Add fine-tuned model

README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-1.7B
+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/Qwen3-1.7B",
+  "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",
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "down_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 sha256:70d6e6a54402a0766c2c6a0d6f0a2b7cbaf50129e46fed59244789fea3a846e8
+size 278973888

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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:baf4233a05cc80d36da049c8c40877aa3b37dab8c9bc156c928f7b2ef5575305
+size 7032431

tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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\\n' }}\n    {%- endif %}\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    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- 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    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "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 +1,1588 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 0,
+  "global_step": 222,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0045045045045045045,
+      "grad_norm": 3.4618234634399414,
+      "learning_rate": 1e-05,
+      "loss": 2.6001,
+      "step": 1
+    },
+    {
+      "epoch": 0.009009009009009009,
+      "grad_norm": 3.3645927906036377,
+      "learning_rate": 9.954954954954956e-06,
+      "loss": 2.6307,
+      "step": 2
+    },
+    {
+      "epoch": 0.013513513513513514,
+      "grad_norm": 3.065110921859741,
+      "learning_rate": 9.90990990990991e-06,
+      "loss": 2.6657,
+      "step": 3
+    },
+    {
+      "epoch": 0.018018018018018018,
+      "grad_norm": 2.7996578216552734,
+      "learning_rate": 9.864864864864865e-06,
+      "loss": 2.6424,
+      "step": 4
+    },
+    {
+      "epoch": 0.02252252252252252,
+      "grad_norm": 2.491414785385132,
+      "learning_rate": 9.81981981981982e-06,
+      "loss": 2.4789,
+      "step": 5
+    },
+    {
+      "epoch": 0.02702702702702703,
+      "grad_norm": 2.2924463748931885,
+      "learning_rate": 9.774774774774776e-06,
+      "loss": 2.5258,
+      "step": 6
+    },
+    {
+      "epoch": 0.03153153153153153,
+      "grad_norm": 2.1462929248809814,
+      "learning_rate": 9.729729729729732e-06,
+      "loss": 2.5148,
+      "step": 7
+    },
+    {
+      "epoch": 0.036036036036036036,
+      "grad_norm": 1.8647502660751343,
+      "learning_rate": 9.684684684684685e-06,
+      "loss": 2.5141,
+      "step": 8
+    },
+    {
+      "epoch": 0.04054054054054054,
+      "grad_norm": 1.70541512966156,
+      "learning_rate": 9.63963963963964e-06,
+      "loss": 2.3598,
+      "step": 9
+    },
+    {
+      "epoch": 0.04504504504504504,
+      "grad_norm": 1.575402855873108,
+      "learning_rate": 9.594594594594594e-06,
+      "loss": 2.4029,
+      "step": 10
+    },
+    {
+      "epoch": 0.04954954954954955,
+      "grad_norm": 1.519256830215454,
+      "learning_rate": 9.54954954954955e-06,
+      "loss": 2.3365,
+      "step": 11
+    },
+    {
+      "epoch": 0.05405405405405406,
+      "grad_norm": 1.4052317142486572,
+      "learning_rate": 9.504504504504505e-06,
+      "loss": 2.411,
+      "step": 12
+    },
+    {
+      "epoch": 0.05855855855855856,
+      "grad_norm": 1.3125083446502686,
+      "learning_rate": 9.45945945945946e-06,
+      "loss": 2.3526,
+      "step": 13
+    },
+    {
+      "epoch": 0.06306306306306306,
+      "grad_norm": 1.2365236282348633,
+      "learning_rate": 9.414414414414416e-06,
+      "loss": 2.4095,
+      "step": 14
+    },
+    {
+      "epoch": 0.06756756756756757,
+      "grad_norm": 1.150956630706787,
+      "learning_rate": 9.36936936936937e-06,
+      "loss": 2.3604,
+      "step": 15
+    },
+    {
+      "epoch": 0.07207207207207207,
+      "grad_norm": 1.049568772315979,
+      "learning_rate": 9.324324324324325e-06,
+      "loss": 2.3305,
+      "step": 16
+    },
+    {
+      "epoch": 0.07657657657657657,
+      "grad_norm": 0.9859227538108826,
+      "learning_rate": 9.27927927927928e-06,
+      "loss": 2.297,
+      "step": 17
+    },
+    {
+      "epoch": 0.08108108108108109,
+      "grad_norm": 0.9480313658714294,
+      "learning_rate": 9.234234234234236e-06,
+      "loss": 2.3005,
+      "step": 18
+    },
+    {
+      "epoch": 0.08558558558558559,
+      "grad_norm": 0.8677704930305481,
+      "learning_rate": 9.189189189189191e-06,
+      "loss": 2.2562,
+      "step": 19
+    },
+    {
+      "epoch": 0.09009009009009009,
+      "grad_norm": 0.9002907872200012,
+      "learning_rate": 9.144144144144145e-06,
+      "loss": 2.194,
+      "step": 20
+    },
+    {
+      "epoch": 0.0945945945945946,
+      "grad_norm": 0.8388268351554871,
+      "learning_rate": 9.0990990990991e-06,
+      "loss": 2.2484,
+      "step": 21
+    },
+    {
+      "epoch": 0.0990990990990991,
+      "grad_norm": 0.7674593925476074,
+      "learning_rate": 9.054054054054054e-06,
+      "loss": 2.2072,
+      "step": 22
+    },
+    {
+      "epoch": 0.1036036036036036,
+      "grad_norm": 0.7858290076255798,
+      "learning_rate": 9.00900900900901e-06,
+      "loss": 2.2069,
+      "step": 23
+    },
+    {
+      "epoch": 0.10810810810810811,
+      "grad_norm": 0.7265046834945679,
+      "learning_rate": 8.963963963963965e-06,
+      "loss": 2.155,
+      "step": 24
+    },
+    {
+      "epoch": 0.11261261261261261,
+      "grad_norm": 0.7166778445243835,
+      "learning_rate": 8.91891891891892e-06,
+      "loss": 2.1444,
+      "step": 25
+    },
+    {
+      "epoch": 0.11711711711711711,
+      "grad_norm": 0.6849911212921143,
+      "learning_rate": 8.873873873873876e-06,
+      "loss": 2.1187,
+      "step": 26
+    },
+    {
+      "epoch": 0.12162162162162163,
+      "grad_norm": 0.7022340297698975,
+      "learning_rate": 8.82882882882883e-06,
+      "loss": 2.1996,
+      "step": 27
+    },
+    {
+      "epoch": 0.12612612612612611,
+      "grad_norm": 0.633515477180481,
+      "learning_rate": 8.783783783783785e-06,
+      "loss": 2.0704,
+      "step": 28
+    },
+    {
+      "epoch": 0.13063063063063063,
+      "grad_norm": 0.627775251865387,
+      "learning_rate": 8.738738738738739e-06,
+      "loss": 2.1014,
+      "step": 29
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 0.6084970831871033,
+      "learning_rate": 8.693693693693694e-06,
+      "loss": 2.0819,
+      "step": 30
+    },
+    {
+      "epoch": 0.13963963963963963,
+      "grad_norm": 0.6401589512825012,
+      "learning_rate": 8.64864864864865e-06,
+      "loss": 2.1203,
+      "step": 31
+    },
+    {
+      "epoch": 0.14414414414414414,
+      "grad_norm": 0.6475760340690613,
+      "learning_rate": 8.603603603603605e-06,
+      "loss": 2.0912,
+      "step": 32
+    },
+    {
+      "epoch": 0.14864864864864866,
+      "grad_norm": 0.6095289587974548,
+      "learning_rate": 8.55855855855856e-06,
+      "loss": 2.0502,
+      "step": 33
+    },
+    {
+      "epoch": 0.15315315315315314,
+      "grad_norm": 0.5864396691322327,
+      "learning_rate": 8.513513513513514e-06,
+      "loss": 2.0702,
+      "step": 34
+    },
+    {
+      "epoch": 0.15765765765765766,
+      "grad_norm": 0.5499593615531921,
+      "learning_rate": 8.46846846846847e-06,
+      "loss": 2.0222,
+      "step": 35
+    },
+    {
+      "epoch": 0.16216216216216217,
+      "grad_norm": 0.5458055734634399,
+      "learning_rate": 8.423423423423423e-06,
+      "loss": 2.0236,
+      "step": 36
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.5508635640144348,
+      "learning_rate": 8.378378378378378e-06,
+      "loss": 2.0447,
+      "step": 37
+    },
+    {
+      "epoch": 0.17117117117117117,
+      "grad_norm": 0.5145464539527893,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 1.9726,
+      "step": 38
+    },
+    {
+      "epoch": 0.17567567567567569,
+      "grad_norm": 0.5341795086860657,
+      "learning_rate": 8.288288288288289e-06,
+      "loss": 2.0392,
+      "step": 39
+    },
+    {
+      "epoch": 0.18018018018018017,
+      "grad_norm": 0.5210247039794922,
+      "learning_rate": 8.243243243243245e-06,
+      "loss": 1.9915,
+      "step": 40
+    },
+    {
+      "epoch": 0.18468468468468469,
+      "grad_norm": 0.49647679924964905,
+      "learning_rate": 8.198198198198198e-06,
+      "loss": 1.9797,
+      "step": 41
+    },
+    {
+      "epoch": 0.1891891891891892,
+      "grad_norm": 0.5066887736320496,
+      "learning_rate": 8.153153153153154e-06,
+      "loss": 1.9937,
+      "step": 42
+    },
+    {
+      "epoch": 0.19369369369369369,
+      "grad_norm": 0.5093082189559937,
+      "learning_rate": 8.108108108108109e-06,
+      "loss": 2.0124,
+      "step": 43
+    },
+    {
+      "epoch": 0.1981981981981982,
+      "grad_norm": 0.4824818968772888,
+      "learning_rate": 8.063063063063063e-06,
+      "loss": 1.9615,
+      "step": 44
+    },
+    {
+      "epoch": 0.20270270270270271,
+      "grad_norm": 0.5253979563713074,
+      "learning_rate": 8.018018018018018e-06,
+      "loss": 1.967,
+      "step": 45
+    },
+    {
+      "epoch": 0.2072072072072072,
+      "grad_norm": 0.5245465040206909,
+      "learning_rate": 7.972972972972974e-06,
+      "loss": 2.0298,
+      "step": 46
+    },
+    {
+      "epoch": 0.21171171171171171,
+      "grad_norm": 0.4816925823688507,
+      "learning_rate": 7.927927927927929e-06,
+      "loss": 2.0132,
+      "step": 47
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "grad_norm": 0.4973873794078827,
+      "learning_rate": 7.882882882882884e-06,
+      "loss": 2.0363,
+      "step": 48
+    },
+    {
+      "epoch": 0.22072072072072071,
+      "grad_norm": 0.461952269077301,
+      "learning_rate": 7.837837837837838e-06,
+      "loss": 1.9707,
+      "step": 49
+    },
+    {
+      "epoch": 0.22522522522522523,
+      "grad_norm": 0.450893759727478,
+      "learning_rate": 7.792792792792793e-06,
+      "loss": 1.9285,
+      "step": 50
+    },
+    {
+      "epoch": 0.22972972972972974,
+      "grad_norm": 0.45231375098228455,
+      "learning_rate": 7.747747747747749e-06,
+      "loss": 1.9003,
+      "step": 51
+    },
+    {
+      "epoch": 0.23423423423423423,
+      "grad_norm": 0.4198550581932068,
+      "learning_rate": 7.702702702702704e-06,
+      "loss": 1.8864,
+      "step": 52
+    },
+    {
+      "epoch": 0.23873873873873874,
+      "grad_norm": 0.41821354627609253,
+      "learning_rate": 7.657657657657658e-06,
+      "loss": 1.9022,
+      "step": 53
+    },
+    {
+      "epoch": 0.24324324324324326,
+      "grad_norm": 0.4159207344055176,
+      "learning_rate": 7.612612612612613e-06,
+      "loss": 1.8989,
+      "step": 54
+    },
+    {
+      "epoch": 0.24774774774774774,
+      "grad_norm": 0.4249446392059326,
+      "learning_rate": 7.567567567567569e-06,
+      "loss": 1.8928,
+      "step": 55
+    },
+    {
+      "epoch": 0.25225225225225223,
+      "grad_norm": 0.43254926800727844,
+      "learning_rate": 7.5225225225225225e-06,
+      "loss": 1.9572,
+      "step": 56
+    },
+    {
+      "epoch": 0.25675675675675674,
+      "grad_norm": 0.5341597199440002,
+      "learning_rate": 7.477477477477479e-06,
+      "loss": 1.9215,
+      "step": 57
+    },
+    {
+      "epoch": 0.26126126126126126,
+      "grad_norm": 0.41006702184677124,
+      "learning_rate": 7.4324324324324324e-06,
+      "loss": 1.9183,
+      "step": 58
+    },
+    {
+      "epoch": 0.26576576576576577,
+      "grad_norm": 0.45759063959121704,
+      "learning_rate": 7.387387387387388e-06,
+      "loss": 1.8702,
+      "step": 59
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 0.41543591022491455,
+      "learning_rate": 7.342342342342343e-06,
+      "loss": 1.9162,
+      "step": 60
+    },
+    {
+      "epoch": 0.2747747747747748,
+      "grad_norm": 0.4476662278175354,
+      "learning_rate": 7.297297297297298e-06,
+      "loss": 1.8759,
+      "step": 61
+    },
+    {
+      "epoch": 0.27927927927927926,
+      "grad_norm": 0.43256688117980957,
+      "learning_rate": 7.252252252252253e-06,
+      "loss": 1.9299,
+      "step": 62
+    },
+    {
+      "epoch": 0.28378378378378377,
+      "grad_norm": 0.46529731154441833,
+      "learning_rate": 7.207207207207208e-06,
+      "loss": 2.0264,
+      "step": 63
+    },
+    {
+      "epoch": 0.2882882882882883,
+      "grad_norm": 0.39733076095581055,
+      "learning_rate": 7.162162162162163e-06,
+      "loss": 1.868,
+      "step": 64
+    },
+    {
+      "epoch": 0.2927927927927928,
+      "grad_norm": 0.3892308473587036,
+      "learning_rate": 7.117117117117117e-06,
+      "loss": 1.8749,
+      "step": 65
+    },
+    {
+      "epoch": 0.2972972972972973,
+      "grad_norm": 0.46271243691444397,
+      "learning_rate": 7.072072072072072e-06,
+      "loss": 1.8241,
+      "step": 66
+    },
+    {
+      "epoch": 0.30180180180180183,
+      "grad_norm": 0.3786090016365051,
+      "learning_rate": 7.027027027027028e-06,
+      "loss": 1.7992,
+      "step": 67
+    },
+    {
+      "epoch": 0.3063063063063063,
+      "grad_norm": 0.394674688577652,
+      "learning_rate": 6.981981981981982e-06,
+      "loss": 1.8436,
+      "step": 68
+    },
+    {
+      "epoch": 0.3108108108108108,
+      "grad_norm": 0.36820194125175476,
+      "learning_rate": 6.936936936936938e-06,
+      "loss": 1.8284,
+      "step": 69
+    },
+    {
+      "epoch": 0.3153153153153153,
+      "grad_norm": 0.389141708612442,
+      "learning_rate": 6.891891891891892e-06,
+      "loss": 1.8153,
+      "step": 70
+    },
+    {
+      "epoch": 0.31981981981981983,
+      "grad_norm": 0.4735696613788605,
+      "learning_rate": 6.846846846846848e-06,
+      "loss": 1.8535,
+      "step": 71
+    },
+    {
+      "epoch": 0.32432432432432434,
+      "grad_norm": 0.37137389183044434,
+      "learning_rate": 6.801801801801803e-06,
+      "loss": 1.8457,
+      "step": 72
+    },
+    {
+      "epoch": 0.32882882882882886,
+      "grad_norm": 0.36660048365592957,
+      "learning_rate": 6.7567567567567575e-06,
+      "loss": 1.8191,
+      "step": 73
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.36980313062667847,
+      "learning_rate": 6.711711711711713e-06,
+      "loss": 1.8441,
+      "step": 74
+    },
+    {
+      "epoch": 0.33783783783783783,
+      "grad_norm": 0.3742966949939728,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.8521,
+      "step": 75
+    },
+    {
+      "epoch": 0.34234234234234234,
+      "grad_norm": 0.37553393840789795,
+      "learning_rate": 6.621621621621622e-06,
+      "loss": 1.8133,
+      "step": 76
+    },
+    {
+      "epoch": 0.34684684684684686,
+      "grad_norm": 0.48281577229499817,
+      "learning_rate": 6.5765765765765775e-06,
+      "loss": 1.8447,
+      "step": 77
+    },
+    {
+      "epoch": 0.35135135135135137,
+      "grad_norm": 0.37523260712623596,
+      "learning_rate": 6.531531531531532e-06,
+      "loss": 1.8422,
+      "step": 78
+    },
+    {
+      "epoch": 0.35585585585585583,
+      "grad_norm": 0.3609691262245178,
+      "learning_rate": 6.486486486486487e-06,
+      "loss": 1.8179,
+      "step": 79
+    },
+    {
+      "epoch": 0.36036036036036034,
+      "grad_norm": 0.47471126914024353,
+      "learning_rate": 6.441441441441442e-06,
+      "loss": 1.828,
+      "step": 80
+    },
+    {
+      "epoch": 0.36486486486486486,
+      "grad_norm": 0.3547884225845337,
+      "learning_rate": 6.396396396396397e-06,
+      "loss": 1.8362,
+      "step": 81
+    },
+    {
+      "epoch": 0.36936936936936937,
+      "grad_norm": 0.38408973813056946,
+      "learning_rate": 6.351351351351351e-06,
+      "loss": 1.8652,
+      "step": 82
+    },
+    {
+      "epoch": 0.3738738738738739,
+      "grad_norm": 0.36634501814842224,
+      "learning_rate": 6.3063063063063065e-06,
+      "loss": 1.799,
+      "step": 83
+    },
+    {
+      "epoch": 0.3783783783783784,
+      "grad_norm": 0.3446308970451355,
+      "learning_rate": 6.261261261261262e-06,
+      "loss": 1.7622,
+      "step": 84
+    },
+    {
+      "epoch": 0.38288288288288286,
+      "grad_norm": 0.36346280574798584,
+      "learning_rate": 6.2162162162162164e-06,
+      "loss": 1.7713,
+      "step": 85
+    },
+    {
+      "epoch": 0.38738738738738737,
+      "grad_norm": 0.34694963693618774,
+      "learning_rate": 6.171171171171172e-06,
+      "loss": 1.7814,
+      "step": 86
+    },
+    {
+      "epoch": 0.3918918918918919,
+      "grad_norm": 0.355396568775177,
+      "learning_rate": 6.126126126126126e-06,
+      "loss": 1.8025,
+      "step": 87
+    },
+    {
+      "epoch": 0.3963963963963964,
+      "grad_norm": 0.3488863706588745,
+      "learning_rate": 6.081081081081082e-06,
+      "loss": 1.7832,
+      "step": 88
+    },
+    {
+      "epoch": 0.4009009009009009,
+      "grad_norm": 0.3477393686771393,
+      "learning_rate": 6.036036036036037e-06,
+      "loss": 1.7375,
+      "step": 89
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 0.3712894022464752,
+      "learning_rate": 5.990990990990992e-06,
+      "loss": 1.8348,
+      "step": 90
+    },
+    {
+      "epoch": 0.4099099099099099,
+      "grad_norm": 0.44912734627723694,
+      "learning_rate": 5.945945945945947e-06,
+      "loss": 1.7269,
+      "step": 91
+    },
+    {
+      "epoch": 0.4144144144144144,
+      "grad_norm": 0.35568878054618835,
+      "learning_rate": 5.900900900900901e-06,
+      "loss": 1.8012,
+      "step": 92
+    },
+    {
+      "epoch": 0.4189189189189189,
+      "grad_norm": 0.3438522219657898,
+      "learning_rate": 5.855855855855856e-06,
+      "loss": 1.7039,
+      "step": 93
+    },
+    {
+      "epoch": 0.42342342342342343,
+      "grad_norm": 0.5138081312179565,
+      "learning_rate": 5.810810810810811e-06,
+      "loss": 1.78,
+      "step": 94
+    },
+    {
+      "epoch": 0.42792792792792794,
+      "grad_norm": 0.3379000723361969,
+      "learning_rate": 5.765765765765766e-06,
+      "loss": 1.7418,
+      "step": 95
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 0.3370780348777771,
+      "learning_rate": 5.720720720720722e-06,
+      "loss": 1.7348,
+      "step": 96
+    },
+    {
+      "epoch": 0.4369369369369369,
+      "grad_norm": 0.3390265107154846,
+      "learning_rate": 5.675675675675676e-06,
+      "loss": 1.721,
+      "step": 97
+    },
+    {
+      "epoch": 0.44144144144144143,
+      "grad_norm": 0.3562930226325989,
+      "learning_rate": 5.6306306306306316e-06,
+      "loss": 1.7826,
+      "step": 98
+    },
+    {
+      "epoch": 0.44594594594594594,
+      "grad_norm": 0.477252334356308,
+      "learning_rate": 5.585585585585585e-06,
+      "loss": 1.7175,
+      "step": 99
+    },
+    {
+      "epoch": 0.45045045045045046,
+      "grad_norm": 0.334209680557251,
+      "learning_rate": 5.540540540540541e-06,
+      "loss": 1.7416,
+      "step": 100
+    },
+    {
+      "epoch": 0.45495495495495497,
+      "grad_norm": 0.4595113694667816,
+      "learning_rate": 5.495495495495496e-06,
+      "loss": 1.7259,
+      "step": 101
+    },
+    {
+      "epoch": 0.4594594594594595,
+      "grad_norm": 0.4791535437107086,
+      "learning_rate": 5.450450450450451e-06,
+      "loss": 1.7314,
+      "step": 102
+    },
+    {
+      "epoch": 0.46396396396396394,
+      "grad_norm": 0.34569066762924194,
+      "learning_rate": 5.405405405405406e-06,
+      "loss": 1.7451,
+      "step": 103
+    },
+    {
+      "epoch": 0.46846846846846846,
+      "grad_norm": 0.33820703625679016,
+      "learning_rate": 5.360360360360361e-06,
+      "loss": 1.7172,
+      "step": 104
+    },
+    {
+      "epoch": 0.47297297297297297,
+      "grad_norm": 0.3545491695404053,
+      "learning_rate": 5.315315315315316e-06,
+      "loss": 1.7654,
+      "step": 105
+    },
+    {
+      "epoch": 0.4774774774774775,
+      "grad_norm": 0.45435503125190735,
+      "learning_rate": 5.2702702702702705e-06,
+      "loss": 1.6965,
+      "step": 106
+    },
+    {
+      "epoch": 0.481981981981982,
+      "grad_norm": 0.3440285921096802,
+      "learning_rate": 5.225225225225226e-06,
+      "loss": 1.7138,
+      "step": 107
+    },
+    {
+      "epoch": 0.4864864864864865,
+      "grad_norm": 0.3427916467189789,
+      "learning_rate": 5.180180180180181e-06,
+      "loss": 1.7171,
+      "step": 108
+    },
+    {
+      "epoch": 0.49099099099099097,
+      "grad_norm": 0.341746985912323,
+      "learning_rate": 5.135135135135135e-06,
+      "loss": 1.7144,
+      "step": 109
+    },
+    {
+      "epoch": 0.4954954954954955,
+      "grad_norm": 0.3410569131374359,
+      "learning_rate": 5.0900900900900905e-06,
+      "loss": 1.7582,
+      "step": 110
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.34173962473869324,
+      "learning_rate": 5.045045045045045e-06,
+      "loss": 1.7419,
+      "step": 111
+    },
+    {
+      "epoch": 0.5045045045045045,
+      "grad_norm": 0.34266290068626404,
+      "learning_rate": 5e-06,
+      "loss": 1.7169,
+      "step": 112
+    },
+    {
+      "epoch": 0.509009009009009,
+      "grad_norm": 0.3380753993988037,
+      "learning_rate": 4.954954954954955e-06,
+      "loss": 1.7385,
+      "step": 113
+    },
+    {
+      "epoch": 0.5135135135135135,
+      "grad_norm": 0.45319607853889465,
+      "learning_rate": 4.90990990990991e-06,
+      "loss": 1.673,
+      "step": 114
+    },
+    {
+      "epoch": 0.5180180180180181,
+      "grad_norm": 0.3970378339290619,
+      "learning_rate": 4.864864864864866e-06,
+      "loss": 1.7046,
+      "step": 115
+    },
+    {
+      "epoch": 0.5225225225225225,
+      "grad_norm": 0.5082581043243408,
+      "learning_rate": 4.81981981981982e-06,
+      "loss": 1.7395,
+      "step": 116
+    },
+    {
+      "epoch": 0.527027027027027,
+      "grad_norm": 0.33490023016929626,
+      "learning_rate": 4.774774774774775e-06,
+      "loss": 1.7578,
+      "step": 117
+    },
+    {
+      "epoch": 0.5315315315315315,
+      "grad_norm": 0.3550601601600647,
+      "learning_rate": 4.72972972972973e-06,
+      "loss": 1.7359,
+      "step": 118
+    },
+    {
+      "epoch": 0.536036036036036,
+      "grad_norm": 0.39418432116508484,
+      "learning_rate": 4.684684684684685e-06,
+      "loss": 1.7227,
+      "step": 119
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.34488528966903687,
+      "learning_rate": 4.63963963963964e-06,
+      "loss": 1.7826,
+      "step": 120
+    },
+    {
+      "epoch": 0.545045045045045,
+      "grad_norm": 0.36367273330688477,
+      "learning_rate": 4.594594594594596e-06,
+      "loss": 1.6977,
+      "step": 121
+    },
+    {
+      "epoch": 0.5495495495495496,
+      "grad_norm": 0.3362616300582886,
+      "learning_rate": 4.54954954954955e-06,
+      "loss": 1.7513,
+      "step": 122
+    },
+    {
+      "epoch": 0.5540540540540541,
+      "grad_norm": 0.35472577810287476,
+      "learning_rate": 4.504504504504505e-06,
+      "loss": 1.7207,
+      "step": 123
+    },
+    {
+      "epoch": 0.5585585585585585,
+      "grad_norm": 0.33426880836486816,
+      "learning_rate": 4.45945945945946e-06,
+      "loss": 1.7081,
+      "step": 124
+    },
+    {
+      "epoch": 0.5630630630630631,
+      "grad_norm": 0.44085991382598877,
+      "learning_rate": 4.414414414414415e-06,
+      "loss": 1.7064,
+      "step": 125
+    },
+    {
+      "epoch": 0.5675675675675675,
+      "grad_norm": 0.34073606133461,
+      "learning_rate": 4.369369369369369e-06,
+      "loss": 1.7106,
+      "step": 126
+    },
+    {
+      "epoch": 0.5720720720720721,
+      "grad_norm": 0.33393681049346924,
+      "learning_rate": 4.324324324324325e-06,
+      "loss": 1.7123,
+      "step": 127
+    },
+    {
+      "epoch": 0.5765765765765766,
+      "grad_norm": 0.34808585047721863,
+      "learning_rate": 4.27927927927928e-06,
+      "loss": 1.746,
+      "step": 128
+    },
+    {
+      "epoch": 0.581081081081081,
+      "grad_norm": 0.32998034358024597,
+      "learning_rate": 4.234234234234235e-06,
+      "loss": 1.6711,
+      "step": 129
+    },
+    {
+      "epoch": 0.5855855855855856,
+      "grad_norm": 0.3403429090976715,
+      "learning_rate": 4.189189189189189e-06,
+      "loss": 1.6766,
+      "step": 130
+    },
+    {
+      "epoch": 0.5900900900900901,
+      "grad_norm": 0.3442879617214203,
+      "learning_rate": 4.1441441441441446e-06,
+      "loss": 1.7167,
+      "step": 131
+    },
+    {
+      "epoch": 0.5945945945945946,
+      "grad_norm": 0.35281968116760254,
+      "learning_rate": 4.099099099099099e-06,
+      "loss": 1.6911,
+      "step": 132
+    },
+    {
+      "epoch": 0.5990990990990991,
+      "grad_norm": 0.36312294006347656,
+      "learning_rate": 4.0540540540540545e-06,
+      "loss": 1.6752,
+      "step": 133
+    },
+    {
+      "epoch": 0.6036036036036037,
+      "grad_norm": 0.5125902891159058,
+      "learning_rate": 4.009009009009009e-06,
+      "loss": 1.7018,
+      "step": 134
+    },
+    {
+      "epoch": 0.6081081081081081,
+      "grad_norm": 0.3540242314338684,
+      "learning_rate": 3.9639639639639645e-06,
+      "loss": 1.7434,
+      "step": 135
+    },
+    {
+      "epoch": 0.6126126126126126,
+      "grad_norm": 0.3490309417247772,
+      "learning_rate": 3.918918918918919e-06,
+      "loss": 1.6623,
+      "step": 136
+    },
+    {
+      "epoch": 0.6171171171171171,
+      "grad_norm": 0.3411913812160492,
+      "learning_rate": 3.8738738738738744e-06,
+      "loss": 1.6375,
+      "step": 137
+    },
+    {
+      "epoch": 0.6216216216216216,
+      "grad_norm": 0.3555877208709717,
+      "learning_rate": 3.828828828828829e-06,
+      "loss": 1.6833,
+      "step": 138
+    },
+    {
+      "epoch": 0.6261261261261262,
+      "grad_norm": 0.391271710395813,
+      "learning_rate": 3.7837837837837844e-06,
+      "loss": 1.6057,
+      "step": 139
+    },
+    {
+      "epoch": 0.6306306306306306,
+      "grad_norm": 0.3273333013057709,
+      "learning_rate": 3.7387387387387394e-06,
+      "loss": 1.6553,
+      "step": 140
+    },
+    {
+      "epoch": 0.6351351351351351,
+      "grad_norm": 0.3500949442386627,
+      "learning_rate": 3.693693693693694e-06,
+      "loss": 1.6151,
+      "step": 141
+    },
+    {
+      "epoch": 0.6396396396396397,
+      "grad_norm": 0.36416658759117126,
+      "learning_rate": 3.648648648648649e-06,
+      "loss": 1.6769,
+      "step": 142
+    },
+    {
+      "epoch": 0.6441441441441441,
+      "grad_norm": 0.3524824380874634,
+      "learning_rate": 3.603603603603604e-06,
+      "loss": 1.6869,
+      "step": 143
+    },
+    {
+      "epoch": 0.6486486486486487,
+      "grad_norm": 0.3461499512195587,
+      "learning_rate": 3.5585585585585584e-06,
+      "loss": 1.665,
+      "step": 144
+    },
+    {
+      "epoch": 0.6531531531531531,
+      "grad_norm": 0.3453364074230194,
+      "learning_rate": 3.513513513513514e-06,
+      "loss": 1.6884,
+      "step": 145
+    },
+    {
+      "epoch": 0.6576576576576577,
+      "grad_norm": 0.3358488976955414,
+      "learning_rate": 3.468468468468469e-06,
+      "loss": 1.6457,
+      "step": 146
+    },
+    {
+      "epoch": 0.6621621621621622,
+      "grad_norm": 0.3561137020587921,
+      "learning_rate": 3.423423423423424e-06,
+      "loss": 1.7074,
+      "step": 147
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.3294833302497864,
+      "learning_rate": 3.3783783783783788e-06,
+      "loss": 1.6475,
+      "step": 148
+    },
+    {
+      "epoch": 0.6711711711711712,
+      "grad_norm": 0.3332567512989044,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.6376,
+      "step": 149
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 0.4869362711906433,
+      "learning_rate": 3.2882882882882887e-06,
+      "loss": 1.6186,
+      "step": 150
+    },
+    {
+      "epoch": 0.6801801801801802,
+      "grad_norm": 0.33938735723495483,
+      "learning_rate": 3.2432432432432437e-06,
+      "loss": 1.6374,
+      "step": 151
+    },
+    {
+      "epoch": 0.6846846846846847,
+      "grad_norm": 0.48691487312316895,
+      "learning_rate": 3.1981981981981987e-06,
+      "loss": 1.6214,
+      "step": 152
+    },
+    {
+      "epoch": 0.6891891891891891,
+      "grad_norm": 0.3412449359893799,
+      "learning_rate": 3.1531531531531532e-06,
+      "loss": 1.6594,
+      "step": 153
+    },
+    {
+      "epoch": 0.6936936936936937,
+      "grad_norm": 0.35119444131851196,
+      "learning_rate": 3.1081081081081082e-06,
+      "loss": 1.7138,
+      "step": 154
+    },
+    {
+      "epoch": 0.6981981981981982,
+      "grad_norm": 0.37252432107925415,
+      "learning_rate": 3.063063063063063e-06,
+      "loss": 1.6712,
+      "step": 155
+    },
+    {
+      "epoch": 0.7027027027027027,
+      "grad_norm": 0.32262712717056274,
+      "learning_rate": 3.0180180180180186e-06,
+      "loss": 1.6269,
+      "step": 156
+    },
+    {
+      "epoch": 0.7072072072072072,
+      "grad_norm": 0.3406342566013336,
+      "learning_rate": 2.9729729729729736e-06,
+      "loss": 1.694,
+      "step": 157
+    },
+    {
+      "epoch": 0.7117117117117117,
+      "grad_norm": 0.34315645694732666,
+      "learning_rate": 2.927927927927928e-06,
+      "loss": 1.7172,
+      "step": 158
+    },
+    {
+      "epoch": 0.7162162162162162,
+      "grad_norm": 0.4974067807197571,
+      "learning_rate": 2.882882882882883e-06,
+      "loss": 1.6876,
+      "step": 159
+    },
+    {
+      "epoch": 0.7207207207207207,
+      "grad_norm": 0.3327634334564209,
+      "learning_rate": 2.837837837837838e-06,
+      "loss": 1.668,
+      "step": 160
+    },
+    {
+      "epoch": 0.7252252252252253,
+      "grad_norm": 0.363633930683136,
+      "learning_rate": 2.7927927927927926e-06,
+      "loss": 1.6732,
+      "step": 161
+    },
+    {
+      "epoch": 0.7297297297297297,
+      "grad_norm": 0.35024866461753845,
+      "learning_rate": 2.747747747747748e-06,
+      "loss": 1.6703,
+      "step": 162
+    },
+    {
+      "epoch": 0.7342342342342343,
+      "grad_norm": 0.34215882420539856,
+      "learning_rate": 2.702702702702703e-06,
+      "loss": 1.6729,
+      "step": 163
+    },
+    {
+      "epoch": 0.7387387387387387,
+      "grad_norm": 0.34051352739334106,
+      "learning_rate": 2.657657657657658e-06,
+      "loss": 1.6548,
+      "step": 164
+    },
+    {
+      "epoch": 0.7432432432432432,
+      "grad_norm": 0.5225317478179932,
+      "learning_rate": 2.612612612612613e-06,
+      "loss": 1.6344,
+      "step": 165
+    },
+    {
+      "epoch": 0.7477477477477478,
+      "grad_norm": 0.40349280834198,
+      "learning_rate": 2.5675675675675675e-06,
+      "loss": 1.6252,
+      "step": 166
+    },
+    {
+      "epoch": 0.7522522522522522,
+      "grad_norm": 0.3395436704158783,
+      "learning_rate": 2.5225225225225225e-06,
+      "loss": 1.6486,
+      "step": 167
+    },
+    {
+      "epoch": 0.7567567567567568,
+      "grad_norm": 0.3456726670265198,
+      "learning_rate": 2.4774774774774775e-06,
+      "loss": 1.6756,
+      "step": 168
+    },
+    {
+      "epoch": 0.7612612612612613,
+      "grad_norm": 0.3367043435573578,
+      "learning_rate": 2.432432432432433e-06,
+      "loss": 1.6589,
+      "step": 169
+    },
+    {
+      "epoch": 0.7657657657657657,
+      "grad_norm": 0.3494514226913452,
+      "learning_rate": 2.3873873873873874e-06,
+      "loss": 1.6763,
+      "step": 170
+    },
+    {
+      "epoch": 0.7702702702702703,
+      "grad_norm": 0.3343624770641327,
+      "learning_rate": 2.3423423423423424e-06,
+      "loss": 1.6118,
+      "step": 171
+    },
+    {
+      "epoch": 0.7747747747747747,
+      "grad_norm": 0.33982744812965393,
+      "learning_rate": 2.297297297297298e-06,
+      "loss": 1.639,
+      "step": 172
+    },
+    {
+      "epoch": 0.7792792792792793,
+      "grad_norm": 0.33141806721687317,
+      "learning_rate": 2.2522522522522524e-06,
+      "loss": 1.6643,
+      "step": 173
+    },
+    {
+      "epoch": 0.7837837837837838,
+      "grad_norm": 0.3434072434902191,
+      "learning_rate": 2.2072072072072073e-06,
+      "loss": 1.5689,
+      "step": 174
+    },
+    {
+      "epoch": 0.7882882882882883,
+      "grad_norm": 0.3629867136478424,
+      "learning_rate": 2.1621621621621623e-06,
+      "loss": 1.6995,
+      "step": 175
+    },
+    {
+      "epoch": 0.7927927927927928,
+      "grad_norm": 0.33522751927375793,
+      "learning_rate": 2.1171171171171173e-06,
+      "loss": 1.6482,
+      "step": 176
+    },
+    {
+      "epoch": 0.7972972972972973,
+      "grad_norm": 0.34863755106925964,
+      "learning_rate": 2.0720720720720723e-06,
+      "loss": 1.6613,
+      "step": 177
+    },
+    {
+      "epoch": 0.8018018018018018,
+      "grad_norm": 0.3450457751750946,
+      "learning_rate": 2.0270270270270273e-06,
+      "loss": 1.6708,
+      "step": 178
+    },
+    {
+      "epoch": 0.8063063063063063,
+      "grad_norm": 0.3388313055038452,
+      "learning_rate": 1.9819819819819822e-06,
+      "loss": 1.6517,
+      "step": 179
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 0.3772425651550293,
+      "learning_rate": 1.9369369369369372e-06,
+      "loss": 1.5883,
+      "step": 180
+    },
+    {
+      "epoch": 0.8153153153153153,
+      "grad_norm": 0.34325921535491943,
+      "learning_rate": 1.8918918918918922e-06,
+      "loss": 1.6263,
+      "step": 181
+    },
+    {
+      "epoch": 0.8198198198198198,
+      "grad_norm": 0.31989938020706177,
+      "learning_rate": 1.846846846846847e-06,
+      "loss": 1.6133,
+      "step": 182
+    },
+    {
+      "epoch": 0.8243243243243243,
+      "grad_norm": 0.3870126008987427,
+      "learning_rate": 1.801801801801802e-06,
+      "loss": 1.6299,
+      "step": 183
+    },
+    {
+      "epoch": 0.8288288288288288,
+      "grad_norm": 0.3582821190357208,
+      "learning_rate": 1.756756756756757e-06,
+      "loss": 1.6416,
+      "step": 184
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.3285435736179352,
+      "learning_rate": 1.711711711711712e-06,
+      "loss": 1.6556,
+      "step": 185
+    },
+    {
+      "epoch": 0.8378378378378378,
+      "grad_norm": 0.3296816647052765,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.6513,
+      "step": 186
+    },
+    {
+      "epoch": 0.8423423423423423,
+      "grad_norm": 0.32003799080848694,
+      "learning_rate": 1.6216216216216219e-06,
+      "loss": 1.6641,
+      "step": 187
+    },
+    {
+      "epoch": 0.8468468468468469,
+      "grad_norm": 0.41711196303367615,
+      "learning_rate": 1.5765765765765766e-06,
+      "loss": 1.6022,
+      "step": 188
+    },
+    {
+      "epoch": 0.8513513513513513,
+      "grad_norm": 0.3556946814060211,
+      "learning_rate": 1.5315315315315316e-06,
+      "loss": 1.6824,
+      "step": 189
+    },
+    {
+      "epoch": 0.8558558558558559,
+      "grad_norm": 0.33673131465911865,
+      "learning_rate": 1.4864864864864868e-06,
+      "loss": 1.6419,
+      "step": 190
+    },
+    {
+      "epoch": 0.8603603603603603,
+      "grad_norm": 0.41371607780456543,
+      "learning_rate": 1.4414414414414416e-06,
+      "loss": 1.6329,
+      "step": 191
+    },
+    {
+      "epoch": 0.8648648648648649,
+      "grad_norm": 0.3232820928096771,
+      "learning_rate": 1.3963963963963963e-06,
+      "loss": 1.645,
+      "step": 192
+    },
+    {
+      "epoch": 0.8693693693693694,
+      "grad_norm": 0.5039376616477966,
+      "learning_rate": 1.3513513513513515e-06,
+      "loss": 1.6429,
+      "step": 193
+    },
+    {
+      "epoch": 0.8738738738738738,
+      "grad_norm": 0.4405737519264221,
+      "learning_rate": 1.3063063063063065e-06,
+      "loss": 1.6726,
+      "step": 194
+    },
+    {
+      "epoch": 0.8783783783783784,
+      "grad_norm": 0.32625824213027954,
+      "learning_rate": 1.2612612612612613e-06,
+      "loss": 1.6614,
+      "step": 195
+    },
+    {
+      "epoch": 0.8828828828828829,
+      "grad_norm": 0.34024447202682495,
+      "learning_rate": 1.2162162162162164e-06,
+      "loss": 1.6198,
+      "step": 196
+    },
+    {
+      "epoch": 0.8873873873873874,
+      "grad_norm": 0.3739813566207886,
+      "learning_rate": 1.1711711711711712e-06,
+      "loss": 1.6033,
+      "step": 197
+    },
+    {
+      "epoch": 0.8918918918918919,
+      "grad_norm": 0.35833895206451416,
+      "learning_rate": 1.1261261261261262e-06,
+      "loss": 1.7058,
+      "step": 198
+    },
+    {
+      "epoch": 0.8963963963963963,
+      "grad_norm": 0.3302564322948456,
+      "learning_rate": 1.0810810810810812e-06,
+      "loss": 1.5926,
+      "step": 199
+    },
+    {
+      "epoch": 0.9009009009009009,
+      "grad_norm": 0.32919058203697205,
+      "learning_rate": 1.0360360360360361e-06,
+      "loss": 1.6766,
+      "step": 200
+    },
+    {
+      "epoch": 0.9054054054054054,
+      "grad_norm": 0.3549056649208069,
+      "learning_rate": 9.909909909909911e-07,
+      "loss": 1.644,
+      "step": 201
+    },
+    {
+      "epoch": 0.9099099099099099,
+      "grad_norm": 0.3365701735019684,
+      "learning_rate": 9.459459459459461e-07,
+      "loss": 1.6275,
+      "step": 202
+    },
+    {
+      "epoch": 0.9144144144144144,
+      "grad_norm": 0.3276926577091217,
+      "learning_rate": 9.00900900900901e-07,
+      "loss": 1.5943,
+      "step": 203
+    },
+    {
+      "epoch": 0.918918918918919,
+      "grad_norm": 0.47995641827583313,
+      "learning_rate": 8.55855855855856e-07,
+      "loss": 1.6125,
+      "step": 204
+    },
+    {
+      "epoch": 0.9234234234234234,
+      "grad_norm": 0.3210660517215729,
+      "learning_rate": 8.108108108108109e-07,
+      "loss": 1.5901,
+      "step": 205
+    },
+    {
+      "epoch": 0.9279279279279279,
+      "grad_norm": 0.35450634360313416,
+      "learning_rate": 7.657657657657658e-07,
+      "loss": 1.6628,
+      "step": 206
+    },
+    {
+      "epoch": 0.9324324324324325,
+      "grad_norm": 0.33351245522499084,
+      "learning_rate": 7.207207207207208e-07,
+      "loss": 1.5704,
+      "step": 207
+    },
+    {
+      "epoch": 0.9369369369369369,
+      "grad_norm": 0.40133386850357056,
+      "learning_rate": 6.756756756756758e-07,
+      "loss": 1.572,
+      "step": 208
+    },
+    {
+      "epoch": 0.9414414414414415,
+      "grad_norm": 0.35304591059684753,
+      "learning_rate": 6.306306306306306e-07,
+      "loss": 1.6827,
+      "step": 209
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 0.4823031425476074,
+      "learning_rate": 5.855855855855856e-07,
+      "loss": 1.6265,
+      "step": 210
+    },
+    {
+      "epoch": 0.9504504504504504,
+      "grad_norm": 0.3416145443916321,
+      "learning_rate": 5.405405405405406e-07,
+      "loss": 1.5836,
+      "step": 211
+    },
+    {
+      "epoch": 0.954954954954955,
+      "grad_norm": 0.34280046820640564,
+      "learning_rate": 4.954954954954956e-07,
+      "loss": 1.61,
+      "step": 212
+    },
+    {
+      "epoch": 0.9594594594594594,
+      "grad_norm": 0.3362351357936859,
+      "learning_rate": 4.504504504504505e-07,
+      "loss": 1.6703,
+      "step": 213
+    },
+    {
+      "epoch": 0.963963963963964,
+      "grad_norm": 0.32132312655448914,
+      "learning_rate": 4.0540540540540546e-07,
+      "loss": 1.6469,
+      "step": 214
+    },
+    {
+      "epoch": 0.9684684684684685,
+      "grad_norm": 0.3417748212814331,
+      "learning_rate": 3.603603603603604e-07,
+      "loss": 1.6052,
+      "step": 215
+    },
+    {
+      "epoch": 0.972972972972973,
+      "grad_norm": 0.3503134548664093,
+      "learning_rate": 3.153153153153153e-07,
+      "loss": 1.6253,
+      "step": 216
+    },
+    {
+      "epoch": 0.9774774774774775,
+      "grad_norm": 0.332475870847702,
+      "learning_rate": 2.702702702702703e-07,
+      "loss": 1.6158,
+      "step": 217
+    },
+    {
+      "epoch": 0.9819819819819819,
+      "grad_norm": 0.3545438349246979,
+      "learning_rate": 2.2522522522522524e-07,
+      "loss": 1.67,
+      "step": 218
+    },
+    {
+      "epoch": 0.9864864864864865,
+      "grad_norm": 0.3189946115016937,
+      "learning_rate": 1.801801801801802e-07,
+      "loss": 1.5921,
+      "step": 219
+    },
+    {
+      "epoch": 0.990990990990991,
+      "grad_norm": 0.35738781094551086,
+      "learning_rate": 1.3513513513513515e-07,
+      "loss": 1.6595,
+      "step": 220
+    },
+    {
+      "epoch": 0.9954954954954955,
+      "grad_norm": 0.41471225023269653,
+      "learning_rate": 9.00900900900901e-08,
+      "loss": 1.6064,
+      "step": 221
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.33184003829956055,
+      "learning_rate": 4.504504504504505e-08,
+      "loss": 1.6121,
+      "step": 222
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 222,
+  "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": 1.5005440937033728e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}