Upload folder using huggingface_hub

.gitattributes

@@ -37,3 +37,13 @@ checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-11000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-12000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-13000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-13532/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-6000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-7000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-8000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-9000/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-10000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Qwen3-8B-Base
+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 0.15.2

checkpoint-10000/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen3-8B-Base",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-10000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b5c1f3d0cf60e09fd92334de54cec7a7a9ec07651c8d37851b37be377890d9
+size 2838563408

checkpoint-10000/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
+}

checkpoint-10000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7d1f2636357fd4a71075f6edd5f93f7126589a2ac5205871dfca1b8058a947d
+size 2706136909

checkpoint-10000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de69a2834426ff9ef8199d077e00892579278af31d8969d77f98235b5cfc010a
+size 14645

checkpoint-10000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c390ecfb1f5916743f3b8376c9946a83a444cdd8284b5d5902ca5ef5c9250027
+size 1465

checkpoint-10000/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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-10000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-10000/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 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.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').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        {{- 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    {%- 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": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-10000/trainer_state.json

@@ -0,0 +1,2834 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.47778067698219,
+  "eval_steps": 500,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0036945613747462877,
+      "grad_norm": 2.2292165756225586,
+      "learning_rate": 5.911330049261084e-06,
+      "loss": 0.9395,
+      "step": 25
+    },
+    {
+      "epoch": 0.007389122749492575,
+      "grad_norm": 0.8381065130233765,
+      "learning_rate": 1.206896551724138e-05,
+      "loss": 0.89,
+      "step": 50
+    },
+    {
+      "epoch": 0.011083684124238862,
+      "grad_norm": 0.9238471984863281,
+      "learning_rate": 1.8226600985221676e-05,
+      "loss": 0.8384,
+      "step": 75
+    },
+    {
+      "epoch": 0.01477824549898515,
+      "grad_norm": 0.6837311387062073,
+      "learning_rate": 2.438423645320197e-05,
+      "loss": 0.784,
+      "step": 100
+    },
+    {
+      "epoch": 0.01847280687373144,
+      "grad_norm": 0.7093706727027893,
+      "learning_rate": 3.0541871921182266e-05,
+      "loss": 0.7675,
+      "step": 125
+    },
+    {
+      "epoch": 0.022167368248477724,
+      "grad_norm": 0.6208077073097229,
+      "learning_rate": 3.669950738916256e-05,
+      "loss": 0.7466,
+      "step": 150
+    },
+    {
+      "epoch": 0.025861929623224013,
+      "grad_norm": 0.8929094076156616,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 0.7386,
+      "step": 175
+    },
+    {
+      "epoch": 0.0295564909979703,
+      "grad_norm": 0.7828120589256287,
+      "learning_rate": 4.901477832512316e-05,
+      "loss": 0.7173,
+      "step": 200
+    },
+    {
+      "epoch": 0.03325105237271659,
+      "grad_norm": 0.7134449481964111,
+      "learning_rate": 5.517241379310345e-05,
+      "loss": 0.7108,
+      "step": 225
+    },
+    {
+      "epoch": 0.03694561374746288,
+      "grad_norm": 0.7464851140975952,
+      "learning_rate": 6.133004926108375e-05,
+      "loss": 0.7332,
+      "step": 250
+    },
+    {
+      "epoch": 0.04064017512220916,
+      "grad_norm": 0.677793025970459,
+      "learning_rate": 6.748768472906404e-05,
+      "loss": 0.7194,
+      "step": 275
+    },
+    {
+      "epoch": 0.04433473649695545,
+      "grad_norm": 0.7936354875564575,
+      "learning_rate": 7.364532019704434e-05,
+      "loss": 0.7253,
+      "step": 300
+    },
+    {
+      "epoch": 0.04802929787170174,
+      "grad_norm": 0.6711100935935974,
+      "learning_rate": 7.980295566502463e-05,
+      "loss": 0.7018,
+      "step": 325
+    },
+    {
+      "epoch": 0.051723859246448026,
+      "grad_norm": 0.5816489458084106,
+      "learning_rate": 8.596059113300493e-05,
+      "loss": 0.7298,
+      "step": 350
+    },
+    {
+      "epoch": 0.055418420621194314,
+      "grad_norm": 0.6680681705474854,
+      "learning_rate": 9.211822660098522e-05,
+      "loss": 0.7149,
+      "step": 375
+    },
+    {
+      "epoch": 0.0591129819959406,
+      "grad_norm": 0.5643934607505798,
+      "learning_rate": 9.827586206896552e-05,
+      "loss": 0.763,
+      "step": 400
+    },
+    {
+      "epoch": 0.06280754337068689,
+      "grad_norm": 0.5739309191703796,
+      "learning_rate": 9.986286759104069e-05,
+      "loss": 0.7345,
+      "step": 425
+    },
+    {
+      "epoch": 0.06650210474543318,
+      "grad_norm": 0.5929909944534302,
+      "learning_rate": 9.967240591193052e-05,
+      "loss": 0.7364,
+      "step": 450
+    },
+    {
+      "epoch": 0.07019666612017947,
+      "grad_norm": 0.609235405921936,
+      "learning_rate": 9.948194423282036e-05,
+      "loss": 0.7294,
+      "step": 475
+    },
+    {
+      "epoch": 0.07389122749492576,
+      "grad_norm": 0.4643324613571167,
+      "learning_rate": 9.92914825537102e-05,
+      "loss": 0.7344,
+      "step": 500
+    },
+    {
+      "epoch": 0.07758578886967203,
+      "grad_norm": 0.5267598032951355,
+      "learning_rate": 9.910102087460003e-05,
+      "loss": 0.7249,
+      "step": 525
+    },
+    {
+      "epoch": 0.08128035024441832,
+      "grad_norm": 0.47951069474220276,
+      "learning_rate": 9.891055919548987e-05,
+      "loss": 0.7256,
+      "step": 550
+    },
+    {
+      "epoch": 0.08497491161916461,
+      "grad_norm": 0.4505012333393097,
+      "learning_rate": 9.87200975163797e-05,
+      "loss": 0.7359,
+      "step": 575
+    },
+    {
+      "epoch": 0.0886694729939109,
+      "grad_norm": 0.5320091247558594,
+      "learning_rate": 9.852963583726955e-05,
+      "loss": 0.6856,
+      "step": 600
+    },
+    {
+      "epoch": 0.09236403436865719,
+      "grad_norm": 0.5583036541938782,
+      "learning_rate": 9.833917415815939e-05,
+      "loss": 0.7235,
+      "step": 625
+    },
+    {
+      "epoch": 0.09605859574340347,
+      "grad_norm": 0.5139252543449402,
+      "learning_rate": 9.814871247904922e-05,
+      "loss": 0.7272,
+      "step": 650
+    },
+    {
+      "epoch": 0.09975315711814976,
+      "grad_norm": 0.4989326000213623,
+      "learning_rate": 9.795825079993906e-05,
+      "loss": 0.6952,
+      "step": 675
+    },
+    {
+      "epoch": 0.10344771849289605,
+      "grad_norm": 0.47355732321739197,
+      "learning_rate": 9.776778912082889e-05,
+      "loss": 0.7266,
+      "step": 700
+    },
+    {
+      "epoch": 0.10714227986764234,
+      "grad_norm": 0.3588508367538452,
+      "learning_rate": 9.757732744171874e-05,
+      "loss": 0.7406,
+      "step": 725
+    },
+    {
+      "epoch": 0.11083684124238863,
+      "grad_norm": 0.4120556712150574,
+      "learning_rate": 9.738686576260857e-05,
+      "loss": 0.7443,
+      "step": 750
+    },
+    {
+      "epoch": 0.11453140261713492,
+      "grad_norm": 0.5160555839538574,
+      "learning_rate": 9.71964040834984e-05,
+      "loss": 0.7134,
+      "step": 775
+    },
+    {
+      "epoch": 0.1182259639918812,
+      "grad_norm": 0.5423145890235901,
+      "learning_rate": 9.700594240438823e-05,
+      "loss": 0.7289,
+      "step": 800
+    },
+    {
+      "epoch": 0.1219205253666275,
+      "grad_norm": 0.5352346301078796,
+      "learning_rate": 9.681548072527808e-05,
+      "loss": 0.7144,
+      "step": 825
+    },
+    {
+      "epoch": 0.12561508674137378,
+      "grad_norm": 0.47908860445022583,
+      "learning_rate": 9.662501904616791e-05,
+      "loss": 0.7175,
+      "step": 850
+    },
+    {
+      "epoch": 0.12930964811612006,
+      "grad_norm": 0.47986069321632385,
+      "learning_rate": 9.643455736705776e-05,
+      "loss": 0.6983,
+      "step": 875
+    },
+    {
+      "epoch": 0.13300420949086636,
+      "grad_norm": 0.6903620958328247,
+      "learning_rate": 9.624409568794759e-05,
+      "loss": 0.7086,
+      "step": 900
+    },
+    {
+      "epoch": 0.13669877086561263,
+      "grad_norm": 0.44413208961486816,
+      "learning_rate": 9.605363400883742e-05,
+      "loss": 0.7306,
+      "step": 925
+    },
+    {
+      "epoch": 0.14039333224035894,
+      "grad_norm": 0.4634678065776825,
+      "learning_rate": 9.586317232972727e-05,
+      "loss": 0.7061,
+      "step": 950
+    },
+    {
+      "epoch": 0.1440878936151052,
+      "grad_norm": 0.5110129714012146,
+      "learning_rate": 9.56727106506171e-05,
+      "loss": 0.7406,
+      "step": 975
+    },
+    {
+      "epoch": 0.1477824549898515,
+      "grad_norm": 0.5460866093635559,
+      "learning_rate": 9.548224897150694e-05,
+      "loss": 0.721,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1514770163645978,
+      "grad_norm": 0.5179885029792786,
+      "learning_rate": 9.529178729239677e-05,
+      "loss": 0.7068,
+      "step": 1025
+    },
+    {
+      "epoch": 0.15517157773934406,
+      "grad_norm": 0.40280836820602417,
+      "learning_rate": 9.51013256132866e-05,
+      "loss": 0.7009,
+      "step": 1050
+    },
+    {
+      "epoch": 0.15886613911409037,
+      "grad_norm": 1.2706756591796875,
+      "learning_rate": 9.491086393417645e-05,
+      "loss": 0.7125,
+      "step": 1075
+    },
+    {
+      "epoch": 0.16256070048883664,
+      "grad_norm": 0.4963163435459137,
+      "learning_rate": 9.47204022550663e-05,
+      "loss": 0.7149,
+      "step": 1100
+    },
+    {
+      "epoch": 0.16625526186358294,
+      "grad_norm": 0.5147728323936462,
+      "learning_rate": 9.452994057595613e-05,
+      "loss": 0.7245,
+      "step": 1125
+    },
+    {
+      "epoch": 0.16994982323832922,
+      "grad_norm": 0.5933899879455566,
+      "learning_rate": 9.433947889684596e-05,
+      "loss": 0.7261,
+      "step": 1150
+    },
+    {
+      "epoch": 0.17364438461307552,
+      "grad_norm": 0.4750466048717499,
+      "learning_rate": 9.414901721773579e-05,
+      "loss": 0.7206,
+      "step": 1175
+    },
+    {
+      "epoch": 0.1773389459878218,
+      "grad_norm": 0.46546968817710876,
+      "learning_rate": 9.395855553862564e-05,
+      "loss": 0.7121,
+      "step": 1200
+    },
+    {
+      "epoch": 0.1810335073625681,
+      "grad_norm": 0.6512172818183899,
+      "learning_rate": 9.376809385951547e-05,
+      "loss": 0.7212,
+      "step": 1225
+    },
+    {
+      "epoch": 0.18472806873731437,
+      "grad_norm": 0.34932607412338257,
+      "learning_rate": 9.35776321804053e-05,
+      "loss": 0.704,
+      "step": 1250
+    },
+    {
+      "epoch": 0.18842263011206067,
+      "grad_norm": 0.4648846983909607,
+      "learning_rate": 9.338717050129514e-05,
+      "loss": 0.7419,
+      "step": 1275
+    },
+    {
+      "epoch": 0.19211719148680695,
+      "grad_norm": 0.4566064774990082,
+      "learning_rate": 9.319670882218498e-05,
+      "loss": 0.7318,
+      "step": 1300
+    },
+    {
+      "epoch": 0.19581175286155325,
+      "grad_norm": 0.5357668399810791,
+      "learning_rate": 9.300624714307481e-05,
+      "loss": 0.6973,
+      "step": 1325
+    },
+    {
+      "epoch": 0.19950631423629953,
+      "grad_norm": 0.4423241913318634,
+      "learning_rate": 9.281578546396466e-05,
+      "loss": 0.7298,
+      "step": 1350
+    },
+    {
+      "epoch": 0.20320087561104583,
+      "grad_norm": 0.4530033767223358,
+      "learning_rate": 9.26253237848545e-05,
+      "loss": 0.7161,
+      "step": 1375
+    },
+    {
+      "epoch": 0.2068954369857921,
+      "grad_norm": 0.4678841233253479,
+      "learning_rate": 9.243486210574433e-05,
+      "loss": 0.6972,
+      "step": 1400
+    },
+    {
+      "epoch": 0.21058999836053838,
+      "grad_norm": 0.6039907336235046,
+      "learning_rate": 9.224440042663417e-05,
+      "loss": 0.7165,
+      "step": 1425
+    },
+    {
+      "epoch": 0.21428455973528468,
+      "grad_norm": 0.4463271498680115,
+      "learning_rate": 9.2053938747524e-05,
+      "loss": 0.6863,
+      "step": 1450
+    },
+    {
+      "epoch": 0.21797912111003095,
+      "grad_norm": 0.5739301443099976,
+      "learning_rate": 9.186347706841384e-05,
+      "loss": 0.6907,
+      "step": 1475
+    },
+    {
+      "epoch": 0.22167368248477726,
+      "grad_norm": 0.4577805697917938,
+      "learning_rate": 9.167301538930367e-05,
+      "loss": 0.7114,
+      "step": 1500
+    },
+    {
+      "epoch": 0.22536824385952353,
+      "grad_norm": 0.4522150158882141,
+      "learning_rate": 9.14825537101935e-05,
+      "loss": 0.6877,
+      "step": 1525
+    },
+    {
+      "epoch": 0.22906280523426983,
+      "grad_norm": 0.49612903594970703,
+      "learning_rate": 9.129209203108335e-05,
+      "loss": 0.7112,
+      "step": 1550
+    },
+    {
+      "epoch": 0.2327573666090161,
+      "grad_norm": 0.4710284471511841,
+      "learning_rate": 9.11016303519732e-05,
+      "loss": 0.7062,
+      "step": 1575
+    },
+    {
+      "epoch": 0.2364519279837624,
+      "grad_norm": 0.5009223818778992,
+      "learning_rate": 9.091116867286303e-05,
+      "loss": 0.7275,
+      "step": 1600
+    },
+    {
+      "epoch": 0.24014648935850869,
+      "grad_norm": 0.5547946691513062,
+      "learning_rate": 9.072070699375286e-05,
+      "loss": 0.6993,
+      "step": 1625
+    },
+    {
+      "epoch": 0.243841050733255,
+      "grad_norm": 0.4580361843109131,
+      "learning_rate": 9.05302453146427e-05,
+      "loss": 0.7106,
+      "step": 1650
+    },
+    {
+      "epoch": 0.24753561210800126,
+      "grad_norm": 0.4767173230648041,
+      "learning_rate": 9.033978363553254e-05,
+      "loss": 0.7103,
+      "step": 1675
+    },
+    {
+      "epoch": 0.25123017348274757,
+      "grad_norm": 0.502202570438385,
+      "learning_rate": 9.014932195642237e-05,
+      "loss": 0.6921,
+      "step": 1700
+    },
+    {
+      "epoch": 0.25492473485749384,
+      "grad_norm": 0.5283953547477722,
+      "learning_rate": 8.99588602773122e-05,
+      "loss": 0.7077,
+      "step": 1725
+    },
+    {
+      "epoch": 0.2586192962322401,
+      "grad_norm": 0.4994209408760071,
+      "learning_rate": 8.976839859820204e-05,
+      "loss": 0.7,
+      "step": 1750
+    },
+    {
+      "epoch": 0.2623138576069864,
+      "grad_norm": 0.48279210925102234,
+      "learning_rate": 8.957793691909188e-05,
+      "loss": 0.7114,
+      "step": 1775
+    },
+    {
+      "epoch": 0.2660084189817327,
+      "grad_norm": 0.6055914759635925,
+      "learning_rate": 8.938747523998172e-05,
+      "loss": 0.7081,
+      "step": 1800
+    },
+    {
+      "epoch": 0.269702980356479,
+      "grad_norm": 0.489519327878952,
+      "learning_rate": 8.919701356087156e-05,
+      "loss": 0.6946,
+      "step": 1825
+    },
+    {
+      "epoch": 0.27339754173122527,
+      "grad_norm": 0.5379961133003235,
+      "learning_rate": 8.90065518817614e-05,
+      "loss": 0.6996,
+      "step": 1850
+    },
+    {
+      "epoch": 0.27709210310597154,
+      "grad_norm": 0.47824332118034363,
+      "learning_rate": 8.881609020265123e-05,
+      "loss": 0.6881,
+      "step": 1875
+    },
+    {
+      "epoch": 0.2807866644807179,
+      "grad_norm": 1551.0594482421875,
+      "learning_rate": 8.862562852354107e-05,
+      "loss": 0.6998,
+      "step": 1900
+    },
+    {
+      "epoch": 0.28448122585546415,
+      "grad_norm": 0.4107681214809418,
+      "learning_rate": 8.84351668444309e-05,
+      "loss": 0.7088,
+      "step": 1925
+    },
+    {
+      "epoch": 0.2881757872302104,
+      "grad_norm": 0.4558309316635132,
+      "learning_rate": 8.824470516532074e-05,
+      "loss": 0.712,
+      "step": 1950
+    },
+    {
+      "epoch": 0.2918703486049567,
+      "grad_norm": 0.539107620716095,
+      "learning_rate": 8.805424348621057e-05,
+      "loss": 0.7159,
+      "step": 1975
+    },
+    {
+      "epoch": 0.295564909979703,
+      "grad_norm": 0.5768142938613892,
+      "learning_rate": 8.786378180710042e-05,
+      "loss": 0.7072,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2992594713544493,
+      "grad_norm": 0.5575465559959412,
+      "learning_rate": 8.767332012799025e-05,
+      "loss": 0.7118,
+      "step": 2025
+    },
+    {
+      "epoch": 0.3029540327291956,
+      "grad_norm": 0.5190144181251526,
+      "learning_rate": 8.748285844888008e-05,
+      "loss": 0.7099,
+      "step": 2050
+    },
+    {
+      "epoch": 0.30664859410394185,
+      "grad_norm": 0.4934520125389099,
+      "learning_rate": 8.729239676976993e-05,
+      "loss": 0.692,
+      "step": 2075
+    },
+    {
+      "epoch": 0.3103431554786881,
+      "grad_norm": 0.42613571882247925,
+      "learning_rate": 8.710193509065976e-05,
+      "loss": 0.7277,
+      "step": 2100
+    },
+    {
+      "epoch": 0.31403771685343446,
+      "grad_norm": 0.5124602317810059,
+      "learning_rate": 8.691147341154961e-05,
+      "loss": 0.6801,
+      "step": 2125
+    },
+    {
+      "epoch": 0.31773227822818073,
+      "grad_norm": 0.5284898281097412,
+      "learning_rate": 8.672101173243944e-05,
+      "loss": 0.7103,
+      "step": 2150
+    },
+    {
+      "epoch": 0.321426839602927,
+      "grad_norm": 0.43099457025527954,
+      "learning_rate": 8.653055005332927e-05,
+      "loss": 0.7023,
+      "step": 2175
+    },
+    {
+      "epoch": 0.3251214009776733,
+      "grad_norm": 0.5190865993499756,
+      "learning_rate": 8.63400883742191e-05,
+      "loss": 0.7144,
+      "step": 2200
+    },
+    {
+      "epoch": 0.3288159623524196,
+      "grad_norm": 0.4722968637943268,
+      "learning_rate": 8.614962669510895e-05,
+      "loss": 0.7351,
+      "step": 2225
+    },
+    {
+      "epoch": 0.3325105237271659,
+      "grad_norm": 0.6091466546058655,
+      "learning_rate": 8.595916501599878e-05,
+      "loss": 0.7062,
+      "step": 2250
+    },
+    {
+      "epoch": 0.33620508510191216,
+      "grad_norm": 0.6135897040367126,
+      "learning_rate": 8.576870333688862e-05,
+      "loss": 0.7117,
+      "step": 2275
+    },
+    {
+      "epoch": 0.33989964647665843,
+      "grad_norm": 0.5224157571792603,
+      "learning_rate": 8.557824165777846e-05,
+      "loss": 0.7068,
+      "step": 2300
+    },
+    {
+      "epoch": 0.34359420785140476,
+      "grad_norm": 0.4863536059856415,
+      "learning_rate": 8.53877799786683e-05,
+      "loss": 0.6952,
+      "step": 2325
+    },
+    {
+      "epoch": 0.34728876922615104,
+      "grad_norm": 0.4728885889053345,
+      "learning_rate": 8.519731829955814e-05,
+      "loss": 0.7289,
+      "step": 2350
+    },
+    {
+      "epoch": 0.3509833306008973,
+      "grad_norm": 0.5152695775032043,
+      "learning_rate": 8.500685662044798e-05,
+      "loss": 0.6986,
+      "step": 2375
+    },
+    {
+      "epoch": 0.3546778919756436,
+      "grad_norm": 0.4407690465450287,
+      "learning_rate": 8.481639494133781e-05,
+      "loss": 0.6983,
+      "step": 2400
+    },
+    {
+      "epoch": 0.3583724533503899,
+      "grad_norm": 0.4756406545639038,
+      "learning_rate": 8.462593326222764e-05,
+      "loss": 0.6626,
+      "step": 2425
+    },
+    {
+      "epoch": 0.3620670147251362,
+      "grad_norm": 0.48595255613327026,
+      "learning_rate": 8.443547158311747e-05,
+      "loss": 0.6892,
+      "step": 2450
+    },
+    {
+      "epoch": 0.36576157609988247,
+      "grad_norm": 0.47830772399902344,
+      "learning_rate": 8.424500990400732e-05,
+      "loss": 0.7162,
+      "step": 2475
+    },
+    {
+      "epoch": 0.36945613747462874,
+      "grad_norm": 0.43090149760246277,
+      "learning_rate": 8.405454822489715e-05,
+      "loss": 0.6913,
+      "step": 2500
+    },
+    {
+      "epoch": 0.373150698849375,
+      "grad_norm": 0.5338718295097351,
+      "learning_rate": 8.386408654578698e-05,
+      "loss": 0.7159,
+      "step": 2525
+    },
+    {
+      "epoch": 0.37684526022412135,
+      "grad_norm": 0.4907350242137909,
+      "learning_rate": 8.367362486667683e-05,
+      "loss": 0.7022,
+      "step": 2550
+    },
+    {
+      "epoch": 0.3805398215988676,
+      "grad_norm": 0.44093430042266846,
+      "learning_rate": 8.348316318756668e-05,
+      "loss": 0.7124,
+      "step": 2575
+    },
+    {
+      "epoch": 0.3842343829736139,
+      "grad_norm": 0.5388796925544739,
+      "learning_rate": 8.329270150845651e-05,
+      "loss": 0.7304,
+      "step": 2600
+    },
+    {
+      "epoch": 0.38792894434836017,
+      "grad_norm": 0.4456349313259125,
+      "learning_rate": 8.310223982934634e-05,
+      "loss": 0.6964,
+      "step": 2625
+    },
+    {
+      "epoch": 0.3916235057231065,
+      "grad_norm": 0.4602237343788147,
+      "learning_rate": 8.291177815023617e-05,
+      "loss": 0.6707,
+      "step": 2650
+    },
+    {
+      "epoch": 0.3953180670978528,
+      "grad_norm": 0.4726378917694092,
+      "learning_rate": 8.272131647112601e-05,
+      "loss": 0.694,
+      "step": 2675
+    },
+    {
+      "epoch": 0.39901262847259905,
+      "grad_norm": 0.500451922416687,
+      "learning_rate": 8.253085479201585e-05,
+      "loss": 0.6812,
+      "step": 2700
+    },
+    {
+      "epoch": 0.4027071898473453,
+      "grad_norm": 0.4073813259601593,
+      "learning_rate": 8.234039311290569e-05,
+      "loss": 0.7028,
+      "step": 2725
+    },
+    {
+      "epoch": 0.40640175122209166,
+      "grad_norm": 0.43644702434539795,
+      "learning_rate": 8.214993143379552e-05,
+      "loss": 0.6936,
+      "step": 2750
+    },
+    {
+      "epoch": 0.41009631259683793,
+      "grad_norm": 0.5256789922714233,
+      "learning_rate": 8.195946975468535e-05,
+      "loss": 0.7035,
+      "step": 2775
+    },
+    {
+      "epoch": 0.4137908739715842,
+      "grad_norm": 0.48385316133499146,
+      "learning_rate": 8.17690080755752e-05,
+      "loss": 0.6736,
+      "step": 2800
+    },
+    {
+      "epoch": 0.4174854353463305,
+      "grad_norm": 0.49825233221054077,
+      "learning_rate": 8.157854639646504e-05,
+      "loss": 0.7019,
+      "step": 2825
+    },
+    {
+      "epoch": 0.42117999672107675,
+      "grad_norm": 0.5086994171142578,
+      "learning_rate": 8.138808471735488e-05,
+      "loss": 0.6918,
+      "step": 2850
+    },
+    {
+      "epoch": 0.4248745580958231,
+      "grad_norm": 0.5430259108543396,
+      "learning_rate": 8.119762303824471e-05,
+      "loss": 0.7175,
+      "step": 2875
+    },
+    {
+      "epoch": 0.42856911947056936,
+      "grad_norm": 0.5889118313789368,
+      "learning_rate": 8.100716135913454e-05,
+      "loss": 0.6967,
+      "step": 2900
+    },
+    {
+      "epoch": 0.43226368084531563,
+      "grad_norm": 0.5345672369003296,
+      "learning_rate": 8.081669968002439e-05,
+      "loss": 0.6926,
+      "step": 2925
+    },
+    {
+      "epoch": 0.4359582422200619,
+      "grad_norm": 0.511101245880127,
+      "learning_rate": 8.062623800091422e-05,
+      "loss": 0.7248,
+      "step": 2950
+    },
+    {
+      "epoch": 0.43965280359480824,
+      "grad_norm": 0.511239767074585,
+      "learning_rate": 8.043577632180405e-05,
+      "loss": 0.7319,
+      "step": 2975
+    },
+    {
+      "epoch": 0.4433473649695545,
+      "grad_norm": 0.5121573805809021,
+      "learning_rate": 8.024531464269389e-05,
+      "loss": 0.7023,
+      "step": 3000
+    },
+    {
+      "epoch": 0.4470419263443008,
+      "grad_norm": 0.5658753514289856,
+      "learning_rate": 8.005485296358373e-05,
+      "loss": 0.6934,
+      "step": 3025
+    },
+    {
+      "epoch": 0.45073648771904706,
+      "grad_norm": 0.5475583672523499,
+      "learning_rate": 7.986439128447358e-05,
+      "loss": 0.6701,
+      "step": 3050
+    },
+    {
+      "epoch": 0.4544310490937934,
+      "grad_norm": 0.6107661724090576,
+      "learning_rate": 7.967392960536341e-05,
+      "loss": 0.7056,
+      "step": 3075
+    },
+    {
+      "epoch": 0.45812561046853967,
+      "grad_norm": 0.48424115777015686,
+      "learning_rate": 7.948346792625324e-05,
+      "loss": 0.7179,
+      "step": 3100
+    },
+    {
+      "epoch": 0.46182017184328594,
+      "grad_norm": 0.6184881329536438,
+      "learning_rate": 7.929300624714308e-05,
+      "loss": 0.7141,
+      "step": 3125
+    },
+    {
+      "epoch": 0.4655147332180322,
+      "grad_norm": 0.49919527769088745,
+      "learning_rate": 7.910254456803291e-05,
+      "loss": 0.7027,
+      "step": 3150
+    },
+    {
+      "epoch": 0.4692092945927785,
+      "grad_norm": 0.5012905597686768,
+      "learning_rate": 7.891208288892276e-05,
+      "loss": 0.6852,
+      "step": 3175
+    },
+    {
+      "epoch": 0.4729038559675248,
+      "grad_norm": 0.5033735036849976,
+      "learning_rate": 7.872162120981259e-05,
+      "loss": 0.7199,
+      "step": 3200
+    },
+    {
+      "epoch": 0.4765984173422711,
+      "grad_norm": 0.5746079087257385,
+      "learning_rate": 7.853115953070242e-05,
+      "loss": 0.715,
+      "step": 3225
+    },
+    {
+      "epoch": 0.48029297871701737,
+      "grad_norm": 0.5436145663261414,
+      "learning_rate": 7.834069785159225e-05,
+      "loss": 0.697,
+      "step": 3250
+    },
+    {
+      "epoch": 0.48398754009176365,
+      "grad_norm": 0.5836604833602905,
+      "learning_rate": 7.81502361724821e-05,
+      "loss": 0.7129,
+      "step": 3275
+    },
+    {
+      "epoch": 0.48768210146651,
+      "grad_norm": 0.5618935227394104,
+      "learning_rate": 7.795977449337195e-05,
+      "loss": 0.6993,
+      "step": 3300
+    },
+    {
+      "epoch": 0.49137666284125625,
+      "grad_norm": 0.6251245737075806,
+      "learning_rate": 7.776931281426178e-05,
+      "loss": 0.7132,
+      "step": 3325
+    },
+    {
+      "epoch": 0.4950712242160025,
+      "grad_norm": 0.5123202800750732,
+      "learning_rate": 7.757885113515161e-05,
+      "loss": 0.7218,
+      "step": 3350
+    },
+    {
+      "epoch": 0.4987657855907488,
+      "grad_norm": 0.5818086862564087,
+      "learning_rate": 7.738838945604144e-05,
+      "loss": 0.7154,
+      "step": 3375
+    },
+    {
+      "epoch": 0.5024603469654951,
+      "grad_norm": 0.5861947536468506,
+      "learning_rate": 7.719792777693129e-05,
+      "loss": 0.7013,
+      "step": 3400
+    },
+    {
+      "epoch": 0.5061549083402413,
+      "grad_norm": 0.4849907457828522,
+      "learning_rate": 7.700746609782112e-05,
+      "loss": 0.6902,
+      "step": 3425
+    },
+    {
+      "epoch": 0.5098494697149877,
+      "grad_norm": 0.5476916432380676,
+      "learning_rate": 7.681700441871096e-05,
+      "loss": 0.7147,
+      "step": 3450
+    },
+    {
+      "epoch": 0.513544031089734,
+      "grad_norm": 0.5822548866271973,
+      "learning_rate": 7.662654273960079e-05,
+      "loss": 0.7431,
+      "step": 3475
+    },
+    {
+      "epoch": 0.5172385924644802,
+      "grad_norm": 0.44818004965782166,
+      "learning_rate": 7.643608106049063e-05,
+      "loss": 0.718,
+      "step": 3500
+    },
+    {
+      "epoch": 0.5209331538392266,
+      "grad_norm": 0.544068455696106,
+      "learning_rate": 7.624561938138047e-05,
+      "loss": 0.7201,
+      "step": 3525
+    },
+    {
+      "epoch": 0.5246277152139728,
+      "grad_norm": 0.5535098910331726,
+      "learning_rate": 7.605515770227031e-05,
+      "loss": 0.6998,
+      "step": 3550
+    },
+    {
+      "epoch": 0.5283222765887191,
+      "grad_norm": 0.5754445195198059,
+      "learning_rate": 7.586469602316015e-05,
+      "loss": 0.6918,
+      "step": 3575
+    },
+    {
+      "epoch": 0.5320168379634654,
+      "grad_norm": 0.5976133942604065,
+      "learning_rate": 7.567423434404998e-05,
+      "loss": 0.693,
+      "step": 3600
+    },
+    {
+      "epoch": 0.5357113993382117,
+      "grad_norm": 0.4844263195991516,
+      "learning_rate": 7.548377266493982e-05,
+      "loss": 0.68,
+      "step": 3625
+    },
+    {
+      "epoch": 0.539405960712958,
+      "grad_norm": 0.5436462163925171,
+      "learning_rate": 7.529331098582966e-05,
+      "loss": 0.7075,
+      "step": 3650
+    },
+    {
+      "epoch": 0.5431005220877043,
+      "grad_norm": 0.6490929126739502,
+      "learning_rate": 7.510284930671949e-05,
+      "loss": 0.6956,
+      "step": 3675
+    },
+    {
+      "epoch": 0.5467950834624505,
+      "grad_norm": 0.47479814291000366,
+      "learning_rate": 7.491238762760932e-05,
+      "loss": 0.7026,
+      "step": 3700
+    },
+    {
+      "epoch": 0.5504896448371969,
+      "grad_norm": 0.590874969959259,
+      "learning_rate": 7.472192594849915e-05,
+      "loss": 0.7117,
+      "step": 3725
+    },
+    {
+      "epoch": 0.5541842062119431,
+      "grad_norm": 0.46487829089164734,
+      "learning_rate": 7.4531464269389e-05,
+      "loss": 0.6919,
+      "step": 3750
+    },
+    {
+      "epoch": 0.5578787675866894,
+      "grad_norm": 0.6609780192375183,
+      "learning_rate": 7.434100259027885e-05,
+      "loss": 0.7089,
+      "step": 3775
+    },
+    {
+      "epoch": 0.5615733289614357,
+      "grad_norm": 0.6165657639503479,
+      "learning_rate": 7.415054091116868e-05,
+      "loss": 0.7444,
+      "step": 3800
+    },
+    {
+      "epoch": 0.565267890336182,
+      "grad_norm": 0.5194655656814575,
+      "learning_rate": 7.396007923205851e-05,
+      "loss": 0.7114,
+      "step": 3825
+    },
+    {
+      "epoch": 0.5689624517109283,
+      "grad_norm": 0.4813441336154938,
+      "learning_rate": 7.376961755294836e-05,
+      "loss": 0.6953,
+      "step": 3850
+    },
+    {
+      "epoch": 0.5726570130856745,
+      "grad_norm": 0.7607313990592957,
+      "learning_rate": 7.357915587383819e-05,
+      "loss": 0.7058,
+      "step": 3875
+    },
+    {
+      "epoch": 0.5763515744604208,
+      "grad_norm": 0.48498719930648804,
+      "learning_rate": 7.338869419472802e-05,
+      "loss": 0.6866,
+      "step": 3900
+    },
+    {
+      "epoch": 0.5800461358351672,
+      "grad_norm": 0.5969393253326416,
+      "learning_rate": 7.319823251561786e-05,
+      "loss": 0.6951,
+      "step": 3925
+    },
+    {
+      "epoch": 0.5837406972099134,
+      "grad_norm": 0.6178887486457825,
+      "learning_rate": 7.300777083650769e-05,
+      "loss": 0.7036,
+      "step": 3950
+    },
+    {
+      "epoch": 0.5874352585846597,
+      "grad_norm": 0.5318612456321716,
+      "learning_rate": 7.281730915739754e-05,
+      "loss": 0.6856,
+      "step": 3975
+    },
+    {
+      "epoch": 0.591129819959406,
+      "grad_norm": 0.6101936101913452,
+      "learning_rate": 7.262684747828737e-05,
+      "loss": 0.7103,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5948243813341523,
+      "grad_norm": 0.5605831742286682,
+      "learning_rate": 7.243638579917721e-05,
+      "loss": 0.6684,
+      "step": 4025
+    },
+    {
+      "epoch": 0.5985189427088986,
+      "grad_norm": 0.6576380133628845,
+      "learning_rate": 7.224592412006705e-05,
+      "loss": 0.6955,
+      "step": 4050
+    },
+    {
+      "epoch": 0.6022135040836448,
+      "grad_norm": 0.49083924293518066,
+      "learning_rate": 7.205546244095688e-05,
+      "loss": 0.7089,
+      "step": 4075
+    },
+    {
+      "epoch": 0.6059080654583912,
+      "grad_norm": 0.4783398509025574,
+      "learning_rate": 7.186500076184673e-05,
+      "loss": 0.6766,
+      "step": 4100
+    },
+    {
+      "epoch": 0.6096026268331375,
+      "grad_norm": 0.5773366689682007,
+      "learning_rate": 7.167453908273656e-05,
+      "loss": 0.666,
+      "step": 4125
+    },
+    {
+      "epoch": 0.6132971882078837,
+      "grad_norm": 0.5449897050857544,
+      "learning_rate": 7.148407740362639e-05,
+      "loss": 0.6795,
+      "step": 4150
+    },
+    {
+      "epoch": 0.61699174958263,
+      "grad_norm": 0.519882082939148,
+      "learning_rate": 7.129361572451622e-05,
+      "loss": 0.6892,
+      "step": 4175
+    },
+    {
+      "epoch": 0.6206863109573763,
+      "grad_norm": 0.5653222799301147,
+      "learning_rate": 7.110315404540607e-05,
+      "loss": 0.7029,
+      "step": 4200
+    },
+    {
+      "epoch": 0.6243808723321226,
+      "grad_norm": 0.542448878288269,
+      "learning_rate": 7.09126923662959e-05,
+      "loss": 0.6885,
+      "step": 4225
+    },
+    {
+      "epoch": 0.6280754337068689,
+      "grad_norm": 0.5602554082870483,
+      "learning_rate": 7.072223068718575e-05,
+      "loss": 0.6811,
+      "step": 4250
+    },
+    {
+      "epoch": 0.6317699950816151,
+      "grad_norm": 0.5326575636863708,
+      "learning_rate": 7.053176900807558e-05,
+      "loss": 0.7032,
+      "step": 4275
+    },
+    {
+      "epoch": 0.6354645564563615,
+      "grad_norm": 0.5822186470031738,
+      "learning_rate": 7.034130732896541e-05,
+      "loss": 0.6951,
+      "step": 4300
+    },
+    {
+      "epoch": 0.6391591178311078,
+      "grad_norm": 0.5309107899665833,
+      "learning_rate": 7.015084564985526e-05,
+      "loss": 0.6891,
+      "step": 4325
+    },
+    {
+      "epoch": 0.642853679205854,
+      "grad_norm": 0.6958228349685669,
+      "learning_rate": 6.996038397074509e-05,
+      "loss": 0.6932,
+      "step": 4350
+    },
+    {
+      "epoch": 0.6465482405806003,
+      "grad_norm": 0.4864750802516937,
+      "learning_rate": 6.976992229163493e-05,
+      "loss": 0.6897,
+      "step": 4375
+    },
+    {
+      "epoch": 0.6502428019553466,
+      "grad_norm": 0.5077944993972778,
+      "learning_rate": 6.957946061252476e-05,
+      "loss": 0.7067,
+      "step": 4400
+    },
+    {
+      "epoch": 0.6539373633300929,
+      "grad_norm": 0.5589050054550171,
+      "learning_rate": 6.938899893341459e-05,
+      "loss": 0.6927,
+      "step": 4425
+    },
+    {
+      "epoch": 0.6576319247048392,
+      "grad_norm": 0.6064692735671997,
+      "learning_rate": 6.919853725430444e-05,
+      "loss": 0.7186,
+      "step": 4450
+    },
+    {
+      "epoch": 0.6613264860795854,
+      "grad_norm": 0.5546572208404541,
+      "learning_rate": 6.900807557519427e-05,
+      "loss": 0.6865,
+      "step": 4475
+    },
+    {
+      "epoch": 0.6650210474543318,
+      "grad_norm": 0.6032342314720154,
+      "learning_rate": 6.881761389608412e-05,
+      "loss": 0.6999,
+      "step": 4500
+    },
+    {
+      "epoch": 0.668715608829078,
+      "grad_norm": 0.5067450404167175,
+      "learning_rate": 6.862715221697395e-05,
+      "loss": 0.7068,
+      "step": 4525
+    },
+    {
+      "epoch": 0.6724101702038243,
+      "grad_norm": 0.6697527170181274,
+      "learning_rate": 6.84366905378638e-05,
+      "loss": 0.7075,
+      "step": 4550
+    },
+    {
+      "epoch": 0.6761047315785707,
+      "grad_norm": 0.48360082507133484,
+      "learning_rate": 6.824622885875363e-05,
+      "loss": 0.7076,
+      "step": 4575
+    },
+    {
+      "epoch": 0.6797992929533169,
+      "grad_norm": 0.6387288570404053,
+      "learning_rate": 6.805576717964346e-05,
+      "loss": 0.6871,
+      "step": 4600
+    },
+    {
+      "epoch": 0.6834938543280632,
+      "grad_norm": 0.6431862115859985,
+      "learning_rate": 6.786530550053329e-05,
+      "loss": 0.7138,
+      "step": 4625
+    },
+    {
+      "epoch": 0.6871884157028095,
+      "grad_norm": 0.6050564050674438,
+      "learning_rate": 6.767484382142313e-05,
+      "loss": 0.6978,
+      "step": 4650
+    },
+    {
+      "epoch": 0.6908829770775557,
+      "grad_norm": 0.7160177230834961,
+      "learning_rate": 6.748438214231297e-05,
+      "loss": 0.6813,
+      "step": 4675
+    },
+    {
+      "epoch": 0.6945775384523021,
+      "grad_norm": 0.6984575986862183,
+      "learning_rate": 6.72939204632028e-05,
+      "loss": 0.7155,
+      "step": 4700
+    },
+    {
+      "epoch": 0.6982720998270483,
+      "grad_norm": 0.5910038352012634,
+      "learning_rate": 6.710345878409264e-05,
+      "loss": 0.6689,
+      "step": 4725
+    },
+    {
+      "epoch": 0.7019666612017946,
+      "grad_norm": 0.5897320508956909,
+      "learning_rate": 6.691299710498248e-05,
+      "loss": 0.7169,
+      "step": 4750
+    },
+    {
+      "epoch": 0.705661222576541,
+      "grad_norm": 0.5735405683517456,
+      "learning_rate": 6.672253542587232e-05,
+      "loss": 0.6779,
+      "step": 4775
+    },
+    {
+      "epoch": 0.7093557839512872,
+      "grad_norm": 0.6408699750900269,
+      "learning_rate": 6.653207374676216e-05,
+      "loss": 0.7069,
+      "step": 4800
+    },
+    {
+      "epoch": 0.7130503453260335,
+      "grad_norm": 0.6292117834091187,
+      "learning_rate": 6.6341612067652e-05,
+      "loss": 0.698,
+      "step": 4825
+    },
+    {
+      "epoch": 0.7167449067007798,
+      "grad_norm": 0.6101416349411011,
+      "learning_rate": 6.615115038854183e-05,
+      "loss": 0.6708,
+      "step": 4850
+    },
+    {
+      "epoch": 0.7204394680755261,
+      "grad_norm": 0.6805480122566223,
+      "learning_rate": 6.596068870943166e-05,
+      "loss": 0.7115,
+      "step": 4875
+    },
+    {
+      "epoch": 0.7241340294502724,
+      "grad_norm": 0.6465732455253601,
+      "learning_rate": 6.57702270303215e-05,
+      "loss": 0.688,
+      "step": 4900
+    },
+    {
+      "epoch": 0.7278285908250186,
+      "grad_norm": 0.5873344540596008,
+      "learning_rate": 6.557976535121134e-05,
+      "loss": 0.7032,
+      "step": 4925
+    },
+    {
+      "epoch": 0.7315231521997649,
+      "grad_norm": 0.5717042088508606,
+      "learning_rate": 6.538930367210117e-05,
+      "loss": 0.6907,
+      "step": 4950
+    },
+    {
+      "epoch": 0.7352177135745113,
+      "grad_norm": 0.6366106867790222,
+      "learning_rate": 6.519884199299102e-05,
+      "loss": 0.7061,
+      "step": 4975
+    },
+    {
+      "epoch": 0.7389122749492575,
+      "grad_norm": 0.7421902418136597,
+      "learning_rate": 6.500838031388085e-05,
+      "loss": 0.7267,
+      "step": 5000
+    },
+    {
+      "epoch": 0.7426068363240038,
+      "grad_norm": 0.5897513031959534,
+      "learning_rate": 6.48179186347707e-05,
+      "loss": 0.7089,
+      "step": 5025
+    },
+    {
+      "epoch": 0.74630139769875,
+      "grad_norm": 0.6692824959754944,
+      "learning_rate": 6.462745695566053e-05,
+      "loss": 0.7059,
+      "step": 5050
+    },
+    {
+      "epoch": 0.7499959590734964,
+      "grad_norm": 0.5818034410476685,
+      "learning_rate": 6.443699527655036e-05,
+      "loss": 0.6734,
+      "step": 5075
+    },
+    {
+      "epoch": 0.7536905204482427,
+      "grad_norm": 0.5975498557090759,
+      "learning_rate": 6.42465335974402e-05,
+      "loss": 0.6857,
+      "step": 5100
+    },
+    {
+      "epoch": 0.7573850818229889,
+      "grad_norm": 0.5827130675315857,
+      "learning_rate": 6.405607191833003e-05,
+      "loss": 0.7156,
+      "step": 5125
+    },
+    {
+      "epoch": 0.7610796431977352,
+      "grad_norm": 0.660932719707489,
+      "learning_rate": 6.386561023921987e-05,
+      "loss": 0.688,
+      "step": 5150
+    },
+    {
+      "epoch": 0.7647742045724816,
+      "grad_norm": 0.5963577628135681,
+      "learning_rate": 6.36751485601097e-05,
+      "loss": 0.709,
+      "step": 5175
+    },
+    {
+      "epoch": 0.7684687659472278,
+      "grad_norm": 0.6608302593231201,
+      "learning_rate": 6.348468688099954e-05,
+      "loss": 0.6761,
+      "step": 5200
+    },
+    {
+      "epoch": 0.7721633273219741,
+      "grad_norm": 0.6137542724609375,
+      "learning_rate": 6.329422520188938e-05,
+      "loss": 0.6845,
+      "step": 5225
+    },
+    {
+      "epoch": 0.7758578886967203,
+      "grad_norm": 0.6861995458602905,
+      "learning_rate": 6.310376352277923e-05,
+      "loss": 0.6746,
+      "step": 5250
+    },
+    {
+      "epoch": 0.7795524500714667,
+      "grad_norm": 0.6537772417068481,
+      "learning_rate": 6.291330184366906e-05,
+      "loss": 0.6777,
+      "step": 5275
+    },
+    {
+      "epoch": 0.783247011446213,
+      "grad_norm": 0.6634919047355652,
+      "learning_rate": 6.27228401645589e-05,
+      "loss": 0.6945,
+      "step": 5300
+    },
+    {
+      "epoch": 0.7869415728209592,
+      "grad_norm": 0.610098123550415,
+      "learning_rate": 6.253237848544873e-05,
+      "loss": 0.6909,
+      "step": 5325
+    },
+    {
+      "epoch": 0.7906361341957056,
+      "grad_norm": 0.6167535185813904,
+      "learning_rate": 6.234191680633856e-05,
+      "loss": 0.6988,
+      "step": 5350
+    },
+    {
+      "epoch": 0.7943306955704518,
+      "grad_norm": 0.6502842903137207,
+      "learning_rate": 6.215145512722841e-05,
+      "loss": 0.6937,
+      "step": 5375
+    },
+    {
+      "epoch": 0.7980252569451981,
+      "grad_norm": 0.5586534142494202,
+      "learning_rate": 6.196099344811824e-05,
+      "loss": 0.6891,
+      "step": 5400
+    },
+    {
+      "epoch": 0.8017198183199444,
+      "grad_norm": 0.577847957611084,
+      "learning_rate": 6.177053176900807e-05,
+      "loss": 0.7111,
+      "step": 5425
+    },
+    {
+      "epoch": 0.8054143796946907,
+      "grad_norm": 0.5086051225662231,
+      "learning_rate": 6.158007008989792e-05,
+      "loss": 0.6892,
+      "step": 5450
+    },
+    {
+      "epoch": 0.809108941069437,
+      "grad_norm": 0.6650702953338623,
+      "learning_rate": 6.138960841078775e-05,
+      "loss": 0.6853,
+      "step": 5475
+    },
+    {
+      "epoch": 0.8128035024441833,
+      "grad_norm": 0.730775773525238,
+      "learning_rate": 6.11991467316776e-05,
+      "loss": 0.6972,
+      "step": 5500
+    },
+    {
+      "epoch": 0.8164980638189295,
+      "grad_norm": 0.6812962293624878,
+      "learning_rate": 6.100868505256743e-05,
+      "loss": 0.7179,
+      "step": 5525
+    },
+    {
+      "epoch": 0.8201926251936759,
+      "grad_norm": 0.6698195934295654,
+      "learning_rate": 6.081822337345726e-05,
+      "loss": 0.6935,
+      "step": 5550
+    },
+    {
+      "epoch": 0.8238871865684221,
+      "grad_norm": 0.7661596536636353,
+      "learning_rate": 6.0627761694347096e-05,
+      "loss": 0.7081,
+      "step": 5575
+    },
+    {
+      "epoch": 0.8275817479431684,
+      "grad_norm": 0.63306725025177,
+      "learning_rate": 6.043730001523694e-05,
+      "loss": 0.6814,
+      "step": 5600
+    },
+    {
+      "epoch": 0.8312763093179147,
+      "grad_norm": 0.638088047504425,
+      "learning_rate": 6.0246838336126774e-05,
+      "loss": 0.7162,
+      "step": 5625
+    },
+    {
+      "epoch": 0.834970870692661,
+      "grad_norm": 0.6416764259338379,
+      "learning_rate": 6.0056376657016614e-05,
+      "loss": 0.6935,
+      "step": 5650
+    },
+    {
+      "epoch": 0.8386654320674073,
+      "grad_norm": 0.6060255169868469,
+      "learning_rate": 5.9865914977906447e-05,
+      "loss": 0.6935,
+      "step": 5675
+    },
+    {
+      "epoch": 0.8423599934421535,
+      "grad_norm": 0.6919652223587036,
+      "learning_rate": 5.967545329879628e-05,
+      "loss": 0.6781,
+      "step": 5700
+    },
+    {
+      "epoch": 0.8460545548168998,
+      "grad_norm": 0.5610880851745605,
+      "learning_rate": 5.9484991619686125e-05,
+      "loss": 0.6924,
+      "step": 5725
+    },
+    {
+      "epoch": 0.8497491161916462,
+      "grad_norm": 0.6481006145477295,
+      "learning_rate": 5.929452994057596e-05,
+      "loss": 0.6708,
+      "step": 5750
+    },
+    {
+      "epoch": 0.8534436775663924,
+      "grad_norm": 0.618869423866272,
+      "learning_rate": 5.91040682614658e-05,
+      "loss": 0.6801,
+      "step": 5775
+    },
+    {
+      "epoch": 0.8571382389411387,
+      "grad_norm": 0.5622214674949646,
+      "learning_rate": 5.891360658235563e-05,
+      "loss": 0.6932,
+      "step": 5800
+    },
+    {
+      "epoch": 0.860832800315885,
+      "grad_norm": 0.6936132311820984,
+      "learning_rate": 5.8723144903245476e-05,
+      "loss": 0.6932,
+      "step": 5825
+    },
+    {
+      "epoch": 0.8645273616906313,
+      "grad_norm": 0.6182092428207397,
+      "learning_rate": 5.853268322413531e-05,
+      "loss": 0.6767,
+      "step": 5850
+    },
+    {
+      "epoch": 0.8682219230653776,
+      "grad_norm": 0.6932141184806824,
+      "learning_rate": 5.834222154502514e-05,
+      "loss": 0.694,
+      "step": 5875
+    },
+    {
+      "epoch": 0.8719164844401238,
+      "grad_norm": 0.4943319261074066,
+      "learning_rate": 5.815175986591498e-05,
+      "loss": 0.6884,
+      "step": 5900
+    },
+    {
+      "epoch": 0.8756110458148701,
+      "grad_norm": 0.730697512626648,
+      "learning_rate": 5.7961298186804814e-05,
+      "loss": 0.6906,
+      "step": 5925
+    },
+    {
+      "epoch": 0.8793056071896165,
+      "grad_norm": 0.5535916090011597,
+      "learning_rate": 5.777083650769466e-05,
+      "loss": 0.6992,
+      "step": 5950
+    },
+    {
+      "epoch": 0.8830001685643627,
+      "grad_norm": 0.6035041809082031,
+      "learning_rate": 5.758037482858449e-05,
+      "loss": 0.6637,
+      "step": 5975
+    },
+    {
+      "epoch": 0.886694729939109,
+      "grad_norm": 0.6580167412757874,
+      "learning_rate": 5.7389913149474325e-05,
+      "loss": 0.7056,
+      "step": 6000
+    },
+    {
+      "epoch": 0.8903892913138552,
+      "grad_norm": 0.5391905903816223,
+      "learning_rate": 5.7199451470364165e-05,
+      "loss": 0.7169,
+      "step": 6025
+    },
+    {
+      "epoch": 0.8940838526886016,
+      "grad_norm": 0.7833768725395203,
+      "learning_rate": 5.7008989791254e-05,
+      "loss": 0.682,
+      "step": 6050
+    },
+    {
+      "epoch": 0.8977784140633479,
+      "grad_norm": 0.6040502190589905,
+      "learning_rate": 5.681852811214384e-05,
+      "loss": 0.6893,
+      "step": 6075
+    },
+    {
+      "epoch": 0.9014729754380941,
+      "grad_norm": 0.5723184943199158,
+      "learning_rate": 5.6628066433033676e-05,
+      "loss": 0.7041,
+      "step": 6100
+    },
+    {
+      "epoch": 0.9051675368128405,
+      "grad_norm": 0.7001731395721436,
+      "learning_rate": 5.643760475392351e-05,
+      "loss": 0.69,
+      "step": 6125
+    },
+    {
+      "epoch": 0.9088620981875868,
+      "grad_norm": 0.6454519629478455,
+      "learning_rate": 5.624714307481335e-05,
+      "loss": 0.6777,
+      "step": 6150
+    },
+    {
+      "epoch": 0.912556659562333,
+      "grad_norm": 0.6187843680381775,
+      "learning_rate": 5.6056681395703194e-05,
+      "loss": 0.7069,
+      "step": 6175
+    },
+    {
+      "epoch": 0.9162512209370793,
+      "grad_norm": 0.6245271563529968,
+      "learning_rate": 5.586621971659303e-05,
+      "loss": 0.6735,
+      "step": 6200
+    },
+    {
+      "epoch": 0.9199457823118256,
+      "grad_norm": 0.513124406337738,
+      "learning_rate": 5.567575803748286e-05,
+      "loss": 0.6859,
+      "step": 6225
+    },
+    {
+      "epoch": 0.9236403436865719,
+      "grad_norm": 0.5510721206665039,
+      "learning_rate": 5.54852963583727e-05,
+      "loss": 0.7195,
+      "step": 6250
+    },
+    {
+      "epoch": 0.9273349050613182,
+      "grad_norm": 0.7087464332580566,
+      "learning_rate": 5.529483467926253e-05,
+      "loss": 0.6761,
+      "step": 6275
+    },
+    {
+      "epoch": 0.9310294664360644,
+      "grad_norm": 0.6695664525032043,
+      "learning_rate": 5.510437300015238e-05,
+      "loss": 0.7013,
+      "step": 6300
+    },
+    {
+      "epoch": 0.9347240278108108,
+      "grad_norm": 0.6182588934898376,
+      "learning_rate": 5.491391132104221e-05,
+      "loss": 0.6793,
+      "step": 6325
+    },
+    {
+      "epoch": 0.938418589185557,
+      "grad_norm": 0.7019252181053162,
+      "learning_rate": 5.472344964193204e-05,
+      "loss": 0.7122,
+      "step": 6350
+    },
+    {
+      "epoch": 0.9421131505603033,
+      "grad_norm": 0.772847592830658,
+      "learning_rate": 5.453298796282188e-05,
+      "loss": 0.6991,
+      "step": 6375
+    },
+    {
+      "epoch": 0.9458077119350496,
+      "grad_norm": 0.7126289010047913,
+      "learning_rate": 5.4342526283711715e-05,
+      "loss": 0.6992,
+      "step": 6400
+    },
+    {
+      "epoch": 0.9495022733097959,
+      "grad_norm": 0.7134938836097717,
+      "learning_rate": 5.415206460460156e-05,
+      "loss": 0.7091,
+      "step": 6425
+    },
+    {
+      "epoch": 0.9531968346845422,
+      "grad_norm": 0.7651578187942505,
+      "learning_rate": 5.3961602925491394e-05,
+      "loss": 0.6829,
+      "step": 6450
+    },
+    {
+      "epoch": 0.9568913960592885,
+      "grad_norm": 0.6493939161300659,
+      "learning_rate": 5.377114124638123e-05,
+      "loss": 0.6831,
+      "step": 6475
+    },
+    {
+      "epoch": 0.9605859574340347,
+      "grad_norm": 0.5992809534072876,
+      "learning_rate": 5.3580679567271066e-05,
+      "loss": 0.6984,
+      "step": 6500
+    },
+    {
+      "epoch": 0.9642805188087811,
+      "grad_norm": 0.6597899794578552,
+      "learning_rate": 5.339021788816091e-05,
+      "loss": 0.6893,
+      "step": 6525
+    },
+    {
+      "epoch": 0.9679750801835273,
+      "grad_norm": 0.6459916234016418,
+      "learning_rate": 5.3199756209050745e-05,
+      "loss": 0.6935,
+      "step": 6550
+    },
+    {
+      "epoch": 0.9716696415582736,
+      "grad_norm": 0.7714385986328125,
+      "learning_rate": 5.300929452994058e-05,
+      "loss": 0.6883,
+      "step": 6575
+    },
+    {
+      "epoch": 0.97536420293302,
+      "grad_norm": 0.5793107748031616,
+      "learning_rate": 5.281883285083041e-05,
+      "loss": 0.6795,
+      "step": 6600
+    },
+    {
+      "epoch": 0.9790587643077662,
+      "grad_norm": 0.5452476739883423,
+      "learning_rate": 5.262837117172025e-05,
+      "loss": 0.6809,
+      "step": 6625
+    },
+    {
+      "epoch": 0.9827533256825125,
+      "grad_norm": 0.6292601823806763,
+      "learning_rate": 5.2437909492610096e-05,
+      "loss": 0.7021,
+      "step": 6650
+    },
+    {
+      "epoch": 0.9864478870572587,
+      "grad_norm": 0.6509853601455688,
+      "learning_rate": 5.224744781349993e-05,
+      "loss": 0.6808,
+      "step": 6675
+    },
+    {
+      "epoch": 0.990142448432005,
+      "grad_norm": 0.6169773936271667,
+      "learning_rate": 5.205698613438976e-05,
+      "loss": 0.677,
+      "step": 6700
+    },
+    {
+      "epoch": 0.9938370098067514,
+      "grad_norm": 0.6769931316375732,
+      "learning_rate": 5.1866524455279594e-05,
+      "loss": 0.7188,
+      "step": 6725
+    },
+    {
+      "epoch": 0.9975315711814976,
+      "grad_norm": 0.6493127346038818,
+      "learning_rate": 5.167606277616944e-05,
+      "loss": 0.68,
+      "step": 6750
+    },
+    {
+      "epoch": 1.001182259639919,
+      "grad_norm": 0.6528682708740234,
+      "learning_rate": 5.148560109705928e-05,
+      "loss": 0.6982,
+      "step": 6775
+    },
+    {
+      "epoch": 1.004876821014665,
+      "grad_norm": 0.6537097692489624,
+      "learning_rate": 5.129513941794911e-05,
+      "loss": 0.6513,
+      "step": 6800
+    },
+    {
+      "epoch": 1.0085713823894114,
+      "grad_norm": 0.6426008939743042,
+      "learning_rate": 5.1104677738838945e-05,
+      "loss": 0.668,
+      "step": 6825
+    },
+    {
+      "epoch": 1.0122659437641577,
+      "grad_norm": 0.5742406249046326,
+      "learning_rate": 5.0914216059728784e-05,
+      "loss": 0.67,
+      "step": 6850
+    },
+    {
+      "epoch": 1.015960505138904,
+      "grad_norm": 0.7166649103164673,
+      "learning_rate": 5.0723754380618623e-05,
+      "loss": 0.6602,
+      "step": 6875
+    },
+    {
+      "epoch": 1.0196550665136503,
+      "grad_norm": 0.7485601305961609,
+      "learning_rate": 5.053329270150846e-05,
+      "loss": 0.6567,
+      "step": 6900
+    },
+    {
+      "epoch": 1.0233496278883965,
+      "grad_norm": 0.7126789689064026,
+      "learning_rate": 5.0342831022398296e-05,
+      "loss": 0.6624,
+      "step": 6925
+    },
+    {
+      "epoch": 1.0270441892631428,
+      "grad_norm": 0.7238374948501587,
+      "learning_rate": 5.015236934328813e-05,
+      "loss": 0.6613,
+      "step": 6950
+    },
+    {
+      "epoch": 1.0307387506378891,
+      "grad_norm": 0.6505608558654785,
+      "learning_rate": 4.996190766417797e-05,
+      "loss": 0.6554,
+      "step": 6975
+    },
+    {
+      "epoch": 1.0344333120126354,
+      "grad_norm": 0.6918332576751709,
+      "learning_rate": 4.977144598506781e-05,
+      "loss": 0.6645,
+      "step": 7000
+    },
+    {
+      "epoch": 1.0381278733873818,
+      "grad_norm": 0.5876255035400391,
+      "learning_rate": 4.9580984305957646e-05,
+      "loss": 0.6638,
+      "step": 7025
+    },
+    {
+      "epoch": 1.0418224347621279,
+      "grad_norm": 0.7554610967636108,
+      "learning_rate": 4.939052262684748e-05,
+      "loss": 0.6742,
+      "step": 7050
+    },
+    {
+      "epoch": 1.0455169961368742,
+      "grad_norm": 0.6300481557846069,
+      "learning_rate": 4.920006094773732e-05,
+      "loss": 0.6409,
+      "step": 7075
+    },
+    {
+      "epoch": 1.0492115575116205,
+      "grad_norm": 0.5924395322799683,
+      "learning_rate": 4.900959926862715e-05,
+      "loss": 0.668,
+      "step": 7100
+    },
+    {
+      "epoch": 1.0529061188863669,
+      "grad_norm": 0.6832597851753235,
+      "learning_rate": 4.881913758951699e-05,
+      "loss": 0.6431,
+      "step": 7125
+    },
+    {
+      "epoch": 1.0566006802611132,
+      "grad_norm": 0.702418863773346,
+      "learning_rate": 4.862867591040683e-05,
+      "loss": 0.6463,
+      "step": 7150
+    },
+    {
+      "epoch": 1.0602952416358593,
+      "grad_norm": 0.6264967918395996,
+      "learning_rate": 4.843821423129666e-05,
+      "loss": 0.653,
+      "step": 7175
+    },
+    {
+      "epoch": 1.0639898030106056,
+      "grad_norm": 0.6441030502319336,
+      "learning_rate": 4.82477525521865e-05,
+      "loss": 0.6415,
+      "step": 7200
+    },
+    {
+      "epoch": 1.067684364385352,
+      "grad_norm": 0.5445654392242432,
+      "learning_rate": 4.805729087307634e-05,
+      "loss": 0.6516,
+      "step": 7225
+    },
+    {
+      "epoch": 1.0713789257600983,
+      "grad_norm": 0.634982168674469,
+      "learning_rate": 4.786682919396618e-05,
+      "loss": 0.6617,
+      "step": 7250
+    },
+    {
+      "epoch": 1.0750734871348446,
+      "grad_norm": 0.5670004487037659,
+      "learning_rate": 4.7676367514856013e-05,
+      "loss": 0.644,
+      "step": 7275
+    },
+    {
+      "epoch": 1.0787680485095907,
+      "grad_norm": 0.6136172413825989,
+      "learning_rate": 4.7485905835745846e-05,
+      "loss": 0.6404,
+      "step": 7300
+    },
+    {
+      "epoch": 1.082462609884337,
+      "grad_norm": 0.6087863445281982,
+      "learning_rate": 4.7295444156635686e-05,
+      "loss": 0.666,
+      "step": 7325
+    },
+    {
+      "epoch": 1.0861571712590834,
+      "grad_norm": 0.54926997423172,
+      "learning_rate": 4.7104982477525525e-05,
+      "loss": 0.6157,
+      "step": 7350
+    },
+    {
+      "epoch": 1.0898517326338297,
+      "grad_norm": 0.6426320672035217,
+      "learning_rate": 4.6914520798415364e-05,
+      "loss": 0.6349,
+      "step": 7375
+    },
+    {
+      "epoch": 1.093546294008576,
+      "grad_norm": 0.5854539275169373,
+      "learning_rate": 4.67240591193052e-05,
+      "loss": 0.6583,
+      "step": 7400
+    },
+    {
+      "epoch": 1.0972408553833224,
+      "grad_norm": 0.7021641731262207,
+      "learning_rate": 4.6533597440195036e-05,
+      "loss": 0.6682,
+      "step": 7425
+    },
+    {
+      "epoch": 1.1009354167580685,
+      "grad_norm": 0.7356472611427307,
+      "learning_rate": 4.634313576108487e-05,
+      "loss": 0.6563,
+      "step": 7450
+    },
+    {
+      "epoch": 1.1046299781328148,
+      "grad_norm": 0.6147669553756714,
+      "learning_rate": 4.615267408197471e-05,
+      "loss": 0.667,
+      "step": 7475
+    },
+    {
+      "epoch": 1.1083245395075612,
+      "grad_norm": 0.6394315958023071,
+      "learning_rate": 4.596221240286455e-05,
+      "loss": 0.6737,
+      "step": 7500
+    },
+    {
+      "epoch": 1.1120191008823075,
+      "grad_norm": 0.7234614491462708,
+      "learning_rate": 4.577175072375438e-05,
+      "loss": 0.6556,
+      "step": 7525
+    },
+    {
+      "epoch": 1.1157136622570538,
+      "grad_norm": 0.6812229156494141,
+      "learning_rate": 4.558128904464422e-05,
+      "loss": 0.6544,
+      "step": 7550
+    },
+    {
+      "epoch": 1.1194082236318,
+      "grad_norm": 0.6218217611312866,
+      "learning_rate": 4.539082736553405e-05,
+      "loss": 0.668,
+      "step": 7575
+    },
+    {
+      "epoch": 1.1231027850065463,
+      "grad_norm": 0.8202681541442871,
+      "learning_rate": 4.52003656864239e-05,
+      "loss": 0.679,
+      "step": 7600
+    },
+    {
+      "epoch": 1.1267973463812926,
+      "grad_norm": 0.5360725522041321,
+      "learning_rate": 4.500990400731373e-05,
+      "loss": 0.6463,
+      "step": 7625
+    },
+    {
+      "epoch": 1.130491907756039,
+      "grad_norm": 0.6142716407775879,
+      "learning_rate": 4.481944232820357e-05,
+      "loss": 0.659,
+      "step": 7650
+    },
+    {
+      "epoch": 1.1341864691307852,
+      "grad_norm": 0.619349479675293,
+      "learning_rate": 4.4628980649093404e-05,
+      "loss": 0.6724,
+      "step": 7675
+    },
+    {
+      "epoch": 1.1378810305055314,
+      "grad_norm": 0.6891987323760986,
+      "learning_rate": 4.4438518969983236e-05,
+      "loss": 0.6509,
+      "step": 7700
+    },
+    {
+      "epoch": 1.1415755918802777,
+      "grad_norm": 0.7174720168113708,
+      "learning_rate": 4.424805729087308e-05,
+      "loss": 0.6715,
+      "step": 7725
+    },
+    {
+      "epoch": 1.145270153255024,
+      "grad_norm": 0.7424497008323669,
+      "learning_rate": 4.4057595611762915e-05,
+      "loss": 0.6449,
+      "step": 7750
+    },
+    {
+      "epoch": 1.1489647146297703,
+      "grad_norm": 0.6533998847007751,
+      "learning_rate": 4.3867133932652754e-05,
+      "loss": 0.6528,
+      "step": 7775
+    },
+    {
+      "epoch": 1.1526592760045167,
+      "grad_norm": 0.7500383853912354,
+      "learning_rate": 4.367667225354259e-05,
+      "loss": 0.6592,
+      "step": 7800
+    },
+    {
+      "epoch": 1.156353837379263,
+      "grad_norm": 0.6293950080871582,
+      "learning_rate": 4.3486210574432427e-05,
+      "loss": 0.6584,
+      "step": 7825
+    },
+    {
+      "epoch": 1.1600483987540091,
+      "grad_norm": 0.8463473320007324,
+      "learning_rate": 4.3295748895322266e-05,
+      "loss": 0.6656,
+      "step": 7850
+    },
+    {
+      "epoch": 1.1637429601287554,
+      "grad_norm": 0.6918061971664429,
+      "learning_rate": 4.31052872162121e-05,
+      "loss": 0.6603,
+      "step": 7875
+    },
+    {
+      "epoch": 1.1674375215035018,
+      "grad_norm": 0.5433516502380371,
+      "learning_rate": 4.291482553710194e-05,
+      "loss": 0.6422,
+      "step": 7900
+    },
+    {
+      "epoch": 1.171132082878248,
+      "grad_norm": 0.6414408087730408,
+      "learning_rate": 4.272436385799177e-05,
+      "loss": 0.6279,
+      "step": 7925
+    },
+    {
+      "epoch": 1.1748266442529944,
+      "grad_norm": 0.814218282699585,
+      "learning_rate": 4.253390217888161e-05,
+      "loss": 0.6673,
+      "step": 7950
+    },
+    {
+      "epoch": 1.1785212056277405,
+      "grad_norm": 0.7378386855125427,
+      "learning_rate": 4.234344049977145e-05,
+      "loss": 0.6651,
+      "step": 7975
+    },
+    {
+      "epoch": 1.1822157670024869,
+      "grad_norm": 0.6620386242866516,
+      "learning_rate": 4.215297882066129e-05,
+      "loss": 0.6984,
+      "step": 8000
+    },
+    {
+      "epoch": 1.1859103283772332,
+      "grad_norm": 0.6845581531524658,
+      "learning_rate": 4.196251714155112e-05,
+      "loss": 0.6524,
+      "step": 8025
+    },
+    {
+      "epoch": 1.1896048897519795,
+      "grad_norm": 0.7139785289764404,
+      "learning_rate": 4.1772055462440954e-05,
+      "loss": 0.6453,
+      "step": 8050
+    },
+    {
+      "epoch": 1.1932994511267259,
+      "grad_norm": 0.6536353230476379,
+      "learning_rate": 4.1581593783330794e-05,
+      "loss": 0.6456,
+      "step": 8075
+    },
+    {
+      "epoch": 1.196994012501472,
+      "grad_norm": 0.6225493550300598,
+      "learning_rate": 4.139113210422063e-05,
+      "loss": 0.6192,
+      "step": 8100
+    },
+    {
+      "epoch": 1.2006885738762183,
+      "grad_norm": 0.6810159683227539,
+      "learning_rate": 4.120067042511047e-05,
+      "loss": 0.6634,
+      "step": 8125
+    },
+    {
+      "epoch": 1.2043831352509646,
+      "grad_norm": 0.5847315788269043,
+      "learning_rate": 4.1010208746000305e-05,
+      "loss": 0.6231,
+      "step": 8150
+    },
+    {
+      "epoch": 1.208077696625711,
+      "grad_norm": 0.6385469436645508,
+      "learning_rate": 4.0819747066890144e-05,
+      "loss": 0.6619,
+      "step": 8175
+    },
+    {
+      "epoch": 1.2117722580004573,
+      "grad_norm": 0.7124472260475159,
+      "learning_rate": 4.0629285387779984e-05,
+      "loss": 0.6626,
+      "step": 8200
+    },
+    {
+      "epoch": 1.2154668193752034,
+      "grad_norm": 0.658824622631073,
+      "learning_rate": 4.0438823708669817e-05,
+      "loss": 0.6653,
+      "step": 8225
+    },
+    {
+      "epoch": 1.2191613807499497,
+      "grad_norm": 0.6626468300819397,
+      "learning_rate": 4.0248362029559656e-05,
+      "loss": 0.6777,
+      "step": 8250
+    },
+    {
+      "epoch": 1.222855942124696,
+      "grad_norm": 0.6238393783569336,
+      "learning_rate": 4.005790035044949e-05,
+      "loss": 0.6622,
+      "step": 8275
+    },
+    {
+      "epoch": 1.2265505034994424,
+      "grad_norm": 0.685213565826416,
+      "learning_rate": 3.986743867133933e-05,
+      "loss": 0.6423,
+      "step": 8300
+    },
+    {
+      "epoch": 1.2302450648741887,
+      "grad_norm": 0.7486940622329712,
+      "learning_rate": 3.967697699222917e-05,
+      "loss": 0.6631,
+      "step": 8325
+    },
+    {
+      "epoch": 1.2339396262489348,
+      "grad_norm": 0.7994277477264404,
+      "learning_rate": 3.948651531311901e-05,
+      "loss": 0.6725,
+      "step": 8350
+    },
+    {
+      "epoch": 1.2376341876236812,
+      "grad_norm": 0.6204445958137512,
+      "learning_rate": 3.929605363400884e-05,
+      "loss": 0.6411,
+      "step": 8375
+    },
+    {
+      "epoch": 1.2413287489984275,
+      "grad_norm": 0.7625504732131958,
+      "learning_rate": 3.910559195489867e-05,
+      "loss": 0.6819,
+      "step": 8400
+    },
+    {
+      "epoch": 1.2450233103731738,
+      "grad_norm": 0.6892343163490295,
+      "learning_rate": 3.891513027578851e-05,
+      "loss": 0.6614,
+      "step": 8425
+    },
+    {
+      "epoch": 1.2487178717479201,
+      "grad_norm": 0.6849514245986938,
+      "learning_rate": 3.872466859667835e-05,
+      "loss": 0.6442,
+      "step": 8450
+    },
+    {
+      "epoch": 1.2524124331226663,
+      "grad_norm": 0.7257765531539917,
+      "learning_rate": 3.853420691756819e-05,
+      "loss": 0.6475,
+      "step": 8475
+    },
+    {
+      "epoch": 1.2561069944974126,
+      "grad_norm": 0.7827818393707275,
+      "learning_rate": 3.834374523845802e-05,
+      "loss": 0.6317,
+      "step": 8500
+    },
+    {
+      "epoch": 1.259801555872159,
+      "grad_norm": 0.7970981597900391,
+      "learning_rate": 3.815328355934786e-05,
+      "loss": 0.6585,
+      "step": 8525
+    },
+    {
+      "epoch": 1.2634961172469052,
+      "grad_norm": 0.7086262106895447,
+      "learning_rate": 3.7962821880237695e-05,
+      "loss": 0.6499,
+      "step": 8550
+    },
+    {
+      "epoch": 1.2671906786216516,
+      "grad_norm": 0.654151439666748,
+      "learning_rate": 3.7772360201127535e-05,
+      "loss": 0.6587,
+      "step": 8575
+    },
+    {
+      "epoch": 1.2708852399963977,
+      "grad_norm": 0.6484542489051819,
+      "learning_rate": 3.7581898522017374e-05,
+      "loss": 0.6533,
+      "step": 8600
+    },
+    {
+      "epoch": 1.274579801371144,
+      "grad_norm": 0.5822983384132385,
+      "learning_rate": 3.7391436842907207e-05,
+      "loss": 0.6535,
+      "step": 8625
+    },
+    {
+      "epoch": 1.2782743627458903,
+      "grad_norm": 0.6506041884422302,
+      "learning_rate": 3.7200975163797046e-05,
+      "loss": 0.6527,
+      "step": 8650
+    },
+    {
+      "epoch": 1.2819689241206367,
+      "grad_norm": 0.6804136037826538,
+      "learning_rate": 3.701051348468688e-05,
+      "loss": 0.642,
+      "step": 8675
+    },
+    {
+      "epoch": 1.285663485495383,
+      "grad_norm": 0.7997829914093018,
+      "learning_rate": 3.6820051805576725e-05,
+      "loss": 0.6489,
+      "step": 8700
+    },
+    {
+      "epoch": 1.2893580468701291,
+      "grad_norm": 0.7355867028236389,
+      "learning_rate": 3.662959012646656e-05,
+      "loss": 0.6777,
+      "step": 8725
+    },
+    {
+      "epoch": 1.2930526082448754,
+      "grad_norm": 9.047796249389648,
+      "learning_rate": 3.643912844735639e-05,
+      "loss": 0.6777,
+      "step": 8750
+    },
+    {
+      "epoch": 1.2967471696196218,
+      "grad_norm": 0.7236223220825195,
+      "learning_rate": 3.624866676824623e-05,
+      "loss": 0.6777,
+      "step": 8775
+    },
+    {
+      "epoch": 1.300441730994368,
+      "grad_norm": 0.6845753192901611,
+      "learning_rate": 3.605820508913607e-05,
+      "loss": 0.6284,
+      "step": 8800
+    },
+    {
+      "epoch": 1.3041362923691144,
+      "grad_norm": 0.7639452815055847,
+      "learning_rate": 3.586774341002591e-05,
+      "loss": 0.6822,
+      "step": 8825
+    },
+    {
+      "epoch": 1.3078308537438605,
+      "grad_norm": 0.6909865736961365,
+      "learning_rate": 3.567728173091574e-05,
+      "loss": 0.6737,
+      "step": 8850
+    },
+    {
+      "epoch": 1.311525415118607,
+      "grad_norm": 0.6128563284873962,
+      "learning_rate": 3.548682005180558e-05,
+      "loss": 0.666,
+      "step": 8875
+    },
+    {
+      "epoch": 1.3152199764933532,
+      "grad_norm": 0.7517656087875366,
+      "learning_rate": 3.529635837269541e-05,
+      "loss": 0.6389,
+      "step": 8900
+    },
+    {
+      "epoch": 1.3189145378680995,
+      "grad_norm": 0.7127660512924194,
+      "learning_rate": 3.510589669358525e-05,
+      "loss": 0.6334,
+      "step": 8925
+    },
+    {
+      "epoch": 1.3226090992428459,
+      "grad_norm": 0.7129451632499695,
+      "learning_rate": 3.491543501447509e-05,
+      "loss": 0.6545,
+      "step": 8950
+    },
+    {
+      "epoch": 1.3263036606175922,
+      "grad_norm": 0.7367307543754578,
+      "learning_rate": 3.4724973335364925e-05,
+      "loss": 0.6329,
+      "step": 8975
+    },
+    {
+      "epoch": 1.3299982219923385,
+      "grad_norm": 0.7707272171974182,
+      "learning_rate": 3.4534511656254764e-05,
+      "loss": 0.6469,
+      "step": 9000
+    },
+    {
+      "epoch": 1.3336927833670846,
+      "grad_norm": 0.5796623826026917,
+      "learning_rate": 3.43440499771446e-05,
+      "loss": 0.6533,
+      "step": 9025
+    },
+    {
+      "epoch": 1.337387344741831,
+      "grad_norm": 210.8633270263672,
+      "learning_rate": 3.4153588298034436e-05,
+      "loss": 0.663,
+      "step": 9050
+    },
+    {
+      "epoch": 1.3410819061165773,
+      "grad_norm": 0.6077564358711243,
+      "learning_rate": 3.3963126618924275e-05,
+      "loss": 0.6529,
+      "step": 9075
+    },
+    {
+      "epoch": 1.3447764674913236,
+      "grad_norm": 0.5756903290748596,
+      "learning_rate": 3.3772664939814115e-05,
+      "loss": 0.6379,
+      "step": 9100
+    },
+    {
+      "epoch": 1.34847102886607,
+      "grad_norm": 0.6951320171356201,
+      "learning_rate": 3.358220326070395e-05,
+      "loss": 0.6572,
+      "step": 9125
+    },
+    {
+      "epoch": 1.352165590240816,
+      "grad_norm": 0.654563307762146,
+      "learning_rate": 3.339174158159378e-05,
+      "loss": 0.6571,
+      "step": 9150
+    },
+    {
+      "epoch": 1.3558601516155624,
+      "grad_norm": 0.8268250823020935,
+      "learning_rate": 3.320127990248362e-05,
+      "loss": 0.6952,
+      "step": 9175
+    },
+    {
+      "epoch": 1.3595547129903087,
+      "grad_norm": 0.7915245890617371,
+      "learning_rate": 3.301081822337346e-05,
+      "loss": 0.6442,
+      "step": 9200
+    },
+    {
+      "epoch": 1.363249274365055,
+      "grad_norm": 0.7299513816833496,
+      "learning_rate": 3.28203565442633e-05,
+      "loss": 0.6347,
+      "step": 9225
+    },
+    {
+      "epoch": 1.3669438357398014,
+      "grad_norm": 0.6474806070327759,
+      "learning_rate": 3.262989486515313e-05,
+      "loss": 0.6604,
+      "step": 9250
+    },
+    {
+      "epoch": 1.3706383971145475,
+      "grad_norm": 0.6813268661499023,
+      "learning_rate": 3.243943318604297e-05,
+      "loss": 0.66,
+      "step": 9275
+    },
+    {
+      "epoch": 1.3743329584892938,
+      "grad_norm": 0.7166799306869507,
+      "learning_rate": 3.224897150693281e-05,
+      "loss": 0.6689,
+      "step": 9300
+    },
+    {
+      "epoch": 1.3780275198640402,
+      "grad_norm": 0.6958301663398743,
+      "learning_rate": 3.205850982782264e-05,
+      "loss": 0.6512,
+      "step": 9325
+    },
+    {
+      "epoch": 1.3817220812387865,
+      "grad_norm": 0.8137691617012024,
+      "learning_rate": 3.186804814871248e-05,
+      "loss": 0.6691,
+      "step": 9350
+    },
+    {
+      "epoch": 1.3854166426135328,
+      "grad_norm": 0.6115707159042358,
+      "learning_rate": 3.1677586469602315e-05,
+      "loss": 0.6733,
+      "step": 9375
+    },
+    {
+      "epoch": 1.389111203988279,
+      "grad_norm": 0.7478678822517395,
+      "learning_rate": 3.1487124790492154e-05,
+      "loss": 0.6514,
+      "step": 9400
+    },
+    {
+      "epoch": 1.3928057653630252,
+      "grad_norm": 0.7280460000038147,
+      "learning_rate": 3.1296663111381993e-05,
+      "loss": 0.6375,
+      "step": 9425
+    },
+    {
+      "epoch": 1.3965003267377716,
+      "grad_norm": 0.6709932088851929,
+      "learning_rate": 3.110620143227183e-05,
+      "loss": 0.6843,
+      "step": 9450
+    },
+    {
+      "epoch": 1.400194888112518,
+      "grad_norm": 0.6445898413658142,
+      "learning_rate": 3.0915739753161666e-05,
+      "loss": 0.6395,
+      "step": 9475
+    },
+    {
+      "epoch": 1.4038894494872642,
+      "grad_norm": 0.6072065830230713,
+      "learning_rate": 3.07252780740515e-05,
+      "loss": 0.6615,
+      "step": 9500
+    },
+    {
+      "epoch": 1.4075840108620103,
+      "grad_norm": 0.7841944098472595,
+      "learning_rate": 3.053481639494134e-05,
+      "loss": 0.6388,
+      "step": 9525
+    },
+    {
+      "epoch": 1.4112785722367567,
+      "grad_norm": 0.7215288281440735,
+      "learning_rate": 3.0344354715831174e-05,
+      "loss": 0.6694,
+      "step": 9550
+    },
+    {
+      "epoch": 1.414973133611503,
+      "grad_norm": 0.5916579961776733,
+      "learning_rate": 3.0153893036721016e-05,
+      "loss": 0.7004,
+      "step": 9575
+    },
+    {
+      "epoch": 1.4186676949862493,
+      "grad_norm": 0.6357461214065552,
+      "learning_rate": 2.996343135761085e-05,
+      "loss": 0.6416,
+      "step": 9600
+    },
+    {
+      "epoch": 1.4223622563609957,
+      "grad_norm": 0.735261857509613,
+      "learning_rate": 2.977296967850069e-05,
+      "loss": 0.6374,
+      "step": 9625
+    },
+    {
+      "epoch": 1.4260568177357418,
+      "grad_norm": 0.7285844087600708,
+      "learning_rate": 2.9582507999390525e-05,
+      "loss": 0.6448,
+      "step": 9650
+    },
+    {
+      "epoch": 1.429751379110488,
+      "grad_norm": 0.7573617100715637,
+      "learning_rate": 2.9392046320280357e-05,
+      "loss": 0.6672,
+      "step": 9675
+    },
+    {
+      "epoch": 1.4334459404852344,
+      "grad_norm": 0.5082629919052124,
+      "learning_rate": 2.92015846411702e-05,
+      "loss": 0.6514,
+      "step": 9700
+    },
+    {
+      "epoch": 1.4371405018599808,
+      "grad_norm": 0.6786466836929321,
+      "learning_rate": 2.9011122962060033e-05,
+      "loss": 0.6542,
+      "step": 9725
+    },
+    {
+      "epoch": 1.440835063234727,
+      "grad_norm": 0.6085937023162842,
+      "learning_rate": 2.8820661282949872e-05,
+      "loss": 0.6581,
+      "step": 9750
+    },
+    {
+      "epoch": 1.4445296246094732,
+      "grad_norm": 0.6520203351974487,
+      "learning_rate": 2.8630199603839708e-05,
+      "loss": 0.6469,
+      "step": 9775
+    },
+    {
+      "epoch": 1.4482241859842195,
+      "grad_norm": 0.5597354769706726,
+      "learning_rate": 2.8439737924729548e-05,
+      "loss": 0.6418,
+      "step": 9800
+    },
+    {
+      "epoch": 1.4519187473589659,
+      "grad_norm": 0.6233022809028625,
+      "learning_rate": 2.8249276245619384e-05,
+      "loss": 0.6371,
+      "step": 9825
+    },
+    {
+      "epoch": 1.4556133087337122,
+      "grad_norm": 0.880703866481781,
+      "learning_rate": 2.8058814566509216e-05,
+      "loss": 0.6647,
+      "step": 9850
+    },
+    {
+      "epoch": 1.4593078701084585,
+      "grad_norm": 0.6821489334106445,
+      "learning_rate": 2.786835288739906e-05,
+      "loss": 0.6545,
+      "step": 9875
+    },
+    {
+      "epoch": 1.4630024314832046,
+      "grad_norm": 0.6734182834625244,
+      "learning_rate": 2.767789120828889e-05,
+      "loss": 0.6385,
+      "step": 9900
+    },
+    {
+      "epoch": 1.466696992857951,
+      "grad_norm": 0.8161661028862,
+      "learning_rate": 2.748742952917873e-05,
+      "loss": 0.6526,
+      "step": 9925
+    },
+    {
+      "epoch": 1.4703915542326973,
+      "grad_norm": 0.6308382153511047,
+      "learning_rate": 2.7296967850068567e-05,
+      "loss": 0.6561,
+      "step": 9950
+    },
+    {
+      "epoch": 1.4740861156074436,
+      "grad_norm": 0.791493833065033,
+      "learning_rate": 2.7106506170958406e-05,
+      "loss": 0.6607,
+      "step": 9975
+    },
+    {
+      "epoch": 1.47778067698219,
+      "grad_norm": 0.7888880372047424,
+      "learning_rate": 2.6916044491848243e-05,
+      "loss": 0.6511,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 13532,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.001171062528594e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddec6eef92f76dd21b66ba65fc3f8486e2d925551fb3a26f493b39225b02363f
+size 5969

checkpoint-11000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Qwen3-8B-Base
+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 0.15.2

checkpoint-11000/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen3-8B-Base",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-11000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:030b89f4b6884a074530d5409f3883af935c5c59340b284c0735fa940e7cf8ef
+size 2838563408

checkpoint-11000/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
+}

checkpoint-11000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6abbef3e7769a829003a169dd94ef074ba6ac16a2ce828e6af4b7b913bb2270
+size 2706136909

checkpoint-11000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de69a2834426ff9ef8199d077e00892579278af31d8969d77f98235b5cfc010a
+size 14645

checkpoint-11000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb24d096d2f8bff4d8a71163f4fedb5401bf03cc617a704f21afaedb47914aa
+size 1465

checkpoint-11000/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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-11000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-11000/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 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.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').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        {{- 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    {%- 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": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-11000/trainer_state.json

@@ -0,0 +1,3114 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6255631319720414,
+  "eval_steps": 500,
+  "global_step": 11000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0036945613747462877,
+      "grad_norm": 2.2292165756225586,
+      "learning_rate": 5.911330049261084e-06,
+      "loss": 0.9395,
+      "step": 25
+    },
+    {
+      "epoch": 0.007389122749492575,
+      "grad_norm": 0.8381065130233765,
+      "learning_rate": 1.206896551724138e-05,
+      "loss": 0.89,
+      "step": 50
+    },
+    {
+      "epoch": 0.011083684124238862,
+      "grad_norm": 0.9238471984863281,
+      "learning_rate": 1.8226600985221676e-05,
+      "loss": 0.8384,
+      "step": 75
+    },
+    {
+      "epoch": 0.01477824549898515,
+      "grad_norm": 0.6837311387062073,
+      "learning_rate": 2.438423645320197e-05,
+      "loss": 0.784,
+      "step": 100
+    },
+    {
+      "epoch": 0.01847280687373144,
+      "grad_norm": 0.7093706727027893,
+      "learning_rate": 3.0541871921182266e-05,
+      "loss": 0.7675,
+      "step": 125
+    },
+    {
+      "epoch": 0.022167368248477724,
+      "grad_norm": 0.6208077073097229,
+      "learning_rate": 3.669950738916256e-05,
+      "loss": 0.7466,
+      "step": 150
+    },
+    {
+      "epoch": 0.025861929623224013,
+      "grad_norm": 0.8929094076156616,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 0.7386,
+      "step": 175
+    },
+    {
+      "epoch": 0.0295564909979703,
+      "grad_norm": 0.7828120589256287,
+      "learning_rate": 4.901477832512316e-05,
+      "loss": 0.7173,
+      "step": 200
+    },
+    {
+      "epoch": 0.03325105237271659,
+      "grad_norm": 0.7134449481964111,
+      "learning_rate": 5.517241379310345e-05,
+      "loss": 0.7108,
+      "step": 225
+    },
+    {
+      "epoch": 0.03694561374746288,
+      "grad_norm": 0.7464851140975952,
+      "learning_rate": 6.133004926108375e-05,
+      "loss": 0.7332,
+      "step": 250
+    },
+    {
+      "epoch": 0.04064017512220916,
+      "grad_norm": 0.677793025970459,
+      "learning_rate": 6.748768472906404e-05,
+      "loss": 0.7194,
+      "step": 275
+    },
+    {
+      "epoch": 0.04433473649695545,
+      "grad_norm": 0.7936354875564575,
+      "learning_rate": 7.364532019704434e-05,
+      "loss": 0.7253,
+      "step": 300
+    },
+    {
+      "epoch": 0.04802929787170174,
+      "grad_norm": 0.6711100935935974,
+      "learning_rate": 7.980295566502463e-05,
+      "loss": 0.7018,
+      "step": 325
+    },
+    {
+      "epoch": 0.051723859246448026,
+      "grad_norm": 0.5816489458084106,
+      "learning_rate": 8.596059113300493e-05,
+      "loss": 0.7298,
+      "step": 350
+    },
+    {
+      "epoch": 0.055418420621194314,
+      "grad_norm": 0.6680681705474854,
+      "learning_rate": 9.211822660098522e-05,
+      "loss": 0.7149,
+      "step": 375
+    },
+    {
+      "epoch": 0.0591129819959406,
+      "grad_norm": 0.5643934607505798,
+      "learning_rate": 9.827586206896552e-05,
+      "loss": 0.763,
+      "step": 400
+    },
+    {
+      "epoch": 0.06280754337068689,
+      "grad_norm": 0.5739309191703796,
+      "learning_rate": 9.986286759104069e-05,
+      "loss": 0.7345,
+      "step": 425
+    },
+    {
+      "epoch": 0.06650210474543318,
+      "grad_norm": 0.5929909944534302,
+      "learning_rate": 9.967240591193052e-05,
+      "loss": 0.7364,
+      "step": 450
+    },
+    {
+      "epoch": 0.07019666612017947,
+      "grad_norm": 0.609235405921936,
+      "learning_rate": 9.948194423282036e-05,
+      "loss": 0.7294,
+      "step": 475
+    },
+    {
+      "epoch": 0.07389122749492576,
+      "grad_norm": 0.4643324613571167,
+      "learning_rate": 9.92914825537102e-05,
+      "loss": 0.7344,
+      "step": 500
+    },
+    {
+      "epoch": 0.07758578886967203,
+      "grad_norm": 0.5267598032951355,
+      "learning_rate": 9.910102087460003e-05,
+      "loss": 0.7249,
+      "step": 525
+    },
+    {
+      "epoch": 0.08128035024441832,
+      "grad_norm": 0.47951069474220276,
+      "learning_rate": 9.891055919548987e-05,
+      "loss": 0.7256,
+      "step": 550
+    },
+    {
+      "epoch": 0.08497491161916461,
+      "grad_norm": 0.4505012333393097,
+      "learning_rate": 9.87200975163797e-05,
+      "loss": 0.7359,
+      "step": 575
+    },
+    {
+      "epoch": 0.0886694729939109,
+      "grad_norm": 0.5320091247558594,
+      "learning_rate": 9.852963583726955e-05,
+      "loss": 0.6856,
+      "step": 600
+    },
+    {
+      "epoch": 0.09236403436865719,
+      "grad_norm": 0.5583036541938782,
+      "learning_rate": 9.833917415815939e-05,
+      "loss": 0.7235,
+      "step": 625
+    },
+    {
+      "epoch": 0.09605859574340347,
+      "grad_norm": 0.5139252543449402,
+      "learning_rate": 9.814871247904922e-05,
+      "loss": 0.7272,
+      "step": 650
+    },
+    {
+      "epoch": 0.09975315711814976,
+      "grad_norm": 0.4989326000213623,
+      "learning_rate": 9.795825079993906e-05,
+      "loss": 0.6952,
+      "step": 675
+    },
+    {
+      "epoch": 0.10344771849289605,
+      "grad_norm": 0.47355732321739197,
+      "learning_rate": 9.776778912082889e-05,
+      "loss": 0.7266,
+      "step": 700
+    },
+    {
+      "epoch": 0.10714227986764234,
+      "grad_norm": 0.3588508367538452,
+      "learning_rate": 9.757732744171874e-05,
+      "loss": 0.7406,
+      "step": 725
+    },
+    {
+      "epoch": 0.11083684124238863,
+      "grad_norm": 0.4120556712150574,
+      "learning_rate": 9.738686576260857e-05,
+      "loss": 0.7443,
+      "step": 750
+    },
+    {
+      "epoch": 0.11453140261713492,
+      "grad_norm": 0.5160555839538574,
+      "learning_rate": 9.71964040834984e-05,
+      "loss": 0.7134,
+      "step": 775
+    },
+    {
+      "epoch": 0.1182259639918812,
+      "grad_norm": 0.5423145890235901,
+      "learning_rate": 9.700594240438823e-05,
+      "loss": 0.7289,
+      "step": 800
+    },
+    {
+      "epoch": 0.1219205253666275,
+      "grad_norm": 0.5352346301078796,
+      "learning_rate": 9.681548072527808e-05,
+      "loss": 0.7144,
+      "step": 825
+    },
+    {
+      "epoch": 0.12561508674137378,
+      "grad_norm": 0.47908860445022583,
+      "learning_rate": 9.662501904616791e-05,
+      "loss": 0.7175,
+      "step": 850
+    },
+    {
+      "epoch": 0.12930964811612006,
+      "grad_norm": 0.47986069321632385,
+      "learning_rate": 9.643455736705776e-05,
+      "loss": 0.6983,
+      "step": 875
+    },
+    {
+      "epoch": 0.13300420949086636,
+      "grad_norm": 0.6903620958328247,
+      "learning_rate": 9.624409568794759e-05,
+      "loss": 0.7086,
+      "step": 900
+    },
+    {
+      "epoch": 0.13669877086561263,
+      "grad_norm": 0.44413208961486816,
+      "learning_rate": 9.605363400883742e-05,
+      "loss": 0.7306,
+      "step": 925
+    },
+    {
+      "epoch": 0.14039333224035894,
+      "grad_norm": 0.4634678065776825,
+      "learning_rate": 9.586317232972727e-05,
+      "loss": 0.7061,
+      "step": 950
+    },
+    {
+      "epoch": 0.1440878936151052,
+      "grad_norm": 0.5110129714012146,
+      "learning_rate": 9.56727106506171e-05,
+      "loss": 0.7406,
+      "step": 975
+    },
+    {
+      "epoch": 0.1477824549898515,
+      "grad_norm": 0.5460866093635559,
+      "learning_rate": 9.548224897150694e-05,
+      "loss": 0.721,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1514770163645978,
+      "grad_norm": 0.5179885029792786,
+      "learning_rate": 9.529178729239677e-05,
+      "loss": 0.7068,
+      "step": 1025
+    },
+    {
+      "epoch": 0.15517157773934406,
+      "grad_norm": 0.40280836820602417,
+      "learning_rate": 9.51013256132866e-05,
+      "loss": 0.7009,
+      "step": 1050
+    },
+    {
+      "epoch": 0.15886613911409037,
+      "grad_norm": 1.2706756591796875,
+      "learning_rate": 9.491086393417645e-05,
+      "loss": 0.7125,
+      "step": 1075
+    },
+    {
+      "epoch": 0.16256070048883664,
+      "grad_norm": 0.4963163435459137,
+      "learning_rate": 9.47204022550663e-05,
+      "loss": 0.7149,
+      "step": 1100
+    },
+    {
+      "epoch": 0.16625526186358294,
+      "grad_norm": 0.5147728323936462,
+      "learning_rate": 9.452994057595613e-05,
+      "loss": 0.7245,
+      "step": 1125
+    },
+    {
+      "epoch": 0.16994982323832922,
+      "grad_norm": 0.5933899879455566,
+      "learning_rate": 9.433947889684596e-05,
+      "loss": 0.7261,
+      "step": 1150
+    },
+    {
+      "epoch": 0.17364438461307552,
+      "grad_norm": 0.4750466048717499,
+      "learning_rate": 9.414901721773579e-05,
+      "loss": 0.7206,
+      "step": 1175
+    },
+    {
+      "epoch": 0.1773389459878218,
+      "grad_norm": 0.46546968817710876,
+      "learning_rate": 9.395855553862564e-05,
+      "loss": 0.7121,
+      "step": 1200
+    },
+    {
+      "epoch": 0.1810335073625681,
+      "grad_norm": 0.6512172818183899,
+      "learning_rate": 9.376809385951547e-05,
+      "loss": 0.7212,
+      "step": 1225
+    },
+    {
+      "epoch": 0.18472806873731437,
+      "grad_norm": 0.34932607412338257,
+      "learning_rate": 9.35776321804053e-05,
+      "loss": 0.704,
+      "step": 1250
+    },
+    {
+      "epoch": 0.18842263011206067,
+      "grad_norm": 0.4648846983909607,
+      "learning_rate": 9.338717050129514e-05,
+      "loss": 0.7419,
+      "step": 1275
+    },
+    {
+      "epoch": 0.19211719148680695,
+      "grad_norm": 0.4566064774990082,
+      "learning_rate": 9.319670882218498e-05,
+      "loss": 0.7318,
+      "step": 1300
+    },
+    {
+      "epoch": 0.19581175286155325,
+      "grad_norm": 0.5357668399810791,
+      "learning_rate": 9.300624714307481e-05,
+      "loss": 0.6973,
+      "step": 1325
+    },
+    {
+      "epoch": 0.19950631423629953,
+      "grad_norm": 0.4423241913318634,
+      "learning_rate": 9.281578546396466e-05,
+      "loss": 0.7298,
+      "step": 1350
+    },
+    {
+      "epoch": 0.20320087561104583,
+      "grad_norm": 0.4530033767223358,
+      "learning_rate": 9.26253237848545e-05,
+      "loss": 0.7161,
+      "step": 1375
+    },
+    {
+      "epoch": 0.2068954369857921,
+      "grad_norm": 0.4678841233253479,
+      "learning_rate": 9.243486210574433e-05,
+      "loss": 0.6972,
+      "step": 1400
+    },
+    {
+      "epoch": 0.21058999836053838,
+      "grad_norm": 0.6039907336235046,
+      "learning_rate": 9.224440042663417e-05,
+      "loss": 0.7165,
+      "step": 1425
+    },
+    {
+      "epoch": 0.21428455973528468,
+      "grad_norm": 0.4463271498680115,
+      "learning_rate": 9.2053938747524e-05,
+      "loss": 0.6863,
+      "step": 1450
+    },
+    {
+      "epoch": 0.21797912111003095,
+      "grad_norm": 0.5739301443099976,
+      "learning_rate": 9.186347706841384e-05,
+      "loss": 0.6907,
+      "step": 1475
+    },
+    {
+      "epoch": 0.22167368248477726,
+      "grad_norm": 0.4577805697917938,
+      "learning_rate": 9.167301538930367e-05,
+      "loss": 0.7114,
+      "step": 1500
+    },
+    {
+      "epoch": 0.22536824385952353,
+      "grad_norm": 0.4522150158882141,
+      "learning_rate": 9.14825537101935e-05,
+      "loss": 0.6877,
+      "step": 1525
+    },
+    {
+      "epoch": 0.22906280523426983,
+      "grad_norm": 0.49612903594970703,
+      "learning_rate": 9.129209203108335e-05,
+      "loss": 0.7112,
+      "step": 1550
+    },
+    {
+      "epoch": 0.2327573666090161,
+      "grad_norm": 0.4710284471511841,
+      "learning_rate": 9.11016303519732e-05,
+      "loss": 0.7062,
+      "step": 1575
+    },
+    {
+      "epoch": 0.2364519279837624,
+      "grad_norm": 0.5009223818778992,
+      "learning_rate": 9.091116867286303e-05,
+      "loss": 0.7275,
+      "step": 1600
+    },
+    {
+      "epoch": 0.24014648935850869,
+      "grad_norm": 0.5547946691513062,
+      "learning_rate": 9.072070699375286e-05,
+      "loss": 0.6993,
+      "step": 1625
+    },
+    {
+      "epoch": 0.243841050733255,
+      "grad_norm": 0.4580361843109131,
+      "learning_rate": 9.05302453146427e-05,
+      "loss": 0.7106,
+      "step": 1650
+    },
+    {
+      "epoch": 0.24753561210800126,
+      "grad_norm": 0.4767173230648041,
+      "learning_rate": 9.033978363553254e-05,
+      "loss": 0.7103,
+      "step": 1675
+    },
+    {
+      "epoch": 0.25123017348274757,
+      "grad_norm": 0.502202570438385,
+      "learning_rate": 9.014932195642237e-05,
+      "loss": 0.6921,
+      "step": 1700
+    },
+    {
+      "epoch": 0.25492473485749384,
+      "grad_norm": 0.5283953547477722,
+      "learning_rate": 8.99588602773122e-05,
+      "loss": 0.7077,
+      "step": 1725
+    },
+    {
+      "epoch": 0.2586192962322401,
+      "grad_norm": 0.4994209408760071,
+      "learning_rate": 8.976839859820204e-05,
+      "loss": 0.7,
+      "step": 1750
+    },
+    {
+      "epoch": 0.2623138576069864,
+      "grad_norm": 0.48279210925102234,
+      "learning_rate": 8.957793691909188e-05,
+      "loss": 0.7114,
+      "step": 1775
+    },
+    {
+      "epoch": 0.2660084189817327,
+      "grad_norm": 0.6055914759635925,
+      "learning_rate": 8.938747523998172e-05,
+      "loss": 0.7081,
+      "step": 1800
+    },
+    {
+      "epoch": 0.269702980356479,
+      "grad_norm": 0.489519327878952,
+      "learning_rate": 8.919701356087156e-05,
+      "loss": 0.6946,
+      "step": 1825
+    },
+    {
+      "epoch": 0.27339754173122527,
+      "grad_norm": 0.5379961133003235,
+      "learning_rate": 8.90065518817614e-05,
+      "loss": 0.6996,
+      "step": 1850
+    },
+    {
+      "epoch": 0.27709210310597154,
+      "grad_norm": 0.47824332118034363,
+      "learning_rate": 8.881609020265123e-05,
+      "loss": 0.6881,
+      "step": 1875
+    },
+    {
+      "epoch": 0.2807866644807179,
+      "grad_norm": 1551.0594482421875,
+      "learning_rate": 8.862562852354107e-05,
+      "loss": 0.6998,
+      "step": 1900
+    },
+    {
+      "epoch": 0.28448122585546415,
+      "grad_norm": 0.4107681214809418,
+      "learning_rate": 8.84351668444309e-05,
+      "loss": 0.7088,
+      "step": 1925
+    },
+    {
+      "epoch": 0.2881757872302104,
+      "grad_norm": 0.4558309316635132,
+      "learning_rate": 8.824470516532074e-05,
+      "loss": 0.712,
+      "step": 1950
+    },
+    {
+      "epoch": 0.2918703486049567,
+      "grad_norm": 0.539107620716095,
+      "learning_rate": 8.805424348621057e-05,
+      "loss": 0.7159,
+      "step": 1975
+    },
+    {
+      "epoch": 0.295564909979703,
+      "grad_norm": 0.5768142938613892,
+      "learning_rate": 8.786378180710042e-05,
+      "loss": 0.7072,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2992594713544493,
+      "grad_norm": 0.5575465559959412,
+      "learning_rate": 8.767332012799025e-05,
+      "loss": 0.7118,
+      "step": 2025
+    },
+    {
+      "epoch": 0.3029540327291956,
+      "grad_norm": 0.5190144181251526,
+      "learning_rate": 8.748285844888008e-05,
+      "loss": 0.7099,
+      "step": 2050
+    },
+    {
+      "epoch": 0.30664859410394185,
+      "grad_norm": 0.4934520125389099,
+      "learning_rate": 8.729239676976993e-05,
+      "loss": 0.692,
+      "step": 2075
+    },
+    {
+      "epoch": 0.3103431554786881,
+      "grad_norm": 0.42613571882247925,
+      "learning_rate": 8.710193509065976e-05,
+      "loss": 0.7277,
+      "step": 2100
+    },
+    {
+      "epoch": 0.31403771685343446,
+      "grad_norm": 0.5124602317810059,
+      "learning_rate": 8.691147341154961e-05,
+      "loss": 0.6801,
+      "step": 2125
+    },
+    {
+      "epoch": 0.31773227822818073,
+      "grad_norm": 0.5284898281097412,
+      "learning_rate": 8.672101173243944e-05,
+      "loss": 0.7103,
+      "step": 2150
+    },
+    {
+      "epoch": 0.321426839602927,
+      "grad_norm": 0.43099457025527954,
+      "learning_rate": 8.653055005332927e-05,
+      "loss": 0.7023,
+      "step": 2175
+    },
+    {
+      "epoch": 0.3251214009776733,
+      "grad_norm": 0.5190865993499756,
+      "learning_rate": 8.63400883742191e-05,
+      "loss": 0.7144,
+      "step": 2200
+    },
+    {
+      "epoch": 0.3288159623524196,
+      "grad_norm": 0.4722968637943268,
+      "learning_rate": 8.614962669510895e-05,
+      "loss": 0.7351,
+      "step": 2225
+    },
+    {
+      "epoch": 0.3325105237271659,
+      "grad_norm": 0.6091466546058655,
+      "learning_rate": 8.595916501599878e-05,
+      "loss": 0.7062,
+      "step": 2250
+    },
+    {
+      "epoch": 0.33620508510191216,
+      "grad_norm": 0.6135897040367126,
+      "learning_rate": 8.576870333688862e-05,
+      "loss": 0.7117,
+      "step": 2275
+    },
+    {
+      "epoch": 0.33989964647665843,
+      "grad_norm": 0.5224157571792603,
+      "learning_rate": 8.557824165777846e-05,
+      "loss": 0.7068,
+      "step": 2300
+    },
+    {
+      "epoch": 0.34359420785140476,
+      "grad_norm": 0.4863536059856415,
+      "learning_rate": 8.53877799786683e-05,
+      "loss": 0.6952,
+      "step": 2325
+    },
+    {
+      "epoch": 0.34728876922615104,
+      "grad_norm": 0.4728885889053345,
+      "learning_rate": 8.519731829955814e-05,
+      "loss": 0.7289,
+      "step": 2350
+    },
+    {
+      "epoch": 0.3509833306008973,
+      "grad_norm": 0.5152695775032043,
+      "learning_rate": 8.500685662044798e-05,
+      "loss": 0.6986,
+      "step": 2375
+    },
+    {
+      "epoch": 0.3546778919756436,
+      "grad_norm": 0.4407690465450287,
+      "learning_rate": 8.481639494133781e-05,
+      "loss": 0.6983,
+      "step": 2400
+    },
+    {
+      "epoch": 0.3583724533503899,
+      "grad_norm": 0.4756406545639038,
+      "learning_rate": 8.462593326222764e-05,
+      "loss": 0.6626,
+      "step": 2425
+    },
+    {
+      "epoch": 0.3620670147251362,
+      "grad_norm": 0.48595255613327026,
+      "learning_rate": 8.443547158311747e-05,
+      "loss": 0.6892,
+      "step": 2450
+    },
+    {
+      "epoch": 0.36576157609988247,
+      "grad_norm": 0.47830772399902344,
+      "learning_rate": 8.424500990400732e-05,
+      "loss": 0.7162,
+      "step": 2475
+    },
+    {
+      "epoch": 0.36945613747462874,
+      "grad_norm": 0.43090149760246277,
+      "learning_rate": 8.405454822489715e-05,
+      "loss": 0.6913,
+      "step": 2500
+    },
+    {
+      "epoch": 0.373150698849375,
+      "grad_norm": 0.5338718295097351,
+      "learning_rate": 8.386408654578698e-05,
+      "loss": 0.7159,
+      "step": 2525
+    },
+    {
+      "epoch": 0.37684526022412135,
+      "grad_norm": 0.4907350242137909,
+      "learning_rate": 8.367362486667683e-05,
+      "loss": 0.7022,
+      "step": 2550
+    },
+    {
+      "epoch": 0.3805398215988676,
+      "grad_norm": 0.44093430042266846,
+      "learning_rate": 8.348316318756668e-05,
+      "loss": 0.7124,
+      "step": 2575
+    },
+    {
+      "epoch": 0.3842343829736139,
+      "grad_norm": 0.5388796925544739,
+      "learning_rate": 8.329270150845651e-05,
+      "loss": 0.7304,
+      "step": 2600
+    },
+    {
+      "epoch": 0.38792894434836017,
+      "grad_norm": 0.4456349313259125,
+      "learning_rate": 8.310223982934634e-05,
+      "loss": 0.6964,
+      "step": 2625
+    },
+    {
+      "epoch": 0.3916235057231065,
+      "grad_norm": 0.4602237343788147,
+      "learning_rate": 8.291177815023617e-05,
+      "loss": 0.6707,
+      "step": 2650
+    },
+    {
+      "epoch": 0.3953180670978528,
+      "grad_norm": 0.4726378917694092,
+      "learning_rate": 8.272131647112601e-05,
+      "loss": 0.694,
+      "step": 2675
+    },
+    {
+      "epoch": 0.39901262847259905,
+      "grad_norm": 0.500451922416687,
+      "learning_rate": 8.253085479201585e-05,
+      "loss": 0.6812,
+      "step": 2700
+    },
+    {
+      "epoch": 0.4027071898473453,
+      "grad_norm": 0.4073813259601593,
+      "learning_rate": 8.234039311290569e-05,
+      "loss": 0.7028,
+      "step": 2725
+    },
+    {
+      "epoch": 0.40640175122209166,
+      "grad_norm": 0.43644702434539795,
+      "learning_rate": 8.214993143379552e-05,
+      "loss": 0.6936,
+      "step": 2750
+    },
+    {
+      "epoch": 0.41009631259683793,
+      "grad_norm": 0.5256789922714233,
+      "learning_rate": 8.195946975468535e-05,
+      "loss": 0.7035,
+      "step": 2775
+    },
+    {
+      "epoch": 0.4137908739715842,
+      "grad_norm": 0.48385316133499146,
+      "learning_rate": 8.17690080755752e-05,
+      "loss": 0.6736,
+      "step": 2800
+    },
+    {
+      "epoch": 0.4174854353463305,
+      "grad_norm": 0.49825233221054077,
+      "learning_rate": 8.157854639646504e-05,
+      "loss": 0.7019,
+      "step": 2825
+    },
+    {
+      "epoch": 0.42117999672107675,
+      "grad_norm": 0.5086994171142578,
+      "learning_rate": 8.138808471735488e-05,
+      "loss": 0.6918,
+      "step": 2850
+    },
+    {
+      "epoch": 0.4248745580958231,
+      "grad_norm": 0.5430259108543396,
+      "learning_rate": 8.119762303824471e-05,
+      "loss": 0.7175,
+      "step": 2875
+    },
+    {
+      "epoch": 0.42856911947056936,
+      "grad_norm": 0.5889118313789368,
+      "learning_rate": 8.100716135913454e-05,
+      "loss": 0.6967,
+      "step": 2900
+    },
+    {
+      "epoch": 0.43226368084531563,
+      "grad_norm": 0.5345672369003296,
+      "learning_rate": 8.081669968002439e-05,
+      "loss": 0.6926,
+      "step": 2925
+    },
+    {
+      "epoch": 0.4359582422200619,
+      "grad_norm": 0.511101245880127,
+      "learning_rate": 8.062623800091422e-05,
+      "loss": 0.7248,
+      "step": 2950
+    },
+    {
+      "epoch": 0.43965280359480824,
+      "grad_norm": 0.511239767074585,
+      "learning_rate": 8.043577632180405e-05,
+      "loss": 0.7319,
+      "step": 2975
+    },
+    {
+      "epoch": 0.4433473649695545,
+      "grad_norm": 0.5121573805809021,
+      "learning_rate": 8.024531464269389e-05,
+      "loss": 0.7023,
+      "step": 3000
+    },
+    {
+      "epoch": 0.4470419263443008,
+      "grad_norm": 0.5658753514289856,
+      "learning_rate": 8.005485296358373e-05,
+      "loss": 0.6934,
+      "step": 3025
+    },
+    {
+      "epoch": 0.45073648771904706,
+      "grad_norm": 0.5475583672523499,
+      "learning_rate": 7.986439128447358e-05,
+      "loss": 0.6701,
+      "step": 3050
+    },
+    {
+      "epoch": 0.4544310490937934,
+      "grad_norm": 0.6107661724090576,
+      "learning_rate": 7.967392960536341e-05,
+      "loss": 0.7056,
+      "step": 3075
+    },
+    {
+      "epoch": 0.45812561046853967,
+      "grad_norm": 0.48424115777015686,
+      "learning_rate": 7.948346792625324e-05,
+      "loss": 0.7179,
+      "step": 3100
+    },
+    {
+      "epoch": 0.46182017184328594,
+      "grad_norm": 0.6184881329536438,
+      "learning_rate": 7.929300624714308e-05,
+      "loss": 0.7141,
+      "step": 3125
+    },
+    {
+      "epoch": 0.4655147332180322,
+      "grad_norm": 0.49919527769088745,
+      "learning_rate": 7.910254456803291e-05,
+      "loss": 0.7027,
+      "step": 3150
+    },
+    {
+      "epoch": 0.4692092945927785,
+      "grad_norm": 0.5012905597686768,
+      "learning_rate": 7.891208288892276e-05,
+      "loss": 0.6852,
+      "step": 3175
+    },
+    {
+      "epoch": 0.4729038559675248,
+      "grad_norm": 0.5033735036849976,
+      "learning_rate": 7.872162120981259e-05,
+      "loss": 0.7199,
+      "step": 3200
+    },
+    {
+      "epoch": 0.4765984173422711,
+      "grad_norm": 0.5746079087257385,
+      "learning_rate": 7.853115953070242e-05,
+      "loss": 0.715,
+      "step": 3225
+    },
+    {
+      "epoch": 0.48029297871701737,
+      "grad_norm": 0.5436145663261414,
+      "learning_rate": 7.834069785159225e-05,
+      "loss": 0.697,
+      "step": 3250
+    },
+    {
+      "epoch": 0.48398754009176365,
+      "grad_norm": 0.5836604833602905,
+      "learning_rate": 7.81502361724821e-05,
+      "loss": 0.7129,
+      "step": 3275
+    },
+    {
+      "epoch": 0.48768210146651,
+      "grad_norm": 0.5618935227394104,
+      "learning_rate": 7.795977449337195e-05,
+      "loss": 0.6993,
+      "step": 3300
+    },
+    {
+      "epoch": 0.49137666284125625,
+      "grad_norm": 0.6251245737075806,
+      "learning_rate": 7.776931281426178e-05,
+      "loss": 0.7132,
+      "step": 3325
+    },
+    {
+      "epoch": 0.4950712242160025,
+      "grad_norm": 0.5123202800750732,
+      "learning_rate": 7.757885113515161e-05,
+      "loss": 0.7218,
+      "step": 3350
+    },
+    {
+      "epoch": 0.4987657855907488,
+      "grad_norm": 0.5818086862564087,
+      "learning_rate": 7.738838945604144e-05,
+      "loss": 0.7154,
+      "step": 3375
+    },
+    {
+      "epoch": 0.5024603469654951,
+      "grad_norm": 0.5861947536468506,
+      "learning_rate": 7.719792777693129e-05,
+      "loss": 0.7013,
+      "step": 3400
+    },
+    {
+      "epoch": 0.5061549083402413,
+      "grad_norm": 0.4849907457828522,
+      "learning_rate": 7.700746609782112e-05,
+      "loss": 0.6902,
+      "step": 3425
+    },
+    {
+      "epoch": 0.5098494697149877,
+      "grad_norm": 0.5476916432380676,
+      "learning_rate": 7.681700441871096e-05,
+      "loss": 0.7147,
+      "step": 3450
+    },
+    {
+      "epoch": 0.513544031089734,
+      "grad_norm": 0.5822548866271973,
+      "learning_rate": 7.662654273960079e-05,
+      "loss": 0.7431,
+      "step": 3475
+    },
+    {
+      "epoch": 0.5172385924644802,
+      "grad_norm": 0.44818004965782166,
+      "learning_rate": 7.643608106049063e-05,
+      "loss": 0.718,
+      "step": 3500
+    },
+    {
+      "epoch": 0.5209331538392266,
+      "grad_norm": 0.544068455696106,
+      "learning_rate": 7.624561938138047e-05,
+      "loss": 0.7201,
+      "step": 3525
+    },
+    {
+      "epoch": 0.5246277152139728,
+      "grad_norm": 0.5535098910331726,
+      "learning_rate": 7.605515770227031e-05,
+      "loss": 0.6998,
+      "step": 3550
+    },
+    {
+      "epoch": 0.5283222765887191,
+      "grad_norm": 0.5754445195198059,
+      "learning_rate": 7.586469602316015e-05,
+      "loss": 0.6918,
+      "step": 3575
+    },
+    {
+      "epoch": 0.5320168379634654,
+      "grad_norm": 0.5976133942604065,
+      "learning_rate": 7.567423434404998e-05,
+      "loss": 0.693,
+      "step": 3600
+    },
+    {
+      "epoch": 0.5357113993382117,
+      "grad_norm": 0.4844263195991516,
+      "learning_rate": 7.548377266493982e-05,
+      "loss": 0.68,
+      "step": 3625
+    },
+    {
+      "epoch": 0.539405960712958,
+      "grad_norm": 0.5436462163925171,
+      "learning_rate": 7.529331098582966e-05,
+      "loss": 0.7075,
+      "step": 3650
+    },
+    {
+      "epoch": 0.5431005220877043,
+      "grad_norm": 0.6490929126739502,
+      "learning_rate": 7.510284930671949e-05,
+      "loss": 0.6956,
+      "step": 3675
+    },
+    {
+      "epoch": 0.5467950834624505,
+      "grad_norm": 0.47479814291000366,
+      "learning_rate": 7.491238762760932e-05,
+      "loss": 0.7026,
+      "step": 3700
+    },
+    {
+      "epoch": 0.5504896448371969,
+      "grad_norm": 0.590874969959259,
+      "learning_rate": 7.472192594849915e-05,
+      "loss": 0.7117,
+      "step": 3725
+    },
+    {
+      "epoch": 0.5541842062119431,
+      "grad_norm": 0.46487829089164734,
+      "learning_rate": 7.4531464269389e-05,
+      "loss": 0.6919,
+      "step": 3750
+    },
+    {
+      "epoch": 0.5578787675866894,
+      "grad_norm": 0.6609780192375183,
+      "learning_rate": 7.434100259027885e-05,
+      "loss": 0.7089,
+      "step": 3775
+    },
+    {
+      "epoch": 0.5615733289614357,
+      "grad_norm": 0.6165657639503479,
+      "learning_rate": 7.415054091116868e-05,
+      "loss": 0.7444,
+      "step": 3800
+    },
+    {
+      "epoch": 0.565267890336182,
+      "grad_norm": 0.5194655656814575,
+      "learning_rate": 7.396007923205851e-05,
+      "loss": 0.7114,
+      "step": 3825
+    },
+    {
+      "epoch": 0.5689624517109283,
+      "grad_norm": 0.4813441336154938,
+      "learning_rate": 7.376961755294836e-05,
+      "loss": 0.6953,
+      "step": 3850
+    },
+    {
+      "epoch": 0.5726570130856745,
+      "grad_norm": 0.7607313990592957,
+      "learning_rate": 7.357915587383819e-05,
+      "loss": 0.7058,
+      "step": 3875
+    },
+    {
+      "epoch": 0.5763515744604208,
+      "grad_norm": 0.48498719930648804,
+      "learning_rate": 7.338869419472802e-05,
+      "loss": 0.6866,
+      "step": 3900
+    },
+    {
+      "epoch": 0.5800461358351672,
+      "grad_norm": 0.5969393253326416,
+      "learning_rate": 7.319823251561786e-05,
+      "loss": 0.6951,
+      "step": 3925
+    },
+    {
+      "epoch": 0.5837406972099134,
+      "grad_norm": 0.6178887486457825,
+      "learning_rate": 7.300777083650769e-05,
+      "loss": 0.7036,
+      "step": 3950
+    },
+    {
+      "epoch": 0.5874352585846597,
+      "grad_norm": 0.5318612456321716,
+      "learning_rate": 7.281730915739754e-05,
+      "loss": 0.6856,
+      "step": 3975
+    },
+    {
+      "epoch": 0.591129819959406,
+      "grad_norm": 0.6101936101913452,
+      "learning_rate": 7.262684747828737e-05,
+      "loss": 0.7103,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5948243813341523,
+      "grad_norm": 0.5605831742286682,
+      "learning_rate": 7.243638579917721e-05,
+      "loss": 0.6684,
+      "step": 4025
+    },
+    {
+      "epoch": 0.5985189427088986,
+      "grad_norm": 0.6576380133628845,
+      "learning_rate": 7.224592412006705e-05,
+      "loss": 0.6955,
+      "step": 4050
+    },
+    {
+      "epoch": 0.6022135040836448,
+      "grad_norm": 0.49083924293518066,
+      "learning_rate": 7.205546244095688e-05,
+      "loss": 0.7089,
+      "step": 4075
+    },
+    {
+      "epoch": 0.6059080654583912,
+      "grad_norm": 0.4783398509025574,
+      "learning_rate": 7.186500076184673e-05,
+      "loss": 0.6766,
+      "step": 4100
+    },
+    {
+      "epoch": 0.6096026268331375,
+      "grad_norm": 0.5773366689682007,
+      "learning_rate": 7.167453908273656e-05,
+      "loss": 0.666,
+      "step": 4125
+    },
+    {
+      "epoch": 0.6132971882078837,
+      "grad_norm": 0.5449897050857544,
+      "learning_rate": 7.148407740362639e-05,
+      "loss": 0.6795,
+      "step": 4150
+    },
+    {
+      "epoch": 0.61699174958263,
+      "grad_norm": 0.519882082939148,
+      "learning_rate": 7.129361572451622e-05,
+      "loss": 0.6892,
+      "step": 4175
+    },
+    {
+      "epoch": 0.6206863109573763,
+      "grad_norm": 0.5653222799301147,
+      "learning_rate": 7.110315404540607e-05,
+      "loss": 0.7029,
+      "step": 4200
+    },
+    {
+      "epoch": 0.6243808723321226,
+      "grad_norm": 0.542448878288269,
+      "learning_rate": 7.09126923662959e-05,
+      "loss": 0.6885,
+      "step": 4225
+    },
+    {
+      "epoch": 0.6280754337068689,
+      "grad_norm": 0.5602554082870483,
+      "learning_rate": 7.072223068718575e-05,
+      "loss": 0.6811,
+      "step": 4250
+    },
+    {
+      "epoch": 0.6317699950816151,
+      "grad_norm": 0.5326575636863708,
+      "learning_rate": 7.053176900807558e-05,
+      "loss": 0.7032,
+      "step": 4275
+    },
+    {
+      "epoch": 0.6354645564563615,
+      "grad_norm": 0.5822186470031738,
+      "learning_rate": 7.034130732896541e-05,
+      "loss": 0.6951,
+      "step": 4300
+    },
+    {
+      "epoch": 0.6391591178311078,
+      "grad_norm": 0.5309107899665833,
+      "learning_rate": 7.015084564985526e-05,
+      "loss": 0.6891,
+      "step": 4325
+    },
+    {
+      "epoch": 0.642853679205854,
+      "grad_norm": 0.6958228349685669,
+      "learning_rate": 6.996038397074509e-05,
+      "loss": 0.6932,
+      "step": 4350
+    },
+    {
+      "epoch": 0.6465482405806003,
+      "grad_norm": 0.4864750802516937,
+      "learning_rate": 6.976992229163493e-05,
+      "loss": 0.6897,
+      "step": 4375
+    },
+    {
+      "epoch": 0.6502428019553466,
+      "grad_norm": 0.5077944993972778,
+      "learning_rate": 6.957946061252476e-05,
+      "loss": 0.7067,
+      "step": 4400
+    },
+    {
+      "epoch": 0.6539373633300929,
+      "grad_norm": 0.5589050054550171,
+      "learning_rate": 6.938899893341459e-05,
+      "loss": 0.6927,
+      "step": 4425
+    },
+    {
+      "epoch": 0.6576319247048392,
+      "grad_norm": 0.6064692735671997,
+      "learning_rate": 6.919853725430444e-05,
+      "loss": 0.7186,
+      "step": 4450
+    },
+    {
+      "epoch": 0.6613264860795854,
+      "grad_norm": 0.5546572208404541,
+      "learning_rate": 6.900807557519427e-05,
+      "loss": 0.6865,
+      "step": 4475
+    },
+    {
+      "epoch": 0.6650210474543318,
+      "grad_norm": 0.6032342314720154,
+      "learning_rate": 6.881761389608412e-05,
+      "loss": 0.6999,
+      "step": 4500
+    },
+    {
+      "epoch": 0.668715608829078,
+      "grad_norm": 0.5067450404167175,
+      "learning_rate": 6.862715221697395e-05,
+      "loss": 0.7068,
+      "step": 4525
+    },
+    {
+      "epoch": 0.6724101702038243,
+      "grad_norm": 0.6697527170181274,
+      "learning_rate": 6.84366905378638e-05,
+      "loss": 0.7075,
+      "step": 4550
+    },
+    {
+      "epoch": 0.6761047315785707,
+      "grad_norm": 0.48360082507133484,
+      "learning_rate": 6.824622885875363e-05,
+      "loss": 0.7076,
+      "step": 4575
+    },
+    {
+      "epoch": 0.6797992929533169,
+      "grad_norm": 0.6387288570404053,
+      "learning_rate": 6.805576717964346e-05,
+      "loss": 0.6871,
+      "step": 4600
+    },
+    {
+      "epoch": 0.6834938543280632,
+      "grad_norm": 0.6431862115859985,
+      "learning_rate": 6.786530550053329e-05,
+      "loss": 0.7138,
+      "step": 4625
+    },
+    {
+      "epoch": 0.6871884157028095,
+      "grad_norm": 0.6050564050674438,
+      "learning_rate": 6.767484382142313e-05,
+      "loss": 0.6978,
+      "step": 4650
+    },
+    {
+      "epoch": 0.6908829770775557,
+      "grad_norm": 0.7160177230834961,
+      "learning_rate": 6.748438214231297e-05,
+      "loss": 0.6813,
+      "step": 4675
+    },
+    {
+      "epoch": 0.6945775384523021,
+      "grad_norm": 0.6984575986862183,
+      "learning_rate": 6.72939204632028e-05,
+      "loss": 0.7155,
+      "step": 4700
+    },
+    {
+      "epoch": 0.6982720998270483,
+      "grad_norm": 0.5910038352012634,
+      "learning_rate": 6.710345878409264e-05,
+      "loss": 0.6689,
+      "step": 4725
+    },
+    {
+      "epoch": 0.7019666612017946,
+      "grad_norm": 0.5897320508956909,
+      "learning_rate": 6.691299710498248e-05,
+      "loss": 0.7169,
+      "step": 4750
+    },
+    {
+      "epoch": 0.705661222576541,
+      "grad_norm": 0.5735405683517456,
+      "learning_rate": 6.672253542587232e-05,
+      "loss": 0.6779,
+      "step": 4775
+    },
+    {
+      "epoch": 0.7093557839512872,
+      "grad_norm": 0.6408699750900269,
+      "learning_rate": 6.653207374676216e-05,
+      "loss": 0.7069,
+      "step": 4800
+    },
+    {
+      "epoch": 0.7130503453260335,
+      "grad_norm": 0.6292117834091187,
+      "learning_rate": 6.6341612067652e-05,
+      "loss": 0.698,
+      "step": 4825
+    },
+    {
+      "epoch": 0.7167449067007798,
+      "grad_norm": 0.6101416349411011,
+      "learning_rate": 6.615115038854183e-05,
+      "loss": 0.6708,
+      "step": 4850
+    },
+    {
+      "epoch": 0.7204394680755261,
+      "grad_norm": 0.6805480122566223,
+      "learning_rate": 6.596068870943166e-05,
+      "loss": 0.7115,
+      "step": 4875
+    },
+    {
+      "epoch": 0.7241340294502724,
+      "grad_norm": 0.6465732455253601,
+      "learning_rate": 6.57702270303215e-05,
+      "loss": 0.688,
+      "step": 4900
+    },
+    {
+      "epoch": 0.7278285908250186,
+      "grad_norm": 0.5873344540596008,
+      "learning_rate": 6.557976535121134e-05,
+      "loss": 0.7032,
+      "step": 4925
+    },
+    {
+      "epoch": 0.7315231521997649,
+      "grad_norm": 0.5717042088508606,
+      "learning_rate": 6.538930367210117e-05,
+      "loss": 0.6907,
+      "step": 4950
+    },
+    {
+      "epoch": 0.7352177135745113,
+      "grad_norm": 0.6366106867790222,
+      "learning_rate": 6.519884199299102e-05,
+      "loss": 0.7061,
+      "step": 4975
+    },
+    {
+      "epoch": 0.7389122749492575,
+      "grad_norm": 0.7421902418136597,
+      "learning_rate": 6.500838031388085e-05,
+      "loss": 0.7267,
+      "step": 5000
+    },
+    {
+      "epoch": 0.7426068363240038,
+      "grad_norm": 0.5897513031959534,
+      "learning_rate": 6.48179186347707e-05,
+      "loss": 0.7089,
+      "step": 5025
+    },
+    {
+      "epoch": 0.74630139769875,
+      "grad_norm": 0.6692824959754944,
+      "learning_rate": 6.462745695566053e-05,
+      "loss": 0.7059,
+      "step": 5050
+    },
+    {
+      "epoch": 0.7499959590734964,
+      "grad_norm": 0.5818034410476685,
+      "learning_rate": 6.443699527655036e-05,
+      "loss": 0.6734,
+      "step": 5075
+    },
+    {
+      "epoch": 0.7536905204482427,
+      "grad_norm": 0.5975498557090759,
+      "learning_rate": 6.42465335974402e-05,
+      "loss": 0.6857,
+      "step": 5100
+    },
+    {
+      "epoch": 0.7573850818229889,
+      "grad_norm": 0.5827130675315857,
+      "learning_rate": 6.405607191833003e-05,
+      "loss": 0.7156,
+      "step": 5125
+    },
+    {
+      "epoch": 0.7610796431977352,
+      "grad_norm": 0.660932719707489,
+      "learning_rate": 6.386561023921987e-05,
+      "loss": 0.688,
+      "step": 5150
+    },
+    {
+      "epoch": 0.7647742045724816,
+      "grad_norm": 0.5963577628135681,
+      "learning_rate": 6.36751485601097e-05,
+      "loss": 0.709,
+      "step": 5175
+    },
+    {
+      "epoch": 0.7684687659472278,
+      "grad_norm": 0.6608302593231201,
+      "learning_rate": 6.348468688099954e-05,
+      "loss": 0.6761,
+      "step": 5200
+    },
+    {
+      "epoch": 0.7721633273219741,
+      "grad_norm": 0.6137542724609375,
+      "learning_rate": 6.329422520188938e-05,
+      "loss": 0.6845,
+      "step": 5225
+    },
+    {
+      "epoch": 0.7758578886967203,
+      "grad_norm": 0.6861995458602905,
+      "learning_rate": 6.310376352277923e-05,
+      "loss": 0.6746,
+      "step": 5250
+    },
+    {
+      "epoch": 0.7795524500714667,
+      "grad_norm": 0.6537772417068481,
+      "learning_rate": 6.291330184366906e-05,
+      "loss": 0.6777,
+      "step": 5275
+    },
+    {
+      "epoch": 0.783247011446213,
+      "grad_norm": 0.6634919047355652,
+      "learning_rate": 6.27228401645589e-05,
+      "loss": 0.6945,
+      "step": 5300
+    },
+    {
+      "epoch": 0.7869415728209592,
+      "grad_norm": 0.610098123550415,
+      "learning_rate": 6.253237848544873e-05,
+      "loss": 0.6909,
+      "step": 5325
+    },
+    {
+      "epoch": 0.7906361341957056,
+      "grad_norm": 0.6167535185813904,
+      "learning_rate": 6.234191680633856e-05,
+      "loss": 0.6988,
+      "step": 5350
+    },
+    {
+      "epoch": 0.7943306955704518,
+      "grad_norm": 0.6502842903137207,
+      "learning_rate": 6.215145512722841e-05,
+      "loss": 0.6937,
+      "step": 5375
+    },
+    {
+      "epoch": 0.7980252569451981,
+      "grad_norm": 0.5586534142494202,
+      "learning_rate": 6.196099344811824e-05,
+      "loss": 0.6891,
+      "step": 5400
+    },
+    {
+      "epoch": 0.8017198183199444,
+      "grad_norm": 0.577847957611084,
+      "learning_rate": 6.177053176900807e-05,
+      "loss": 0.7111,
+      "step": 5425
+    },
+    {
+      "epoch": 0.8054143796946907,
+      "grad_norm": 0.5086051225662231,
+      "learning_rate": 6.158007008989792e-05,
+      "loss": 0.6892,
+      "step": 5450
+    },
+    {
+      "epoch": 0.809108941069437,
+      "grad_norm": 0.6650702953338623,
+      "learning_rate": 6.138960841078775e-05,
+      "loss": 0.6853,
+      "step": 5475
+    },
+    {
+      "epoch": 0.8128035024441833,
+      "grad_norm": 0.730775773525238,
+      "learning_rate": 6.11991467316776e-05,
+      "loss": 0.6972,
+      "step": 5500
+    },
+    {
+      "epoch": 0.8164980638189295,
+      "grad_norm": 0.6812962293624878,
+      "learning_rate": 6.100868505256743e-05,
+      "loss": 0.7179,
+      "step": 5525
+    },
+    {
+      "epoch": 0.8201926251936759,
+      "grad_norm": 0.6698195934295654,
+      "learning_rate": 6.081822337345726e-05,
+      "loss": 0.6935,
+      "step": 5550
+    },
+    {
+      "epoch": 0.8238871865684221,
+      "grad_norm": 0.7661596536636353,
+      "learning_rate": 6.0627761694347096e-05,
+      "loss": 0.7081,
+      "step": 5575
+    },
+    {
+      "epoch": 0.8275817479431684,
+      "grad_norm": 0.63306725025177,
+      "learning_rate": 6.043730001523694e-05,
+      "loss": 0.6814,
+      "step": 5600
+    },
+    {
+      "epoch": 0.8312763093179147,
+      "grad_norm": 0.638088047504425,
+      "learning_rate": 6.0246838336126774e-05,
+      "loss": 0.7162,
+      "step": 5625
+    },
+    {
+      "epoch": 0.834970870692661,
+      "grad_norm": 0.6416764259338379,
+      "learning_rate": 6.0056376657016614e-05,
+      "loss": 0.6935,
+      "step": 5650
+    },
+    {
+      "epoch": 0.8386654320674073,
+      "grad_norm": 0.6060255169868469,
+      "learning_rate": 5.9865914977906447e-05,
+      "loss": 0.6935,
+      "step": 5675
+    },
+    {
+      "epoch": 0.8423599934421535,
+      "grad_norm": 0.6919652223587036,
+      "learning_rate": 5.967545329879628e-05,
+      "loss": 0.6781,
+      "step": 5700
+    },
+    {
+      "epoch": 0.8460545548168998,
+      "grad_norm": 0.5610880851745605,
+      "learning_rate": 5.9484991619686125e-05,
+      "loss": 0.6924,
+      "step": 5725
+    },
+    {
+      "epoch": 0.8497491161916462,
+      "grad_norm": 0.6481006145477295,
+      "learning_rate": 5.929452994057596e-05,
+      "loss": 0.6708,
+      "step": 5750
+    },
+    {
+      "epoch": 0.8534436775663924,
+      "grad_norm": 0.618869423866272,
+      "learning_rate": 5.91040682614658e-05,
+      "loss": 0.6801,
+      "step": 5775
+    },
+    {
+      "epoch": 0.8571382389411387,
+      "grad_norm": 0.5622214674949646,
+      "learning_rate": 5.891360658235563e-05,
+      "loss": 0.6932,
+      "step": 5800
+    },
+    {
+      "epoch": 0.860832800315885,
+      "grad_norm": 0.6936132311820984,
+      "learning_rate": 5.8723144903245476e-05,
+      "loss": 0.6932,
+      "step": 5825
+    },
+    {
+      "epoch": 0.8645273616906313,
+      "grad_norm": 0.6182092428207397,
+      "learning_rate": 5.853268322413531e-05,
+      "loss": 0.6767,
+      "step": 5850
+    },
+    {
+      "epoch": 0.8682219230653776,
+      "grad_norm": 0.6932141184806824,
+      "learning_rate": 5.834222154502514e-05,
+      "loss": 0.694,
+      "step": 5875
+    },
+    {
+      "epoch": 0.8719164844401238,
+      "grad_norm": 0.4943319261074066,
+      "learning_rate": 5.815175986591498e-05,
+      "loss": 0.6884,
+      "step": 5900
+    },
+    {
+      "epoch": 0.8756110458148701,
+      "grad_norm": 0.730697512626648,
+      "learning_rate": 5.7961298186804814e-05,
+      "loss": 0.6906,
+      "step": 5925
+    },
+    {
+      "epoch": 0.8793056071896165,
+      "grad_norm": 0.5535916090011597,
+      "learning_rate": 5.777083650769466e-05,
+      "loss": 0.6992,
+      "step": 5950
+    },
+    {
+      "epoch": 0.8830001685643627,
+      "grad_norm": 0.6035041809082031,
+      "learning_rate": 5.758037482858449e-05,
+      "loss": 0.6637,
+      "step": 5975
+    },
+    {
+      "epoch": 0.886694729939109,
+      "grad_norm": 0.6580167412757874,
+      "learning_rate": 5.7389913149474325e-05,
+      "loss": 0.7056,
+      "step": 6000
+    },
+    {
+      "epoch": 0.8903892913138552,
+      "grad_norm": 0.5391905903816223,
+      "learning_rate": 5.7199451470364165e-05,
+      "loss": 0.7169,
+      "step": 6025
+    },
+    {
+      "epoch": 0.8940838526886016,
+      "grad_norm": 0.7833768725395203,
+      "learning_rate": 5.7008989791254e-05,
+      "loss": 0.682,
+      "step": 6050
+    },
+    {
+      "epoch": 0.8977784140633479,
+      "grad_norm": 0.6040502190589905,
+      "learning_rate": 5.681852811214384e-05,
+      "loss": 0.6893,
+      "step": 6075
+    },
+    {
+      "epoch": 0.9014729754380941,
+      "grad_norm": 0.5723184943199158,
+      "learning_rate": 5.6628066433033676e-05,
+      "loss": 0.7041,
+      "step": 6100
+    },
+    {
+      "epoch": 0.9051675368128405,
+      "grad_norm": 0.7001731395721436,
+      "learning_rate": 5.643760475392351e-05,
+      "loss": 0.69,
+      "step": 6125
+    },
+    {
+      "epoch": 0.9088620981875868,
+      "grad_norm": 0.6454519629478455,
+      "learning_rate": 5.624714307481335e-05,
+      "loss": 0.6777,
+      "step": 6150
+    },
+    {
+      "epoch": 0.912556659562333,
+      "grad_norm": 0.6187843680381775,
+      "learning_rate": 5.6056681395703194e-05,
+      "loss": 0.7069,
+      "step": 6175
+    },
+    {
+      "epoch": 0.9162512209370793,
+      "grad_norm": 0.6245271563529968,
+      "learning_rate": 5.586621971659303e-05,
+      "loss": 0.6735,
+      "step": 6200
+    },
+    {
+      "epoch": 0.9199457823118256,
+      "grad_norm": 0.513124406337738,
+      "learning_rate": 5.567575803748286e-05,
+      "loss": 0.6859,
+      "step": 6225
+    },
+    {
+      "epoch": 0.9236403436865719,
+      "grad_norm": 0.5510721206665039,
+      "learning_rate": 5.54852963583727e-05,
+      "loss": 0.7195,
+      "step": 6250
+    },
+    {
+      "epoch": 0.9273349050613182,
+      "grad_norm": 0.7087464332580566,
+      "learning_rate": 5.529483467926253e-05,
+      "loss": 0.6761,
+      "step": 6275
+    },
+    {
+      "epoch": 0.9310294664360644,
+      "grad_norm": 0.6695664525032043,
+      "learning_rate": 5.510437300015238e-05,
+      "loss": 0.7013,
+      "step": 6300
+    },
+    {
+      "epoch": 0.9347240278108108,
+      "grad_norm": 0.6182588934898376,
+      "learning_rate": 5.491391132104221e-05,
+      "loss": 0.6793,
+      "step": 6325
+    },
+    {
+      "epoch": 0.938418589185557,
+      "grad_norm": 0.7019252181053162,
+      "learning_rate": 5.472344964193204e-05,
+      "loss": 0.7122,
+      "step": 6350
+    },
+    {
+      "epoch": 0.9421131505603033,
+      "grad_norm": 0.772847592830658,
+      "learning_rate": 5.453298796282188e-05,
+      "loss": 0.6991,
+      "step": 6375
+    },
+    {
+      "epoch": 0.9458077119350496,
+      "grad_norm": 0.7126289010047913,
+      "learning_rate": 5.4342526283711715e-05,
+      "loss": 0.6992,
+      "step": 6400
+    },
+    {
+      "epoch": 0.9495022733097959,
+      "grad_norm": 0.7134938836097717,
+      "learning_rate": 5.415206460460156e-05,
+      "loss": 0.7091,
+      "step": 6425
+    },
+    {
+      "epoch": 0.9531968346845422,
+      "grad_norm": 0.7651578187942505,
+      "learning_rate": 5.3961602925491394e-05,
+      "loss": 0.6829,
+      "step": 6450
+    },
+    {
+      "epoch": 0.9568913960592885,
+      "grad_norm": 0.6493939161300659,
+      "learning_rate": 5.377114124638123e-05,
+      "loss": 0.6831,
+      "step": 6475
+    },
+    {
+      "epoch": 0.9605859574340347,
+      "grad_norm": 0.5992809534072876,
+      "learning_rate": 5.3580679567271066e-05,
+      "loss": 0.6984,
+      "step": 6500
+    },
+    {
+      "epoch": 0.9642805188087811,
+      "grad_norm": 0.6597899794578552,
+      "learning_rate": 5.339021788816091e-05,
+      "loss": 0.6893,
+      "step": 6525
+    },
+    {
+      "epoch": 0.9679750801835273,
+      "grad_norm": 0.6459916234016418,
+      "learning_rate": 5.3199756209050745e-05,
+      "loss": 0.6935,
+      "step": 6550
+    },
+    {
+      "epoch": 0.9716696415582736,
+      "grad_norm": 0.7714385986328125,
+      "learning_rate": 5.300929452994058e-05,
+      "loss": 0.6883,
+      "step": 6575
+    },
+    {
+      "epoch": 0.97536420293302,
+      "grad_norm": 0.5793107748031616,
+      "learning_rate": 5.281883285083041e-05,
+      "loss": 0.6795,
+      "step": 6600
+    },
+    {
+      "epoch": 0.9790587643077662,
+      "grad_norm": 0.5452476739883423,
+      "learning_rate": 5.262837117172025e-05,
+      "loss": 0.6809,
+      "step": 6625
+    },
+    {
+      "epoch": 0.9827533256825125,
+      "grad_norm": 0.6292601823806763,
+      "learning_rate": 5.2437909492610096e-05,
+      "loss": 0.7021,
+      "step": 6650
+    },
+    {
+      "epoch": 0.9864478870572587,
+      "grad_norm": 0.6509853601455688,
+      "learning_rate": 5.224744781349993e-05,
+      "loss": 0.6808,
+      "step": 6675
+    },
+    {
+      "epoch": 0.990142448432005,
+      "grad_norm": 0.6169773936271667,
+      "learning_rate": 5.205698613438976e-05,
+      "loss": 0.677,
+      "step": 6700
+    },
+    {
+      "epoch": 0.9938370098067514,
+      "grad_norm": 0.6769931316375732,
+      "learning_rate": 5.1866524455279594e-05,
+      "loss": 0.7188,
+      "step": 6725
+    },
+    {
+      "epoch": 0.9975315711814976,
+      "grad_norm": 0.6493127346038818,
+      "learning_rate": 5.167606277616944e-05,
+      "loss": 0.68,
+      "step": 6750
+    },
+    {
+      "epoch": 1.001182259639919,
+      "grad_norm": 0.6528682708740234,
+      "learning_rate": 5.148560109705928e-05,
+      "loss": 0.6982,
+      "step": 6775
+    },
+    {
+      "epoch": 1.004876821014665,
+      "grad_norm": 0.6537097692489624,
+      "learning_rate": 5.129513941794911e-05,
+      "loss": 0.6513,
+      "step": 6800
+    },
+    {
+      "epoch": 1.0085713823894114,
+      "grad_norm": 0.6426008939743042,
+      "learning_rate": 5.1104677738838945e-05,
+      "loss": 0.668,
+      "step": 6825
+    },
+    {
+      "epoch": 1.0122659437641577,
+      "grad_norm": 0.5742406249046326,
+      "learning_rate": 5.0914216059728784e-05,
+      "loss": 0.67,
+      "step": 6850
+    },
+    {
+      "epoch": 1.015960505138904,
+      "grad_norm": 0.7166649103164673,
+      "learning_rate": 5.0723754380618623e-05,
+      "loss": 0.6602,
+      "step": 6875
+    },
+    {
+      "epoch": 1.0196550665136503,
+      "grad_norm": 0.7485601305961609,
+      "learning_rate": 5.053329270150846e-05,
+      "loss": 0.6567,
+      "step": 6900
+    },
+    {
+      "epoch": 1.0233496278883965,
+      "grad_norm": 0.7126789689064026,
+      "learning_rate": 5.0342831022398296e-05,
+      "loss": 0.6624,
+      "step": 6925
+    },
+    {
+      "epoch": 1.0270441892631428,
+      "grad_norm": 0.7238374948501587,
+      "learning_rate": 5.015236934328813e-05,
+      "loss": 0.6613,
+      "step": 6950
+    },
+    {
+      "epoch": 1.0307387506378891,
+      "grad_norm": 0.6505608558654785,
+      "learning_rate": 4.996190766417797e-05,
+      "loss": 0.6554,
+      "step": 6975
+    },
+    {
+      "epoch": 1.0344333120126354,
+      "grad_norm": 0.6918332576751709,
+      "learning_rate": 4.977144598506781e-05,
+      "loss": 0.6645,
+      "step": 7000
+    },
+    {
+      "epoch": 1.0381278733873818,
+      "grad_norm": 0.5876255035400391,
+      "learning_rate": 4.9580984305957646e-05,
+      "loss": 0.6638,
+      "step": 7025
+    },
+    {
+      "epoch": 1.0418224347621279,
+      "grad_norm": 0.7554610967636108,
+      "learning_rate": 4.939052262684748e-05,
+      "loss": 0.6742,
+      "step": 7050
+    },
+    {
+      "epoch": 1.0455169961368742,
+      "grad_norm": 0.6300481557846069,
+      "learning_rate": 4.920006094773732e-05,
+      "loss": 0.6409,
+      "step": 7075
+    },
+    {
+      "epoch": 1.0492115575116205,
+      "grad_norm": 0.5924395322799683,
+      "learning_rate": 4.900959926862715e-05,
+      "loss": 0.668,
+      "step": 7100
+    },
+    {
+      "epoch": 1.0529061188863669,
+      "grad_norm": 0.6832597851753235,
+      "learning_rate": 4.881913758951699e-05,
+      "loss": 0.6431,
+      "step": 7125
+    },
+    {
+      "epoch": 1.0566006802611132,
+      "grad_norm": 0.702418863773346,
+      "learning_rate": 4.862867591040683e-05,
+      "loss": 0.6463,
+      "step": 7150
+    },
+    {
+      "epoch": 1.0602952416358593,
+      "grad_norm": 0.6264967918395996,
+      "learning_rate": 4.843821423129666e-05,
+      "loss": 0.653,
+      "step": 7175
+    },
+    {
+      "epoch": 1.0639898030106056,
+      "grad_norm": 0.6441030502319336,
+      "learning_rate": 4.82477525521865e-05,
+      "loss": 0.6415,
+      "step": 7200
+    },
+    {
+      "epoch": 1.067684364385352,
+      "grad_norm": 0.5445654392242432,
+      "learning_rate": 4.805729087307634e-05,
+      "loss": 0.6516,
+      "step": 7225
+    },
+    {
+      "epoch": 1.0713789257600983,
+      "grad_norm": 0.634982168674469,
+      "learning_rate": 4.786682919396618e-05,
+      "loss": 0.6617,
+      "step": 7250
+    },
+    {
+      "epoch": 1.0750734871348446,
+      "grad_norm": 0.5670004487037659,
+      "learning_rate": 4.7676367514856013e-05,
+      "loss": 0.644,
+      "step": 7275
+    },
+    {
+      "epoch": 1.0787680485095907,
+      "grad_norm": 0.6136172413825989,
+      "learning_rate": 4.7485905835745846e-05,
+      "loss": 0.6404,
+      "step": 7300
+    },
+    {
+      "epoch": 1.082462609884337,
+      "grad_norm": 0.6087863445281982,
+      "learning_rate": 4.7295444156635686e-05,
+      "loss": 0.666,
+      "step": 7325
+    },
+    {
+      "epoch": 1.0861571712590834,
+      "grad_norm": 0.54926997423172,
+      "learning_rate": 4.7104982477525525e-05,
+      "loss": 0.6157,
+      "step": 7350
+    },
+    {
+      "epoch": 1.0898517326338297,
+      "grad_norm": 0.6426320672035217,
+      "learning_rate": 4.6914520798415364e-05,
+      "loss": 0.6349,
+      "step": 7375
+    },
+    {
+      "epoch": 1.093546294008576,
+      "grad_norm": 0.5854539275169373,
+      "learning_rate": 4.67240591193052e-05,
+      "loss": 0.6583,
+      "step": 7400
+    },
+    {
+      "epoch": 1.0972408553833224,
+      "grad_norm": 0.7021641731262207,
+      "learning_rate": 4.6533597440195036e-05,
+      "loss": 0.6682,
+      "step": 7425
+    },
+    {
+      "epoch": 1.1009354167580685,
+      "grad_norm": 0.7356472611427307,
+      "learning_rate": 4.634313576108487e-05,
+      "loss": 0.6563,
+      "step": 7450
+    },
+    {
+      "epoch": 1.1046299781328148,
+      "grad_norm": 0.6147669553756714,
+      "learning_rate": 4.615267408197471e-05,
+      "loss": 0.667,
+      "step": 7475
+    },
+    {
+      "epoch": 1.1083245395075612,
+      "grad_norm": 0.6394315958023071,
+      "learning_rate": 4.596221240286455e-05,
+      "loss": 0.6737,
+      "step": 7500
+    },
+    {
+      "epoch": 1.1120191008823075,
+      "grad_norm": 0.7234614491462708,
+      "learning_rate": 4.577175072375438e-05,
+      "loss": 0.6556,
+      "step": 7525
+    },
+    {
+      "epoch": 1.1157136622570538,
+      "grad_norm": 0.6812229156494141,
+      "learning_rate": 4.558128904464422e-05,
+      "loss": 0.6544,
+      "step": 7550
+    },
+    {
+      "epoch": 1.1194082236318,
+      "grad_norm": 0.6218217611312866,
+      "learning_rate": 4.539082736553405e-05,
+      "loss": 0.668,
+      "step": 7575
+    },
+    {
+      "epoch": 1.1231027850065463,
+      "grad_norm": 0.8202681541442871,
+      "learning_rate": 4.52003656864239e-05,
+      "loss": 0.679,
+      "step": 7600
+    },
+    {
+      "epoch": 1.1267973463812926,
+      "grad_norm": 0.5360725522041321,
+      "learning_rate": 4.500990400731373e-05,
+      "loss": 0.6463,
+      "step": 7625
+    },
+    {
+      "epoch": 1.130491907756039,
+      "grad_norm": 0.6142716407775879,
+      "learning_rate": 4.481944232820357e-05,
+      "loss": 0.659,
+      "step": 7650
+    },
+    {
+      "epoch": 1.1341864691307852,
+      "grad_norm": 0.619349479675293,
+      "learning_rate": 4.4628980649093404e-05,
+      "loss": 0.6724,
+      "step": 7675
+    },
+    {
+      "epoch": 1.1378810305055314,
+      "grad_norm": 0.6891987323760986,
+      "learning_rate": 4.4438518969983236e-05,
+      "loss": 0.6509,
+      "step": 7700
+    },
+    {
+      "epoch": 1.1415755918802777,
+      "grad_norm": 0.7174720168113708,
+      "learning_rate": 4.424805729087308e-05,
+      "loss": 0.6715,
+      "step": 7725
+    },
+    {
+      "epoch": 1.145270153255024,
+      "grad_norm": 0.7424497008323669,
+      "learning_rate": 4.4057595611762915e-05,
+      "loss": 0.6449,
+      "step": 7750
+    },
+    {
+      "epoch": 1.1489647146297703,
+      "grad_norm": 0.6533998847007751,
+      "learning_rate": 4.3867133932652754e-05,
+      "loss": 0.6528,
+      "step": 7775
+    },
+    {
+      "epoch": 1.1526592760045167,
+      "grad_norm": 0.7500383853912354,
+      "learning_rate": 4.367667225354259e-05,
+      "loss": 0.6592,
+      "step": 7800
+    },
+    {
+      "epoch": 1.156353837379263,
+      "grad_norm": 0.6293950080871582,
+      "learning_rate": 4.3486210574432427e-05,
+      "loss": 0.6584,
+      "step": 7825
+    },
+    {
+      "epoch": 1.1600483987540091,
+      "grad_norm": 0.8463473320007324,
+      "learning_rate": 4.3295748895322266e-05,
+      "loss": 0.6656,
+      "step": 7850
+    },
+    {
+      "epoch": 1.1637429601287554,
+      "grad_norm": 0.6918061971664429,
+      "learning_rate": 4.31052872162121e-05,
+      "loss": 0.6603,
+      "step": 7875
+    },
+    {
+      "epoch": 1.1674375215035018,
+      "grad_norm": 0.5433516502380371,
+      "learning_rate": 4.291482553710194e-05,
+      "loss": 0.6422,
+      "step": 7900
+    },
+    {
+      "epoch": 1.171132082878248,
+      "grad_norm": 0.6414408087730408,
+      "learning_rate": 4.272436385799177e-05,
+      "loss": 0.6279,
+      "step": 7925
+    },
+    {
+      "epoch": 1.1748266442529944,
+      "grad_norm": 0.814218282699585,
+      "learning_rate": 4.253390217888161e-05,
+      "loss": 0.6673,
+      "step": 7950
+    },
+    {
+      "epoch": 1.1785212056277405,
+      "grad_norm": 0.7378386855125427,
+      "learning_rate": 4.234344049977145e-05,
+      "loss": 0.6651,
+      "step": 7975
+    },
+    {
+      "epoch": 1.1822157670024869,
+      "grad_norm": 0.6620386242866516,
+      "learning_rate": 4.215297882066129e-05,
+      "loss": 0.6984,
+      "step": 8000
+    },
+    {
+      "epoch": 1.1859103283772332,
+      "grad_norm": 0.6845581531524658,
+      "learning_rate": 4.196251714155112e-05,
+      "loss": 0.6524,
+      "step": 8025
+    },
+    {
+      "epoch": 1.1896048897519795,
+      "grad_norm": 0.7139785289764404,
+      "learning_rate": 4.1772055462440954e-05,
+      "loss": 0.6453,
+      "step": 8050
+    },
+    {
+      "epoch": 1.1932994511267259,
+      "grad_norm": 0.6536353230476379,
+      "learning_rate": 4.1581593783330794e-05,
+      "loss": 0.6456,
+      "step": 8075
+    },
+    {
+      "epoch": 1.196994012501472,
+      "grad_norm": 0.6225493550300598,
+      "learning_rate": 4.139113210422063e-05,
+      "loss": 0.6192,
+      "step": 8100
+    },
+    {
+      "epoch": 1.2006885738762183,
+      "grad_norm": 0.6810159683227539,
+      "learning_rate": 4.120067042511047e-05,
+      "loss": 0.6634,
+      "step": 8125
+    },
+    {
+      "epoch": 1.2043831352509646,
+      "grad_norm": 0.5847315788269043,
+      "learning_rate": 4.1010208746000305e-05,
+      "loss": 0.6231,
+      "step": 8150
+    },
+    {
+      "epoch": 1.208077696625711,
+      "grad_norm": 0.6385469436645508,
+      "learning_rate": 4.0819747066890144e-05,
+      "loss": 0.6619,
+      "step": 8175
+    },
+    {
+      "epoch": 1.2117722580004573,
+      "grad_norm": 0.7124472260475159,
+      "learning_rate": 4.0629285387779984e-05,
+      "loss": 0.6626,
+      "step": 8200
+    },
+    {
+      "epoch": 1.2154668193752034,
+      "grad_norm": 0.658824622631073,
+      "learning_rate": 4.0438823708669817e-05,
+      "loss": 0.6653,
+      "step": 8225
+    },
+    {
+      "epoch": 1.2191613807499497,
+      "grad_norm": 0.6626468300819397,
+      "learning_rate": 4.0248362029559656e-05,
+      "loss": 0.6777,
+      "step": 8250
+    },
+    {
+      "epoch": 1.222855942124696,
+      "grad_norm": 0.6238393783569336,
+      "learning_rate": 4.005790035044949e-05,
+      "loss": 0.6622,
+      "step": 8275
+    },
+    {
+      "epoch": 1.2265505034994424,
+      "grad_norm": 0.685213565826416,
+      "learning_rate": 3.986743867133933e-05,
+      "loss": 0.6423,
+      "step": 8300
+    },
+    {
+      "epoch": 1.2302450648741887,
+      "grad_norm": 0.7486940622329712,
+      "learning_rate": 3.967697699222917e-05,
+      "loss": 0.6631,
+      "step": 8325
+    },
+    {
+      "epoch": 1.2339396262489348,
+      "grad_norm": 0.7994277477264404,
+      "learning_rate": 3.948651531311901e-05,
+      "loss": 0.6725,
+      "step": 8350
+    },
+    {
+      "epoch": 1.2376341876236812,
+      "grad_norm": 0.6204445958137512,
+      "learning_rate": 3.929605363400884e-05,
+      "loss": 0.6411,
+      "step": 8375
+    },
+    {
+      "epoch": 1.2413287489984275,
+      "grad_norm": 0.7625504732131958,
+      "learning_rate": 3.910559195489867e-05,
+      "loss": 0.6819,
+      "step": 8400
+    },
+    {
+      "epoch": 1.2450233103731738,
+      "grad_norm": 0.6892343163490295,
+      "learning_rate": 3.891513027578851e-05,
+      "loss": 0.6614,
+      "step": 8425
+    },
+    {
+      "epoch": 1.2487178717479201,
+      "grad_norm": 0.6849514245986938,
+      "learning_rate": 3.872466859667835e-05,
+      "loss": 0.6442,
+      "step": 8450
+    },
+    {
+      "epoch": 1.2524124331226663,
+      "grad_norm": 0.7257765531539917,
+      "learning_rate": 3.853420691756819e-05,
+      "loss": 0.6475,
+      "step": 8475
+    },
+    {
+      "epoch": 1.2561069944974126,
+      "grad_norm": 0.7827818393707275,
+      "learning_rate": 3.834374523845802e-05,
+      "loss": 0.6317,
+      "step": 8500
+    },
+    {
+      "epoch": 1.259801555872159,
+      "grad_norm": 0.7970981597900391,
+      "learning_rate": 3.815328355934786e-05,
+      "loss": 0.6585,
+      "step": 8525
+    },
+    {
+      "epoch": 1.2634961172469052,
+      "grad_norm": 0.7086262106895447,
+      "learning_rate": 3.7962821880237695e-05,
+      "loss": 0.6499,
+      "step": 8550
+    },
+    {
+      "epoch": 1.2671906786216516,
+      "grad_norm": 0.654151439666748,
+      "learning_rate": 3.7772360201127535e-05,
+      "loss": 0.6587,
+      "step": 8575
+    },
+    {
+      "epoch": 1.2708852399963977,
+      "grad_norm": 0.6484542489051819,
+      "learning_rate": 3.7581898522017374e-05,
+      "loss": 0.6533,
+      "step": 8600
+    },
+    {
+      "epoch": 1.274579801371144,
+      "grad_norm": 0.5822983384132385,
+      "learning_rate": 3.7391436842907207e-05,
+      "loss": 0.6535,
+      "step": 8625
+    },
+    {
+      "epoch": 1.2782743627458903,
+      "grad_norm": 0.6506041884422302,
+      "learning_rate": 3.7200975163797046e-05,
+      "loss": 0.6527,
+      "step": 8650
+    },
+    {
+      "epoch": 1.2819689241206367,
+      "grad_norm": 0.6804136037826538,
+      "learning_rate": 3.701051348468688e-05,
+      "loss": 0.642,
+      "step": 8675
+    },
+    {
+      "epoch": 1.285663485495383,
+      "grad_norm": 0.7997829914093018,
+      "learning_rate": 3.6820051805576725e-05,
+      "loss": 0.6489,
+      "step": 8700
+    },
+    {
+      "epoch": 1.2893580468701291,
+      "grad_norm": 0.7355867028236389,
+      "learning_rate": 3.662959012646656e-05,
+      "loss": 0.6777,
+      "step": 8725
+    },
+    {
+      "epoch": 1.2930526082448754,
+      "grad_norm": 9.047796249389648,
+      "learning_rate": 3.643912844735639e-05,
+      "loss": 0.6777,
+      "step": 8750
+    },
+    {
+      "epoch": 1.2967471696196218,
+      "grad_norm": 0.7236223220825195,
+      "learning_rate": 3.624866676824623e-05,
+      "loss": 0.6777,
+      "step": 8775
+    },
+    {
+      "epoch": 1.300441730994368,
+      "grad_norm": 0.6845753192901611,
+      "learning_rate": 3.605820508913607e-05,
+      "loss": 0.6284,
+      "step": 8800
+    },
+    {
+      "epoch": 1.3041362923691144,
+      "grad_norm": 0.7639452815055847,
+      "learning_rate": 3.586774341002591e-05,
+      "loss": 0.6822,
+      "step": 8825
+    },
+    {
+      "epoch": 1.3078308537438605,
+      "grad_norm": 0.6909865736961365,
+      "learning_rate": 3.567728173091574e-05,
+      "loss": 0.6737,
+      "step": 8850
+    },
+    {
+      "epoch": 1.311525415118607,
+      "grad_norm": 0.6128563284873962,
+      "learning_rate": 3.548682005180558e-05,
+      "loss": 0.666,
+      "step": 8875
+    },
+    {
+      "epoch": 1.3152199764933532,
+      "grad_norm": 0.7517656087875366,
+      "learning_rate": 3.529635837269541e-05,
+      "loss": 0.6389,
+      "step": 8900
+    },
+    {
+      "epoch": 1.3189145378680995,
+      "grad_norm": 0.7127660512924194,
+      "learning_rate": 3.510589669358525e-05,
+      "loss": 0.6334,
+      "step": 8925
+    },
+    {
+      "epoch": 1.3226090992428459,
+      "grad_norm": 0.7129451632499695,
+      "learning_rate": 3.491543501447509e-05,
+      "loss": 0.6545,
+      "step": 8950
+    },
+    {
+      "epoch": 1.3263036606175922,
+      "grad_norm": 0.7367307543754578,
+      "learning_rate": 3.4724973335364925e-05,
+      "loss": 0.6329,
+      "step": 8975
+    },
+    {
+      "epoch": 1.3299982219923385,
+      "grad_norm": 0.7707272171974182,
+      "learning_rate": 3.4534511656254764e-05,
+      "loss": 0.6469,
+      "step": 9000
+    },
+    {
+      "epoch": 1.3336927833670846,
+      "grad_norm": 0.5796623826026917,
+      "learning_rate": 3.43440499771446e-05,
+      "loss": 0.6533,
+      "step": 9025
+    },
+    {
+      "epoch": 1.337387344741831,
+      "grad_norm": 210.8633270263672,
+      "learning_rate": 3.4153588298034436e-05,
+      "loss": 0.663,
+      "step": 9050
+    },
+    {
+      "epoch": 1.3410819061165773,
+      "grad_norm": 0.6077564358711243,
+      "learning_rate": 3.3963126618924275e-05,
+      "loss": 0.6529,
+      "step": 9075
+    },
+    {
+      "epoch": 1.3447764674913236,
+      "grad_norm": 0.5756903290748596,
+      "learning_rate": 3.3772664939814115e-05,
+      "loss": 0.6379,
+      "step": 9100
+    },
+    {
+      "epoch": 1.34847102886607,
+      "grad_norm": 0.6951320171356201,
+      "learning_rate": 3.358220326070395e-05,
+      "loss": 0.6572,
+      "step": 9125
+    },
+    {
+      "epoch": 1.352165590240816,
+      "grad_norm": 0.654563307762146,
+      "learning_rate": 3.339174158159378e-05,
+      "loss": 0.6571,
+      "step": 9150
+    },
+    {
+      "epoch": 1.3558601516155624,
+      "grad_norm": 0.8268250823020935,
+      "learning_rate": 3.320127990248362e-05,
+      "loss": 0.6952,
+      "step": 9175
+    },
+    {
+      "epoch": 1.3595547129903087,
+      "grad_norm": 0.7915245890617371,
+      "learning_rate": 3.301081822337346e-05,
+      "loss": 0.6442,
+      "step": 9200
+    },
+    {
+      "epoch": 1.363249274365055,
+      "grad_norm": 0.7299513816833496,
+      "learning_rate": 3.28203565442633e-05,
+      "loss": 0.6347,
+      "step": 9225
+    },
+    {
+      "epoch": 1.3669438357398014,
+      "grad_norm": 0.6474806070327759,
+      "learning_rate": 3.262989486515313e-05,
+      "loss": 0.6604,
+      "step": 9250
+    },
+    {
+      "epoch": 1.3706383971145475,
+      "grad_norm": 0.6813268661499023,
+      "learning_rate": 3.243943318604297e-05,
+      "loss": 0.66,
+      "step": 9275
+    },
+    {
+      "epoch": 1.3743329584892938,
+      "grad_norm": 0.7166799306869507,
+      "learning_rate": 3.224897150693281e-05,
+      "loss": 0.6689,
+      "step": 9300
+    },
+    {
+      "epoch": 1.3780275198640402,
+      "grad_norm": 0.6958301663398743,
+      "learning_rate": 3.205850982782264e-05,
+      "loss": 0.6512,
+      "step": 9325
+    },
+    {
+      "epoch": 1.3817220812387865,
+      "grad_norm": 0.8137691617012024,
+      "learning_rate": 3.186804814871248e-05,
+      "loss": 0.6691,
+      "step": 9350
+    },
+    {
+      "epoch": 1.3854166426135328,
+      "grad_norm": 0.6115707159042358,
+      "learning_rate": 3.1677586469602315e-05,
+      "loss": 0.6733,
+      "step": 9375
+    },
+    {
+      "epoch": 1.389111203988279,
+      "grad_norm": 0.7478678822517395,
+      "learning_rate": 3.1487124790492154e-05,
+      "loss": 0.6514,
+      "step": 9400
+    },
+    {
+      "epoch": 1.3928057653630252,
+      "grad_norm": 0.7280460000038147,
+      "learning_rate": 3.1296663111381993e-05,
+      "loss": 0.6375,
+      "step": 9425
+    },
+    {
+      "epoch": 1.3965003267377716,
+      "grad_norm": 0.6709932088851929,
+      "learning_rate": 3.110620143227183e-05,
+      "loss": 0.6843,
+      "step": 9450
+    },
+    {
+      "epoch": 1.400194888112518,
+      "grad_norm": 0.6445898413658142,
+      "learning_rate": 3.0915739753161666e-05,
+      "loss": 0.6395,
+      "step": 9475
+    },
+    {
+      "epoch": 1.4038894494872642,
+      "grad_norm": 0.6072065830230713,
+      "learning_rate": 3.07252780740515e-05,
+      "loss": 0.6615,
+      "step": 9500
+    },
+    {
+      "epoch": 1.4075840108620103,
+      "grad_norm": 0.7841944098472595,
+      "learning_rate": 3.053481639494134e-05,
+      "loss": 0.6388,
+      "step": 9525
+    },
+    {
+      "epoch": 1.4112785722367567,
+      "grad_norm": 0.7215288281440735,
+      "learning_rate": 3.0344354715831174e-05,
+      "loss": 0.6694,
+      "step": 9550
+    },
+    {
+      "epoch": 1.414973133611503,
+      "grad_norm": 0.5916579961776733,
+      "learning_rate": 3.0153893036721016e-05,
+      "loss": 0.7004,
+      "step": 9575
+    },
+    {
+      "epoch": 1.4186676949862493,
+      "grad_norm": 0.6357461214065552,
+      "learning_rate": 2.996343135761085e-05,
+      "loss": 0.6416,
+      "step": 9600
+    },
+    {
+      "epoch": 1.4223622563609957,
+      "grad_norm": 0.735261857509613,
+      "learning_rate": 2.977296967850069e-05,
+      "loss": 0.6374,
+      "step": 9625
+    },
+    {
+      "epoch": 1.4260568177357418,
+      "grad_norm": 0.7285844087600708,
+      "learning_rate": 2.9582507999390525e-05,
+      "loss": 0.6448,
+      "step": 9650
+    },
+    {
+      "epoch": 1.429751379110488,
+      "grad_norm": 0.7573617100715637,
+      "learning_rate": 2.9392046320280357e-05,
+      "loss": 0.6672,
+      "step": 9675
+    },
+    {
+      "epoch": 1.4334459404852344,
+      "grad_norm": 0.5082629919052124,
+      "learning_rate": 2.92015846411702e-05,
+      "loss": 0.6514,
+      "step": 9700
+    },
+    {
+      "epoch": 1.4371405018599808,
+      "grad_norm": 0.6786466836929321,
+      "learning_rate": 2.9011122962060033e-05,
+      "loss": 0.6542,
+      "step": 9725
+    },
+    {
+      "epoch": 1.440835063234727,
+      "grad_norm": 0.6085937023162842,
+      "learning_rate": 2.8820661282949872e-05,
+      "loss": 0.6581,
+      "step": 9750
+    },
+    {
+      "epoch": 1.4445296246094732,
+      "grad_norm": 0.6520203351974487,
+      "learning_rate": 2.8630199603839708e-05,
+      "loss": 0.6469,
+      "step": 9775
+    },
+    {
+      "epoch": 1.4482241859842195,
+      "grad_norm": 0.5597354769706726,
+      "learning_rate": 2.8439737924729548e-05,
+      "loss": 0.6418,
+      "step": 9800
+    },
+    {
+      "epoch": 1.4519187473589659,
+      "grad_norm": 0.6233022809028625,
+      "learning_rate": 2.8249276245619384e-05,
+      "loss": 0.6371,
+      "step": 9825
+    },
+    {
+      "epoch": 1.4556133087337122,
+      "grad_norm": 0.880703866481781,
+      "learning_rate": 2.8058814566509216e-05,
+      "loss": 0.6647,
+      "step": 9850
+    },
+    {
+      "epoch": 1.4593078701084585,
+      "grad_norm": 0.6821489334106445,
+      "learning_rate": 2.786835288739906e-05,
+      "loss": 0.6545,
+      "step": 9875
+    },
+    {
+      "epoch": 1.4630024314832046,
+      "grad_norm": 0.6734182834625244,
+      "learning_rate": 2.767789120828889e-05,
+      "loss": 0.6385,
+      "step": 9900
+    },
+    {
+      "epoch": 1.466696992857951,
+      "grad_norm": 0.8161661028862,
+      "learning_rate": 2.748742952917873e-05,
+      "loss": 0.6526,
+      "step": 9925
+    },
+    {
+      "epoch": 1.4703915542326973,
+      "grad_norm": 0.6308382153511047,
+      "learning_rate": 2.7296967850068567e-05,
+      "loss": 0.6561,
+      "step": 9950
+    },
+    {
+      "epoch": 1.4740861156074436,
+      "grad_norm": 0.791493833065033,
+      "learning_rate": 2.7106506170958406e-05,
+      "loss": 0.6607,
+      "step": 9975
+    },
+    {
+      "epoch": 1.47778067698219,
+      "grad_norm": 0.7888880372047424,
+      "learning_rate": 2.6916044491848243e-05,
+      "loss": 0.6511,
+      "step": 10000
+    },
+    {
+      "epoch": 1.481475238356936,
+      "grad_norm": 0.7792957425117493,
+      "learning_rate": 2.6725582812738075e-05,
+      "loss": 0.6522,
+      "step": 10025
+    },
+    {
+      "epoch": 1.4851697997316826,
+      "grad_norm": 0.6947233080863953,
+      "learning_rate": 2.6535121133627915e-05,
+      "loss": 0.6412,
+      "step": 10050
+    },
+    {
+      "epoch": 1.4888643611064287,
+      "grad_norm": 0.6176926493644714,
+      "learning_rate": 2.634465945451775e-05,
+      "loss": 0.6486,
+      "step": 10075
+    },
+    {
+      "epoch": 1.492558922481175,
+      "grad_norm": 0.700943112373352,
+      "learning_rate": 2.615419777540759e-05,
+      "loss": 0.6475,
+      "step": 10100
+    },
+    {
+      "epoch": 1.4962534838559214,
+      "grad_norm": 0.6516005396842957,
+      "learning_rate": 2.5963736096297426e-05,
+      "loss": 0.6589,
+      "step": 10125
+    },
+    {
+      "epoch": 1.4999480452306675,
+      "grad_norm": 0.8346360921859741,
+      "learning_rate": 2.5773274417187265e-05,
+      "loss": 0.6444,
+      "step": 10150
+    },
+    {
+      "epoch": 1.503642606605414,
+      "grad_norm": 0.6748323440551758,
+      "learning_rate": 2.55828127380771e-05,
+      "loss": 0.6539,
+      "step": 10175
+    },
+    {
+      "epoch": 1.5073371679801602,
+      "grad_norm": 0.6239715814590454,
+      "learning_rate": 2.5392351058966934e-05,
+      "loss": 0.6137,
+      "step": 10200
+    },
+    {
+      "epoch": 1.5110317293549065,
+      "grad_norm": 0.7011853456497192,
+      "learning_rate": 2.5201889379856774e-05,
+      "loss": 0.6415,
+      "step": 10225
+    },
+    {
+      "epoch": 1.5147262907296528,
+      "grad_norm": 0.6292597055435181,
+      "learning_rate": 2.501142770074661e-05,
+      "loss": 0.6341,
+      "step": 10250
+    },
+    {
+      "epoch": 1.518420852104399,
+      "grad_norm": 0.7244909405708313,
+      "learning_rate": 2.482096602163645e-05,
+      "loss": 0.658,
+      "step": 10275
+    },
+    {
+      "epoch": 1.5221154134791455,
+      "grad_norm": 0.6337189674377441,
+      "learning_rate": 2.4630504342526285e-05,
+      "loss": 0.6804,
+      "step": 10300
+    },
+    {
+      "epoch": 1.5258099748538916,
+      "grad_norm": 0.720902681350708,
+      "learning_rate": 2.444004266341612e-05,
+      "loss": 0.6819,
+      "step": 10325
+    },
+    {
+      "epoch": 1.529504536228638,
+      "grad_norm": 0.5961156487464905,
+      "learning_rate": 2.4249580984305957e-05,
+      "loss": 0.6417,
+      "step": 10350
+    },
+    {
+      "epoch": 1.5331990976033842,
+      "grad_norm": 0.8305853605270386,
+      "learning_rate": 2.4059119305195797e-05,
+      "loss": 0.6694,
+      "step": 10375
+    },
+    {
+      "epoch": 1.5368936589781304,
+      "grad_norm": 0.7062313556671143,
+      "learning_rate": 2.3868657626085633e-05,
+      "loss": 0.6587,
+      "step": 10400
+    },
+    {
+      "epoch": 1.540588220352877,
+      "grad_norm": 0.6674323081970215,
+      "learning_rate": 2.3678195946975472e-05,
+      "loss": 0.6557,
+      "step": 10425
+    },
+    {
+      "epoch": 1.544282781727623,
+      "grad_norm": 0.7407240271568298,
+      "learning_rate": 2.3487734267865308e-05,
+      "loss": 0.6599,
+      "step": 10450
+    },
+    {
+      "epoch": 1.5479773431023693,
+      "grad_norm": 0.783926248550415,
+      "learning_rate": 2.3297272588755144e-05,
+      "loss": 0.6616,
+      "step": 10475
+    },
+    {
+      "epoch": 1.5516719044771157,
+      "grad_norm": 0.6342896819114685,
+      "learning_rate": 2.310681090964498e-05,
+      "loss": 0.6747,
+      "step": 10500
+    },
+    {
+      "epoch": 1.5553664658518618,
+      "grad_norm": 0.6193211674690247,
+      "learning_rate": 2.2916349230534816e-05,
+      "loss": 0.6294,
+      "step": 10525
+    },
+    {
+      "epoch": 1.5590610272266083,
+      "grad_norm": 0.6950103640556335,
+      "learning_rate": 2.2725887551424656e-05,
+      "loss": 0.6483,
+      "step": 10550
+    },
+    {
+      "epoch": 1.5627555886013544,
+      "grad_norm": 0.7468893527984619,
+      "learning_rate": 2.253542587231449e-05,
+      "loss": 0.6542,
+      "step": 10575
+    },
+    {
+      "epoch": 1.5664501499761008,
+      "grad_norm": 0.6315162777900696,
+      "learning_rate": 2.2344964193204328e-05,
+      "loss": 0.6576,
+      "step": 10600
+    },
+    {
+      "epoch": 1.570144711350847,
+      "grad_norm": 0.7328910231590271,
+      "learning_rate": 2.2154502514094167e-05,
+      "loss": 0.6643,
+      "step": 10625
+    },
+    {
+      "epoch": 1.5738392727255934,
+      "grad_norm": 0.7641509771347046,
+      "learning_rate": 2.1964040834984e-05,
+      "loss": 0.6406,
+      "step": 10650
+    },
+    {
+      "epoch": 1.5775338341003398,
+      "grad_norm": 0.6303021311759949,
+      "learning_rate": 2.177357915587384e-05,
+      "loss": 0.6414,
+      "step": 10675
+    },
+    {
+      "epoch": 1.5812283954750859,
+      "grad_norm": 0.7340176701545715,
+      "learning_rate": 2.1583117476763675e-05,
+      "loss": 0.6676,
+      "step": 10700
+    },
+    {
+      "epoch": 1.5849229568498322,
+      "grad_norm": 0.7646533846855164,
+      "learning_rate": 2.1392655797653515e-05,
+      "loss": 0.6595,
+      "step": 10725
+    },
+    {
+      "epoch": 1.5886175182245785,
+      "grad_norm": 0.6361941695213318,
+      "learning_rate": 2.120219411854335e-05,
+      "loss": 0.6683,
+      "step": 10750
+    },
+    {
+      "epoch": 1.5923120795993249,
+      "grad_norm": 0.7954297065734863,
+      "learning_rate": 2.1011732439433187e-05,
+      "loss": 0.6389,
+      "step": 10775
+    },
+    {
+      "epoch": 1.5960066409740712,
+      "grad_norm": 0.6926315426826477,
+      "learning_rate": 2.0821270760323026e-05,
+      "loss": 0.6377,
+      "step": 10800
+    },
+    {
+      "epoch": 1.5997012023488173,
+      "grad_norm": 0.7757145762443542,
+      "learning_rate": 2.063080908121286e-05,
+      "loss": 0.6499,
+      "step": 10825
+    },
+    {
+      "epoch": 1.6033957637235636,
+      "grad_norm": 0.6862484812736511,
+      "learning_rate": 2.0440347402102698e-05,
+      "loss": 0.6465,
+      "step": 10850
+    },
+    {
+      "epoch": 1.60709032509831,
+      "grad_norm": 0.7413581013679504,
+      "learning_rate": 2.0249885722992534e-05,
+      "loss": 0.628,
+      "step": 10875
+    },
+    {
+      "epoch": 1.6107848864730563,
+      "grad_norm": 0.7850485444068909,
+      "learning_rate": 2.005942404388237e-05,
+      "loss": 0.6648,
+      "step": 10900
+    },
+    {
+      "epoch": 1.6144794478478026,
+      "grad_norm": 0.6554867029190063,
+      "learning_rate": 1.986896236477221e-05,
+      "loss": 0.6386,
+      "step": 10925
+    },
+    {
+      "epoch": 1.6181740092225487,
+      "grad_norm": 0.6911448836326599,
+      "learning_rate": 1.9678500685662046e-05,
+      "loss": 0.6474,
+      "step": 10950
+    },
+    {
+      "epoch": 1.6218685705972953,
+      "grad_norm": 0.838879406452179,
+      "learning_rate": 1.9488039006551885e-05,
+      "loss": 0.6406,
+      "step": 10975
+    },
+    {
+      "epoch": 1.6255631319720414,
+      "grad_norm": 0.678164005279541,
+      "learning_rate": 1.929757732744172e-05,
+      "loss": 0.6462,
+      "step": 11000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 13532,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.400437197467376e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-11000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddec6eef92f76dd21b66ba65fc3f8486e2d925551fb3a26f493b39225b02363f
+size 5969

checkpoint-12000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Qwen3-8B-Base
+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 0.15.2

checkpoint-12000/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen3-8B-Base",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-12000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5e8edc45c0b1526092c10ed430cec82a6166a7de0705b3df93813989a1b46a2
+size 2838563408

checkpoint-12000/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
+}

checkpoint-12000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc8e504029ba1a09e845baa394a468590e1ba5ccab3db39116c7d85d0c1731bc
+size 2706136909

checkpoint-12000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de69a2834426ff9ef8199d077e00892579278af31d8969d77f98235b5cfc010a
+size 14645

checkpoint-12000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fb63a0d7544f9719b5d1dd3cc0ef925a617eed672dfb021b0147d8e500d785b
+size 1465

checkpoint-12000/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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-12000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-12000/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 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.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').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        {{- 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    {%- 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": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-12000/trainer_state.json

@@ -0,0 +1,3394 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.7733455869618928,
+  "eval_steps": 500,
+  "global_step": 12000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0036945613747462877,
+      "grad_norm": 2.2292165756225586,
+      "learning_rate": 5.911330049261084e-06,
+      "loss": 0.9395,
+      "step": 25
+    },
+    {
+      "epoch": 0.007389122749492575,
+      "grad_norm": 0.8381065130233765,
+      "learning_rate": 1.206896551724138e-05,
+      "loss": 0.89,
+      "step": 50
+    },
+    {
+      "epoch": 0.011083684124238862,
+      "grad_norm": 0.9238471984863281,
+      "learning_rate": 1.8226600985221676e-05,
+      "loss": 0.8384,
+      "step": 75
+    },
+    {
+      "epoch": 0.01477824549898515,
+      "grad_norm": 0.6837311387062073,
+      "learning_rate": 2.438423645320197e-05,
+      "loss": 0.784,
+      "step": 100
+    },
+    {
+      "epoch": 0.01847280687373144,
+      "grad_norm": 0.7093706727027893,
+      "learning_rate": 3.0541871921182266e-05,
+      "loss": 0.7675,
+      "step": 125
+    },
+    {
+      "epoch": 0.022167368248477724,
+      "grad_norm": 0.6208077073097229,
+      "learning_rate": 3.669950738916256e-05,
+      "loss": 0.7466,
+      "step": 150
+    },
+    {
+      "epoch": 0.025861929623224013,
+      "grad_norm": 0.8929094076156616,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 0.7386,
+      "step": 175
+    },
+    {
+      "epoch": 0.0295564909979703,
+      "grad_norm": 0.7828120589256287,
+      "learning_rate": 4.901477832512316e-05,
+      "loss": 0.7173,
+      "step": 200
+    },
+    {
+      "epoch": 0.03325105237271659,
+      "grad_norm": 0.7134449481964111,
+      "learning_rate": 5.517241379310345e-05,
+      "loss": 0.7108,
+      "step": 225
+    },
+    {
+      "epoch": 0.03694561374746288,
+      "grad_norm": 0.7464851140975952,
+      "learning_rate": 6.133004926108375e-05,
+      "loss": 0.7332,
+      "step": 250
+    },
+    {
+      "epoch": 0.04064017512220916,
+      "grad_norm": 0.677793025970459,
+      "learning_rate": 6.748768472906404e-05,
+      "loss": 0.7194,
+      "step": 275
+    },
+    {
+      "epoch": 0.04433473649695545,
+      "grad_norm": 0.7936354875564575,
+      "learning_rate": 7.364532019704434e-05,
+      "loss": 0.7253,
+      "step": 300
+    },
+    {
+      "epoch": 0.04802929787170174,
+      "grad_norm": 0.6711100935935974,
+      "learning_rate": 7.980295566502463e-05,
+      "loss": 0.7018,
+      "step": 325
+    },
+    {
+      "epoch": 0.051723859246448026,
+      "grad_norm": 0.5816489458084106,
+      "learning_rate": 8.596059113300493e-05,
+      "loss": 0.7298,
+      "step": 350
+    },
+    {
+      "epoch": 0.055418420621194314,
+      "grad_norm": 0.6680681705474854,
+      "learning_rate": 9.211822660098522e-05,
+      "loss": 0.7149,
+      "step": 375
+    },
+    {
+      "epoch": 0.0591129819959406,
+      "grad_norm": 0.5643934607505798,
+      "learning_rate": 9.827586206896552e-05,
+      "loss": 0.763,
+      "step": 400
+    },
+    {
+      "epoch": 0.06280754337068689,
+      "grad_norm": 0.5739309191703796,
+      "learning_rate": 9.986286759104069e-05,
+      "loss": 0.7345,
+      "step": 425
+    },
+    {
+      "epoch": 0.06650210474543318,
+      "grad_norm": 0.5929909944534302,
+      "learning_rate": 9.967240591193052e-05,
+      "loss": 0.7364,
+      "step": 450
+    },
+    {
+      "epoch": 0.07019666612017947,
+      "grad_norm": 0.609235405921936,
+      "learning_rate": 9.948194423282036e-05,
+      "loss": 0.7294,
+      "step": 475
+    },
+    {
+      "epoch": 0.07389122749492576,
+      "grad_norm": 0.4643324613571167,
+      "learning_rate": 9.92914825537102e-05,
+      "loss": 0.7344,
+      "step": 500
+    },
+    {
+      "epoch": 0.07758578886967203,
+      "grad_norm": 0.5267598032951355,
+      "learning_rate": 9.910102087460003e-05,
+      "loss": 0.7249,
+      "step": 525
+    },
+    {
+      "epoch": 0.08128035024441832,
+      "grad_norm": 0.47951069474220276,
+      "learning_rate": 9.891055919548987e-05,
+      "loss": 0.7256,
+      "step": 550
+    },
+    {
+      "epoch": 0.08497491161916461,
+      "grad_norm": 0.4505012333393097,
+      "learning_rate": 9.87200975163797e-05,
+      "loss": 0.7359,
+      "step": 575
+    },
+    {
+      "epoch": 0.0886694729939109,
+      "grad_norm": 0.5320091247558594,
+      "learning_rate": 9.852963583726955e-05,
+      "loss": 0.6856,
+      "step": 600
+    },
+    {
+      "epoch": 0.09236403436865719,
+      "grad_norm": 0.5583036541938782,
+      "learning_rate": 9.833917415815939e-05,
+      "loss": 0.7235,
+      "step": 625
+    },
+    {
+      "epoch": 0.09605859574340347,
+      "grad_norm": 0.5139252543449402,
+      "learning_rate": 9.814871247904922e-05,
+      "loss": 0.7272,
+      "step": 650
+    },
+    {
+      "epoch": 0.09975315711814976,
+      "grad_norm": 0.4989326000213623,
+      "learning_rate": 9.795825079993906e-05,
+      "loss": 0.6952,
+      "step": 675
+    },
+    {
+      "epoch": 0.10344771849289605,
+      "grad_norm": 0.47355732321739197,
+      "learning_rate": 9.776778912082889e-05,
+      "loss": 0.7266,
+      "step": 700
+    },
+    {
+      "epoch": 0.10714227986764234,
+      "grad_norm": 0.3588508367538452,
+      "learning_rate": 9.757732744171874e-05,
+      "loss": 0.7406,
+      "step": 725
+    },
+    {
+      "epoch": 0.11083684124238863,
+      "grad_norm": 0.4120556712150574,
+      "learning_rate": 9.738686576260857e-05,
+      "loss": 0.7443,
+      "step": 750
+    },
+    {
+      "epoch": 0.11453140261713492,
+      "grad_norm": 0.5160555839538574,
+      "learning_rate": 9.71964040834984e-05,
+      "loss": 0.7134,
+      "step": 775
+    },
+    {
+      "epoch": 0.1182259639918812,
+      "grad_norm": 0.5423145890235901,
+      "learning_rate": 9.700594240438823e-05,
+      "loss": 0.7289,
+      "step": 800
+    },
+    {
+      "epoch": 0.1219205253666275,
+      "grad_norm": 0.5352346301078796,
+      "learning_rate": 9.681548072527808e-05,
+      "loss": 0.7144,
+      "step": 825
+    },
+    {
+      "epoch": 0.12561508674137378,
+      "grad_norm": 0.47908860445022583,
+      "learning_rate": 9.662501904616791e-05,
+      "loss": 0.7175,
+      "step": 850
+    },
+    {
+      "epoch": 0.12930964811612006,
+      "grad_norm": 0.47986069321632385,
+      "learning_rate": 9.643455736705776e-05,
+      "loss": 0.6983,
+      "step": 875
+    },
+    {
+      "epoch": 0.13300420949086636,
+      "grad_norm": 0.6903620958328247,
+      "learning_rate": 9.624409568794759e-05,
+      "loss": 0.7086,
+      "step": 900
+    },
+    {
+      "epoch": 0.13669877086561263,
+      "grad_norm": 0.44413208961486816,
+      "learning_rate": 9.605363400883742e-05,
+      "loss": 0.7306,
+      "step": 925
+    },
+    {
+      "epoch": 0.14039333224035894,
+      "grad_norm": 0.4634678065776825,
+      "learning_rate": 9.586317232972727e-05,
+      "loss": 0.7061,
+      "step": 950
+    },
+    {
+      "epoch": 0.1440878936151052,
+      "grad_norm": 0.5110129714012146,
+      "learning_rate": 9.56727106506171e-05,
+      "loss": 0.7406,
+      "step": 975
+    },
+    {
+      "epoch": 0.1477824549898515,
+      "grad_norm": 0.5460866093635559,
+      "learning_rate": 9.548224897150694e-05,
+      "loss": 0.721,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1514770163645978,
+      "grad_norm": 0.5179885029792786,
+      "learning_rate": 9.529178729239677e-05,
+      "loss": 0.7068,
+      "step": 1025
+    },
+    {
+      "epoch": 0.15517157773934406,
+      "grad_norm": 0.40280836820602417,
+      "learning_rate": 9.51013256132866e-05,
+      "loss": 0.7009,
+      "step": 1050
+    },
+    {
+      "epoch": 0.15886613911409037,
+      "grad_norm": 1.2706756591796875,
+      "learning_rate": 9.491086393417645e-05,
+      "loss": 0.7125,
+      "step": 1075
+    },
+    {
+      "epoch": 0.16256070048883664,
+      "grad_norm": 0.4963163435459137,
+      "learning_rate": 9.47204022550663e-05,
+      "loss": 0.7149,
+      "step": 1100
+    },
+    {
+      "epoch": 0.16625526186358294,
+      "grad_norm": 0.5147728323936462,
+      "learning_rate": 9.452994057595613e-05,
+      "loss": 0.7245,
+      "step": 1125
+    },
+    {
+      "epoch": 0.16994982323832922,
+      "grad_norm": 0.5933899879455566,
+      "learning_rate": 9.433947889684596e-05,
+      "loss": 0.7261,
+      "step": 1150
+    },
+    {
+      "epoch": 0.17364438461307552,
+      "grad_norm": 0.4750466048717499,
+      "learning_rate": 9.414901721773579e-05,
+      "loss": 0.7206,
+      "step": 1175
+    },
+    {
+      "epoch": 0.1773389459878218,
+      "grad_norm": 0.46546968817710876,
+      "learning_rate": 9.395855553862564e-05,
+      "loss": 0.7121,
+      "step": 1200
+    },
+    {
+      "epoch": 0.1810335073625681,
+      "grad_norm": 0.6512172818183899,
+      "learning_rate": 9.376809385951547e-05,
+      "loss": 0.7212,
+      "step": 1225
+    },
+    {
+      "epoch": 0.18472806873731437,
+      "grad_norm": 0.34932607412338257,
+      "learning_rate": 9.35776321804053e-05,
+      "loss": 0.704,
+      "step": 1250
+    },
+    {
+      "epoch": 0.18842263011206067,
+      "grad_norm": 0.4648846983909607,
+      "learning_rate": 9.338717050129514e-05,
+      "loss": 0.7419,
+      "step": 1275
+    },
+    {
+      "epoch": 0.19211719148680695,
+      "grad_norm": 0.4566064774990082,
+      "learning_rate": 9.319670882218498e-05,
+      "loss": 0.7318,
+      "step": 1300
+    },
+    {
+      "epoch": 0.19581175286155325,
+      "grad_norm": 0.5357668399810791,
+      "learning_rate": 9.300624714307481e-05,
+      "loss": 0.6973,
+      "step": 1325
+    },
+    {
+      "epoch": 0.19950631423629953,
+      "grad_norm": 0.4423241913318634,
+      "learning_rate": 9.281578546396466e-05,
+      "loss": 0.7298,
+      "step": 1350
+    },
+    {
+      "epoch": 0.20320087561104583,
+      "grad_norm": 0.4530033767223358,
+      "learning_rate": 9.26253237848545e-05,
+      "loss": 0.7161,
+      "step": 1375
+    },
+    {
+      "epoch": 0.2068954369857921,
+      "grad_norm": 0.4678841233253479,
+      "learning_rate": 9.243486210574433e-05,
+      "loss": 0.6972,
+      "step": 1400
+    },
+    {
+      "epoch": 0.21058999836053838,
+      "grad_norm": 0.6039907336235046,
+      "learning_rate": 9.224440042663417e-05,
+      "loss": 0.7165,
+      "step": 1425
+    },
+    {
+      "epoch": 0.21428455973528468,
+      "grad_norm": 0.4463271498680115,
+      "learning_rate": 9.2053938747524e-05,
+      "loss": 0.6863,
+      "step": 1450
+    },
+    {
+      "epoch": 0.21797912111003095,
+      "grad_norm": 0.5739301443099976,
+      "learning_rate": 9.186347706841384e-05,
+      "loss": 0.6907,
+      "step": 1475
+    },
+    {
+      "epoch": 0.22167368248477726,
+      "grad_norm": 0.4577805697917938,
+      "learning_rate": 9.167301538930367e-05,
+      "loss": 0.7114,
+      "step": 1500
+    },
+    {
+      "epoch": 0.22536824385952353,
+      "grad_norm": 0.4522150158882141,
+      "learning_rate": 9.14825537101935e-05,
+      "loss": 0.6877,
+      "step": 1525
+    },
+    {
+      "epoch": 0.22906280523426983,
+      "grad_norm": 0.49612903594970703,
+      "learning_rate": 9.129209203108335e-05,
+      "loss": 0.7112,
+      "step": 1550
+    },
+    {
+      "epoch": 0.2327573666090161,
+      "grad_norm": 0.4710284471511841,
+      "learning_rate": 9.11016303519732e-05,
+      "loss": 0.7062,
+      "step": 1575
+    },
+    {
+      "epoch": 0.2364519279837624,
+      "grad_norm": 0.5009223818778992,
+      "learning_rate": 9.091116867286303e-05,
+      "loss": 0.7275,
+      "step": 1600
+    },
+    {
+      "epoch": 0.24014648935850869,
+      "grad_norm": 0.5547946691513062,
+      "learning_rate": 9.072070699375286e-05,
+      "loss": 0.6993,
+      "step": 1625
+    },
+    {
+      "epoch": 0.243841050733255,
+      "grad_norm": 0.4580361843109131,
+      "learning_rate": 9.05302453146427e-05,
+      "loss": 0.7106,
+      "step": 1650
+    },
+    {
+      "epoch": 0.24753561210800126,
+      "grad_norm": 0.4767173230648041,
+      "learning_rate": 9.033978363553254e-05,
+      "loss": 0.7103,
+      "step": 1675
+    },
+    {
+      "epoch": 0.25123017348274757,
+      "grad_norm": 0.502202570438385,
+      "learning_rate": 9.014932195642237e-05,
+      "loss": 0.6921,
+      "step": 1700
+    },
+    {
+      "epoch": 0.25492473485749384,
+      "grad_norm": 0.5283953547477722,
+      "learning_rate": 8.99588602773122e-05,
+      "loss": 0.7077,
+      "step": 1725
+    },
+    {
+      "epoch": 0.2586192962322401,
+      "grad_norm": 0.4994209408760071,
+      "learning_rate": 8.976839859820204e-05,
+      "loss": 0.7,
+      "step": 1750
+    },
+    {
+      "epoch": 0.2623138576069864,
+      "grad_norm": 0.48279210925102234,
+      "learning_rate": 8.957793691909188e-05,
+      "loss": 0.7114,
+      "step": 1775
+    },
+    {
+      "epoch": 0.2660084189817327,
+      "grad_norm": 0.6055914759635925,
+      "learning_rate": 8.938747523998172e-05,
+      "loss": 0.7081,
+      "step": 1800
+    },
+    {
+      "epoch": 0.269702980356479,
+      "grad_norm": 0.489519327878952,
+      "learning_rate": 8.919701356087156e-05,
+      "loss": 0.6946,
+      "step": 1825
+    },
+    {
+      "epoch": 0.27339754173122527,
+      "grad_norm": 0.5379961133003235,
+      "learning_rate": 8.90065518817614e-05,
+      "loss": 0.6996,
+      "step": 1850
+    },
+    {
+      "epoch": 0.27709210310597154,
+      "grad_norm": 0.47824332118034363,
+      "learning_rate": 8.881609020265123e-05,
+      "loss": 0.6881,
+      "step": 1875
+    },
+    {
+      "epoch": 0.2807866644807179,
+      "grad_norm": 1551.0594482421875,
+      "learning_rate": 8.862562852354107e-05,
+      "loss": 0.6998,
+      "step": 1900
+    },
+    {
+      "epoch": 0.28448122585546415,
+      "grad_norm": 0.4107681214809418,
+      "learning_rate": 8.84351668444309e-05,
+      "loss": 0.7088,
+      "step": 1925
+    },
+    {
+      "epoch": 0.2881757872302104,
+      "grad_norm": 0.4558309316635132,
+      "learning_rate": 8.824470516532074e-05,
+      "loss": 0.712,
+      "step": 1950
+    },
+    {
+      "epoch": 0.2918703486049567,
+      "grad_norm": 0.539107620716095,
+      "learning_rate": 8.805424348621057e-05,
+      "loss": 0.7159,
+      "step": 1975
+    },
+    {
+      "epoch": 0.295564909979703,
+      "grad_norm": 0.5768142938613892,
+      "learning_rate": 8.786378180710042e-05,
+      "loss": 0.7072,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2992594713544493,
+      "grad_norm": 0.5575465559959412,
+      "learning_rate": 8.767332012799025e-05,
+      "loss": 0.7118,
+      "step": 2025
+    },
+    {
+      "epoch": 0.3029540327291956,
+      "grad_norm": 0.5190144181251526,
+      "learning_rate": 8.748285844888008e-05,
+      "loss": 0.7099,
+      "step": 2050
+    },
+    {
+      "epoch": 0.30664859410394185,
+      "grad_norm": 0.4934520125389099,
+      "learning_rate": 8.729239676976993e-05,
+      "loss": 0.692,
+      "step": 2075
+    },
+    {
+      "epoch": 0.3103431554786881,
+      "grad_norm": 0.42613571882247925,
+      "learning_rate": 8.710193509065976e-05,
+      "loss": 0.7277,
+      "step": 2100
+    },
+    {
+      "epoch": 0.31403771685343446,
+      "grad_norm": 0.5124602317810059,
+      "learning_rate": 8.691147341154961e-05,
+      "loss": 0.6801,
+      "step": 2125
+    },
+    {
+      "epoch": 0.31773227822818073,
+      "grad_norm": 0.5284898281097412,
+      "learning_rate": 8.672101173243944e-05,
+      "loss": 0.7103,
+      "step": 2150
+    },
+    {
+      "epoch": 0.321426839602927,
+      "grad_norm": 0.43099457025527954,
+      "learning_rate": 8.653055005332927e-05,
+      "loss": 0.7023,
+      "step": 2175
+    },
+    {
+      "epoch": 0.3251214009776733,
+      "grad_norm": 0.5190865993499756,
+      "learning_rate": 8.63400883742191e-05,
+      "loss": 0.7144,
+      "step": 2200
+    },
+    {
+      "epoch": 0.3288159623524196,
+      "grad_norm": 0.4722968637943268,
+      "learning_rate": 8.614962669510895e-05,
+      "loss": 0.7351,
+      "step": 2225
+    },
+    {
+      "epoch": 0.3325105237271659,
+      "grad_norm": 0.6091466546058655,
+      "learning_rate": 8.595916501599878e-05,
+      "loss": 0.7062,
+      "step": 2250
+    },
+    {
+      "epoch": 0.33620508510191216,
+      "grad_norm": 0.6135897040367126,
+      "learning_rate": 8.576870333688862e-05,
+      "loss": 0.7117,
+      "step": 2275
+    },
+    {
+      "epoch": 0.33989964647665843,
+      "grad_norm": 0.5224157571792603,
+      "learning_rate": 8.557824165777846e-05,
+      "loss": 0.7068,
+      "step": 2300
+    },
+    {
+      "epoch": 0.34359420785140476,
+      "grad_norm": 0.4863536059856415,
+      "learning_rate": 8.53877799786683e-05,
+      "loss": 0.6952,
+      "step": 2325
+    },
+    {
+      "epoch": 0.34728876922615104,
+      "grad_norm": 0.4728885889053345,
+      "learning_rate": 8.519731829955814e-05,
+      "loss": 0.7289,
+      "step": 2350
+    },
+    {
+      "epoch": 0.3509833306008973,
+      "grad_norm": 0.5152695775032043,
+      "learning_rate": 8.500685662044798e-05,
+      "loss": 0.6986,
+      "step": 2375
+    },
+    {
+      "epoch": 0.3546778919756436,
+      "grad_norm": 0.4407690465450287,
+      "learning_rate": 8.481639494133781e-05,
+      "loss": 0.6983,
+      "step": 2400
+    },
+    {
+      "epoch": 0.3583724533503899,
+      "grad_norm": 0.4756406545639038,
+      "learning_rate": 8.462593326222764e-05,
+      "loss": 0.6626,
+      "step": 2425
+    },
+    {
+      "epoch": 0.3620670147251362,
+      "grad_norm": 0.48595255613327026,
+      "learning_rate": 8.443547158311747e-05,
+      "loss": 0.6892,
+      "step": 2450
+    },
+    {
+      "epoch": 0.36576157609988247,
+      "grad_norm": 0.47830772399902344,
+      "learning_rate": 8.424500990400732e-05,
+      "loss": 0.7162,
+      "step": 2475
+    },
+    {
+      "epoch": 0.36945613747462874,
+      "grad_norm": 0.43090149760246277,
+      "learning_rate": 8.405454822489715e-05,
+      "loss": 0.6913,
+      "step": 2500
+    },
+    {
+      "epoch": 0.373150698849375,
+      "grad_norm": 0.5338718295097351,
+      "learning_rate": 8.386408654578698e-05,
+      "loss": 0.7159,
+      "step": 2525
+    },
+    {
+      "epoch": 0.37684526022412135,
+      "grad_norm": 0.4907350242137909,
+      "learning_rate": 8.367362486667683e-05,
+      "loss": 0.7022,
+      "step": 2550
+    },
+    {
+      "epoch": 0.3805398215988676,
+      "grad_norm": 0.44093430042266846,
+      "learning_rate": 8.348316318756668e-05,
+      "loss": 0.7124,
+      "step": 2575
+    },
+    {
+      "epoch": 0.3842343829736139,
+      "grad_norm": 0.5388796925544739,
+      "learning_rate": 8.329270150845651e-05,
+      "loss": 0.7304,
+      "step": 2600
+    },
+    {
+      "epoch": 0.38792894434836017,
+      "grad_norm": 0.4456349313259125,
+      "learning_rate": 8.310223982934634e-05,
+      "loss": 0.6964,
+      "step": 2625
+    },
+    {
+      "epoch": 0.3916235057231065,
+      "grad_norm": 0.4602237343788147,
+      "learning_rate": 8.291177815023617e-05,
+      "loss": 0.6707,
+      "step": 2650
+    },
+    {
+      "epoch": 0.3953180670978528,
+      "grad_norm": 0.4726378917694092,
+      "learning_rate": 8.272131647112601e-05,
+      "loss": 0.694,
+      "step": 2675
+    },
+    {
+      "epoch": 0.39901262847259905,
+      "grad_norm": 0.500451922416687,
+      "learning_rate": 8.253085479201585e-05,
+      "loss": 0.6812,
+      "step": 2700
+    },
+    {
+      "epoch": 0.4027071898473453,
+      "grad_norm": 0.4073813259601593,
+      "learning_rate": 8.234039311290569e-05,
+      "loss": 0.7028,
+      "step": 2725
+    },
+    {
+      "epoch": 0.40640175122209166,
+      "grad_norm": 0.43644702434539795,
+      "learning_rate": 8.214993143379552e-05,
+      "loss": 0.6936,
+      "step": 2750
+    },
+    {
+      "epoch": 0.41009631259683793,
+      "grad_norm": 0.5256789922714233,
+      "learning_rate": 8.195946975468535e-05,
+      "loss": 0.7035,
+      "step": 2775
+    },
+    {
+      "epoch": 0.4137908739715842,
+      "grad_norm": 0.48385316133499146,
+      "learning_rate": 8.17690080755752e-05,
+      "loss": 0.6736,
+      "step": 2800
+    },
+    {
+      "epoch": 0.4174854353463305,
+      "grad_norm": 0.49825233221054077,
+      "learning_rate": 8.157854639646504e-05,
+      "loss": 0.7019,
+      "step": 2825
+    },
+    {
+      "epoch": 0.42117999672107675,
+      "grad_norm": 0.5086994171142578,
+      "learning_rate": 8.138808471735488e-05,
+      "loss": 0.6918,
+      "step": 2850
+    },
+    {
+      "epoch": 0.4248745580958231,
+      "grad_norm": 0.5430259108543396,
+      "learning_rate": 8.119762303824471e-05,
+      "loss": 0.7175,
+      "step": 2875
+    },
+    {
+      "epoch": 0.42856911947056936,
+      "grad_norm": 0.5889118313789368,
+      "learning_rate": 8.100716135913454e-05,
+      "loss": 0.6967,
+      "step": 2900
+    },
+    {
+      "epoch": 0.43226368084531563,
+      "grad_norm": 0.5345672369003296,
+      "learning_rate": 8.081669968002439e-05,
+      "loss": 0.6926,
+      "step": 2925
+    },
+    {
+      "epoch": 0.4359582422200619,
+      "grad_norm": 0.511101245880127,
+      "learning_rate": 8.062623800091422e-05,
+      "loss": 0.7248,
+      "step": 2950
+    },
+    {
+      "epoch": 0.43965280359480824,
+      "grad_norm": 0.511239767074585,
+      "learning_rate": 8.043577632180405e-05,
+      "loss": 0.7319,
+      "step": 2975
+    },
+    {
+      "epoch": 0.4433473649695545,
+      "grad_norm": 0.5121573805809021,
+      "learning_rate": 8.024531464269389e-05,
+      "loss": 0.7023,
+      "step": 3000
+    },
+    {
+      "epoch": 0.4470419263443008,
+      "grad_norm": 0.5658753514289856,
+      "learning_rate": 8.005485296358373e-05,
+      "loss": 0.6934,
+      "step": 3025
+    },
+    {
+      "epoch": 0.45073648771904706,
+      "grad_norm": 0.5475583672523499,
+      "learning_rate": 7.986439128447358e-05,
+      "loss": 0.6701,
+      "step": 3050
+    },
+    {
+      "epoch": 0.4544310490937934,
+      "grad_norm": 0.6107661724090576,
+      "learning_rate": 7.967392960536341e-05,
+      "loss": 0.7056,
+      "step": 3075
+    },
+    {
+      "epoch": 0.45812561046853967,
+      "grad_norm": 0.48424115777015686,
+      "learning_rate": 7.948346792625324e-05,
+      "loss": 0.7179,
+      "step": 3100
+    },
+    {
+      "epoch": 0.46182017184328594,
+      "grad_norm": 0.6184881329536438,
+      "learning_rate": 7.929300624714308e-05,
+      "loss": 0.7141,
+      "step": 3125
+    },
+    {
+      "epoch": 0.4655147332180322,
+      "grad_norm": 0.49919527769088745,
+      "learning_rate": 7.910254456803291e-05,
+      "loss": 0.7027,
+      "step": 3150
+    },
+    {
+      "epoch": 0.4692092945927785,
+      "grad_norm": 0.5012905597686768,
+      "learning_rate": 7.891208288892276e-05,
+      "loss": 0.6852,
+      "step": 3175
+    },
+    {
+      "epoch": 0.4729038559675248,
+      "grad_norm": 0.5033735036849976,
+      "learning_rate": 7.872162120981259e-05,
+      "loss": 0.7199,
+      "step": 3200
+    },
+    {
+      "epoch": 0.4765984173422711,
+      "grad_norm": 0.5746079087257385,
+      "learning_rate": 7.853115953070242e-05,
+      "loss": 0.715,
+      "step": 3225
+    },
+    {
+      "epoch": 0.48029297871701737,
+      "grad_norm": 0.5436145663261414,
+      "learning_rate": 7.834069785159225e-05,
+      "loss": 0.697,
+      "step": 3250
+    },
+    {
+      "epoch": 0.48398754009176365,
+      "grad_norm": 0.5836604833602905,
+      "learning_rate": 7.81502361724821e-05,
+      "loss": 0.7129,
+      "step": 3275
+    },
+    {
+      "epoch": 0.48768210146651,
+      "grad_norm": 0.5618935227394104,
+      "learning_rate": 7.795977449337195e-05,
+      "loss": 0.6993,
+      "step": 3300
+    },
+    {
+      "epoch": 0.49137666284125625,
+      "grad_norm": 0.6251245737075806,
+      "learning_rate": 7.776931281426178e-05,
+      "loss": 0.7132,
+      "step": 3325
+    },
+    {
+      "epoch": 0.4950712242160025,
+      "grad_norm": 0.5123202800750732,
+      "learning_rate": 7.757885113515161e-05,
+      "loss": 0.7218,
+      "step": 3350
+    },
+    {
+      "epoch": 0.4987657855907488,
+      "grad_norm": 0.5818086862564087,
+      "learning_rate": 7.738838945604144e-05,
+      "loss": 0.7154,
+      "step": 3375
+    },
+    {
+      "epoch": 0.5024603469654951,
+      "grad_norm": 0.5861947536468506,
+      "learning_rate": 7.719792777693129e-05,
+      "loss": 0.7013,
+      "step": 3400
+    },
+    {
+      "epoch": 0.5061549083402413,
+      "grad_norm": 0.4849907457828522,
+      "learning_rate": 7.700746609782112e-05,
+      "loss": 0.6902,
+      "step": 3425
+    },
+    {
+      "epoch": 0.5098494697149877,
+      "grad_norm": 0.5476916432380676,
+      "learning_rate": 7.681700441871096e-05,
+      "loss": 0.7147,
+      "step": 3450
+    },
+    {
+      "epoch": 0.513544031089734,
+      "grad_norm": 0.5822548866271973,
+      "learning_rate": 7.662654273960079e-05,
+      "loss": 0.7431,
+      "step": 3475
+    },
+    {
+      "epoch": 0.5172385924644802,
+      "grad_norm": 0.44818004965782166,
+      "learning_rate": 7.643608106049063e-05,
+      "loss": 0.718,
+      "step": 3500
+    },
+    {
+      "epoch": 0.5209331538392266,
+      "grad_norm": 0.544068455696106,
+      "learning_rate": 7.624561938138047e-05,
+      "loss": 0.7201,
+      "step": 3525
+    },
+    {
+      "epoch": 0.5246277152139728,
+      "grad_norm": 0.5535098910331726,
+      "learning_rate": 7.605515770227031e-05,
+      "loss": 0.6998,
+      "step": 3550
+    },
+    {
+      "epoch": 0.5283222765887191,
+      "grad_norm": 0.5754445195198059,
+      "learning_rate": 7.586469602316015e-05,
+      "loss": 0.6918,
+      "step": 3575
+    },
+    {
+      "epoch": 0.5320168379634654,
+      "grad_norm": 0.5976133942604065,
+      "learning_rate": 7.567423434404998e-05,
+      "loss": 0.693,
+      "step": 3600
+    },
+    {
+      "epoch": 0.5357113993382117,
+      "grad_norm": 0.4844263195991516,
+      "learning_rate": 7.548377266493982e-05,
+      "loss": 0.68,
+      "step": 3625
+    },
+    {
+      "epoch": 0.539405960712958,
+      "grad_norm": 0.5436462163925171,
+      "learning_rate": 7.529331098582966e-05,
+      "loss": 0.7075,
+      "step": 3650
+    },
+    {
+      "epoch": 0.5431005220877043,
+      "grad_norm": 0.6490929126739502,
+      "learning_rate": 7.510284930671949e-05,
+      "loss": 0.6956,
+      "step": 3675
+    },
+    {
+      "epoch": 0.5467950834624505,
+      "grad_norm": 0.47479814291000366,
+      "learning_rate": 7.491238762760932e-05,
+      "loss": 0.7026,
+      "step": 3700
+    },
+    {
+      "epoch": 0.5504896448371969,
+      "grad_norm": 0.590874969959259,
+      "learning_rate": 7.472192594849915e-05,
+      "loss": 0.7117,
+      "step": 3725
+    },
+    {
+      "epoch": 0.5541842062119431,
+      "grad_norm": 0.46487829089164734,
+      "learning_rate": 7.4531464269389e-05,
+      "loss": 0.6919,
+      "step": 3750
+    },
+    {
+      "epoch": 0.5578787675866894,
+      "grad_norm": 0.6609780192375183,
+      "learning_rate": 7.434100259027885e-05,
+      "loss": 0.7089,
+      "step": 3775
+    },
+    {
+      "epoch": 0.5615733289614357,
+      "grad_norm": 0.6165657639503479,
+      "learning_rate": 7.415054091116868e-05,
+      "loss": 0.7444,
+      "step": 3800
+    },
+    {
+      "epoch": 0.565267890336182,
+      "grad_norm": 0.5194655656814575,
+      "learning_rate": 7.396007923205851e-05,
+      "loss": 0.7114,
+      "step": 3825
+    },
+    {
+      "epoch": 0.5689624517109283,
+      "grad_norm": 0.4813441336154938,
+      "learning_rate": 7.376961755294836e-05,
+      "loss": 0.6953,
+      "step": 3850
+    },
+    {
+      "epoch": 0.5726570130856745,
+      "grad_norm": 0.7607313990592957,
+      "learning_rate": 7.357915587383819e-05,
+      "loss": 0.7058,
+      "step": 3875
+    },
+    {
+      "epoch": 0.5763515744604208,
+      "grad_norm": 0.48498719930648804,
+      "learning_rate": 7.338869419472802e-05,
+      "loss": 0.6866,
+      "step": 3900
+    },
+    {
+      "epoch": 0.5800461358351672,
+      "grad_norm": 0.5969393253326416,
+      "learning_rate": 7.319823251561786e-05,
+      "loss": 0.6951,
+      "step": 3925
+    },
+    {
+      "epoch": 0.5837406972099134,
+      "grad_norm": 0.6178887486457825,
+      "learning_rate": 7.300777083650769e-05,
+      "loss": 0.7036,
+      "step": 3950
+    },
+    {
+      "epoch": 0.5874352585846597,
+      "grad_norm": 0.5318612456321716,
+      "learning_rate": 7.281730915739754e-05,
+      "loss": 0.6856,
+      "step": 3975
+    },
+    {
+      "epoch": 0.591129819959406,
+      "grad_norm": 0.6101936101913452,
+      "learning_rate": 7.262684747828737e-05,
+      "loss": 0.7103,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5948243813341523,
+      "grad_norm": 0.5605831742286682,
+      "learning_rate": 7.243638579917721e-05,
+      "loss": 0.6684,
+      "step": 4025
+    },
+    {
+      "epoch": 0.5985189427088986,
+      "grad_norm": 0.6576380133628845,
+      "learning_rate": 7.224592412006705e-05,
+      "loss": 0.6955,
+      "step": 4050
+    },
+    {
+      "epoch": 0.6022135040836448,
+      "grad_norm": 0.49083924293518066,
+      "learning_rate": 7.205546244095688e-05,
+      "loss": 0.7089,
+      "step": 4075
+    },
+    {
+      "epoch": 0.6059080654583912,
+      "grad_norm": 0.4783398509025574,
+      "learning_rate": 7.186500076184673e-05,
+      "loss": 0.6766,
+      "step": 4100
+    },
+    {
+      "epoch": 0.6096026268331375,
+      "grad_norm": 0.5773366689682007,
+      "learning_rate": 7.167453908273656e-05,
+      "loss": 0.666,
+      "step": 4125
+    },
+    {
+      "epoch": 0.6132971882078837,
+      "grad_norm": 0.5449897050857544,
+      "learning_rate": 7.148407740362639e-05,
+      "loss": 0.6795,
+      "step": 4150
+    },
+    {
+      "epoch": 0.61699174958263,
+      "grad_norm": 0.519882082939148,
+      "learning_rate": 7.129361572451622e-05,
+      "loss": 0.6892,
+      "step": 4175
+    },
+    {
+      "epoch": 0.6206863109573763,
+      "grad_norm": 0.5653222799301147,
+      "learning_rate": 7.110315404540607e-05,
+      "loss": 0.7029,
+      "step": 4200
+    },
+    {
+      "epoch": 0.6243808723321226,
+      "grad_norm": 0.542448878288269,
+      "learning_rate": 7.09126923662959e-05,
+      "loss": 0.6885,
+      "step": 4225
+    },
+    {
+      "epoch": 0.6280754337068689,
+      "grad_norm": 0.5602554082870483,
+      "learning_rate": 7.072223068718575e-05,
+      "loss": 0.6811,
+      "step": 4250
+    },
+    {
+      "epoch": 0.6317699950816151,
+      "grad_norm": 0.5326575636863708,
+      "learning_rate": 7.053176900807558e-05,
+      "loss": 0.7032,
+      "step": 4275
+    },
+    {
+      "epoch": 0.6354645564563615,
+      "grad_norm": 0.5822186470031738,
+      "learning_rate": 7.034130732896541e-05,
+      "loss": 0.6951,
+      "step": 4300
+    },
+    {
+      "epoch": 0.6391591178311078,
+      "grad_norm": 0.5309107899665833,
+      "learning_rate": 7.015084564985526e-05,
+      "loss": 0.6891,
+      "step": 4325
+    },
+    {
+      "epoch": 0.642853679205854,
+      "grad_norm": 0.6958228349685669,
+      "learning_rate": 6.996038397074509e-05,
+      "loss": 0.6932,
+      "step": 4350
+    },
+    {
+      "epoch": 0.6465482405806003,
+      "grad_norm": 0.4864750802516937,
+      "learning_rate": 6.976992229163493e-05,
+      "loss": 0.6897,
+      "step": 4375
+    },
+    {
+      "epoch": 0.6502428019553466,
+      "grad_norm": 0.5077944993972778,
+      "learning_rate": 6.957946061252476e-05,
+      "loss": 0.7067,
+      "step": 4400
+    },
+    {
+      "epoch": 0.6539373633300929,
+      "grad_norm": 0.5589050054550171,
+      "learning_rate": 6.938899893341459e-05,
+      "loss": 0.6927,
+      "step": 4425
+    },
+    {
+      "epoch": 0.6576319247048392,
+      "grad_norm": 0.6064692735671997,
+      "learning_rate": 6.919853725430444e-05,
+      "loss": 0.7186,
+      "step": 4450
+    },
+    {
+      "epoch": 0.6613264860795854,
+      "grad_norm": 0.5546572208404541,
+      "learning_rate": 6.900807557519427e-05,
+      "loss": 0.6865,
+      "step": 4475
+    },
+    {
+      "epoch": 0.6650210474543318,
+      "grad_norm": 0.6032342314720154,
+      "learning_rate": 6.881761389608412e-05,
+      "loss": 0.6999,
+      "step": 4500
+    },
+    {
+      "epoch": 0.668715608829078,
+      "grad_norm": 0.5067450404167175,
+      "learning_rate": 6.862715221697395e-05,
+      "loss": 0.7068,
+      "step": 4525
+    },
+    {
+      "epoch": 0.6724101702038243,
+      "grad_norm": 0.6697527170181274,
+      "learning_rate": 6.84366905378638e-05,
+      "loss": 0.7075,
+      "step": 4550
+    },
+    {
+      "epoch": 0.6761047315785707,
+      "grad_norm": 0.48360082507133484,
+      "learning_rate": 6.824622885875363e-05,
+      "loss": 0.7076,
+      "step": 4575
+    },
+    {
+      "epoch": 0.6797992929533169,
+      "grad_norm": 0.6387288570404053,
+      "learning_rate": 6.805576717964346e-05,
+      "loss": 0.6871,
+      "step": 4600
+    },
+    {
+      "epoch": 0.6834938543280632,
+      "grad_norm": 0.6431862115859985,
+      "learning_rate": 6.786530550053329e-05,
+      "loss": 0.7138,
+      "step": 4625
+    },
+    {
+      "epoch": 0.6871884157028095,
+      "grad_norm": 0.6050564050674438,
+      "learning_rate": 6.767484382142313e-05,
+      "loss": 0.6978,
+      "step": 4650
+    },
+    {
+      "epoch": 0.6908829770775557,
+      "grad_norm": 0.7160177230834961,
+      "learning_rate": 6.748438214231297e-05,
+      "loss": 0.6813,
+      "step": 4675
+    },
+    {
+      "epoch": 0.6945775384523021,
+      "grad_norm": 0.6984575986862183,
+      "learning_rate": 6.72939204632028e-05,
+      "loss": 0.7155,
+      "step": 4700
+    },
+    {
+      "epoch": 0.6982720998270483,
+      "grad_norm": 0.5910038352012634,
+      "learning_rate": 6.710345878409264e-05,
+      "loss": 0.6689,
+      "step": 4725
+    },
+    {
+      "epoch": 0.7019666612017946,
+      "grad_norm": 0.5897320508956909,
+      "learning_rate": 6.691299710498248e-05,
+      "loss": 0.7169,
+      "step": 4750
+    },
+    {
+      "epoch": 0.705661222576541,
+      "grad_norm": 0.5735405683517456,
+      "learning_rate": 6.672253542587232e-05,
+      "loss": 0.6779,
+      "step": 4775
+    },
+    {
+      "epoch": 0.7093557839512872,
+      "grad_norm": 0.6408699750900269,
+      "learning_rate": 6.653207374676216e-05,
+      "loss": 0.7069,
+      "step": 4800
+    },
+    {
+      "epoch": 0.7130503453260335,
+      "grad_norm": 0.6292117834091187,
+      "learning_rate": 6.6341612067652e-05,
+      "loss": 0.698,
+      "step": 4825
+    },
+    {
+      "epoch": 0.7167449067007798,
+      "grad_norm": 0.6101416349411011,
+      "learning_rate": 6.615115038854183e-05,
+      "loss": 0.6708,
+      "step": 4850
+    },
+    {
+      "epoch": 0.7204394680755261,
+      "grad_norm": 0.6805480122566223,
+      "learning_rate": 6.596068870943166e-05,
+      "loss": 0.7115,
+      "step": 4875
+    },
+    {
+      "epoch": 0.7241340294502724,
+      "grad_norm": 0.6465732455253601,
+      "learning_rate": 6.57702270303215e-05,
+      "loss": 0.688,
+      "step": 4900
+    },
+    {
+      "epoch": 0.7278285908250186,
+      "grad_norm": 0.5873344540596008,
+      "learning_rate": 6.557976535121134e-05,
+      "loss": 0.7032,
+      "step": 4925
+    },
+    {
+      "epoch": 0.7315231521997649,
+      "grad_norm": 0.5717042088508606,
+      "learning_rate": 6.538930367210117e-05,
+      "loss": 0.6907,
+      "step": 4950
+    },
+    {
+      "epoch": 0.7352177135745113,
+      "grad_norm": 0.6366106867790222,
+      "learning_rate": 6.519884199299102e-05,
+      "loss": 0.7061,
+      "step": 4975
+    },
+    {
+      "epoch": 0.7389122749492575,
+      "grad_norm": 0.7421902418136597,
+      "learning_rate": 6.500838031388085e-05,
+      "loss": 0.7267,
+      "step": 5000
+    },
+    {
+      "epoch": 0.7426068363240038,
+      "grad_norm": 0.5897513031959534,
+      "learning_rate": 6.48179186347707e-05,
+      "loss": 0.7089,
+      "step": 5025
+    },
+    {
+      "epoch": 0.74630139769875,
+      "grad_norm": 0.6692824959754944,
+      "learning_rate": 6.462745695566053e-05,
+      "loss": 0.7059,
+      "step": 5050
+    },
+    {
+      "epoch": 0.7499959590734964,
+      "grad_norm": 0.5818034410476685,
+      "learning_rate": 6.443699527655036e-05,
+      "loss": 0.6734,
+      "step": 5075
+    },
+    {
+      "epoch": 0.7536905204482427,
+      "grad_norm": 0.5975498557090759,
+      "learning_rate": 6.42465335974402e-05,
+      "loss": 0.6857,
+      "step": 5100
+    },
+    {
+      "epoch": 0.7573850818229889,
+      "grad_norm": 0.5827130675315857,
+      "learning_rate": 6.405607191833003e-05,
+      "loss": 0.7156,
+      "step": 5125
+    },
+    {
+      "epoch": 0.7610796431977352,
+      "grad_norm": 0.660932719707489,
+      "learning_rate": 6.386561023921987e-05,
+      "loss": 0.688,
+      "step": 5150
+    },
+    {
+      "epoch": 0.7647742045724816,
+      "grad_norm": 0.5963577628135681,
+      "learning_rate": 6.36751485601097e-05,
+      "loss": 0.709,
+      "step": 5175
+    },
+    {
+      "epoch": 0.7684687659472278,
+      "grad_norm": 0.6608302593231201,
+      "learning_rate": 6.348468688099954e-05,
+      "loss": 0.6761,
+      "step": 5200
+    },
+    {
+      "epoch": 0.7721633273219741,
+      "grad_norm": 0.6137542724609375,
+      "learning_rate": 6.329422520188938e-05,
+      "loss": 0.6845,
+      "step": 5225
+    },
+    {
+      "epoch": 0.7758578886967203,
+      "grad_norm": 0.6861995458602905,
+      "learning_rate": 6.310376352277923e-05,
+      "loss": 0.6746,
+      "step": 5250
+    },
+    {
+      "epoch": 0.7795524500714667,
+      "grad_norm": 0.6537772417068481,
+      "learning_rate": 6.291330184366906e-05,
+      "loss": 0.6777,
+      "step": 5275
+    },
+    {
+      "epoch": 0.783247011446213,
+      "grad_norm": 0.6634919047355652,
+      "learning_rate": 6.27228401645589e-05,
+      "loss": 0.6945,
+      "step": 5300
+    },
+    {
+      "epoch": 0.7869415728209592,
+      "grad_norm": 0.610098123550415,
+      "learning_rate": 6.253237848544873e-05,
+      "loss": 0.6909,
+      "step": 5325
+    },
+    {
+      "epoch": 0.7906361341957056,
+      "grad_norm": 0.6167535185813904,
+      "learning_rate": 6.234191680633856e-05,
+      "loss": 0.6988,
+      "step": 5350
+    },
+    {
+      "epoch": 0.7943306955704518,
+      "grad_norm": 0.6502842903137207,
+      "learning_rate": 6.215145512722841e-05,
+      "loss": 0.6937,
+      "step": 5375
+    },
+    {
+      "epoch": 0.7980252569451981,
+      "grad_norm": 0.5586534142494202,
+      "learning_rate": 6.196099344811824e-05,
+      "loss": 0.6891,
+      "step": 5400
+    },
+    {
+      "epoch": 0.8017198183199444,
+      "grad_norm": 0.577847957611084,
+      "learning_rate": 6.177053176900807e-05,
+      "loss": 0.7111,
+      "step": 5425
+    },
+    {
+      "epoch": 0.8054143796946907,
+      "grad_norm": 0.5086051225662231,
+      "learning_rate": 6.158007008989792e-05,
+      "loss": 0.6892,
+      "step": 5450
+    },
+    {
+      "epoch": 0.809108941069437,
+      "grad_norm": 0.6650702953338623,
+      "learning_rate": 6.138960841078775e-05,
+      "loss": 0.6853,
+      "step": 5475
+    },
+    {
+      "epoch": 0.8128035024441833,
+      "grad_norm": 0.730775773525238,
+      "learning_rate": 6.11991467316776e-05,
+      "loss": 0.6972,
+      "step": 5500
+    },
+    {
+      "epoch": 0.8164980638189295,
+      "grad_norm": 0.6812962293624878,
+      "learning_rate": 6.100868505256743e-05,
+      "loss": 0.7179,
+      "step": 5525
+    },
+    {
+      "epoch": 0.8201926251936759,
+      "grad_norm": 0.6698195934295654,
+      "learning_rate": 6.081822337345726e-05,
+      "loss": 0.6935,
+      "step": 5550
+    },
+    {
+      "epoch": 0.8238871865684221,
+      "grad_norm": 0.7661596536636353,
+      "learning_rate": 6.0627761694347096e-05,
+      "loss": 0.7081,
+      "step": 5575
+    },
+    {
+      "epoch": 0.8275817479431684,
+      "grad_norm": 0.63306725025177,
+      "learning_rate": 6.043730001523694e-05,
+      "loss": 0.6814,
+      "step": 5600
+    },
+    {
+      "epoch": 0.8312763093179147,
+      "grad_norm": 0.638088047504425,
+      "learning_rate": 6.0246838336126774e-05,
+      "loss": 0.7162,
+      "step": 5625
+    },
+    {
+      "epoch": 0.834970870692661,
+      "grad_norm": 0.6416764259338379,
+      "learning_rate": 6.0056376657016614e-05,
+      "loss": 0.6935,
+      "step": 5650
+    },
+    {
+      "epoch": 0.8386654320674073,
+      "grad_norm": 0.6060255169868469,
+      "learning_rate": 5.9865914977906447e-05,
+      "loss": 0.6935,
+      "step": 5675
+    },
+    {
+      "epoch": 0.8423599934421535,
+      "grad_norm": 0.6919652223587036,
+      "learning_rate": 5.967545329879628e-05,
+      "loss": 0.6781,
+      "step": 5700
+    },
+    {
+      "epoch": 0.8460545548168998,
+      "grad_norm": 0.5610880851745605,
+      "learning_rate": 5.9484991619686125e-05,
+      "loss": 0.6924,
+      "step": 5725
+    },
+    {
+      "epoch": 0.8497491161916462,
+      "grad_norm": 0.6481006145477295,
+      "learning_rate": 5.929452994057596e-05,
+      "loss": 0.6708,
+      "step": 5750
+    },
+    {
+      "epoch": 0.8534436775663924,
+      "grad_norm": 0.618869423866272,
+      "learning_rate": 5.91040682614658e-05,
+      "loss": 0.6801,
+      "step": 5775
+    },
+    {
+      "epoch": 0.8571382389411387,
+      "grad_norm": 0.5622214674949646,
+      "learning_rate": 5.891360658235563e-05,
+      "loss": 0.6932,
+      "step": 5800
+    },
+    {
+      "epoch": 0.860832800315885,
+      "grad_norm": 0.6936132311820984,
+      "learning_rate": 5.8723144903245476e-05,
+      "loss": 0.6932,
+      "step": 5825
+    },
+    {
+      "epoch": 0.8645273616906313,
+      "grad_norm": 0.6182092428207397,
+      "learning_rate": 5.853268322413531e-05,
+      "loss": 0.6767,
+      "step": 5850
+    },
+    {
+      "epoch": 0.8682219230653776,
+      "grad_norm": 0.6932141184806824,
+      "learning_rate": 5.834222154502514e-05,
+      "loss": 0.694,
+      "step": 5875
+    },
+    {
+      "epoch": 0.8719164844401238,
+      "grad_norm": 0.4943319261074066,
+      "learning_rate": 5.815175986591498e-05,
+      "loss": 0.6884,
+      "step": 5900
+    },
+    {
+      "epoch": 0.8756110458148701,
+      "grad_norm": 0.730697512626648,
+      "learning_rate": 5.7961298186804814e-05,
+      "loss": 0.6906,
+      "step": 5925
+    },
+    {
+      "epoch": 0.8793056071896165,
+      "grad_norm": 0.5535916090011597,
+      "learning_rate": 5.777083650769466e-05,
+      "loss": 0.6992,
+      "step": 5950
+    },
+    {
+      "epoch": 0.8830001685643627,
+      "grad_norm": 0.6035041809082031,
+      "learning_rate": 5.758037482858449e-05,
+      "loss": 0.6637,
+      "step": 5975
+    },
+    {
+      "epoch": 0.886694729939109,
+      "grad_norm": 0.6580167412757874,
+      "learning_rate": 5.7389913149474325e-05,
+      "loss": 0.7056,
+      "step": 6000
+    },
+    {
+      "epoch": 0.8903892913138552,
+      "grad_norm": 0.5391905903816223,
+      "learning_rate": 5.7199451470364165e-05,
+      "loss": 0.7169,
+      "step": 6025
+    },
+    {
+      "epoch": 0.8940838526886016,
+      "grad_norm": 0.7833768725395203,
+      "learning_rate": 5.7008989791254e-05,
+      "loss": 0.682,
+      "step": 6050
+    },
+    {
+      "epoch": 0.8977784140633479,
+      "grad_norm": 0.6040502190589905,
+      "learning_rate": 5.681852811214384e-05,
+      "loss": 0.6893,
+      "step": 6075
+    },
+    {
+      "epoch": 0.9014729754380941,
+      "grad_norm": 0.5723184943199158,
+      "learning_rate": 5.6628066433033676e-05,
+      "loss": 0.7041,
+      "step": 6100
+    },
+    {
+      "epoch": 0.9051675368128405,
+      "grad_norm": 0.7001731395721436,
+      "learning_rate": 5.643760475392351e-05,
+      "loss": 0.69,
+      "step": 6125
+    },
+    {
+      "epoch": 0.9088620981875868,
+      "grad_norm": 0.6454519629478455,
+      "learning_rate": 5.624714307481335e-05,
+      "loss": 0.6777,
+      "step": 6150
+    },
+    {
+      "epoch": 0.912556659562333,
+      "grad_norm": 0.6187843680381775,
+      "learning_rate": 5.6056681395703194e-05,
+      "loss": 0.7069,
+      "step": 6175
+    },
+    {
+      "epoch": 0.9162512209370793,
+      "grad_norm": 0.6245271563529968,
+      "learning_rate": 5.586621971659303e-05,
+      "loss": 0.6735,
+      "step": 6200
+    },
+    {
+      "epoch": 0.9199457823118256,
+      "grad_norm": 0.513124406337738,
+      "learning_rate": 5.567575803748286e-05,
+      "loss": 0.6859,
+      "step": 6225
+    },
+    {
+      "epoch": 0.9236403436865719,
+      "grad_norm": 0.5510721206665039,
+      "learning_rate": 5.54852963583727e-05,
+      "loss": 0.7195,
+      "step": 6250
+    },
+    {
+      "epoch": 0.9273349050613182,
+      "grad_norm": 0.7087464332580566,
+      "learning_rate": 5.529483467926253e-05,
+      "loss": 0.6761,
+      "step": 6275
+    },
+    {
+      "epoch": 0.9310294664360644,
+      "grad_norm": 0.6695664525032043,
+      "learning_rate": 5.510437300015238e-05,
+      "loss": 0.7013,
+      "step": 6300
+    },
+    {
+      "epoch": 0.9347240278108108,
+      "grad_norm": 0.6182588934898376,
+      "learning_rate": 5.491391132104221e-05,
+      "loss": 0.6793,
+      "step": 6325
+    },
+    {
+      "epoch": 0.938418589185557,
+      "grad_norm": 0.7019252181053162,
+      "learning_rate": 5.472344964193204e-05,
+      "loss": 0.7122,
+      "step": 6350
+    },
+    {
+      "epoch": 0.9421131505603033,
+      "grad_norm": 0.772847592830658,
+      "learning_rate": 5.453298796282188e-05,
+      "loss": 0.6991,
+      "step": 6375
+    },
+    {
+      "epoch": 0.9458077119350496,
+      "grad_norm": 0.7126289010047913,
+      "learning_rate": 5.4342526283711715e-05,
+      "loss": 0.6992,
+      "step": 6400
+    },
+    {
+      "epoch": 0.9495022733097959,
+      "grad_norm": 0.7134938836097717,
+      "learning_rate": 5.415206460460156e-05,
+      "loss": 0.7091,
+      "step": 6425
+    },
+    {
+      "epoch": 0.9531968346845422,
+      "grad_norm": 0.7651578187942505,
+      "learning_rate": 5.3961602925491394e-05,
+      "loss": 0.6829,
+      "step": 6450
+    },
+    {
+      "epoch": 0.9568913960592885,
+      "grad_norm": 0.6493939161300659,
+      "learning_rate": 5.377114124638123e-05,
+      "loss": 0.6831,
+      "step": 6475
+    },
+    {
+      "epoch": 0.9605859574340347,
+      "grad_norm": 0.5992809534072876,
+      "learning_rate": 5.3580679567271066e-05,
+      "loss": 0.6984,
+      "step": 6500
+    },
+    {
+      "epoch": 0.9642805188087811,
+      "grad_norm": 0.6597899794578552,
+      "learning_rate": 5.339021788816091e-05,
+      "loss": 0.6893,
+      "step": 6525
+    },
+    {
+      "epoch": 0.9679750801835273,
+      "grad_norm": 0.6459916234016418,
+      "learning_rate": 5.3199756209050745e-05,
+      "loss": 0.6935,
+      "step": 6550
+    },
+    {
+      "epoch": 0.9716696415582736,
+      "grad_norm": 0.7714385986328125,
+      "learning_rate": 5.300929452994058e-05,
+      "loss": 0.6883,
+      "step": 6575
+    },
+    {
+      "epoch": 0.97536420293302,
+      "grad_norm": 0.5793107748031616,
+      "learning_rate": 5.281883285083041e-05,
+      "loss": 0.6795,
+      "step": 6600
+    },
+    {
+      "epoch": 0.9790587643077662,
+      "grad_norm": 0.5452476739883423,
+      "learning_rate": 5.262837117172025e-05,
+      "loss": 0.6809,
+      "step": 6625
+    },
+    {
+      "epoch": 0.9827533256825125,
+      "grad_norm": 0.6292601823806763,
+      "learning_rate": 5.2437909492610096e-05,
+      "loss": 0.7021,
+      "step": 6650
+    },
+    {
+      "epoch": 0.9864478870572587,
+      "grad_norm": 0.6509853601455688,
+      "learning_rate": 5.224744781349993e-05,
+      "loss": 0.6808,
+      "step": 6675
+    },
+    {
+      "epoch": 0.990142448432005,
+      "grad_norm": 0.6169773936271667,
+      "learning_rate": 5.205698613438976e-05,
+      "loss": 0.677,
+      "step": 6700
+    },
+    {
+      "epoch": 0.9938370098067514,
+      "grad_norm": 0.6769931316375732,
+      "learning_rate": 5.1866524455279594e-05,
+      "loss": 0.7188,
+      "step": 6725
+    },
+    {
+      "epoch": 0.9975315711814976,
+      "grad_norm": 0.6493127346038818,
+      "learning_rate": 5.167606277616944e-05,
+      "loss": 0.68,
+      "step": 6750
+    },
+    {
+      "epoch": 1.001182259639919,
+      "grad_norm": 0.6528682708740234,
+      "learning_rate": 5.148560109705928e-05,
+      "loss": 0.6982,
+      "step": 6775
+    },
+    {
+      "epoch": 1.004876821014665,
+      "grad_norm": 0.6537097692489624,
+      "learning_rate": 5.129513941794911e-05,
+      "loss": 0.6513,
+      "step": 6800
+    },
+    {
+      "epoch": 1.0085713823894114,
+      "grad_norm": 0.6426008939743042,
+      "learning_rate": 5.1104677738838945e-05,
+      "loss": 0.668,
+      "step": 6825
+    },
+    {
+      "epoch": 1.0122659437641577,
+      "grad_norm": 0.5742406249046326,
+      "learning_rate": 5.0914216059728784e-05,
+      "loss": 0.67,
+      "step": 6850
+    },
+    {
+      "epoch": 1.015960505138904,
+      "grad_norm": 0.7166649103164673,
+      "learning_rate": 5.0723754380618623e-05,
+      "loss": 0.6602,
+      "step": 6875
+    },
+    {
+      "epoch": 1.0196550665136503,
+      "grad_norm": 0.7485601305961609,
+      "learning_rate": 5.053329270150846e-05,
+      "loss": 0.6567,
+      "step": 6900
+    },
+    {
+      "epoch": 1.0233496278883965,
+      "grad_norm": 0.7126789689064026,
+      "learning_rate": 5.0342831022398296e-05,
+      "loss": 0.6624,
+      "step": 6925
+    },
+    {
+      "epoch": 1.0270441892631428,
+      "grad_norm": 0.7238374948501587,
+      "learning_rate": 5.015236934328813e-05,
+      "loss": 0.6613,
+      "step": 6950
+    },
+    {
+      "epoch": 1.0307387506378891,
+      "grad_norm": 0.6505608558654785,
+      "learning_rate": 4.996190766417797e-05,
+      "loss": 0.6554,
+      "step": 6975
+    },
+    {
+      "epoch": 1.0344333120126354,
+      "grad_norm": 0.6918332576751709,
+      "learning_rate": 4.977144598506781e-05,
+      "loss": 0.6645,
+      "step": 7000
+    },
+    {
+      "epoch": 1.0381278733873818,
+      "grad_norm": 0.5876255035400391,
+      "learning_rate": 4.9580984305957646e-05,
+      "loss": 0.6638,
+      "step": 7025
+    },
+    {
+      "epoch": 1.0418224347621279,
+      "grad_norm": 0.7554610967636108,
+      "learning_rate": 4.939052262684748e-05,
+      "loss": 0.6742,
+      "step": 7050
+    },
+    {
+      "epoch": 1.0455169961368742,
+      "grad_norm": 0.6300481557846069,
+      "learning_rate": 4.920006094773732e-05,
+      "loss": 0.6409,
+      "step": 7075
+    },
+    {
+      "epoch": 1.0492115575116205,
+      "grad_norm": 0.5924395322799683,
+      "learning_rate": 4.900959926862715e-05,
+      "loss": 0.668,
+      "step": 7100
+    },
+    {
+      "epoch": 1.0529061188863669,
+      "grad_norm": 0.6832597851753235,
+      "learning_rate": 4.881913758951699e-05,
+      "loss": 0.6431,
+      "step": 7125
+    },
+    {
+      "epoch": 1.0566006802611132,
+      "grad_norm": 0.702418863773346,
+      "learning_rate": 4.862867591040683e-05,
+      "loss": 0.6463,
+      "step": 7150
+    },
+    {
+      "epoch": 1.0602952416358593,
+      "grad_norm": 0.6264967918395996,
+      "learning_rate": 4.843821423129666e-05,
+      "loss": 0.653,
+      "step": 7175
+    },
+    {
+      "epoch": 1.0639898030106056,
+      "grad_norm": 0.6441030502319336,
+      "learning_rate": 4.82477525521865e-05,
+      "loss": 0.6415,
+      "step": 7200
+    },
+    {
+      "epoch": 1.067684364385352,
+      "grad_norm": 0.5445654392242432,
+      "learning_rate": 4.805729087307634e-05,
+      "loss": 0.6516,
+      "step": 7225
+    },
+    {
+      "epoch": 1.0713789257600983,
+      "grad_norm": 0.634982168674469,
+      "learning_rate": 4.786682919396618e-05,
+      "loss": 0.6617,
+      "step": 7250
+    },
+    {
+      "epoch": 1.0750734871348446,
+      "grad_norm": 0.5670004487037659,
+      "learning_rate": 4.7676367514856013e-05,
+      "loss": 0.644,
+      "step": 7275
+    },
+    {
+      "epoch": 1.0787680485095907,
+      "grad_norm": 0.6136172413825989,
+      "learning_rate": 4.7485905835745846e-05,
+      "loss": 0.6404,
+      "step": 7300
+    },
+    {
+      "epoch": 1.082462609884337,
+      "grad_norm": 0.6087863445281982,
+      "learning_rate": 4.7295444156635686e-05,
+      "loss": 0.666,
+      "step": 7325
+    },
+    {
+      "epoch": 1.0861571712590834,
+      "grad_norm": 0.54926997423172,
+      "learning_rate": 4.7104982477525525e-05,
+      "loss": 0.6157,
+      "step": 7350
+    },
+    {
+      "epoch": 1.0898517326338297,
+      "grad_norm": 0.6426320672035217,
+      "learning_rate": 4.6914520798415364e-05,
+      "loss": 0.6349,
+      "step": 7375
+    },
+    {
+      "epoch": 1.093546294008576,
+      "grad_norm": 0.5854539275169373,
+      "learning_rate": 4.67240591193052e-05,
+      "loss": 0.6583,
+      "step": 7400
+    },
+    {
+      "epoch": 1.0972408553833224,
+      "grad_norm": 0.7021641731262207,
+      "learning_rate": 4.6533597440195036e-05,
+      "loss": 0.6682,
+      "step": 7425
+    },
+    {
+      "epoch": 1.1009354167580685,
+      "grad_norm": 0.7356472611427307,
+      "learning_rate": 4.634313576108487e-05,
+      "loss": 0.6563,
+      "step": 7450
+    },
+    {
+      "epoch": 1.1046299781328148,
+      "grad_norm": 0.6147669553756714,
+      "learning_rate": 4.615267408197471e-05,
+      "loss": 0.667,
+      "step": 7475
+    },
+    {
+      "epoch": 1.1083245395075612,
+      "grad_norm": 0.6394315958023071,
+      "learning_rate": 4.596221240286455e-05,
+      "loss": 0.6737,
+      "step": 7500
+    },
+    {
+      "epoch": 1.1120191008823075,
+      "grad_norm": 0.7234614491462708,
+      "learning_rate": 4.577175072375438e-05,
+      "loss": 0.6556,
+      "step": 7525
+    },
+    {
+      "epoch": 1.1157136622570538,
+      "grad_norm": 0.6812229156494141,
+      "learning_rate": 4.558128904464422e-05,
+      "loss": 0.6544,
+      "step": 7550
+    },
+    {
+      "epoch": 1.1194082236318,
+      "grad_norm": 0.6218217611312866,
+      "learning_rate": 4.539082736553405e-05,
+      "loss": 0.668,
+      "step": 7575
+    },
+    {
+      "epoch": 1.1231027850065463,
+      "grad_norm": 0.8202681541442871,
+      "learning_rate": 4.52003656864239e-05,
+      "loss": 0.679,
+      "step": 7600
+    },
+    {
+      "epoch": 1.1267973463812926,
+      "grad_norm": 0.5360725522041321,
+      "learning_rate": 4.500990400731373e-05,
+      "loss": 0.6463,
+      "step": 7625
+    },
+    {
+      "epoch": 1.130491907756039,
+      "grad_norm": 0.6142716407775879,
+      "learning_rate": 4.481944232820357e-05,
+      "loss": 0.659,
+      "step": 7650
+    },
+    {
+      "epoch": 1.1341864691307852,
+      "grad_norm": 0.619349479675293,
+      "learning_rate": 4.4628980649093404e-05,
+      "loss": 0.6724,
+      "step": 7675
+    },
+    {
+      "epoch": 1.1378810305055314,
+      "grad_norm": 0.6891987323760986,
+      "learning_rate": 4.4438518969983236e-05,
+      "loss": 0.6509,
+      "step": 7700
+    },
+    {
+      "epoch": 1.1415755918802777,
+      "grad_norm": 0.7174720168113708,
+      "learning_rate": 4.424805729087308e-05,
+      "loss": 0.6715,
+      "step": 7725
+    },
+    {
+      "epoch": 1.145270153255024,
+      "grad_norm": 0.7424497008323669,
+      "learning_rate": 4.4057595611762915e-05,
+      "loss": 0.6449,
+      "step": 7750
+    },
+    {
+      "epoch": 1.1489647146297703,
+      "grad_norm": 0.6533998847007751,
+      "learning_rate": 4.3867133932652754e-05,
+      "loss": 0.6528,
+      "step": 7775
+    },
+    {
+      "epoch": 1.1526592760045167,
+      "grad_norm": 0.7500383853912354,
+      "learning_rate": 4.367667225354259e-05,
+      "loss": 0.6592,
+      "step": 7800
+    },
+    {
+      "epoch": 1.156353837379263,
+      "grad_norm": 0.6293950080871582,
+      "learning_rate": 4.3486210574432427e-05,
+      "loss": 0.6584,
+      "step": 7825
+    },
+    {
+      "epoch": 1.1600483987540091,
+      "grad_norm": 0.8463473320007324,
+      "learning_rate": 4.3295748895322266e-05,
+      "loss": 0.6656,
+      "step": 7850
+    },
+    {
+      "epoch": 1.1637429601287554,
+      "grad_norm": 0.6918061971664429,
+      "learning_rate": 4.31052872162121e-05,
+      "loss": 0.6603,
+      "step": 7875
+    },
+    {
+      "epoch": 1.1674375215035018,
+      "grad_norm": 0.5433516502380371,
+      "learning_rate": 4.291482553710194e-05,
+      "loss": 0.6422,
+      "step": 7900
+    },
+    {
+      "epoch": 1.171132082878248,
+      "grad_norm": 0.6414408087730408,
+      "learning_rate": 4.272436385799177e-05,
+      "loss": 0.6279,
+      "step": 7925
+    },
+    {
+      "epoch": 1.1748266442529944,
+      "grad_norm": 0.814218282699585,
+      "learning_rate": 4.253390217888161e-05,
+      "loss": 0.6673,
+      "step": 7950
+    },
+    {
+      "epoch": 1.1785212056277405,
+      "grad_norm": 0.7378386855125427,
+      "learning_rate": 4.234344049977145e-05,
+      "loss": 0.6651,
+      "step": 7975
+    },
+    {
+      "epoch": 1.1822157670024869,
+      "grad_norm": 0.6620386242866516,
+      "learning_rate": 4.215297882066129e-05,
+      "loss": 0.6984,
+      "step": 8000
+    },
+    {
+      "epoch": 1.1859103283772332,
+      "grad_norm": 0.6845581531524658,
+      "learning_rate": 4.196251714155112e-05,
+      "loss": 0.6524,
+      "step": 8025
+    },
+    {
+      "epoch": 1.1896048897519795,
+      "grad_norm": 0.7139785289764404,
+      "learning_rate": 4.1772055462440954e-05,
+      "loss": 0.6453,
+      "step": 8050
+    },
+    {
+      "epoch": 1.1932994511267259,
+      "grad_norm": 0.6536353230476379,
+      "learning_rate": 4.1581593783330794e-05,
+      "loss": 0.6456,
+      "step": 8075
+    },
+    {
+      "epoch": 1.196994012501472,
+      "grad_norm": 0.6225493550300598,
+      "learning_rate": 4.139113210422063e-05,
+      "loss": 0.6192,
+      "step": 8100
+    },
+    {
+      "epoch": 1.2006885738762183,
+      "grad_norm": 0.6810159683227539,
+      "learning_rate": 4.120067042511047e-05,
+      "loss": 0.6634,
+      "step": 8125
+    },
+    {
+      "epoch": 1.2043831352509646,
+      "grad_norm": 0.5847315788269043,
+      "learning_rate": 4.1010208746000305e-05,
+      "loss": 0.6231,
+      "step": 8150
+    },
+    {
+      "epoch": 1.208077696625711,
+      "grad_norm": 0.6385469436645508,
+      "learning_rate": 4.0819747066890144e-05,
+      "loss": 0.6619,
+      "step": 8175
+    },
+    {
+      "epoch": 1.2117722580004573,
+      "grad_norm": 0.7124472260475159,
+      "learning_rate": 4.0629285387779984e-05,
+      "loss": 0.6626,
+      "step": 8200
+    },
+    {
+      "epoch": 1.2154668193752034,
+      "grad_norm": 0.658824622631073,
+      "learning_rate": 4.0438823708669817e-05,
+      "loss": 0.6653,
+      "step": 8225
+    },
+    {
+      "epoch": 1.2191613807499497,
+      "grad_norm": 0.6626468300819397,
+      "learning_rate": 4.0248362029559656e-05,
+      "loss": 0.6777,
+      "step": 8250
+    },
+    {
+      "epoch": 1.222855942124696,
+      "grad_norm": 0.6238393783569336,
+      "learning_rate": 4.005790035044949e-05,
+      "loss": 0.6622,
+      "step": 8275
+    },
+    {
+      "epoch": 1.2265505034994424,
+      "grad_norm": 0.685213565826416,
+      "learning_rate": 3.986743867133933e-05,
+      "loss": 0.6423,
+      "step": 8300
+    },
+    {
+      "epoch": 1.2302450648741887,
+      "grad_norm": 0.7486940622329712,
+      "learning_rate": 3.967697699222917e-05,
+      "loss": 0.6631,
+      "step": 8325
+    },
+    {
+      "epoch": 1.2339396262489348,
+      "grad_norm": 0.7994277477264404,
+      "learning_rate": 3.948651531311901e-05,
+      "loss": 0.6725,
+      "step": 8350
+    },
+    {
+      "epoch": 1.2376341876236812,
+      "grad_norm": 0.6204445958137512,
+      "learning_rate": 3.929605363400884e-05,
+      "loss": 0.6411,
+      "step": 8375
+    },
+    {
+      "epoch": 1.2413287489984275,
+      "grad_norm": 0.7625504732131958,
+      "learning_rate": 3.910559195489867e-05,
+      "loss": 0.6819,
+      "step": 8400
+    },
+    {
+      "epoch": 1.2450233103731738,
+      "grad_norm": 0.6892343163490295,
+      "learning_rate": 3.891513027578851e-05,
+      "loss": 0.6614,
+      "step": 8425
+    },
+    {
+      "epoch": 1.2487178717479201,
+      "grad_norm": 0.6849514245986938,
+      "learning_rate": 3.872466859667835e-05,
+      "loss": 0.6442,
+      "step": 8450
+    },
+    {
+      "epoch": 1.2524124331226663,
+      "grad_norm": 0.7257765531539917,
+      "learning_rate": 3.853420691756819e-05,
+      "loss": 0.6475,
+      "step": 8475
+    },
+    {
+      "epoch": 1.2561069944974126,
+      "grad_norm": 0.7827818393707275,
+      "learning_rate": 3.834374523845802e-05,
+      "loss": 0.6317,
+      "step": 8500
+    },
+    {
+      "epoch": 1.259801555872159,
+      "grad_norm": 0.7970981597900391,
+      "learning_rate": 3.815328355934786e-05,
+      "loss": 0.6585,
+      "step": 8525
+    },
+    {
+      "epoch": 1.2634961172469052,
+      "grad_norm": 0.7086262106895447,
+      "learning_rate": 3.7962821880237695e-05,
+      "loss": 0.6499,
+      "step": 8550
+    },
+    {
+      "epoch": 1.2671906786216516,
+      "grad_norm": 0.654151439666748,
+      "learning_rate": 3.7772360201127535e-05,
+      "loss": 0.6587,
+      "step": 8575
+    },
+    {
+      "epoch": 1.2708852399963977,
+      "grad_norm": 0.6484542489051819,
+      "learning_rate": 3.7581898522017374e-05,
+      "loss": 0.6533,
+      "step": 8600
+    },
+    {
+      "epoch": 1.274579801371144,
+      "grad_norm": 0.5822983384132385,
+      "learning_rate": 3.7391436842907207e-05,
+      "loss": 0.6535,
+      "step": 8625
+    },
+    {
+      "epoch": 1.2782743627458903,
+      "grad_norm": 0.6506041884422302,
+      "learning_rate": 3.7200975163797046e-05,
+      "loss": 0.6527,
+      "step": 8650
+    },
+    {
+      "epoch": 1.2819689241206367,
+      "grad_norm": 0.6804136037826538,
+      "learning_rate": 3.701051348468688e-05,
+      "loss": 0.642,
+      "step": 8675
+    },
+    {
+      "epoch": 1.285663485495383,
+      "grad_norm": 0.7997829914093018,
+      "learning_rate": 3.6820051805576725e-05,
+      "loss": 0.6489,
+      "step": 8700
+    },
+    {
+      "epoch": 1.2893580468701291,
+      "grad_norm": 0.7355867028236389,
+      "learning_rate": 3.662959012646656e-05,
+      "loss": 0.6777,
+      "step": 8725
+    },
+    {
+      "epoch": 1.2930526082448754,
+      "grad_norm": 9.047796249389648,
+      "learning_rate": 3.643912844735639e-05,
+      "loss": 0.6777,
+      "step": 8750
+    },
+    {
+      "epoch": 1.2967471696196218,
+      "grad_norm": 0.7236223220825195,
+      "learning_rate": 3.624866676824623e-05,
+      "loss": 0.6777,
+      "step": 8775
+    },
+    {
+      "epoch": 1.300441730994368,
+      "grad_norm": 0.6845753192901611,
+      "learning_rate": 3.605820508913607e-05,
+      "loss": 0.6284,
+      "step": 8800
+    },
+    {
+      "epoch": 1.3041362923691144,
+      "grad_norm": 0.7639452815055847,
+      "learning_rate": 3.586774341002591e-05,
+      "loss": 0.6822,
+      "step": 8825
+    },
+    {
+      "epoch": 1.3078308537438605,
+      "grad_norm": 0.6909865736961365,
+      "learning_rate": 3.567728173091574e-05,
+      "loss": 0.6737,
+      "step": 8850
+    },
+    {
+      "epoch": 1.311525415118607,
+      "grad_norm": 0.6128563284873962,
+      "learning_rate": 3.548682005180558e-05,
+      "loss": 0.666,
+      "step": 8875
+    },
+    {
+      "epoch": 1.3152199764933532,
+      "grad_norm": 0.7517656087875366,
+      "learning_rate": 3.529635837269541e-05,
+      "loss": 0.6389,
+      "step": 8900
+    },
+    {
+      "epoch": 1.3189145378680995,
+      "grad_norm": 0.7127660512924194,
+      "learning_rate": 3.510589669358525e-05,
+      "loss": 0.6334,
+      "step": 8925
+    },
+    {
+      "epoch": 1.3226090992428459,
+      "grad_norm": 0.7129451632499695,
+      "learning_rate": 3.491543501447509e-05,
+      "loss": 0.6545,
+      "step": 8950
+    },
+    {
+      "epoch": 1.3263036606175922,
+      "grad_norm": 0.7367307543754578,
+      "learning_rate": 3.4724973335364925e-05,
+      "loss": 0.6329,
+      "step": 8975
+    },
+    {
+      "epoch": 1.3299982219923385,
+      "grad_norm": 0.7707272171974182,
+      "learning_rate": 3.4534511656254764e-05,
+      "loss": 0.6469,
+      "step": 9000
+    },
+    {
+      "epoch": 1.3336927833670846,
+      "grad_norm": 0.5796623826026917,
+      "learning_rate": 3.43440499771446e-05,
+      "loss": 0.6533,
+      "step": 9025
+    },
+    {
+      "epoch": 1.337387344741831,
+      "grad_norm": 210.8633270263672,
+      "learning_rate": 3.4153588298034436e-05,
+      "loss": 0.663,
+      "step": 9050
+    },
+    {
+      "epoch": 1.3410819061165773,
+      "grad_norm": 0.6077564358711243,
+      "learning_rate": 3.3963126618924275e-05,
+      "loss": 0.6529,
+      "step": 9075
+    },
+    {
+      "epoch": 1.3447764674913236,
+      "grad_norm": 0.5756903290748596,
+      "learning_rate": 3.3772664939814115e-05,
+      "loss": 0.6379,
+      "step": 9100
+    },
+    {
+      "epoch": 1.34847102886607,
+      "grad_norm": 0.6951320171356201,
+      "learning_rate": 3.358220326070395e-05,
+      "loss": 0.6572,
+      "step": 9125
+    },
+    {
+      "epoch": 1.352165590240816,
+      "grad_norm": 0.654563307762146,
+      "learning_rate": 3.339174158159378e-05,
+      "loss": 0.6571,
+      "step": 9150
+    },
+    {
+      "epoch": 1.3558601516155624,
+      "grad_norm": 0.8268250823020935,
+      "learning_rate": 3.320127990248362e-05,
+      "loss": 0.6952,
+      "step": 9175
+    },
+    {
+      "epoch": 1.3595547129903087,
+      "grad_norm": 0.7915245890617371,
+      "learning_rate": 3.301081822337346e-05,
+      "loss": 0.6442,
+      "step": 9200
+    },
+    {
+      "epoch": 1.363249274365055,
+      "grad_norm": 0.7299513816833496,
+      "learning_rate": 3.28203565442633e-05,
+      "loss": 0.6347,
+      "step": 9225
+    },
+    {
+      "epoch": 1.3669438357398014,
+      "grad_norm": 0.6474806070327759,
+      "learning_rate": 3.262989486515313e-05,
+      "loss": 0.6604,
+      "step": 9250
+    },
+    {
+      "epoch": 1.3706383971145475,
+      "grad_norm": 0.6813268661499023,
+      "learning_rate": 3.243943318604297e-05,
+      "loss": 0.66,
+      "step": 9275
+    },
+    {
+      "epoch": 1.3743329584892938,
+      "grad_norm": 0.7166799306869507,
+      "learning_rate": 3.224897150693281e-05,
+      "loss": 0.6689,
+      "step": 9300
+    },
+    {
+      "epoch": 1.3780275198640402,
+      "grad_norm": 0.6958301663398743,
+      "learning_rate": 3.205850982782264e-05,
+      "loss": 0.6512,
+      "step": 9325
+    },
+    {
+      "epoch": 1.3817220812387865,
+      "grad_norm": 0.8137691617012024,
+      "learning_rate": 3.186804814871248e-05,
+      "loss": 0.6691,
+      "step": 9350
+    },
+    {
+      "epoch": 1.3854166426135328,
+      "grad_norm": 0.6115707159042358,
+      "learning_rate": 3.1677586469602315e-05,
+      "loss": 0.6733,
+      "step": 9375
+    },
+    {
+      "epoch": 1.389111203988279,
+      "grad_norm": 0.7478678822517395,
+      "learning_rate": 3.1487124790492154e-05,
+      "loss": 0.6514,
+      "step": 9400
+    },
+    {
+      "epoch": 1.3928057653630252,
+      "grad_norm": 0.7280460000038147,
+      "learning_rate": 3.1296663111381993e-05,
+      "loss": 0.6375,
+      "step": 9425
+    },
+    {
+      "epoch": 1.3965003267377716,
+      "grad_norm": 0.6709932088851929,
+      "learning_rate": 3.110620143227183e-05,
+      "loss": 0.6843,
+      "step": 9450
+    },
+    {
+      "epoch": 1.400194888112518,
+      "grad_norm": 0.6445898413658142,
+      "learning_rate": 3.0915739753161666e-05,
+      "loss": 0.6395,
+      "step": 9475
+    },
+    {
+      "epoch": 1.4038894494872642,
+      "grad_norm": 0.6072065830230713,
+      "learning_rate": 3.07252780740515e-05,
+      "loss": 0.6615,
+      "step": 9500
+    },
+    {
+      "epoch": 1.4075840108620103,
+      "grad_norm": 0.7841944098472595,
+      "learning_rate": 3.053481639494134e-05,
+      "loss": 0.6388,
+      "step": 9525
+    },
+    {
+      "epoch": 1.4112785722367567,
+      "grad_norm": 0.7215288281440735,
+      "learning_rate": 3.0344354715831174e-05,
+      "loss": 0.6694,
+      "step": 9550
+    },
+    {
+      "epoch": 1.414973133611503,
+      "grad_norm": 0.5916579961776733,
+      "learning_rate": 3.0153893036721016e-05,
+      "loss": 0.7004,
+      "step": 9575
+    },
+    {
+      "epoch": 1.4186676949862493,
+      "grad_norm": 0.6357461214065552,
+      "learning_rate": 2.996343135761085e-05,
+      "loss": 0.6416,
+      "step": 9600
+    },
+    {
+      "epoch": 1.4223622563609957,
+      "grad_norm": 0.735261857509613,
+      "learning_rate": 2.977296967850069e-05,
+      "loss": 0.6374,
+      "step": 9625
+    },
+    {
+      "epoch": 1.4260568177357418,
+      "grad_norm": 0.7285844087600708,
+      "learning_rate": 2.9582507999390525e-05,
+      "loss": 0.6448,
+      "step": 9650
+    },
+    {
+      "epoch": 1.429751379110488,
+      "grad_norm": 0.7573617100715637,
+      "learning_rate": 2.9392046320280357e-05,
+      "loss": 0.6672,
+      "step": 9675
+    },
+    {
+      "epoch": 1.4334459404852344,
+      "grad_norm": 0.5082629919052124,
+      "learning_rate": 2.92015846411702e-05,
+      "loss": 0.6514,
+      "step": 9700
+    },
+    {
+      "epoch": 1.4371405018599808,
+      "grad_norm": 0.6786466836929321,
+      "learning_rate": 2.9011122962060033e-05,
+      "loss": 0.6542,
+      "step": 9725
+    },
+    {
+      "epoch": 1.440835063234727,
+      "grad_norm": 0.6085937023162842,
+      "learning_rate": 2.8820661282949872e-05,
+      "loss": 0.6581,
+      "step": 9750
+    },
+    {
+      "epoch": 1.4445296246094732,
+      "grad_norm": 0.6520203351974487,
+      "learning_rate": 2.8630199603839708e-05,
+      "loss": 0.6469,
+      "step": 9775
+    },
+    {
+      "epoch": 1.4482241859842195,
+      "grad_norm": 0.5597354769706726,
+      "learning_rate": 2.8439737924729548e-05,
+      "loss": 0.6418,
+      "step": 9800
+    },
+    {
+      "epoch": 1.4519187473589659,
+      "grad_norm": 0.6233022809028625,
+      "learning_rate": 2.8249276245619384e-05,
+      "loss": 0.6371,
+      "step": 9825
+    },
+    {
+      "epoch": 1.4556133087337122,
+      "grad_norm": 0.880703866481781,
+      "learning_rate": 2.8058814566509216e-05,
+      "loss": 0.6647,
+      "step": 9850
+    },
+    {
+      "epoch": 1.4593078701084585,
+      "grad_norm": 0.6821489334106445,
+      "learning_rate": 2.786835288739906e-05,
+      "loss": 0.6545,
+      "step": 9875
+    },
+    {
+      "epoch": 1.4630024314832046,
+      "grad_norm": 0.6734182834625244,
+      "learning_rate": 2.767789120828889e-05,
+      "loss": 0.6385,
+      "step": 9900
+    },
+    {
+      "epoch": 1.466696992857951,
+      "grad_norm": 0.8161661028862,
+      "learning_rate": 2.748742952917873e-05,
+      "loss": 0.6526,
+      "step": 9925
+    },
+    {
+      "epoch": 1.4703915542326973,
+      "grad_norm": 0.6308382153511047,
+      "learning_rate": 2.7296967850068567e-05,
+      "loss": 0.6561,
+      "step": 9950
+    },
+    {
+      "epoch": 1.4740861156074436,
+      "grad_norm": 0.791493833065033,
+      "learning_rate": 2.7106506170958406e-05,
+      "loss": 0.6607,
+      "step": 9975
+    },
+    {
+      "epoch": 1.47778067698219,
+      "grad_norm": 0.7888880372047424,
+      "learning_rate": 2.6916044491848243e-05,
+      "loss": 0.6511,
+      "step": 10000
+    },
+    {
+      "epoch": 1.481475238356936,
+      "grad_norm": 0.7792957425117493,
+      "learning_rate": 2.6725582812738075e-05,
+      "loss": 0.6522,
+      "step": 10025
+    },
+    {
+      "epoch": 1.4851697997316826,
+      "grad_norm": 0.6947233080863953,
+      "learning_rate": 2.6535121133627915e-05,
+      "loss": 0.6412,
+      "step": 10050
+    },
+    {
+      "epoch": 1.4888643611064287,
+      "grad_norm": 0.6176926493644714,
+      "learning_rate": 2.634465945451775e-05,
+      "loss": 0.6486,
+      "step": 10075
+    },
+    {
+      "epoch": 1.492558922481175,
+      "grad_norm": 0.700943112373352,
+      "learning_rate": 2.615419777540759e-05,
+      "loss": 0.6475,
+      "step": 10100
+    },
+    {
+      "epoch": 1.4962534838559214,
+      "grad_norm": 0.6516005396842957,
+      "learning_rate": 2.5963736096297426e-05,
+      "loss": 0.6589,
+      "step": 10125
+    },
+    {
+      "epoch": 1.4999480452306675,
+      "grad_norm": 0.8346360921859741,
+      "learning_rate": 2.5773274417187265e-05,
+      "loss": 0.6444,
+      "step": 10150
+    },
+    {
+      "epoch": 1.503642606605414,
+      "grad_norm": 0.6748323440551758,
+      "learning_rate": 2.55828127380771e-05,
+      "loss": 0.6539,
+      "step": 10175
+    },
+    {
+      "epoch": 1.5073371679801602,
+      "grad_norm": 0.6239715814590454,
+      "learning_rate": 2.5392351058966934e-05,
+      "loss": 0.6137,
+      "step": 10200
+    },
+    {
+      "epoch": 1.5110317293549065,
+      "grad_norm": 0.7011853456497192,
+      "learning_rate": 2.5201889379856774e-05,
+      "loss": 0.6415,
+      "step": 10225
+    },
+    {
+      "epoch": 1.5147262907296528,
+      "grad_norm": 0.6292597055435181,
+      "learning_rate": 2.501142770074661e-05,
+      "loss": 0.6341,
+      "step": 10250
+    },
+    {
+      "epoch": 1.518420852104399,
+      "grad_norm": 0.7244909405708313,
+      "learning_rate": 2.482096602163645e-05,
+      "loss": 0.658,
+      "step": 10275
+    },
+    {
+      "epoch": 1.5221154134791455,
+      "grad_norm": 0.6337189674377441,
+      "learning_rate": 2.4630504342526285e-05,
+      "loss": 0.6804,
+      "step": 10300
+    },
+    {
+      "epoch": 1.5258099748538916,
+      "grad_norm": 0.720902681350708,
+      "learning_rate": 2.444004266341612e-05,
+      "loss": 0.6819,
+      "step": 10325
+    },
+    {
+      "epoch": 1.529504536228638,
+      "grad_norm": 0.5961156487464905,
+      "learning_rate": 2.4249580984305957e-05,
+      "loss": 0.6417,
+      "step": 10350
+    },
+    {
+      "epoch": 1.5331990976033842,
+      "grad_norm": 0.8305853605270386,
+      "learning_rate": 2.4059119305195797e-05,
+      "loss": 0.6694,
+      "step": 10375
+    },
+    {
+      "epoch": 1.5368936589781304,
+      "grad_norm": 0.7062313556671143,
+      "learning_rate": 2.3868657626085633e-05,
+      "loss": 0.6587,
+      "step": 10400
+    },
+    {
+      "epoch": 1.540588220352877,
+      "grad_norm": 0.6674323081970215,
+      "learning_rate": 2.3678195946975472e-05,
+      "loss": 0.6557,
+      "step": 10425
+    },
+    {
+      "epoch": 1.544282781727623,
+      "grad_norm": 0.7407240271568298,
+      "learning_rate": 2.3487734267865308e-05,
+      "loss": 0.6599,
+      "step": 10450
+    },
+    {
+      "epoch": 1.5479773431023693,
+      "grad_norm": 0.783926248550415,
+      "learning_rate": 2.3297272588755144e-05,
+      "loss": 0.6616,
+      "step": 10475
+    },
+    {
+      "epoch": 1.5516719044771157,
+      "grad_norm": 0.6342896819114685,
+      "learning_rate": 2.310681090964498e-05,
+      "loss": 0.6747,
+      "step": 10500
+    },
+    {
+      "epoch": 1.5553664658518618,
+      "grad_norm": 0.6193211674690247,
+      "learning_rate": 2.2916349230534816e-05,
+      "loss": 0.6294,
+      "step": 10525
+    },
+    {
+      "epoch": 1.5590610272266083,
+      "grad_norm": 0.6950103640556335,
+      "learning_rate": 2.2725887551424656e-05,
+      "loss": 0.6483,
+      "step": 10550
+    },
+    {
+      "epoch": 1.5627555886013544,
+      "grad_norm": 0.7468893527984619,
+      "learning_rate": 2.253542587231449e-05,
+      "loss": 0.6542,
+      "step": 10575
+    },
+    {
+      "epoch": 1.5664501499761008,
+      "grad_norm": 0.6315162777900696,
+      "learning_rate": 2.2344964193204328e-05,
+      "loss": 0.6576,
+      "step": 10600
+    },
+    {
+      "epoch": 1.570144711350847,
+      "grad_norm": 0.7328910231590271,
+      "learning_rate": 2.2154502514094167e-05,
+      "loss": 0.6643,
+      "step": 10625
+    },
+    {
+      "epoch": 1.5738392727255934,
+      "grad_norm": 0.7641509771347046,
+      "learning_rate": 2.1964040834984e-05,
+      "loss": 0.6406,
+      "step": 10650
+    },
+    {
+      "epoch": 1.5775338341003398,
+      "grad_norm": 0.6303021311759949,
+      "learning_rate": 2.177357915587384e-05,
+      "loss": 0.6414,
+      "step": 10675
+    },
+    {
+      "epoch": 1.5812283954750859,
+      "grad_norm": 0.7340176701545715,
+      "learning_rate": 2.1583117476763675e-05,
+      "loss": 0.6676,
+      "step": 10700
+    },
+    {
+      "epoch": 1.5849229568498322,
+      "grad_norm": 0.7646533846855164,
+      "learning_rate": 2.1392655797653515e-05,
+      "loss": 0.6595,
+      "step": 10725
+    },
+    {
+      "epoch": 1.5886175182245785,
+      "grad_norm": 0.6361941695213318,
+      "learning_rate": 2.120219411854335e-05,
+      "loss": 0.6683,
+      "step": 10750
+    },
+    {
+      "epoch": 1.5923120795993249,
+      "grad_norm": 0.7954297065734863,
+      "learning_rate": 2.1011732439433187e-05,
+      "loss": 0.6389,
+      "step": 10775
+    },
+    {
+      "epoch": 1.5960066409740712,
+      "grad_norm": 0.6926315426826477,
+      "learning_rate": 2.0821270760323026e-05,
+      "loss": 0.6377,
+      "step": 10800
+    },
+    {
+      "epoch": 1.5997012023488173,
+      "grad_norm": 0.7757145762443542,
+      "learning_rate": 2.063080908121286e-05,
+      "loss": 0.6499,
+      "step": 10825
+    },
+    {
+      "epoch": 1.6033957637235636,
+      "grad_norm": 0.6862484812736511,
+      "learning_rate": 2.0440347402102698e-05,
+      "loss": 0.6465,
+      "step": 10850
+    },
+    {
+      "epoch": 1.60709032509831,
+      "grad_norm": 0.7413581013679504,
+      "learning_rate": 2.0249885722992534e-05,
+      "loss": 0.628,
+      "step": 10875
+    },
+    {
+      "epoch": 1.6107848864730563,
+      "grad_norm": 0.7850485444068909,
+      "learning_rate": 2.005942404388237e-05,
+      "loss": 0.6648,
+      "step": 10900
+    },
+    {
+      "epoch": 1.6144794478478026,
+      "grad_norm": 0.6554867029190063,
+      "learning_rate": 1.986896236477221e-05,
+      "loss": 0.6386,
+      "step": 10925
+    },
+    {
+      "epoch": 1.6181740092225487,
+      "grad_norm": 0.6911448836326599,
+      "learning_rate": 1.9678500685662046e-05,
+      "loss": 0.6474,
+      "step": 10950
+    },
+    {
+      "epoch": 1.6218685705972953,
+      "grad_norm": 0.838879406452179,
+      "learning_rate": 1.9488039006551885e-05,
+      "loss": 0.6406,
+      "step": 10975
+    },
+    {
+      "epoch": 1.6255631319720414,
+      "grad_norm": 0.678164005279541,
+      "learning_rate": 1.929757732744172e-05,
+      "loss": 0.6462,
+      "step": 11000
+    },
+    {
+      "epoch": 1.6292576933467877,
+      "grad_norm": 0.631232500076294,
+      "learning_rate": 1.9107115648331557e-05,
+      "loss": 0.6585,
+      "step": 11025
+    },
+    {
+      "epoch": 1.632952254721534,
+      "grad_norm": 1.6280548572540283,
+      "learning_rate": 1.8916653969221393e-05,
+      "loss": 0.6653,
+      "step": 11050
+    },
+    {
+      "epoch": 1.6366468160962802,
+      "grad_norm": 0.8536248207092285,
+      "learning_rate": 1.872619229011123e-05,
+      "loss": 0.6638,
+      "step": 11075
+    },
+    {
+      "epoch": 1.6403413774710267,
+      "grad_norm": 0.7218347191810608,
+      "learning_rate": 1.853573061100107e-05,
+      "loss": 0.6563,
+      "step": 11100
+    },
+    {
+      "epoch": 1.6440359388457728,
+      "grad_norm": 0.8350931406021118,
+      "learning_rate": 1.8345268931890905e-05,
+      "loss": 0.6678,
+      "step": 11125
+    },
+    {
+      "epoch": 1.6477305002205191,
+      "grad_norm": 1.3850131034851074,
+      "learning_rate": 1.815480725278074e-05,
+      "loss": 0.6555,
+      "step": 11150
+    },
+    {
+      "epoch": 1.6514250615952655,
+      "grad_norm": 0.7521851658821106,
+      "learning_rate": 1.796434557367058e-05,
+      "loss": 0.6323,
+      "step": 11175
+    },
+    {
+      "epoch": 1.6551196229700116,
+      "grad_norm": 0.702224612236023,
+      "learning_rate": 1.7773883894560413e-05,
+      "loss": 0.6556,
+      "step": 11200
+    },
+    {
+      "epoch": 1.6588141843447581,
+      "grad_norm": 0.7224965691566467,
+      "learning_rate": 1.7583422215450252e-05,
+      "loss": 0.6762,
+      "step": 11225
+    },
+    {
+      "epoch": 1.6625087457195042,
+      "grad_norm": 0.7941840291023254,
+      "learning_rate": 1.7392960536340088e-05,
+      "loss": 0.6327,
+      "step": 11250
+    },
+    {
+      "epoch": 1.6662033070942506,
+      "grad_norm": 0.708652138710022,
+      "learning_rate": 1.7202498857229928e-05,
+      "loss": 0.6487,
+      "step": 11275
+    },
+    {
+      "epoch": 1.669897868468997,
+      "grad_norm": 0.8155368566513062,
+      "learning_rate": 1.7012037178119764e-05,
+      "loss": 0.6683,
+      "step": 11300
+    },
+    {
+      "epoch": 1.673592429843743,
+      "grad_norm": 0.670620858669281,
+      "learning_rate": 1.68215754990096e-05,
+      "loss": 0.6585,
+      "step": 11325
+    },
+    {
+      "epoch": 1.6772869912184896,
+      "grad_norm": 0.8028390407562256,
+      "learning_rate": 1.663111381989944e-05,
+      "loss": 0.6455,
+      "step": 11350
+    },
+    {
+      "epoch": 1.6809815525932357,
+      "grad_norm": 0.7525009512901306,
+      "learning_rate": 1.644065214078927e-05,
+      "loss": 0.6543,
+      "step": 11375
+    },
+    {
+      "epoch": 1.684676113967982,
+      "grad_norm": 0.7528089284896851,
+      "learning_rate": 1.625019046167911e-05,
+      "loss": 0.6513,
+      "step": 11400
+    },
+    {
+      "epoch": 1.6883706753427283,
+      "grad_norm": 0.7208414077758789,
+      "learning_rate": 1.6059728782568947e-05,
+      "loss": 0.6307,
+      "step": 11425
+    },
+    {
+      "epoch": 1.6920652367174744,
+      "grad_norm": 0.7996485829353333,
+      "learning_rate": 1.5869267103458783e-05,
+      "loss": 0.6273,
+      "step": 11450
+    },
+    {
+      "epoch": 1.695759798092221,
+      "grad_norm": 0.6856933832168579,
+      "learning_rate": 1.5678805424348623e-05,
+      "loss": 0.6662,
+      "step": 11475
+    },
+    {
+      "epoch": 1.699454359466967,
+      "grad_norm": 0.7587810158729553,
+      "learning_rate": 1.548834374523846e-05,
+      "loss": 0.668,
+      "step": 11500
+    },
+    {
+      "epoch": 1.7031489208417134,
+      "grad_norm": 0.7210506200790405,
+      "learning_rate": 1.5297882066128298e-05,
+      "loss": 0.6477,
+      "step": 11525
+    },
+    {
+      "epoch": 1.7068434822164598,
+      "grad_norm": 0.6589523553848267,
+      "learning_rate": 1.510742038701813e-05,
+      "loss": 0.6611,
+      "step": 11550
+    },
+    {
+      "epoch": 1.7105380435912059,
+      "grad_norm": 0.6659300923347473,
+      "learning_rate": 1.4916958707907968e-05,
+      "loss": 0.6529,
+      "step": 11575
+    },
+    {
+      "epoch": 1.7142326049659524,
+      "grad_norm": 0.7367228269577026,
+      "learning_rate": 1.4726497028797806e-05,
+      "loss": 0.6601,
+      "step": 11600
+    },
+    {
+      "epoch": 1.7179271663406985,
+      "grad_norm": 0.7335773706436157,
+      "learning_rate": 1.4536035349687644e-05,
+      "loss": 0.6413,
+      "step": 11625
+    },
+    {
+      "epoch": 1.7216217277154449,
+      "grad_norm": 0.7640318274497986,
+      "learning_rate": 1.434557367057748e-05,
+      "loss": 0.6602,
+      "step": 11650
+    },
+    {
+      "epoch": 1.7253162890901912,
+      "grad_norm": 0.6898975968360901,
+      "learning_rate": 1.4155111991467318e-05,
+      "loss": 0.6365,
+      "step": 11675
+    },
+    {
+      "epoch": 1.7290108504649373,
+      "grad_norm": 0.7251124978065491,
+      "learning_rate": 1.3964650312357155e-05,
+      "loss": 0.6294,
+      "step": 11700
+    },
+    {
+      "epoch": 1.7327054118396839,
+      "grad_norm": 0.6592761278152466,
+      "learning_rate": 1.3774188633246993e-05,
+      "loss": 0.6788,
+      "step": 11725
+    },
+    {
+      "epoch": 1.73639997321443,
+      "grad_norm": 0.667373776435852,
+      "learning_rate": 1.3583726954136827e-05,
+      "loss": 0.6357,
+      "step": 11750
+    },
+    {
+      "epoch": 1.7400945345891763,
+      "grad_norm": 0.6673570871353149,
+      "learning_rate": 1.3393265275026665e-05,
+      "loss": 0.655,
+      "step": 11775
+    },
+    {
+      "epoch": 1.7437890959639226,
+      "grad_norm": 0.7344043254852295,
+      "learning_rate": 1.3202803595916501e-05,
+      "loss": 0.6527,
+      "step": 11800
+    },
+    {
+      "epoch": 1.747483657338669,
+      "grad_norm": 0.7692918181419373,
+      "learning_rate": 1.3012341916806339e-05,
+      "loss": 0.6587,
+      "step": 11825
+    },
+    {
+      "epoch": 1.7511782187134153,
+      "grad_norm": 0.7446296811103821,
+      "learning_rate": 1.2821880237696177e-05,
+      "loss": 0.6758,
+      "step": 11850
+    },
+    {
+      "epoch": 1.7548727800881614,
+      "grad_norm": 0.712960422039032,
+      "learning_rate": 1.2631418558586014e-05,
+      "loss": 0.6436,
+      "step": 11875
+    },
+    {
+      "epoch": 1.7585673414629077,
+      "grad_norm": 0.9338545799255371,
+      "learning_rate": 1.244095687947585e-05,
+      "loss": 0.684,
+      "step": 11900
+    },
+    {
+      "epoch": 1.762261902837654,
+      "grad_norm": 0.844122588634491,
+      "learning_rate": 1.2250495200365688e-05,
+      "loss": 0.6728,
+      "step": 11925
+    },
+    {
+      "epoch": 1.7659564642124004,
+      "grad_norm": 0.7671127915382385,
+      "learning_rate": 1.2060033521255524e-05,
+      "loss": 0.6519,
+      "step": 11950
+    },
+    {
+      "epoch": 1.7696510255871467,
+      "grad_norm": 0.6529008150100708,
+      "learning_rate": 1.186957184214536e-05,
+      "loss": 0.646,
+      "step": 11975
+    },
+    {
+      "epoch": 1.7733455869618928,
+      "grad_norm": 0.7962942123413086,
+      "learning_rate": 1.1679110163035198e-05,
+      "loss": 0.6378,
+      "step": 12000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 13532,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.800279870658046e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-12000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddec6eef92f76dd21b66ba65fc3f8486e2d925551fb3a26f493b39225b02363f
+size 5969

checkpoint-13000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Qwen3-8B-Base
+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 0.15.2

checkpoint-13000/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen3-8B-Base",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-13000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a9abbfe49044532fb1112f8320ad852e1a0c9d560fc3291536dbe863d66459b
+size 2838563408

checkpoint-13000/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
+}

checkpoint-13000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:210da07cb0972568522d38c59b1420a0e798fe143000ebdc456fbacda013d756
+size 2706136909

checkpoint-13000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de69a2834426ff9ef8199d077e00892579278af31d8969d77f98235b5cfc010a
+size 14645