Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-178/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-267/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-356/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-445/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-89/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-178/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/qwen2.5-vl-7b-instruct-bnb-4bit
+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 0.14.0

checkpoint-178/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/qwen2.5-vl-7b-instruct-bnb-4bit",
+  "bias": "none",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:qkv|proj|gate_proj|up_proj|down_proj|q_proj|k_proj|v_proj|o_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:qkv|proj|gate_proj|up_proj|down_proj|q_proj|k_proj|v_proj|o_proj)))",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-178/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c59f1f3dc5a05a74c4fff1eef49909cd270cdac34e1c7d08aec69a0e3af0644f
+size 824439856

checkpoint-178/added_tokens.json

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

checkpoint-178/chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

checkpoint-178/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac59da060621620fac2dab537f5a1b986fb3ab704e2e2c1feeb3c23e479ed17a
+size 328469620

checkpoint-178/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

checkpoint-178/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:203e9bfabd925cb4ec7129d24877156fcee87215187c35a867e358e56a9425a4
+size 14244

checkpoint-178/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:371f59c1c99ad057b642537b7b86333152eddb482e54b0929f65049599646289
+size 988

checkpoint-178/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a15dc095bce42f318ed34948d80b4e0b4ddad0629bb7be67b22f973650c1d5c7
+size 1064

checkpoint-178/special_tokens_map.json

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

checkpoint-178/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:741c85ffe434aad73e934a73ef380c85e94cd863b8f55e1a1ad66cacb5a93dfd
+size 11422164

checkpoint-178/tokenizer_config.json

@@ -0,0 +1,210 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-178/trainer_state.json

@@ -0,0 +1,1280 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 178,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011235955056179775,
+      "grad_norm": 10.042351722717285,
+      "learning_rate": 4e-05,
+      "loss": 9.033,
+      "step": 1
+    },
+    {
+      "epoch": 0.02247191011235955,
+      "grad_norm": 10.187106132507324,
+      "learning_rate": 8e-05,
+      "loss": 9.1846,
+      "step": 2
+    },
+    {
+      "epoch": 0.033707865168539325,
+      "grad_norm": 8.38694953918457,
+      "learning_rate": 0.00012,
+      "loss": 7.9832,
+      "step": 3
+    },
+    {
+      "epoch": 0.0449438202247191,
+      "grad_norm": 5.938446521759033,
+      "learning_rate": 0.00016,
+      "loss": 5.6493,
+      "step": 4
+    },
+    {
+      "epoch": 0.056179775280898875,
+      "grad_norm": 4.586862087249756,
+      "learning_rate": 0.0002,
+      "loss": 4.0131,
+      "step": 5
+    },
+    {
+      "epoch": 0.06741573033707865,
+      "grad_norm": 4.84490442276001,
+      "learning_rate": 0.00019954545454545455,
+      "loss": 2.9931,
+      "step": 6
+    },
+    {
+      "epoch": 0.07865168539325842,
+      "grad_norm": 4.460867881774902,
+      "learning_rate": 0.0001990909090909091,
+      "loss": 2.261,
+      "step": 7
+    },
+    {
+      "epoch": 0.0898876404494382,
+      "grad_norm": 3.067777395248413,
+      "learning_rate": 0.00019863636363636364,
+      "loss": 1.8861,
+      "step": 8
+    },
+    {
+      "epoch": 0.10112359550561797,
+      "grad_norm": 1.5425913333892822,
+      "learning_rate": 0.00019818181818181821,
+      "loss": 1.4675,
+      "step": 9
+    },
+    {
+      "epoch": 0.11235955056179775,
+      "grad_norm": 1.346417784690857,
+      "learning_rate": 0.00019772727272727273,
+      "loss": 1.3642,
+      "step": 10
+    },
+    {
+      "epoch": 0.12359550561797752,
+      "grad_norm": 1.1825133562088013,
+      "learning_rate": 0.00019727272727272728,
+      "loss": 1.0109,
+      "step": 11
+    },
+    {
+      "epoch": 0.1348314606741573,
+      "grad_norm": 0.9976914525032043,
+      "learning_rate": 0.00019681818181818185,
+      "loss": 0.9873,
+      "step": 12
+    },
+    {
+      "epoch": 0.14606741573033707,
+      "grad_norm": 0.6481193900108337,
+      "learning_rate": 0.00019636363636363636,
+      "loss": 0.6746,
+      "step": 13
+    },
+    {
+      "epoch": 0.15730337078651685,
+      "grad_norm": 0.5585954189300537,
+      "learning_rate": 0.0001959090909090909,
+      "loss": 0.5289,
+      "step": 14
+    },
+    {
+      "epoch": 0.16853932584269662,
+      "grad_norm": 0.9624674916267395,
+      "learning_rate": 0.00019545454545454548,
+      "loss": 0.5552,
+      "step": 15
+    },
+    {
+      "epoch": 0.1797752808988764,
+      "grad_norm": 0.7732966542243958,
+      "learning_rate": 0.000195,
+      "loss": 0.5047,
+      "step": 16
+    },
+    {
+      "epoch": 0.19101123595505617,
+      "grad_norm": 0.7540618777275085,
+      "learning_rate": 0.00019454545454545457,
+      "loss": 0.5803,
+      "step": 17
+    },
+    {
+      "epoch": 0.20224719101123595,
+      "grad_norm": 0.9345465302467346,
+      "learning_rate": 0.0001940909090909091,
+      "loss": 0.611,
+      "step": 18
+    },
+    {
+      "epoch": 0.21348314606741572,
+      "grad_norm": 0.5613678693771362,
+      "learning_rate": 0.00019363636363636363,
+      "loss": 0.4007,
+      "step": 19
+    },
+    {
+      "epoch": 0.2247191011235955,
+      "grad_norm": 0.8053308725357056,
+      "learning_rate": 0.0001931818181818182,
+      "loss": 0.5202,
+      "step": 20
+    },
+    {
+      "epoch": 0.23595505617977527,
+      "grad_norm": 0.6621015667915344,
+      "learning_rate": 0.00019272727272727274,
+      "loss": 0.4851,
+      "step": 21
+    },
+    {
+      "epoch": 0.24719101123595505,
+      "grad_norm": 0.797894299030304,
+      "learning_rate": 0.00019227272727272726,
+      "loss": 0.5401,
+      "step": 22
+    },
+    {
+      "epoch": 0.25842696629213485,
+      "grad_norm": 0.5635455250740051,
+      "learning_rate": 0.00019181818181818183,
+      "loss": 0.4295,
+      "step": 23
+    },
+    {
+      "epoch": 0.2696629213483146,
+      "grad_norm": 0.5012619495391846,
+      "learning_rate": 0.00019136363636363638,
+      "loss": 0.3133,
+      "step": 24
+    },
+    {
+      "epoch": 0.2808988764044944,
+      "grad_norm": 0.5143508911132812,
+      "learning_rate": 0.00019090909090909092,
+      "loss": 0.3207,
+      "step": 25
+    },
+    {
+      "epoch": 0.29213483146067415,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019090909090909092,
+      "loss": 0.622,
+      "step": 26
+    },
+    {
+      "epoch": 0.30337078651685395,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019090909090909092,
+      "loss": 0.5544,
+      "step": 27
+    },
+    {
+      "epoch": 0.3146067415730337,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019090909090909092,
+      "loss": 0.4251,
+      "step": 28
+    },
+    {
+      "epoch": 0.3258426966292135,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019090909090909092,
+      "loss": 0.626,
+      "step": 29
+    },
+    {
+      "epoch": 0.33707865168539325,
+      "grad_norm": 551.2264404296875,
+      "learning_rate": 0.00019045454545454547,
+      "loss": 0.5757,
+      "step": 30
+    },
+    {
+      "epoch": 0.34831460674157305,
+      "grad_norm": 0.5639562010765076,
+      "learning_rate": 0.00019,
+      "loss": 0.3197,
+      "step": 31
+    },
+    {
+      "epoch": 0.3595505617977528,
+      "grad_norm": 0.5104588270187378,
+      "learning_rate": 0.00018954545454545455,
+      "loss": 0.2792,
+      "step": 32
+    },
+    {
+      "epoch": 0.3707865168539326,
+      "grad_norm": 0.6046687960624695,
+      "learning_rate": 0.0001890909090909091,
+      "loss": 0.4017,
+      "step": 33
+    },
+    {
+      "epoch": 0.38202247191011235,
+      "grad_norm": 0.5290363430976868,
+      "learning_rate": 0.00018863636363636364,
+      "loss": 0.2522,
+      "step": 34
+    },
+    {
+      "epoch": 0.39325842696629215,
+      "grad_norm": 0.4888989329338074,
+      "learning_rate": 0.0001881818181818182,
+      "loss": 0.2513,
+      "step": 35
+    },
+    {
+      "epoch": 0.4044943820224719,
+      "grad_norm": 0.4538341164588928,
+      "learning_rate": 0.00018772727272727273,
+      "loss": 0.2394,
+      "step": 36
+    },
+    {
+      "epoch": 0.4157303370786517,
+      "grad_norm": 0.5249782800674438,
+      "learning_rate": 0.00018727272727272728,
+      "loss": 0.3383,
+      "step": 37
+    },
+    {
+      "epoch": 0.42696629213483145,
+      "grad_norm": 0.544735312461853,
+      "learning_rate": 0.00018681818181818182,
+      "loss": 0.3345,
+      "step": 38
+    },
+    {
+      "epoch": 0.43820224719101125,
+      "grad_norm": 0.3868374228477478,
+      "learning_rate": 0.00018636363636363636,
+      "loss": 0.2425,
+      "step": 39
+    },
+    {
+      "epoch": 0.449438202247191,
+      "grad_norm": 0.41138726472854614,
+      "learning_rate": 0.0001859090909090909,
+      "loss": 0.2625,
+      "step": 40
+    },
+    {
+      "epoch": 0.4606741573033708,
+      "grad_norm": 0.684403657913208,
+      "learning_rate": 0.00018545454545454545,
+      "loss": 0.3363,
+      "step": 41
+    },
+    {
+      "epoch": 0.47191011235955055,
+      "grad_norm": 0.4800611138343811,
+      "learning_rate": 0.00018500000000000002,
+      "loss": 0.2339,
+      "step": 42
+    },
+    {
+      "epoch": 0.48314606741573035,
+      "grad_norm": 0.47672778367996216,
+      "learning_rate": 0.00018454545454545454,
+      "loss": 0.2908,
+      "step": 43
+    },
+    {
+      "epoch": 0.4943820224719101,
+      "grad_norm": 0.44971343874931335,
+      "learning_rate": 0.00018409090909090909,
+      "loss": 0.2553,
+      "step": 44
+    },
+    {
+      "epoch": 0.5056179775280899,
+      "grad_norm": 0.45129504799842834,
+      "learning_rate": 0.00018363636363636366,
+      "loss": 0.325,
+      "step": 45
+    },
+    {
+      "epoch": 0.5168539325842697,
+      "grad_norm": 0.48597297072410583,
+      "learning_rate": 0.00018318181818181817,
+      "loss": 0.2843,
+      "step": 46
+    },
+    {
+      "epoch": 0.5280898876404494,
+      "grad_norm": 0.3514116704463959,
+      "learning_rate": 0.00018272727272727275,
+      "loss": 0.2128,
+      "step": 47
+    },
+    {
+      "epoch": 0.5393258426966292,
+      "grad_norm": 0.46826595067977905,
+      "learning_rate": 0.0001822727272727273,
+      "loss": 0.2601,
+      "step": 48
+    },
+    {
+      "epoch": 0.550561797752809,
+      "grad_norm": 0.3118669390678406,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 0.2192,
+      "step": 49
+    },
+    {
+      "epoch": 0.5617977528089888,
+      "grad_norm": 0.37151020765304565,
+      "learning_rate": 0.00018136363636363638,
+      "loss": 0.2255,
+      "step": 50
+    },
+    {
+      "epoch": 0.5730337078651685,
+      "grad_norm": 0.4220457971096039,
+      "learning_rate": 0.00018090909090909092,
+      "loss": 0.2463,
+      "step": 51
+    },
+    {
+      "epoch": 0.5842696629213483,
+      "grad_norm": 0.298927366733551,
+      "learning_rate": 0.00018045454545454547,
+      "loss": 0.1939,
+      "step": 52
+    },
+    {
+      "epoch": 0.5955056179775281,
+      "grad_norm": 0.3494245707988739,
+      "learning_rate": 0.00018,
+      "loss": 0.2276,
+      "step": 53
+    },
+    {
+      "epoch": 0.6067415730337079,
+      "grad_norm": 0.7135240435600281,
+      "learning_rate": 0.00017954545454545456,
+      "loss": 0.316,
+      "step": 54
+    },
+    {
+      "epoch": 0.6179775280898876,
+      "grad_norm": 0.47558313608169556,
+      "learning_rate": 0.0001790909090909091,
+      "loss": 0.1915,
+      "step": 55
+    },
+    {
+      "epoch": 0.6292134831460674,
+      "grad_norm": 0.47424033284187317,
+      "learning_rate": 0.00017863636363636364,
+      "loss": 0.268,
+      "step": 56
+    },
+    {
+      "epoch": 0.6404494382022472,
+      "grad_norm": 0.3898255228996277,
+      "learning_rate": 0.0001781818181818182,
+      "loss": 0.2346,
+      "step": 57
+    },
+    {
+      "epoch": 0.651685393258427,
+      "grad_norm": 0.3044908940792084,
+      "learning_rate": 0.00017772727272727273,
+      "loss": 0.2244,
+      "step": 58
+    },
+    {
+      "epoch": 0.6629213483146067,
+      "grad_norm": 0.4012211561203003,
+      "learning_rate": 0.00017727272727272728,
+      "loss": 0.2548,
+      "step": 59
+    },
+    {
+      "epoch": 0.6741573033707865,
+      "grad_norm": 0.36978745460510254,
+      "learning_rate": 0.00017681818181818182,
+      "loss": 0.1945,
+      "step": 60
+    },
+    {
+      "epoch": 0.6853932584269663,
+      "grad_norm": 0.3404884338378906,
+      "learning_rate": 0.00017636363636363637,
+      "loss": 0.2486,
+      "step": 61
+    },
+    {
+      "epoch": 0.6966292134831461,
+      "grad_norm": 0.3647669851779938,
+      "learning_rate": 0.0001759090909090909,
+      "loss": 0.2267,
+      "step": 62
+    },
+    {
+      "epoch": 0.7078651685393258,
+      "grad_norm": 0.2504497170448303,
+      "learning_rate": 0.00017545454545454548,
+      "loss": 0.1854,
+      "step": 63
+    },
+    {
+      "epoch": 0.7191011235955056,
+      "grad_norm": 0.3424750566482544,
+      "learning_rate": 0.000175,
+      "loss": 0.2586,
+      "step": 64
+    },
+    {
+      "epoch": 0.7303370786516854,
+      "grad_norm": 0.3164011836051941,
+      "learning_rate": 0.00017454545454545454,
+      "loss": 0.217,
+      "step": 65
+    },
+    {
+      "epoch": 0.7415730337078652,
+      "grad_norm": 0.32831573486328125,
+      "learning_rate": 0.00017409090909090911,
+      "loss": 0.2326,
+      "step": 66
+    },
+    {
+      "epoch": 0.7528089887640449,
+      "grad_norm": 0.3514035940170288,
+      "learning_rate": 0.00017363636363636363,
+      "loss": 0.2591,
+      "step": 67
+    },
+    {
+      "epoch": 0.7640449438202247,
+      "grad_norm": 0.30864688754081726,
+      "learning_rate": 0.0001731818181818182,
+      "loss": 0.2073,
+      "step": 68
+    },
+    {
+      "epoch": 0.7752808988764045,
+      "grad_norm": 0.32905542850494385,
+      "learning_rate": 0.00017272727272727275,
+      "loss": 0.2224,
+      "step": 69
+    },
+    {
+      "epoch": 0.7865168539325843,
+      "grad_norm": 0.27842977643013,
+      "learning_rate": 0.00017227272727272726,
+      "loss": 0.1893,
+      "step": 70
+    },
+    {
+      "epoch": 0.797752808988764,
+      "grad_norm": 0.3048170804977417,
+      "learning_rate": 0.00017181818181818184,
+      "loss": 0.2206,
+      "step": 71
+    },
+    {
+      "epoch": 0.8089887640449438,
+      "grad_norm": 0.25344306230545044,
+      "learning_rate": 0.00017136363636363638,
+      "loss": 0.1876,
+      "step": 72
+    },
+    {
+      "epoch": 0.8202247191011236,
+      "grad_norm": 0.3092687427997589,
+      "learning_rate": 0.0001709090909090909,
+      "loss": 0.1791,
+      "step": 73
+    },
+    {
+      "epoch": 0.8314606741573034,
+      "grad_norm": 0.30857375264167786,
+      "learning_rate": 0.00017045454545454547,
+      "loss": 0.2099,
+      "step": 74
+    },
+    {
+      "epoch": 0.8426966292134831,
+      "grad_norm": 0.20455722510814667,
+      "learning_rate": 0.00017,
+      "loss": 0.1705,
+      "step": 75
+    },
+    {
+      "epoch": 0.8539325842696629,
+      "grad_norm": 0.273429274559021,
+      "learning_rate": 0.00016954545454545456,
+      "loss": 0.162,
+      "step": 76
+    },
+    {
+      "epoch": 0.8651685393258427,
+      "grad_norm": 0.25422728061676025,
+      "learning_rate": 0.0001690909090909091,
+      "loss": 0.1804,
+      "step": 77
+    },
+    {
+      "epoch": 0.8764044943820225,
+      "grad_norm": 0.2745291292667389,
+      "learning_rate": 0.00016863636363636364,
+      "loss": 0.2184,
+      "step": 78
+    },
+    {
+      "epoch": 0.8876404494382022,
+      "grad_norm": 0.30162861943244934,
+      "learning_rate": 0.0001681818181818182,
+      "loss": 0.2371,
+      "step": 79
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 0.29733604192733765,
+      "learning_rate": 0.00016772727272727273,
+      "loss": 0.2018,
+      "step": 80
+    },
+    {
+      "epoch": 0.9101123595505618,
+      "grad_norm": 0.22824084758758545,
+      "learning_rate": 0.00016727272727272728,
+      "loss": 0.1819,
+      "step": 81
+    },
+    {
+      "epoch": 0.9213483146067416,
+      "grad_norm": 0.2034444659948349,
+      "learning_rate": 0.00016681818181818182,
+      "loss": 0.1715,
+      "step": 82
+    },
+    {
+      "epoch": 0.9325842696629213,
+      "grad_norm": 0.2859365940093994,
+      "learning_rate": 0.00016636363636363637,
+      "loss": 0.2157,
+      "step": 83
+    },
+    {
+      "epoch": 0.9438202247191011,
+      "grad_norm": 0.2006848305463791,
+      "learning_rate": 0.00016590909090909094,
+      "loss": 0.1595,
+      "step": 84
+    },
+    {
+      "epoch": 0.9550561797752809,
+      "grad_norm": 0.3615463972091675,
+      "learning_rate": 0.00016545454545454545,
+      "loss": 0.2056,
+      "step": 85
+    },
+    {
+      "epoch": 0.9662921348314607,
+      "grad_norm": 0.24181589484214783,
+      "learning_rate": 0.000165,
+      "loss": 0.2051,
+      "step": 86
+    },
+    {
+      "epoch": 0.9775280898876404,
+      "grad_norm": 0.1747487634420395,
+      "learning_rate": 0.00016454545454545457,
+      "loss": 0.155,
+      "step": 87
+    },
+    {
+      "epoch": 0.9887640449438202,
+      "grad_norm": 0.240757554769516,
+      "learning_rate": 0.0001640909090909091,
+      "loss": 0.1786,
+      "step": 88
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.27025192975997925,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 0.1894,
+      "step": 89
+    },
+    {
+      "epoch": 1.0112359550561798,
+      "grad_norm": 0.2341006100177765,
+      "learning_rate": 0.0001631818181818182,
+      "loss": 0.2067,
+      "step": 90
+    },
+    {
+      "epoch": 1.0224719101123596,
+      "grad_norm": 0.2805992364883423,
+      "learning_rate": 0.00016272727272727272,
+      "loss": 0.223,
+      "step": 91
+    },
+    {
+      "epoch": 1.0337078651685394,
+      "grad_norm": 0.21516099572181702,
+      "learning_rate": 0.0001622727272727273,
+      "loss": 0.1891,
+      "step": 92
+    },
+    {
+      "epoch": 1.0449438202247192,
+      "grad_norm": 0.2255050241947174,
+      "learning_rate": 0.00016181818181818184,
+      "loss": 0.195,
+      "step": 93
+    },
+    {
+      "epoch": 1.0561797752808988,
+      "grad_norm": 0.278639554977417,
+      "learning_rate": 0.00016136363636363635,
+      "loss": 0.2074,
+      "step": 94
+    },
+    {
+      "epoch": 1.0674157303370786,
+      "grad_norm": 0.2584143877029419,
+      "learning_rate": 0.00016090909090909092,
+      "loss": 0.2121,
+      "step": 95
+    },
+    {
+      "epoch": 1.0786516853932584,
+      "grad_norm": 0.2629978358745575,
+      "learning_rate": 0.00016045454545454547,
+      "loss": 0.2038,
+      "step": 96
+    },
+    {
+      "epoch": 1.0898876404494382,
+      "grad_norm": 0.2283640205860138,
+      "learning_rate": 0.00016,
+      "loss": 0.1768,
+      "step": 97
+    },
+    {
+      "epoch": 1.101123595505618,
+      "grad_norm": 0.2216864973306656,
+      "learning_rate": 0.00015954545454545456,
+      "loss": 0.1989,
+      "step": 98
+    },
+    {
+      "epoch": 1.1123595505617978,
+      "grad_norm": 0.18183070421218872,
+      "learning_rate": 0.0001590909090909091,
+      "loss": 0.1631,
+      "step": 99
+    },
+    {
+      "epoch": 1.1235955056179776,
+      "grad_norm": 0.19485391676425934,
+      "learning_rate": 0.00015863636363636365,
+      "loss": 0.1748,
+      "step": 100
+    },
+    {
+      "epoch": 1.1348314606741572,
+      "grad_norm": 0.2579084038734436,
+      "learning_rate": 0.0001581818181818182,
+      "loss": 0.2012,
+      "step": 101
+    },
+    {
+      "epoch": 1.146067415730337,
+      "grad_norm": 0.1952996402978897,
+      "learning_rate": 0.00015772727272727273,
+      "loss": 0.1634,
+      "step": 102
+    },
+    {
+      "epoch": 1.1573033707865168,
+      "grad_norm": 0.20118536055088043,
+      "learning_rate": 0.00015727272727272728,
+      "loss": 0.1839,
+      "step": 103
+    },
+    {
+      "epoch": 1.1685393258426966,
+      "grad_norm": 0.23753251135349274,
+      "learning_rate": 0.00015681818181818182,
+      "loss": 0.1861,
+      "step": 104
+    },
+    {
+      "epoch": 1.1797752808988764,
+      "grad_norm": 0.26496222615242004,
+      "learning_rate": 0.00015636363636363637,
+      "loss": 0.226,
+      "step": 105
+    },
+    {
+      "epoch": 1.1910112359550562,
+      "grad_norm": 0.17998002469539642,
+      "learning_rate": 0.0001559090909090909,
+      "loss": 0.1595,
+      "step": 106
+    },
+    {
+      "epoch": 1.202247191011236,
+      "grad_norm": 0.25317177176475525,
+      "learning_rate": 0.00015545454545454546,
+      "loss": 0.1825,
+      "step": 107
+    },
+    {
+      "epoch": 1.2134831460674158,
+      "grad_norm": 0.20935533940792084,
+      "learning_rate": 0.000155,
+      "loss": 0.1747,
+      "step": 108
+    },
+    {
+      "epoch": 1.2247191011235956,
+      "grad_norm": 0.23691172897815704,
+      "learning_rate": 0.00015454545454545454,
+      "loss": 0.2247,
+      "step": 109
+    },
+    {
+      "epoch": 1.2359550561797752,
+      "grad_norm": 0.22647719085216522,
+      "learning_rate": 0.00015409090909090912,
+      "loss": 0.1829,
+      "step": 110
+    },
+    {
+      "epoch": 1.247191011235955,
+      "grad_norm": 0.23936079442501068,
+      "learning_rate": 0.00015363636363636363,
+      "loss": 0.1938,
+      "step": 111
+    },
+    {
+      "epoch": 1.2584269662921348,
+      "grad_norm": 0.19330653548240662,
+      "learning_rate": 0.00015318181818181818,
+      "loss": 0.1603,
+      "step": 112
+    },
+    {
+      "epoch": 1.2696629213483146,
+      "grad_norm": 0.19124047458171844,
+      "learning_rate": 0.00015272727272727275,
+      "loss": 0.184,
+      "step": 113
+    },
+    {
+      "epoch": 1.2808988764044944,
+      "grad_norm": 0.1912234127521515,
+      "learning_rate": 0.00015227272727272727,
+      "loss": 0.1659,
+      "step": 114
+    },
+    {
+      "epoch": 1.2921348314606742,
+      "grad_norm": 0.1903829127550125,
+      "learning_rate": 0.0001518181818181818,
+      "loss": 0.1755,
+      "step": 115
+    },
+    {
+      "epoch": 1.303370786516854,
+      "grad_norm": 0.1836494654417038,
+      "learning_rate": 0.00015136363636363638,
+      "loss": 0.1575,
+      "step": 116
+    },
+    {
+      "epoch": 1.3146067415730336,
+      "grad_norm": 0.21919198334217072,
+      "learning_rate": 0.0001509090909090909,
+      "loss": 0.1978,
+      "step": 117
+    },
+    {
+      "epoch": 1.3258426966292136,
+      "grad_norm": 0.22532597184181213,
+      "learning_rate": 0.00015045454545454547,
+      "loss": 0.1604,
+      "step": 118
+    },
+    {
+      "epoch": 1.3370786516853932,
+      "grad_norm": 0.22674380242824554,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.183,
+      "step": 119
+    },
+    {
+      "epoch": 1.348314606741573,
+      "grad_norm": 0.23995709419250488,
+      "learning_rate": 0.00014954545454545453,
+      "loss": 0.1777,
+      "step": 120
+    },
+    {
+      "epoch": 1.3595505617977528,
+      "grad_norm": 0.15110474824905396,
+      "learning_rate": 0.0001490909090909091,
+      "loss": 0.154,
+      "step": 121
+    },
+    {
+      "epoch": 1.3707865168539326,
+      "grad_norm": 0.1769479662179947,
+      "learning_rate": 0.00014863636363636365,
+      "loss": 0.1824,
+      "step": 122
+    },
+    {
+      "epoch": 1.3820224719101124,
+      "grad_norm": 0.2355855405330658,
+      "learning_rate": 0.0001481818181818182,
+      "loss": 0.187,
+      "step": 123
+    },
+    {
+      "epoch": 1.3932584269662922,
+      "grad_norm": 0.21928639709949493,
+      "learning_rate": 0.00014772727272727274,
+      "loss": 0.2154,
+      "step": 124
+    },
+    {
+      "epoch": 1.404494382022472,
+      "grad_norm": 0.23884353041648865,
+      "learning_rate": 0.00014727272727272728,
+      "loss": 0.2144,
+      "step": 125
+    },
+    {
+      "epoch": 1.4157303370786516,
+      "grad_norm": 0.19905094802379608,
+      "learning_rate": 0.00014681818181818182,
+      "loss": 0.1758,
+      "step": 126
+    },
+    {
+      "epoch": 1.4269662921348314,
+      "grad_norm": 0.20008406043052673,
+      "learning_rate": 0.00014636363636363637,
+      "loss": 0.1988,
+      "step": 127
+    },
+    {
+      "epoch": 1.4382022471910112,
+      "grad_norm": 0.14788155257701874,
+      "learning_rate": 0.0001459090909090909,
+      "loss": 0.1591,
+      "step": 128
+    },
+    {
+      "epoch": 1.449438202247191,
+      "grad_norm": 0.17816966772079468,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 0.1607,
+      "step": 129
+    },
+    {
+      "epoch": 1.4606741573033708,
+      "grad_norm": 0.2414962351322174,
+      "learning_rate": 0.000145,
+      "loss": 0.1988,
+      "step": 130
+    },
+    {
+      "epoch": 1.4719101123595506,
+      "grad_norm": 0.21710173785686493,
+      "learning_rate": 0.00014454545454545457,
+      "loss": 0.1749,
+      "step": 131
+    },
+    {
+      "epoch": 1.4831460674157304,
+      "grad_norm": 0.30704858899116516,
+      "learning_rate": 0.0001440909090909091,
+      "loss": 0.2106,
+      "step": 132
+    },
+    {
+      "epoch": 1.49438202247191,
+      "grad_norm": 0.22256992757320404,
+      "learning_rate": 0.00014363636363636363,
+      "loss": 0.1828,
+      "step": 133
+    },
+    {
+      "epoch": 1.50561797752809,
+      "grad_norm": 0.2698194980621338,
+      "learning_rate": 0.0001431818181818182,
+      "loss": 0.2418,
+      "step": 134
+    },
+    {
+      "epoch": 1.5168539325842696,
+      "grad_norm": 0.22738061845302582,
+      "learning_rate": 0.00014272727272727272,
+      "loss": 0.2023,
+      "step": 135
+    },
+    {
+      "epoch": 1.5280898876404494,
+      "grad_norm": 0.2749398946762085,
+      "learning_rate": 0.00014227272727272727,
+      "loss": 0.2201,
+      "step": 136
+    },
+    {
+      "epoch": 1.5393258426966292,
+      "grad_norm": 0.20003195106983185,
+      "learning_rate": 0.00014181818181818184,
+      "loss": 0.1658,
+      "step": 137
+    },
+    {
+      "epoch": 1.550561797752809,
+      "grad_norm": 0.1827768236398697,
+      "learning_rate": 0.00014136363636363635,
+      "loss": 0.1787,
+      "step": 138
+    },
+    {
+      "epoch": 1.5617977528089888,
+      "grad_norm": 0.20226892828941345,
+      "learning_rate": 0.00014090909090909093,
+      "loss": 0.1812,
+      "step": 139
+    },
+    {
+      "epoch": 1.5730337078651684,
+      "grad_norm": 0.18449921905994415,
+      "learning_rate": 0.00014045454545454547,
+      "loss": 0.183,
+      "step": 140
+    },
+    {
+      "epoch": 1.5842696629213484,
+      "grad_norm": 0.22666248679161072,
+      "learning_rate": 0.00014,
+      "loss": 0.2163,
+      "step": 141
+    },
+    {
+      "epoch": 1.595505617977528,
+      "grad_norm": 0.2258187234401703,
+      "learning_rate": 0.00013954545454545456,
+      "loss": 0.2024,
+      "step": 142
+    },
+    {
+      "epoch": 1.606741573033708,
+      "grad_norm": 0.17761889100074768,
+      "learning_rate": 0.0001390909090909091,
+      "loss": 0.1822,
+      "step": 143
+    },
+    {
+      "epoch": 1.6179775280898876,
+      "grad_norm": 0.1967982053756714,
+      "learning_rate": 0.00013863636363636365,
+      "loss": 0.1768,
+      "step": 144
+    },
+    {
+      "epoch": 1.6292134831460674,
+      "grad_norm": 0.21614395081996918,
+      "learning_rate": 0.0001381818181818182,
+      "loss": 0.1941,
+      "step": 145
+    },
+    {
+      "epoch": 1.6404494382022472,
+      "grad_norm": 0.21362508833408356,
+      "learning_rate": 0.00013772727272727274,
+      "loss": 0.2053,
+      "step": 146
+    },
+    {
+      "epoch": 1.651685393258427,
+      "grad_norm": 0.1829160451889038,
+      "learning_rate": 0.00013727272727272728,
+      "loss": 0.1601,
+      "step": 147
+    },
+    {
+      "epoch": 1.6629213483146068,
+      "grad_norm": 0.19813786447048187,
+      "learning_rate": 0.00013681818181818182,
+      "loss": 0.2027,
+      "step": 148
+    },
+    {
+      "epoch": 1.6741573033707864,
+      "grad_norm": 0.19203445315361023,
+      "learning_rate": 0.00013636363636363637,
+      "loss": 0.1638,
+      "step": 149
+    },
+    {
+      "epoch": 1.6853932584269664,
+      "grad_norm": 0.1693754941225052,
+      "learning_rate": 0.0001359090909090909,
+      "loss": 0.1695,
+      "step": 150
+    },
+    {
+      "epoch": 1.696629213483146,
+      "grad_norm": 0.19884233176708221,
+      "learning_rate": 0.00013545454545454546,
+      "loss": 0.2037,
+      "step": 151
+    },
+    {
+      "epoch": 1.7078651685393258,
+      "grad_norm": 0.20025449991226196,
+      "learning_rate": 0.00013500000000000003,
+      "loss": 0.1927,
+      "step": 152
+    },
+    {
+      "epoch": 1.7191011235955056,
+      "grad_norm": 0.1659104973077774,
+      "learning_rate": 0.00013454545454545455,
+      "loss": 0.164,
+      "step": 153
+    },
+    {
+      "epoch": 1.7303370786516854,
+      "grad_norm": 0.16635450720787048,
+      "learning_rate": 0.0001340909090909091,
+      "loss": 0.1729,
+      "step": 154
+    },
+    {
+      "epoch": 1.7415730337078652,
+      "grad_norm": 0.2119787037372589,
+      "learning_rate": 0.00013363636363636366,
+      "loss": 0.1761,
+      "step": 155
+    },
+    {
+      "epoch": 1.7528089887640448,
+      "grad_norm": 0.1592678278684616,
+      "learning_rate": 0.00013318181818181818,
+      "loss": 0.1582,
+      "step": 156
+    },
+    {
+      "epoch": 1.7640449438202248,
+      "grad_norm": 0.20228628814220428,
+      "learning_rate": 0.00013272727272727275,
+      "loss": 0.1833,
+      "step": 157
+    },
+    {
+      "epoch": 1.7752808988764044,
+      "grad_norm": 0.19576573371887207,
+      "learning_rate": 0.0001322727272727273,
+      "loss": 0.1716,
+      "step": 158
+    },
+    {
+      "epoch": 1.7865168539325844,
+      "grad_norm": 0.17609822750091553,
+      "learning_rate": 0.0001318181818181818,
+      "loss": 0.1566,
+      "step": 159
+    },
+    {
+      "epoch": 1.797752808988764,
+      "grad_norm": 0.19382323324680328,
+      "learning_rate": 0.00013136363636363638,
+      "loss": 0.1637,
+      "step": 160
+    },
+    {
+      "epoch": 1.8089887640449438,
+      "grad_norm": 0.26488256454467773,
+      "learning_rate": 0.00013090909090909093,
+      "loss": 0.2064,
+      "step": 161
+    },
+    {
+      "epoch": 1.8202247191011236,
+      "grad_norm": 0.23723822832107544,
+      "learning_rate": 0.00013045454545454544,
+      "loss": 0.177,
+      "step": 162
+    },
+    {
+      "epoch": 1.8314606741573034,
+      "grad_norm": 0.1890057623386383,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 0.1784,
+      "step": 163
+    },
+    {
+      "epoch": 1.8426966292134832,
+      "grad_norm": 0.1911257803440094,
+      "learning_rate": 0.00012954545454545456,
+      "loss": 0.1788,
+      "step": 164
+    },
+    {
+      "epoch": 1.8539325842696628,
+      "grad_norm": 0.2343178540468216,
+      "learning_rate": 0.0001290909090909091,
+      "loss": 0.1833,
+      "step": 165
+    },
+    {
+      "epoch": 1.8651685393258428,
+      "grad_norm": 0.1506495475769043,
+      "learning_rate": 0.00012863636363636365,
+      "loss": 0.1655,
+      "step": 166
+    },
+    {
+      "epoch": 1.8764044943820224,
+      "grad_norm": 0.17160733044147491,
+      "learning_rate": 0.0001281818181818182,
+      "loss": 0.1586,
+      "step": 167
+    },
+    {
+      "epoch": 1.8876404494382022,
+      "grad_norm": 0.13511358201503754,
+      "learning_rate": 0.00012772727272727274,
+      "loss": 0.1439,
+      "step": 168
+    },
+    {
+      "epoch": 1.898876404494382,
+      "grad_norm": 0.1821577399969101,
+      "learning_rate": 0.00012727272727272728,
+      "loss": 0.1973,
+      "step": 169
+    },
+    {
+      "epoch": 1.9101123595505618,
+      "grad_norm": 0.18846295773983002,
+      "learning_rate": 0.00012681818181818183,
+      "loss": 0.1767,
+      "step": 170
+    },
+    {
+      "epoch": 1.9213483146067416,
+      "grad_norm": 0.17300470173358917,
+      "learning_rate": 0.00012636363636363637,
+      "loss": 0.1726,
+      "step": 171
+    },
+    {
+      "epoch": 1.9325842696629212,
+      "grad_norm": 0.20833244919776917,
+      "learning_rate": 0.00012590909090909091,
+      "loss": 0.2248,
+      "step": 172
+    },
+    {
+      "epoch": 1.9438202247191012,
+      "grad_norm": 0.17537686228752136,
+      "learning_rate": 0.00012545454545454546,
+      "loss": 0.147,
+      "step": 173
+    },
+    {
+      "epoch": 1.9550561797752808,
+      "grad_norm": 0.17684531211853027,
+      "learning_rate": 0.000125,
+      "loss": 0.1774,
+      "step": 174
+    },
+    {
+      "epoch": 1.9662921348314608,
+      "grad_norm": 0.20325636863708496,
+      "learning_rate": 0.00012454545454545455,
+      "loss": 0.1921,
+      "step": 175
+    },
+    {
+      "epoch": 1.9775280898876404,
+      "grad_norm": 0.2229178249835968,
+      "learning_rate": 0.0001240909090909091,
+      "loss": 0.2058,
+      "step": 176
+    },
+    {
+      "epoch": 1.9887640449438202,
+      "grad_norm": 0.18187855184078217,
+      "learning_rate": 0.00012363636363636364,
+      "loss": 0.1883,
+      "step": 177
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.18570281565189362,
+      "learning_rate": 0.0001231818181818182,
+      "loss": 0.1716,
+      "step": 178
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 445,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.933479100108186e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-178/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9936502145859cfb12f653ac1259cd6cfb3aef369ebb44c3892d632b7bb2264
+size 5624

checkpoint-267/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/qwen2.5-vl-7b-instruct-bnb-4bit
+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 0.14.0

checkpoint-267/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/qwen2.5-vl-7b-instruct-bnb-4bit",
+  "bias": "none",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:qkv|proj|gate_proj|up_proj|down_proj|q_proj|k_proj|v_proj|o_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:qkv|proj|gate_proj|up_proj|down_proj|q_proj|k_proj|v_proj|o_proj)))",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-267/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:072d12d0f250d969d8c776a7e3f5cfa2c30a9ee16fcc9c7d9526855824cd4693
+size 824439856

checkpoint-267/added_tokens.json

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

checkpoint-267/chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

checkpoint-267/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71251f7633f1309679e652d6e95cc5b2f50f40fd4c03ac5bc8016220584e98f1
+size 328470068

checkpoint-267/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

checkpoint-267/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4981123ff3cf7bd5b7f76839e90e4776f747ca4c38dcb41876fa010c0dea8b23
+size 14244

checkpoint-267/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42f339b4bf088ccb402f1f4d17a9ad72f156a9e1daec0fdf398f3848f0f281a9
+size 988

checkpoint-267/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1ac584f1cade9f8e78d0f4f0d1f3eeb02460db68644a6c30b461995436427c0
+size 1064

checkpoint-267/special_tokens_map.json

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

checkpoint-267/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:741c85ffe434aad73e934a73ef380c85e94cd863b8f55e1a1ad66cacb5a93dfd
+size 11422164

checkpoint-267/tokenizer_config.json

@@ -0,0 +1,210 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-267/trainer_state.json

@@ -0,0 +1,1903 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 267,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011235955056179775,
+      "grad_norm": 10.042351722717285,
+      "learning_rate": 4e-05,
+      "loss": 9.033,
+      "step": 1
+    },
+    {
+      "epoch": 0.02247191011235955,
+      "grad_norm": 10.187106132507324,
+      "learning_rate": 8e-05,
+      "loss": 9.1846,
+      "step": 2
+    },
+    {
+      "epoch": 0.033707865168539325,
+      "grad_norm": 8.38694953918457,
+      "learning_rate": 0.00012,
+      "loss": 7.9832,
+      "step": 3
+    },
+    {
+      "epoch": 0.0449438202247191,
+      "grad_norm": 5.938446521759033,
+      "learning_rate": 0.00016,
+      "loss": 5.6493,
+      "step": 4
+    },
+    {
+      "epoch": 0.056179775280898875,
+      "grad_norm": 4.586862087249756,
+      "learning_rate": 0.0002,
+      "loss": 4.0131,
+      "step": 5
+    },
+    {
+      "epoch": 0.06741573033707865,
+      "grad_norm": 4.84490442276001,
+      "learning_rate": 0.00019954545454545455,
+      "loss": 2.9931,
+      "step": 6
+    },
+    {
+      "epoch": 0.07865168539325842,
+      "grad_norm": 4.460867881774902,
+      "learning_rate": 0.0001990909090909091,
+      "loss": 2.261,
+      "step": 7
+    },
+    {
+      "epoch": 0.0898876404494382,
+      "grad_norm": 3.067777395248413,
+      "learning_rate": 0.00019863636363636364,
+      "loss": 1.8861,
+      "step": 8
+    },
+    {
+      "epoch": 0.10112359550561797,
+      "grad_norm": 1.5425913333892822,
+      "learning_rate": 0.00019818181818181821,
+      "loss": 1.4675,
+      "step": 9
+    },
+    {
+      "epoch": 0.11235955056179775,
+      "grad_norm": 1.346417784690857,
+      "learning_rate": 0.00019772727272727273,
+      "loss": 1.3642,
+      "step": 10
+    },
+    {
+      "epoch": 0.12359550561797752,
+      "grad_norm": 1.1825133562088013,
+      "learning_rate": 0.00019727272727272728,
+      "loss": 1.0109,
+      "step": 11
+    },
+    {
+      "epoch": 0.1348314606741573,
+      "grad_norm": 0.9976914525032043,
+      "learning_rate": 0.00019681818181818185,
+      "loss": 0.9873,
+      "step": 12
+    },
+    {
+      "epoch": 0.14606741573033707,
+      "grad_norm": 0.6481193900108337,
+      "learning_rate": 0.00019636363636363636,
+      "loss": 0.6746,
+      "step": 13
+    },
+    {
+      "epoch": 0.15730337078651685,
+      "grad_norm": 0.5585954189300537,
+      "learning_rate": 0.0001959090909090909,
+      "loss": 0.5289,
+      "step": 14
+    },
+    {
+      "epoch": 0.16853932584269662,
+      "grad_norm": 0.9624674916267395,
+      "learning_rate": 0.00019545454545454548,
+      "loss": 0.5552,
+      "step": 15
+    },
+    {
+      "epoch": 0.1797752808988764,
+      "grad_norm": 0.7732966542243958,
+      "learning_rate": 0.000195,
+      "loss": 0.5047,
+      "step": 16
+    },
+    {
+      "epoch": 0.19101123595505617,
+      "grad_norm": 0.7540618777275085,
+      "learning_rate": 0.00019454545454545457,
+      "loss": 0.5803,
+      "step": 17
+    },
+    {
+      "epoch": 0.20224719101123595,
+      "grad_norm": 0.9345465302467346,
+      "learning_rate": 0.0001940909090909091,
+      "loss": 0.611,
+      "step": 18
+    },
+    {
+      "epoch": 0.21348314606741572,
+      "grad_norm": 0.5613678693771362,
+      "learning_rate": 0.00019363636363636363,
+      "loss": 0.4007,
+      "step": 19
+    },
+    {
+      "epoch": 0.2247191011235955,
+      "grad_norm": 0.8053308725357056,
+      "learning_rate": 0.0001931818181818182,
+      "loss": 0.5202,
+      "step": 20
+    },
+    {
+      "epoch": 0.23595505617977527,
+      "grad_norm": 0.6621015667915344,
+      "learning_rate": 0.00019272727272727274,
+      "loss": 0.4851,
+      "step": 21
+    },
+    {
+      "epoch": 0.24719101123595505,
+      "grad_norm": 0.797894299030304,
+      "learning_rate": 0.00019227272727272726,
+      "loss": 0.5401,
+      "step": 22
+    },
+    {
+      "epoch": 0.25842696629213485,
+      "grad_norm": 0.5635455250740051,
+      "learning_rate": 0.00019181818181818183,
+      "loss": 0.4295,
+      "step": 23
+    },
+    {
+      "epoch": 0.2696629213483146,
+      "grad_norm": 0.5012619495391846,
+      "learning_rate": 0.00019136363636363638,
+      "loss": 0.3133,
+      "step": 24
+    },
+    {
+      "epoch": 0.2808988764044944,
+      "grad_norm": 0.5143508911132812,
+      "learning_rate": 0.00019090909090909092,
+      "loss": 0.3207,
+      "step": 25
+    },
+    {
+      "epoch": 0.29213483146067415,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019090909090909092,
+      "loss": 0.622,
+      "step": 26
+    },
+    {
+      "epoch": 0.30337078651685395,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019090909090909092,
+      "loss": 0.5544,
+      "step": 27
+    },
+    {
+      "epoch": 0.3146067415730337,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019090909090909092,
+      "loss": 0.4251,
+      "step": 28
+    },
+    {
+      "epoch": 0.3258426966292135,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019090909090909092,
+      "loss": 0.626,
+      "step": 29
+    },
+    {
+      "epoch": 0.33707865168539325,
+      "grad_norm": 551.2264404296875,
+      "learning_rate": 0.00019045454545454547,
+      "loss": 0.5757,
+      "step": 30
+    },
+    {
+      "epoch": 0.34831460674157305,
+      "grad_norm": 0.5639562010765076,
+      "learning_rate": 0.00019,
+      "loss": 0.3197,
+      "step": 31
+    },
+    {
+      "epoch": 0.3595505617977528,
+      "grad_norm": 0.5104588270187378,
+      "learning_rate": 0.00018954545454545455,
+      "loss": 0.2792,
+      "step": 32
+    },
+    {
+      "epoch": 0.3707865168539326,
+      "grad_norm": 0.6046687960624695,
+      "learning_rate": 0.0001890909090909091,
+      "loss": 0.4017,
+      "step": 33
+    },
+    {
+      "epoch": 0.38202247191011235,
+      "grad_norm": 0.5290363430976868,
+      "learning_rate": 0.00018863636363636364,
+      "loss": 0.2522,
+      "step": 34
+    },
+    {
+      "epoch": 0.39325842696629215,
+      "grad_norm": 0.4888989329338074,
+      "learning_rate": 0.0001881818181818182,
+      "loss": 0.2513,
+      "step": 35
+    },
+    {
+      "epoch": 0.4044943820224719,
+      "grad_norm": 0.4538341164588928,
+      "learning_rate": 0.00018772727272727273,
+      "loss": 0.2394,
+      "step": 36
+    },
+    {
+      "epoch": 0.4157303370786517,
+      "grad_norm": 0.5249782800674438,
+      "learning_rate": 0.00018727272727272728,
+      "loss": 0.3383,
+      "step": 37
+    },
+    {
+      "epoch": 0.42696629213483145,
+      "grad_norm": 0.544735312461853,
+      "learning_rate": 0.00018681818181818182,
+      "loss": 0.3345,
+      "step": 38
+    },
+    {
+      "epoch": 0.43820224719101125,
+      "grad_norm": 0.3868374228477478,
+      "learning_rate": 0.00018636363636363636,
+      "loss": 0.2425,
+      "step": 39
+    },
+    {
+      "epoch": 0.449438202247191,
+      "grad_norm": 0.41138726472854614,
+      "learning_rate": 0.0001859090909090909,
+      "loss": 0.2625,
+      "step": 40
+    },
+    {
+      "epoch": 0.4606741573033708,
+      "grad_norm": 0.684403657913208,
+      "learning_rate": 0.00018545454545454545,
+      "loss": 0.3363,
+      "step": 41
+    },
+    {
+      "epoch": 0.47191011235955055,
+      "grad_norm": 0.4800611138343811,
+      "learning_rate": 0.00018500000000000002,
+      "loss": 0.2339,
+      "step": 42
+    },
+    {
+      "epoch": 0.48314606741573035,
+      "grad_norm": 0.47672778367996216,
+      "learning_rate": 0.00018454545454545454,
+      "loss": 0.2908,
+      "step": 43
+    },
+    {
+      "epoch": 0.4943820224719101,
+      "grad_norm": 0.44971343874931335,
+      "learning_rate": 0.00018409090909090909,
+      "loss": 0.2553,
+      "step": 44
+    },
+    {
+      "epoch": 0.5056179775280899,
+      "grad_norm": 0.45129504799842834,
+      "learning_rate": 0.00018363636363636366,
+      "loss": 0.325,
+      "step": 45
+    },
+    {
+      "epoch": 0.5168539325842697,
+      "grad_norm": 0.48597297072410583,
+      "learning_rate": 0.00018318181818181817,
+      "loss": 0.2843,
+      "step": 46
+    },
+    {
+      "epoch": 0.5280898876404494,
+      "grad_norm": 0.3514116704463959,
+      "learning_rate": 0.00018272727272727275,
+      "loss": 0.2128,
+      "step": 47
+    },
+    {
+      "epoch": 0.5393258426966292,
+      "grad_norm": 0.46826595067977905,
+      "learning_rate": 0.0001822727272727273,
+      "loss": 0.2601,
+      "step": 48
+    },
+    {
+      "epoch": 0.550561797752809,
+      "grad_norm": 0.3118669390678406,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 0.2192,
+      "step": 49
+    },
+    {
+      "epoch": 0.5617977528089888,
+      "grad_norm": 0.37151020765304565,
+      "learning_rate": 0.00018136363636363638,
+      "loss": 0.2255,
+      "step": 50
+    },
+    {
+      "epoch": 0.5730337078651685,
+      "grad_norm": 0.4220457971096039,
+      "learning_rate": 0.00018090909090909092,
+      "loss": 0.2463,
+      "step": 51
+    },
+    {
+      "epoch": 0.5842696629213483,
+      "grad_norm": 0.298927366733551,
+      "learning_rate": 0.00018045454545454547,
+      "loss": 0.1939,
+      "step": 52
+    },
+    {
+      "epoch": 0.5955056179775281,
+      "grad_norm": 0.3494245707988739,
+      "learning_rate": 0.00018,
+      "loss": 0.2276,
+      "step": 53
+    },
+    {
+      "epoch": 0.6067415730337079,
+      "grad_norm": 0.7135240435600281,
+      "learning_rate": 0.00017954545454545456,
+      "loss": 0.316,
+      "step": 54
+    },
+    {
+      "epoch": 0.6179775280898876,
+      "grad_norm": 0.47558313608169556,
+      "learning_rate": 0.0001790909090909091,
+      "loss": 0.1915,
+      "step": 55
+    },
+    {
+      "epoch": 0.6292134831460674,
+      "grad_norm": 0.47424033284187317,
+      "learning_rate": 0.00017863636363636364,
+      "loss": 0.268,
+      "step": 56
+    },
+    {
+      "epoch": 0.6404494382022472,
+      "grad_norm": 0.3898255228996277,
+      "learning_rate": 0.0001781818181818182,
+      "loss": 0.2346,
+      "step": 57
+    },
+    {
+      "epoch": 0.651685393258427,
+      "grad_norm": 0.3044908940792084,
+      "learning_rate": 0.00017772727272727273,
+      "loss": 0.2244,
+      "step": 58
+    },
+    {
+      "epoch": 0.6629213483146067,
+      "grad_norm": 0.4012211561203003,
+      "learning_rate": 0.00017727272727272728,
+      "loss": 0.2548,
+      "step": 59
+    },
+    {
+      "epoch": 0.6741573033707865,
+      "grad_norm": 0.36978745460510254,
+      "learning_rate": 0.00017681818181818182,
+      "loss": 0.1945,
+      "step": 60
+    },
+    {
+      "epoch": 0.6853932584269663,
+      "grad_norm": 0.3404884338378906,
+      "learning_rate": 0.00017636363636363637,
+      "loss": 0.2486,
+      "step": 61
+    },
+    {
+      "epoch": 0.6966292134831461,
+      "grad_norm": 0.3647669851779938,
+      "learning_rate": 0.0001759090909090909,
+      "loss": 0.2267,
+      "step": 62
+    },
+    {
+      "epoch": 0.7078651685393258,
+      "grad_norm": 0.2504497170448303,
+      "learning_rate": 0.00017545454545454548,
+      "loss": 0.1854,
+      "step": 63
+    },
+    {
+      "epoch": 0.7191011235955056,
+      "grad_norm": 0.3424750566482544,
+      "learning_rate": 0.000175,
+      "loss": 0.2586,
+      "step": 64
+    },
+    {
+      "epoch": 0.7303370786516854,
+      "grad_norm": 0.3164011836051941,
+      "learning_rate": 0.00017454545454545454,
+      "loss": 0.217,
+      "step": 65
+    },
+    {
+      "epoch": 0.7415730337078652,
+      "grad_norm": 0.32831573486328125,
+      "learning_rate": 0.00017409090909090911,
+      "loss": 0.2326,
+      "step": 66
+    },
+    {
+      "epoch": 0.7528089887640449,
+      "grad_norm": 0.3514035940170288,
+      "learning_rate": 0.00017363636363636363,
+      "loss": 0.2591,
+      "step": 67
+    },
+    {
+      "epoch": 0.7640449438202247,
+      "grad_norm": 0.30864688754081726,
+      "learning_rate": 0.0001731818181818182,
+      "loss": 0.2073,
+      "step": 68
+    },
+    {
+      "epoch": 0.7752808988764045,
+      "grad_norm": 0.32905542850494385,
+      "learning_rate": 0.00017272727272727275,
+      "loss": 0.2224,
+      "step": 69
+    },
+    {
+      "epoch": 0.7865168539325843,
+      "grad_norm": 0.27842977643013,
+      "learning_rate": 0.00017227272727272726,
+      "loss": 0.1893,
+      "step": 70
+    },
+    {
+      "epoch": 0.797752808988764,
+      "grad_norm": 0.3048170804977417,
+      "learning_rate": 0.00017181818181818184,
+      "loss": 0.2206,
+      "step": 71
+    },
+    {
+      "epoch": 0.8089887640449438,
+      "grad_norm": 0.25344306230545044,
+      "learning_rate": 0.00017136363636363638,
+      "loss": 0.1876,
+      "step": 72
+    },
+    {
+      "epoch": 0.8202247191011236,
+      "grad_norm": 0.3092687427997589,
+      "learning_rate": 0.0001709090909090909,
+      "loss": 0.1791,
+      "step": 73
+    },
+    {
+      "epoch": 0.8314606741573034,
+      "grad_norm": 0.30857375264167786,
+      "learning_rate": 0.00017045454545454547,
+      "loss": 0.2099,
+      "step": 74
+    },
+    {
+      "epoch": 0.8426966292134831,
+      "grad_norm": 0.20455722510814667,
+      "learning_rate": 0.00017,
+      "loss": 0.1705,
+      "step": 75
+    },
+    {
+      "epoch": 0.8539325842696629,
+      "grad_norm": 0.273429274559021,
+      "learning_rate": 0.00016954545454545456,
+      "loss": 0.162,
+      "step": 76
+    },
+    {
+      "epoch": 0.8651685393258427,
+      "grad_norm": 0.25422728061676025,
+      "learning_rate": 0.0001690909090909091,
+      "loss": 0.1804,
+      "step": 77
+    },
+    {
+      "epoch": 0.8764044943820225,
+      "grad_norm": 0.2745291292667389,
+      "learning_rate": 0.00016863636363636364,
+      "loss": 0.2184,
+      "step": 78
+    },
+    {
+      "epoch": 0.8876404494382022,
+      "grad_norm": 0.30162861943244934,
+      "learning_rate": 0.0001681818181818182,
+      "loss": 0.2371,
+      "step": 79
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 0.29733604192733765,
+      "learning_rate": 0.00016772727272727273,
+      "loss": 0.2018,
+      "step": 80
+    },
+    {
+      "epoch": 0.9101123595505618,
+      "grad_norm": 0.22824084758758545,
+      "learning_rate": 0.00016727272727272728,
+      "loss": 0.1819,
+      "step": 81
+    },
+    {
+      "epoch": 0.9213483146067416,
+      "grad_norm": 0.2034444659948349,
+      "learning_rate": 0.00016681818181818182,
+      "loss": 0.1715,
+      "step": 82
+    },
+    {
+      "epoch": 0.9325842696629213,
+      "grad_norm": 0.2859365940093994,
+      "learning_rate": 0.00016636363636363637,
+      "loss": 0.2157,
+      "step": 83
+    },
+    {
+      "epoch": 0.9438202247191011,
+      "grad_norm": 0.2006848305463791,
+      "learning_rate": 0.00016590909090909094,
+      "loss": 0.1595,
+      "step": 84
+    },
+    {
+      "epoch": 0.9550561797752809,
+      "grad_norm": 0.3615463972091675,
+      "learning_rate": 0.00016545454545454545,
+      "loss": 0.2056,
+      "step": 85
+    },
+    {
+      "epoch": 0.9662921348314607,
+      "grad_norm": 0.24181589484214783,
+      "learning_rate": 0.000165,
+      "loss": 0.2051,
+      "step": 86
+    },
+    {
+      "epoch": 0.9775280898876404,
+      "grad_norm": 0.1747487634420395,
+      "learning_rate": 0.00016454545454545457,
+      "loss": 0.155,
+      "step": 87
+    },
+    {
+      "epoch": 0.9887640449438202,
+      "grad_norm": 0.240757554769516,
+      "learning_rate": 0.0001640909090909091,
+      "loss": 0.1786,
+      "step": 88
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.27025192975997925,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 0.1894,
+      "step": 89
+    },
+    {
+      "epoch": 1.0112359550561798,
+      "grad_norm": 0.2341006100177765,
+      "learning_rate": 0.0001631818181818182,
+      "loss": 0.2067,
+      "step": 90
+    },
+    {
+      "epoch": 1.0224719101123596,
+      "grad_norm": 0.2805992364883423,
+      "learning_rate": 0.00016272727272727272,
+      "loss": 0.223,
+      "step": 91
+    },
+    {
+      "epoch": 1.0337078651685394,
+      "grad_norm": 0.21516099572181702,
+      "learning_rate": 0.0001622727272727273,
+      "loss": 0.1891,
+      "step": 92
+    },
+    {
+      "epoch": 1.0449438202247192,
+      "grad_norm": 0.2255050241947174,
+      "learning_rate": 0.00016181818181818184,
+      "loss": 0.195,
+      "step": 93
+    },
+    {
+      "epoch": 1.0561797752808988,
+      "grad_norm": 0.278639554977417,
+      "learning_rate": 0.00016136363636363635,
+      "loss": 0.2074,
+      "step": 94
+    },
+    {
+      "epoch": 1.0674157303370786,
+      "grad_norm": 0.2584143877029419,
+      "learning_rate": 0.00016090909090909092,
+      "loss": 0.2121,
+      "step": 95
+    },
+    {
+      "epoch": 1.0786516853932584,
+      "grad_norm": 0.2629978358745575,
+      "learning_rate": 0.00016045454545454547,
+      "loss": 0.2038,
+      "step": 96
+    },
+    {
+      "epoch": 1.0898876404494382,
+      "grad_norm": 0.2283640205860138,
+      "learning_rate": 0.00016,
+      "loss": 0.1768,
+      "step": 97
+    },
+    {
+      "epoch": 1.101123595505618,
+      "grad_norm": 0.2216864973306656,
+      "learning_rate": 0.00015954545454545456,
+      "loss": 0.1989,
+      "step": 98
+    },
+    {
+      "epoch": 1.1123595505617978,
+      "grad_norm": 0.18183070421218872,
+      "learning_rate": 0.0001590909090909091,
+      "loss": 0.1631,
+      "step": 99
+    },
+    {
+      "epoch": 1.1235955056179776,
+      "grad_norm": 0.19485391676425934,
+      "learning_rate": 0.00015863636363636365,
+      "loss": 0.1748,
+      "step": 100
+    },
+    {
+      "epoch": 1.1348314606741572,
+      "grad_norm": 0.2579084038734436,
+      "learning_rate": 0.0001581818181818182,
+      "loss": 0.2012,
+      "step": 101
+    },
+    {
+      "epoch": 1.146067415730337,
+      "grad_norm": 0.1952996402978897,
+      "learning_rate": 0.00015772727272727273,
+      "loss": 0.1634,
+      "step": 102
+    },
+    {
+      "epoch": 1.1573033707865168,
+      "grad_norm": 0.20118536055088043,
+      "learning_rate": 0.00015727272727272728,
+      "loss": 0.1839,
+      "step": 103
+    },
+    {
+      "epoch": 1.1685393258426966,
+      "grad_norm": 0.23753251135349274,
+      "learning_rate": 0.00015681818181818182,
+      "loss": 0.1861,
+      "step": 104
+    },
+    {
+      "epoch": 1.1797752808988764,
+      "grad_norm": 0.26496222615242004,
+      "learning_rate": 0.00015636363636363637,
+      "loss": 0.226,
+      "step": 105
+    },
+    {
+      "epoch": 1.1910112359550562,
+      "grad_norm": 0.17998002469539642,
+      "learning_rate": 0.0001559090909090909,
+      "loss": 0.1595,
+      "step": 106
+    },
+    {
+      "epoch": 1.202247191011236,
+      "grad_norm": 0.25317177176475525,
+      "learning_rate": 0.00015545454545454546,
+      "loss": 0.1825,
+      "step": 107
+    },
+    {
+      "epoch": 1.2134831460674158,
+      "grad_norm": 0.20935533940792084,
+      "learning_rate": 0.000155,
+      "loss": 0.1747,
+      "step": 108
+    },
+    {
+      "epoch": 1.2247191011235956,
+      "grad_norm": 0.23691172897815704,
+      "learning_rate": 0.00015454545454545454,
+      "loss": 0.2247,
+      "step": 109
+    },
+    {
+      "epoch": 1.2359550561797752,
+      "grad_norm": 0.22647719085216522,
+      "learning_rate": 0.00015409090909090912,
+      "loss": 0.1829,
+      "step": 110
+    },
+    {
+      "epoch": 1.247191011235955,
+      "grad_norm": 0.23936079442501068,
+      "learning_rate": 0.00015363636363636363,
+      "loss": 0.1938,
+      "step": 111
+    },
+    {
+      "epoch": 1.2584269662921348,
+      "grad_norm": 0.19330653548240662,
+      "learning_rate": 0.00015318181818181818,
+      "loss": 0.1603,
+      "step": 112
+    },
+    {
+      "epoch": 1.2696629213483146,
+      "grad_norm": 0.19124047458171844,
+      "learning_rate": 0.00015272727272727275,
+      "loss": 0.184,
+      "step": 113
+    },
+    {
+      "epoch": 1.2808988764044944,
+      "grad_norm": 0.1912234127521515,
+      "learning_rate": 0.00015227272727272727,
+      "loss": 0.1659,
+      "step": 114
+    },
+    {
+      "epoch": 1.2921348314606742,
+      "grad_norm": 0.1903829127550125,
+      "learning_rate": 0.0001518181818181818,
+      "loss": 0.1755,
+      "step": 115
+    },
+    {
+      "epoch": 1.303370786516854,
+      "grad_norm": 0.1836494654417038,
+      "learning_rate": 0.00015136363636363638,
+      "loss": 0.1575,
+      "step": 116
+    },
+    {
+      "epoch": 1.3146067415730336,
+      "grad_norm": 0.21919198334217072,
+      "learning_rate": 0.0001509090909090909,
+      "loss": 0.1978,
+      "step": 117
+    },
+    {
+      "epoch": 1.3258426966292136,
+      "grad_norm": 0.22532597184181213,
+      "learning_rate": 0.00015045454545454547,
+      "loss": 0.1604,
+      "step": 118
+    },
+    {
+      "epoch": 1.3370786516853932,
+      "grad_norm": 0.22674380242824554,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.183,
+      "step": 119
+    },
+    {
+      "epoch": 1.348314606741573,
+      "grad_norm": 0.23995709419250488,
+      "learning_rate": 0.00014954545454545453,
+      "loss": 0.1777,
+      "step": 120
+    },
+    {
+      "epoch": 1.3595505617977528,
+      "grad_norm": 0.15110474824905396,
+      "learning_rate": 0.0001490909090909091,
+      "loss": 0.154,
+      "step": 121
+    },
+    {
+      "epoch": 1.3707865168539326,
+      "grad_norm": 0.1769479662179947,
+      "learning_rate": 0.00014863636363636365,
+      "loss": 0.1824,
+      "step": 122
+    },
+    {
+      "epoch": 1.3820224719101124,
+      "grad_norm": 0.2355855405330658,
+      "learning_rate": 0.0001481818181818182,
+      "loss": 0.187,
+      "step": 123
+    },
+    {
+      "epoch": 1.3932584269662922,
+      "grad_norm": 0.21928639709949493,
+      "learning_rate": 0.00014772727272727274,
+      "loss": 0.2154,
+      "step": 124
+    },
+    {
+      "epoch": 1.404494382022472,
+      "grad_norm": 0.23884353041648865,
+      "learning_rate": 0.00014727272727272728,
+      "loss": 0.2144,
+      "step": 125
+    },
+    {
+      "epoch": 1.4157303370786516,
+      "grad_norm": 0.19905094802379608,
+      "learning_rate": 0.00014681818181818182,
+      "loss": 0.1758,
+      "step": 126
+    },
+    {
+      "epoch": 1.4269662921348314,
+      "grad_norm": 0.20008406043052673,
+      "learning_rate": 0.00014636363636363637,
+      "loss": 0.1988,
+      "step": 127
+    },
+    {
+      "epoch": 1.4382022471910112,
+      "grad_norm": 0.14788155257701874,
+      "learning_rate": 0.0001459090909090909,
+      "loss": 0.1591,
+      "step": 128
+    },
+    {
+      "epoch": 1.449438202247191,
+      "grad_norm": 0.17816966772079468,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 0.1607,
+      "step": 129
+    },
+    {
+      "epoch": 1.4606741573033708,
+      "grad_norm": 0.2414962351322174,
+      "learning_rate": 0.000145,
+      "loss": 0.1988,
+      "step": 130
+    },
+    {
+      "epoch": 1.4719101123595506,
+      "grad_norm": 0.21710173785686493,
+      "learning_rate": 0.00014454545454545457,
+      "loss": 0.1749,
+      "step": 131
+    },
+    {
+      "epoch": 1.4831460674157304,
+      "grad_norm": 0.30704858899116516,
+      "learning_rate": 0.0001440909090909091,
+      "loss": 0.2106,
+      "step": 132
+    },
+    {
+      "epoch": 1.49438202247191,
+      "grad_norm": 0.22256992757320404,
+      "learning_rate": 0.00014363636363636363,
+      "loss": 0.1828,
+      "step": 133
+    },
+    {
+      "epoch": 1.50561797752809,
+      "grad_norm": 0.2698194980621338,
+      "learning_rate": 0.0001431818181818182,
+      "loss": 0.2418,
+      "step": 134
+    },
+    {
+      "epoch": 1.5168539325842696,
+      "grad_norm": 0.22738061845302582,
+      "learning_rate": 0.00014272727272727272,
+      "loss": 0.2023,
+      "step": 135
+    },
+    {
+      "epoch": 1.5280898876404494,
+      "grad_norm": 0.2749398946762085,
+      "learning_rate": 0.00014227272727272727,
+      "loss": 0.2201,
+      "step": 136
+    },
+    {
+      "epoch": 1.5393258426966292,
+      "grad_norm": 0.20003195106983185,
+      "learning_rate": 0.00014181818181818184,
+      "loss": 0.1658,
+      "step": 137
+    },
+    {
+      "epoch": 1.550561797752809,
+      "grad_norm": 0.1827768236398697,
+      "learning_rate": 0.00014136363636363635,
+      "loss": 0.1787,
+      "step": 138
+    },
+    {
+      "epoch": 1.5617977528089888,
+      "grad_norm": 0.20226892828941345,
+      "learning_rate": 0.00014090909090909093,
+      "loss": 0.1812,
+      "step": 139
+    },
+    {
+      "epoch": 1.5730337078651684,
+      "grad_norm": 0.18449921905994415,
+      "learning_rate": 0.00014045454545454547,
+      "loss": 0.183,
+      "step": 140
+    },
+    {
+      "epoch": 1.5842696629213484,
+      "grad_norm": 0.22666248679161072,
+      "learning_rate": 0.00014,
+      "loss": 0.2163,
+      "step": 141
+    },
+    {
+      "epoch": 1.595505617977528,
+      "grad_norm": 0.2258187234401703,
+      "learning_rate": 0.00013954545454545456,
+      "loss": 0.2024,
+      "step": 142
+    },
+    {
+      "epoch": 1.606741573033708,
+      "grad_norm": 0.17761889100074768,
+      "learning_rate": 0.0001390909090909091,
+      "loss": 0.1822,
+      "step": 143
+    },
+    {
+      "epoch": 1.6179775280898876,
+      "grad_norm": 0.1967982053756714,
+      "learning_rate": 0.00013863636363636365,
+      "loss": 0.1768,
+      "step": 144
+    },
+    {
+      "epoch": 1.6292134831460674,
+      "grad_norm": 0.21614395081996918,
+      "learning_rate": 0.0001381818181818182,
+      "loss": 0.1941,
+      "step": 145
+    },
+    {
+      "epoch": 1.6404494382022472,
+      "grad_norm": 0.21362508833408356,
+      "learning_rate": 0.00013772727272727274,
+      "loss": 0.2053,
+      "step": 146
+    },
+    {
+      "epoch": 1.651685393258427,
+      "grad_norm": 0.1829160451889038,
+      "learning_rate": 0.00013727272727272728,
+      "loss": 0.1601,
+      "step": 147
+    },
+    {
+      "epoch": 1.6629213483146068,
+      "grad_norm": 0.19813786447048187,
+      "learning_rate": 0.00013681818181818182,
+      "loss": 0.2027,
+      "step": 148
+    },
+    {
+      "epoch": 1.6741573033707864,
+      "grad_norm": 0.19203445315361023,
+      "learning_rate": 0.00013636363636363637,
+      "loss": 0.1638,
+      "step": 149
+    },
+    {
+      "epoch": 1.6853932584269664,
+      "grad_norm": 0.1693754941225052,
+      "learning_rate": 0.0001359090909090909,
+      "loss": 0.1695,
+      "step": 150
+    },
+    {
+      "epoch": 1.696629213483146,
+      "grad_norm": 0.19884233176708221,
+      "learning_rate": 0.00013545454545454546,
+      "loss": 0.2037,
+      "step": 151
+    },
+    {
+      "epoch": 1.7078651685393258,
+      "grad_norm": 0.20025449991226196,
+      "learning_rate": 0.00013500000000000003,
+      "loss": 0.1927,
+      "step": 152
+    },
+    {
+      "epoch": 1.7191011235955056,
+      "grad_norm": 0.1659104973077774,
+      "learning_rate": 0.00013454545454545455,
+      "loss": 0.164,
+      "step": 153
+    },
+    {
+      "epoch": 1.7303370786516854,
+      "grad_norm": 0.16635450720787048,
+      "learning_rate": 0.0001340909090909091,
+      "loss": 0.1729,
+      "step": 154
+    },
+    {
+      "epoch": 1.7415730337078652,
+      "grad_norm": 0.2119787037372589,
+      "learning_rate": 0.00013363636363636366,
+      "loss": 0.1761,
+      "step": 155
+    },
+    {
+      "epoch": 1.7528089887640448,
+      "grad_norm": 0.1592678278684616,
+      "learning_rate": 0.00013318181818181818,
+      "loss": 0.1582,
+      "step": 156
+    },
+    {
+      "epoch": 1.7640449438202248,
+      "grad_norm": 0.20228628814220428,
+      "learning_rate": 0.00013272727272727275,
+      "loss": 0.1833,
+      "step": 157
+    },
+    {
+      "epoch": 1.7752808988764044,
+      "grad_norm": 0.19576573371887207,
+      "learning_rate": 0.0001322727272727273,
+      "loss": 0.1716,
+      "step": 158
+    },
+    {
+      "epoch": 1.7865168539325844,
+      "grad_norm": 0.17609822750091553,
+      "learning_rate": 0.0001318181818181818,
+      "loss": 0.1566,
+      "step": 159
+    },
+    {
+      "epoch": 1.797752808988764,
+      "grad_norm": 0.19382323324680328,
+      "learning_rate": 0.00013136363636363638,
+      "loss": 0.1637,
+      "step": 160
+    },
+    {
+      "epoch": 1.8089887640449438,
+      "grad_norm": 0.26488256454467773,
+      "learning_rate": 0.00013090909090909093,
+      "loss": 0.2064,
+      "step": 161
+    },
+    {
+      "epoch": 1.8202247191011236,
+      "grad_norm": 0.23723822832107544,
+      "learning_rate": 0.00013045454545454544,
+      "loss": 0.177,
+      "step": 162
+    },
+    {
+      "epoch": 1.8314606741573034,
+      "grad_norm": 0.1890057623386383,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 0.1784,
+      "step": 163
+    },
+    {
+      "epoch": 1.8426966292134832,
+      "grad_norm": 0.1911257803440094,
+      "learning_rate": 0.00012954545454545456,
+      "loss": 0.1788,
+      "step": 164
+    },
+    {
+      "epoch": 1.8539325842696628,
+      "grad_norm": 0.2343178540468216,
+      "learning_rate": 0.0001290909090909091,
+      "loss": 0.1833,
+      "step": 165
+    },
+    {
+      "epoch": 1.8651685393258428,
+      "grad_norm": 0.1506495475769043,
+      "learning_rate": 0.00012863636363636365,
+      "loss": 0.1655,
+      "step": 166
+    },
+    {
+      "epoch": 1.8764044943820224,
+      "grad_norm": 0.17160733044147491,
+      "learning_rate": 0.0001281818181818182,
+      "loss": 0.1586,
+      "step": 167
+    },
+    {
+      "epoch": 1.8876404494382022,
+      "grad_norm": 0.13511358201503754,
+      "learning_rate": 0.00012772727272727274,
+      "loss": 0.1439,
+      "step": 168
+    },
+    {
+      "epoch": 1.898876404494382,
+      "grad_norm": 0.1821577399969101,
+      "learning_rate": 0.00012727272727272728,
+      "loss": 0.1973,
+      "step": 169
+    },
+    {
+      "epoch": 1.9101123595505618,
+      "grad_norm": 0.18846295773983002,
+      "learning_rate": 0.00012681818181818183,
+      "loss": 0.1767,
+      "step": 170
+    },
+    {
+      "epoch": 1.9213483146067416,
+      "grad_norm": 0.17300470173358917,
+      "learning_rate": 0.00012636363636363637,
+      "loss": 0.1726,
+      "step": 171
+    },
+    {
+      "epoch": 1.9325842696629212,
+      "grad_norm": 0.20833244919776917,
+      "learning_rate": 0.00012590909090909091,
+      "loss": 0.2248,
+      "step": 172
+    },
+    {
+      "epoch": 1.9438202247191012,
+      "grad_norm": 0.17537686228752136,
+      "learning_rate": 0.00012545454545454546,
+      "loss": 0.147,
+      "step": 173
+    },
+    {
+      "epoch": 1.9550561797752808,
+      "grad_norm": 0.17684531211853027,
+      "learning_rate": 0.000125,
+      "loss": 0.1774,
+      "step": 174
+    },
+    {
+      "epoch": 1.9662921348314608,
+      "grad_norm": 0.20325636863708496,
+      "learning_rate": 0.00012454545454545455,
+      "loss": 0.1921,
+      "step": 175
+    },
+    {
+      "epoch": 1.9775280898876404,
+      "grad_norm": 0.2229178249835968,
+      "learning_rate": 0.0001240909090909091,
+      "loss": 0.2058,
+      "step": 176
+    },
+    {
+      "epoch": 1.9887640449438202,
+      "grad_norm": 0.18187855184078217,
+      "learning_rate": 0.00012363636363636364,
+      "loss": 0.1883,
+      "step": 177
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.18570281565189362,
+      "learning_rate": 0.0001231818181818182,
+      "loss": 0.1716,
+      "step": 178
+    },
+    {
+      "epoch": 2.0112359550561796,
+      "grad_norm": 0.1995418518781662,
+      "learning_rate": 0.00012272727272727272,
+      "loss": 0.1912,
+      "step": 179
+    },
+    {
+      "epoch": 2.0224719101123596,
+      "grad_norm": 0.14596399664878845,
+      "learning_rate": 0.00012227272727272727,
+      "loss": 0.1632,
+      "step": 180
+    },
+    {
+      "epoch": 2.033707865168539,
+      "grad_norm": 0.16283725202083588,
+      "learning_rate": 0.00012181818181818183,
+      "loss": 0.1625,
+      "step": 181
+    },
+    {
+      "epoch": 2.044943820224719,
+      "grad_norm": 0.1877950131893158,
+      "learning_rate": 0.00012136363636363637,
+      "loss": 0.1652,
+      "step": 182
+    },
+    {
+      "epoch": 2.056179775280899,
+      "grad_norm": 0.1613854616880417,
+      "learning_rate": 0.0001209090909090909,
+      "loss": 0.163,
+      "step": 183
+    },
+    {
+      "epoch": 2.067415730337079,
+      "grad_norm": 0.16473975777626038,
+      "learning_rate": 0.00012045454545454546,
+      "loss": 0.1789,
+      "step": 184
+    },
+    {
+      "epoch": 2.0786516853932584,
+      "grad_norm": 0.16732561588287354,
+      "learning_rate": 0.00012,
+      "loss": 0.1644,
+      "step": 185
+    },
+    {
+      "epoch": 2.0898876404494384,
+      "grad_norm": 0.16880598664283752,
+      "learning_rate": 0.00011954545454545456,
+      "loss": 0.1778,
+      "step": 186
+    },
+    {
+      "epoch": 2.101123595505618,
+      "grad_norm": 0.16750402748584747,
+      "learning_rate": 0.00011909090909090909,
+      "loss": 0.1557,
+      "step": 187
+    },
+    {
+      "epoch": 2.1123595505617976,
+      "grad_norm": 0.14607924222946167,
+      "learning_rate": 0.00011863636363636364,
+      "loss": 0.1495,
+      "step": 188
+    },
+    {
+      "epoch": 2.1235955056179776,
+      "grad_norm": 0.16760137677192688,
+      "learning_rate": 0.0001181818181818182,
+      "loss": 0.1645,
+      "step": 189
+    },
+    {
+      "epoch": 2.134831460674157,
+      "grad_norm": 0.20173385739326477,
+      "learning_rate": 0.00011772727272727272,
+      "loss": 0.1895,
+      "step": 190
+    },
+    {
+      "epoch": 2.146067415730337,
+      "grad_norm": 0.15915413200855255,
+      "learning_rate": 0.00011727272727272727,
+      "loss": 0.1627,
+      "step": 191
+    },
+    {
+      "epoch": 2.157303370786517,
+      "grad_norm": 0.22035230696201324,
+      "learning_rate": 0.00011681818181818183,
+      "loss": 0.2051,
+      "step": 192
+    },
+    {
+      "epoch": 2.168539325842697,
+      "grad_norm": 0.1504964381456375,
+      "learning_rate": 0.00011636363636363636,
+      "loss": 0.1649,
+      "step": 193
+    },
+    {
+      "epoch": 2.1797752808988764,
+      "grad_norm": 0.20308493077754974,
+      "learning_rate": 0.00011590909090909093,
+      "loss": 0.1559,
+      "step": 194
+    },
+    {
+      "epoch": 2.191011235955056,
+      "grad_norm": 0.16288025677204132,
+      "learning_rate": 0.00011545454545454546,
+      "loss": 0.1417,
+      "step": 195
+    },
+    {
+      "epoch": 2.202247191011236,
+      "grad_norm": 0.16168631613254547,
+      "learning_rate": 0.00011499999999999999,
+      "loss": 0.1656,
+      "step": 196
+    },
+    {
+      "epoch": 2.2134831460674156,
+      "grad_norm": 0.14705248177051544,
+      "learning_rate": 0.00011454545454545456,
+      "loss": 0.1457,
+      "step": 197
+    },
+    {
+      "epoch": 2.2247191011235956,
+      "grad_norm": 0.19702956080436707,
+      "learning_rate": 0.00011409090909090909,
+      "loss": 0.1784,
+      "step": 198
+    },
+    {
+      "epoch": 2.235955056179775,
+      "grad_norm": 0.16930997371673584,
+      "learning_rate": 0.00011363636363636365,
+      "loss": 0.1409,
+      "step": 199
+    },
+    {
+      "epoch": 2.247191011235955,
+      "grad_norm": 0.20724202692508698,
+      "learning_rate": 0.0001131818181818182,
+      "loss": 0.1874,
+      "step": 200
+    },
+    {
+      "epoch": 2.258426966292135,
+      "grad_norm": 0.14622414112091064,
+      "learning_rate": 0.00011272727272727272,
+      "loss": 0.1535,
+      "step": 201
+    },
+    {
+      "epoch": 2.2696629213483144,
+      "grad_norm": 0.24741311371326447,
+      "learning_rate": 0.00011227272727272728,
+      "loss": 0.1833,
+      "step": 202
+    },
+    {
+      "epoch": 2.2808988764044944,
+      "grad_norm": 0.20128554105758667,
+      "learning_rate": 0.00011181818181818183,
+      "loss": 0.1929,
+      "step": 203
+    },
+    {
+      "epoch": 2.292134831460674,
+      "grad_norm": 0.17340625822544098,
+      "learning_rate": 0.00011136363636363636,
+      "loss": 0.1656,
+      "step": 204
+    },
+    {
+      "epoch": 2.303370786516854,
+      "grad_norm": 0.15460006892681122,
+      "learning_rate": 0.00011090909090909092,
+      "loss": 0.1643,
+      "step": 205
+    },
+    {
+      "epoch": 2.3146067415730336,
+      "grad_norm": 0.19704340398311615,
+      "learning_rate": 0.00011045454545454546,
+      "loss": 0.1867,
+      "step": 206
+    },
+    {
+      "epoch": 2.3258426966292136,
+      "grad_norm": 0.14527174830436707,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 0.1245,
+      "step": 207
+    },
+    {
+      "epoch": 2.337078651685393,
+      "grad_norm": 0.17086657881736755,
+      "learning_rate": 0.00010954545454545455,
+      "loss": 0.1762,
+      "step": 208
+    },
+    {
+      "epoch": 2.348314606741573,
+      "grad_norm": 0.16618594527244568,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.1565,
+      "step": 209
+    },
+    {
+      "epoch": 2.359550561797753,
+      "grad_norm": 0.17807389795780182,
+      "learning_rate": 0.00010863636363636365,
+      "loss": 0.1778,
+      "step": 210
+    },
+    {
+      "epoch": 2.370786516853933,
+      "grad_norm": 0.18786925077438354,
+      "learning_rate": 0.00010818181818181818,
+      "loss": 0.1655,
+      "step": 211
+    },
+    {
+      "epoch": 2.3820224719101124,
+      "grad_norm": 0.17768800258636475,
+      "learning_rate": 0.00010772727272727274,
+      "loss": 0.1653,
+      "step": 212
+    },
+    {
+      "epoch": 2.393258426966292,
+      "grad_norm": 0.17421704530715942,
+      "learning_rate": 0.00010727272727272728,
+      "loss": 0.1669,
+      "step": 213
+    },
+    {
+      "epoch": 2.404494382022472,
+      "grad_norm": 0.17153479158878326,
+      "learning_rate": 0.00010681818181818181,
+      "loss": 0.1606,
+      "step": 214
+    },
+    {
+      "epoch": 2.4157303370786516,
+      "grad_norm": 0.20289796590805054,
+      "learning_rate": 0.00010636363636363637,
+      "loss": 0.1919,
+      "step": 215
+    },
+    {
+      "epoch": 2.4269662921348316,
+      "grad_norm": 0.194489985704422,
+      "learning_rate": 0.00010590909090909092,
+      "loss": 0.1862,
+      "step": 216
+    },
+    {
+      "epoch": 2.438202247191011,
+      "grad_norm": 0.15572769939899445,
+      "learning_rate": 0.00010545454545454545,
+      "loss": 0.1607,
+      "step": 217
+    },
+    {
+      "epoch": 2.449438202247191,
+      "grad_norm": 0.16038504242897034,
+      "learning_rate": 0.000105,
+      "loss": 0.1543,
+      "step": 218
+    },
+    {
+      "epoch": 2.460674157303371,
+      "grad_norm": 0.19084928929805756,
+      "learning_rate": 0.00010454545454545455,
+      "loss": 0.2027,
+      "step": 219
+    },
+    {
+      "epoch": 2.4719101123595504,
+      "grad_norm": 0.18043439090251923,
+      "learning_rate": 0.0001040909090909091,
+      "loss": 0.1757,
+      "step": 220
+    },
+    {
+      "epoch": 2.4831460674157304,
+      "grad_norm": 0.15195126831531525,
+      "learning_rate": 0.00010363636363636364,
+      "loss": 0.1619,
+      "step": 221
+    },
+    {
+      "epoch": 2.49438202247191,
+      "grad_norm": 0.17387932538986206,
+      "learning_rate": 0.00010318181818181818,
+      "loss": 0.1823,
+      "step": 222
+    },
+    {
+      "epoch": 2.50561797752809,
+      "grad_norm": 0.16068069636821747,
+      "learning_rate": 0.00010272727272727274,
+      "loss": 0.1669,
+      "step": 223
+    },
+    {
+      "epoch": 2.5168539325842696,
+      "grad_norm": 0.18496158719062805,
+      "learning_rate": 0.00010227272727272727,
+      "loss": 0.1647,
+      "step": 224
+    },
+    {
+      "epoch": 2.5280898876404496,
+      "grad_norm": 0.16668476164340973,
+      "learning_rate": 0.00010181818181818181,
+      "loss": 0.1719,
+      "step": 225
+    },
+    {
+      "epoch": 2.539325842696629,
+      "grad_norm": 0.16353961825370789,
+      "learning_rate": 0.00010136363636363637,
+      "loss": 0.1803,
+      "step": 226
+    },
+    {
+      "epoch": 2.550561797752809,
+      "grad_norm": 0.14314891397953033,
+      "learning_rate": 0.0001009090909090909,
+      "loss": 0.1693,
+      "step": 227
+    },
+    {
+      "epoch": 2.561797752808989,
+      "grad_norm": 0.1646391600370407,
+      "learning_rate": 0.00010045454545454547,
+      "loss": 0.1917,
+      "step": 228
+    },
+    {
+      "epoch": 2.5730337078651684,
+      "grad_norm": 0.173238143324852,
+      "learning_rate": 0.0001,
+      "loss": 0.1827,
+      "step": 229
+    },
+    {
+      "epoch": 2.5842696629213484,
+      "grad_norm": 0.16539378464221954,
+      "learning_rate": 9.954545454545455e-05,
+      "loss": 0.1594,
+      "step": 230
+    },
+    {
+      "epoch": 2.595505617977528,
+      "grad_norm": 0.16949477791786194,
+      "learning_rate": 9.909090909090911e-05,
+      "loss": 0.1538,
+      "step": 231
+    },
+    {
+      "epoch": 2.606741573033708,
+      "grad_norm": 0.18005919456481934,
+      "learning_rate": 9.863636363636364e-05,
+      "loss": 0.1769,
+      "step": 232
+    },
+    {
+      "epoch": 2.6179775280898876,
+      "grad_norm": 0.16846978664398193,
+      "learning_rate": 9.818181818181818e-05,
+      "loss": 0.1722,
+      "step": 233
+    },
+    {
+      "epoch": 2.629213483146067,
+      "grad_norm": 0.16401781141757965,
+      "learning_rate": 9.772727272727274e-05,
+      "loss": 0.1633,
+      "step": 234
+    },
+    {
+      "epoch": 2.640449438202247,
+      "grad_norm": 0.196939155459404,
+      "learning_rate": 9.727272727272728e-05,
+      "loss": 0.1887,
+      "step": 235
+    },
+    {
+      "epoch": 2.6516853932584272,
+      "grad_norm": 0.21819128096103668,
+      "learning_rate": 9.681818181818181e-05,
+      "loss": 0.1821,
+      "step": 236
+    },
+    {
+      "epoch": 2.662921348314607,
+      "grad_norm": 0.16041137278079987,
+      "learning_rate": 9.636363636363637e-05,
+      "loss": 0.155,
+      "step": 237
+    },
+    {
+      "epoch": 2.6741573033707864,
+      "grad_norm": 0.17373093962669373,
+      "learning_rate": 9.590909090909092e-05,
+      "loss": 0.1684,
+      "step": 238
+    },
+    {
+      "epoch": 2.6853932584269664,
+      "grad_norm": 0.1691204160451889,
+      "learning_rate": 9.545454545454546e-05,
+      "loss": 0.1819,
+      "step": 239
+    },
+    {
+      "epoch": 2.696629213483146,
+      "grad_norm": 0.15193454921245575,
+      "learning_rate": 9.5e-05,
+      "loss": 0.1594,
+      "step": 240
+    },
+    {
+      "epoch": 2.7078651685393256,
+      "grad_norm": 0.17132344841957092,
+      "learning_rate": 9.454545454545455e-05,
+      "loss": 0.1699,
+      "step": 241
+    },
+    {
+      "epoch": 2.7191011235955056,
+      "grad_norm": 0.16452458500862122,
+      "learning_rate": 9.40909090909091e-05,
+      "loss": 0.1756,
+      "step": 242
+    },
+    {
+      "epoch": 2.7303370786516856,
+      "grad_norm": 0.18071810901165009,
+      "learning_rate": 9.363636363636364e-05,
+      "loss": 0.1597,
+      "step": 243
+    },
+    {
+      "epoch": 2.741573033707865,
+      "grad_norm": 0.20396122336387634,
+      "learning_rate": 9.318181818181818e-05,
+      "loss": 0.1787,
+      "step": 244
+    },
+    {
+      "epoch": 2.752808988764045,
+      "grad_norm": 0.22361145913600922,
+      "learning_rate": 9.272727272727273e-05,
+      "loss": 0.1824,
+      "step": 245
+    },
+    {
+      "epoch": 2.764044943820225,
+      "grad_norm": 0.16991250216960907,
+      "learning_rate": 9.227272727272727e-05,
+      "loss": 0.1605,
+      "step": 246
+    },
+    {
+      "epoch": 2.7752808988764044,
+      "grad_norm": 0.19506555795669556,
+      "learning_rate": 9.181818181818183e-05,
+      "loss": 0.1819,
+      "step": 247
+    },
+    {
+      "epoch": 2.7865168539325844,
+      "grad_norm": 0.14264117181301117,
+      "learning_rate": 9.136363636363637e-05,
+      "loss": 0.1615,
+      "step": 248
+    },
+    {
+      "epoch": 2.797752808988764,
+      "grad_norm": 0.1541077196598053,
+      "learning_rate": 9.090909090909092e-05,
+      "loss": 0.1616,
+      "step": 249
+    },
+    {
+      "epoch": 2.808988764044944,
+      "grad_norm": 0.13672606647014618,
+      "learning_rate": 9.045454545454546e-05,
+      "loss": 0.1548,
+      "step": 250
+    },
+    {
+      "epoch": 2.8202247191011236,
+      "grad_norm": 0.1655198186635971,
+      "learning_rate": 9e-05,
+      "loss": 0.1715,
+      "step": 251
+    },
+    {
+      "epoch": 2.831460674157303,
+      "grad_norm": 0.1501724272966385,
+      "learning_rate": 8.954545454545455e-05,
+      "loss": 0.1435,
+      "step": 252
+    },
+    {
+      "epoch": 2.842696629213483,
+      "grad_norm": 0.17689818143844604,
+      "learning_rate": 8.90909090909091e-05,
+      "loss": 0.1567,
+      "step": 253
+    },
+    {
+      "epoch": 2.853932584269663,
+      "grad_norm": 0.158350870013237,
+      "learning_rate": 8.863636363636364e-05,
+      "loss": 0.1486,
+      "step": 254
+    },
+    {
+      "epoch": 2.865168539325843,
+      "grad_norm": 0.19720739126205444,
+      "learning_rate": 8.818181818181818e-05,
+      "loss": 0.1729,
+      "step": 255
+    },
+    {
+      "epoch": 2.8764044943820224,
+      "grad_norm": 0.17139959335327148,
+      "learning_rate": 8.772727272727274e-05,
+      "loss": 0.185,
+      "step": 256
+    },
+    {
+      "epoch": 2.8876404494382024,
+      "grad_norm": 0.20194506645202637,
+      "learning_rate": 8.727272727272727e-05,
+      "loss": 0.1669,
+      "step": 257
+    },
+    {
+      "epoch": 2.898876404494382,
+      "grad_norm": 0.17279160022735596,
+      "learning_rate": 8.681818181818182e-05,
+      "loss": 0.1695,
+      "step": 258
+    },
+    {
+      "epoch": 2.9101123595505616,
+      "grad_norm": 0.20821331441402435,
+      "learning_rate": 8.636363636363637e-05,
+      "loss": 0.1665,
+      "step": 259
+    },
+    {
+      "epoch": 2.9213483146067416,
+      "grad_norm": 0.18540224432945251,
+      "learning_rate": 8.590909090909092e-05,
+      "loss": 0.1824,
+      "step": 260
+    },
+    {
+      "epoch": 2.932584269662921,
+      "grad_norm": 0.19717296957969666,
+      "learning_rate": 8.545454545454545e-05,
+      "loss": 0.1885,
+      "step": 261
+    },
+    {
+      "epoch": 2.943820224719101,
+      "grad_norm": 0.1944579929113388,
+      "learning_rate": 8.5e-05,
+      "loss": 0.1801,
+      "step": 262
+    },
+    {
+      "epoch": 2.955056179775281,
+      "grad_norm": 0.17243047058582306,
+      "learning_rate": 8.454545454545455e-05,
+      "loss": 0.1564,
+      "step": 263
+    },
+    {
+      "epoch": 2.966292134831461,
+      "grad_norm": 0.1788180023431778,
+      "learning_rate": 8.40909090909091e-05,
+      "loss": 0.1728,
+      "step": 264
+    },
+    {
+      "epoch": 2.9775280898876404,
+      "grad_norm": 0.18186365067958832,
+      "learning_rate": 8.363636363636364e-05,
+      "loss": 0.1805,
+      "step": 265
+    },
+    {
+      "epoch": 2.98876404494382,
+      "grad_norm": 0.1703241765499115,
+      "learning_rate": 8.318181818181818e-05,
+      "loss": 0.1748,
+      "step": 266
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.15256650745868683,
+      "learning_rate": 8.272727272727273e-05,
+      "loss": 0.1658,
+      "step": 267
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 445,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.400125597073818e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-267/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9936502145859cfb12f653ac1259cd6cfb3aef369ebb44c3892d632b7bb2264
+size 5624

checkpoint-356/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/qwen2.5-vl-7b-instruct-bnb-4bit
+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 0.14.0

checkpoint-356/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/qwen2.5-vl-7b-instruct-bnb-4bit",
+  "bias": "none",
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:qkv|proj|gate_proj|up_proj|down_proj|q_proj|k_proj|v_proj|o_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:qkv|proj|gate_proj|up_proj|down_proj|q_proj|k_proj|v_proj|o_proj)))",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-356/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ec65ac2d802d39a4a26ca51062050da4e0242ce151fe59fddd7346d24df708
+size 824439856

checkpoint-356/added_tokens.json

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

checkpoint-356/chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

checkpoint-356/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0bd47b4d9df359b3394f78df649288a5d418bebc0f73612036cea63e3b0f8a9
+size 328470068

checkpoint-356/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

checkpoint-356/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b36f846e18f654c3cfee105cea70c9e74df15bfcb4fc79f4b82ed01c58b83ae3
+size 14244

checkpoint-356/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f727e46a29d0a104044e356c9166faf32bef9504a50b2fe53be63b712d4bc62b
+size 988

checkpoint-356/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebf9fc58d7ae1622dde166e4140e8974c6afc267e6e9edfd1b58efd5bc1f3300
+size 1064

checkpoint-356/special_tokens_map.json

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

checkpoint-356/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:741c85ffe434aad73e934a73ef380c85e94cd863b8f55e1a1ad66cacb5a93dfd
+size 11422164

checkpoint-356/tokenizer_config.json

@@ -0,0 +1,210 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-356/trainer_state.json

@@ -0,0 +1,2526 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 356,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011235955056179775,
+      "grad_norm": 10.042351722717285,
+      "learning_rate": 4e-05,
+      "loss": 9.033,
+      "step": 1
+    },
+    {
+      "epoch": 0.02247191011235955,
+      "grad_norm": 10.187106132507324,
+      "learning_rate": 8e-05,
+      "loss": 9.1846,
+      "step": 2
+    },
+    {
+      "epoch": 0.033707865168539325,
+      "grad_norm": 8.38694953918457,
+      "learning_rate": 0.00012,
+      "loss": 7.9832,
+      "step": 3
+    },
+    {
+      "epoch": 0.0449438202247191,
+      "grad_norm": 5.938446521759033,
+      "learning_rate": 0.00016,
+      "loss": 5.6493,
+      "step": 4
+    },
+    {
+      "epoch": 0.056179775280898875,
+      "grad_norm": 4.586862087249756,
+      "learning_rate": 0.0002,
+      "loss": 4.0131,
+      "step": 5
+    },
+    {
+      "epoch": 0.06741573033707865,
+      "grad_norm": 4.84490442276001,
+      "learning_rate": 0.00019954545454545455,
+      "loss": 2.9931,
+      "step": 6
+    },
+    {
+      "epoch": 0.07865168539325842,
+      "grad_norm": 4.460867881774902,
+      "learning_rate": 0.0001990909090909091,
+      "loss": 2.261,
+      "step": 7
+    },
+    {
+      "epoch": 0.0898876404494382,
+      "grad_norm": 3.067777395248413,
+      "learning_rate": 0.00019863636363636364,
+      "loss": 1.8861,
+      "step": 8
+    },
+    {
+      "epoch": 0.10112359550561797,
+      "grad_norm": 1.5425913333892822,
+      "learning_rate": 0.00019818181818181821,
+      "loss": 1.4675,
+      "step": 9
+    },
+    {
+      "epoch": 0.11235955056179775,
+      "grad_norm": 1.346417784690857,
+      "learning_rate": 0.00019772727272727273,
+      "loss": 1.3642,
+      "step": 10
+    },
+    {
+      "epoch": 0.12359550561797752,
+      "grad_norm": 1.1825133562088013,
+      "learning_rate": 0.00019727272727272728,
+      "loss": 1.0109,
+      "step": 11
+    },
+    {
+      "epoch": 0.1348314606741573,
+      "grad_norm": 0.9976914525032043,
+      "learning_rate": 0.00019681818181818185,
+      "loss": 0.9873,
+      "step": 12
+    },
+    {
+      "epoch": 0.14606741573033707,
+      "grad_norm": 0.6481193900108337,
+      "learning_rate": 0.00019636363636363636,
+      "loss": 0.6746,
+      "step": 13
+    },
+    {
+      "epoch": 0.15730337078651685,
+      "grad_norm": 0.5585954189300537,
+      "learning_rate": 0.0001959090909090909,
+      "loss": 0.5289,
+      "step": 14
+    },
+    {
+      "epoch": 0.16853932584269662,
+      "grad_norm": 0.9624674916267395,
+      "learning_rate": 0.00019545454545454548,
+      "loss": 0.5552,
+      "step": 15
+    },
+    {
+      "epoch": 0.1797752808988764,
+      "grad_norm": 0.7732966542243958,
+      "learning_rate": 0.000195,
+      "loss": 0.5047,
+      "step": 16
+    },
+    {
+      "epoch": 0.19101123595505617,
+      "grad_norm": 0.7540618777275085,
+      "learning_rate": 0.00019454545454545457,
+      "loss": 0.5803,
+      "step": 17
+    },
+    {
+      "epoch": 0.20224719101123595,
+      "grad_norm": 0.9345465302467346,
+      "learning_rate": 0.0001940909090909091,
+      "loss": 0.611,
+      "step": 18
+    },
+    {
+      "epoch": 0.21348314606741572,
+      "grad_norm": 0.5613678693771362,
+      "learning_rate": 0.00019363636363636363,
+      "loss": 0.4007,
+      "step": 19
+    },
+    {
+      "epoch": 0.2247191011235955,
+      "grad_norm": 0.8053308725357056,
+      "learning_rate": 0.0001931818181818182,
+      "loss": 0.5202,
+      "step": 20
+    },
+    {
+      "epoch": 0.23595505617977527,
+      "grad_norm": 0.6621015667915344,
+      "learning_rate": 0.00019272727272727274,
+      "loss": 0.4851,
+      "step": 21
+    },
+    {
+      "epoch": 0.24719101123595505,
+      "grad_norm": 0.797894299030304,
+      "learning_rate": 0.00019227272727272726,
+      "loss": 0.5401,
+      "step": 22
+    },
+    {
+      "epoch": 0.25842696629213485,
+      "grad_norm": 0.5635455250740051,
+      "learning_rate": 0.00019181818181818183,
+      "loss": 0.4295,
+      "step": 23
+    },
+    {
+      "epoch": 0.2696629213483146,
+      "grad_norm": 0.5012619495391846,
+      "learning_rate": 0.00019136363636363638,
+      "loss": 0.3133,
+      "step": 24
+    },
+    {
+      "epoch": 0.2808988764044944,
+      "grad_norm": 0.5143508911132812,
+      "learning_rate": 0.00019090909090909092,
+      "loss": 0.3207,
+      "step": 25
+    },
+    {
+      "epoch": 0.29213483146067415,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019090909090909092,
+      "loss": 0.622,
+      "step": 26
+    },
+    {
+      "epoch": 0.30337078651685395,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019090909090909092,
+      "loss": 0.5544,
+      "step": 27
+    },
+    {
+      "epoch": 0.3146067415730337,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019090909090909092,
+      "loss": 0.4251,
+      "step": 28
+    },
+    {
+      "epoch": 0.3258426966292135,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019090909090909092,
+      "loss": 0.626,
+      "step": 29
+    },
+    {
+      "epoch": 0.33707865168539325,
+      "grad_norm": 551.2264404296875,
+      "learning_rate": 0.00019045454545454547,
+      "loss": 0.5757,
+      "step": 30
+    },
+    {
+      "epoch": 0.34831460674157305,
+      "grad_norm": 0.5639562010765076,
+      "learning_rate": 0.00019,
+      "loss": 0.3197,
+      "step": 31
+    },
+    {
+      "epoch": 0.3595505617977528,
+      "grad_norm": 0.5104588270187378,
+      "learning_rate": 0.00018954545454545455,
+      "loss": 0.2792,
+      "step": 32
+    },
+    {
+      "epoch": 0.3707865168539326,
+      "grad_norm": 0.6046687960624695,
+      "learning_rate": 0.0001890909090909091,
+      "loss": 0.4017,
+      "step": 33
+    },
+    {
+      "epoch": 0.38202247191011235,
+      "grad_norm": 0.5290363430976868,
+      "learning_rate": 0.00018863636363636364,
+      "loss": 0.2522,
+      "step": 34
+    },
+    {
+      "epoch": 0.39325842696629215,
+      "grad_norm": 0.4888989329338074,
+      "learning_rate": 0.0001881818181818182,
+      "loss": 0.2513,
+      "step": 35
+    },
+    {
+      "epoch": 0.4044943820224719,
+      "grad_norm": 0.4538341164588928,
+      "learning_rate": 0.00018772727272727273,
+      "loss": 0.2394,
+      "step": 36
+    },
+    {
+      "epoch": 0.4157303370786517,
+      "grad_norm": 0.5249782800674438,
+      "learning_rate": 0.00018727272727272728,
+      "loss": 0.3383,
+      "step": 37
+    },
+    {
+      "epoch": 0.42696629213483145,
+      "grad_norm": 0.544735312461853,
+      "learning_rate": 0.00018681818181818182,
+      "loss": 0.3345,
+      "step": 38
+    },
+    {
+      "epoch": 0.43820224719101125,
+      "grad_norm": 0.3868374228477478,
+      "learning_rate": 0.00018636363636363636,
+      "loss": 0.2425,
+      "step": 39
+    },
+    {
+      "epoch": 0.449438202247191,
+      "grad_norm": 0.41138726472854614,
+      "learning_rate": 0.0001859090909090909,
+      "loss": 0.2625,
+      "step": 40
+    },
+    {
+      "epoch": 0.4606741573033708,
+      "grad_norm": 0.684403657913208,
+      "learning_rate": 0.00018545454545454545,
+      "loss": 0.3363,
+      "step": 41
+    },
+    {
+      "epoch": 0.47191011235955055,
+      "grad_norm": 0.4800611138343811,
+      "learning_rate": 0.00018500000000000002,
+      "loss": 0.2339,
+      "step": 42
+    },
+    {
+      "epoch": 0.48314606741573035,
+      "grad_norm": 0.47672778367996216,
+      "learning_rate": 0.00018454545454545454,
+      "loss": 0.2908,
+      "step": 43
+    },
+    {
+      "epoch": 0.4943820224719101,
+      "grad_norm": 0.44971343874931335,
+      "learning_rate": 0.00018409090909090909,
+      "loss": 0.2553,
+      "step": 44
+    },
+    {
+      "epoch": 0.5056179775280899,
+      "grad_norm": 0.45129504799842834,
+      "learning_rate": 0.00018363636363636366,
+      "loss": 0.325,
+      "step": 45
+    },
+    {
+      "epoch": 0.5168539325842697,
+      "grad_norm": 0.48597297072410583,
+      "learning_rate": 0.00018318181818181817,
+      "loss": 0.2843,
+      "step": 46
+    },
+    {
+      "epoch": 0.5280898876404494,
+      "grad_norm": 0.3514116704463959,
+      "learning_rate": 0.00018272727272727275,
+      "loss": 0.2128,
+      "step": 47
+    },
+    {
+      "epoch": 0.5393258426966292,
+      "grad_norm": 0.46826595067977905,
+      "learning_rate": 0.0001822727272727273,
+      "loss": 0.2601,
+      "step": 48
+    },
+    {
+      "epoch": 0.550561797752809,
+      "grad_norm": 0.3118669390678406,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 0.2192,
+      "step": 49
+    },
+    {
+      "epoch": 0.5617977528089888,
+      "grad_norm": 0.37151020765304565,
+      "learning_rate": 0.00018136363636363638,
+      "loss": 0.2255,
+      "step": 50
+    },
+    {
+      "epoch": 0.5730337078651685,
+      "grad_norm": 0.4220457971096039,
+      "learning_rate": 0.00018090909090909092,
+      "loss": 0.2463,
+      "step": 51
+    },
+    {
+      "epoch": 0.5842696629213483,
+      "grad_norm": 0.298927366733551,
+      "learning_rate": 0.00018045454545454547,
+      "loss": 0.1939,
+      "step": 52
+    },
+    {
+      "epoch": 0.5955056179775281,
+      "grad_norm": 0.3494245707988739,
+      "learning_rate": 0.00018,
+      "loss": 0.2276,
+      "step": 53
+    },
+    {
+      "epoch": 0.6067415730337079,
+      "grad_norm": 0.7135240435600281,
+      "learning_rate": 0.00017954545454545456,
+      "loss": 0.316,
+      "step": 54
+    },
+    {
+      "epoch": 0.6179775280898876,
+      "grad_norm": 0.47558313608169556,
+      "learning_rate": 0.0001790909090909091,
+      "loss": 0.1915,
+      "step": 55
+    },
+    {
+      "epoch": 0.6292134831460674,
+      "grad_norm": 0.47424033284187317,
+      "learning_rate": 0.00017863636363636364,
+      "loss": 0.268,
+      "step": 56
+    },
+    {
+      "epoch": 0.6404494382022472,
+      "grad_norm": 0.3898255228996277,
+      "learning_rate": 0.0001781818181818182,
+      "loss": 0.2346,
+      "step": 57
+    },
+    {
+      "epoch": 0.651685393258427,
+      "grad_norm": 0.3044908940792084,
+      "learning_rate": 0.00017772727272727273,
+      "loss": 0.2244,
+      "step": 58
+    },
+    {
+      "epoch": 0.6629213483146067,
+      "grad_norm": 0.4012211561203003,
+      "learning_rate": 0.00017727272727272728,
+      "loss": 0.2548,
+      "step": 59
+    },
+    {
+      "epoch": 0.6741573033707865,
+      "grad_norm": 0.36978745460510254,
+      "learning_rate": 0.00017681818181818182,
+      "loss": 0.1945,
+      "step": 60
+    },
+    {
+      "epoch": 0.6853932584269663,
+      "grad_norm": 0.3404884338378906,
+      "learning_rate": 0.00017636363636363637,
+      "loss": 0.2486,
+      "step": 61
+    },
+    {
+      "epoch": 0.6966292134831461,
+      "grad_norm": 0.3647669851779938,
+      "learning_rate": 0.0001759090909090909,
+      "loss": 0.2267,
+      "step": 62
+    },
+    {
+      "epoch": 0.7078651685393258,
+      "grad_norm": 0.2504497170448303,
+      "learning_rate": 0.00017545454545454548,
+      "loss": 0.1854,
+      "step": 63
+    },
+    {
+      "epoch": 0.7191011235955056,
+      "grad_norm": 0.3424750566482544,
+      "learning_rate": 0.000175,
+      "loss": 0.2586,
+      "step": 64
+    },
+    {
+      "epoch": 0.7303370786516854,
+      "grad_norm": 0.3164011836051941,
+      "learning_rate": 0.00017454545454545454,
+      "loss": 0.217,
+      "step": 65
+    },
+    {
+      "epoch": 0.7415730337078652,
+      "grad_norm": 0.32831573486328125,
+      "learning_rate": 0.00017409090909090911,
+      "loss": 0.2326,
+      "step": 66
+    },
+    {
+      "epoch": 0.7528089887640449,
+      "grad_norm": 0.3514035940170288,
+      "learning_rate": 0.00017363636363636363,
+      "loss": 0.2591,
+      "step": 67
+    },
+    {
+      "epoch": 0.7640449438202247,
+      "grad_norm": 0.30864688754081726,
+      "learning_rate": 0.0001731818181818182,
+      "loss": 0.2073,
+      "step": 68
+    },
+    {
+      "epoch": 0.7752808988764045,
+      "grad_norm": 0.32905542850494385,
+      "learning_rate": 0.00017272727272727275,
+      "loss": 0.2224,
+      "step": 69
+    },
+    {
+      "epoch": 0.7865168539325843,
+      "grad_norm": 0.27842977643013,
+      "learning_rate": 0.00017227272727272726,
+      "loss": 0.1893,
+      "step": 70
+    },
+    {
+      "epoch": 0.797752808988764,
+      "grad_norm": 0.3048170804977417,
+      "learning_rate": 0.00017181818181818184,
+      "loss": 0.2206,
+      "step": 71
+    },
+    {
+      "epoch": 0.8089887640449438,
+      "grad_norm": 0.25344306230545044,
+      "learning_rate": 0.00017136363636363638,
+      "loss": 0.1876,
+      "step": 72
+    },
+    {
+      "epoch": 0.8202247191011236,
+      "grad_norm": 0.3092687427997589,
+      "learning_rate": 0.0001709090909090909,
+      "loss": 0.1791,
+      "step": 73
+    },
+    {
+      "epoch": 0.8314606741573034,
+      "grad_norm": 0.30857375264167786,
+      "learning_rate": 0.00017045454545454547,
+      "loss": 0.2099,
+      "step": 74
+    },
+    {
+      "epoch": 0.8426966292134831,
+      "grad_norm": 0.20455722510814667,
+      "learning_rate": 0.00017,
+      "loss": 0.1705,
+      "step": 75
+    },
+    {
+      "epoch": 0.8539325842696629,
+      "grad_norm": 0.273429274559021,
+      "learning_rate": 0.00016954545454545456,
+      "loss": 0.162,
+      "step": 76
+    },
+    {
+      "epoch": 0.8651685393258427,
+      "grad_norm": 0.25422728061676025,
+      "learning_rate": 0.0001690909090909091,
+      "loss": 0.1804,
+      "step": 77
+    },
+    {
+      "epoch": 0.8764044943820225,
+      "grad_norm": 0.2745291292667389,
+      "learning_rate": 0.00016863636363636364,
+      "loss": 0.2184,
+      "step": 78
+    },
+    {
+      "epoch": 0.8876404494382022,
+      "grad_norm": 0.30162861943244934,
+      "learning_rate": 0.0001681818181818182,
+      "loss": 0.2371,
+      "step": 79
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 0.29733604192733765,
+      "learning_rate": 0.00016772727272727273,
+      "loss": 0.2018,
+      "step": 80
+    },
+    {
+      "epoch": 0.9101123595505618,
+      "grad_norm": 0.22824084758758545,
+      "learning_rate": 0.00016727272727272728,
+      "loss": 0.1819,
+      "step": 81
+    },
+    {
+      "epoch": 0.9213483146067416,
+      "grad_norm": 0.2034444659948349,
+      "learning_rate": 0.00016681818181818182,
+      "loss": 0.1715,
+      "step": 82
+    },
+    {
+      "epoch": 0.9325842696629213,
+      "grad_norm": 0.2859365940093994,
+      "learning_rate": 0.00016636363636363637,
+      "loss": 0.2157,
+      "step": 83
+    },
+    {
+      "epoch": 0.9438202247191011,
+      "grad_norm": 0.2006848305463791,
+      "learning_rate": 0.00016590909090909094,
+      "loss": 0.1595,
+      "step": 84
+    },
+    {
+      "epoch": 0.9550561797752809,
+      "grad_norm": 0.3615463972091675,
+      "learning_rate": 0.00016545454545454545,
+      "loss": 0.2056,
+      "step": 85
+    },
+    {
+      "epoch": 0.9662921348314607,
+      "grad_norm": 0.24181589484214783,
+      "learning_rate": 0.000165,
+      "loss": 0.2051,
+      "step": 86
+    },
+    {
+      "epoch": 0.9775280898876404,
+      "grad_norm": 0.1747487634420395,
+      "learning_rate": 0.00016454545454545457,
+      "loss": 0.155,
+      "step": 87
+    },
+    {
+      "epoch": 0.9887640449438202,
+      "grad_norm": 0.240757554769516,
+      "learning_rate": 0.0001640909090909091,
+      "loss": 0.1786,
+      "step": 88
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.27025192975997925,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 0.1894,
+      "step": 89
+    },
+    {
+      "epoch": 1.0112359550561798,
+      "grad_norm": 0.2341006100177765,
+      "learning_rate": 0.0001631818181818182,
+      "loss": 0.2067,
+      "step": 90
+    },
+    {
+      "epoch": 1.0224719101123596,
+      "grad_norm": 0.2805992364883423,
+      "learning_rate": 0.00016272727272727272,
+      "loss": 0.223,
+      "step": 91
+    },
+    {
+      "epoch": 1.0337078651685394,
+      "grad_norm": 0.21516099572181702,
+      "learning_rate": 0.0001622727272727273,
+      "loss": 0.1891,
+      "step": 92
+    },
+    {
+      "epoch": 1.0449438202247192,
+      "grad_norm": 0.2255050241947174,
+      "learning_rate": 0.00016181818181818184,
+      "loss": 0.195,
+      "step": 93
+    },
+    {
+      "epoch": 1.0561797752808988,
+      "grad_norm": 0.278639554977417,
+      "learning_rate": 0.00016136363636363635,
+      "loss": 0.2074,
+      "step": 94
+    },
+    {
+      "epoch": 1.0674157303370786,
+      "grad_norm": 0.2584143877029419,
+      "learning_rate": 0.00016090909090909092,
+      "loss": 0.2121,
+      "step": 95
+    },
+    {
+      "epoch": 1.0786516853932584,
+      "grad_norm": 0.2629978358745575,
+      "learning_rate": 0.00016045454545454547,
+      "loss": 0.2038,
+      "step": 96
+    },
+    {
+      "epoch": 1.0898876404494382,
+      "grad_norm": 0.2283640205860138,
+      "learning_rate": 0.00016,
+      "loss": 0.1768,
+      "step": 97
+    },
+    {
+      "epoch": 1.101123595505618,
+      "grad_norm": 0.2216864973306656,
+      "learning_rate": 0.00015954545454545456,
+      "loss": 0.1989,
+      "step": 98
+    },
+    {
+      "epoch": 1.1123595505617978,
+      "grad_norm": 0.18183070421218872,
+      "learning_rate": 0.0001590909090909091,
+      "loss": 0.1631,
+      "step": 99
+    },
+    {
+      "epoch": 1.1235955056179776,
+      "grad_norm": 0.19485391676425934,
+      "learning_rate": 0.00015863636363636365,
+      "loss": 0.1748,
+      "step": 100
+    },
+    {
+      "epoch": 1.1348314606741572,
+      "grad_norm": 0.2579084038734436,
+      "learning_rate": 0.0001581818181818182,
+      "loss": 0.2012,
+      "step": 101
+    },
+    {
+      "epoch": 1.146067415730337,
+      "grad_norm": 0.1952996402978897,
+      "learning_rate": 0.00015772727272727273,
+      "loss": 0.1634,
+      "step": 102
+    },
+    {
+      "epoch": 1.1573033707865168,
+      "grad_norm": 0.20118536055088043,
+      "learning_rate": 0.00015727272727272728,
+      "loss": 0.1839,
+      "step": 103
+    },
+    {
+      "epoch": 1.1685393258426966,
+      "grad_norm": 0.23753251135349274,
+      "learning_rate": 0.00015681818181818182,
+      "loss": 0.1861,
+      "step": 104
+    },
+    {
+      "epoch": 1.1797752808988764,
+      "grad_norm": 0.26496222615242004,
+      "learning_rate": 0.00015636363636363637,
+      "loss": 0.226,
+      "step": 105
+    },
+    {
+      "epoch": 1.1910112359550562,
+      "grad_norm": 0.17998002469539642,
+      "learning_rate": 0.0001559090909090909,
+      "loss": 0.1595,
+      "step": 106
+    },
+    {
+      "epoch": 1.202247191011236,
+      "grad_norm": 0.25317177176475525,
+      "learning_rate": 0.00015545454545454546,
+      "loss": 0.1825,
+      "step": 107
+    },
+    {
+      "epoch": 1.2134831460674158,
+      "grad_norm": 0.20935533940792084,
+      "learning_rate": 0.000155,
+      "loss": 0.1747,
+      "step": 108
+    },
+    {
+      "epoch": 1.2247191011235956,
+      "grad_norm": 0.23691172897815704,
+      "learning_rate": 0.00015454545454545454,
+      "loss": 0.2247,
+      "step": 109
+    },
+    {
+      "epoch": 1.2359550561797752,
+      "grad_norm": 0.22647719085216522,
+      "learning_rate": 0.00015409090909090912,
+      "loss": 0.1829,
+      "step": 110
+    },
+    {
+      "epoch": 1.247191011235955,
+      "grad_norm": 0.23936079442501068,
+      "learning_rate": 0.00015363636363636363,
+      "loss": 0.1938,
+      "step": 111
+    },
+    {
+      "epoch": 1.2584269662921348,
+      "grad_norm": 0.19330653548240662,
+      "learning_rate": 0.00015318181818181818,
+      "loss": 0.1603,
+      "step": 112
+    },
+    {
+      "epoch": 1.2696629213483146,
+      "grad_norm": 0.19124047458171844,
+      "learning_rate": 0.00015272727272727275,
+      "loss": 0.184,
+      "step": 113
+    },
+    {
+      "epoch": 1.2808988764044944,
+      "grad_norm": 0.1912234127521515,
+      "learning_rate": 0.00015227272727272727,
+      "loss": 0.1659,
+      "step": 114
+    },
+    {
+      "epoch": 1.2921348314606742,
+      "grad_norm": 0.1903829127550125,
+      "learning_rate": 0.0001518181818181818,
+      "loss": 0.1755,
+      "step": 115
+    },
+    {
+      "epoch": 1.303370786516854,
+      "grad_norm": 0.1836494654417038,
+      "learning_rate": 0.00015136363636363638,
+      "loss": 0.1575,
+      "step": 116
+    },
+    {
+      "epoch": 1.3146067415730336,
+      "grad_norm": 0.21919198334217072,
+      "learning_rate": 0.0001509090909090909,
+      "loss": 0.1978,
+      "step": 117
+    },
+    {
+      "epoch": 1.3258426966292136,
+      "grad_norm": 0.22532597184181213,
+      "learning_rate": 0.00015045454545454547,
+      "loss": 0.1604,
+      "step": 118
+    },
+    {
+      "epoch": 1.3370786516853932,
+      "grad_norm": 0.22674380242824554,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.183,
+      "step": 119
+    },
+    {
+      "epoch": 1.348314606741573,
+      "grad_norm": 0.23995709419250488,
+      "learning_rate": 0.00014954545454545453,
+      "loss": 0.1777,
+      "step": 120
+    },
+    {
+      "epoch": 1.3595505617977528,
+      "grad_norm": 0.15110474824905396,
+      "learning_rate": 0.0001490909090909091,
+      "loss": 0.154,
+      "step": 121
+    },
+    {
+      "epoch": 1.3707865168539326,
+      "grad_norm": 0.1769479662179947,
+      "learning_rate": 0.00014863636363636365,
+      "loss": 0.1824,
+      "step": 122
+    },
+    {
+      "epoch": 1.3820224719101124,
+      "grad_norm": 0.2355855405330658,
+      "learning_rate": 0.0001481818181818182,
+      "loss": 0.187,
+      "step": 123
+    },
+    {
+      "epoch": 1.3932584269662922,
+      "grad_norm": 0.21928639709949493,
+      "learning_rate": 0.00014772727272727274,
+      "loss": 0.2154,
+      "step": 124
+    },
+    {
+      "epoch": 1.404494382022472,
+      "grad_norm": 0.23884353041648865,
+      "learning_rate": 0.00014727272727272728,
+      "loss": 0.2144,
+      "step": 125
+    },
+    {
+      "epoch": 1.4157303370786516,
+      "grad_norm": 0.19905094802379608,
+      "learning_rate": 0.00014681818181818182,
+      "loss": 0.1758,
+      "step": 126
+    },
+    {
+      "epoch": 1.4269662921348314,
+      "grad_norm": 0.20008406043052673,
+      "learning_rate": 0.00014636363636363637,
+      "loss": 0.1988,
+      "step": 127
+    },
+    {
+      "epoch": 1.4382022471910112,
+      "grad_norm": 0.14788155257701874,
+      "learning_rate": 0.0001459090909090909,
+      "loss": 0.1591,
+      "step": 128
+    },
+    {
+      "epoch": 1.449438202247191,
+      "grad_norm": 0.17816966772079468,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 0.1607,
+      "step": 129
+    },
+    {
+      "epoch": 1.4606741573033708,
+      "grad_norm": 0.2414962351322174,
+      "learning_rate": 0.000145,
+      "loss": 0.1988,
+      "step": 130
+    },
+    {
+      "epoch": 1.4719101123595506,
+      "grad_norm": 0.21710173785686493,
+      "learning_rate": 0.00014454545454545457,
+      "loss": 0.1749,
+      "step": 131
+    },
+    {
+      "epoch": 1.4831460674157304,
+      "grad_norm": 0.30704858899116516,
+      "learning_rate": 0.0001440909090909091,
+      "loss": 0.2106,
+      "step": 132
+    },
+    {
+      "epoch": 1.49438202247191,
+      "grad_norm": 0.22256992757320404,
+      "learning_rate": 0.00014363636363636363,
+      "loss": 0.1828,
+      "step": 133
+    },
+    {
+      "epoch": 1.50561797752809,
+      "grad_norm": 0.2698194980621338,
+      "learning_rate": 0.0001431818181818182,
+      "loss": 0.2418,
+      "step": 134
+    },
+    {
+      "epoch": 1.5168539325842696,
+      "grad_norm": 0.22738061845302582,
+      "learning_rate": 0.00014272727272727272,
+      "loss": 0.2023,
+      "step": 135
+    },
+    {
+      "epoch": 1.5280898876404494,
+      "grad_norm": 0.2749398946762085,
+      "learning_rate": 0.00014227272727272727,
+      "loss": 0.2201,
+      "step": 136
+    },
+    {
+      "epoch": 1.5393258426966292,
+      "grad_norm": 0.20003195106983185,
+      "learning_rate": 0.00014181818181818184,
+      "loss": 0.1658,
+      "step": 137
+    },
+    {
+      "epoch": 1.550561797752809,
+      "grad_norm": 0.1827768236398697,
+      "learning_rate": 0.00014136363636363635,
+      "loss": 0.1787,
+      "step": 138
+    },
+    {
+      "epoch": 1.5617977528089888,
+      "grad_norm": 0.20226892828941345,
+      "learning_rate": 0.00014090909090909093,
+      "loss": 0.1812,
+      "step": 139
+    },
+    {
+      "epoch": 1.5730337078651684,
+      "grad_norm": 0.18449921905994415,
+      "learning_rate": 0.00014045454545454547,
+      "loss": 0.183,
+      "step": 140
+    },
+    {
+      "epoch": 1.5842696629213484,
+      "grad_norm": 0.22666248679161072,
+      "learning_rate": 0.00014,
+      "loss": 0.2163,
+      "step": 141
+    },
+    {
+      "epoch": 1.595505617977528,
+      "grad_norm": 0.2258187234401703,
+      "learning_rate": 0.00013954545454545456,
+      "loss": 0.2024,
+      "step": 142
+    },
+    {
+      "epoch": 1.606741573033708,
+      "grad_norm": 0.17761889100074768,
+      "learning_rate": 0.0001390909090909091,
+      "loss": 0.1822,
+      "step": 143
+    },
+    {
+      "epoch": 1.6179775280898876,
+      "grad_norm": 0.1967982053756714,
+      "learning_rate": 0.00013863636363636365,
+      "loss": 0.1768,
+      "step": 144
+    },
+    {
+      "epoch": 1.6292134831460674,
+      "grad_norm": 0.21614395081996918,
+      "learning_rate": 0.0001381818181818182,
+      "loss": 0.1941,
+      "step": 145
+    },
+    {
+      "epoch": 1.6404494382022472,
+      "grad_norm": 0.21362508833408356,
+      "learning_rate": 0.00013772727272727274,
+      "loss": 0.2053,
+      "step": 146
+    },
+    {
+      "epoch": 1.651685393258427,
+      "grad_norm": 0.1829160451889038,
+      "learning_rate": 0.00013727272727272728,
+      "loss": 0.1601,
+      "step": 147
+    },
+    {
+      "epoch": 1.6629213483146068,
+      "grad_norm": 0.19813786447048187,
+      "learning_rate": 0.00013681818181818182,
+      "loss": 0.2027,
+      "step": 148
+    },
+    {
+      "epoch": 1.6741573033707864,
+      "grad_norm": 0.19203445315361023,
+      "learning_rate": 0.00013636363636363637,
+      "loss": 0.1638,
+      "step": 149
+    },
+    {
+      "epoch": 1.6853932584269664,
+      "grad_norm": 0.1693754941225052,
+      "learning_rate": 0.0001359090909090909,
+      "loss": 0.1695,
+      "step": 150
+    },
+    {
+      "epoch": 1.696629213483146,
+      "grad_norm": 0.19884233176708221,
+      "learning_rate": 0.00013545454545454546,
+      "loss": 0.2037,
+      "step": 151
+    },
+    {
+      "epoch": 1.7078651685393258,
+      "grad_norm": 0.20025449991226196,
+      "learning_rate": 0.00013500000000000003,
+      "loss": 0.1927,
+      "step": 152
+    },
+    {
+      "epoch": 1.7191011235955056,
+      "grad_norm": 0.1659104973077774,
+      "learning_rate": 0.00013454545454545455,
+      "loss": 0.164,
+      "step": 153
+    },
+    {
+      "epoch": 1.7303370786516854,
+      "grad_norm": 0.16635450720787048,
+      "learning_rate": 0.0001340909090909091,
+      "loss": 0.1729,
+      "step": 154
+    },
+    {
+      "epoch": 1.7415730337078652,
+      "grad_norm": 0.2119787037372589,
+      "learning_rate": 0.00013363636363636366,
+      "loss": 0.1761,
+      "step": 155
+    },
+    {
+      "epoch": 1.7528089887640448,
+      "grad_norm": 0.1592678278684616,
+      "learning_rate": 0.00013318181818181818,
+      "loss": 0.1582,
+      "step": 156
+    },
+    {
+      "epoch": 1.7640449438202248,
+      "grad_norm": 0.20228628814220428,
+      "learning_rate": 0.00013272727272727275,
+      "loss": 0.1833,
+      "step": 157
+    },
+    {
+      "epoch": 1.7752808988764044,
+      "grad_norm": 0.19576573371887207,
+      "learning_rate": 0.0001322727272727273,
+      "loss": 0.1716,
+      "step": 158
+    },
+    {
+      "epoch": 1.7865168539325844,
+      "grad_norm": 0.17609822750091553,
+      "learning_rate": 0.0001318181818181818,
+      "loss": 0.1566,
+      "step": 159
+    },
+    {
+      "epoch": 1.797752808988764,
+      "grad_norm": 0.19382323324680328,
+      "learning_rate": 0.00013136363636363638,
+      "loss": 0.1637,
+      "step": 160
+    },
+    {
+      "epoch": 1.8089887640449438,
+      "grad_norm": 0.26488256454467773,
+      "learning_rate": 0.00013090909090909093,
+      "loss": 0.2064,
+      "step": 161
+    },
+    {
+      "epoch": 1.8202247191011236,
+      "grad_norm": 0.23723822832107544,
+      "learning_rate": 0.00013045454545454544,
+      "loss": 0.177,
+      "step": 162
+    },
+    {
+      "epoch": 1.8314606741573034,
+      "grad_norm": 0.1890057623386383,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 0.1784,
+      "step": 163
+    },
+    {
+      "epoch": 1.8426966292134832,
+      "grad_norm": 0.1911257803440094,
+      "learning_rate": 0.00012954545454545456,
+      "loss": 0.1788,
+      "step": 164
+    },
+    {
+      "epoch": 1.8539325842696628,
+      "grad_norm": 0.2343178540468216,
+      "learning_rate": 0.0001290909090909091,
+      "loss": 0.1833,
+      "step": 165
+    },
+    {
+      "epoch": 1.8651685393258428,
+      "grad_norm": 0.1506495475769043,
+      "learning_rate": 0.00012863636363636365,
+      "loss": 0.1655,
+      "step": 166
+    },
+    {
+      "epoch": 1.8764044943820224,
+      "grad_norm": 0.17160733044147491,
+      "learning_rate": 0.0001281818181818182,
+      "loss": 0.1586,
+      "step": 167
+    },
+    {
+      "epoch": 1.8876404494382022,
+      "grad_norm": 0.13511358201503754,
+      "learning_rate": 0.00012772727272727274,
+      "loss": 0.1439,
+      "step": 168
+    },
+    {
+      "epoch": 1.898876404494382,
+      "grad_norm": 0.1821577399969101,
+      "learning_rate": 0.00012727272727272728,
+      "loss": 0.1973,
+      "step": 169
+    },
+    {
+      "epoch": 1.9101123595505618,
+      "grad_norm": 0.18846295773983002,
+      "learning_rate": 0.00012681818181818183,
+      "loss": 0.1767,
+      "step": 170
+    },
+    {
+      "epoch": 1.9213483146067416,
+      "grad_norm": 0.17300470173358917,
+      "learning_rate": 0.00012636363636363637,
+      "loss": 0.1726,
+      "step": 171
+    },
+    {
+      "epoch": 1.9325842696629212,
+      "grad_norm": 0.20833244919776917,
+      "learning_rate": 0.00012590909090909091,
+      "loss": 0.2248,
+      "step": 172
+    },
+    {
+      "epoch": 1.9438202247191012,
+      "grad_norm": 0.17537686228752136,
+      "learning_rate": 0.00012545454545454546,
+      "loss": 0.147,
+      "step": 173
+    },
+    {
+      "epoch": 1.9550561797752808,
+      "grad_norm": 0.17684531211853027,
+      "learning_rate": 0.000125,
+      "loss": 0.1774,
+      "step": 174
+    },
+    {
+      "epoch": 1.9662921348314608,
+      "grad_norm": 0.20325636863708496,
+      "learning_rate": 0.00012454545454545455,
+      "loss": 0.1921,
+      "step": 175
+    },
+    {
+      "epoch": 1.9775280898876404,
+      "grad_norm": 0.2229178249835968,
+      "learning_rate": 0.0001240909090909091,
+      "loss": 0.2058,
+      "step": 176
+    },
+    {
+      "epoch": 1.9887640449438202,
+      "grad_norm": 0.18187855184078217,
+      "learning_rate": 0.00012363636363636364,
+      "loss": 0.1883,
+      "step": 177
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.18570281565189362,
+      "learning_rate": 0.0001231818181818182,
+      "loss": 0.1716,
+      "step": 178
+    },
+    {
+      "epoch": 2.0112359550561796,
+      "grad_norm": 0.1995418518781662,
+      "learning_rate": 0.00012272727272727272,
+      "loss": 0.1912,
+      "step": 179
+    },
+    {
+      "epoch": 2.0224719101123596,
+      "grad_norm": 0.14596399664878845,
+      "learning_rate": 0.00012227272727272727,
+      "loss": 0.1632,
+      "step": 180
+    },
+    {
+      "epoch": 2.033707865168539,
+      "grad_norm": 0.16283725202083588,
+      "learning_rate": 0.00012181818181818183,
+      "loss": 0.1625,
+      "step": 181
+    },
+    {
+      "epoch": 2.044943820224719,
+      "grad_norm": 0.1877950131893158,
+      "learning_rate": 0.00012136363636363637,
+      "loss": 0.1652,
+      "step": 182
+    },
+    {
+      "epoch": 2.056179775280899,
+      "grad_norm": 0.1613854616880417,
+      "learning_rate": 0.0001209090909090909,
+      "loss": 0.163,
+      "step": 183
+    },
+    {
+      "epoch": 2.067415730337079,
+      "grad_norm": 0.16473975777626038,
+      "learning_rate": 0.00012045454545454546,
+      "loss": 0.1789,
+      "step": 184
+    },
+    {
+      "epoch": 2.0786516853932584,
+      "grad_norm": 0.16732561588287354,
+      "learning_rate": 0.00012,
+      "loss": 0.1644,
+      "step": 185
+    },
+    {
+      "epoch": 2.0898876404494384,
+      "grad_norm": 0.16880598664283752,
+      "learning_rate": 0.00011954545454545456,
+      "loss": 0.1778,
+      "step": 186
+    },
+    {
+      "epoch": 2.101123595505618,
+      "grad_norm": 0.16750402748584747,
+      "learning_rate": 0.00011909090909090909,
+      "loss": 0.1557,
+      "step": 187
+    },
+    {
+      "epoch": 2.1123595505617976,
+      "grad_norm": 0.14607924222946167,
+      "learning_rate": 0.00011863636363636364,
+      "loss": 0.1495,
+      "step": 188
+    },
+    {
+      "epoch": 2.1235955056179776,
+      "grad_norm": 0.16760137677192688,
+      "learning_rate": 0.0001181818181818182,
+      "loss": 0.1645,
+      "step": 189
+    },
+    {
+      "epoch": 2.134831460674157,
+      "grad_norm": 0.20173385739326477,
+      "learning_rate": 0.00011772727272727272,
+      "loss": 0.1895,
+      "step": 190
+    },
+    {
+      "epoch": 2.146067415730337,
+      "grad_norm": 0.15915413200855255,
+      "learning_rate": 0.00011727272727272727,
+      "loss": 0.1627,
+      "step": 191
+    },
+    {
+      "epoch": 2.157303370786517,
+      "grad_norm": 0.22035230696201324,
+      "learning_rate": 0.00011681818181818183,
+      "loss": 0.2051,
+      "step": 192
+    },
+    {
+      "epoch": 2.168539325842697,
+      "grad_norm": 0.1504964381456375,
+      "learning_rate": 0.00011636363636363636,
+      "loss": 0.1649,
+      "step": 193
+    },
+    {
+      "epoch": 2.1797752808988764,
+      "grad_norm": 0.20308493077754974,
+      "learning_rate": 0.00011590909090909093,
+      "loss": 0.1559,
+      "step": 194
+    },
+    {
+      "epoch": 2.191011235955056,
+      "grad_norm": 0.16288025677204132,
+      "learning_rate": 0.00011545454545454546,
+      "loss": 0.1417,
+      "step": 195
+    },
+    {
+      "epoch": 2.202247191011236,
+      "grad_norm": 0.16168631613254547,
+      "learning_rate": 0.00011499999999999999,
+      "loss": 0.1656,
+      "step": 196
+    },
+    {
+      "epoch": 2.2134831460674156,
+      "grad_norm": 0.14705248177051544,
+      "learning_rate": 0.00011454545454545456,
+      "loss": 0.1457,
+      "step": 197
+    },
+    {
+      "epoch": 2.2247191011235956,
+      "grad_norm": 0.19702956080436707,
+      "learning_rate": 0.00011409090909090909,
+      "loss": 0.1784,
+      "step": 198
+    },
+    {
+      "epoch": 2.235955056179775,
+      "grad_norm": 0.16930997371673584,
+      "learning_rate": 0.00011363636363636365,
+      "loss": 0.1409,
+      "step": 199
+    },
+    {
+      "epoch": 2.247191011235955,
+      "grad_norm": 0.20724202692508698,
+      "learning_rate": 0.0001131818181818182,
+      "loss": 0.1874,
+      "step": 200
+    },
+    {
+      "epoch": 2.258426966292135,
+      "grad_norm": 0.14622414112091064,
+      "learning_rate": 0.00011272727272727272,
+      "loss": 0.1535,
+      "step": 201
+    },
+    {
+      "epoch": 2.2696629213483144,
+      "grad_norm": 0.24741311371326447,
+      "learning_rate": 0.00011227272727272728,
+      "loss": 0.1833,
+      "step": 202
+    },
+    {
+      "epoch": 2.2808988764044944,
+      "grad_norm": 0.20128554105758667,
+      "learning_rate": 0.00011181818181818183,
+      "loss": 0.1929,
+      "step": 203
+    },
+    {
+      "epoch": 2.292134831460674,
+      "grad_norm": 0.17340625822544098,
+      "learning_rate": 0.00011136363636363636,
+      "loss": 0.1656,
+      "step": 204
+    },
+    {
+      "epoch": 2.303370786516854,
+      "grad_norm": 0.15460006892681122,
+      "learning_rate": 0.00011090909090909092,
+      "loss": 0.1643,
+      "step": 205
+    },
+    {
+      "epoch": 2.3146067415730336,
+      "grad_norm": 0.19704340398311615,
+      "learning_rate": 0.00011045454545454546,
+      "loss": 0.1867,
+      "step": 206
+    },
+    {
+      "epoch": 2.3258426966292136,
+      "grad_norm": 0.14527174830436707,
+      "learning_rate": 0.00011000000000000002,
+      "loss": 0.1245,
+      "step": 207
+    },
+    {
+      "epoch": 2.337078651685393,
+      "grad_norm": 0.17086657881736755,
+      "learning_rate": 0.00010954545454545455,
+      "loss": 0.1762,
+      "step": 208
+    },
+    {
+      "epoch": 2.348314606741573,
+      "grad_norm": 0.16618594527244568,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.1565,
+      "step": 209
+    },
+    {
+      "epoch": 2.359550561797753,
+      "grad_norm": 0.17807389795780182,
+      "learning_rate": 0.00010863636363636365,
+      "loss": 0.1778,
+      "step": 210
+    },
+    {
+      "epoch": 2.370786516853933,
+      "grad_norm": 0.18786925077438354,
+      "learning_rate": 0.00010818181818181818,
+      "loss": 0.1655,
+      "step": 211
+    },
+    {
+      "epoch": 2.3820224719101124,
+      "grad_norm": 0.17768800258636475,
+      "learning_rate": 0.00010772727272727274,
+      "loss": 0.1653,
+      "step": 212
+    },
+    {
+      "epoch": 2.393258426966292,
+      "grad_norm": 0.17421704530715942,
+      "learning_rate": 0.00010727272727272728,
+      "loss": 0.1669,
+      "step": 213
+    },
+    {
+      "epoch": 2.404494382022472,
+      "grad_norm": 0.17153479158878326,
+      "learning_rate": 0.00010681818181818181,
+      "loss": 0.1606,
+      "step": 214
+    },
+    {
+      "epoch": 2.4157303370786516,
+      "grad_norm": 0.20289796590805054,
+      "learning_rate": 0.00010636363636363637,
+      "loss": 0.1919,
+      "step": 215
+    },
+    {
+      "epoch": 2.4269662921348316,
+      "grad_norm": 0.194489985704422,
+      "learning_rate": 0.00010590909090909092,
+      "loss": 0.1862,
+      "step": 216
+    },
+    {
+      "epoch": 2.438202247191011,
+      "grad_norm": 0.15572769939899445,
+      "learning_rate": 0.00010545454545454545,
+      "loss": 0.1607,
+      "step": 217
+    },
+    {
+      "epoch": 2.449438202247191,
+      "grad_norm": 0.16038504242897034,
+      "learning_rate": 0.000105,
+      "loss": 0.1543,
+      "step": 218
+    },
+    {
+      "epoch": 2.460674157303371,
+      "grad_norm": 0.19084928929805756,
+      "learning_rate": 0.00010454545454545455,
+      "loss": 0.2027,
+      "step": 219
+    },
+    {
+      "epoch": 2.4719101123595504,
+      "grad_norm": 0.18043439090251923,
+      "learning_rate": 0.0001040909090909091,
+      "loss": 0.1757,
+      "step": 220
+    },
+    {
+      "epoch": 2.4831460674157304,
+      "grad_norm": 0.15195126831531525,
+      "learning_rate": 0.00010363636363636364,
+      "loss": 0.1619,
+      "step": 221
+    },
+    {
+      "epoch": 2.49438202247191,
+      "grad_norm": 0.17387932538986206,
+      "learning_rate": 0.00010318181818181818,
+      "loss": 0.1823,
+      "step": 222
+    },
+    {
+      "epoch": 2.50561797752809,
+      "grad_norm": 0.16068069636821747,
+      "learning_rate": 0.00010272727272727274,
+      "loss": 0.1669,
+      "step": 223
+    },
+    {
+      "epoch": 2.5168539325842696,
+      "grad_norm": 0.18496158719062805,
+      "learning_rate": 0.00010227272727272727,
+      "loss": 0.1647,
+      "step": 224
+    },
+    {
+      "epoch": 2.5280898876404496,
+      "grad_norm": 0.16668476164340973,
+      "learning_rate": 0.00010181818181818181,
+      "loss": 0.1719,
+      "step": 225
+    },
+    {
+      "epoch": 2.539325842696629,
+      "grad_norm": 0.16353961825370789,
+      "learning_rate": 0.00010136363636363637,
+      "loss": 0.1803,
+      "step": 226
+    },
+    {
+      "epoch": 2.550561797752809,
+      "grad_norm": 0.14314891397953033,
+      "learning_rate": 0.0001009090909090909,
+      "loss": 0.1693,
+      "step": 227
+    },
+    {
+      "epoch": 2.561797752808989,
+      "grad_norm": 0.1646391600370407,
+      "learning_rate": 0.00010045454545454547,
+      "loss": 0.1917,
+      "step": 228
+    },
+    {
+      "epoch": 2.5730337078651684,
+      "grad_norm": 0.173238143324852,
+      "learning_rate": 0.0001,
+      "loss": 0.1827,
+      "step": 229
+    },
+    {
+      "epoch": 2.5842696629213484,
+      "grad_norm": 0.16539378464221954,
+      "learning_rate": 9.954545454545455e-05,
+      "loss": 0.1594,
+      "step": 230
+    },
+    {
+      "epoch": 2.595505617977528,
+      "grad_norm": 0.16949477791786194,
+      "learning_rate": 9.909090909090911e-05,
+      "loss": 0.1538,
+      "step": 231
+    },
+    {
+      "epoch": 2.606741573033708,
+      "grad_norm": 0.18005919456481934,
+      "learning_rate": 9.863636363636364e-05,
+      "loss": 0.1769,
+      "step": 232
+    },
+    {
+      "epoch": 2.6179775280898876,
+      "grad_norm": 0.16846978664398193,
+      "learning_rate": 9.818181818181818e-05,
+      "loss": 0.1722,
+      "step": 233
+    },
+    {
+      "epoch": 2.629213483146067,
+      "grad_norm": 0.16401781141757965,
+      "learning_rate": 9.772727272727274e-05,
+      "loss": 0.1633,
+      "step": 234
+    },
+    {
+      "epoch": 2.640449438202247,
+      "grad_norm": 0.196939155459404,
+      "learning_rate": 9.727272727272728e-05,
+      "loss": 0.1887,
+      "step": 235
+    },
+    {
+      "epoch": 2.6516853932584272,
+      "grad_norm": 0.21819128096103668,
+      "learning_rate": 9.681818181818181e-05,
+      "loss": 0.1821,
+      "step": 236
+    },
+    {
+      "epoch": 2.662921348314607,
+      "grad_norm": 0.16041137278079987,
+      "learning_rate": 9.636363636363637e-05,
+      "loss": 0.155,
+      "step": 237
+    },
+    {
+      "epoch": 2.6741573033707864,
+      "grad_norm": 0.17373093962669373,
+      "learning_rate": 9.590909090909092e-05,
+      "loss": 0.1684,
+      "step": 238
+    },
+    {
+      "epoch": 2.6853932584269664,
+      "grad_norm": 0.1691204160451889,
+      "learning_rate": 9.545454545454546e-05,
+      "loss": 0.1819,
+      "step": 239
+    },
+    {
+      "epoch": 2.696629213483146,
+      "grad_norm": 0.15193454921245575,
+      "learning_rate": 9.5e-05,
+      "loss": 0.1594,
+      "step": 240
+    },
+    {
+      "epoch": 2.7078651685393256,
+      "grad_norm": 0.17132344841957092,
+      "learning_rate": 9.454545454545455e-05,
+      "loss": 0.1699,
+      "step": 241
+    },
+    {
+      "epoch": 2.7191011235955056,
+      "grad_norm": 0.16452458500862122,
+      "learning_rate": 9.40909090909091e-05,
+      "loss": 0.1756,
+      "step": 242
+    },
+    {
+      "epoch": 2.7303370786516856,
+      "grad_norm": 0.18071810901165009,
+      "learning_rate": 9.363636363636364e-05,
+      "loss": 0.1597,
+      "step": 243
+    },
+    {
+      "epoch": 2.741573033707865,
+      "grad_norm": 0.20396122336387634,
+      "learning_rate": 9.318181818181818e-05,
+      "loss": 0.1787,
+      "step": 244
+    },
+    {
+      "epoch": 2.752808988764045,
+      "grad_norm": 0.22361145913600922,
+      "learning_rate": 9.272727272727273e-05,
+      "loss": 0.1824,
+      "step": 245
+    },
+    {
+      "epoch": 2.764044943820225,
+      "grad_norm": 0.16991250216960907,
+      "learning_rate": 9.227272727272727e-05,
+      "loss": 0.1605,
+      "step": 246
+    },
+    {
+      "epoch": 2.7752808988764044,
+      "grad_norm": 0.19506555795669556,
+      "learning_rate": 9.181818181818183e-05,
+      "loss": 0.1819,
+      "step": 247
+    },
+    {
+      "epoch": 2.7865168539325844,
+      "grad_norm": 0.14264117181301117,
+      "learning_rate": 9.136363636363637e-05,
+      "loss": 0.1615,
+      "step": 248
+    },
+    {
+      "epoch": 2.797752808988764,
+      "grad_norm": 0.1541077196598053,
+      "learning_rate": 9.090909090909092e-05,
+      "loss": 0.1616,
+      "step": 249
+    },
+    {
+      "epoch": 2.808988764044944,
+      "grad_norm": 0.13672606647014618,
+      "learning_rate": 9.045454545454546e-05,
+      "loss": 0.1548,
+      "step": 250
+    },
+    {
+      "epoch": 2.8202247191011236,
+      "grad_norm": 0.1655198186635971,
+      "learning_rate": 9e-05,
+      "loss": 0.1715,
+      "step": 251
+    },
+    {
+      "epoch": 2.831460674157303,
+      "grad_norm": 0.1501724272966385,
+      "learning_rate": 8.954545454545455e-05,
+      "loss": 0.1435,
+      "step": 252
+    },
+    {
+      "epoch": 2.842696629213483,
+      "grad_norm": 0.17689818143844604,
+      "learning_rate": 8.90909090909091e-05,
+      "loss": 0.1567,
+      "step": 253
+    },
+    {
+      "epoch": 2.853932584269663,
+      "grad_norm": 0.158350870013237,
+      "learning_rate": 8.863636363636364e-05,
+      "loss": 0.1486,
+      "step": 254
+    },
+    {
+      "epoch": 2.865168539325843,
+      "grad_norm": 0.19720739126205444,
+      "learning_rate": 8.818181818181818e-05,
+      "loss": 0.1729,
+      "step": 255
+    },
+    {
+      "epoch": 2.8764044943820224,
+      "grad_norm": 0.17139959335327148,
+      "learning_rate": 8.772727272727274e-05,
+      "loss": 0.185,
+      "step": 256
+    },
+    {
+      "epoch": 2.8876404494382024,
+      "grad_norm": 0.20194506645202637,
+      "learning_rate": 8.727272727272727e-05,
+      "loss": 0.1669,
+      "step": 257
+    },
+    {
+      "epoch": 2.898876404494382,
+      "grad_norm": 0.17279160022735596,
+      "learning_rate": 8.681818181818182e-05,
+      "loss": 0.1695,
+      "step": 258
+    },
+    {
+      "epoch": 2.9101123595505616,
+      "grad_norm": 0.20821331441402435,
+      "learning_rate": 8.636363636363637e-05,
+      "loss": 0.1665,
+      "step": 259
+    },
+    {
+      "epoch": 2.9213483146067416,
+      "grad_norm": 0.18540224432945251,
+      "learning_rate": 8.590909090909092e-05,
+      "loss": 0.1824,
+      "step": 260
+    },
+    {
+      "epoch": 2.932584269662921,
+      "grad_norm": 0.19717296957969666,
+      "learning_rate": 8.545454545454545e-05,
+      "loss": 0.1885,
+      "step": 261
+    },
+    {
+      "epoch": 2.943820224719101,
+      "grad_norm": 0.1944579929113388,
+      "learning_rate": 8.5e-05,
+      "loss": 0.1801,
+      "step": 262
+    },
+    {
+      "epoch": 2.955056179775281,
+      "grad_norm": 0.17243047058582306,
+      "learning_rate": 8.454545454545455e-05,
+      "loss": 0.1564,
+      "step": 263
+    },
+    {
+      "epoch": 2.966292134831461,
+      "grad_norm": 0.1788180023431778,
+      "learning_rate": 8.40909090909091e-05,
+      "loss": 0.1728,
+      "step": 264
+    },
+    {
+      "epoch": 2.9775280898876404,
+      "grad_norm": 0.18186365067958832,
+      "learning_rate": 8.363636363636364e-05,
+      "loss": 0.1805,
+      "step": 265
+    },
+    {
+      "epoch": 2.98876404494382,
+      "grad_norm": 0.1703241765499115,
+      "learning_rate": 8.318181818181818e-05,
+      "loss": 0.1748,
+      "step": 266
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.15256650745868683,
+      "learning_rate": 8.272727272727273e-05,
+      "loss": 0.1658,
+      "step": 267
+    },
+    {
+      "epoch": 3.0112359550561796,
+      "grad_norm": 0.1650206446647644,
+      "learning_rate": 8.227272727272729e-05,
+      "loss": 0.1741,
+      "step": 268
+    },
+    {
+      "epoch": 3.0224719101123596,
+      "grad_norm": 0.16593040525913239,
+      "learning_rate": 8.181818181818183e-05,
+      "loss": 0.1556,
+      "step": 269
+    },
+    {
+      "epoch": 3.033707865168539,
+      "grad_norm": 0.18191367387771606,
+      "learning_rate": 8.136363636363636e-05,
+      "loss": 0.1474,
+      "step": 270
+    },
+    {
+      "epoch": 3.044943820224719,
+      "grad_norm": 0.1665167361497879,
+      "learning_rate": 8.090909090909092e-05,
+      "loss": 0.1605,
+      "step": 271
+    },
+    {
+      "epoch": 3.056179775280899,
+      "grad_norm": 0.15633444488048553,
+      "learning_rate": 8.045454545454546e-05,
+      "loss": 0.1481,
+      "step": 272
+    },
+    {
+      "epoch": 3.067415730337079,
+      "grad_norm": 0.16935305297374725,
+      "learning_rate": 8e-05,
+      "loss": 0.1801,
+      "step": 273
+    },
+    {
+      "epoch": 3.0786516853932584,
+      "grad_norm": 0.1403079777956009,
+      "learning_rate": 7.954545454545455e-05,
+      "loss": 0.1419,
+      "step": 274
+    },
+    {
+      "epoch": 3.0898876404494384,
+      "grad_norm": 0.14026261866092682,
+      "learning_rate": 7.90909090909091e-05,
+      "loss": 0.1512,
+      "step": 275
+    },
+    {
+      "epoch": 3.101123595505618,
+      "grad_norm": 0.1634642481803894,
+      "learning_rate": 7.863636363636364e-05,
+      "loss": 0.157,
+      "step": 276
+    },
+    {
+      "epoch": 3.1123595505617976,
+      "grad_norm": 0.21129527688026428,
+      "learning_rate": 7.818181818181818e-05,
+      "loss": 0.1777,
+      "step": 277
+    },
+    {
+      "epoch": 3.1235955056179776,
+      "grad_norm": 0.16718165576457977,
+      "learning_rate": 7.772727272727273e-05,
+      "loss": 0.1616,
+      "step": 278
+    },
+    {
+      "epoch": 3.134831460674157,
+      "grad_norm": 0.15927419066429138,
+      "learning_rate": 7.727272727272727e-05,
+      "loss": 0.1528,
+      "step": 279
+    },
+    {
+      "epoch": 3.146067415730337,
+      "grad_norm": 0.2660486400127411,
+      "learning_rate": 7.681818181818182e-05,
+      "loss": 0.1837,
+      "step": 280
+    },
+    {
+      "epoch": 3.157303370786517,
+      "grad_norm": 0.1409679502248764,
+      "learning_rate": 7.636363636363637e-05,
+      "loss": 0.147,
+      "step": 281
+    },
+    {
+      "epoch": 3.168539325842697,
+      "grad_norm": 0.1339440941810608,
+      "learning_rate": 7.59090909090909e-05,
+      "loss": 0.1525,
+      "step": 282
+    },
+    {
+      "epoch": 3.1797752808988764,
+      "grad_norm": 0.17426900565624237,
+      "learning_rate": 7.545454545454545e-05,
+      "loss": 0.1489,
+      "step": 283
+    },
+    {
+      "epoch": 3.191011235955056,
+      "grad_norm": 0.1393343210220337,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.1423,
+      "step": 284
+    },
+    {
+      "epoch": 3.202247191011236,
+      "grad_norm": 0.1835043877363205,
+      "learning_rate": 7.454545454545455e-05,
+      "loss": 0.1815,
+      "step": 285
+    },
+    {
+      "epoch": 3.2134831460674156,
+      "grad_norm": 0.19945138692855835,
+      "learning_rate": 7.40909090909091e-05,
+      "loss": 0.195,
+      "step": 286
+    },
+    {
+      "epoch": 3.2247191011235956,
+      "grad_norm": 0.12838099896907806,
+      "learning_rate": 7.363636363636364e-05,
+      "loss": 0.1394,
+      "step": 287
+    },
+    {
+      "epoch": 3.235955056179775,
+      "grad_norm": 0.16134722530841827,
+      "learning_rate": 7.318181818181818e-05,
+      "loss": 0.1609,
+      "step": 288
+    },
+    {
+      "epoch": 3.247191011235955,
+      "grad_norm": 0.16024093329906464,
+      "learning_rate": 7.272727272727273e-05,
+      "loss": 0.1617,
+      "step": 289
+    },
+    {
+      "epoch": 3.258426966292135,
+      "grad_norm": 0.13171254098415375,
+      "learning_rate": 7.227272727272729e-05,
+      "loss": 0.1462,
+      "step": 290
+    },
+    {
+      "epoch": 3.2696629213483144,
+      "grad_norm": 0.16412955522537231,
+      "learning_rate": 7.181818181818182e-05,
+      "loss": 0.1616,
+      "step": 291
+    },
+    {
+      "epoch": 3.2808988764044944,
+      "grad_norm": 0.13625764846801758,
+      "learning_rate": 7.136363636363636e-05,
+      "loss": 0.1439,
+      "step": 292
+    },
+    {
+      "epoch": 3.292134831460674,
+      "grad_norm": 0.40764933824539185,
+      "learning_rate": 7.090909090909092e-05,
+      "loss": 0.1493,
+      "step": 293
+    },
+    {
+      "epoch": 3.303370786516854,
+      "grad_norm": 0.15316271781921387,
+      "learning_rate": 7.045454545454546e-05,
+      "loss": 0.1393,
+      "step": 294
+    },
+    {
+      "epoch": 3.3146067415730336,
+      "grad_norm": 0.2046615481376648,
+      "learning_rate": 7e-05,
+      "loss": 0.1835,
+      "step": 295
+    },
+    {
+      "epoch": 3.3258426966292136,
+      "grad_norm": 0.1829833984375,
+      "learning_rate": 6.954545454545455e-05,
+      "loss": 0.1699,
+      "step": 296
+    },
+    {
+      "epoch": 3.337078651685393,
+      "grad_norm": 0.17012086510658264,
+      "learning_rate": 6.90909090909091e-05,
+      "loss": 0.1598,
+      "step": 297
+    },
+    {
+      "epoch": 3.348314606741573,
+      "grad_norm": 0.19913016259670258,
+      "learning_rate": 6.863636363636364e-05,
+      "loss": 0.1819,
+      "step": 298
+    },
+    {
+      "epoch": 3.359550561797753,
+      "grad_norm": 0.15270492434501648,
+      "learning_rate": 6.818181818181818e-05,
+      "loss": 0.1297,
+      "step": 299
+    },
+    {
+      "epoch": 3.370786516853933,
+      "grad_norm": 0.20295540988445282,
+      "learning_rate": 6.772727272727273e-05,
+      "loss": 0.1639,
+      "step": 300
+    },
+    {
+      "epoch": 3.3820224719101124,
+      "grad_norm": 0.28618213534355164,
+      "learning_rate": 6.727272727272727e-05,
+      "loss": 0.1817,
+      "step": 301
+    },
+    {
+      "epoch": 3.393258426966292,
+      "grad_norm": 0.21655607223510742,
+      "learning_rate": 6.681818181818183e-05,
+      "loss": 0.1775,
+      "step": 302
+    },
+    {
+      "epoch": 3.404494382022472,
+      "grad_norm": 0.16043761372566223,
+      "learning_rate": 6.636363636363638e-05,
+      "loss": 0.1408,
+      "step": 303
+    },
+    {
+      "epoch": 3.4157303370786516,
+      "grad_norm": 0.18832853436470032,
+      "learning_rate": 6.59090909090909e-05,
+      "loss": 0.1648,
+      "step": 304
+    },
+    {
+      "epoch": 3.4269662921348316,
+      "grad_norm": 0.19430215656757355,
+      "learning_rate": 6.545454545454546e-05,
+      "loss": 0.1603,
+      "step": 305
+    },
+    {
+      "epoch": 3.438202247191011,
+      "grad_norm": 0.18084602057933807,
+      "learning_rate": 6.500000000000001e-05,
+      "loss": 0.1631,
+      "step": 306
+    },
+    {
+      "epoch": 3.449438202247191,
+      "grad_norm": 0.1944350153207779,
+      "learning_rate": 6.454545454545455e-05,
+      "loss": 0.1719,
+      "step": 307
+    },
+    {
+      "epoch": 3.460674157303371,
+      "grad_norm": 0.1583927869796753,
+      "learning_rate": 6.40909090909091e-05,
+      "loss": 0.1393,
+      "step": 308
+    },
+    {
+      "epoch": 3.4719101123595504,
+      "grad_norm": 0.1504002809524536,
+      "learning_rate": 6.363636363636364e-05,
+      "loss": 0.1479,
+      "step": 309
+    },
+    {
+      "epoch": 3.4831460674157304,
+      "grad_norm": 0.15900583565235138,
+      "learning_rate": 6.318181818181818e-05,
+      "loss": 0.1371,
+      "step": 310
+    },
+    {
+      "epoch": 3.49438202247191,
+      "grad_norm": 0.16969139873981476,
+      "learning_rate": 6.272727272727273e-05,
+      "loss": 0.1651,
+      "step": 311
+    },
+    {
+      "epoch": 3.50561797752809,
+      "grad_norm": 0.19286896288394928,
+      "learning_rate": 6.227272727272727e-05,
+      "loss": 0.181,
+      "step": 312
+    },
+    {
+      "epoch": 3.5168539325842696,
+      "grad_norm": 0.15525083243846893,
+      "learning_rate": 6.181818181818182e-05,
+      "loss": 0.1755,
+      "step": 313
+    },
+    {
+      "epoch": 3.5280898876404496,
+      "grad_norm": 0.14453306794166565,
+      "learning_rate": 6.136363636363636e-05,
+      "loss": 0.1504,
+      "step": 314
+    },
+    {
+      "epoch": 3.539325842696629,
+      "grad_norm": 0.14680127799510956,
+      "learning_rate": 6.090909090909091e-05,
+      "loss": 0.1506,
+      "step": 315
+    },
+    {
+      "epoch": 3.550561797752809,
+      "grad_norm": 0.1838373988866806,
+      "learning_rate": 6.045454545454545e-05,
+      "loss": 0.1682,
+      "step": 316
+    },
+    {
+      "epoch": 3.561797752808989,
+      "grad_norm": 0.21205776929855347,
+      "learning_rate": 6e-05,
+      "loss": 0.1868,
+      "step": 317
+    },
+    {
+      "epoch": 3.5730337078651684,
+      "grad_norm": 0.20755551755428314,
+      "learning_rate": 5.9545454545454546e-05,
+      "loss": 0.1768,
+      "step": 318
+    },
+    {
+      "epoch": 3.5842696629213484,
+      "grad_norm": 0.14389365911483765,
+      "learning_rate": 5.90909090909091e-05,
+      "loss": 0.159,
+      "step": 319
+    },
+    {
+      "epoch": 3.595505617977528,
+      "grad_norm": 0.15817323327064514,
+      "learning_rate": 5.8636363636363634e-05,
+      "loss": 0.167,
+      "step": 320
+    },
+    {
+      "epoch": 3.606741573033708,
+      "grad_norm": 0.1677711457014084,
+      "learning_rate": 5.818181818181818e-05,
+      "loss": 0.1575,
+      "step": 321
+    },
+    {
+      "epoch": 3.6179775280898876,
+      "grad_norm": 0.15083497762680054,
+      "learning_rate": 5.772727272727273e-05,
+      "loss": 0.164,
+      "step": 322
+    },
+    {
+      "epoch": 3.629213483146067,
+      "grad_norm": 0.16184101998806,
+      "learning_rate": 5.727272727272728e-05,
+      "loss": 0.1648,
+      "step": 323
+    },
+    {
+      "epoch": 3.640449438202247,
+      "grad_norm": 0.1676960438489914,
+      "learning_rate": 5.6818181818181825e-05,
+      "loss": 0.1732,
+      "step": 324
+    },
+    {
+      "epoch": 3.6516853932584272,
+      "grad_norm": 0.16604094207286835,
+      "learning_rate": 5.636363636363636e-05,
+      "loss": 0.1797,
+      "step": 325
+    },
+    {
+      "epoch": 3.662921348314607,
+      "grad_norm": 0.1593160778284073,
+      "learning_rate": 5.5909090909090913e-05,
+      "loss": 0.1626,
+      "step": 326
+    },
+    {
+      "epoch": 3.6741573033707864,
+      "grad_norm": 0.16803093254566193,
+      "learning_rate": 5.545454545454546e-05,
+      "loss": 0.1676,
+      "step": 327
+    },
+    {
+      "epoch": 3.6853932584269664,
+      "grad_norm": 0.15591773390769958,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.1571,
+      "step": 328
+    },
+    {
+      "epoch": 3.696629213483146,
+      "grad_norm": 0.15332892537117004,
+      "learning_rate": 5.4545454545454546e-05,
+      "loss": 0.1684,
+      "step": 329
+    },
+    {
+      "epoch": 3.7078651685393256,
+      "grad_norm": 0.15805967152118683,
+      "learning_rate": 5.409090909090909e-05,
+      "loss": 0.1653,
+      "step": 330
+    },
+    {
+      "epoch": 3.7191011235955056,
+      "grad_norm": 0.14145736396312714,
+      "learning_rate": 5.363636363636364e-05,
+      "loss": 0.1551,
+      "step": 331
+    },
+    {
+      "epoch": 3.7303370786516856,
+      "grad_norm": 0.16918998956680298,
+      "learning_rate": 5.3181818181818186e-05,
+      "loss": 0.1653,
+      "step": 332
+    },
+    {
+      "epoch": 3.741573033707865,
+      "grad_norm": 0.13821476697921753,
+      "learning_rate": 5.272727272727272e-05,
+      "loss": 0.1677,
+      "step": 333
+    },
+    {
+      "epoch": 3.752808988764045,
+      "grad_norm": 0.1746775358915329,
+      "learning_rate": 5.2272727272727274e-05,
+      "loss": 0.1698,
+      "step": 334
+    },
+    {
+      "epoch": 3.764044943820225,
+      "grad_norm": 0.15485592186450958,
+      "learning_rate": 5.181818181818182e-05,
+      "loss": 0.1434,
+      "step": 335
+    },
+    {
+      "epoch": 3.7752808988764044,
+      "grad_norm": 0.13947530090808868,
+      "learning_rate": 5.136363636363637e-05,
+      "loss": 0.1561,
+      "step": 336
+    },
+    {
+      "epoch": 3.7865168539325844,
+      "grad_norm": 0.18808624148368835,
+      "learning_rate": 5.090909090909091e-05,
+      "loss": 0.1772,
+      "step": 337
+    },
+    {
+      "epoch": 3.797752808988764,
+      "grad_norm": 0.1359715610742569,
+      "learning_rate": 5.045454545454545e-05,
+      "loss": 0.1588,
+      "step": 338
+    },
+    {
+      "epoch": 3.808988764044944,
+      "grad_norm": 0.14446499943733215,
+      "learning_rate": 5e-05,
+      "loss": 0.1533,
+      "step": 339
+    },
+    {
+      "epoch": 3.8202247191011236,
+      "grad_norm": 0.14543399214744568,
+      "learning_rate": 4.9545454545454553e-05,
+      "loss": 0.1555,
+      "step": 340
+    },
+    {
+      "epoch": 3.831460674157303,
+      "grad_norm": 0.1910828948020935,
+      "learning_rate": 4.909090909090909e-05,
+      "loss": 0.1675,
+      "step": 341
+    },
+    {
+      "epoch": 3.842696629213483,
+      "grad_norm": 0.15429803729057312,
+      "learning_rate": 4.863636363636364e-05,
+      "loss": 0.153,
+      "step": 342
+    },
+    {
+      "epoch": 3.853932584269663,
+      "grad_norm": 0.16174088418483734,
+      "learning_rate": 4.8181818181818186e-05,
+      "loss": 0.1666,
+      "step": 343
+    },
+    {
+      "epoch": 3.865168539325843,
+      "grad_norm": 0.17011404037475586,
+      "learning_rate": 4.772727272727273e-05,
+      "loss": 0.187,
+      "step": 344
+    },
+    {
+      "epoch": 3.8764044943820224,
+      "grad_norm": 0.14925739169120789,
+      "learning_rate": 4.7272727272727275e-05,
+      "loss": 0.1534,
+      "step": 345
+    },
+    {
+      "epoch": 3.8876404494382024,
+      "grad_norm": 0.1602795571088791,
+      "learning_rate": 4.681818181818182e-05,
+      "loss": 0.1512,
+      "step": 346
+    },
+    {
+      "epoch": 3.898876404494382,
+      "grad_norm": 0.15546512603759766,
+      "learning_rate": 4.636363636363636e-05,
+      "loss": 0.1508,
+      "step": 347
+    },
+    {
+      "epoch": 3.9101123595505616,
+      "grad_norm": 0.16389091312885284,
+      "learning_rate": 4.5909090909090914e-05,
+      "loss": 0.1568,
+      "step": 348
+    },
+    {
+      "epoch": 3.9213483146067416,
+      "grad_norm": 0.142495259642601,
+      "learning_rate": 4.545454545454546e-05,
+      "loss": 0.1544,
+      "step": 349
+    },
+    {
+      "epoch": 3.932584269662921,
+      "grad_norm": 0.15719622373580933,
+      "learning_rate": 4.5e-05,
+      "loss": 0.1436,
+      "step": 350
+    },
+    {
+      "epoch": 3.943820224719101,
+      "grad_norm": 0.1477130800485611,
+      "learning_rate": 4.454545454545455e-05,
+      "loss": 0.1593,
+      "step": 351
+    },
+    {
+      "epoch": 3.955056179775281,
+      "grad_norm": 0.1921541690826416,
+      "learning_rate": 4.409090909090909e-05,
+      "loss": 0.1737,
+      "step": 352
+    },
+    {
+      "epoch": 3.966292134831461,
+      "grad_norm": 0.15325406193733215,
+      "learning_rate": 4.3636363636363636e-05,
+      "loss": 0.1575,
+      "step": 353
+    },
+    {
+      "epoch": 3.9775280898876404,
+      "grad_norm": 0.1695924997329712,
+      "learning_rate": 4.318181818181819e-05,
+      "loss": 0.1536,
+      "step": 354
+    },
+    {
+      "epoch": 3.98876404494382,
+      "grad_norm": 0.18062083423137665,
+      "learning_rate": 4.2727272727272724e-05,
+      "loss": 0.1705,
+      "step": 355
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.13164108991622925,
+      "learning_rate": 4.2272727272727275e-05,
+      "loss": 0.1475,
+      "step": 356
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 445,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.867039323421696e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}