      "epoch": 0.20089285714285715,
+      "grad_norm": 0.1811523288488388,
+      "learning_rate": 8.035714285714286e-06,
+      "loss": 1.4263,
+      "step": 45
+    },
+    {
+      "epoch": 0.20535714285714285,
+      "grad_norm": 0.1765059232711792,
+      "learning_rate": 7.99107142857143e-06,
+      "loss": 1.4294,
+      "step": 46
+    },
+    {
+      "epoch": 0.20982142857142858,
+      "grad_norm": 0.16637149453163147,
+      "learning_rate": 7.946428571428571e-06,
+      "loss": 1.3778,
+      "step": 47
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 0.17775599658489227,
+      "learning_rate": 7.901785714285715e-06,
+      "loss": 1.4232,
+      "step": 48
+    },
+    {
+      "epoch": 0.21875,
+      "grad_norm": 0.17176896333694458,
+      "learning_rate": 7.857142857142858e-06,
+      "loss": 1.3946,
+      "step": 49
+    },
+    {
+      "epoch": 0.22321428571428573,
+      "grad_norm": 0.1908663660287857,
+      "learning_rate": 7.8125e-06,
+      "loss": 1.4314,
+      "step": 50
+    },
+    {
+      "epoch": 0.22767857142857142,
+      "grad_norm": 0.15980762243270874,
+      "learning_rate": 7.767857142857144e-06,
+      "loss": 1.3715,
+      "step": 51
+    },
+    {
+      "epoch": 0.23214285714285715,
+      "grad_norm": 0.17836317420005798,
+      "learning_rate": 7.723214285714287e-06,
+      "loss": 1.4074,
+      "step": 52
+    },
+    {
+      "epoch": 0.23660714285714285,
+      "grad_norm": 0.1713654100894928,
+      "learning_rate": 7.67857142857143e-06,
+      "loss": 1.4077,
+      "step": 53
+    },
+    {
+      "epoch": 0.24107142857142858,
+      "grad_norm": 0.16315017640590668,
+      "learning_rate": 7.633928571428572e-06,
+      "loss": 1.3535,
+      "step": 54
+    },
+    {
+      "epoch": 0.24553571428571427,
+      "grad_norm": 0.15950244665145874,
+      "learning_rate": 7.589285714285714e-06,
+      "loss": 1.3692,
+      "step": 55
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.15749427676200867,
+      "learning_rate": 7.544642857142858e-06,
+      "loss": 1.3463,
+      "step": 56
+    },
+    {
+      "epoch": 0.2544642857142857,
+      "grad_norm": 0.1571965217590332,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.391,
+      "step": 57
+    },
+    {
+      "epoch": 0.25892857142857145,
+      "grad_norm": 0.1504509449005127,
+      "learning_rate": 7.4553571428571435e-06,
+      "loss": 1.3147,
+      "step": 58
+    },
+    {
+      "epoch": 0.26339285714285715,
+      "grad_norm": 0.15875661373138428,
+      "learning_rate": 7.410714285714287e-06,
+      "loss": 1.3062,
+      "step": 59
+    },
+    {
+      "epoch": 0.26785714285714285,
+      "grad_norm": 0.15665651857852936,
+      "learning_rate": 7.366071428571429e-06,
+      "loss": 1.3466,
+      "step": 60
+    },
+    {
+      "epoch": 0.27232142857142855,
+      "grad_norm": 0.1499185562133789,
+      "learning_rate": 7.321428571428572e-06,
+      "loss": 1.2897,
+      "step": 61
+    },
+    {
+      "epoch": 0.2767857142857143,
+      "grad_norm": 0.17195631563663483,
+      "learning_rate": 7.276785714285714e-06,
+      "loss": 1.38,
+      "step": 62
+    },
+    {
+      "epoch": 0.28125,
+      "grad_norm": 0.1620142012834549,
+      "learning_rate": 7.232142857142858e-06,
+      "loss": 1.3763,
+      "step": 63
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.14602452516555786,
+      "learning_rate": 7.1875e-06,
+      "loss": 1.3196,
+      "step": 64
+    },
+    {
+      "epoch": 0.29017857142857145,
+      "grad_norm": 0.14299681782722473,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 1.2965,
+      "step": 65
+    },
+    {
+      "epoch": 0.29464285714285715,
+      "grad_norm": 0.14240612089633942,
+      "learning_rate": 7.098214285714287e-06,
+      "loss": 1.3009,
+      "step": 66
+    },
+    {
+      "epoch": 0.29910714285714285,
+      "grad_norm": 0.1413644254207611,
+      "learning_rate": 7.053571428571429e-06,
+      "loss": 1.275,
+      "step": 67
+    },
+    {
+      "epoch": 0.30357142857142855,
+      "grad_norm": 0.14226756989955902,
+      "learning_rate": 7.008928571428572e-06,
+      "loss": 1.3167,
+      "step": 68
+    },
+    {
+      "epoch": 0.3080357142857143,
+      "grad_norm": 0.14311659336090088,
+      "learning_rate": 6.964285714285714e-06,
+      "loss": 1.2767,
+      "step": 69
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 0.1456228643655777,
+      "learning_rate": 6.919642857142858e-06,
+      "loss": 1.307,
+      "step": 70
+    },
+    {
+      "epoch": 0.3169642857142857,
+      "grad_norm": 0.14129480719566345,
+      "learning_rate": 6.875e-06,
+      "loss": 1.2913,
+      "step": 71
+    },
+    {
+      "epoch": 0.32142857142857145,
+      "grad_norm": 0.14857961237430573,
+      "learning_rate": 6.830357142857144e-06,
+      "loss": 1.3067,
+      "step": 72
+    },
+    {
+      "epoch": 0.32589285714285715,
+      "grad_norm": 0.13537095487117767,
+      "learning_rate": 6.785714285714287e-06,
+      "loss": 1.2866,
+      "step": 73
+    },
+    {
+      "epoch": 0.33035714285714285,
+      "grad_norm": 0.14447800815105438,
+      "learning_rate": 6.7410714285714294e-06,
+      "loss": 1.3184,
+      "step": 74
+    },
+    {
+      "epoch": 0.33482142857142855,
+      "grad_norm": 0.13712835311889648,
+      "learning_rate": 6.696428571428571e-06,
+      "loss": 1.2394,
+      "step": 75
+    },
+    {
+      "epoch": 0.3392857142857143,
+      "grad_norm": 0.13952307403087616,
+      "learning_rate": 6.6517857142857144e-06,
+      "loss": 1.3057,
+      "step": 76
+    },
+    {
+      "epoch": 0.34375,
+      "grad_norm": 0.13543088734149933,
+      "learning_rate": 6.607142857142858e-06,
+      "loss": 1.271,
+      "step": 77
+    },
+    {
+      "epoch": 0.3482142857142857,
+      "grad_norm": 0.14161542057991028,
+      "learning_rate": 6.5625e-06,
+      "loss": 1.3145,
+      "step": 78
+    },
+    {
+      "epoch": 0.35267857142857145,
+      "grad_norm": 0.1485525220632553,
+      "learning_rate": 6.517857142857144e-06,
+      "loss": 1.3134,
+      "step": 79
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 0.13326852023601532,
+      "learning_rate": 6.473214285714287e-06,
+      "loss": 1.2916,
+      "step": 80
+    },
+    {
+      "epoch": 0.36160714285714285,
+      "grad_norm": 0.13659986853599548,
+      "learning_rate": 6.4285714285714295e-06,
+      "loss": 1.2736,
+      "step": 81
+    },
+    {
+      "epoch": 0.36607142857142855,
+      "grad_norm": 0.14073261618614197,
+      "learning_rate": 6.383928571428571e-06,
+      "loss": 1.2344,
+      "step": 82
+    },
+    {
+      "epoch": 0.3705357142857143,
+      "grad_norm": 0.13768716156482697,
+      "learning_rate": 6.3392857142857145e-06,
+      "loss": 1.2917,
+      "step": 83
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.1339098960161209,
+      "learning_rate": 6.294642857142858e-06,
+      "loss": 1.2606,
+      "step": 84
+    },
+    {
+      "epoch": 0.3794642857142857,
+      "grad_norm": 0.13438129425048828,
+      "learning_rate": 6.25e-06,
+      "loss": 1.2599,
+      "step": 85
+    },
+    {
+      "epoch": 0.38392857142857145,
+      "grad_norm": 0.1296667456626892,
+      "learning_rate": 6.205357142857144e-06,
+      "loss": 1.2434,
+      "step": 86
+    },
+    {
+      "epoch": 0.38839285714285715,
+      "grad_norm": 0.1329282522201538,
+      "learning_rate": 6.160714285714286e-06,
+      "loss": 1.241,
+      "step": 87
+    },
+    {
+      "epoch": 0.39285714285714285,
+      "grad_norm": 0.13815440237522125,
+      "learning_rate": 6.1160714285714295e-06,
+      "loss": 1.2577,
+      "step": 88
+    },
+    {
+      "epoch": 0.39732142857142855,
+      "grad_norm": 0.13460491597652435,
+      "learning_rate": 6.071428571428571e-06,
+      "loss": 1.2537,
+      "step": 89
+    },
+    {
+      "epoch": 0.4017857142857143,
+      "grad_norm": 0.12949338555335999,
+      "learning_rate": 6.0267857142857145e-06,
+      "loss": 1.2344,
+      "step": 90
+    },
+    {
+      "epoch": 0.40625,
+      "grad_norm": 0.1302238553762436,
+      "learning_rate": 5.982142857142858e-06,
+      "loss": 1.2372,
+      "step": 91
+    },
+    {
+      "epoch": 0.4107142857142857,
+      "grad_norm": 0.13577617704868317,
+      "learning_rate": 5.9375e-06,
+      "loss": 1.2193,
+      "step": 92
+    },
+    {
+      "epoch": 0.41517857142857145,
+      "grad_norm": 0.13365642726421356,
+      "learning_rate": 5.892857142857144e-06,
+      "loss": 1.2037,
+      "step": 93
+    },
+    {
+      "epoch": 0.41964285714285715,
+      "grad_norm": 0.14120595157146454,
+      "learning_rate": 5.848214285714286e-06,
+      "loss": 1.2049,
+      "step": 94
+    },
+    {
+      "epoch": 0.42410714285714285,
+      "grad_norm": 0.12736962735652924,
+      "learning_rate": 5.8035714285714295e-06,
+      "loss": 1.2026,
+      "step": 95
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.14459377527236938,
+      "learning_rate": 5.758928571428571e-06,
+      "loss": 1.2286,
+      "step": 96
+    },
+    {
+      "epoch": 0.4330357142857143,
+      "grad_norm": 0.13745085895061493,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 1.2398,
+      "step": 97
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 0.13263735175132751,
+      "learning_rate": 5.669642857142858e-06,
+      "loss": 1.2096,
+      "step": 98
+    },
+    {
+      "epoch": 0.4419642857142857,
+      "grad_norm": 0.13073395192623138,
+      "learning_rate": 5.625e-06,
+      "loss": 1.2092,
+      "step": 99
+    },
+    {
+      "epoch": 0.44642857142857145,
+      "grad_norm": 0.14043200016021729,
+      "learning_rate": 5.580357142857144e-06,
+      "loss": 1.2014,
+      "step": 100
+    },
+    {
+      "epoch": 0.45089285714285715,
+      "grad_norm": 0.131410151720047,
+      "learning_rate": 5.535714285714286e-06,
+      "loss": 1.2063,
+      "step": 101
+    },
+    {
+      "epoch": 0.45535714285714285,
+      "grad_norm": 0.13128075003623962,
+      "learning_rate": 5.4910714285714295e-06,
+      "loss": 1.2026,
+      "step": 102
+    },
+    {
+      "epoch": 0.45982142857142855,
+      "grad_norm": 0.1351388841867447,
+      "learning_rate": 5.446428571428571e-06,
+      "loss": 1.2252,
+      "step": 103
+    },
+    {
+      "epoch": 0.4642857142857143,
+      "grad_norm": 0.14382533729076385,
+      "learning_rate": 5.4017857142857145e-06,
+      "loss": 1.2404,
+      "step": 104
+    },
+    {
+      "epoch": 0.46875,
+      "grad_norm": 0.1356382519006729,
+      "learning_rate": 5.357142857142857e-06,
+      "loss": 1.1947,
+      "step": 105
+    },
+    {
+      "epoch": 0.4732142857142857,
+      "grad_norm": 0.1357538104057312,
+      "learning_rate": 5.3125e-06,
+      "loss": 1.2438,
+      "step": 106
+    },
+    {
+      "epoch": 0.47767857142857145,
+      "grad_norm": 0.1315409392118454,
+      "learning_rate": 5.267857142857144e-06,
+      "loss": 1.2206,
+      "step": 107
+    },
+    {
+      "epoch": 0.48214285714285715,
+      "grad_norm": 0.13393516838550568,
+      "learning_rate": 5.223214285714286e-06,
+      "loss": 1.2032,
+      "step": 108
+    },
+    {
+      "epoch": 0.48660714285714285,
+      "grad_norm": 0.14275072515010834,
+      "learning_rate": 5.1785714285714296e-06,
+      "loss": 1.1819,
+      "step": 109
+    },
+    {
+      "epoch": 0.49107142857142855,
+      "grad_norm": 0.12889139354228973,
+      "learning_rate": 5.133928571428571e-06,
+      "loss": 1.1878,
+      "step": 110
+    },
+    {
+      "epoch": 0.4955357142857143,
+      "grad_norm": 0.14021390676498413,
+      "learning_rate": 5.0892857142857146e-06,
+      "loss": 1.218,
+      "step": 111
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.16816362738609314,
+      "learning_rate": 5.044642857142857e-06,
+      "loss": 1.2514,
+      "step": 112
+    },
+    {
+      "epoch": 0.5044642857142857,
+      "grad_norm": 0.13309289515018463,
+      "learning_rate": 5e-06,
+      "loss": 1.1518,
+      "step": 113
+    },
+    {
+      "epoch": 0.5089285714285714,
+      "grad_norm": 0.12924863398075104,
+      "learning_rate": 4.955357142857144e-06,
+      "loss": 1.1919,
+      "step": 114
+    },
+    {
+      "epoch": 0.5133928571428571,
+      "grad_norm": 0.12987807393074036,
+      "learning_rate": 4.910714285714286e-06,
+      "loss": 1.1717,
+      "step": 115
+    },
+    {
+      "epoch": 0.5178571428571429,
+      "grad_norm": 0.130936861038208,
+      "learning_rate": 4.866071428571429e-06,
+      "loss": 1.1618,
+      "step": 116
+    },
+    {
+      "epoch": 0.5223214285714286,
+      "grad_norm": 0.12917178869247437,
+      "learning_rate": 4.821428571428572e-06,
+      "loss": 1.186,
+      "step": 117
+    },
+    {
+      "epoch": 0.5267857142857143,
+      "grad_norm": 0.14032940566539764,
+      "learning_rate": 4.776785714285715e-06,
+      "loss": 1.1743,
+      "step": 118
+    },
+    {
+      "epoch": 0.53125,
+      "grad_norm": 0.13372235000133514,
+      "learning_rate": 4.732142857142857e-06,
+      "loss": 1.1939,
+      "step": 119
+    },
+    {
+      "epoch": 0.5357142857142857,
+      "grad_norm": 0.13410191237926483,
+      "learning_rate": 4.6875000000000004e-06,
+      "loss": 1.1945,
+      "step": 120
+    },
+    {
+      "epoch": 0.5401785714285714,
+      "grad_norm": 0.13367801904678345,
+      "learning_rate": 4.642857142857144e-06,
+      "loss": 1.1806,
+      "step": 121
+    },
+    {
+      "epoch": 0.5446428571428571,
+      "grad_norm": 0.13609707355499268,
+      "learning_rate": 4.5982142857142854e-06,
+      "loss": 1.1784,
+      "step": 122
+    },
+    {
+      "epoch": 0.5491071428571429,
+      "grad_norm": 0.15862178802490234,
+      "learning_rate": 4.553571428571429e-06,
+      "loss": 1.191,
+      "step": 123
+    },
+    {
+      "epoch": 0.5535714285714286,
+      "grad_norm": 0.15431225299835205,
+      "learning_rate": 4.508928571428572e-06,
+      "loss": 1.2049,
+      "step": 124
+    },
+    {
+      "epoch": 0.5580357142857143,
+      "grad_norm": 0.1453421711921692,
+      "learning_rate": 4.464285714285715e-06,
+      "loss": 1.1342,
+      "step": 125
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 0.13594257831573486,
+      "learning_rate": 4.419642857142857e-06,
+      "loss": 1.1787,
+      "step": 126
+    },
+    {
+      "epoch": 0.5669642857142857,
+      "grad_norm": 0.13727523386478424,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 1.2001,
+      "step": 127
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.13708378374576569,
+      "learning_rate": 4.330357142857143e-06,
+      "loss": 1.1516,
+      "step": 128
+    },
+    {
+      "epoch": 0.5758928571428571,
+      "grad_norm": 0.13883978128433228,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 1.1368,
+      "step": 129
+    },
+    {
+      "epoch": 0.5803571428571429,
+      "grad_norm": 0.1420813947916031,
+      "learning_rate": 4.241071428571429e-06,
+      "loss": 1.1995,
+      "step": 130
+    },
+    {
+      "epoch": 0.5848214285714286,
+      "grad_norm": 0.1351509690284729,
+      "learning_rate": 4.196428571428572e-06,
+      "loss": 1.1772,
+      "step": 131
+    },
+    {
+      "epoch": 0.5892857142857143,
+      "grad_norm": 0.12754634022712708,
+      "learning_rate": 4.151785714285715e-06,
+      "loss": 1.1762,
+      "step": 132
+    },
+    {
+      "epoch": 0.59375,
+      "grad_norm": 0.14284002780914307,
+      "learning_rate": 4.107142857142857e-06,
+      "loss": 1.1994,
+      "step": 133
+    },
+    {
+      "epoch": 0.5982142857142857,
+      "grad_norm": 0.1389753222465515,
+      "learning_rate": 4.0625000000000005e-06,
+      "loss": 1.1666,
+      "step": 134
+    },
+    {
+      "epoch": 0.6026785714285714,
+      "grad_norm": 0.1371830403804779,
+      "learning_rate": 4.017857142857143e-06,
+      "loss": 1.1708,
+      "step": 135
+    },
+    {
+      "epoch": 0.6071428571428571,
+      "grad_norm": 0.12737953662872314,
+      "learning_rate": 3.9732142857142855e-06,
+      "loss": 1.1414,
+      "step": 136
+    },
+    {
+      "epoch": 0.6116071428571429,
+      "grad_norm": 0.13899219036102295,
+      "learning_rate": 3.928571428571429e-06,
+      "loss": 1.1852,
+      "step": 137
+    },
+    {
+      "epoch": 0.6160714285714286,
+      "grad_norm": 0.1280209869146347,
+      "learning_rate": 3.883928571428572e-06,
+      "loss": 1.1545,
+      "step": 138
+    },
+    {
+      "epoch": 0.6205357142857143,
+      "grad_norm": 0.13463953137397766,
+      "learning_rate": 3.839285714285715e-06,
+      "loss": 1.1774,
+      "step": 139
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.13245397806167603,
+      "learning_rate": 3.794642857142857e-06,
+      "loss": 1.1796,
+      "step": 140
+    },
+    {
+      "epoch": 0.6294642857142857,
+      "grad_norm": 0.1448804885149002,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 1.2024,
+      "step": 141
+    },
+    {
+      "epoch": 0.6339285714285714,
+      "grad_norm": 0.13230714201927185,
+      "learning_rate": 3.7053571428571434e-06,
+      "loss": 1.1409,
+      "step": 142
+    },
+    {
+      "epoch": 0.6383928571428571,
+      "grad_norm": 0.1369924694299698,
+      "learning_rate": 3.660714285714286e-06,
+      "loss": 1.1892,
+      "step": 143
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 0.14439815282821655,
+      "learning_rate": 3.616071428571429e-06,
+      "loss": 1.1925,
+      "step": 144
+    },
+    {
+      "epoch": 0.6473214285714286,
+      "grad_norm": 0.13544173538684845,
+      "learning_rate": 3.5714285714285718e-06,
+      "loss": 1.168,
+      "step": 145
+    },
+    {
+      "epoch": 0.6517857142857143,
+      "grad_norm": 0.1394329071044922,
+      "learning_rate": 3.5267857142857147e-06,
+      "loss": 1.1665,
+      "step": 146
+    },
+    {
+      "epoch": 0.65625,
+      "grad_norm": 0.14236660301685333,
+      "learning_rate": 3.482142857142857e-06,
+      "loss": 1.1826,
+      "step": 147
+    },
+    {
+      "epoch": 0.6607142857142857,
+      "grad_norm": 0.14334525167942047,
+      "learning_rate": 3.4375e-06,
+      "loss": 1.1772,
+      "step": 148
+    },
+    {
+      "epoch": 0.6651785714285714,
+      "grad_norm": 0.14144295454025269,
+      "learning_rate": 3.3928571428571435e-06,
+      "loss": 1.1556,
+      "step": 149
+    },
+    {
+      "epoch": 0.6696428571428571,
+      "grad_norm": 0.1426755040884018,
+      "learning_rate": 3.3482142857142855e-06,
+      "loss": 1.153,
+      "step": 150
+    },
+    {
+      "epoch": 0.6741071428571429,
+      "grad_norm": 0.13503022491931915,
+      "learning_rate": 3.303571428571429e-06,
+      "loss": 1.1511,
+      "step": 151
+    },
+    {
+      "epoch": 0.6785714285714286,
+      "grad_norm": 0.1371900588274002,
+      "learning_rate": 3.258928571428572e-06,
+      "loss": 1.1534,
+      "step": 152
+    },
+    {
+      "epoch": 0.6830357142857143,
+      "grad_norm": 0.1478663980960846,
+      "learning_rate": 3.2142857142857147e-06,
+      "loss": 1.198,
+      "step": 153
+    },
+    {
+      "epoch": 0.6875,
+      "grad_norm": 0.13799931108951569,
+      "learning_rate": 3.1696428571428572e-06,
+      "loss": 1.1568,
+      "step": 154
+    },
+    {
+      "epoch": 0.6919642857142857,
+      "grad_norm": 0.13773539662361145,
+      "learning_rate": 3.125e-06,
+      "loss": 1.179,
+      "step": 155
+    },
+    {
+      "epoch": 0.6964285714285714,
+      "grad_norm": 0.14084257185459137,
+      "learning_rate": 3.080357142857143e-06,
+      "loss": 1.1633,
+      "step": 156
+    },
+    {
+      "epoch": 0.7008928571428571,
+      "grad_norm": 0.13720256090164185,
+      "learning_rate": 3.0357142857142856e-06,
+      "loss": 1.1324,
+      "step": 157
+    },
+    {
+      "epoch": 0.7053571428571429,
+      "grad_norm": 0.14553897082805634,
+      "learning_rate": 2.991071428571429e-06,
+      "loss": 1.1671,
+      "step": 158
+    },
+    {
+      "epoch": 0.7098214285714286,
+      "grad_norm": 0.14883799850940704,
+      "learning_rate": 2.946428571428572e-06,
+      "loss": 1.1145,
+      "step": 159
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.14336156845092773,
+      "learning_rate": 2.9017857142857148e-06,
+      "loss": 1.1823,
+      "step": 160
+    },
+    {
+      "epoch": 0.71875,
+      "grad_norm": 0.13520702719688416,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 1.1643,
+      "step": 161
+    },
+    {
+      "epoch": 0.7232142857142857,
+      "grad_norm": 0.1342165470123291,
+      "learning_rate": 2.8125e-06,
+      "loss": 1.1347,
+      "step": 162
+    },
+    {
+      "epoch": 0.7276785714285714,
+      "grad_norm": 0.1346280872821808,
+      "learning_rate": 2.767857142857143e-06,
+      "loss": 1.1597,
+      "step": 163
+    },
+    {
+      "epoch": 0.7321428571428571,
+      "grad_norm": 0.14048601686954498,
+      "learning_rate": 2.7232142857142856e-06,
+      "loss": 1.1429,
+      "step": 164
+    },
+    {
+      "epoch": 0.7366071428571429,
+      "grad_norm": 0.14143824577331543,
+      "learning_rate": 2.6785714285714285e-06,
+      "loss": 1.1659,
+      "step": 165
+    },
+    {
+      "epoch": 0.7410714285714286,
+      "grad_norm": 0.1457449495792389,
+      "learning_rate": 2.633928571428572e-06,
+      "loss": 1.1637,
+      "step": 166
+    },
+    {
+      "epoch": 0.7455357142857143,
+      "grad_norm": 0.13967274129390717,
+      "learning_rate": 2.5892857142857148e-06,
+      "loss": 1.1369,
+      "step": 167
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.13499391078948975,
+      "learning_rate": 2.5446428571428573e-06,
+      "loss": 1.1571,
+      "step": 168
+    },
+    {
+      "epoch": 0.7544642857142857,
+      "grad_norm": 0.13694655895233154,
+      "learning_rate": 2.5e-06,
+      "loss": 1.1098,
+      "step": 169
+    },
+    {
+      "epoch": 0.7589285714285714,
+      "grad_norm": 0.13261961936950684,
+      "learning_rate": 2.455357142857143e-06,
+      "loss": 1.1453,
+      "step": 170
+    },
+    {
+      "epoch": 0.7633928571428571,
+      "grad_norm": 0.13696026802062988,
+      "learning_rate": 2.410714285714286e-06,
+      "loss": 1.1278,
+      "step": 171
+    },
+    {
+      "epoch": 0.7678571428571429,
+      "grad_norm": 0.1414492428302765,
+      "learning_rate": 2.3660714285714285e-06,
+      "loss": 1.151,
+      "step": 172
+    },
+    {
+      "epoch": 0.7723214285714286,
+      "grad_norm": 0.13871721923351288,
+      "learning_rate": 2.321428571428572e-06,
+      "loss": 1.1331,
+      "step": 173
+    },
+    {
+      "epoch": 0.7767857142857143,
+      "grad_norm": 0.1417056918144226,
+      "learning_rate": 2.2767857142857144e-06,
+      "loss": 1.1731,
+      "step": 174
+    },
+    {
+      "epoch": 0.78125,
+      "grad_norm": 0.13839563727378845,
+      "learning_rate": 2.2321428571428573e-06,
+      "loss": 1.1297,
+      "step": 175
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 0.13981503248214722,
+      "learning_rate": 2.1875000000000002e-06,
+      "loss": 1.1185,
+      "step": 176
+    },
+    {
+      "epoch": 0.7901785714285714,
+      "grad_norm": 0.1417553424835205,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 1.1409,
+      "step": 177
+    },
+    {
+      "epoch": 0.7946428571428571,
+      "grad_norm": 0.1431313455104828,
+      "learning_rate": 2.098214285714286e-06,
+      "loss": 1.1856,
+      "step": 178
+    },
+    {
+      "epoch": 0.7991071428571429,
+      "grad_norm": 0.14143894612789154,
+      "learning_rate": 2.0535714285714286e-06,
+      "loss": 1.1673,
+      "step": 179
+    },
+    {
+      "epoch": 0.8035714285714286,
+      "grad_norm": 0.1380784958600998,
+      "learning_rate": 2.0089285714285715e-06,
+      "loss": 1.1309,
+      "step": 180
+    },
+    {
+      "epoch": 0.8080357142857143,
+      "grad_norm": 0.1358453333377838,
+      "learning_rate": 1.9642857142857144e-06,
+      "loss": 1.1525,
+      "step": 181
+    },
+    {
+      "epoch": 0.8125,
+      "grad_norm": 0.13622991740703583,
+      "learning_rate": 1.9196428571428573e-06,
+      "loss": 1.1368,
+      "step": 182
+    },
+    {
+      "epoch": 0.8169642857142857,
+      "grad_norm": 0.1379437893629074,
+      "learning_rate": 1.8750000000000003e-06,
+      "loss": 1.153,
+      "step": 183
+    },
+    {
+      "epoch": 0.8214285714285714,
+      "grad_norm": 0.13688063621520996,
+      "learning_rate": 1.830357142857143e-06,
+      "loss": 1.1266,
+      "step": 184
+    },
+    {
+      "epoch": 0.8258928571428571,
+      "grad_norm": 0.14775045216083527,
+      "learning_rate": 1.7857142857142859e-06,
+      "loss": 1.1409,
+      "step": 185
+    },
+    {
+      "epoch": 0.8303571428571429,
+      "grad_norm": 0.1389559507369995,
+      "learning_rate": 1.7410714285714286e-06,
+      "loss": 1.1512,
+      "step": 186
+    },
+    {
+      "epoch": 0.8348214285714286,
+      "grad_norm": 0.13888102769851685,
+      "learning_rate": 1.6964285714285717e-06,
+      "loss": 1.1369,
+      "step": 187
+    },
+    {
+      "epoch": 0.8392857142857143,
+      "grad_norm": 0.13742884993553162,
+      "learning_rate": 1.6517857142857144e-06,
+      "loss": 1.1279,
+      "step": 188
+    },
+    {
+      "epoch": 0.84375,
+      "grad_norm": 0.13602739572525024,
+      "learning_rate": 1.6071428571428574e-06,
+      "loss": 1.1382,
+      "step": 189
+    },
+    {
+      "epoch": 0.8482142857142857,
+      "grad_norm": 0.13582037389278412,
+      "learning_rate": 1.5625e-06,
+      "loss": 1.1445,
+      "step": 190
+    },
+    {
+      "epoch": 0.8526785714285714,
+      "grad_norm": 0.13878953456878662,
+      "learning_rate": 1.5178571428571428e-06,
+      "loss": 1.1248,
+      "step": 191
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.13935624063014984,
+      "learning_rate": 1.473214285714286e-06,
+      "loss": 1.1197,
+      "step": 192
+    },
+    {
+      "epoch": 0.8616071428571429,
+      "grad_norm": 0.13934870064258575,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 1.1334,
+      "step": 193
+    },
+    {
+      "epoch": 0.8660714285714286,
+      "grad_norm": 0.13222268223762512,
+      "learning_rate": 1.3839285714285715e-06,
+      "loss": 1.1378,
+      "step": 194
+    },
+    {
+      "epoch": 0.8705357142857143,
+      "grad_norm": 0.13988327980041504,
+      "learning_rate": 1.3392857142857143e-06,
+      "loss": 1.1395,
+      "step": 195
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.13992904126644135,
+      "learning_rate": 1.2946428571428574e-06,
+      "loss": 1.1276,
+      "step": 196
+    },
+    {
+      "epoch": 0.8794642857142857,
+      "grad_norm": 0.1357453167438507,
+      "learning_rate": 1.25e-06,
+      "loss": 1.1442,
+      "step": 197
+    },
+    {
+      "epoch": 0.8839285714285714,
+      "grad_norm": 0.13754713535308838,
+      "learning_rate": 1.205357142857143e-06,
+      "loss": 1.1565,
+      "step": 198
+    },
+    {
+      "epoch": 0.8883928571428571,
+      "grad_norm": 0.1530381590127945,
+      "learning_rate": 1.160714285714286e-06,
+      "loss": 1.1363,
+      "step": 199
+    },
+    {
+      "epoch": 0.8928571428571429,
+      "grad_norm": 0.14479362964630127,
+      "learning_rate": 1.1160714285714287e-06,
+      "loss": 1.1584,
+      "step": 200
+    },
+    {
+      "epoch": 0.8973214285714286,
+      "grad_norm": 0.14227916300296783,
+      "learning_rate": 1.0714285714285714e-06,
+      "loss": 1.156,
+      "step": 201
+    },
+    {
+      "epoch": 0.9017857142857143,
+      "grad_norm": 0.14023557305335999,
+      "learning_rate": 1.0267857142857143e-06,
+      "loss": 1.1288,
+      "step": 202
+    },
+    {
+      "epoch": 0.90625,
+      "grad_norm": 0.15354549884796143,
+      "learning_rate": 9.821428571428572e-07,
+      "loss": 1.1817,
+      "step": 203
+    },
+    {
+      "epoch": 0.9107142857142857,
+      "grad_norm": 0.13673727214336395,
+      "learning_rate": 9.375000000000001e-07,
+      "loss": 1.1269,
+      "step": 204
+    },
+    {
+      "epoch": 0.9151785714285714,
+      "grad_norm": 0.141667902469635,
+      "learning_rate": 8.928571428571429e-07,
+      "loss": 1.1518,
+      "step": 205
+    },
+    {
+      "epoch": 0.9196428571428571,
+      "grad_norm": 0.13802359998226166,
+      "learning_rate": 8.482142857142859e-07,
+      "loss": 1.1455,
+      "step": 206
+    },
+    {
+      "epoch": 0.9241071428571429,
+      "grad_norm": 0.13953754305839539,
+      "learning_rate": 8.035714285714287e-07,
+      "loss": 1.125,
+      "step": 207
+    },
+    {
+      "epoch": 0.9285714285714286,
+      "grad_norm": 0.13995689153671265,
+      "learning_rate": 7.589285714285714e-07,
+      "loss": 1.1074,
+      "step": 208
+    },
+    {
+      "epoch": 0.9330357142857143,
+      "grad_norm": 0.140846848487854,
+      "learning_rate": 7.142857142857143e-07,
+      "loss": 1.1388,
+      "step": 209
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 0.1379406452178955,
+      "learning_rate": 6.696428571428571e-07,
+      "loss": 1.1328,
+      "step": 210
+    },
+    {
+      "epoch": 0.9419642857142857,
+      "grad_norm": 0.13928835093975067,
+      "learning_rate": 6.25e-07,
+      "loss": 1.1407,
+      "step": 211
+    },
+    {
+      "epoch": 0.9464285714285714,
+      "grad_norm": 0.1481056809425354,
+      "learning_rate": 5.80357142857143e-07,
+      "loss": 1.1685,
+      "step": 212
+    },
+    {
+      "epoch": 0.9508928571428571,
+      "grad_norm": 0.1388041079044342,
+      "learning_rate": 5.357142857142857e-07,
+      "loss": 1.1329,
+      "step": 213
+    },
+    {
+      "epoch": 0.9553571428571429,
+      "grad_norm": 0.15218405425548553,
+      "learning_rate": 4.910714285714286e-07,
+      "loss": 1.1223,
+      "step": 214
+    },
+    {
+      "epoch": 0.9598214285714286,
+      "grad_norm": 0.14388203620910645,
+      "learning_rate": 4.4642857142857147e-07,
+      "loss": 1.1789,
+      "step": 215
+    },
+    {
+      "epoch": 0.9642857142857143,
+      "grad_norm": 0.13390113413333893,
+      "learning_rate": 4.0178571428571434e-07,
+      "loss": 1.1238,
+      "step": 216
+    },
+    {
+      "epoch": 0.96875,
+      "grad_norm": 0.14868895709514618,
+      "learning_rate": 3.5714285714285716e-07,
+      "loss": 1.1749,
+      "step": 217
+    },
+    {
+      "epoch": 0.9732142857142857,
+      "grad_norm": 0.1410313993692398,
+      "learning_rate": 3.125e-07,
+      "loss": 1.1383,
+      "step": 218
+    },
+    {
+      "epoch": 0.9776785714285714,
+      "grad_norm": 0.13778162002563477,
+      "learning_rate": 2.6785714285714284e-07,
+      "loss": 1.1644,
+      "step": 219
+    },
+    {
+      "epoch": 0.9821428571428571,
+      "grad_norm": 0.1361704021692276,
+      "learning_rate": 2.2321428571428574e-07,
+      "loss": 1.1087,
+      "step": 220
+    },
+    {
+      "epoch": 0.9866071428571429,
+      "grad_norm": 0.139134481549263,
+      "learning_rate": 1.7857142857142858e-07,
+      "loss": 1.1353,
+      "step": 221
+    },
+    {
+      "epoch": 0.9910714285714286,
+      "grad_norm": 0.1336539089679718,
+      "learning_rate": 1.3392857142857142e-07,
+      "loss": 1.1187,
+      "step": 222
+    },
+    {
+      "epoch": 0.9955357142857143,
+      "grad_norm": 0.14308129251003265,
+      "learning_rate": 8.928571428571429e-08,
+      "loss": 1.1487,
+      "step": 223
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.13715587556362152,
+      "learning_rate": 4.4642857142857145e-08,
+      "loss": 1.1381,
+      "step": 224
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.149679183959961,
+      "eval_runtime": 6.9751,
+      "eval_samples_per_second": 5.018,
+      "eval_steps_per_second": 0.717,
+      "step": 224
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 224,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.549557905717985e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}