SFT warmup LoRA for 8B 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/Qwen3-8B
+tags:
+- base_model:adapter:unsloth/Qwen3-8B
+- llama-factory
+- lora
+- transformers
+- unsloth
+pipeline_tag: text-generation
+model-index:
+- name: CodeRM-SFT-Warmup-Selection-8B-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-8B-LlamaFactory
+
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) 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: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 12
+- 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/Qwen3-8B",
+  "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": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj",
+    "down_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:d49a26e0f493334f0e4e5acd00b3036faf9c449af09b0cf839d72bd9c22af001
+size 698419728

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": 1.4329344655107686e+18,
+    "train_loss": 0.5799389032029312,
+    "train_runtime": 9974.2346,
+    "train_samples_per_second": 0.939,
+    "train_steps_per_second": 0.078
+}

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/Qwen3-8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-8B
+- 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/Qwen3-8B",
+  "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": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj",
+    "down_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 sha256:02d953b063d6f427db2b20eafff10786961ce6736089627e10d1e08175f2f538
+size 698419728

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 sha256:55c59ab128e253a861c652bf1f505e940c18e23661694f24a4724f80d70f4055
+size 1397129547

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": 0.896765239671186,
+  "eval_steps": 25,
+  "global_step": 700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0064054659976513295,
+      "grad_norm": 1.095150351524353,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.9763,
+      "step": 5
+    },
+    {
+      "epoch": 0.012810931995302659,
+      "grad_norm": 1.0511373281478882,
+      "learning_rate": 2.25e-06,
+      "loss": 0.9023,
+      "step": 10
+    },
+    {
+      "epoch": 0.019216397992953986,
+      "grad_norm": 0.817418098449707,
+      "learning_rate": 3.5e-06,
+      "loss": 0.9288,
+      "step": 15
+    },
+    {
+      "epoch": 0.025621863990605318,
+      "grad_norm": 0.624769926071167,
+      "learning_rate": 4.75e-06,
+      "loss": 0.8766,
+      "step": 20
+    },
+    {
+      "epoch": 0.03202732998825664,
+      "grad_norm": 0.5237262845039368,
+      "learning_rate": 4.999659159998194e-06,
+      "loss": 0.8411,
+      "step": 25
+    },
+    {
+      "epoch": 0.03843279598590797,
+      "grad_norm": 0.46350979804992676,
+      "learning_rate": 4.998274656771894e-06,
+      "loss": 0.8132,
+      "step": 30
+    },
+    {
+      "epoch": 0.0448382619835593,
+      "grad_norm": 0.3592084050178528,
+      "learning_rate": 4.995825777227236e-06,
+      "loss": 0.7663,
+      "step": 35
+    },
+    {
+      "epoch": 0.051243727981210636,
+      "grad_norm": 0.34569790959358215,
+      "learning_rate": 4.992313564696022e-06,
+      "loss": 0.7355,
+      "step": 40
+    },
+    {
+      "epoch": 0.057649193978861965,
+      "grad_norm": 0.2865957021713257,
+      "learning_rate": 4.9877395155372815e-06,
+      "loss": 0.7632,
+      "step": 45
+    },
+    {
+      "epoch": 0.06405465997651329,
+      "grad_norm": 0.25277993083000183,
+      "learning_rate": 4.982105578499759e-06,
+      "loss": 0.7539,
+      "step": 50
+    },
+    {
+      "epoch": 0.07046012597416462,
+      "grad_norm": 0.24113819003105164,
+      "learning_rate": 4.975414153891664e-06,
+      "loss": 0.7322,
+      "step": 55
+    },
+    {
+      "epoch": 0.07686559197181594,
+      "grad_norm": 0.2370101362466812,
+      "learning_rate": 4.967668092558024e-06,
+      "loss": 0.7242,
+      "step": 60
+    },
+    {
+      "epoch": 0.08327105796946728,
+      "grad_norm": 0.23438391089439392,
+      "learning_rate": 4.9588706946661066e-06,
+      "loss": 0.6943,
+      "step": 65
+    },
+    {
+      "epoch": 0.0896765239671186,
+      "grad_norm": 0.24512864649295807,
+      "learning_rate": 4.949025708299395e-06,
+      "loss": 0.6866,
+      "step": 70
+    },
+    {
+      "epoch": 0.09608198996476994,
+      "grad_norm": 0.22728285193443298,
+      "learning_rate": 4.93813732786074e-06,
+      "loss": 0.6658,
+      "step": 75
+    },
+    {
+      "epoch": 0.10248745596242127,
+      "grad_norm": 0.2585676610469818,
+      "learning_rate": 4.926210192285359e-06,
+      "loss": 0.7284,
+      "step": 80
+    },
+    {
+      "epoch": 0.1088929219600726,
+      "grad_norm": 0.2257288247346878,
+      "learning_rate": 4.913249383064438e-06,
+      "loss": 0.6844,
+      "step": 85
+    },
+    {
+      "epoch": 0.11529838795772393,
+      "grad_norm": 0.2544812262058258,
+      "learning_rate": 4.899260422080195e-06,
+      "loss": 0.6872,
+      "step": 90
+    },
+    {
+      "epoch": 0.12170385395537525,
+      "grad_norm": 0.23987820744514465,
+      "learning_rate": 4.884249269253309e-06,
+      "loss": 0.6438,
+      "step": 95
+    },
+    {
+      "epoch": 0.12810931995302657,
+      "grad_norm": 0.28527575731277466,
+      "learning_rate": 4.868222320003731e-06,
+      "loss": 0.656,
+      "step": 100
+    },
+    {
+      "epoch": 0.13451478595067792,
+      "grad_norm": 0.25415557622909546,
+      "learning_rate": 4.851186402525946e-06,
+      "loss": 0.6562,
+      "step": 105
+    },
+    {
+      "epoch": 0.14092025194832924,
+      "grad_norm": 0.21308082342147827,
+      "learning_rate": 4.8331487748798636e-06,
+      "loss": 0.6569,
+      "step": 110
+    },
+    {
+      "epoch": 0.14732571794598057,
+      "grad_norm": 0.23867692053318024,
+      "learning_rate": 4.814117121898554e-06,
+      "loss": 0.6158,
+      "step": 115
+    },
+    {
+      "epoch": 0.1537311839436319,
+      "grad_norm": 0.23583965003490448,
+      "learning_rate": 4.794099551914173e-06,
+      "loss": 0.6084,
+      "step": 120
+    },
+    {
+      "epoch": 0.16013664994128324,
+      "grad_norm": 0.22881825268268585,
+      "learning_rate": 4.773104593303449e-06,
+      "loss": 0.6778,
+      "step": 125
+    },
+    {
+      "epoch": 0.16654211593893456,
+      "grad_norm": 0.24278834462165833,
+      "learning_rate": 4.751141190854214e-06,
+      "loss": 0.6071,
+      "step": 130
+    },
+    {
+      "epoch": 0.17294758193658588,
+      "grad_norm": 0.2911915183067322,
+      "learning_rate": 4.728218701954525e-06,
+      "loss": 0.6543,
+      "step": 135
+    },
+    {
+      "epoch": 0.1793530479342372,
+      "grad_norm": 0.2795209586620331,
+      "learning_rate": 4.704346892606001e-06,
+      "loss": 0.5956,
+      "step": 140
+    },
+    {
+      "epoch": 0.18575851393188855,
+      "grad_norm": 0.25558847188949585,
+      "learning_rate": 4.6795359332630694e-06,
+      "loss": 0.6395,
+      "step": 145
+    },
+    {
+      "epoch": 0.19216397992953987,
+      "grad_norm": 0.2465032935142517,
+      "learning_rate": 4.653796394499904e-06,
+      "loss": 0.6136,
+      "step": 150
+    },
+    {
+      "epoch": 0.1985694459271912,
+      "grad_norm": 0.244729146361351,
+      "learning_rate": 4.627139242506882e-06,
+      "loss": 0.6046,
+      "step": 155
+    },
+    {
+      "epoch": 0.20497491192484255,
+      "grad_norm": 0.2569523751735687,
+      "learning_rate": 4.599575834418505e-06,
+      "loss": 0.6483,
+      "step": 160
+    },
+    {
+      "epoch": 0.21138037792249387,
+      "grad_norm": 0.29486870765686035,
+      "learning_rate": 4.571117913474749e-06,
+      "loss": 0.6034,
+      "step": 165
+    },
+    {
+      "epoch": 0.2177858439201452,
+      "grad_norm": 0.26274922490119934,
+      "learning_rate": 4.541777604017924e-06,
+      "loss": 0.5834,
+      "step": 170
+    },
+    {
+      "epoch": 0.2241913099177965,
+      "grad_norm": 0.2968301773071289,
+      "learning_rate": 4.511567406327162e-06,
+      "loss": 0.6063,
+      "step": 175
+    },
+    {
+      "epoch": 0.23059677591544786,
+      "grad_norm": 0.301880419254303,
+      "learning_rate": 4.480500191292744e-06,
+      "loss": 0.5965,
+      "step": 180
+    },
+    {
+      "epoch": 0.23700224191309918,
+      "grad_norm": 0.27574408054351807,
+      "learning_rate": 4.448589194932521e-06,
+      "loss": 0.5959,
+      "step": 185
+    },
+    {
+      "epoch": 0.2434077079107505,
+      "grad_norm": 0.25683072209358215,
+      "learning_rate": 4.415848012752789e-06,
+      "loss": 0.5764,
+      "step": 190
+    },
+    {
+      "epoch": 0.24981317390840183,
+      "grad_norm": 0.3023504912853241,
+      "learning_rate": 4.38229059395599e-06,
+      "loss": 0.6013,
+      "step": 195
+    },
+    {
+      "epoch": 0.25621863990605315,
+      "grad_norm": 0.2837856113910675,
+      "learning_rate": 4.347931235497738e-06,
+      "loss": 0.6044,
+      "step": 200
+    },
+    {
+      "epoch": 0.2626241059037045,
+      "grad_norm": 0.29550132155418396,
+      "learning_rate": 4.312784575995669e-06,
+      "loss": 0.5866,
+      "step": 205
+    },
+    {
+      "epoch": 0.26902957190135585,
+      "grad_norm": 0.28646326065063477,
+      "learning_rate": 4.276865589492747e-06,
+      "loss": 0.5838,
+      "step": 210
+    },
+    {
+      "epoch": 0.27543503789900714,
+      "grad_norm": 0.3569891154766083,
+      "learning_rate": 4.240189579077649e-06,
+      "loss": 0.5701,
+      "step": 215
+    },
+    {
+      "epoch": 0.2818405038966585,
+      "grad_norm": 0.33763790130615234,
+      "learning_rate": 4.202772170364969e-06,
+      "loss": 0.5759,
+      "step": 220
+    },
+    {
+      "epoch": 0.2882459698943098,
+      "grad_norm": 0.245514377951622,
+      "learning_rate": 4.164629304838012e-06,
+      "loss": 0.5694,
+      "step": 225
+    },
+    {
+      "epoch": 0.29465143589196113,
+      "grad_norm": 0.2917734682559967,
+      "learning_rate": 4.125777233057007e-06,
+      "loss": 0.5944,
+      "step": 230
+    },
+    {
+      "epoch": 0.3010569018896125,
+      "grad_norm": 0.2828243374824524,
+      "learning_rate": 4.086232507735648e-06,
+      "loss": 0.5717,
+      "step": 235
+    },
+    {
+      "epoch": 0.3074623678872638,
+      "grad_norm": 0.38584598898887634,
+      "learning_rate": 4.0460119766889e-06,
+      "loss": 0.5931,
+      "step": 240
+    },
+    {
+      "epoch": 0.3138678338849151,
+      "grad_norm": 0.36006131768226624,
+      "learning_rate": 4.005132775655076e-06,
+      "loss": 0.5564,
+      "step": 245
+    },
+    {
+      "epoch": 0.3202732998825665,
+      "grad_norm": 0.372942179441452,
+      "learning_rate": 3.963612320995257e-06,
+      "loss": 0.6025,
+      "step": 250
+    },
+    {
+      "epoch": 0.32667876588021777,
+      "grad_norm": 0.28577810525894165,
+      "learning_rate": 3.921468302273137e-06,
+      "loss": 0.5469,
+      "step": 255
+    },
+    {
+      "epoch": 0.3330842318778691,
+      "grad_norm": 0.3417142331600189,
+      "learning_rate": 3.8787186747184826e-06,
+      "loss": 0.5342,
+      "step": 260
+    },
+    {
+      "epoch": 0.33948969787552047,
+      "grad_norm": 0.35277873277664185,
+      "learning_rate": 3.8353816515774115e-06,
+      "loss": 0.5531,
+      "step": 265
+    },
+    {
+      "epoch": 0.34589516387317176,
+      "grad_norm": 0.2886194586753845,
+      "learning_rate": 3.79147569635273e-06,
+      "loss": 0.5431,
+      "step": 270
+    },
+    {
+      "epoch": 0.3523006298708231,
+      "grad_norm": 0.29417017102241516,
+      "learning_rate": 3.747019514937663e-06,
+      "loss": 0.5826,
+      "step": 275
+    },
+    {
+      "epoch": 0.3587060958684744,
+      "grad_norm": 0.3237856924533844,
+      "learning_rate": 3.70203204764631e-06,
+      "loss": 0.5689,
+      "step": 280
+    },
+    {
+      "epoch": 0.36511156186612576,
+      "grad_norm": 0.3846990168094635,
+      "learning_rate": 3.6565324611442234e-06,
+      "loss": 0.5763,
+      "step": 285
+    },
+    {
+      "epoch": 0.3715170278637771,
+      "grad_norm": 0.2781718969345093,
+      "learning_rate": 3.6105401402825595e-06,
+      "loss": 0.5549,
+      "step": 290
+    },
+    {
+      "epoch": 0.3779224938614284,
+      "grad_norm": 0.2733434736728668,
+      "learning_rate": 3.5640746798392657e-06,
+      "loss": 0.5967,
+      "step": 295
+    },
+    {
+      "epoch": 0.38432795985907975,
+      "grad_norm": 0.34851792454719543,
+      "learning_rate": 3.5171558761708334e-06,
+      "loss": 0.5543,
+      "step": 300
+    },
+    {
+      "epoch": 0.3907334258567311,
+      "grad_norm": 0.34361544251441956,
+      "learning_rate": 3.469803718778166e-06,
+      "loss": 0.5519,
+      "step": 305
+    },
+    {
+      "epoch": 0.3971388918543824,
+      "grad_norm": 0.2903674244880676,
+      "learning_rate": 3.4220383817901625e-06,
+      "loss": 0.562,
+      "step": 310
+    },
+    {
+      "epoch": 0.40354435785203374,
+      "grad_norm": 0.31230857968330383,
+      "learning_rate": 3.3738802153686414e-06,
+      "loss": 0.5537,
+      "step": 315
+    },
+    {
+      "epoch": 0.4099498238496851,
+      "grad_norm": 0.31388580799102783,
+      "learning_rate": 3.3253497370382605e-06,
+      "loss": 0.5551,
+      "step": 320
+    },
+    {
+      "epoch": 0.4163552898473364,
+      "grad_norm": 0.32741594314575195,
+      "learning_rate": 3.2764676229451397e-06,
+      "loss": 0.5498,
+      "step": 325
+    },
+    {
+      "epoch": 0.42276075584498773,
+      "grad_norm": 0.2511857748031616,
+      "learning_rate": 3.227254699047904e-06,
+      "loss": 0.5511,
+      "step": 330
+    },
+    {
+      "epoch": 0.42916622184263903,
+      "grad_norm": 0.3877544105052948,
+      "learning_rate": 3.177731932244892e-06,
+      "loss": 0.5485,
+      "step": 335
+    },
+    {
+      "epoch": 0.4355716878402904,
+      "grad_norm": 0.3445497751235962,
+      "learning_rate": 3.127920421441327e-06,
+      "loss": 0.5639,
+      "step": 340
+    },
+    {
+      "epoch": 0.4419771538379417,
+      "grad_norm": 0.3347369432449341,
+      "learning_rate": 3.077841388560243e-06,
+      "loss": 0.5745,
+      "step": 345
+    },
+    {
+      "epoch": 0.448382619835593,
+      "grad_norm": 0.36205726861953735,
+      "learning_rate": 3.0275161695009975e-06,
+      "loss": 0.5658,
+      "step": 350
+    },
+    {
+      "epoch": 0.45478808583324437,
+      "grad_norm": 0.35722121596336365,
+      "learning_rate": 2.9769662050492276e-06,
+      "loss": 0.5479,
+      "step": 355
+    },
+    {
+      "epoch": 0.4611935518308957,
+      "grad_norm": 0.35634711384773254,
+      "learning_rate": 2.926213031742125e-06,
+      "loss": 0.5595,
+      "step": 360
+    },
+    {
+      "epoch": 0.467599017828547,
+      "grad_norm": 0.32853105664253235,
+      "learning_rate": 2.8752782726929045e-06,
+      "loss": 0.5429,
+      "step": 365
+    },
+    {
+      "epoch": 0.47400448382619836,
+      "grad_norm": 0.3939530551433563,
+      "learning_rate": 2.8241836283784026e-06,
+      "loss": 0.531,
+      "step": 370
+    },
+    {
+      "epoch": 0.48040994982384966,
+      "grad_norm": 0.3002113699913025,
+      "learning_rate": 2.7729508673936972e-06,
+      "loss": 0.5596,
+      "step": 375
+    },
+    {
+      "epoch": 0.486815415821501,
+      "grad_norm": 0.3216375708580017,
+      "learning_rate": 2.721601817177725e-06,
+      "loss": 0.5292,
+      "step": 380
+    },
+    {
+      "epoch": 0.49322088181915236,
+      "grad_norm": 0.3263518810272217,
+      "learning_rate": 2.6701583547138165e-06,
+      "loss": 0.5684,
+      "step": 385
+    },
+    {
+      "epoch": 0.49962634781680365,
+      "grad_norm": 0.3253946900367737,
+      "learning_rate": 2.618642397209126e-06,
+      "loss": 0.5264,
+      "step": 390
+    },
+    {
+      "epoch": 0.5060318138144551,
+      "grad_norm": 0.3231858015060425,
+      "learning_rate": 2.567075892756924e-06,
+      "loss": 0.5448,
+      "step": 395
+    },
+    {
+      "epoch": 0.5124372798121063,
+      "grad_norm": 0.36590418219566345,
+      "learning_rate": 2.5154808109857367e-06,
+      "loss": 0.5248,
+      "step": 400
+    },
+    {
+      "epoch": 0.5188427458097576,
+      "grad_norm": 0.3773280084133148,
+      "learning_rate": 2.4638791336992967e-06,
+      "loss": 0.5505,
+      "step": 405
+    },
+    {
+      "epoch": 0.525248211807409,
+      "grad_norm": 0.3829450309276581,
+      "learning_rate": 2.4122928455113233e-06,
+      "loss": 0.5466,
+      "step": 410
+    },
+    {
+      "epoch": 0.5316536778050603,
+      "grad_norm": 0.3306972086429596,
+      "learning_rate": 2.360743924479093e-06,
+      "loss": 0.5721,
+      "step": 415
+    },
+    {
+      "epoch": 0.5380591438027117,
+      "grad_norm": 0.32845625281333923,
+      "learning_rate": 2.3092543327398083e-06,
+      "loss": 0.5177,
+      "step": 420
+    },
+    {
+      "epoch": 0.5444646098003629,
+      "grad_norm": 0.3088594079017639,
+      "learning_rate": 2.2578460071537512e-06,
+      "loss": 0.5575,
+      "step": 425
+    },
+    {
+      "epoch": 0.5508700757980143,
+      "grad_norm": 0.3912436366081238,
+      "learning_rate": 2.2065408499582e-06,
+      "loss": 0.561,
+      "step": 430
+    },
+    {
+      "epoch": 0.5572755417956656,
+      "grad_norm": 0.3839537799358368,
+      "learning_rate": 2.155360719436102e-06,
+      "loss": 0.526,
+      "step": 435
+    },
+    {
+      "epoch": 0.563681007793317,
+      "grad_norm": 0.3676234185695648,
+      "learning_rate": 2.1043274206034727e-06,
+      "loss": 0.541,
+      "step": 440
+    },
+    {
+      "epoch": 0.5700864737909683,
+      "grad_norm": 0.368198424577713,
+      "learning_rate": 2.0534626959194816e-06,
+      "loss": 0.5212,
+      "step": 445
+    },
+    {
+      "epoch": 0.5764919397886196,
+      "grad_norm": 0.34693998098373413,
+      "learning_rate": 2.002788216023203e-06,
+      "loss": 0.5462,
+      "step": 450
+    },
+    {
+      "epoch": 0.5828974057862709,
+      "grad_norm": 0.37934619188308716,
+      "learning_rate": 1.9523255705009558e-06,
+      "loss": 0.5423,
+      "step": 455
+    },
+    {
+      "epoch": 0.5893028717839223,
+      "grad_norm": 0.3458510637283325,
+      "learning_rate": 1.902096258688174e-06,
+      "loss": 0.4889,
+      "step": 460
+    },
+    {
+      "epoch": 0.5957083377815736,
+      "grad_norm": 0.33206406235694885,
+      "learning_rate": 1.8521216805097358e-06,
+      "loss": 0.5378,
+      "step": 465
+    },
+    {
+      "epoch": 0.602113803779225,
+      "grad_norm": 0.29139187932014465,
+      "learning_rate": 1.8024231273626424e-06,
+      "loss": 0.5444,
+      "step": 470
+    },
+    {
+      "epoch": 0.6085192697768763,
+      "grad_norm": 0.3665342926979065,
+      "learning_rate": 1.7530217730449312e-06,
+      "loss": 0.5276,
+      "step": 475
+    },
+    {
+      "epoch": 0.6149247357745276,
+      "grad_norm": 0.32149678468704224,
+      "learning_rate": 1.7039386647346975e-06,
+      "loss": 0.5117,
+      "step": 480
+    },
+    {
+      "epoch": 0.6213302017721789,
+      "grad_norm": 0.30389899015426636,
+      "learning_rate": 1.6551947140230568e-06,
+      "loss": 0.5573,
+      "step": 485
+    },
+    {
+      "epoch": 0.6277356677698303,
+      "grad_norm": 0.3890632688999176,
+      "learning_rate": 1.6068106880048747e-06,
+      "loss": 0.5395,
+      "step": 490
+    },
+    {
+      "epoch": 0.6341411337674816,
+      "grad_norm": 0.36464181542396545,
+      "learning_rate": 1.5588072004310634e-06,
+      "loss": 0.5497,
+      "step": 495
+    },
+    {
+      "epoch": 0.640546599765133,
+      "grad_norm": 0.32058826088905334,
+      "learning_rate": 1.5112047029262e-06,
+      "loss": 0.5377,
+      "step": 500
+    },
+    {
+      "epoch": 0.6469520657627842,
+      "grad_norm": 0.280649870634079,
+      "learning_rate": 1.4640234762752248e-06,
+      "loss": 0.5349,
+      "step": 505
+    },
+    {
+      "epoch": 0.6533575317604355,
+      "grad_norm": 0.36669427156448364,
+      "learning_rate": 1.4172836217829267e-06,
+      "loss": 0.539,
+      "step": 510
+    },
+    {
+      "epoch": 0.6597629977580869,
+      "grad_norm": 0.3747427463531494,
+      "learning_rate": 1.3710050527098867e-06,
+      "loss": 0.5582,
+      "step": 515
+    },
+    {
+      "epoch": 0.6661684637557382,
+      "grad_norm": 0.3354856073856354,
+      "learning_rate": 1.3252074857885453e-06,
+      "loss": 0.5512,
+      "step": 520
+    },
+    {
+      "epoch": 0.6725739297533896,
+      "grad_norm": 0.3852190673351288,
+      "learning_rate": 1.2799104328229928e-06,
+      "loss": 0.5216,
+      "step": 525
+    },
+    {
+      "epoch": 0.6789793957510409,
+      "grad_norm": 0.3479975759983063,
+      "learning_rate": 1.2351331923760743e-06,
+      "loss": 0.518,
+      "step": 530
+    },
+    {
+      "epoch": 0.6853848617486922,
+      "grad_norm": 0.37335509061813354,
+      "learning_rate": 1.1908948415473418e-06,
+      "loss": 0.5203,
+      "step": 535
+    },
+    {
+      "epoch": 0.6917903277463435,
+      "grad_norm": 0.4034595489501953,
+      "learning_rate": 1.1472142278453582e-06,
+      "loss": 0.5157,
+      "step": 540
+    },
+    {
+      "epoch": 0.6981957937439949,
+      "grad_norm": 0.2966196537017822,
+      "learning_rate": 1.1041099611578177e-06,
+      "loss": 0.541,
+      "step": 545
+    },
+    {
+      "epoch": 0.7046012597416462,
+      "grad_norm": 0.3616897463798523,
+      "learning_rate": 1.0616004058229084e-06,
+      "loss": 0.5254,
+      "step": 550
+    },
+    {
+      "epoch": 0.7110067257392976,
+      "grad_norm": 0.3452332317829132,
+      "learning_rate": 1.0197036728052847e-06,
+      "loss": 0.5543,
+      "step": 555
+    },
+    {
+      "epoch": 0.7174121917369488,
+      "grad_norm": 0.3313845694065094,
+      "learning_rate": 9.784376119799851e-07,
+      "loss": 0.5294,
+      "step": 560
+    },
+    {
+      "epoch": 0.7238176577346002,
+      "grad_norm": 0.37989768385887146,
+      "learning_rate": 9.378198045275968e-07,
+      "loss": 0.5411,
+      "step": 565
+    },
+    {
+      "epoch": 0.7302231237322515,
+      "grad_norm": 0.3642790913581848,
+      "learning_rate": 8.97867555443886e-07,
+      "loss": 0.5186,
+      "step": 570
+    },
+    {
+      "epoch": 0.7366285897299029,
+      "grad_norm": 0.369183748960495,
+      "learning_rate": 8.585978861670958e-07,
+      "loss": 0.5189,
+      "step": 575
+    },
+    {
+      "epoch": 0.7430340557275542,
+      "grad_norm": 0.3428362011909485,
+      "learning_rate": 8.200275273260611e-07,
+      "loss": 0.5326,
+      "step": 580
+    },
+    {
+      "epoch": 0.7494395217252056,
+      "grad_norm": 0.33693212270736694,
+      "learning_rate": 7.821729116122126e-07,
+      "loss": 0.5417,
+      "step": 585
+    },
+    {
+      "epoch": 0.7558449877228568,
+      "grad_norm": 0.35541847348213196,
+      "learning_rate": 7.450501667785146e-07,
+      "loss": 0.531,
+      "step": 590
+    },
+    {
+      "epoch": 0.7622504537205081,
+      "grad_norm": 0.3545955717563629,
+      "learning_rate": 7.086751087683297e-07,
+      "loss": 0.5371,
+      "step": 595
+    },
+    {
+      "epoch": 0.7686559197181595,
+      "grad_norm": 0.369098424911499,
+      "learning_rate": 6.730632349771193e-07,
+      "loss": 0.5444,
+      "step": 600
+    },
+    {
+      "epoch": 0.7750613857158108,
+      "grad_norm": 0.395386666059494,
+      "learning_rate": 6.3822971764986e-07,
+      "loss": 0.5207,
+      "step": 605
+    },
+    {
+      "epoch": 0.7814668517134622,
+      "grad_norm": 0.3929295241832733,
+      "learning_rate": 6.041893974169963e-07,
+      "loss": 0.5223,
+      "step": 610
+    },
+    {
+      "epoch": 0.7878723177111134,
+      "grad_norm": 0.38200634717941284,
+      "learning_rate": 5.709567769716678e-07,
+      "loss": 0.5346,
+      "step": 615
+    },
+    {
+      "epoch": 0.7942777837087648,
+      "grad_norm": 0.35260388255119324,
+      "learning_rate": 5.385460148909169e-07,
+      "loss": 0.5106,
+      "step": 620
+    },
+    {
+      "epoch": 0.8006832497064161,
+      "grad_norm": 0.36902984976768494,
+      "learning_rate": 5.069709196035011e-07,
+      "loss": 0.5333,
+      "step": 625
+    },
+    {
+      "epoch": 0.8070887157040675,
+      "grad_norm": 0.36749160289764404,
+      "learning_rate": 4.762449435068914e-07,
+      "loss": 0.5197,
+      "step": 630
+    },
+    {
+      "epoch": 0.8134941817017188,
+      "grad_norm": 0.37014660239219666,
+      "learning_rate": 4.4638117723595054e-07,
+      "loss": 0.5492,
+      "step": 635
+    },
+    {
+      "epoch": 0.8198996476993702,
+      "grad_norm": 0.3781520426273346,
+      "learning_rate": 4.173923440857358e-07,
+      "loss": 0.5365,
+      "step": 640
+    },
+    {
+      "epoch": 0.8263051136970214,
+      "grad_norm": 0.33049196004867554,
+      "learning_rate": 3.892907945908128e-07,
+      "loss": 0.5163,
+      "step": 645
+    },
+    {
+      "epoch": 0.8327105796946728,
+      "grad_norm": 0.40030181407928467,
+      "learning_rate": 3.6208850126337595e-07,
+      "loss": 0.5111,
+      "step": 650
+    },
+    {
+      "epoch": 0.8391160456923241,
+      "grad_norm": 0.3238008916378021,
+      "learning_rate": 3.357970534924229e-07,
+      "loss": 0.544,
+      "step": 655
+    },
+    {
+      "epoch": 0.8455215116899755,
+      "grad_norm": 0.3207038938999176,
+      "learning_rate": 3.104276526061617e-07,
+      "loss": 0.5242,
+      "step": 660
+    },
+    {
+      "epoch": 0.8519269776876268,
+      "grad_norm": 0.38148337602615356,
+      "learning_rate": 2.859911070997437e-07,
+      "loss": 0.5358,
+      "step": 665
+    },
+    {
+      "epoch": 0.8583324436852781,
+      "grad_norm": 0.44874271750450134,
+      "learning_rate": 2.624978280303628e-07,
+      "loss": 0.5347,
+      "step": 670
+    },
+    {
+      "epoch": 0.8647379096829294,
+      "grad_norm": 0.3957948684692383,
+      "learning_rate": 2.3995782458168276e-07,
+      "loss": 0.5401,
+      "step": 675
+    },
+    {
+      "epoch": 0.8711433756805808,
+      "grad_norm": 0.398444265127182,
+      "learning_rate": 2.1838069979947945e-07,
+      "loss": 0.524,
+      "step": 680
+    },
+    {
+      "epoch": 0.8775488416782321,
+      "grad_norm": 0.37134161591529846,
+      "learning_rate": 1.9777564650031112e-07,
+      "loss": 0.535,
+      "step": 685
+    },
+    {
+      "epoch": 0.8839543076758835,
+      "grad_norm": 0.37950778007507324,
+      "learning_rate": 1.7815144335497524e-07,
+      "loss": 0.5358,
+      "step": 690
+    },
+    {
+      "epoch": 0.8903597736735348,
+      "grad_norm": 0.4200168251991272,
+      "learning_rate": 1.5951645114839875e-07,
+      "loss": 0.5234,
+      "step": 695
+    },
+    {
+      "epoch": 0.896765239671186,
+      "grad_norm": 0.3997882008552551,
+      "learning_rate": 1.4187860921757252e-07,
+      "loss": 0.5437,
+      "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": 1.287549295748481e+18,
+  "train_batch_size": 1,
+  "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:e6ab62dc3c7f9559b1b95a7ccd05854841e1eab0bda7a9f430097903d36e75bf
+size 6417

checkpoint-750/README.md

@@ -0,0 +1,209 @@
+---
+base_model: unsloth/Qwen3-8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-8B
+- 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/Qwen3-8B",
+  "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": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj",
+    "down_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 sha256:96e8f8bde21b609b8852b080fa71ef24d8bb651a686173d942307540247e5c11
+size 698419728

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 sha256:6be317716be9b7b39caaf51a9cbcd5809e82b412ad466a1dd91222f60c87106a
+size 1397129547

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": 0.9608198996476993,
+  "eval_steps": 25,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0064054659976513295,
+      "grad_norm": 1.095150351524353,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.9763,
+      "step": 5
+    },
+    {
+      "epoch": 0.012810931995302659,
+      "grad_norm": 1.0511373281478882,
+      "learning_rate": 2.25e-06,
+      "loss": 0.9023,
+      "step": 10
+    },
+    {
+      "epoch": 0.019216397992953986,
+      "grad_norm": 0.817418098449707,
+      "learning_rate": 3.5e-06,
+      "loss": 0.9288,
+      "step": 15
+    },
+    {
+      "epoch": 0.025621863990605318,
+      "grad_norm": 0.624769926071167,
+      "learning_rate": 4.75e-06,
+      "loss": 0.8766,
+      "step": 20
+    },
+    {
+      "epoch": 0.03202732998825664,
+      "grad_norm": 0.5237262845039368,
+      "learning_rate": 4.999659159998194e-06,
+      "loss": 0.8411,
+      "step": 25
+    },
+    {
+      "epoch": 0.03843279598590797,
+      "grad_norm": 0.46350979804992676,
+      "learning_rate": 4.998274656771894e-06,
+      "loss": 0.8132,
+      "step": 30
+    },
+    {
+      "epoch": 0.0448382619835593,
+      "grad_norm": 0.3592084050178528,
+      "learning_rate": 4.995825777227236e-06,
+      "loss": 0.7663,
+      "step": 35
+    },
+    {
+      "epoch": 0.051243727981210636,
+      "grad_norm": 0.34569790959358215,
+      "learning_rate": 4.992313564696022e-06,
+      "loss": 0.7355,
+      "step": 40
+    },
+    {
+      "epoch": 0.057649193978861965,
+      "grad_norm": 0.2865957021713257,
+      "learning_rate": 4.9877395155372815e-06,
+      "loss": 0.7632,
+      "step": 45
+    },
+    {
+      "epoch": 0.06405465997651329,
+      "grad_norm": 0.25277993083000183,
+      "learning_rate": 4.982105578499759e-06,
+      "loss": 0.7539,
+      "step": 50
+    },
+    {
+      "epoch": 0.07046012597416462,
+      "grad_norm": 0.24113819003105164,
+      "learning_rate": 4.975414153891664e-06,
+      "loss": 0.7322,
+      "step": 55
+    },
+    {
+      "epoch": 0.07686559197181594,
+      "grad_norm": 0.2370101362466812,
+      "learning_rate": 4.967668092558024e-06,
+      "loss": 0.7242,
+      "step": 60
+    },
+    {
+      "epoch": 0.08327105796946728,
+      "grad_norm": 0.23438391089439392,
+      "learning_rate": 4.9588706946661066e-06,
+      "loss": 0.6943,
+      "step": 65
+    },
+    {
+      "epoch": 0.0896765239671186,
+      "grad_norm": 0.24512864649295807,
+      "learning_rate": 4.949025708299395e-06,
+      "loss": 0.6866,
+      "step": 70
+    },
+    {
+      "epoch": 0.09608198996476994,
+      "grad_norm": 0.22728285193443298,
+      "learning_rate": 4.93813732786074e-06,
+      "loss": 0.6658,
+      "step": 75
+    },
+    {
+      "epoch": 0.10248745596242127,
+      "grad_norm": 0.2585676610469818,
+      "learning_rate": 4.926210192285359e-06,
+      "loss": 0.7284,
+      "step": 80
+    },
+    {
+      "epoch": 0.1088929219600726,
+      "grad_norm": 0.2257288247346878,
+      "learning_rate": 4.913249383064438e-06,
+      "loss": 0.6844,
+      "step": 85
+    },
+    {
+      "epoch": 0.11529838795772393,
+      "grad_norm": 0.2544812262058258,
+      "learning_rate": 4.899260422080195e-06,
+      "loss": 0.6872,
+      "step": 90
+    },
+    {
+      "epoch": 0.12170385395537525,
+      "grad_norm": 0.23987820744514465,
+      "learning_rate": 4.884249269253309e-06,
+      "loss": 0.6438,
+      "step": 95
+    },
+    {
+      "epoch": 0.12810931995302657,
+      "grad_norm": 0.28527575731277466,
+      "learning_rate": 4.868222320003731e-06,
+      "loss": 0.656,
+      "step": 100
+    },
+    {
+      "epoch": 0.13451478595067792,
+      "grad_norm": 0.25415557622909546,
+      "learning_rate": 4.851186402525946e-06,
+      "loss": 0.6562,
+      "step": 105
+    },
+    {
+      "epoch": 0.14092025194832924,
+      "grad_norm": 0.21308082342147827,
+      "learning_rate": 4.8331487748798636e-06,
+      "loss": 0.6569,
+      "step": 110
+    },
+    {
+      "epoch": 0.14732571794598057,
+      "grad_norm": 0.23867692053318024,
+      "learning_rate": 4.814117121898554e-06,
+      "loss": 0.6158,
+      "step": 115
+    },
+    {
+      "epoch": 0.1537311839436319,
+      "grad_norm": 0.23583965003490448,
+      "learning_rate": 4.794099551914173e-06,
+      "loss": 0.6084,
+      "step": 120
+    },
+    {
+      "epoch": 0.16013664994128324,
+      "grad_norm": 0.22881825268268585,
+      "learning_rate": 4.773104593303449e-06,
+      "loss": 0.6778,
+      "step": 125
+    },
+    {
+      "epoch": 0.16654211593893456,
+      "grad_norm": 0.24278834462165833,
+      "learning_rate": 4.751141190854214e-06,
+      "loss": 0.6071,
+      "step": 130
+    },
+    {
+      "epoch": 0.17294758193658588,
+      "grad_norm": 0.2911915183067322,
+      "learning_rate": 4.728218701954525e-06,
+      "loss": 0.6543,
+      "step": 135
+    },
+    {
+      "epoch": 0.1793530479342372,
+      "grad_norm": 0.2795209586620331,
+      "learning_rate": 4.704346892606001e-06,
+      "loss": 0.5956,
+      "step": 140
+    },
+    {
+      "epoch": 0.18575851393188855,
+      "grad_norm": 0.25558847188949585,
+      "learning_rate": 4.6795359332630694e-06,
+      "loss": 0.6395,
+      "step": 145
+    },
+    {
+      "epoch": 0.19216397992953987,
+      "grad_norm": 0.2465032935142517,
+      "learning_rate": 4.653796394499904e-06,
+      "loss": 0.6136,
+      "step": 150
+    },
+    {
+      "epoch": 0.1985694459271912,
+      "grad_norm": 0.244729146361351,
+      "learning_rate": 4.627139242506882e-06,
+      "loss": 0.6046,
+      "step": 155
+    },
+    {
+      "epoch": 0.20497491192484255,
+      "grad_norm": 0.2569523751735687,
+      "learning_rate": 4.599575834418505e-06,
+      "loss": 0.6483,
+      "step": 160
+    },
+    {
+      "epoch": 0.21138037792249387,
+      "grad_norm": 0.29486870765686035,
+      "learning_rate": 4.571117913474749e-06,
+      "loss": 0.6034,
+      "step": 165
+    },
+    {
+      "epoch": 0.2177858439201452,
+      "grad_norm": 0.26274922490119934,
+      "learning_rate": 4.541777604017924e-06,
+      "loss": 0.5834,
+      "step": 170
+    },
+    {
+      "epoch": 0.2241913099177965,
+      "grad_norm": 0.2968301773071289,
+      "learning_rate": 4.511567406327162e-06,
+      "loss": 0.6063,
+      "step": 175
+    },
+    {
+      "epoch": 0.23059677591544786,
+      "grad_norm": 0.301880419254303,
+      "learning_rate": 4.480500191292744e-06,
+      "loss": 0.5965,
+      "step": 180
+    },
+    {
+      "epoch": 0.23700224191309918,
+      "grad_norm": 0.27574408054351807,
+      "learning_rate": 4.448589194932521e-06,
+      "loss": 0.5959,
+      "step": 185
+    },
+    {
+      "epoch": 0.2434077079107505,
+      "grad_norm": 0.25683072209358215,
+      "learning_rate": 4.415848012752789e-06,
+      "loss": 0.5764,
+      "step": 190
+    },
+    {
+      "epoch": 0.24981317390840183,
+      "grad_norm": 0.3023504912853241,
+      "learning_rate": 4.38229059395599e-06,
+      "loss": 0.6013,
+      "step": 195
+    },
+    {
+      "epoch": 0.25621863990605315,
+      "grad_norm": 0.2837856113910675,
+      "learning_rate": 4.347931235497738e-06,
+      "loss": 0.6044,
+      "step": 200
+    },
+    {
+      "epoch": 0.2626241059037045,
+      "grad_norm": 0.29550132155418396,
+      "learning_rate": 4.312784575995669e-06,
+      "loss": 0.5866,
+      "step": 205
+    },
+    {
+      "epoch": 0.26902957190135585,
+      "grad_norm": 0.28646326065063477,
+      "learning_rate": 4.276865589492747e-06,
+      "loss": 0.5838,
+      "step": 210
+    },
+    {
+      "epoch": 0.27543503789900714,
+      "grad_norm": 0.3569891154766083,
+      "learning_rate": 4.240189579077649e-06,
+      "loss": 0.5701,
+      "step": 215
+    },
+    {
+      "epoch": 0.2818405038966585,
+      "grad_norm": 0.33763790130615234,
+      "learning_rate": 4.202772170364969e-06,
+      "loss": 0.5759,
+      "step": 220
+    },
+    {
+      "epoch": 0.2882459698943098,
+      "grad_norm": 0.245514377951622,
+      "learning_rate": 4.164629304838012e-06,
+      "loss": 0.5694,
+      "step": 225
+    },
+    {
+      "epoch": 0.29465143589196113,
+      "grad_norm": 0.2917734682559967,
+      "learning_rate": 4.125777233057007e-06,
+      "loss": 0.5944,
+      "step": 230
+    },
+    {
+      "epoch": 0.3010569018896125,
+      "grad_norm": 0.2828243374824524,
+      "learning_rate": 4.086232507735648e-06,
+      "loss": 0.5717,
+      "step": 235
+    },
+    {
+      "epoch": 0.3074623678872638,
+      "grad_norm": 0.38584598898887634,
+      "learning_rate": 4.0460119766889e-06,
+      "loss": 0.5931,
+      "step": 240
+    },
+    {
+      "epoch": 0.3138678338849151,
+      "grad_norm": 0.36006131768226624,
+      "learning_rate": 4.005132775655076e-06,
+      "loss": 0.5564,
+      "step": 245
+    },
+    {
+      "epoch": 0.3202732998825665,
+      "grad_norm": 0.372942179441452,
+      "learning_rate": 3.963612320995257e-06,
+      "loss": 0.6025,
+      "step": 250
+    },
+    {
+      "epoch": 0.32667876588021777,
+      "grad_norm": 0.28577810525894165,
+      "learning_rate": 3.921468302273137e-06,
+      "loss": 0.5469,
+      "step": 255
+    },
+    {
+      "epoch": 0.3330842318778691,
+      "grad_norm": 0.3417142331600189,
+      "learning_rate": 3.8787186747184826e-06,
+      "loss": 0.5342,
+      "step": 260
+    },
+    {
+      "epoch": 0.33948969787552047,
+      "grad_norm": 0.35277873277664185,
+      "learning_rate": 3.8353816515774115e-06,
+      "loss": 0.5531,
+      "step": 265
+    },
+    {
+      "epoch": 0.34589516387317176,
+      "grad_norm": 0.2886194586753845,
+      "learning_rate": 3.79147569635273e-06,
+      "loss": 0.5431,
+      "step": 270
+    },
+    {
+      "epoch": 0.3523006298708231,
+      "grad_norm": 0.29417017102241516,
+      "learning_rate": 3.747019514937663e-06,
+      "loss": 0.5826,
+      "step": 275
+    },
+    {
+      "epoch": 0.3587060958684744,
+      "grad_norm": 0.3237856924533844,
+      "learning_rate": 3.70203204764631e-06,
+      "loss": 0.5689,
+      "step": 280
+    },
+    {
+      "epoch": 0.36511156186612576,
+      "grad_norm": 0.3846990168094635,
+      "learning_rate": 3.6565324611442234e-06,
+      "loss": 0.5763,
+      "step": 285
+    },
+    {
+      "epoch": 0.3715170278637771,
+      "grad_norm": 0.2781718969345093,
+      "learning_rate": 3.6105401402825595e-06,
+      "loss": 0.5549,
+      "step": 290
+    },
+    {
+      "epoch": 0.3779224938614284,
+      "grad_norm": 0.2733434736728668,
+      "learning_rate": 3.5640746798392657e-06,
+      "loss": 0.5967,
+      "step": 295
+    },
+    {
+      "epoch": 0.38432795985907975,
+      "grad_norm": 0.34851792454719543,
+      "learning_rate": 3.5171558761708334e-06,
+      "loss": 0.5543,
+      "step": 300
+    },
+    {
+      "epoch": 0.3907334258567311,
+      "grad_norm": 0.34361544251441956,
+      "learning_rate": 3.469803718778166e-06,
+      "loss": 0.5519,
+      "step": 305
+    },
+    {
+      "epoch": 0.3971388918543824,
+      "grad_norm": 0.2903674244880676,
+      "learning_rate": 3.4220383817901625e-06,
+      "loss": 0.562,
+      "step": 310
+    },
+    {
+      "epoch": 0.40354435785203374,
+      "grad_norm": 0.31230857968330383,
+      "learning_rate": 3.3738802153686414e-06,
+      "loss": 0.5537,
+      "step": 315
+    },
+    {
+      "epoch": 0.4099498238496851,
+      "grad_norm": 0.31388580799102783,
+      "learning_rate": 3.3253497370382605e-06,
+      "loss": 0.5551,
+      "step": 320
+    },
+    {
+      "epoch": 0.4163552898473364,
+      "grad_norm": 0.32741594314575195,
+      "learning_rate": 3.2764676229451397e-06,
+      "loss": 0.5498,
+      "step": 325
+    },
+    {
+      "epoch": 0.42276075584498773,
+      "grad_norm": 0.2511857748031616,
+      "learning_rate": 3.227254699047904e-06,
+      "loss": 0.5511,
+      "step": 330
+    },
+    {
+      "epoch": 0.42916622184263903,
+      "grad_norm": 0.3877544105052948,
+      "learning_rate": 3.177731932244892e-06,
+      "loss": 0.5485,
+      "step": 335
+    },
+    {
+      "epoch": 0.4355716878402904,
+      "grad_norm": 0.3445497751235962,
+      "learning_rate": 3.127920421441327e-06,
+      "loss": 0.5639,
+      "step": 340
+    },
+    {
+      "epoch": 0.4419771538379417,
+      "grad_norm": 0.3347369432449341,
+      "learning_rate": 3.077841388560243e-06,
+      "loss": 0.5745,
+      "step": 345
+    },
+    {
+      "epoch": 0.448382619835593,
+      "grad_norm": 0.36205726861953735,
+      "learning_rate": 3.0275161695009975e-06,
+      "loss": 0.5658,
+      "step": 350
+    },
+    {
+      "epoch": 0.45478808583324437,
+      "grad_norm": 0.35722121596336365,
+      "learning_rate": 2.9769662050492276e-06,
+      "loss": 0.5479,
+      "step": 355
+    },
+    {
+      "epoch": 0.4611935518308957,
+      "grad_norm": 0.35634711384773254,
+      "learning_rate": 2.926213031742125e-06,
+      "loss": 0.5595,
+      "step": 360
+    },
+    {
+      "epoch": 0.467599017828547,
+      "grad_norm": 0.32853105664253235,
+      "learning_rate": 2.8752782726929045e-06,
+      "loss": 0.5429,
+      "step": 365
+    },
+    {
+      "epoch": 0.47400448382619836,
+      "grad_norm": 0.3939530551433563,
+      "learning_rate": 2.8241836283784026e-06,
+      "loss": 0.531,
+      "step": 370
+    },
+    {
+      "epoch": 0.48040994982384966,
+      "grad_norm": 0.3002113699913025,
+      "learning_rate": 2.7729508673936972e-06,
+      "loss": 0.5596,
+      "step": 375
+    },
+    {
+      "epoch": 0.486815415821501,
+      "grad_norm": 0.3216375708580017,
+      "learning_rate": 2.721601817177725e-06,
+      "loss": 0.5292,
+      "step": 380
+    },
+    {
+      "epoch": 0.49322088181915236,
+      "grad_norm": 0.3263518810272217,
+      "learning_rate": 2.6701583547138165e-06,
+      "loss": 0.5684,
+      "step": 385
+    },
+    {
+      "epoch": 0.49962634781680365,
+      "grad_norm": 0.3253946900367737,
+      "learning_rate": 2.618642397209126e-06,
+      "loss": 0.5264,
+      "step": 390
+    },
+    {
+      "epoch": 0.5060318138144551,
+      "grad_norm": 0.3231858015060425,
+      "learning_rate": 2.567075892756924e-06,
+      "loss": 0.5448,
+      "step": 395
+    },
+    {
+      "epoch": 0.5124372798121063,
+      "grad_norm": 0.36590418219566345,
+      "learning_rate": 2.5154808109857367e-06,
+      "loss": 0.5248,
+      "step": 400
+    },
+    {
+      "epoch": 0.5188427458097576,
+      "grad_norm": 0.3773280084133148,
+      "learning_rate": 2.4638791336992967e-06,
+      "loss": 0.5505,
+      "step": 405
+    },
+    {
+      "epoch": 0.525248211807409,
+      "grad_norm": 0.3829450309276581,
+      "learning_rate": 2.4122928455113233e-06,
+      "loss": 0.5466,
+      "step": 410
+    },
+    {
+      "epoch": 0.5316536778050603,
+      "grad_norm": 0.3306972086429596,
+      "learning_rate": 2.360743924479093e-06,
+      "loss": 0.5721,
+      "step": 415
+    },
+    {
+      "epoch": 0.5380591438027117,
+      "grad_norm": 0.32845625281333923,
+      "learning_rate": 2.3092543327398083e-06,
+      "loss": 0.5177,
+      "step": 420
+    },
+    {
+      "epoch": 0.5444646098003629,
+      "grad_norm": 0.3088594079017639,
+      "learning_rate": 2.2578460071537512e-06,
+      "loss": 0.5575,
+      "step": 425
+    },
+    {
+      "epoch": 0.5508700757980143,
+      "grad_norm": 0.3912436366081238,
+      "learning_rate": 2.2065408499582e-06,
+      "loss": 0.561,
+      "step": 430
+    },
+    {
+      "epoch": 0.5572755417956656,
+      "grad_norm": 0.3839537799358368,
+      "learning_rate": 2.155360719436102e-06,
+      "loss": 0.526,
+      "step": 435
+    },
+    {
+      "epoch": 0.563681007793317,
+      "grad_norm": 0.3676234185695648,
+      "learning_rate": 2.1043274206034727e-06,
+      "loss": 0.541,
+      "step": 440
+    },
+    {
+      "epoch": 0.5700864737909683,
+      "grad_norm": 0.368198424577713,
+      "learning_rate": 2.0534626959194816e-06,
+      "loss": 0.5212,
+      "step": 445
+    },
+    {
+      "epoch": 0.5764919397886196,
+      "grad_norm": 0.34693998098373413,
+      "learning_rate": 2.002788216023203e-06,
+      "loss": 0.5462,
+      "step": 450
+    },
+    {
+      "epoch": 0.5828974057862709,
+      "grad_norm": 0.37934619188308716,
+      "learning_rate": 1.9523255705009558e-06,
+      "loss": 0.5423,
+      "step": 455
+    },
+    {
+      "epoch": 0.5893028717839223,
+      "grad_norm": 0.3458510637283325,
+      "learning_rate": 1.902096258688174e-06,
+      "loss": 0.4889,
+      "step": 460
+    },
+    {
+      "epoch": 0.5957083377815736,
+      "grad_norm": 0.33206406235694885,
+      "learning_rate": 1.8521216805097358e-06,
+      "loss": 0.5378,
+      "step": 465
+    },
+    {
+      "epoch": 0.602113803779225,
+      "grad_norm": 0.29139187932014465,
+      "learning_rate": 1.8024231273626424e-06,
+      "loss": 0.5444,
+      "step": 470
+    },
+    {
+      "epoch": 0.6085192697768763,
+      "grad_norm": 0.3665342926979065,
+      "learning_rate": 1.7530217730449312e-06,
+      "loss": 0.5276,
+      "step": 475
+    },
+    {
+      "epoch": 0.6149247357745276,
+      "grad_norm": 0.32149678468704224,
+      "learning_rate": 1.7039386647346975e-06,
+      "loss": 0.5117,
+      "step": 480
+    },
+    {
+      "epoch": 0.6213302017721789,
+      "grad_norm": 0.30389899015426636,
+      "learning_rate": 1.6551947140230568e-06,
+      "loss": 0.5573,
+      "step": 485
+    },
+    {
+      "epoch": 0.6277356677698303,
+      "grad_norm": 0.3890632688999176,
+      "learning_rate": 1.6068106880048747e-06,
+      "loss": 0.5395,
+      "step": 490
+    },
+    {
+      "epoch": 0.6341411337674816,
+      "grad_norm": 0.36464181542396545,
+      "learning_rate": 1.5588072004310634e-06,
+      "loss": 0.5497,
+      "step": 495
+    },
+    {
+      "epoch": 0.640546599765133,
+      "grad_norm": 0.32058826088905334,
+      "learning_rate": 1.5112047029262e-06,
+      "loss": 0.5377,
+      "step": 500
+    },
+    {
+      "epoch": 0.6469520657627842,
+      "grad_norm": 0.280649870634079,
+      "learning_rate": 1.4640234762752248e-06,
+      "loss": 0.5349,
+      "step": 505
+    },
+    {
+      "epoch": 0.6533575317604355,
+      "grad_norm": 0.36669427156448364,
+      "learning_rate": 1.4172836217829267e-06,
+      "loss": 0.539,
+      "step": 510
+    },
+    {
+      "epoch": 0.6597629977580869,
+      "grad_norm": 0.3747427463531494,
+      "learning_rate": 1.3710050527098867e-06,
+      "loss": 0.5582,
+      "step": 515
+    },
+    {
+      "epoch": 0.6661684637557382,
+      "grad_norm": 0.3354856073856354,
+      "learning_rate": 1.3252074857885453e-06,
+      "loss": 0.5512,
+      "step": 520
+    },
+    {
+      "epoch": 0.6725739297533896,
+      "grad_norm": 0.3852190673351288,
+      "learning_rate": 1.2799104328229928e-06,
+      "loss": 0.5216,
+      "step": 525
+    },
+    {
+      "epoch": 0.6789793957510409,
+      "grad_norm": 0.3479975759983063,
+      "learning_rate": 1.2351331923760743e-06,
+      "loss": 0.518,
+      "step": 530
+    },
+    {
+      "epoch": 0.6853848617486922,
+      "grad_norm": 0.37335509061813354,
+      "learning_rate": 1.1908948415473418e-06,
+      "loss": 0.5203,
+      "step": 535
+    },
+    {
+      "epoch": 0.6917903277463435,
+      "grad_norm": 0.4034595489501953,
+      "learning_rate": 1.1472142278453582e-06,
+      "loss": 0.5157,
+      "step": 540
+    },
+    {
+      "epoch": 0.6981957937439949,
+      "grad_norm": 0.2966196537017822,
+      "learning_rate": 1.1041099611578177e-06,
+      "loss": 0.541,
+      "step": 545
+    },
+    {
+      "epoch": 0.7046012597416462,
+      "grad_norm": 0.3616897463798523,
+      "learning_rate": 1.0616004058229084e-06,
+      "loss": 0.5254,
+      "step": 550
+    },
+    {
+      "epoch": 0.7110067257392976,
+      "grad_norm": 0.3452332317829132,
+      "learning_rate": 1.0197036728052847e-06,
+      "loss": 0.5543,
+      "step": 555
+    },
+    {
+      "epoch": 0.7174121917369488,
+      "grad_norm": 0.3313845694065094,
+      "learning_rate": 9.784376119799851e-07,
+      "loss": 0.5294,
+      "step": 560
+    },
+    {
+      "epoch": 0.7238176577346002,
+      "grad_norm": 0.37989768385887146,
+      "learning_rate": 9.378198045275968e-07,
+      "loss": 0.5411,
+      "step": 565
+    },
+    {
+      "epoch": 0.7302231237322515,
+      "grad_norm": 0.3642790913581848,
+      "learning_rate": 8.97867555443886e-07,
+      "loss": 0.5186,
+      "step": 570
+    },
+    {
+      "epoch": 0.7366285897299029,
+      "grad_norm": 0.369183748960495,
+      "learning_rate": 8.585978861670958e-07,
+      "loss": 0.5189,
+      "step": 575
+    },
+    {
+      "epoch": 0.7430340557275542,
+      "grad_norm": 0.3428362011909485,
+      "learning_rate": 8.200275273260611e-07,
+      "loss": 0.5326,
+      "step": 580
+    },
+    {
+      "epoch": 0.7494395217252056,
+      "grad_norm": 0.33693212270736694,
+      "learning_rate": 7.821729116122126e-07,
+      "loss": 0.5417,
+      "step": 585
+    },
+    {
+      "epoch": 0.7558449877228568,
+      "grad_norm": 0.35541847348213196,
+      "learning_rate": 7.450501667785146e-07,
+      "loss": 0.531,
+      "step": 590
+    },
+    {
+      "epoch": 0.7622504537205081,
+      "grad_norm": 0.3545955717563629,
+      "learning_rate": 7.086751087683297e-07,
+      "loss": 0.5371,
+      "step": 595
+    },
+    {
+      "epoch": 0.7686559197181595,
+      "grad_norm": 0.369098424911499,
+      "learning_rate": 6.730632349771193e-07,
+      "loss": 0.5444,
+      "step": 600
+    },
+    {
+      "epoch": 0.7750613857158108,
+      "grad_norm": 0.395386666059494,
+      "learning_rate": 6.3822971764986e-07,
+      "loss": 0.5207,
+      "step": 605
+    },
+    {
+      "epoch": 0.7814668517134622,
+      "grad_norm": 0.3929295241832733,
+      "learning_rate": 6.041893974169963e-07,
+      "loss": 0.5223,
+      "step": 610
+    },
+    {
+      "epoch": 0.7878723177111134,
+      "grad_norm": 0.38200634717941284,
+      "learning_rate": 5.709567769716678e-07,
+      "loss": 0.5346,
+      "step": 615
+    },
+    {
+      "epoch": 0.7942777837087648,
+      "grad_norm": 0.35260388255119324,
+      "learning_rate": 5.385460148909169e-07,
+      "loss": 0.5106,
+      "step": 620
+    },
+    {
+      "epoch": 0.8006832497064161,
+      "grad_norm": 0.36902984976768494,
+      "learning_rate": 5.069709196035011e-07,
+      "loss": 0.5333,
+      "step": 625
+    },
+    {
+      "epoch": 0.8070887157040675,
+      "grad_norm": 0.36749160289764404,
+      "learning_rate": 4.762449435068914e-07,
+      "loss": 0.5197,
+      "step": 630
+    },
+    {
+      "epoch": 0.8134941817017188,
+      "grad_norm": 0.37014660239219666,
+      "learning_rate": 4.4638117723595054e-07,
+      "loss": 0.5492,
+      "step": 635
+    },
+    {
+      "epoch": 0.8198996476993702,
+      "grad_norm": 0.3781520426273346,
+      "learning_rate": 4.173923440857358e-07,
+      "loss": 0.5365,
+      "step": 640
+    },
+    {
+      "epoch": 0.8263051136970214,
+      "grad_norm": 0.33049196004867554,
+      "learning_rate": 3.892907945908128e-07,
+      "loss": 0.5163,
+      "step": 645
+    },
+    {
+      "epoch": 0.8327105796946728,
+      "grad_norm": 0.40030181407928467,
+      "learning_rate": 3.6208850126337595e-07,
+      "loss": 0.5111,
+      "step": 650
+    },
+    {
+      "epoch": 0.8391160456923241,
+      "grad_norm": 0.3238008916378021,
+      "learning_rate": 3.357970534924229e-07,
+      "loss": 0.544,
+      "step": 655
+    },
+    {
+      "epoch": 0.8455215116899755,
+      "grad_norm": 0.3207038938999176,
+      "learning_rate": 3.104276526061617e-07,
+      "loss": 0.5242,
+      "step": 660
+    },
+    {
+      "epoch": 0.8519269776876268,
+      "grad_norm": 0.38148337602615356,
+      "learning_rate": 2.859911070997437e-07,
+      "loss": 0.5358,
+      "step": 665
+    },
+    {
+      "epoch": 0.8583324436852781,
+      "grad_norm": 0.44874271750450134,
+      "learning_rate": 2.624978280303628e-07,
+      "loss": 0.5347,
+      "step": 670
+    },
+    {
+      "epoch": 0.8647379096829294,
+      "grad_norm": 0.3957948684692383,
+      "learning_rate": 2.3995782458168276e-07,
+      "loss": 0.5401,
+      "step": 675
+    },
+    {
+      "epoch": 0.8711433756805808,
+      "grad_norm": 0.398444265127182,
+      "learning_rate": 2.1838069979947945e-07,
+      "loss": 0.524,
+      "step": 680
+    },
+    {
+      "epoch": 0.8775488416782321,
+      "grad_norm": 0.37134161591529846,
+      "learning_rate": 1.9777564650031112e-07,
+      "loss": 0.535,
+      "step": 685
+    },
+    {
+      "epoch": 0.8839543076758835,
+      "grad_norm": 0.37950778007507324,
+      "learning_rate": 1.7815144335497524e-07,
+      "loss": 0.5358,
+      "step": 690
+    },
+    {
+      "epoch": 0.8903597736735348,
+      "grad_norm": 0.4200168251991272,
+      "learning_rate": 1.5951645114839875e-07,
+      "loss": 0.5234,
+      "step": 695
+    },
+    {
+      "epoch": 0.896765239671186,
+      "grad_norm": 0.3997882008552551,
+      "learning_rate": 1.4187860921757252e-07,
+      "loss": 0.5437,
+      "step": 700
+    },
+    {
+      "epoch": 0.9031707056688374,
+      "grad_norm": 0.405408650636673,
+      "learning_rate": 1.2524543206904188e-07,
+      "loss": 0.5443,
+      "step": 705
+    },
+    {
+      "epoch": 0.9095761716664887,
+      "grad_norm": 0.368826299905777,
+      "learning_rate": 1.0962400617738872e-07,
+      "loss": 0.564,
+      "step": 710
+    },
+    {
+      "epoch": 0.9159816376641401,
+      "grad_norm": 0.41221150755882263,
+      "learning_rate": 9.502098696608147e-08,
+      "loss": 0.5288,
+      "step": 715
+    },
+    {
+      "epoch": 0.9223871036617914,
+      "grad_norm": 0.30681097507476807,
+      "learning_rate": 8.144259597196308e-08,
+      "loss": 0.5356,
+      "step": 720
+    },
+    {
+      "epoch": 0.9287925696594427,
+      "grad_norm": 0.3287171423435211,
+      "learning_rate": 6.889461819460485e-08,
+      "loss": 0.5228,
+      "step": 725
+    },
+    {
+      "epoch": 0.935198035657094,
+      "grad_norm": 0.39335137605667114,
+      "learning_rate": 5.738239963163472e-08,
+      "loss": 0.5102,
+      "step": 730
+    },
+    {
+      "epoch": 0.9416035016547454,
+      "grad_norm": 0.5197286605834961,
+      "learning_rate": 4.691084500110521e-08,
+      "loss": 0.5134,
+      "step": 735
+    },
+    {
+      "epoch": 0.9480089676523967,
+      "grad_norm": 0.37825560569763184,
+      "learning_rate": 3.748441565186583e-08,
+      "loss": 0.495,
+      "step": 740
+    },
+    {
+      "epoch": 0.9544144336500481,
+      "grad_norm": 0.39631250500679016,
+      "learning_rate": 2.910712766282908e-08,
+      "loss": 0.5227,
+      "step": 745
+    },
+    {
+      "epoch": 0.9608198996476993,
+      "grad_norm": 0.40286198258399963,
+      "learning_rate": 2.178255013194075e-08,
+      "loss": 0.5142,
+      "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": 1.378422924703187e+18,
+  "train_batch_size": 1,
+  "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:e6ab62dc3c7f9559b1b95a7ccd05854841e1eab0bda7a9f430097903d36e75bf
+size 6417

checkpoint-781/README.md

@@ -0,0 +1,209 @@
+---
+base_model: unsloth/Qwen3-8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen3-8B
+- 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/Qwen3-8B",
+  "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": [
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj",
+    "down_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:d49a26e0f493334f0e4e5acd00b3036faf9c449af09b0cf839d72bd9c22af001
+size 698419728

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 sha256:9059c42e58cc18f4f8db36844e008e233383dfc31e621b6c3e4bdd15b1cc9033
+size 1397129547

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": 0.0064054659976513295,
+      "grad_norm": 1.095150351524353,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.9763,
+      "step": 5
+    },
+    {
+      "epoch": 0.012810931995302659,
+      "grad_norm": 1.0511373281478882,
+      "learning_rate": 2.25e-06,
+      "loss": 0.9023,
+      "step": 10
+    },
+    {
+      "epoch": 0.019216397992953986,
+      "grad_norm": 0.817418098449707,
+      "learning_rate": 3.5e-06,
+      "loss": 0.9288,
+      "step": 15
+    },
+    {
+      "epoch": 0.025621863990605318,
+      "grad_norm": 0.624769926071167,
+      "learning_rate": 4.75e-06,
+      "loss": 0.8766,
+      "step": 20
+    },
+    {
+      "epoch": 0.03202732998825664,
+      "grad_norm": 0.5237262845039368,
+      "learning_rate": 4.999659159998194e-06,
+      "loss": 0.8411,
+      "step": 25
+    },
+    {
+      "epoch": 0.03843279598590797,
+      "grad_norm": 0.46350979804992676,
+      "learning_rate": 4.998274656771894e-06,
+      "loss": 0.8132,
+      "step": 30
+    },
+    {
+      "epoch": 0.0448382619835593,
+      "grad_norm": 0.3592084050178528,
+      "learning_rate": 4.995825777227236e-06,
+      "loss": 0.7663,
+      "step": 35
+    },
+    {
+      "epoch": 0.051243727981210636,
+      "grad_norm": 0.34569790959358215,
+      "learning_rate": 4.992313564696022e-06,
+      "loss": 0.7355,
+      "step": 40
+    },
+    {
+      "epoch": 0.057649193978861965,
+      "grad_norm": 0.2865957021713257,
+      "learning_rate": 4.9877395155372815e-06,
+      "loss": 0.7632,
+      "step": 45
+    },
+    {
+      "epoch": 0.06405465997651329,
+      "grad_norm": 0.25277993083000183,
+      "learning_rate": 4.982105578499759e-06,
+      "loss": 0.7539,
+      "step": 50
+    },
+    {
+      "epoch": 0.07046012597416462,
+      "grad_norm": 0.24113819003105164,
+      "learning_rate": 4.975414153891664e-06,
+      "loss": 0.7322,
+      "step": 55
+    },
+    {
+      "epoch": 0.07686559197181594,
+      "grad_norm": 0.2370101362466812,
+      "learning_rate": 4.967668092558024e-06,
+      "loss": 0.7242,
+      "step": 60
+    },
+    {
+      "epoch": 0.08327105796946728,
+      "grad_norm": 0.23438391089439392,
+      "learning_rate": 4.9588706946661066e-06,
+      "loss": 0.6943,
+      "step": 65
+    },
+    {
+      "epoch": 0.0896765239671186,
+      "grad_norm": 0.24512864649295807,
+      "learning_rate": 4.949025708299395e-06,
+      "loss": 0.6866,
+      "step": 70
+    },
+    {
+      "epoch": 0.09608198996476994,
+      "grad_norm": 0.22728285193443298,
+      "learning_rate": 4.93813732786074e-06,
+      "loss": 0.6658,
+      "step": 75
+    },
+    {
+      "epoch": 0.10248745596242127,
+      "grad_norm": 0.2585676610469818,
+      "learning_rate": 4.926210192285359e-06,
+      "loss": 0.7284,
+      "step": 80
+    },
+    {
+      "epoch": 0.1088929219600726,
+      "grad_norm": 0.2257288247346878,
+      "learning_rate": 4.913249383064438e-06,
+      "loss": 0.6844,
+      "step": 85
+    },
+    {
+      "epoch": 0.11529838795772393,
+      "grad_norm": 0.2544812262058258,
+      "learning_rate": 4.899260422080195e-06,
+      "loss": 0.6872,
+      "step": 90
+    },
+    {
+      "epoch": 0.12170385395537525,
+      "grad_norm": 0.23987820744514465,
+      "learning_rate": 4.884249269253309e-06,
+      "loss": 0.6438,
+      "step": 95
+    },
+    {
+      "epoch": 0.12810931995302657,
+      "grad_norm": 0.28527575731277466,
+      "learning_rate": 4.868222320003731e-06,
+      "loss": 0.656,
+      "step": 100
+    },
+    {
+      "epoch": 0.13451478595067792,
+      "grad_norm": 0.25415557622909546,
+      "learning_rate": 4.851186402525946e-06,
+      "loss": 0.6562,
+      "step": 105
+    },
+    {
+      "epoch": 0.14092025194832924,
+      "grad_norm": 0.21308082342147827,
+      "learning_rate": 4.8331487748798636e-06,
+      "loss": 0.6569,
+      "step": 110
+    },
+    {
+      "epoch": 0.14732571794598057,
+      "grad_norm": 0.23867692053318024,
+      "learning_rate": 4.814117121898554e-06,
+      "loss": 0.6158,
+      "step": 115
+    },
+    {
+      "epoch": 0.1537311839436319,
+      "grad_norm": 0.23583965003490448,
+      "learning_rate": 4.794099551914173e-06,
+      "loss": 0.6084,
+      "step": 120
+    },
+    {
+      "epoch": 0.16013664994128324,
+      "grad_norm": 0.22881825268268585,
+      "learning_rate": 4.773104593303449e-06,
+      "loss": 0.6778,
+      "step": 125
+    },
+    {
+      "epoch": 0.16654211593893456,
+      "grad_norm": 0.24278834462165833,
+      "learning_rate": 4.751141190854214e-06,
+      "loss": 0.6071,
+      "step": 130
+    },
+    {
+      "epoch": 0.17294758193658588,
+      "grad_norm": 0.2911915183067322,
+      "learning_rate": 4.728218701954525e-06,
+      "loss": 0.6543,
+      "step": 135
+    },
+    {
+      "epoch": 0.1793530479342372,
+      "grad_norm": 0.2795209586620331,
+      "learning_rate": 4.704346892606001e-06,
+      "loss": 0.5956,
+      "step": 140
+    },
+    {
+      "epoch": 0.18575851393188855,
+      "grad_norm": 0.25558847188949585,
+      "learning_rate": 4.6795359332630694e-06,
+      "loss": 0.6395,
+      "step": 145
+    },
+    {
+      "epoch": 0.19216397992953987,
+      "grad_norm": 0.2465032935142517,
+      "learning_rate": 4.653796394499904e-06,
+      "loss": 0.6136,
+      "step": 150
+    },
+    {
+      "epoch": 0.1985694459271912,
+      "grad_norm": 0.244729146361351,
+      "learning_rate": 4.627139242506882e-06,
+      "loss": 0.6046,
+      "step": 155
+    },
+    {
+      "epoch": 0.20497491192484255,
+      "grad_norm": 0.2569523751735687,
+      "learning_rate": 4.599575834418505e-06,
+      "loss": 0.6483,
+      "step": 160
+    },
+    {
+      "epoch": 0.21138037792249387,
+      "grad_norm": 0.29486870765686035,
+      "learning_rate": 4.571117913474749e-06,
+      "loss": 0.6034,
+      "step": 165
+    },
+    {
+      "epoch": 0.2177858439201452,
+      "grad_norm": 0.26274922490119934,
+      "learning_rate": 4.541777604017924e-06,
+      "loss": 0.5834,
+      "step": 170
+    },
+    {
+      "epoch": 0.2241913099177965,
+      "grad_norm": 0.2968301773071289,
+      "learning_rate": 4.511567406327162e-06,
+      "loss": 0.6063,
+      "step": 175
+    },
+    {
+      "epoch": 0.23059677591544786,
+      "grad_norm": 0.301880419254303,
+      "learning_rate": 4.480500191292744e-06,
+      "loss": 0.5965,
+      "step": 180
+    },
+    {
+      "epoch": 0.23700224191309918,
+      "grad_norm": 0.27574408054351807,
+      "learning_rate": 4.448589194932521e-06,
+      "loss": 0.5959,
+      "step": 185
+    },
+    {
+      "epoch": 0.2434077079107505,
+      "grad_norm": 0.25683072209358215,
+      "learning_rate": 4.415848012752789e-06,
+      "loss": 0.5764,
+      "step": 190
+    },
+    {
+      "epoch": 0.24981317390840183,
+      "grad_norm": 0.3023504912853241,
+      "learning_rate": 4.38229059395599e-06,
+      "loss": 0.6013,
+      "step": 195
+    },
+    {
+      "epoch": 0.25621863990605315,
+      "grad_norm": 0.2837856113910675,
+      "learning_rate": 4.347931235497738e-06,
+      "loss": 0.6044,
+      "step": 200
+    },
+    {
+      "epoch": 0.2626241059037045,
+      "grad_norm": 0.29550132155418396,
+      "learning_rate": 4.312784575995669e-06,
+      "loss": 0.5866,
+      "step": 205
+    },
+    {
+      "epoch": 0.26902957190135585,
+      "grad_norm": 0.28646326065063477,
+      "learning_rate": 4.276865589492747e-06,
+      "loss": 0.5838,
+      "step": 210
+    },
+    {
+      "epoch": 0.27543503789900714,
+      "grad_norm": 0.3569891154766083,
+      "learning_rate": 4.240189579077649e-06,
+      "loss": 0.5701,
+      "step": 215
+    },
+    {
+      "epoch": 0.2818405038966585,
+      "grad_norm": 0.33763790130615234,
+      "learning_rate": 4.202772170364969e-06,
+      "loss": 0.5759,
+      "step": 220
+    },
+    {
+      "epoch": 0.2882459698943098,
+      "grad_norm": 0.245514377951622,
+      "learning_rate": 4.164629304838012e-06,
+      "loss": 0.5694,
+      "step": 225
+    },
+    {
+      "epoch": 0.29465143589196113,
+      "grad_norm": 0.2917734682559967,
+      "learning_rate": 4.125777233057007e-06,
+      "loss": 0.5944,
+      "step": 230
+    },
+    {
+      "epoch": 0.3010569018896125,
+      "grad_norm": 0.2828243374824524,
+      "learning_rate": 4.086232507735648e-06,
+      "loss": 0.5717,
+      "step": 235
+    },
+    {
+      "epoch": 0.3074623678872638,
+      "grad_norm": 0.38584598898887634,
+      "learning_rate": 4.0460119766889e-06,
+      "loss": 0.5931,
+      "step": 240
+    },
+    {
+      "epoch": 0.3138678338849151,
+      "grad_norm": 0.36006131768226624,
+      "learning_rate": 4.005132775655076e-06,
+      "loss": 0.5564,
+      "step": 245
+    },
+    {
+      "epoch": 0.3202732998825665,
+      "grad_norm": 0.372942179441452,
+      "learning_rate": 3.963612320995257e-06,
+      "loss": 0.6025,
+      "step": 250
+    },
+    {
+      "epoch": 0.32667876588021777,
+      "grad_norm": 0.28577810525894165,
+      "learning_rate": 3.921468302273137e-06,
+      "loss": 0.5469,
+      "step": 255
+    },
+    {
+      "epoch": 0.3330842318778691,
+      "grad_norm": 0.3417142331600189,
+      "learning_rate": 3.8787186747184826e-06,
+      "loss": 0.5342,
+      "step": 260
+    },
+    {
+      "epoch": 0.33948969787552047,
+      "grad_norm": 0.35277873277664185,
+      "learning_rate": 3.8353816515774115e-06,
+      "loss": 0.5531,
+      "step": 265
+    },
+    {
+      "epoch": 0.34589516387317176,
+      "grad_norm": 0.2886194586753845,
+      "learning_rate": 3.79147569635273e-06,
+      "loss": 0.5431,
+      "step": 270
+    },
+    {
+      "epoch": 0.3523006298708231,
+      "grad_norm": 0.29417017102241516,
+      "learning_rate": 3.747019514937663e-06,
+      "loss": 0.5826,
+      "step": 275
+    },
+    {
+      "epoch": 0.3587060958684744,
+      "grad_norm": 0.3237856924533844,
+      "learning_rate": 3.70203204764631e-06,
+      "loss": 0.5689,
+      "step": 280
+    },
+    {
+      "epoch": 0.36511156186612576,
+      "grad_norm": 0.3846990168094635,
+      "learning_rate": 3.6565324611442234e-06,
+      "loss": 0.5763,
+      "step": 285
+    },
+    {
+      "epoch": 0.3715170278637771,
+      "grad_norm": 0.2781718969345093,
+      "learning_rate": 3.6105401402825595e-06,
+      "loss": 0.5549,
+      "step": 290
+    },
+    {
+      "epoch": 0.3779224938614284,
+      "grad_norm": 0.2733434736728668,
+      "learning_rate": 3.5640746798392657e-06,
+      "loss": 0.5967,
+      "step": 295
+    },
+    {
+      "epoch": 0.38432795985907975,
+      "grad_norm": 0.34851792454719543,
+      "learning_rate": 3.5171558761708334e-06,
+      "loss": 0.5543,
+      "step": 300
+    },
+    {
+      "epoch": 0.3907334258567311,
+      "grad_norm": 0.34361544251441956,
+      "learning_rate": 3.469803718778166e-06,
+      "loss": 0.5519,
+      "step": 305
+    },
+    {
+      "epoch": 0.3971388918543824,
+      "grad_norm": 0.2903674244880676,
+      "learning_rate": 3.4220383817901625e-06,
+      "loss": 0.562,
+      "step": 310
+    },
+    {
+      "epoch": 0.40354435785203374,
+      "grad_norm": 0.31230857968330383,
+      "learning_rate": 3.3738802153686414e-06,
+      "loss": 0.5537,
+      "step": 315
+    },
+    {
+      "epoch": 0.4099498238496851,
+      "grad_norm": 0.31388580799102783,
+      "learning_rate": 3.3253497370382605e-06,
+      "loss": 0.5551,
+      "step": 320
+    },
+    {
+      "epoch": 0.4163552898473364,
+      "grad_norm": 0.32741594314575195,
+      "learning_rate": 3.2764676229451397e-06,
+      "loss": 0.5498,
+      "step": 325
+    },
+    {
+      "epoch": 0.42276075584498773,
+      "grad_norm": 0.2511857748031616,
+      "learning_rate": 3.227254699047904e-06,
+      "loss": 0.5511,
+      "step": 330
+    },
+    {
+      "epoch": 0.42916622184263903,
+      "grad_norm": 0.3877544105052948,
+      "learning_rate": 3.177731932244892e-06,
+      "loss": 0.5485,
+      "step": 335
+    },
+    {
+      "epoch": 0.4355716878402904,
+      "grad_norm": 0.3445497751235962,
+      "learning_rate": 3.127920421441327e-06,
+      "loss": 0.5639,
+      "step": 340
+    },
+    {
+      "epoch": 0.4419771538379417,
+      "grad_norm": 0.3347369432449341,
+      "learning_rate": 3.077841388560243e-06,
+      "loss": 0.5745,
+      "step": 345
+    },
+    {
+      "epoch": 0.448382619835593,
+      "grad_norm": 0.36205726861953735,
+      "learning_rate": 3.0275161695009975e-06,
+      "loss": 0.5658,
+      "step": 350
+    },
+    {
+      "epoch": 0.45478808583324437,
+      "grad_norm": 0.35722121596336365,
+      "learning_rate": 2.9769662050492276e-06,
+      "loss": 0.5479,
+      "step": 355
+    },
+    {
+      "epoch": 0.4611935518308957,
+      "grad_norm": 0.35634711384773254,
+      "learning_rate": 2.926213031742125e-06,
+      "loss": 0.5595,
+      "step": 360
+    },
+    {
+      "epoch": 0.467599017828547,
+      "grad_norm": 0.32853105664253235,
+      "learning_rate": 2.8752782726929045e-06,
+      "loss": 0.5429,
+      "step": 365
+    },
+    {
+      "epoch": 0.47400448382619836,
+      "grad_norm": 0.3939530551433563,
+      "learning_rate": 2.8241836283784026e-06,
+      "loss": 0.531,
+      "step": 370
+    },
+    {
+      "epoch": 0.48040994982384966,
+      "grad_norm": 0.3002113699913025,
+      "learning_rate": 2.7729508673936972e-06,
+      "loss": 0.5596,
+      "step": 375
+    },
+    {
+      "epoch": 0.486815415821501,
+      "grad_norm": 0.3216375708580017,
+      "learning_rate": 2.721601817177725e-06,
+      "loss": 0.5292,
+      "step": 380
+    },
+    {
+      "epoch": 0.49322088181915236,
+      "grad_norm": 0.3263518810272217,
+      "learning_rate": 2.6701583547138165e-06,
+      "loss": 0.5684,
+      "step": 385
+    },
+    {
+      "epoch": 0.49962634781680365,
+      "grad_norm": 0.3253946900367737,
+      "learning_rate": 2.618642397209126e-06,
+      "loss": 0.5264,
+      "step": 390
+    },
+    {
+      "epoch": 0.5060318138144551,
+      "grad_norm": 0.3231858015060425,
+      "learning_rate": 2.567075892756924e-06,
+      "loss": 0.5448,
+      "step": 395
+    },
+    {
+      "epoch": 0.5124372798121063,
+      "grad_norm": 0.36590418219566345,
+      "learning_rate": 2.5154808109857367e-06,
+      "loss": 0.5248,
+      "step": 400
+    },
+    {
+      "epoch": 0.5188427458097576,
+      "grad_norm": 0.3773280084133148,
+      "learning_rate": 2.4638791336992967e-06,
+      "loss": 0.5505,
+      "step": 405
+    },
+    {
+      "epoch": 0.525248211807409,
+      "grad_norm": 0.3829450309276581,
+      "learning_rate": 2.4122928455113233e-06,
+      "loss": 0.5466,
+      "step": 410
+    },
+    {
+      "epoch": 0.5316536778050603,
+      "grad_norm": 0.3306972086429596,
+      "learning_rate": 2.360743924479093e-06,
+      "loss": 0.5721,
+      "step": 415
+    },
+    {
+      "epoch": 0.5380591438027117,
+      "grad_norm": 0.32845625281333923,
+      "learning_rate": 2.3092543327398083e-06,
+      "loss": 0.5177,
+      "step": 420
+    },
+    {
+      "epoch": 0.5444646098003629,
+      "grad_norm": 0.3088594079017639,
+      "learning_rate": 2.2578460071537512e-06,
+      "loss": 0.5575,
+      "step": 425
+    },
+    {
+      "epoch": 0.5508700757980143,
+      "grad_norm": 0.3912436366081238,
+      "learning_rate": 2.2065408499582e-06,
+      "loss": 0.561,
+      "step": 430
+    },
+    {
+      "epoch": 0.5572755417956656,
+      "grad_norm": 0.3839537799358368,
+      "learning_rate": 2.155360719436102e-06,
+      "loss": 0.526,
+      "step": 435
+    },
+    {
+      "epoch": 0.563681007793317,
+      "grad_norm": 0.3676234185695648,
+      "learning_rate": 2.1043274206034727e-06,
+      "loss": 0.541,
+      "step": 440
+    },
+    {
+      "epoch": 0.5700864737909683,
+      "grad_norm": 0.368198424577713,
+      "learning_rate": 2.0534626959194816e-06,
+      "loss": 0.5212,
+      "step": 445
+    },
+    {
+      "epoch": 0.5764919397886196,
+      "grad_norm": 0.34693998098373413,
+      "learning_rate": 2.002788216023203e-06,
+      "loss": 0.5462,
+      "step": 450
+    },
+    {
+      "epoch": 0.5828974057862709,
+      "grad_norm": 0.37934619188308716,
+      "learning_rate": 1.9523255705009558e-06,
+      "loss": 0.5423,
+      "step": 455
+    },
+    {
+      "epoch": 0.5893028717839223,
+      "grad_norm": 0.3458510637283325,
+      "learning_rate": 1.902096258688174e-06,
+      "loss": 0.4889,
+      "step": 460
+    },
+    {
+      "epoch": 0.5957083377815736,
+      "grad_norm": 0.33206406235694885,
+      "learning_rate": 1.8521216805097358e-06,
+      "loss": 0.5378,
+      "step": 465
+    },
+    {
+      "epoch": 0.602113803779225,
+      "grad_norm": 0.29139187932014465,
+      "learning_rate": 1.8024231273626424e-06,
+      "loss": 0.5444,
+      "step": 470
+    },
+    {
+      "epoch": 0.6085192697768763,
+      "grad_norm": 0.3665342926979065,
+      "learning_rate": 1.7530217730449312e-06,
+      "loss": 0.5276,
+      "step": 475
+    },
+    {
+      "epoch": 0.6149247357745276,
+      "grad_norm": 0.32149678468704224,
+      "learning_rate": 1.7039386647346975e-06,
+      "loss": 0.5117,
+      "step": 480
+    },
+    {
+      "epoch": 0.6213302017721789,
+      "grad_norm": 0.30389899015426636,
+      "learning_rate": 1.6551947140230568e-06,
+      "loss": 0.5573,
+      "step": 485
+    },
+    {
+      "epoch": 0.6277356677698303,
+      "grad_norm": 0.3890632688999176,
+      "learning_rate": 1.6068106880048747e-06,
+      "loss": 0.5395,
+      "step": 490
+    },
+    {
+      "epoch": 0.6341411337674816,
+      "grad_norm": 0.36464181542396545,
+      "learning_rate": 1.5588072004310634e-06,
+      "loss": 0.5497,
+      "step": 495
+    },
+    {
+      "epoch": 0.640546599765133,
+      "grad_norm": 0.32058826088905334,
+      "learning_rate": 1.5112047029262e-06,
+      "loss": 0.5377,
+      "step": 500
+    },
+    {
+      "epoch": 0.6469520657627842,
+      "grad_norm": 0.280649870634079,
+      "learning_rate": 1.4640234762752248e-06,
+      "loss": 0.5349,
+      "step": 505
+    },
+    {
+      "epoch": 0.6533575317604355,
+      "grad_norm": 0.36669427156448364,
+      "learning_rate": 1.4172836217829267e-06,
+      "loss": 0.539,
+      "step": 510
+    },
+    {
+      "epoch": 0.6597629977580869,
+      "grad_norm": 0.3747427463531494,
+      "learning_rate": 1.3710050527098867e-06,
+      "loss": 0.5582,
+      "step": 515
+    },
+    {
+      "epoch": 0.6661684637557382,
+      "grad_norm": 0.3354856073856354,
+      "learning_rate": 1.3252074857885453e-06,
+      "loss": 0.5512,
+      "step": 520
+    },
+    {
+      "epoch": 0.6725739297533896,
+      "grad_norm": 0.3852190673351288,
+      "learning_rate": 1.2799104328229928e-06,
+      "loss": 0.5216,
+      "step": 525
+    },
+    {
+      "epoch": 0.6789793957510409,
+      "grad_norm": 0.3479975759983063,
+      "learning_rate": 1.2351331923760743e-06,
+      "loss": 0.518,
+      "step": 530
+    },
+    {
+      "epoch": 0.6853848617486922,
+      "grad_norm": 0.37335509061813354,
+      "learning_rate": 1.1908948415473418e-06,
+      "loss": 0.5203,
+      "step": 535
+    },
+    {
+      "epoch": 0.6917903277463435,
+      "grad_norm": 0.4034595489501953,
+      "learning_rate": 1.1472142278453582e-06,
+      "loss": 0.5157,
+      "step": 540
+    },
+    {
+      "epoch": 0.6981957937439949,
+      "grad_norm": 0.2966196537017822,
+      "learning_rate": 1.1041099611578177e-06,
+      "loss": 0.541,
+      "step": 545
+    },
+    {
+      "epoch": 0.7046012597416462,
+      "grad_norm": 0.3616897463798523,
+      "learning_rate": 1.0616004058229084e-06,
+      "loss": 0.5254,
+      "step": 550
+    },
+    {
+      "epoch": 0.7110067257392976,
+      "grad_norm": 0.3452332317829132,
+      "learning_rate": 1.0197036728052847e-06,
+      "loss": 0.5543,
+      "step": 555
+    },
+    {
+      "epoch": 0.7174121917369488,
+      "grad_norm": 0.3313845694065094,
+      "learning_rate": 9.784376119799851e-07,
+      "loss": 0.5294,
+      "step": 560
+    },
+    {
+      "epoch": 0.7238176577346002,
+      "grad_norm": 0.37989768385887146,
+      "learning_rate": 9.378198045275968e-07,
+      "loss": 0.5411,
+      "step": 565
+    },
+    {
+      "epoch": 0.7302231237322515,
+      "grad_norm": 0.3642790913581848,
+      "learning_rate": 8.97867555443886e-07,
+      "loss": 0.5186,
+      "step": 570
+    },
+    {
+      "epoch": 0.7366285897299029,
+      "grad_norm": 0.369183748960495,
+      "learning_rate": 8.585978861670958e-07,
+      "loss": 0.5189,
+      "step": 575
+    },
+    {
+      "epoch": 0.7430340557275542,
+      "grad_norm": 0.3428362011909485,
+      "learning_rate": 8.200275273260611e-07,
+      "loss": 0.5326,
+      "step": 580
+    },
+    {
+      "epoch": 0.7494395217252056,
+      "grad_norm": 0.33693212270736694,
+      "learning_rate": 7.821729116122126e-07,
+      "loss": 0.5417,
+      "step": 585
+    },
+    {
+      "epoch": 0.7558449877228568,
+      "grad_norm": 0.35541847348213196,
+      "learning_rate": 7.450501667785146e-07,
+      "loss": 0.531,
+      "step": 590
+    },
+    {
+      "epoch": 0.7622504537205081,
+      "grad_norm": 0.3545955717563629,
+      "learning_rate": 7.086751087683297e-07,
+      "loss": 0.5371,
+      "step": 595
+    },
+    {
+      "epoch": 0.7686559197181595,
+      "grad_norm": 0.369098424911499,
+      "learning_rate": 6.730632349771193e-07,
+      "loss": 0.5444,
+      "step": 600
+    },
+    {
+      "epoch": 0.7750613857158108,
+      "grad_norm": 0.395386666059494,
+      "learning_rate": 6.3822971764986e-07,
+      "loss": 0.5207,
+      "step": 605
+    },
+    {
+      "epoch": 0.7814668517134622,
+      "grad_norm": 0.3929295241832733,
+      "learning_rate": 6.041893974169963e-07,
+      "loss": 0.5223,
+      "step": 610
+    },
+    {
+      "epoch": 0.7878723177111134,
+      "grad_norm": 0.38200634717941284,
+      "learning_rate": 5.709567769716678e-07,
+      "loss": 0.5346,
+      "step": 615
+    },
+    {
+      "epoch": 0.7942777837087648,
+      "grad_norm": 0.35260388255119324,
+      "learning_rate": 5.385460148909169e-07,
+      "loss": 0.5106,
+      "step": 620
+    },
+    {
+      "epoch": 0.8006832497064161,
+      "grad_norm": 0.36902984976768494,
+      "learning_rate": 5.069709196035011e-07,
+      "loss": 0.5333,
+      "step": 625
+    },
+    {
+      "epoch": 0.8070887157040675,
+      "grad_norm": 0.36749160289764404,
+      "learning_rate": 4.762449435068914e-07,
+      "loss": 0.5197,
+      "step": 630
+    },
+    {
+      "epoch": 0.8134941817017188,
+      "grad_norm": 0.37014660239219666,
+      "learning_rate": 4.4638117723595054e-07,
+      "loss": 0.5492,
+      "step": 635
+    },
+    {
+      "epoch": 0.8198996476993702,
+      "grad_norm": 0.3781520426273346,
+      "learning_rate": 4.173923440857358e-07,
+      "loss": 0.5365,
+      "step": 640
+    },
+    {
+      "epoch": 0.8263051136970214,
+      "grad_norm": 0.33049196004867554,
+      "learning_rate": 3.892907945908128e-07,
+      "loss": 0.5163,
+      "step": 645
+    },
+    {
+      "epoch": 0.8327105796946728,
+      "grad_norm": 0.40030181407928467,
+      "learning_rate": 3.6208850126337595e-07,
+      "loss": 0.5111,
+      "step": 650
+    },
+    {
+      "epoch": 0.8391160456923241,
+      "grad_norm": 0.3238008916378021,
+      "learning_rate": 3.357970534924229e-07,
+      "loss": 0.544,
+      "step": 655
+    },
+    {
+      "epoch": 0.8455215116899755,
+      "grad_norm": 0.3207038938999176,
+      "learning_rate": 3.104276526061617e-07,
+      "loss": 0.5242,
+      "step": 660
+    },
+    {
+      "epoch": 0.8519269776876268,
+      "grad_norm": 0.38148337602615356,
+      "learning_rate": 2.859911070997437e-07,
+      "loss": 0.5358,
+      "step": 665
+    },
+    {
+      "epoch": 0.8583324436852781,
+      "grad_norm": 0.44874271750450134,
+      "learning_rate": 2.624978280303628e-07,
+      "loss": 0.5347,
+      "step": 670
+    },
+    {
+      "epoch": 0.8647379096829294,
+      "grad_norm": 0.3957948684692383,
+      "learning_rate": 2.3995782458168276e-07,
+      "loss": 0.5401,
+      "step": 675
+    },
+    {
+      "epoch": 0.8711433756805808,
+      "grad_norm": 0.398444265127182,
+      "learning_rate": 2.1838069979947945e-07,
+      "loss": 0.524,
+      "step": 680
+    },
+    {
+      "epoch": 0.8775488416782321,
+      "grad_norm": 0.37134161591529846,
+      "learning_rate": 1.9777564650031112e-07,
+      "loss": 0.535,
+      "step": 685
+    },
+    {
+      "epoch": 0.8839543076758835,
+      "grad_norm": 0.37950778007507324,
+      "learning_rate": 1.7815144335497524e-07,
+      "loss": 0.5358,
+      "step": 690
+    },
+    {
+      "epoch": 0.8903597736735348,
+      "grad_norm": 0.4200168251991272,
+      "learning_rate": 1.5951645114839875e-07,
+      "loss": 0.5234,
+      "step": 695
+    },
+    {
+      "epoch": 0.896765239671186,
+      "grad_norm": 0.3997882008552551,
+      "learning_rate": 1.4187860921757252e-07,
+      "loss": 0.5437,
+      "step": 700
+    },
+    {
+      "epoch": 0.9031707056688374,
+      "grad_norm": 0.405408650636673,
+      "learning_rate": 1.2524543206904188e-07,
+      "loss": 0.5443,
+      "step": 705
+    },
+    {
+      "epoch": 0.9095761716664887,
+      "grad_norm": 0.368826299905777,
+      "learning_rate": 1.0962400617738872e-07,
+      "loss": 0.564,
+      "step": 710
+    },
+    {
+      "epoch": 0.9159816376641401,
+      "grad_norm": 0.41221150755882263,
+      "learning_rate": 9.502098696608147e-08,
+      "loss": 0.5288,
+      "step": 715
+    },
+    {
+      "epoch": 0.9223871036617914,
+      "grad_norm": 0.30681097507476807,
+      "learning_rate": 8.144259597196308e-08,
+      "loss": 0.5356,
+      "step": 720
+    },
+    {
+      "epoch": 0.9287925696594427,
+      "grad_norm": 0.3287171423435211,
+      "learning_rate": 6.889461819460485e-08,
+      "loss": 0.5228,
+      "step": 725
+    },
+    {
+      "epoch": 0.935198035657094,
+      "grad_norm": 0.39335137605667114,
+      "learning_rate": 5.738239963163472e-08,
+      "loss": 0.5102,
+      "step": 730
+    },
+    {
+      "epoch": 0.9416035016547454,
+      "grad_norm": 0.5197286605834961,
+      "learning_rate": 4.691084500110521e-08,
+      "loss": 0.5134,
+      "step": 735
+    },
+    {
+      "epoch": 0.9480089676523967,
+      "grad_norm": 0.37825560569763184,
+      "learning_rate": 3.748441565186583e-08,
+      "loss": 0.495,
+      "step": 740
+    },
+    {
+      "epoch": 0.9544144336500481,
+      "grad_norm": 0.39631250500679016,
+      "learning_rate": 2.910712766282908e-08,
+      "loss": 0.5227,
+      "step": 745
+    },
+    {
+      "epoch": 0.9608198996476993,
+      "grad_norm": 0.40286198258399963,
+      "learning_rate": 2.178255013194075e-08,
+      "loss": 0.5142,
+      "step": 750
+    },
+    {
+      "epoch": 0.9672253656453507,
+      "grad_norm": 0.31852659583091736,
+      "learning_rate": 1.5513803655587966e-08,
+      "loss": 0.4985,
+      "step": 755
+    },
+    {
+      "epoch": 0.973630831643002,
+      "grad_norm": 0.3686765134334564,
+      "learning_rate": 1.0303558999082974e-08,
+      "loss": 0.5464,
+      "step": 760
+    },
+    {
+      "epoch": 0.9800362976406534,
+      "grad_norm": 0.3755616843700409,
+      "learning_rate": 6.1540359588005416e-09,
+      "loss": 0.5158,
+      "step": 765
+    },
+    {
+      "epoch": 0.9864417636383047,
+      "grad_norm": 0.31239190697669983,
+      "learning_rate": 3.067002416444198e-09,
+      "loss": 0.499,
+      "step": 770
+    },
+    {
+      "epoch": 0.9928472296359561,
+      "grad_norm": 0.3598840534687042,
+      "learning_rate": 1.0437735858506715e-09,
+      "loss": 0.5246,
+      "step": 775
+    },
+    {
+      "epoch": 0.9992526956336073,
+      "grad_norm": 0.3162603974342346,
+      "learning_rate": 8.521145264978048e-11,
+      "loss": 0.5619,
+      "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": 1.4329344655107686e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}