SFT warmup LoRA for 4B judge (9367 samples, 1 epoch)

.gitattributes

@@ -33,3 +33,7 @@ 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-700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-750/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-781/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+library_name: peft
+license: other
+base_model: unsloth/Qwen3-4B
+tags:
+- base_model:adapter:unsloth/Qwen3-4B
+- llama-factory
+- lora
+- transformers
+- unsloth
+pipeline_tag: text-generation
+model-index:
+- name: CodeRM-SFT-Warmup-Selection-4B-LlamaFactory
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# CodeRM-SFT-Warmup-Selection-4B-LlamaFactory
+
+This model is a fine-tuned version of [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) on the sft_warmup_selection_combined dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 6
+- total_train_batch_size: 12
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.17.1
+- Transformers 4.57.1
+- Pytorch 2.7.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.2

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-4B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d58bb27f819c825e6d940b4a9d2dba32fd3cb9335b22c235e291eb82117df5e2
+size 528550256

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 7.995150581897871e+17,
+    "train_loss": 0.5977290161287891,
+    "train_runtime": 6942.3995,
+    "train_samples_per_second": 1.349,
+    "train_steps_per_second": 0.112
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-700/README.md

@@ -0,0 +1,209 @@
+---
+base_model: unsloth/Qwen3-4B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-4B
+- llama-factory
+- lora
+- transformers
+- unsloth
+---
+
+# 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 0.17.1

checkpoint-700/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-4B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-700/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1933da9ed2bba72f7f089bb2587613ad7a53e8ef486a0a1436fc6007da56c26
+size 528550256

checkpoint-700/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-700/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-700/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:256613d87aba0337d34275b571c735101ce7ed823698ad328458fe1a1470467d
+size 1057390923

checkpoint-700/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

checkpoint-700/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc876fd454b48eb27c7b152597796e005c38f9ef5c716d9fa35ab37f054061ad
+size 1465

checkpoint-700/special_tokens_map.json

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

checkpoint-700/tokenizer.json

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

checkpoint-700/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-700/trainer_state.json

@@ -0,0 +1,1014 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.89666951323655,
+  "eval_steps": 25,
+  "global_step": 700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0064047822374039285,
+      "grad_norm": 5.6078200340271,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.1562,
+      "step": 5
+    },
+    {
+      "epoch": 0.012809564474807857,
+      "grad_norm": 5.326383590698242,
+      "learning_rate": 2.25e-06,
+      "loss": 1.0619,
+      "step": 10
+    },
+    {
+      "epoch": 0.019214346712211786,
+      "grad_norm": 2.7833762168884277,
+      "learning_rate": 3.5e-06,
+      "loss": 1.0511,
+      "step": 15
+    },
+    {
+      "epoch": 0.025619128949615714,
+      "grad_norm": 1.1198874711990356,
+      "learning_rate": 4.75e-06,
+      "loss": 0.931,
+      "step": 20
+    },
+    {
+      "epoch": 0.03202391118701964,
+      "grad_norm": 1.2183799743652344,
+      "learning_rate": 4.999659159998194e-06,
+      "loss": 0.8819,
+      "step": 25
+    },
+    {
+      "epoch": 0.03842869342442357,
+      "grad_norm": 0.7168175578117371,
+      "learning_rate": 4.998274656771894e-06,
+      "loss": 0.845,
+      "step": 30
+    },
+    {
+      "epoch": 0.0448334756618275,
+      "grad_norm": 0.5571187734603882,
+      "learning_rate": 4.995825777227236e-06,
+      "loss": 0.7982,
+      "step": 35
+    },
+    {
+      "epoch": 0.05123825789923143,
+      "grad_norm": 0.5454768538475037,
+      "learning_rate": 4.992313564696022e-06,
+      "loss": 0.7583,
+      "step": 40
+    },
+    {
+      "epoch": 0.057643040136635355,
+      "grad_norm": 0.4312361776828766,
+      "learning_rate": 4.9877395155372815e-06,
+      "loss": 0.7783,
+      "step": 45
+    },
+    {
+      "epoch": 0.06404782237403928,
+      "grad_norm": 0.34762468934059143,
+      "learning_rate": 4.982105578499759e-06,
+      "loss": 0.7645,
+      "step": 50
+    },
+    {
+      "epoch": 0.07045260461144322,
+      "grad_norm": 0.34647414088249207,
+      "learning_rate": 4.975414153891664e-06,
+      "loss": 0.7397,
+      "step": 55
+    },
+    {
+      "epoch": 0.07685738684884715,
+      "grad_norm": 0.33078256249427795,
+      "learning_rate": 4.967668092558024e-06,
+      "loss": 0.7325,
+      "step": 60
+    },
+    {
+      "epoch": 0.08326216908625107,
+      "grad_norm": 0.3410351872444153,
+      "learning_rate": 4.9588706946661066e-06,
+      "loss": 0.7037,
+      "step": 65
+    },
+    {
+      "epoch": 0.089666951323655,
+      "grad_norm": 0.3349353075027466,
+      "learning_rate": 4.949025708299395e-06,
+      "loss": 0.6928,
+      "step": 70
+    },
+    {
+      "epoch": 0.09607173356105893,
+      "grad_norm": 0.32335689663887024,
+      "learning_rate": 4.93813732786074e-06,
+      "loss": 0.6764,
+      "step": 75
+    },
+    {
+      "epoch": 0.10247651579846286,
+      "grad_norm": 0.33923929929733276,
+      "learning_rate": 4.926210192285359e-06,
+      "loss": 0.7398,
+      "step": 80
+    },
+    {
+      "epoch": 0.10888129803586678,
+      "grad_norm": 0.32697415351867676,
+      "learning_rate": 4.913249383064438e-06,
+      "loss": 0.6927,
+      "step": 85
+    },
+    {
+      "epoch": 0.11528608027327071,
+      "grad_norm": 0.34032362699508667,
+      "learning_rate": 4.899260422080195e-06,
+      "loss": 0.6909,
+      "step": 90
+    },
+    {
+      "epoch": 0.12169086251067464,
+      "grad_norm": 0.3949951231479645,
+      "learning_rate": 4.884249269253309e-06,
+      "loss": 0.6517,
+      "step": 95
+    },
+    {
+      "epoch": 0.12809564474807855,
+      "grad_norm": 0.40848004817962646,
+      "learning_rate": 4.868222320003731e-06,
+      "loss": 0.6625,
+      "step": 100
+    },
+    {
+      "epoch": 0.1345004269854825,
+      "grad_norm": 0.36571186780929565,
+      "learning_rate": 4.851186402525946e-06,
+      "loss": 0.6693,
+      "step": 105
+    },
+    {
+      "epoch": 0.14090520922288644,
+      "grad_norm": 0.33602604269981384,
+      "learning_rate": 4.8331487748798636e-06,
+      "loss": 0.6699,
+      "step": 110
+    },
+    {
+      "epoch": 0.14730999146029036,
+      "grad_norm": 0.3456333875656128,
+      "learning_rate": 4.814117121898554e-06,
+      "loss": 0.6265,
+      "step": 115
+    },
+    {
+      "epoch": 0.1537147736976943,
+      "grad_norm": 0.2806994915008545,
+      "learning_rate": 4.794099551914173e-06,
+      "loss": 0.6181,
+      "step": 120
+    },
+    {
+      "epoch": 0.16011955593509822,
+      "grad_norm": 0.352857381105423,
+      "learning_rate": 4.773104593303449e-06,
+      "loss": 0.6869,
+      "step": 125
+    },
+    {
+      "epoch": 0.16652433817250215,
+      "grad_norm": 0.3353271782398224,
+      "learning_rate": 4.751141190854214e-06,
+      "loss": 0.6184,
+      "step": 130
+    },
+    {
+      "epoch": 0.17292912040990607,
+      "grad_norm": 0.39950162172317505,
+      "learning_rate": 4.728218701954525e-06,
+      "loss": 0.6631,
+      "step": 135
+    },
+    {
+      "epoch": 0.17933390264731,
+      "grad_norm": 0.3852960169315338,
+      "learning_rate": 4.704346892606001e-06,
+      "loss": 0.6077,
+      "step": 140
+    },
+    {
+      "epoch": 0.18573868488471393,
+      "grad_norm": 0.3433144688606262,
+      "learning_rate": 4.6795359332630694e-06,
+      "loss": 0.6487,
+      "step": 145
+    },
+    {
+      "epoch": 0.19214346712211786,
+      "grad_norm": 0.437122106552124,
+      "learning_rate": 4.653796394499904e-06,
+      "loss": 0.6284,
+      "step": 150
+    },
+    {
+      "epoch": 0.19854824935952178,
+      "grad_norm": 0.3337637484073639,
+      "learning_rate": 4.627139242506882e-06,
+      "loss": 0.6177,
+      "step": 155
+    },
+    {
+      "epoch": 0.2049530315969257,
+      "grad_norm": 0.3271448016166687,
+      "learning_rate": 4.599575834418505e-06,
+      "loss": 0.6604,
+      "step": 160
+    },
+    {
+      "epoch": 0.21135781383432964,
+      "grad_norm": 0.4029073715209961,
+      "learning_rate": 4.571117913474749e-06,
+      "loss": 0.6151,
+      "step": 165
+    },
+    {
+      "epoch": 0.21776259607173357,
+      "grad_norm": 0.35433897376060486,
+      "learning_rate": 4.541777604017924e-06,
+      "loss": 0.5941,
+      "step": 170
+    },
+    {
+      "epoch": 0.2241673783091375,
+      "grad_norm": 0.40683719515800476,
+      "learning_rate": 4.511567406327162e-06,
+      "loss": 0.6196,
+      "step": 175
+    },
+    {
+      "epoch": 0.23057216054654142,
+      "grad_norm": 0.41791296005249023,
+      "learning_rate": 4.480500191292744e-06,
+      "loss": 0.6104,
+      "step": 180
+    },
+    {
+      "epoch": 0.23697694278394535,
+      "grad_norm": 0.3712579011917114,
+      "learning_rate": 4.448589194932521e-06,
+      "loss": 0.6091,
+      "step": 185
+    },
+    {
+      "epoch": 0.24338172502134928,
+      "grad_norm": 0.3512028157711029,
+      "learning_rate": 4.415848012752789e-06,
+      "loss": 0.5894,
+      "step": 190
+    },
+    {
+      "epoch": 0.2497865072587532,
+      "grad_norm": 0.3832685649394989,
+      "learning_rate": 4.38229059395599e-06,
+      "loss": 0.6143,
+      "step": 195
+    },
+    {
+      "epoch": 0.2561912894961571,
+      "grad_norm": 0.3921290338039398,
+      "learning_rate": 4.347931235497738e-06,
+      "loss": 0.6161,
+      "step": 200
+    },
+    {
+      "epoch": 0.26259607173356103,
+      "grad_norm": 0.40466588735580444,
+      "learning_rate": 4.312784575995669e-06,
+      "loss": 0.6008,
+      "step": 205
+    },
+    {
+      "epoch": 0.269000853970965,
+      "grad_norm": 0.9247767329216003,
+      "learning_rate": 4.276865589492747e-06,
+      "loss": 0.5971,
+      "step": 210
+    },
+    {
+      "epoch": 0.27540563620836894,
+      "grad_norm": 0.5003313422203064,
+      "learning_rate": 4.240189579077649e-06,
+      "loss": 0.5832,
+      "step": 215
+    },
+    {
+      "epoch": 0.28181041844577287,
+      "grad_norm": 0.41465386748313904,
+      "learning_rate": 4.202772170364969e-06,
+      "loss": 0.5909,
+      "step": 220
+    },
+    {
+      "epoch": 0.2882152006831768,
+      "grad_norm": 0.3520627021789551,
+      "learning_rate": 4.164629304838012e-06,
+      "loss": 0.5826,
+      "step": 225
+    },
+    {
+      "epoch": 0.2946199829205807,
+      "grad_norm": 0.38733118772506714,
+      "learning_rate": 4.125777233057007e-06,
+      "loss": 0.6092,
+      "step": 230
+    },
+    {
+      "epoch": 0.30102476515798465,
+      "grad_norm": 0.3622700870037079,
+      "learning_rate": 4.086232507735648e-06,
+      "loss": 0.5844,
+      "step": 235
+    },
+    {
+      "epoch": 0.3074295473953886,
+      "grad_norm": 0.47380566596984863,
+      "learning_rate": 4.0460119766889e-06,
+      "loss": 0.6075,
+      "step": 240
+    },
+    {
+      "epoch": 0.3138343296327925,
+      "grad_norm": 0.4540008008480072,
+      "learning_rate": 4.005132775655076e-06,
+      "loss": 0.572,
+      "step": 245
+    },
+    {
+      "epoch": 0.32023911187019644,
+      "grad_norm": 0.47770172357559204,
+      "learning_rate": 3.963612320995257e-06,
+      "loss": 0.6175,
+      "step": 250
+    },
+    {
+      "epoch": 0.32664389410760036,
+      "grad_norm": 0.3514467179775238,
+      "learning_rate": 3.921468302273137e-06,
+      "loss": 0.5618,
+      "step": 255
+    },
+    {
+      "epoch": 0.3330486763450043,
+      "grad_norm": 0.45986905694007874,
+      "learning_rate": 3.8787186747184826e-06,
+      "loss": 0.5442,
+      "step": 260
+    },
+    {
+      "epoch": 0.3394534585824082,
+      "grad_norm": 0.4583056569099426,
+      "learning_rate": 3.8353816515774115e-06,
+      "loss": 0.569,
+      "step": 265
+    },
+    {
+      "epoch": 0.34585824081981215,
+      "grad_norm": 0.3687354028224945,
+      "learning_rate": 3.79147569635273e-06,
+      "loss": 0.5555,
+      "step": 270
+    },
+    {
+      "epoch": 0.3522630230572161,
+      "grad_norm": 0.38063594698905945,
+      "learning_rate": 3.747019514937663e-06,
+      "loss": 0.6,
+      "step": 275
+    },
+    {
+      "epoch": 0.35866780529462,
+      "grad_norm": 0.430896520614624,
+      "learning_rate": 3.70203204764631e-06,
+      "loss": 0.5843,
+      "step": 280
+    },
+    {
+      "epoch": 0.36507258753202393,
+      "grad_norm": 0.5169083476066589,
+      "learning_rate": 3.6565324611442234e-06,
+      "loss": 0.5914,
+      "step": 285
+    },
+    {
+      "epoch": 0.37147736976942786,
+      "grad_norm": 0.36347025632858276,
+      "learning_rate": 3.6105401402825595e-06,
+      "loss": 0.5674,
+      "step": 290
+    },
+    {
+      "epoch": 0.3778821520068318,
+      "grad_norm": 0.3636574447154999,
+      "learning_rate": 3.5640746798392657e-06,
+      "loss": 0.6123,
+      "step": 295
+    },
+    {
+      "epoch": 0.3842869342442357,
+      "grad_norm": 0.4619109332561493,
+      "learning_rate": 3.5171558761708334e-06,
+      "loss": 0.5708,
+      "step": 300
+    },
+    {
+      "epoch": 0.39069171648163964,
+      "grad_norm": 0.447704553604126,
+      "learning_rate": 3.469803718778166e-06,
+      "loss": 0.5722,
+      "step": 305
+    },
+    {
+      "epoch": 0.39709649871904357,
+      "grad_norm": 0.39746832847595215,
+      "learning_rate": 3.4220383817901625e-06,
+      "loss": 0.5772,
+      "step": 310
+    },
+    {
+      "epoch": 0.4035012809564475,
+      "grad_norm": 0.4326777160167694,
+      "learning_rate": 3.3738802153686414e-06,
+      "loss": 0.5715,
+      "step": 315
+    },
+    {
+      "epoch": 0.4099060631938514,
+      "grad_norm": 0.4147851765155792,
+      "learning_rate": 3.3253497370382605e-06,
+      "loss": 0.572,
+      "step": 320
+    },
+    {
+      "epoch": 0.41631084543125535,
+      "grad_norm": 0.43767350912094116,
+      "learning_rate": 3.2764676229451397e-06,
+      "loss": 0.563,
+      "step": 325
+    },
+    {
+      "epoch": 0.4227156276686593,
+      "grad_norm": 0.36241263151168823,
+      "learning_rate": 3.227254699047904e-06,
+      "loss": 0.5649,
+      "step": 330
+    },
+    {
+      "epoch": 0.4291204099060632,
+      "grad_norm": 0.5232857465744019,
+      "learning_rate": 3.177731932244892e-06,
+      "loss": 0.5645,
+      "step": 335
+    },
+    {
+      "epoch": 0.43552519214346713,
+      "grad_norm": 0.4475226104259491,
+      "learning_rate": 3.127920421441327e-06,
+      "loss": 0.5767,
+      "step": 340
+    },
+    {
+      "epoch": 0.44192997438087106,
+      "grad_norm": 0.4484921991825104,
+      "learning_rate": 3.077841388560243e-06,
+      "loss": 0.591,
+      "step": 345
+    },
+    {
+      "epoch": 0.448334756618275,
+      "grad_norm": 0.5250320434570312,
+      "learning_rate": 3.0275161695009975e-06,
+      "loss": 0.5814,
+      "step": 350
+    },
+    {
+      "epoch": 0.4547395388556789,
+      "grad_norm": 0.47690996527671814,
+      "learning_rate": 2.9769662050492276e-06,
+      "loss": 0.5602,
+      "step": 355
+    },
+    {
+      "epoch": 0.46114432109308284,
+      "grad_norm": 0.4651663899421692,
+      "learning_rate": 2.926213031742125e-06,
+      "loss": 0.5741,
+      "step": 360
+    },
+    {
+      "epoch": 0.46754910333048677,
+      "grad_norm": 0.46296215057373047,
+      "learning_rate": 2.8752782726929045e-06,
+      "loss": 0.5614,
+      "step": 365
+    },
+    {
+      "epoch": 0.4739538855678907,
+      "grad_norm": 0.5162904262542725,
+      "learning_rate": 2.8241836283784026e-06,
+      "loss": 0.5483,
+      "step": 370
+    },
+    {
+      "epoch": 0.4803586678052946,
+      "grad_norm": 0.3958864212036133,
+      "learning_rate": 2.7729508673936972e-06,
+      "loss": 0.5745,
+      "step": 375
+    },
+    {
+      "epoch": 0.48676345004269855,
+      "grad_norm": 0.4186757504940033,
+      "learning_rate": 2.721601817177725e-06,
+      "loss": 0.5459,
+      "step": 380
+    },
+    {
+      "epoch": 0.4931682322801025,
+      "grad_norm": 0.4372413456439972,
+      "learning_rate": 2.6701583547138165e-06,
+      "loss": 0.5852,
+      "step": 385
+    },
+    {
+      "epoch": 0.4995730145175064,
+      "grad_norm": 0.4488023519515991,
+      "learning_rate": 2.618642397209126e-06,
+      "loss": 0.5427,
+      "step": 390
+    },
+    {
+      "epoch": 0.5059777967549103,
+      "grad_norm": 0.4278182089328766,
+      "learning_rate": 2.567075892756924e-06,
+      "loss": 0.5586,
+      "step": 395
+    },
+    {
+      "epoch": 0.5123825789923142,
+      "grad_norm": 0.48016875982284546,
+      "learning_rate": 2.5154808109857367e-06,
+      "loss": 0.5405,
+      "step": 400
+    },
+    {
+      "epoch": 0.5187873612297181,
+      "grad_norm": 0.5077680945396423,
+      "learning_rate": 2.4638791336992967e-06,
+      "loss": 0.5682,
+      "step": 405
+    },
+    {
+      "epoch": 0.5251921434671221,
+      "grad_norm": 0.5091099739074707,
+      "learning_rate": 2.4122928455113233e-06,
+      "loss": 0.5619,
+      "step": 410
+    },
+    {
+      "epoch": 0.531596925704526,
+      "grad_norm": 0.4333205223083496,
+      "learning_rate": 2.360743924479093e-06,
+      "loss": 0.5879,
+      "step": 415
+    },
+    {
+      "epoch": 0.53800170794193,
+      "grad_norm": 0.4178122282028198,
+      "learning_rate": 2.3092543327398083e-06,
+      "loss": 0.5332,
+      "step": 420
+    },
+    {
+      "epoch": 0.544406490179334,
+      "grad_norm": 0.4080513119697571,
+      "learning_rate": 2.2578460071537512e-06,
+      "loss": 0.5728,
+      "step": 425
+    },
+    {
+      "epoch": 0.5508112724167379,
+      "grad_norm": 0.48982349038124084,
+      "learning_rate": 2.2065408499582e-06,
+      "loss": 0.575,
+      "step": 430
+    },
+    {
+      "epoch": 0.5572160546541418,
+      "grad_norm": 0.4953416883945465,
+      "learning_rate": 2.155360719436102e-06,
+      "loss": 0.5404,
+      "step": 435
+    },
+    {
+      "epoch": 0.5636208368915457,
+      "grad_norm": 0.4608188271522522,
+      "learning_rate": 2.1043274206034727e-06,
+      "loss": 0.5579,
+      "step": 440
+    },
+    {
+      "epoch": 0.5700256191289497,
+      "grad_norm": 0.48403236269950867,
+      "learning_rate": 2.0534626959194816e-06,
+      "loss": 0.5383,
+      "step": 445
+    },
+    {
+      "epoch": 0.5764304013663536,
+      "grad_norm": 0.4532581865787506,
+      "learning_rate": 2.002788216023203e-06,
+      "loss": 0.5638,
+      "step": 450
+    },
+    {
+      "epoch": 0.5828351836037575,
+      "grad_norm": 0.53521728515625,
+      "learning_rate": 1.9523255705009558e-06,
+      "loss": 0.5549,
+      "step": 455
+    },
+    {
+      "epoch": 0.5892399658411615,
+      "grad_norm": 0.4711097180843353,
+      "learning_rate": 1.902096258688174e-06,
+      "loss": 0.5027,
+      "step": 460
+    },
+    {
+      "epoch": 0.5956447480785654,
+      "grad_norm": 0.43662044405937195,
+      "learning_rate": 1.8521216805097358e-06,
+      "loss": 0.556,
+      "step": 465
+    },
+    {
+      "epoch": 0.6020495303159693,
+      "grad_norm": 0.3957918882369995,
+      "learning_rate": 1.8024231273626424e-06,
+      "loss": 0.5596,
+      "step": 470
+    },
+    {
+      "epoch": 0.6084543125533732,
+      "grad_norm": 0.5218236446380615,
+      "learning_rate": 1.7530217730449312e-06,
+      "loss": 0.5405,
+      "step": 475
+    },
+    {
+      "epoch": 0.6148590947907772,
+      "grad_norm": 0.4223135709762573,
+      "learning_rate": 1.7039386647346975e-06,
+      "loss": 0.5279,
+      "step": 480
+    },
+    {
+      "epoch": 0.6212638770281811,
+      "grad_norm": 0.3835909068584442,
+      "learning_rate": 1.6551947140230568e-06,
+      "loss": 0.5747,
+      "step": 485
+    },
+    {
+      "epoch": 0.627668659265585,
+      "grad_norm": 0.5082884430885315,
+      "learning_rate": 1.6068106880048747e-06,
+      "loss": 0.5518,
+      "step": 490
+    },
+    {
+      "epoch": 0.6340734415029889,
+      "grad_norm": 0.4860563278198242,
+      "learning_rate": 1.5588072004310634e-06,
+      "loss": 0.5641,
+      "step": 495
+    },
+    {
+      "epoch": 0.6404782237403929,
+      "grad_norm": 0.4176677167415619,
+      "learning_rate": 1.5112047029262e-06,
+      "loss": 0.5547,
+      "step": 500
+    },
+    {
+      "epoch": 0.6468830059777968,
+      "grad_norm": 0.3659776747226715,
+      "learning_rate": 1.4640234762752248e-06,
+      "loss": 0.5503,
+      "step": 505
+    },
+    {
+      "epoch": 0.6532877882152007,
+      "grad_norm": 0.4908987283706665,
+      "learning_rate": 1.4172836217829267e-06,
+      "loss": 0.5549,
+      "step": 510
+    },
+    {
+      "epoch": 0.6596925704526047,
+      "grad_norm": 0.44962796568870544,
+      "learning_rate": 1.3710050527098867e-06,
+      "loss": 0.573,
+      "step": 515
+    },
+    {
+      "epoch": 0.6660973526900086,
+      "grad_norm": 0.4549601376056671,
+      "learning_rate": 1.3252074857885453e-06,
+      "loss": 0.5666,
+      "step": 520
+    },
+    {
+      "epoch": 0.6725021349274125,
+      "grad_norm": 0.48955774307250977,
+      "learning_rate": 1.2799104328229928e-06,
+      "loss": 0.5379,
+      "step": 525
+    },
+    {
+      "epoch": 0.6789069171648164,
+      "grad_norm": 0.45902734994888306,
+      "learning_rate": 1.2351331923760743e-06,
+      "loss": 0.5345,
+      "step": 530
+    },
+    {
+      "epoch": 0.6853116994022204,
+      "grad_norm": 0.49846968054771423,
+      "learning_rate": 1.1908948415473418e-06,
+      "loss": 0.5367,
+      "step": 535
+    },
+    {
+      "epoch": 0.6917164816396243,
+      "grad_norm": 0.48370206356048584,
+      "learning_rate": 1.1472142278453582e-06,
+      "loss": 0.5325,
+      "step": 540
+    },
+    {
+      "epoch": 0.6981212638770282,
+      "grad_norm": 0.3830443024635315,
+      "learning_rate": 1.1041099611578177e-06,
+      "loss": 0.5585,
+      "step": 545
+    },
+    {
+      "epoch": 0.7045260461144321,
+      "grad_norm": 0.47550487518310547,
+      "learning_rate": 1.0616004058229084e-06,
+      "loss": 0.5417,
+      "step": 550
+    },
+    {
+      "epoch": 0.7109308283518361,
+      "grad_norm": 0.46026965975761414,
+      "learning_rate": 1.0197036728052847e-06,
+      "loss": 0.5715,
+      "step": 555
+    },
+    {
+      "epoch": 0.71733561058924,
+      "grad_norm": 0.42247724533081055,
+      "learning_rate": 9.784376119799851e-07,
+      "loss": 0.5459,
+      "step": 560
+    },
+    {
+      "epoch": 0.7237403928266439,
+      "grad_norm": 0.5001282095909119,
+      "learning_rate": 9.378198045275968e-07,
+      "loss": 0.5557,
+      "step": 565
+    },
+    {
+      "epoch": 0.7301451750640479,
+      "grad_norm": 0.4762704372406006,
+      "learning_rate": 8.97867555443886e-07,
+      "loss": 0.5338,
+      "step": 570
+    },
+    {
+      "epoch": 0.7365499573014518,
+      "grad_norm": 0.48811063170433044,
+      "learning_rate": 8.585978861670958e-07,
+      "loss": 0.5331,
+      "step": 575
+    },
+    {
+      "epoch": 0.7429547395388557,
+      "grad_norm": 0.45258718729019165,
+      "learning_rate": 8.200275273260611e-07,
+      "loss": 0.5461,
+      "step": 580
+    },
+    {
+      "epoch": 0.7493595217762596,
+      "grad_norm": 0.4314691424369812,
+      "learning_rate": 7.821729116122126e-07,
+      "loss": 0.558,
+      "step": 585
+    },
+    {
+      "epoch": 0.7557643040136636,
+      "grad_norm": 0.4526233673095703,
+      "learning_rate": 7.450501667785146e-07,
+      "loss": 0.5455,
+      "step": 590
+    },
+    {
+      "epoch": 0.7621690862510675,
+      "grad_norm": 0.4625132977962494,
+      "learning_rate": 7.086751087683297e-07,
+      "loss": 0.5514,
+      "step": 595
+    },
+    {
+      "epoch": 0.7685738684884714,
+      "grad_norm": 0.4986107349395752,
+      "learning_rate": 6.730632349771193e-07,
+      "loss": 0.5566,
+      "step": 600
+    },
+    {
+      "epoch": 0.7749786507258754,
+      "grad_norm": 0.5132951140403748,
+      "learning_rate": 6.3822971764986e-07,
+      "loss": 0.5363,
+      "step": 605
+    },
+    {
+      "epoch": 0.7813834329632793,
+      "grad_norm": 0.48895248770713806,
+      "learning_rate": 6.041893974169963e-07,
+      "loss": 0.5382,
+      "step": 610
+    },
+    {
+      "epoch": 0.7877882152006832,
+      "grad_norm": 0.48889264464378357,
+      "learning_rate": 5.709567769716678e-07,
+      "loss": 0.5511,
+      "step": 615
+    },
+    {
+      "epoch": 0.7941929974380871,
+      "grad_norm": 0.4542140066623688,
+      "learning_rate": 5.385460148909169e-07,
+      "loss": 0.5227,
+      "step": 620
+    },
+    {
+      "epoch": 0.8005977796754911,
+      "grad_norm": 0.48940637707710266,
+      "learning_rate": 5.069709196035011e-07,
+      "loss": 0.5519,
+      "step": 625
+    },
+    {
+      "epoch": 0.807002561912895,
+      "grad_norm": 0.45722976326942444,
+      "learning_rate": 4.762449435068914e-07,
+      "loss": 0.5358,
+      "step": 630
+    },
+    {
+      "epoch": 0.8134073441502989,
+      "grad_norm": 0.5042068958282471,
+      "learning_rate": 4.4638117723595054e-07,
+      "loss": 0.5686,
+      "step": 635
+    },
+    {
+      "epoch": 0.8198121263877028,
+      "grad_norm": 0.4974375069141388,
+      "learning_rate": 4.173923440857358e-07,
+      "loss": 0.5528,
+      "step": 640
+    },
+    {
+      "epoch": 0.8262169086251068,
+      "grad_norm": 0.4234403669834137,
+      "learning_rate": 3.892907945908128e-07,
+      "loss": 0.5305,
+      "step": 645
+    },
+    {
+      "epoch": 0.8326216908625107,
+      "grad_norm": 0.5144878029823303,
+      "learning_rate": 3.6208850126337595e-07,
+      "loss": 0.5282,
+      "step": 650
+    },
+    {
+      "epoch": 0.8390264730999146,
+      "grad_norm": 0.41059333086013794,
+      "learning_rate": 3.357970534924229e-07,
+      "loss": 0.5601,
+      "step": 655
+    },
+    {
+      "epoch": 0.8454312553373186,
+      "grad_norm": 0.40885528922080994,
+      "learning_rate": 3.104276526061617e-07,
+      "loss": 0.536,
+      "step": 660
+    },
+    {
+      "epoch": 0.8518360375747225,
+      "grad_norm": 0.462971568107605,
+      "learning_rate": 2.859911070997437e-07,
+      "loss": 0.5513,
+      "step": 665
+    },
+    {
+      "epoch": 0.8582408198121264,
+      "grad_norm": 0.6165898442268372,
+      "learning_rate": 2.624978280303628e-07,
+      "loss": 0.5542,
+      "step": 670
+    },
+    {
+      "epoch": 0.8646456020495303,
+      "grad_norm": 0.514519453048706,
+      "learning_rate": 2.3995782458168276e-07,
+      "loss": 0.5572,
+      "step": 675
+    },
+    {
+      "epoch": 0.8710503842869343,
+      "grad_norm": 0.5139626264572144,
+      "learning_rate": 2.1838069979947945e-07,
+      "loss": 0.5372,
+      "step": 680
+    },
+    {
+      "epoch": 0.8774551665243382,
+      "grad_norm": 1.6515536308288574,
+      "learning_rate": 1.9777564650031112e-07,
+      "loss": 0.5515,
+      "step": 685
+    },
+    {
+      "epoch": 0.8838599487617421,
+      "grad_norm": 0.4731055200099945,
+      "learning_rate": 1.7815144335497524e-07,
+      "loss": 0.5515,
+      "step": 690
+    },
+    {
+      "epoch": 0.890264730999146,
+      "grad_norm": 0.5183550715446472,
+      "learning_rate": 1.5951645114839875e-07,
+      "loss": 0.5419,
+      "step": 695
+    },
+    {
+      "epoch": 0.89666951323655,
+      "grad_norm": 0.5357317328453064,
+      "learning_rate": 1.4187860921757252e-07,
+      "loss": 0.5571,
+      "step": 700
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 781,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.188029729285407e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-700/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e589d07524a7c0f0a1d12d5318498811c749686a723a601fe53896da63fc46f5
+size 6417

checkpoint-750/README.md

@@ -0,0 +1,209 @@
+---
+base_model: unsloth/Qwen3-4B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-4B
+- llama-factory
+- lora
+- transformers
+- unsloth
+---
+
+# 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 0.17.1

checkpoint-750/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-4B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-750/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf499ca368ba6fd89ddc8d5f63e2de8106553fa74cf3905a3739ada99d241d21
+size 528550256

checkpoint-750/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-750/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-750/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c58c70e57788c2342a0aea02ad1df87c700c82b1a4e602f9934ccb1d9593758
+size 1057390923

checkpoint-750/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

checkpoint-750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d3a4b357a0509edb297752f7c1a977f02b72fe1361f511d67e1661149605a75
+size 1465

checkpoint-750/special_tokens_map.json

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

checkpoint-750/tokenizer.json

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

checkpoint-750/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-750/trainer_state.json

@@ -0,0 +1,1084 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9607173356105893,
+  "eval_steps": 25,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0064047822374039285,
+      "grad_norm": 5.6078200340271,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.1562,
+      "step": 5
+    },
+    {
+      "epoch": 0.012809564474807857,
+      "grad_norm": 5.326383590698242,
+      "learning_rate": 2.25e-06,
+      "loss": 1.0619,
+      "step": 10
+    },
+    {
+      "epoch": 0.019214346712211786,
+      "grad_norm": 2.7833762168884277,
+      "learning_rate": 3.5e-06,
+      "loss": 1.0511,
+      "step": 15
+    },
+    {
+      "epoch": 0.025619128949615714,
+      "grad_norm": 1.1198874711990356,
+      "learning_rate": 4.75e-06,
+      "loss": 0.931,
+      "step": 20
+    },
+    {
+      "epoch": 0.03202391118701964,
+      "grad_norm": 1.2183799743652344,
+      "learning_rate": 4.999659159998194e-06,
+      "loss": 0.8819,
+      "step": 25
+    },
+    {
+      "epoch": 0.03842869342442357,
+      "grad_norm": 0.7168175578117371,
+      "learning_rate": 4.998274656771894e-06,
+      "loss": 0.845,
+      "step": 30
+    },
+    {
+      "epoch": 0.0448334756618275,
+      "grad_norm": 0.5571187734603882,
+      "learning_rate": 4.995825777227236e-06,
+      "loss": 0.7982,
+      "step": 35
+    },
+    {
+      "epoch": 0.05123825789923143,
+      "grad_norm": 0.5454768538475037,
+      "learning_rate": 4.992313564696022e-06,
+      "loss": 0.7583,
+      "step": 40
+    },
+    {
+      "epoch": 0.057643040136635355,
+      "grad_norm": 0.4312361776828766,
+      "learning_rate": 4.9877395155372815e-06,
+      "loss": 0.7783,
+      "step": 45
+    },
+    {
+      "epoch": 0.06404782237403928,
+      "grad_norm": 0.34762468934059143,
+      "learning_rate": 4.982105578499759e-06,
+      "loss": 0.7645,
+      "step": 50
+    },
+    {
+      "epoch": 0.07045260461144322,
+      "grad_norm": 0.34647414088249207,
+      "learning_rate": 4.975414153891664e-06,
+      "loss": 0.7397,
+      "step": 55
+    },
+    {
+      "epoch": 0.07685738684884715,
+      "grad_norm": 0.33078256249427795,
+      "learning_rate": 4.967668092558024e-06,
+      "loss": 0.7325,
+      "step": 60
+    },
+    {
+      "epoch": 0.08326216908625107,
+      "grad_norm": 0.3410351872444153,
+      "learning_rate": 4.9588706946661066e-06,
+      "loss": 0.7037,
+      "step": 65
+    },
+    {
+      "epoch": 0.089666951323655,
+      "grad_norm": 0.3349353075027466,
+      "learning_rate": 4.949025708299395e-06,
+      "loss": 0.6928,
+      "step": 70
+    },
+    {
+      "epoch": 0.09607173356105893,
+      "grad_norm": 0.32335689663887024,
+      "learning_rate": 4.93813732786074e-06,
+      "loss": 0.6764,
+      "step": 75
+    },
+    {
+      "epoch": 0.10247651579846286,
+      "grad_norm": 0.33923929929733276,
+      "learning_rate": 4.926210192285359e-06,
+      "loss": 0.7398,
+      "step": 80
+    },
+    {
+      "epoch": 0.10888129803586678,
+      "grad_norm": 0.32697415351867676,
+      "learning_rate": 4.913249383064438e-06,
+      "loss": 0.6927,
+      "step": 85
+    },
+    {
+      "epoch": 0.11528608027327071,
+      "grad_norm": 0.34032362699508667,
+      "learning_rate": 4.899260422080195e-06,
+      "loss": 0.6909,
+      "step": 90
+    },
+    {
+      "epoch": 0.12169086251067464,
+      "grad_norm": 0.3949951231479645,
+      "learning_rate": 4.884249269253309e-06,
+      "loss": 0.6517,
+      "step": 95
+    },
+    {
+      "epoch": 0.12809564474807855,
+      "grad_norm": 0.40848004817962646,
+      "learning_rate": 4.868222320003731e-06,
+      "loss": 0.6625,
+      "step": 100
+    },
+    {
+      "epoch": 0.1345004269854825,
+      "grad_norm": 0.36571186780929565,
+      "learning_rate": 4.851186402525946e-06,
+      "loss": 0.6693,
+      "step": 105
+    },
+    {
+      "epoch": 0.14090520922288644,
+      "grad_norm": 0.33602604269981384,
+      "learning_rate": 4.8331487748798636e-06,
+      "loss": 0.6699,
+      "step": 110
+    },
+    {
+      "epoch": 0.14730999146029036,
+      "grad_norm": 0.3456333875656128,
+      "learning_rate": 4.814117121898554e-06,
+      "loss": 0.6265,
+      "step": 115
+    },
+    {
+      "epoch": 0.1537147736976943,
+      "grad_norm": 0.2806994915008545,
+      "learning_rate": 4.794099551914173e-06,
+      "loss": 0.6181,
+      "step": 120
+    },
+    {
+      "epoch": 0.16011955593509822,
+      "grad_norm": 0.352857381105423,
+      "learning_rate": 4.773104593303449e-06,
+      "loss": 0.6869,
+      "step": 125
+    },
+    {
+      "epoch": 0.16652433817250215,
+      "grad_norm": 0.3353271782398224,
+      "learning_rate": 4.751141190854214e-06,
+      "loss": 0.6184,
+      "step": 130
+    },
+    {
+      "epoch": 0.17292912040990607,
+      "grad_norm": 0.39950162172317505,
+      "learning_rate": 4.728218701954525e-06,
+      "loss": 0.6631,
+      "step": 135
+    },
+    {
+      "epoch": 0.17933390264731,
+      "grad_norm": 0.3852960169315338,
+      "learning_rate": 4.704346892606001e-06,
+      "loss": 0.6077,
+      "step": 140
+    },
+    {
+      "epoch": 0.18573868488471393,
+      "grad_norm": 0.3433144688606262,
+      "learning_rate": 4.6795359332630694e-06,
+      "loss": 0.6487,
+      "step": 145
+    },
+    {
+      "epoch": 0.19214346712211786,
+      "grad_norm": 0.437122106552124,
+      "learning_rate": 4.653796394499904e-06,
+      "loss": 0.6284,
+      "step": 150
+    },
+    {
+      "epoch": 0.19854824935952178,
+      "grad_norm": 0.3337637484073639,
+      "learning_rate": 4.627139242506882e-06,
+      "loss": 0.6177,
+      "step": 155
+    },
+    {
+      "epoch": 0.2049530315969257,
+      "grad_norm": 0.3271448016166687,
+      "learning_rate": 4.599575834418505e-06,
+      "loss": 0.6604,
+      "step": 160
+    },
+    {
+      "epoch": 0.21135781383432964,
+      "grad_norm": 0.4029073715209961,
+      "learning_rate": 4.571117913474749e-06,
+      "loss": 0.6151,
+      "step": 165
+    },
+    {
+      "epoch": 0.21776259607173357,
+      "grad_norm": 0.35433897376060486,
+      "learning_rate": 4.541777604017924e-06,
+      "loss": 0.5941,
+      "step": 170
+    },
+    {
+      "epoch": 0.2241673783091375,
+      "grad_norm": 0.40683719515800476,
+      "learning_rate": 4.511567406327162e-06,
+      "loss": 0.6196,
+      "step": 175
+    },
+    {
+      "epoch": 0.23057216054654142,
+      "grad_norm": 0.41791296005249023,
+      "learning_rate": 4.480500191292744e-06,
+      "loss": 0.6104,
+      "step": 180
+    },
+    {
+      "epoch": 0.23697694278394535,
+      "grad_norm": 0.3712579011917114,
+      "learning_rate": 4.448589194932521e-06,
+      "loss": 0.6091,
+      "step": 185
+    },
+    {
+      "epoch": 0.24338172502134928,
+      "grad_norm": 0.3512028157711029,
+      "learning_rate": 4.415848012752789e-06,
+      "loss": 0.5894,
+      "step": 190
+    },
+    {
+      "epoch": 0.2497865072587532,
+      "grad_norm": 0.3832685649394989,
+      "learning_rate": 4.38229059395599e-06,
+      "loss": 0.6143,
+      "step": 195
+    },
+    {
+      "epoch": 0.2561912894961571,
+      "grad_norm": 0.3921290338039398,
+      "learning_rate": 4.347931235497738e-06,
+      "loss": 0.6161,
+      "step": 200
+    },
+    {
+      "epoch": 0.26259607173356103,
+      "grad_norm": 0.40466588735580444,
+      "learning_rate": 4.312784575995669e-06,
+      "loss": 0.6008,
+      "step": 205
+    },
+    {
+      "epoch": 0.269000853970965,
+      "grad_norm": 0.9247767329216003,
+      "learning_rate": 4.276865589492747e-06,
+      "loss": 0.5971,
+      "step": 210
+    },
+    {
+      "epoch": 0.27540563620836894,
+      "grad_norm": 0.5003313422203064,
+      "learning_rate": 4.240189579077649e-06,
+      "loss": 0.5832,
+      "step": 215
+    },
+    {
+      "epoch": 0.28181041844577287,
+      "grad_norm": 0.41465386748313904,
+      "learning_rate": 4.202772170364969e-06,
+      "loss": 0.5909,
+      "step": 220
+    },
+    {
+      "epoch": 0.2882152006831768,
+      "grad_norm": 0.3520627021789551,
+      "learning_rate": 4.164629304838012e-06,
+      "loss": 0.5826,
+      "step": 225
+    },
+    {
+      "epoch": 0.2946199829205807,
+      "grad_norm": 0.38733118772506714,
+      "learning_rate": 4.125777233057007e-06,
+      "loss": 0.6092,
+      "step": 230
+    },
+    {
+      "epoch": 0.30102476515798465,
+      "grad_norm": 0.3622700870037079,
+      "learning_rate": 4.086232507735648e-06,
+      "loss": 0.5844,
+      "step": 235
+    },
+    {
+      "epoch": 0.3074295473953886,
+      "grad_norm": 0.47380566596984863,
+      "learning_rate": 4.0460119766889e-06,
+      "loss": 0.6075,
+      "step": 240
+    },
+    {
+      "epoch": 0.3138343296327925,
+      "grad_norm": 0.4540008008480072,
+      "learning_rate": 4.005132775655076e-06,
+      "loss": 0.572,
+      "step": 245
+    },
+    {
+      "epoch": 0.32023911187019644,
+      "grad_norm": 0.47770172357559204,
+      "learning_rate": 3.963612320995257e-06,
+      "loss": 0.6175,
+      "step": 250
+    },
+    {
+      "epoch": 0.32664389410760036,
+      "grad_norm": 0.3514467179775238,
+      "learning_rate": 3.921468302273137e-06,
+      "loss": 0.5618,
+      "step": 255
+    },
+    {
+      "epoch": 0.3330486763450043,
+      "grad_norm": 0.45986905694007874,
+      "learning_rate": 3.8787186747184826e-06,
+      "loss": 0.5442,
+      "step": 260
+    },
+    {
+      "epoch": 0.3394534585824082,
+      "grad_norm": 0.4583056569099426,
+      "learning_rate": 3.8353816515774115e-06,
+      "loss": 0.569,
+      "step": 265
+    },
+    {
+      "epoch": 0.34585824081981215,
+      "grad_norm": 0.3687354028224945,
+      "learning_rate": 3.79147569635273e-06,
+      "loss": 0.5555,
+      "step": 270
+    },
+    {
+      "epoch": 0.3522630230572161,
+      "grad_norm": 0.38063594698905945,
+      "learning_rate": 3.747019514937663e-06,
+      "loss": 0.6,
+      "step": 275
+    },
+    {
+      "epoch": 0.35866780529462,
+      "grad_norm": 0.430896520614624,
+      "learning_rate": 3.70203204764631e-06,
+      "loss": 0.5843,
+      "step": 280
+    },
+    {
+      "epoch": 0.36507258753202393,
+      "grad_norm": 0.5169083476066589,
+      "learning_rate": 3.6565324611442234e-06,
+      "loss": 0.5914,
+      "step": 285
+    },
+    {
+      "epoch": 0.37147736976942786,
+      "grad_norm": 0.36347025632858276,
+      "learning_rate": 3.6105401402825595e-06,
+      "loss": 0.5674,
+      "step": 290
+    },
+    {
+      "epoch": 0.3778821520068318,
+      "grad_norm": 0.3636574447154999,
+      "learning_rate": 3.5640746798392657e-06,
+      "loss": 0.6123,
+      "step": 295
+    },
+    {
+      "epoch": 0.3842869342442357,
+      "grad_norm": 0.4619109332561493,
+      "learning_rate": 3.5171558761708334e-06,
+      "loss": 0.5708,
+      "step": 300
+    },
+    {
+      "epoch": 0.39069171648163964,
+      "grad_norm": 0.447704553604126,
+      "learning_rate": 3.469803718778166e-06,
+      "loss": 0.5722,
+      "step": 305
+    },
+    {
+      "epoch": 0.39709649871904357,
+      "grad_norm": 0.39746832847595215,
+      "learning_rate": 3.4220383817901625e-06,
+      "loss": 0.5772,
+      "step": 310
+    },
+    {
+      "epoch": 0.4035012809564475,
+      "grad_norm": 0.4326777160167694,
+      "learning_rate": 3.3738802153686414e-06,
+      "loss": 0.5715,
+      "step": 315
+    },
+    {
+      "epoch": 0.4099060631938514,
+      "grad_norm": 0.4147851765155792,
+      "learning_rate": 3.3253497370382605e-06,
+      "loss": 0.572,
+      "step": 320
+    },
+    {
+      "epoch": 0.41631084543125535,
+      "grad_norm": 0.43767350912094116,
+      "learning_rate": 3.2764676229451397e-06,
+      "loss": 0.563,
+      "step": 325
+    },
+    {
+      "epoch": 0.4227156276686593,
+      "grad_norm": 0.36241263151168823,
+      "learning_rate": 3.227254699047904e-06,
+      "loss": 0.5649,
+      "step": 330
+    },
+    {
+      "epoch": 0.4291204099060632,
+      "grad_norm": 0.5232857465744019,
+      "learning_rate": 3.177731932244892e-06,
+      "loss": 0.5645,
+      "step": 335
+    },
+    {
+      "epoch": 0.43552519214346713,
+      "grad_norm": 0.4475226104259491,
+      "learning_rate": 3.127920421441327e-06,
+      "loss": 0.5767,
+      "step": 340
+    },
+    {
+      "epoch": 0.44192997438087106,
+      "grad_norm": 0.4484921991825104,
+      "learning_rate": 3.077841388560243e-06,
+      "loss": 0.591,
+      "step": 345
+    },
+    {
+      "epoch": 0.448334756618275,
+      "grad_norm": 0.5250320434570312,
+      "learning_rate": 3.0275161695009975e-06,
+      "loss": 0.5814,
+      "step": 350
+    },
+    {
+      "epoch": 0.4547395388556789,
+      "grad_norm": 0.47690996527671814,
+      "learning_rate": 2.9769662050492276e-06,
+      "loss": 0.5602,
+      "step": 355
+    },
+    {
+      "epoch": 0.46114432109308284,
+      "grad_norm": 0.4651663899421692,
+      "learning_rate": 2.926213031742125e-06,
+      "loss": 0.5741,
+      "step": 360
+    },
+    {
+      "epoch": 0.46754910333048677,
+      "grad_norm": 0.46296215057373047,
+      "learning_rate": 2.8752782726929045e-06,
+      "loss": 0.5614,
+      "step": 365
+    },
+    {
+      "epoch": 0.4739538855678907,
+      "grad_norm": 0.5162904262542725,
+      "learning_rate": 2.8241836283784026e-06,
+      "loss": 0.5483,
+      "step": 370
+    },
+    {
+      "epoch": 0.4803586678052946,
+      "grad_norm": 0.3958864212036133,
+      "learning_rate": 2.7729508673936972e-06,
+      "loss": 0.5745,
+      "step": 375
+    },
+    {
+      "epoch": 0.48676345004269855,
+      "grad_norm": 0.4186757504940033,
+      "learning_rate": 2.721601817177725e-06,
+      "loss": 0.5459,
+      "step": 380
+    },
+    {
+      "epoch": 0.4931682322801025,
+      "grad_norm": 0.4372413456439972,
+      "learning_rate": 2.6701583547138165e-06,
+      "loss": 0.5852,
+      "step": 385
+    },
+    {
+      "epoch": 0.4995730145175064,
+      "grad_norm": 0.4488023519515991,
+      "learning_rate": 2.618642397209126e-06,
+      "loss": 0.5427,
+      "step": 390
+    },
+    {
+      "epoch": 0.5059777967549103,
+      "grad_norm": 0.4278182089328766,
+      "learning_rate": 2.567075892756924e-06,
+      "loss": 0.5586,
+      "step": 395
+    },
+    {
+      "epoch": 0.5123825789923142,
+      "grad_norm": 0.48016875982284546,
+      "learning_rate": 2.5154808109857367e-06,
+      "loss": 0.5405,
+      "step": 400
+    },
+    {
+      "epoch": 0.5187873612297181,
+      "grad_norm": 0.5077680945396423,
+      "learning_rate": 2.4638791336992967e-06,
+      "loss": 0.5682,
+      "step": 405
+    },
+    {
+      "epoch": 0.5251921434671221,
+      "grad_norm": 0.5091099739074707,
+      "learning_rate": 2.4122928455113233e-06,
+      "loss": 0.5619,
+      "step": 410
+    },
+    {
+      "epoch": 0.531596925704526,
+      "grad_norm": 0.4333205223083496,
+      "learning_rate": 2.360743924479093e-06,
+      "loss": 0.5879,
+      "step": 415
+    },
+    {
+      "epoch": 0.53800170794193,
+      "grad_norm": 0.4178122282028198,
+      "learning_rate": 2.3092543327398083e-06,
+      "loss": 0.5332,
+      "step": 420
+    },
+    {
+      "epoch": 0.544406490179334,
+      "grad_norm": 0.4080513119697571,
+      "learning_rate": 2.2578460071537512e-06,
+      "loss": 0.5728,
+      "step": 425
+    },
+    {
+      "epoch": 0.5508112724167379,
+      "grad_norm": 0.48982349038124084,
+      "learning_rate": 2.2065408499582e-06,
+      "loss": 0.575,
+      "step": 430
+    },
+    {
+      "epoch": 0.5572160546541418,
+      "grad_norm": 0.4953416883945465,
+      "learning_rate": 2.155360719436102e-06,
+      "loss": 0.5404,
+      "step": 435
+    },
+    {
+      "epoch": 0.5636208368915457,
+      "grad_norm": 0.4608188271522522,
+      "learning_rate": 2.1043274206034727e-06,
+      "loss": 0.5579,
+      "step": 440
+    },
+    {
+      "epoch": 0.5700256191289497,
+      "grad_norm": 0.48403236269950867,
+      "learning_rate": 2.0534626959194816e-06,
+      "loss": 0.5383,
+      "step": 445
+    },
+    {
+      "epoch": 0.5764304013663536,
+      "grad_norm": 0.4532581865787506,
+      "learning_rate": 2.002788216023203e-06,
+      "loss": 0.5638,
+      "step": 450
+    },
+    {
+      "epoch": 0.5828351836037575,
+      "grad_norm": 0.53521728515625,
+      "learning_rate": 1.9523255705009558e-06,
+      "loss": 0.5549,
+      "step": 455
+    },
+    {
+      "epoch": 0.5892399658411615,
+      "grad_norm": 0.4711097180843353,
+      "learning_rate": 1.902096258688174e-06,
+      "loss": 0.5027,
+      "step": 460
+    },
+    {
+      "epoch": 0.5956447480785654,
+      "grad_norm": 0.43662044405937195,
+      "learning_rate": 1.8521216805097358e-06,
+      "loss": 0.556,
+      "step": 465
+    },
+    {
+      "epoch": 0.6020495303159693,
+      "grad_norm": 0.3957918882369995,
+      "learning_rate": 1.8024231273626424e-06,
+      "loss": 0.5596,
+      "step": 470
+    },
+    {
+      "epoch": 0.6084543125533732,
+      "grad_norm": 0.5218236446380615,
+      "learning_rate": 1.7530217730449312e-06,
+      "loss": 0.5405,
+      "step": 475
+    },
+    {
+      "epoch": 0.6148590947907772,
+      "grad_norm": 0.4223135709762573,
+      "learning_rate": 1.7039386647346975e-06,
+      "loss": 0.5279,
+      "step": 480
+    },
+    {
+      "epoch": 0.6212638770281811,
+      "grad_norm": 0.3835909068584442,
+      "learning_rate": 1.6551947140230568e-06,
+      "loss": 0.5747,
+      "step": 485
+    },
+    {
+      "epoch": 0.627668659265585,
+      "grad_norm": 0.5082884430885315,
+      "learning_rate": 1.6068106880048747e-06,
+      "loss": 0.5518,
+      "step": 490
+    },
+    {
+      "epoch": 0.6340734415029889,
+      "grad_norm": 0.4860563278198242,
+      "learning_rate": 1.5588072004310634e-06,
+      "loss": 0.5641,
+      "step": 495
+    },
+    {
+      "epoch": 0.6404782237403929,
+      "grad_norm": 0.4176677167415619,
+      "learning_rate": 1.5112047029262e-06,
+      "loss": 0.5547,
+      "step": 500
+    },
+    {
+      "epoch": 0.6468830059777968,
+      "grad_norm": 0.3659776747226715,
+      "learning_rate": 1.4640234762752248e-06,
+      "loss": 0.5503,
+      "step": 505
+    },
+    {
+      "epoch": 0.6532877882152007,
+      "grad_norm": 0.4908987283706665,
+      "learning_rate": 1.4172836217829267e-06,
+      "loss": 0.5549,
+      "step": 510
+    },
+    {
+      "epoch": 0.6596925704526047,
+      "grad_norm": 0.44962796568870544,
+      "learning_rate": 1.3710050527098867e-06,
+      "loss": 0.573,
+      "step": 515
+    },
+    {
+      "epoch": 0.6660973526900086,
+      "grad_norm": 0.4549601376056671,
+      "learning_rate": 1.3252074857885453e-06,
+      "loss": 0.5666,
+      "step": 520
+    },
+    {
+      "epoch": 0.6725021349274125,
+      "grad_norm": 0.48955774307250977,
+      "learning_rate": 1.2799104328229928e-06,
+      "loss": 0.5379,
+      "step": 525
+    },
+    {
+      "epoch": 0.6789069171648164,
+      "grad_norm": 0.45902734994888306,
+      "learning_rate": 1.2351331923760743e-06,
+      "loss": 0.5345,
+      "step": 530
+    },
+    {
+      "epoch": 0.6853116994022204,
+      "grad_norm": 0.49846968054771423,
+      "learning_rate": 1.1908948415473418e-06,
+      "loss": 0.5367,
+      "step": 535
+    },
+    {
+      "epoch": 0.6917164816396243,
+      "grad_norm": 0.48370206356048584,
+      "learning_rate": 1.1472142278453582e-06,
+      "loss": 0.5325,
+      "step": 540
+    },
+    {
+      "epoch": 0.6981212638770282,
+      "grad_norm": 0.3830443024635315,
+      "learning_rate": 1.1041099611578177e-06,
+      "loss": 0.5585,
+      "step": 545
+    },
+    {
+      "epoch": 0.7045260461144321,
+      "grad_norm": 0.47550487518310547,
+      "learning_rate": 1.0616004058229084e-06,
+      "loss": 0.5417,
+      "step": 550
+    },
+    {
+      "epoch": 0.7109308283518361,
+      "grad_norm": 0.46026965975761414,
+      "learning_rate": 1.0197036728052847e-06,
+      "loss": 0.5715,
+      "step": 555
+    },
+    {
+      "epoch": 0.71733561058924,
+      "grad_norm": 0.42247724533081055,
+      "learning_rate": 9.784376119799851e-07,
+      "loss": 0.5459,
+      "step": 560
+    },
+    {
+      "epoch": 0.7237403928266439,
+      "grad_norm": 0.5001282095909119,
+      "learning_rate": 9.378198045275968e-07,
+      "loss": 0.5557,
+      "step": 565
+    },
+    {
+      "epoch": 0.7301451750640479,
+      "grad_norm": 0.4762704372406006,
+      "learning_rate": 8.97867555443886e-07,
+      "loss": 0.5338,
+      "step": 570
+    },
+    {
+      "epoch": 0.7365499573014518,
+      "grad_norm": 0.48811063170433044,
+      "learning_rate": 8.585978861670958e-07,
+      "loss": 0.5331,
+      "step": 575
+    },
+    {
+      "epoch": 0.7429547395388557,
+      "grad_norm": 0.45258718729019165,
+      "learning_rate": 8.200275273260611e-07,
+      "loss": 0.5461,
+      "step": 580
+    },
+    {
+      "epoch": 0.7493595217762596,
+      "grad_norm": 0.4314691424369812,
+      "learning_rate": 7.821729116122126e-07,
+      "loss": 0.558,
+      "step": 585
+    },
+    {
+      "epoch": 0.7557643040136636,
+      "grad_norm": 0.4526233673095703,
+      "learning_rate": 7.450501667785146e-07,
+      "loss": 0.5455,
+      "step": 590
+    },
+    {
+      "epoch": 0.7621690862510675,
+      "grad_norm": 0.4625132977962494,
+      "learning_rate": 7.086751087683297e-07,
+      "loss": 0.5514,
+      "step": 595
+    },
+    {
+      "epoch": 0.7685738684884714,
+      "grad_norm": 0.4986107349395752,
+      "learning_rate": 6.730632349771193e-07,
+      "loss": 0.5566,
+      "step": 600
+    },
+    {
+      "epoch": 0.7749786507258754,
+      "grad_norm": 0.5132951140403748,
+      "learning_rate": 6.3822971764986e-07,
+      "loss": 0.5363,
+      "step": 605
+    },
+    {
+      "epoch": 0.7813834329632793,
+      "grad_norm": 0.48895248770713806,
+      "learning_rate": 6.041893974169963e-07,
+      "loss": 0.5382,
+      "step": 610
+    },
+    {
+      "epoch": 0.7877882152006832,
+      "grad_norm": 0.48889264464378357,
+      "learning_rate": 5.709567769716678e-07,
+      "loss": 0.5511,
+      "step": 615
+    },
+    {
+      "epoch": 0.7941929974380871,
+      "grad_norm": 0.4542140066623688,
+      "learning_rate": 5.385460148909169e-07,
+      "loss": 0.5227,
+      "step": 620
+    },
+    {
+      "epoch": 0.8005977796754911,
+      "grad_norm": 0.48940637707710266,
+      "learning_rate": 5.069709196035011e-07,
+      "loss": 0.5519,
+      "step": 625
+    },
+    {
+      "epoch": 0.807002561912895,
+      "grad_norm": 0.45722976326942444,
+      "learning_rate": 4.762449435068914e-07,
+      "loss": 0.5358,
+      "step": 630
+    },
+    {
+      "epoch": 0.8134073441502989,
+      "grad_norm": 0.5042068958282471,
+      "learning_rate": 4.4638117723595054e-07,
+      "loss": 0.5686,
+      "step": 635
+    },
+    {
+      "epoch": 0.8198121263877028,
+      "grad_norm": 0.4974375069141388,
+      "learning_rate": 4.173923440857358e-07,
+      "loss": 0.5528,
+      "step": 640
+    },
+    {
+      "epoch": 0.8262169086251068,
+      "grad_norm": 0.4234403669834137,
+      "learning_rate": 3.892907945908128e-07,
+      "loss": 0.5305,
+      "step": 645
+    },
+    {
+      "epoch": 0.8326216908625107,
+      "grad_norm": 0.5144878029823303,
+      "learning_rate": 3.6208850126337595e-07,
+      "loss": 0.5282,
+      "step": 650
+    },
+    {
+      "epoch": 0.8390264730999146,
+      "grad_norm": 0.41059333086013794,
+      "learning_rate": 3.357970534924229e-07,
+      "loss": 0.5601,
+      "step": 655
+    },
+    {
+      "epoch": 0.8454312553373186,
+      "grad_norm": 0.40885528922080994,
+      "learning_rate": 3.104276526061617e-07,
+      "loss": 0.536,
+      "step": 660
+    },
+    {
+      "epoch": 0.8518360375747225,
+      "grad_norm": 0.462971568107605,
+      "learning_rate": 2.859911070997437e-07,
+      "loss": 0.5513,
+      "step": 665
+    },
+    {
+      "epoch": 0.8582408198121264,
+      "grad_norm": 0.6165898442268372,
+      "learning_rate": 2.624978280303628e-07,
+      "loss": 0.5542,
+      "step": 670
+    },
+    {
+      "epoch": 0.8646456020495303,
+      "grad_norm": 0.514519453048706,
+      "learning_rate": 2.3995782458168276e-07,
+      "loss": 0.5572,
+      "step": 675
+    },
+    {
+      "epoch": 0.8710503842869343,
+      "grad_norm": 0.5139626264572144,
+      "learning_rate": 2.1838069979947945e-07,
+      "loss": 0.5372,
+      "step": 680
+    },
+    {
+      "epoch": 0.8774551665243382,
+      "grad_norm": 1.6515536308288574,
+      "learning_rate": 1.9777564650031112e-07,
+      "loss": 0.5515,
+      "step": 685
+    },
+    {
+      "epoch": 0.8838599487617421,
+      "grad_norm": 0.4731055200099945,
+      "learning_rate": 1.7815144335497524e-07,
+      "loss": 0.5515,
+      "step": 690
+    },
+    {
+      "epoch": 0.890264730999146,
+      "grad_norm": 0.5183550715446472,
+      "learning_rate": 1.5951645114839875e-07,
+      "loss": 0.5419,
+      "step": 695
+    },
+    {
+      "epoch": 0.89666951323655,
+      "grad_norm": 0.5357317328453064,
+      "learning_rate": 1.4187860921757252e-07,
+      "loss": 0.5571,
+      "step": 700
+    },
+    {
+      "epoch": 0.9030742954739539,
+      "grad_norm": 0.5177751779556274,
+      "learning_rate": 1.2524543206904188e-07,
+      "loss": 0.5607,
+      "step": 705
+    },
+    {
+      "epoch": 0.9094790777113578,
+      "grad_norm": 0.4790054261684418,
+      "learning_rate": 1.0962400617738872e-07,
+      "loss": 0.581,
+      "step": 710
+    },
+    {
+      "epoch": 0.9158838599487618,
+      "grad_norm": 0.5255675911903381,
+      "learning_rate": 9.502098696608147e-08,
+      "loss": 0.5449,
+      "step": 715
+    },
+    {
+      "epoch": 0.9222886421861657,
+      "grad_norm": 0.38730135560035706,
+      "learning_rate": 8.144259597196308e-08,
+      "loss": 0.5518,
+      "step": 720
+    },
+    {
+      "epoch": 0.9286934244235696,
+      "grad_norm": 0.42933622002601624,
+      "learning_rate": 6.889461819460485e-08,
+      "loss": 0.5365,
+      "step": 725
+    },
+    {
+      "epoch": 0.9350982066609735,
+      "grad_norm": 0.50970458984375,
+      "learning_rate": 5.738239963163472e-08,
+      "loss": 0.5282,
+      "step": 730
+    },
+    {
+      "epoch": 0.9415029888983775,
+      "grad_norm": 0.5318973064422607,
+      "learning_rate": 4.691084500110521e-08,
+      "loss": 0.5281,
+      "step": 735
+    },
+    {
+      "epoch": 0.9479077711357814,
+      "grad_norm": 0.4877215623855591,
+      "learning_rate": 3.748441565186583e-08,
+      "loss": 0.5136,
+      "step": 740
+    },
+    {
+      "epoch": 0.9543125533731853,
+      "grad_norm": 0.5620718002319336,
+      "learning_rate": 2.910712766282908e-08,
+      "loss": 0.5385,
+      "step": 745
+    },
+    {
+      "epoch": 0.9607173356105893,
+      "grad_norm": 0.5282920598983765,
+      "learning_rate": 2.178255013194075e-08,
+      "loss": 0.5296,
+      "step": 750
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 781,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.69266304597033e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-750/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e589d07524a7c0f0a1d12d5318498811c749686a723a601fe53896da63fc46f5
+size 6417

checkpoint-781/README.md

@@ -0,0 +1,209 @@
+---
+base_model: unsloth/Qwen3-4B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-4B
+- llama-factory
+- lora
+- transformers
+- unsloth
+---
+
+# 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 0.17.1

checkpoint-781/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-4B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-781/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d58bb27f819c825e6d940b4a9d2dba32fd3cb9335b22c235e291eb82117df5e2
+size 528550256

checkpoint-781/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-781/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-781/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:866b9299c595feea2a3a7e22230fc383b71e61556266596ecb04f42d8a0291f1
+size 1057390923

checkpoint-781/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

checkpoint-781/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:554b1b2de4d1cd2760e748878b010c59cfc2ea5e177b197c9e6e1a6e7b08bd6d
+size 1465

checkpoint-781/special_tokens_map.json

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

checkpoint-781/tokenizer.json

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

checkpoint-781/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-781/trainer_state.json

@@ -0,0 +1,1126 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 25,
+  "global_step": 781,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0064047822374039285,
+      "grad_norm": 5.6078200340271,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.1562,
+      "step": 5
+    },
+    {
+      "epoch": 0.012809564474807857,
+      "grad_norm": 5.326383590698242,
+      "learning_rate": 2.25e-06,
+      "loss": 1.0619,
+      "step": 10
+    },
+    {
+      "epoch": 0.019214346712211786,
+      "grad_norm": 2.7833762168884277,
+      "learning_rate": 3.5e-06,
+      "loss": 1.0511,
+      "step": 15
+    },
+    {
+      "epoch": 0.025619128949615714,
+      "grad_norm": 1.1198874711990356,
+      "learning_rate": 4.75e-06,
+      "loss": 0.931,
+      "step": 20
+    },
+    {
+      "epoch": 0.03202391118701964,
+      "grad_norm": 1.2183799743652344,
+      "learning_rate": 4.999659159998194e-06,
+      "loss": 0.8819,
+      "step": 25
+    },
+    {
+      "epoch": 0.03842869342442357,
+      "grad_norm": 0.7168175578117371,
+      "learning_rate": 4.998274656771894e-06,
+      "loss": 0.845,
+      "step": 30
+    },
+    {
+      "epoch": 0.0448334756618275,
+      "grad_norm": 0.5571187734603882,
+      "learning_rate": 4.995825777227236e-06,
+      "loss": 0.7982,
+      "step": 35
+    },
+    {
+      "epoch": 0.05123825789923143,
+      "grad_norm": 0.5454768538475037,
+      "learning_rate": 4.992313564696022e-06,
+      "loss": 0.7583,
+      "step": 40
+    },
+    {
+      "epoch": 0.057643040136635355,
+      "grad_norm": 0.4312361776828766,
+      "learning_rate": 4.9877395155372815e-06,
+      "loss": 0.7783,
+      "step": 45
+    },
+    {
+      "epoch": 0.06404782237403928,
+      "grad_norm": 0.34762468934059143,
+      "learning_rate": 4.982105578499759e-06,
+      "loss": 0.7645,
+      "step": 50
+    },
+    {
+      "epoch": 0.07045260461144322,
+      "grad_norm": 0.34647414088249207,
+      "learning_rate": 4.975414153891664e-06,
+      "loss": 0.7397,
+      "step": 55
+    },
+    {
+      "epoch": 0.07685738684884715,
+      "grad_norm": 0.33078256249427795,
+      "learning_rate": 4.967668092558024e-06,
+      "loss": 0.7325,
+      "step": 60
+    },
+    {
+      "epoch": 0.08326216908625107,
+      "grad_norm": 0.3410351872444153,
+      "learning_rate": 4.9588706946661066e-06,
+      "loss": 0.7037,
+      "step": 65
+    },
+    {
+      "epoch": 0.089666951323655,
+      "grad_norm": 0.3349353075027466,
+      "learning_rate": 4.949025708299395e-06,
+      "loss": 0.6928,
+      "step": 70
+    },
+    {
+      "epoch": 0.09607173356105893,
+      "grad_norm": 0.32335689663887024,
+      "learning_rate": 4.93813732786074e-06,
+      "loss": 0.6764,
+      "step": 75
+    },
+    {
+      "epoch": 0.10247651579846286,
+      "grad_norm": 0.33923929929733276,
+      "learning_rate": 4.926210192285359e-06,
+      "loss": 0.7398,
+      "step": 80
+    },
+    {
+      "epoch": 0.10888129803586678,
+      "grad_norm": 0.32697415351867676,
+      "learning_rate": 4.913249383064438e-06,
+      "loss": 0.6927,
+      "step": 85
+    },
+    {
+      "epoch": 0.11528608027327071,
+      "grad_norm": 0.34032362699508667,
+      "learning_rate": 4.899260422080195e-06,
+      "loss": 0.6909,
+      "step": 90
+    },
+    {
+      "epoch": 0.12169086251067464,
+      "grad_norm": 0.3949951231479645,
+      "learning_rate": 4.884249269253309e-06,
+      "loss": 0.6517,
+      "step": 95
+    },
+    {
+      "epoch": 0.12809564474807855,
+      "grad_norm": 0.40848004817962646,
+      "learning_rate": 4.868222320003731e-06,
+      "loss": 0.6625,
+      "step": 100
+    },
+    {
+      "epoch": 0.1345004269854825,
+      "grad_norm": 0.36571186780929565,
+      "learning_rate": 4.851186402525946e-06,
+      "loss": 0.6693,
+      "step": 105
+    },
+    {
+      "epoch": 0.14090520922288644,
+      "grad_norm": 0.33602604269981384,
+      "learning_rate": 4.8331487748798636e-06,
+      "loss": 0.6699,
+      "step": 110
+    },
+    {
+      "epoch": 0.14730999146029036,
+      "grad_norm": 0.3456333875656128,
+      "learning_rate": 4.814117121898554e-06,
+      "loss": 0.6265,
+      "step": 115
+    },
+    {
+      "epoch": 0.1537147736976943,
+      "grad_norm": 0.2806994915008545,
+      "learning_rate": 4.794099551914173e-06,
+      "loss": 0.6181,
+      "step": 120
+    },
+    {
+      "epoch": 0.16011955593509822,
+      "grad_norm": 0.352857381105423,
+      "learning_rate": 4.773104593303449e-06,
+      "loss": 0.6869,
+      "step": 125
+    },
+    {
+      "epoch": 0.16652433817250215,
+      "grad_norm": 0.3353271782398224,
+      "learning_rate": 4.751141190854214e-06,
+      "loss": 0.6184,
+      "step": 130
+    },
+    {
+      "epoch": 0.17292912040990607,
+      "grad_norm": 0.39950162172317505,
+      "learning_rate": 4.728218701954525e-06,
+      "loss": 0.6631,
+      "step": 135
+    },
+    {
+      "epoch": 0.17933390264731,
+      "grad_norm": 0.3852960169315338,
+      "learning_rate": 4.704346892606001e-06,
+      "loss": 0.6077,
+      "step": 140
+    },
+    {
+      "epoch": 0.18573868488471393,
+      "grad_norm": 0.3433144688606262,
+      "learning_rate": 4.6795359332630694e-06,
+      "loss": 0.6487,
+      "step": 145
+    },
+    {
+      "epoch": 0.19214346712211786,
+      "grad_norm": 0.437122106552124,
+      "learning_rate": 4.653796394499904e-06,
+      "loss": 0.6284,
+      "step": 150
+    },
+    {
+      "epoch": 0.19854824935952178,
+      "grad_norm": 0.3337637484073639,
+      "learning_rate": 4.627139242506882e-06,
+      "loss": 0.6177,
+      "step": 155
+    },
+    {
+      "epoch": 0.2049530315969257,
+      "grad_norm": 0.3271448016166687,
+      "learning_rate": 4.599575834418505e-06,
+      "loss": 0.6604,
+      "step": 160
+    },
+    {
+      "epoch": 0.21135781383432964,
+      "grad_norm": 0.4029073715209961,
+      "learning_rate": 4.571117913474749e-06,
+      "loss": 0.6151,
+      "step": 165
+    },
+    {
+      "epoch": 0.21776259607173357,
+      "grad_norm": 0.35433897376060486,
+      "learning_rate": 4.541777604017924e-06,
+      "loss": 0.5941,
+      "step": 170
+    },
+    {
+      "epoch": 0.2241673783091375,
+      "grad_norm": 0.40683719515800476,
+      "learning_rate": 4.511567406327162e-06,
+      "loss": 0.6196,
+      "step": 175
+    },
+    {
+      "epoch": 0.23057216054654142,
+      "grad_norm": 0.41791296005249023,
+      "learning_rate": 4.480500191292744e-06,
+      "loss": 0.6104,
+      "step": 180
+    },
+    {
+      "epoch": 0.23697694278394535,
+      "grad_norm": 0.3712579011917114,
+      "learning_rate": 4.448589194932521e-06,
+      "loss": 0.6091,
+      "step": 185
+    },
+    {
+      "epoch": 0.24338172502134928,
+      "grad_norm": 0.3512028157711029,
+      "learning_rate": 4.415848012752789e-06,
+      "loss": 0.5894,
+      "step": 190
+    },
+    {
+      "epoch": 0.2497865072587532,
+      "grad_norm": 0.3832685649394989,
+      "learning_rate": 4.38229059395599e-06,
+      "loss": 0.6143,
+      "step": 195
+    },
+    {
+      "epoch": 0.2561912894961571,
+      "grad_norm": 0.3921290338039398,
+      "learning_rate": 4.347931235497738e-06,
+      "loss": 0.6161,
+      "step": 200
+    },
+    {
+      "epoch": 0.26259607173356103,
+      "grad_norm": 0.40466588735580444,
+      "learning_rate": 4.312784575995669e-06,
+      "loss": 0.6008,
+      "step": 205
+    },
+    {
+      "epoch": 0.269000853970965,
+      "grad_norm": 0.9247767329216003,
+      "learning_rate": 4.276865589492747e-06,
+      "loss": 0.5971,
+      "step": 210
+    },
+    {
+      "epoch": 0.27540563620836894,
+      "grad_norm": 0.5003313422203064,
+      "learning_rate": 4.240189579077649e-06,
+      "loss": 0.5832,
+      "step": 215
+    },
+    {
+      "epoch": 0.28181041844577287,
+      "grad_norm": 0.41465386748313904,
+      "learning_rate": 4.202772170364969e-06,
+      "loss": 0.5909,
+      "step": 220
+    },
+    {
+      "epoch": 0.2882152006831768,
+      "grad_norm": 0.3520627021789551,
+      "learning_rate": 4.164629304838012e-06,
+      "loss": 0.5826,
+      "step": 225
+    },
+    {
+      "epoch": 0.2946199829205807,
+      "grad_norm": 0.38733118772506714,
+      "learning_rate": 4.125777233057007e-06,
+      "loss": 0.6092,
+      "step": 230
+    },
+    {
+      "epoch": 0.30102476515798465,
+      "grad_norm": 0.3622700870037079,
+      "learning_rate": 4.086232507735648e-06,
+      "loss": 0.5844,
+      "step": 235
+    },
+    {
+      "epoch": 0.3074295473953886,
+      "grad_norm": 0.47380566596984863,
+      "learning_rate": 4.0460119766889e-06,
+      "loss": 0.6075,
+      "step": 240
+    },
+    {
+      "epoch": 0.3138343296327925,
+      "grad_norm": 0.4540008008480072,
+      "learning_rate": 4.005132775655076e-06,
+      "loss": 0.572,
+      "step": 245
+    },
+    {
+      "epoch": 0.32023911187019644,
+      "grad_norm": 0.47770172357559204,
+      "learning_rate": 3.963612320995257e-06,
+      "loss": 0.6175,
+      "step": 250
+    },
+    {
+      "epoch": 0.32664389410760036,
+      "grad_norm": 0.3514467179775238,
+      "learning_rate": 3.921468302273137e-06,
+      "loss": 0.5618,
+      "step": 255
+    },
+    {
+      "epoch": 0.3330486763450043,
+      "grad_norm": 0.45986905694007874,
+      "learning_rate": 3.8787186747184826e-06,
+      "loss": 0.5442,
+      "step": 260
+    },
+    {
+      "epoch": 0.3394534585824082,
+      "grad_norm": 0.4583056569099426,
+      "learning_rate": 3.8353816515774115e-06,
+      "loss": 0.569,
+      "step": 265
+    },
+    {
+      "epoch": 0.34585824081981215,
+      "grad_norm": 0.3687354028224945,
+      "learning_rate": 3.79147569635273e-06,
+      "loss": 0.5555,
+      "step": 270
+    },
+    {
+      "epoch": 0.3522630230572161,
+      "grad_norm": 0.38063594698905945,
+      "learning_rate": 3.747019514937663e-06,
+      "loss": 0.6,
+      "step": 275
+    },
+    {
+      "epoch": 0.35866780529462,
+      "grad_norm": 0.430896520614624,
+      "learning_rate": 3.70203204764631e-06,
+      "loss": 0.5843,
+      "step": 280
+    },
+    {
+      "epoch": 0.36507258753202393,
+      "grad_norm": 0.5169083476066589,
+      "learning_rate": 3.6565324611442234e-06,
+      "loss": 0.5914,
+      "step": 285
+    },
+    {
+      "epoch": 0.37147736976942786,
+      "grad_norm": 0.36347025632858276,
+      "learning_rate": 3.6105401402825595e-06,
+      "loss": 0.5674,
+      "step": 290
+    },
+    {
+      "epoch": 0.3778821520068318,
+      "grad_norm": 0.3636574447154999,
+      "learning_rate": 3.5640746798392657e-06,
+      "loss": 0.6123,
+      "step": 295
+    },
+    {
+      "epoch": 0.3842869342442357,
+      "grad_norm": 0.4619109332561493,
+      "learning_rate": 3.5171558761708334e-06,
+      "loss": 0.5708,
+      "step": 300
+    },
+    {
+      "epoch": 0.39069171648163964,
+      "grad_norm": 0.447704553604126,
+      "learning_rate": 3.469803718778166e-06,
+      "loss": 0.5722,
+      "step": 305
+    },
+    {
+      "epoch": 0.39709649871904357,
+      "grad_norm": 0.39746832847595215,
+      "learning_rate": 3.4220383817901625e-06,
+      "loss": 0.5772,
+      "step": 310
+    },
+    {
+      "epoch": 0.4035012809564475,
+      "grad_norm": 0.4326777160167694,
+      "learning_rate": 3.3738802153686414e-06,
+      "loss": 0.5715,
+      "step": 315
+    },
+    {
+      "epoch": 0.4099060631938514,
+      "grad_norm": 0.4147851765155792,
+      "learning_rate": 3.3253497370382605e-06,
+      "loss": 0.572,
+      "step": 320
+    },
+    {
+      "epoch": 0.41631084543125535,
+      "grad_norm": 0.43767350912094116,
+      "learning_rate": 3.2764676229451397e-06,
+      "loss": 0.563,
+      "step": 325
+    },
+    {
+      "epoch": 0.4227156276686593,
+      "grad_norm": 0.36241263151168823,
+      "learning_rate": 3.227254699047904e-06,
+      "loss": 0.5649,
+      "step": 330
+    },
+    {
+      "epoch": 0.4291204099060632,
+      "grad_norm": 0.5232857465744019,
+      "learning_rate": 3.177731932244892e-06,
+      "loss": 0.5645,
+      "step": 335
+    },
+    {
+      "epoch": 0.43552519214346713,
+      "grad_norm": 0.4475226104259491,
+      "learning_rate": 3.127920421441327e-06,
+      "loss": 0.5767,
+      "step": 340
+    },
+    {
+      "epoch": 0.44192997438087106,
+      "grad_norm": 0.4484921991825104,
+      "learning_rate": 3.077841388560243e-06,
+      "loss": 0.591,
+      "step": 345
+    },
+    {
+      "epoch": 0.448334756618275,
+      "grad_norm": 0.5250320434570312,
+      "learning_rate": 3.0275161695009975e-06,
+      "loss": 0.5814,
+      "step": 350
+    },
+    {
+      "epoch": 0.4547395388556789,
+      "grad_norm": 0.47690996527671814,
+      "learning_rate": 2.9769662050492276e-06,
+      "loss": 0.5602,
+      "step": 355
+    },
+    {
+      "epoch": 0.46114432109308284,
+      "grad_norm": 0.4651663899421692,
+      "learning_rate": 2.926213031742125e-06,
+      "loss": 0.5741,
+      "step": 360
+    },
+    {
+      "epoch": 0.46754910333048677,
+      "grad_norm": 0.46296215057373047,
+      "learning_rate": 2.8752782726929045e-06,
+      "loss": 0.5614,
+      "step": 365
+    },
+    {
+      "epoch": 0.4739538855678907,
+      "grad_norm": 0.5162904262542725,
+      "learning_rate": 2.8241836283784026e-06,
+      "loss": 0.5483,
+      "step": 370
+    },
+    {
+      "epoch": 0.4803586678052946,
+      "grad_norm": 0.3958864212036133,
+      "learning_rate": 2.7729508673936972e-06,
+      "loss": 0.5745,
+      "step": 375
+    },
+    {
+      "epoch": 0.48676345004269855,
+      "grad_norm": 0.4186757504940033,
+      "learning_rate": 2.721601817177725e-06,
+      "loss": 0.5459,
+      "step": 380
+    },
+    {
+      "epoch": 0.4931682322801025,
+      "grad_norm": 0.4372413456439972,
+      "learning_rate": 2.6701583547138165e-06,
+      "loss": 0.5852,
+      "step": 385
+    },
+    {
+      "epoch": 0.4995730145175064,
+      "grad_norm": 0.4488023519515991,
+      "learning_rate": 2.618642397209126e-06,
+      "loss": 0.5427,
+      "step": 390
+    },
+    {
+      "epoch": 0.5059777967549103,
+      "grad_norm": 0.4278182089328766,
+      "learning_rate": 2.567075892756924e-06,
+      "loss": 0.5586,
+      "step": 395
+    },
+    {
+      "epoch": 0.5123825789923142,
+      "grad_norm": 0.48016875982284546,
+      "learning_rate": 2.5154808109857367e-06,
+      "loss": 0.5405,
+      "step": 400
+    },
+    {
+      "epoch": 0.5187873612297181,
+      "grad_norm": 0.5077680945396423,
+      "learning_rate": 2.4638791336992967e-06,
+      "loss": 0.5682,
+      "step": 405
+    },
+    {
+      "epoch": 0.5251921434671221,
+      "grad_norm": 0.5091099739074707,
+      "learning_rate": 2.4122928455113233e-06,
+      "loss": 0.5619,
+      "step": 410
+    },
+    {
+      "epoch": 0.531596925704526,
+      "grad_norm": 0.4333205223083496,
+      "learning_rate": 2.360743924479093e-06,
+      "loss": 0.5879,
+      "step": 415
+    },
+    {
+      "epoch": 0.53800170794193,
+      "grad_norm": 0.4178122282028198,
+      "learning_rate": 2.3092543327398083e-06,
+      "loss": 0.5332,
+      "step": 420
+    },
+    {
+      "epoch": 0.544406490179334,
+      "grad_norm": 0.4080513119697571,
+      "learning_rate": 2.2578460071537512e-06,
+      "loss": 0.5728,
+      "step": 425
+    },
+    {
+      "epoch": 0.5508112724167379,
+      "grad_norm": 0.48982349038124084,
+      "learning_rate": 2.2065408499582e-06,
+      "loss": 0.575,
+      "step": 430
+    },
+    {
+      "epoch": 0.5572160546541418,
+      "grad_norm": 0.4953416883945465,
+      "learning_rate": 2.155360719436102e-06,
+      "loss": 0.5404,
+      "step": 435
+    },
+    {
+      "epoch": 0.5636208368915457,
+      "grad_norm": 0.4608188271522522,
+      "learning_rate": 2.1043274206034727e-06,
+      "loss": 0.5579,
+      "step": 440
+    },
+    {
+      "epoch": 0.5700256191289497,
+      "grad_norm": 0.48403236269950867,
+      "learning_rate": 2.0534626959194816e-06,
+      "loss": 0.5383,
+      "step": 445
+    },
+    {
+      "epoch": 0.5764304013663536,
+      "grad_norm": 0.4532581865787506,
+      "learning_rate": 2.002788216023203e-06,
+      "loss": 0.5638,
+      "step": 450
+    },
+    {
+      "epoch": 0.5828351836037575,
+      "grad_norm": 0.53521728515625,
+      "learning_rate": 1.9523255705009558e-06,
+      "loss": 0.5549,
+      "step": 455
+    },
+    {
+      "epoch": 0.5892399658411615,
+      "grad_norm": 0.4711097180843353,
+      "learning_rate": 1.902096258688174e-06,
+      "loss": 0.5027,
+      "step": 460
+    },
+    {
+      "epoch": 0.5956447480785654,
+      "grad_norm": 0.43662044405937195,
+      "learning_rate": 1.8521216805097358e-06,
+      "loss": 0.556,
+      "step": 465
+    },
+    {
+      "epoch": 0.6020495303159693,
+      "grad_norm": 0.3957918882369995,
+      "learning_rate": 1.8024231273626424e-06,
+      "loss": 0.5596,
+      "step": 470
+    },
+    {
+      "epoch": 0.6084543125533732,
+      "grad_norm": 0.5218236446380615,
+      "learning_rate": 1.7530217730449312e-06,
+      "loss": 0.5405,
+      "step": 475
+    },
+    {
+      "epoch": 0.6148590947907772,
+      "grad_norm": 0.4223135709762573,
+      "learning_rate": 1.7039386647346975e-06,
+      "loss": 0.5279,
+      "step": 480
+    },
+    {
+      "epoch": 0.6212638770281811,
+      "grad_norm": 0.3835909068584442,
+      "learning_rate": 1.6551947140230568e-06,
+      "loss": 0.5747,
+      "step": 485
+    },
+    {
+      "epoch": 0.627668659265585,
+      "grad_norm": 0.5082884430885315,
+      "learning_rate": 1.6068106880048747e-06,
+      "loss": 0.5518,
+      "step": 490
+    },
+    {
+      "epoch": 0.6340734415029889,
+      "grad_norm": 0.4860563278198242,
+      "learning_rate": 1.5588072004310634e-06,
+      "loss": 0.5641,
+      "step": 495
+    },
+    {
+      "epoch": 0.6404782237403929,
+      "grad_norm": 0.4176677167415619,
+      "learning_rate": 1.5112047029262e-06,
+      "loss": 0.5547,
+      "step": 500
+    },
+    {
+      "epoch": 0.6468830059777968,
+      "grad_norm": 0.3659776747226715,
+      "learning_rate": 1.4640234762752248e-06,
+      "loss": 0.5503,
+      "step": 505
+    },
+    {
+      "epoch": 0.6532877882152007,
+      "grad_norm": 0.4908987283706665,
+      "learning_rate": 1.4172836217829267e-06,
+      "loss": 0.5549,
+      "step": 510
+    },
+    {
+      "epoch": 0.6596925704526047,
+      "grad_norm": 0.44962796568870544,
+      "learning_rate": 1.3710050527098867e-06,
+      "loss": 0.573,
+      "step": 515
+    },
+    {
+      "epoch": 0.6660973526900086,
+      "grad_norm": 0.4549601376056671,
+      "learning_rate": 1.3252074857885453e-06,
+      "loss": 0.5666,
+      "step": 520
+    },
+    {
+      "epoch": 0.6725021349274125,
+      "grad_norm": 0.48955774307250977,
+      "learning_rate": 1.2799104328229928e-06,
+      "loss": 0.5379,
+      "step": 525
+    },
+    {
+      "epoch": 0.6789069171648164,
+      "grad_norm": 0.45902734994888306,
+      "learning_rate": 1.2351331923760743e-06,
+      "loss": 0.5345,
+      "step": 530
+    },
+    {
+      "epoch": 0.6853116994022204,
+      "grad_norm": 0.49846968054771423,
+      "learning_rate": 1.1908948415473418e-06,
+      "loss": 0.5367,
+      "step": 535
+    },
+    {
+      "epoch": 0.6917164816396243,
+      "grad_norm": 0.48370206356048584,
+      "learning_rate": 1.1472142278453582e-06,
+      "loss": 0.5325,
+      "step": 540
+    },
+    {
+      "epoch": 0.6981212638770282,
+      "grad_norm": 0.3830443024635315,
+      "learning_rate": 1.1041099611578177e-06,
+      "loss": 0.5585,
+      "step": 545
+    },
+    {
+      "epoch": 0.7045260461144321,
+      "grad_norm": 0.47550487518310547,
+      "learning_rate": 1.0616004058229084e-06,
+      "loss": 0.5417,
+      "step": 550
+    },
+    {
+      "epoch": 0.7109308283518361,
+      "grad_norm": 0.46026965975761414,
+      "learning_rate": 1.0197036728052847e-06,
+      "loss": 0.5715,
+      "step": 555
+    },
+    {
+      "epoch": 0.71733561058924,
+      "grad_norm": 0.42247724533081055,
+      "learning_rate": 9.784376119799851e-07,
+      "loss": 0.5459,
+      "step": 560
+    },
+    {
+      "epoch": 0.7237403928266439,
+      "grad_norm": 0.5001282095909119,
+      "learning_rate": 9.378198045275968e-07,
+      "loss": 0.5557,
+      "step": 565
+    },
+    {
+      "epoch": 0.7301451750640479,
+      "grad_norm": 0.4762704372406006,
+      "learning_rate": 8.97867555443886e-07,
+      "loss": 0.5338,
+      "step": 570
+    },
+    {
+      "epoch": 0.7365499573014518,
+      "grad_norm": 0.48811063170433044,
+      "learning_rate": 8.585978861670958e-07,
+      "loss": 0.5331,
+      "step": 575
+    },
+    {
+      "epoch": 0.7429547395388557,
+      "grad_norm": 0.45258718729019165,
+      "learning_rate": 8.200275273260611e-07,
+      "loss": 0.5461,
+      "step": 580
+    },
+    {
+      "epoch": 0.7493595217762596,
+      "grad_norm": 0.4314691424369812,
+      "learning_rate": 7.821729116122126e-07,
+      "loss": 0.558,
+      "step": 585
+    },
+    {
+      "epoch": 0.7557643040136636,
+      "grad_norm": 0.4526233673095703,
+      "learning_rate": 7.450501667785146e-07,
+      "loss": 0.5455,
+      "step": 590
+    },
+    {
+      "epoch": 0.7621690862510675,
+      "grad_norm": 0.4625132977962494,
+      "learning_rate": 7.086751087683297e-07,
+      "loss": 0.5514,
+      "step": 595
+    },
+    {
+      "epoch": 0.7685738684884714,
+      "grad_norm": 0.4986107349395752,
+      "learning_rate": 6.730632349771193e-07,
+      "loss": 0.5566,
+      "step": 600
+    },
+    {
+      "epoch": 0.7749786507258754,
+      "grad_norm": 0.5132951140403748,
+      "learning_rate": 6.3822971764986e-07,
+      "loss": 0.5363,
+      "step": 605
+    },
+    {
+      "epoch": 0.7813834329632793,
+      "grad_norm": 0.48895248770713806,
+      "learning_rate": 6.041893974169963e-07,
+      "loss": 0.5382,
+      "step": 610
+    },
+    {
+      "epoch": 0.7877882152006832,
+      "grad_norm": 0.48889264464378357,
+      "learning_rate": 5.709567769716678e-07,
+      "loss": 0.5511,
+      "step": 615
+    },
+    {
+      "epoch": 0.7941929974380871,
+      "grad_norm": 0.4542140066623688,
+      "learning_rate": 5.385460148909169e-07,
+      "loss": 0.5227,
+      "step": 620
+    },
+    {
+      "epoch": 0.8005977796754911,
+      "grad_norm": 0.48940637707710266,
+      "learning_rate": 5.069709196035011e-07,
+      "loss": 0.5519,
+      "step": 625
+    },
+    {
+      "epoch": 0.807002561912895,
+      "grad_norm": 0.45722976326942444,
+      "learning_rate": 4.762449435068914e-07,
+      "loss": 0.5358,
+      "step": 630
+    },
+    {
+      "epoch": 0.8134073441502989,
+      "grad_norm": 0.5042068958282471,
+      "learning_rate": 4.4638117723595054e-07,
+      "loss": 0.5686,
+      "step": 635
+    },
+    {
+      "epoch": 0.8198121263877028,
+      "grad_norm": 0.4974375069141388,
+      "learning_rate": 4.173923440857358e-07,
+      "loss": 0.5528,
+      "step": 640
+    },
+    {
+      "epoch": 0.8262169086251068,
+      "grad_norm": 0.4234403669834137,
+      "learning_rate": 3.892907945908128e-07,
+      "loss": 0.5305,
+      "step": 645
+    },
+    {
+      "epoch": 0.8326216908625107,
+      "grad_norm": 0.5144878029823303,
+      "learning_rate": 3.6208850126337595e-07,
+      "loss": 0.5282,
+      "step": 650
+    },
+    {
+      "epoch": 0.8390264730999146,
+      "grad_norm": 0.41059333086013794,
+      "learning_rate": 3.357970534924229e-07,
+      "loss": 0.5601,
+      "step": 655
+    },
+    {
+      "epoch": 0.8454312553373186,
+      "grad_norm": 0.40885528922080994,
+      "learning_rate": 3.104276526061617e-07,
+      "loss": 0.536,
+      "step": 660
+    },
+    {
+      "epoch": 0.8518360375747225,
+      "grad_norm": 0.462971568107605,
+      "learning_rate": 2.859911070997437e-07,
+      "loss": 0.5513,
+      "step": 665
+    },
+    {
+      "epoch": 0.8582408198121264,
+      "grad_norm": 0.6165898442268372,
+      "learning_rate": 2.624978280303628e-07,
+      "loss": 0.5542,
+      "step": 670
+    },
+    {
+      "epoch": 0.8646456020495303,
+      "grad_norm": 0.514519453048706,
+      "learning_rate": 2.3995782458168276e-07,
+      "loss": 0.5572,
+      "step": 675
+    },
+    {
+      "epoch": 0.8710503842869343,
+      "grad_norm": 0.5139626264572144,
+      "learning_rate": 2.1838069979947945e-07,
+      "loss": 0.5372,
+      "step": 680
+    },
+    {
+      "epoch": 0.8774551665243382,
+      "grad_norm": 1.6515536308288574,
+      "learning_rate": 1.9777564650031112e-07,
+      "loss": 0.5515,
+      "step": 685
+    },
+    {
+      "epoch": 0.8838599487617421,
+      "grad_norm": 0.4731055200099945,
+      "learning_rate": 1.7815144335497524e-07,
+      "loss": 0.5515,
+      "step": 690
+    },
+    {
+      "epoch": 0.890264730999146,
+      "grad_norm": 0.5183550715446472,
+      "learning_rate": 1.5951645114839875e-07,
+      "loss": 0.5419,
+      "step": 695
+    },
+    {
+      "epoch": 0.89666951323655,
+      "grad_norm": 0.5357317328453064,
+      "learning_rate": 1.4187860921757252e-07,
+      "loss": 0.5571,
+      "step": 700
+    },
+    {
+      "epoch": 0.9030742954739539,
+      "grad_norm": 0.5177751779556274,
+      "learning_rate": 1.2524543206904188e-07,
+      "loss": 0.5607,
+      "step": 705
+    },
+    {
+      "epoch": 0.9094790777113578,
+      "grad_norm": 0.4790054261684418,
+      "learning_rate": 1.0962400617738872e-07,
+      "loss": 0.581,
+      "step": 710
+    },
+    {
+      "epoch": 0.9158838599487618,
+      "grad_norm": 0.5255675911903381,
+      "learning_rate": 9.502098696608147e-08,
+      "loss": 0.5449,
+      "step": 715
+    },
+    {
+      "epoch": 0.9222886421861657,
+      "grad_norm": 0.38730135560035706,
+      "learning_rate": 8.144259597196308e-08,
+      "loss": 0.5518,
+      "step": 720
+    },
+    {
+      "epoch": 0.9286934244235696,
+      "grad_norm": 0.42933622002601624,
+      "learning_rate": 6.889461819460485e-08,
+      "loss": 0.5365,
+      "step": 725
+    },
+    {
+      "epoch": 0.9350982066609735,
+      "grad_norm": 0.50970458984375,
+      "learning_rate": 5.738239963163472e-08,
+      "loss": 0.5282,
+      "step": 730
+    },
+    {
+      "epoch": 0.9415029888983775,
+      "grad_norm": 0.5318973064422607,
+      "learning_rate": 4.691084500110521e-08,
+      "loss": 0.5281,
+      "step": 735
+    },
+    {
+      "epoch": 0.9479077711357814,
+      "grad_norm": 0.4877215623855591,
+      "learning_rate": 3.748441565186583e-08,
+      "loss": 0.5136,
+      "step": 740
+    },
+    {
+      "epoch": 0.9543125533731853,
+      "grad_norm": 0.5620718002319336,
+      "learning_rate": 2.910712766282908e-08,
+      "loss": 0.5385,
+      "step": 745
+    },
+    {
+      "epoch": 0.9607173356105893,
+      "grad_norm": 0.5282920598983765,
+      "learning_rate": 2.178255013194075e-08,
+      "loss": 0.5296,
+      "step": 750
+    },
+    {
+      "epoch": 0.9671221178479932,
+      "grad_norm": 0.422025591135025,
+      "learning_rate": 1.5513803655587966e-08,
+      "loss": 0.5131,
+      "step": 755
+    },
+    {
+      "epoch": 0.9735269000853971,
+      "grad_norm": 0.5139475464820862,
+      "learning_rate": 1.0303558999082974e-08,
+      "loss": 0.5625,
+      "step": 760
+    },
+    {
+      "epoch": 0.979931682322801,
+      "grad_norm": 0.48410946130752563,
+      "learning_rate": 6.1540359588005416e-09,
+      "loss": 0.5286,
+      "step": 765
+    },
+    {
+      "epoch": 0.986336464560205,
+      "grad_norm": 0.4075927138328552,
+      "learning_rate": 3.067002416444198e-09,
+      "loss": 0.5113,
+      "step": 770
+    },
+    {
+      "epoch": 0.9927412467976089,
+      "grad_norm": 0.4521820545196533,
+      "learning_rate": 1.0437735858506715e-09,
+      "loss": 0.5399,
+      "step": 775
+    },
+    {
+      "epoch": 0.9991460290350128,
+      "grad_norm": 0.41308000683784485,
+      "learning_rate": 8.521145264978048e-11,
+      "loss": 0.5787,
+      "step": 780
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 781,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.995150581897871e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}