Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ 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-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,74 @@
+---
+base_model: unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
+library_name: peft
+model_name: dpo_v2
+tags:
+- base_model:adapter:unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
+- dpo
+- lora
+- transformers
+- trl
+- unsloth
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for dpo_v2
+
+This model is a fine-tuned version of [unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit](https://huggingface.co/unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
+
+### Framework versions
+
+- PEFT 0.18.1
+- TRL: 0.24.0
+- Transformers: 4.57.6
+- Pytorch: 2.10.0
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+Cite DPO as:
+
+```bibtex
+@inproceedings{rafailov2023direct,
+    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
+    author       = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
+    year         = 2023,
+    booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
+    url          = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
+    editor       = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
+}
+```
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": true,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6952f5c0dfff8585a8d94ad0267e7bf11f1889ecfabee07044add3fa8dfe753
+size 533009160

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
+}

chat_template.jinja

@@ -0,0 +1,86 @@
+{%- 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' }}
+{%- endif %}

checkpoint-400/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
+- dpo
+- lora
+- transformers
+- trl
+- 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 0.18.1

checkpoint-400/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": true,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70057b802b86aa7b4877c354c79f8711bfc2d7d76f8d1d7bde37a04e6830ae3e
+size 533009160

checkpoint-400/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-400/chat_template.jinja

@@ -0,0 +1,86 @@
+{%- 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' }}
+{%- endif %}

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07a52805a397dbdb8f82b3453c5ff45b19be1f613d7858c35bd5604be7b02021
+size 272956501

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c800b778fa7e115e4c34de8529902de8b61c9a1b4bab3eb8295d06dafff030e
+size 14645

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12962f444faed28515777d02e6370168ef1c4d890d314c1480b339341fb48484
+size 1465

checkpoint-400/special_tokens_map.json

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

checkpoint-400/tokenizer.json

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

checkpoint-400/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": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-400/trainer_state.json

@@ -0,0 +1,634 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "grad_norm": 8.528485298156738,
+      "learning_rate": 9e-06,
+      "logits/chosen": 2.054985523223877,
+      "logits/rejected": 1.9033839702606201,
+      "logps/chosen": -23.966228485107422,
+      "logps/rejected": -53.68938446044922,
+      "loss": 0.5192,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": 3.1913700103759766,
+      "rewards/margins": 0.7934623956680298,
+      "rewards/rejected": 2.3979074954986572,
+      "step": 10
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.4699181616306305,
+      "learning_rate": 1.9e-05,
+      "logits/chosen": 2.652074098587036,
+      "logits/rejected": 2.6142349243164062,
+      "logps/chosen": -19.591583251953125,
+      "logps/rejected": -71.51148986816406,
+      "loss": 0.2992,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 3.1300272941589355,
+      "rewards/margins": 2.6587636470794678,
+      "rewards/rejected": 0.47126370668411255,
+      "step": 20
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 6.240016937255859,
+      "learning_rate": 2.9e-05,
+      "logits/chosen": 3.368675947189331,
+      "logits/rejected": 3.328001022338867,
+      "logps/chosen": -21.065635681152344,
+      "logps/rejected": -97.60667419433594,
+      "loss": 0.2464,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 3.2080636024475098,
+      "rewards/margins": 5.249109745025635,
+      "rewards/rejected": -2.041045904159546,
+      "step": 30
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.10691515356302261,
+      "learning_rate": 3.9000000000000006e-05,
+      "logits/chosen": 2.1906957626342773,
+      "logits/rejected": 2.274221658706665,
+      "logps/chosen": -17.63897132873535,
+      "logps/rejected": -90.91486358642578,
+      "loss": 0.2946,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 3.081021785736084,
+      "rewards/margins": 5.548964500427246,
+      "rewards/rejected": -2.467942714691162,
+      "step": 40
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6372888088226318,
+      "learning_rate": 4.9e-05,
+      "logits/chosen": 0.6477093696594238,
+      "logits/rejected": 0.833999752998352,
+      "logps/chosen": -29.2796630859375,
+      "logps/rejected": -124.37042236328125,
+      "loss": 0.2171,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 2.3345980644226074,
+      "rewards/margins": 7.417657375335693,
+      "rewards/rejected": -5.083059310913086,
+      "step": 50
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.571674108505249,
+      "learning_rate": 4.9e-05,
+      "logits/chosen": 2.270029067993164,
+      "logits/rejected": 2.524890899658203,
+      "logps/chosen": -27.73245620727539,
+      "logps/rejected": -103.86787414550781,
+      "loss": 0.2655,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 2.1670007705688477,
+      "rewards/margins": 5.720990180969238,
+      "rewards/rejected": -3.5539894104003906,
+      "step": 60
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.6424742937088013,
+      "learning_rate": 4.7888888888888886e-05,
+      "logits/chosen": 1.0871316194534302,
+      "logits/rejected": 1.31881582736969,
+      "logps/chosen": -35.905784606933594,
+      "logps/rejected": -127.39874267578125,
+      "loss": 0.2822,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 2.1068429946899414,
+      "rewards/margins": 7.130377769470215,
+      "rewards/rejected": -5.02353572845459,
+      "step": 70
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.2139262557029724,
+      "learning_rate": 4.677777777777778e-05,
+      "logits/chosen": 1.289627194404602,
+      "logits/rejected": 1.5509237051010132,
+      "logps/chosen": -37.245338439941406,
+      "logps/rejected": -143.37571716308594,
+      "loss": 0.2551,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 1.7066528797149658,
+      "rewards/margins": 8.251852989196777,
+      "rewards/rejected": -6.545199394226074,
+      "step": 80
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 9.060225486755371,
+      "learning_rate": 4.566666666666667e-05,
+      "logits/chosen": -0.21008212864398956,
+      "logits/rejected": 0.13004381954669952,
+      "logps/chosen": -34.545066833496094,
+      "logps/rejected": -136.86561584472656,
+      "loss": 0.2398,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 2.3621673583984375,
+      "rewards/margins": 8.225154876708984,
+      "rewards/rejected": -5.862987041473389,
+      "step": 90
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.8874521255493164,
+      "learning_rate": 4.4555555555555555e-05,
+      "logits/chosen": 0.8144568204879761,
+      "logits/rejected": 1.1611213684082031,
+      "logps/chosen": -41.461158752441406,
+      "logps/rejected": -139.0437469482422,
+      "loss": 0.2243,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.0751674175262451,
+      "rewards/margins": 7.963423728942871,
+      "rewards/rejected": -6.8882575035095215,
+      "step": 100
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.21037925779819489,
+      "learning_rate": 4.344444444444445e-05,
+      "logits/chosen": -0.559118390083313,
+      "logits/rejected": -0.11641822755336761,
+      "logps/chosen": -47.142601013183594,
+      "logps/rejected": -150.99496459960938,
+      "loss": 0.2594,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": 0.32266765832901,
+      "rewards/margins": 8.18213939666748,
+      "rewards/rejected": -7.859471321105957,
+      "step": 110
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.33475127816200256,
+      "learning_rate": 4.233333333333334e-05,
+      "logits/chosen": -0.39622828364372253,
+      "logits/rejected": -0.1825840175151825,
+      "logps/chosen": -46.026100158691406,
+      "logps/rejected": -142.27127075195312,
+      "loss": 0.2442,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 0.987580418586731,
+      "rewards/margins": 7.525818824768066,
+      "rewards/rejected": -6.538238525390625,
+      "step": 120
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.12689562141895294,
+      "learning_rate": 4.1222222222222224e-05,
+      "logits/chosen": -0.23490352928638458,
+      "logits/rejected": 0.27892929315567017,
+      "logps/chosen": -33.58977508544922,
+      "logps/rejected": -144.8148956298828,
+      "loss": 0.2096,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.9526748657226562,
+      "rewards/margins": 8.64609146118164,
+      "rewards/rejected": -6.693416595458984,
+      "step": 130
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.12881708145141602,
+      "learning_rate": 4.011111111111111e-05,
+      "logits/chosen": -1.1939542293548584,
+      "logits/rejected": -0.9672979116439819,
+      "logps/chosen": -37.64386749267578,
+      "logps/rejected": -125.4320068359375,
+      "loss": 0.2528,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 2.0000433921813965,
+      "rewards/margins": 6.926792144775391,
+      "rewards/rejected": -4.926749229431152,
+      "step": 140
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.21873943507671356,
+      "learning_rate": 3.9000000000000006e-05,
+      "logits/chosen": -1.780418038368225,
+      "logits/rejected": -1.4915210008621216,
+      "logps/chosen": -35.17759704589844,
+      "logps/rejected": -136.65286254882812,
+      "loss": 0.2278,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 1.875436544418335,
+      "rewards/margins": 8.086755752563477,
+      "rewards/rejected": -6.211319923400879,
+      "step": 150
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.053676556795835495,
+      "learning_rate": 3.7888888888888894e-05,
+      "logits/chosen": -1.770747423171997,
+      "logits/rejected": -1.2938441038131714,
+      "logps/chosen": -29.032825469970703,
+      "logps/rejected": -138.14309692382812,
+      "loss": 0.2089,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 2.1548972129821777,
+      "rewards/margins": 8.57084846496582,
+      "rewards/rejected": -6.41594934463501,
+      "step": 160
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.31680184602737427,
+      "learning_rate": 3.677777777777778e-05,
+      "logits/chosen": -1.9017817974090576,
+      "logits/rejected": -1.6287091970443726,
+      "logps/chosen": -32.30609893798828,
+      "logps/rejected": -135.4978485107422,
+      "loss": 0.1837,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 2.9330215454101562,
+      "rewards/margins": 8.456713676452637,
+      "rewards/rejected": -5.5236921310424805,
+      "step": 170
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.12343556433916092,
+      "learning_rate": 3.566666666666667e-05,
+      "logits/chosen": -2.0771210193634033,
+      "logits/rejected": -1.8654956817626953,
+      "logps/chosen": -38.074161529541016,
+      "logps/rejected": -140.7716522216797,
+      "loss": 0.2189,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.6962649822235107,
+      "rewards/margins": 8.185938835144043,
+      "rewards/rejected": -6.4896745681762695,
+      "step": 180
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.16018041968345642,
+      "learning_rate": 3.4555555555555556e-05,
+      "logits/chosen": -2.5613696575164795,
+      "logits/rejected": -2.160233736038208,
+      "logps/chosen": -35.08837127685547,
+      "logps/rejected": -174.58566284179688,
+      "loss": 0.1491,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 1.949218511581421,
+      "rewards/margins": 11.258779525756836,
+      "rewards/rejected": -9.309560775756836,
+      "step": 190
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.166445016860962,
+      "learning_rate": 3.3444444444444443e-05,
+      "logits/chosen": -3.0443778038024902,
+      "logits/rejected": -2.7526583671569824,
+      "logps/chosen": -40.106178283691406,
+      "logps/rejected": -151.62503051757812,
+      "loss": 0.2624,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.3750978708267212,
+      "rewards/margins": 9.279211044311523,
+      "rewards/rejected": -7.904112339019775,
+      "step": 200
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.3322606384754181,
+      "learning_rate": 3.233333333333333e-05,
+      "logits/chosen": -2.9914917945861816,
+      "logits/rejected": -2.5901548862457275,
+      "logps/chosen": -43.788307189941406,
+      "logps/rejected": -210.02102661132812,
+      "loss": 0.2258,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.1431424617767334,
+      "rewards/margins": 13.883976936340332,
+      "rewards/rejected": -12.740835189819336,
+      "step": 210
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.2920965850353241,
+      "learning_rate": 3.1222222222222225e-05,
+      "logits/chosen": -2.3677401542663574,
+      "logits/rejected": -1.9734885692596436,
+      "logps/chosen": -36.96697235107422,
+      "logps/rejected": -187.7698211669922,
+      "loss": 0.2081,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 1.8709278106689453,
+      "rewards/margins": 12.740228652954102,
+      "rewards/rejected": -10.86929988861084,
+      "step": 220
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.15863250195980072,
+      "learning_rate": 3.0111111111111113e-05,
+      "logits/chosen": -1.819131851196289,
+      "logits/rejected": -1.4921624660491943,
+      "logps/chosen": -41.595420837402344,
+      "logps/rejected": -186.645751953125,
+      "loss": 0.1995,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 0.9655638933181763,
+      "rewards/margins": 12.226719856262207,
+      "rewards/rejected": -11.26115608215332,
+      "step": 230
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.0697341114282608,
+      "learning_rate": 2.9e-05,
+      "logits/chosen": -2.357139825820923,
+      "logits/rejected": -1.888144850730896,
+      "logps/chosen": -52.9119987487793,
+      "logps/rejected": -263.25390625,
+      "loss": 0.1824,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 0.7968165874481201,
+      "rewards/margins": 18.26348304748535,
+      "rewards/rejected": -17.466665267944336,
+      "step": 240
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8565608859062195,
+      "learning_rate": 2.788888888888889e-05,
+      "logits/chosen": -2.9249751567840576,
+      "logits/rejected": -2.6594655513763428,
+      "logps/chosen": -49.89072799682617,
+      "logps/rejected": -190.1117401123047,
+      "loss": 0.2175,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.047927260398864746,
+      "rewards/margins": 11.593302726745605,
+      "rewards/rejected": -11.54537582397461,
+      "step": 250
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.4322703778743744,
+      "learning_rate": 2.677777777777778e-05,
+      "logits/chosen": -2.591165781021118,
+      "logits/rejected": -2.2559447288513184,
+      "logps/chosen": -42.47401428222656,
+      "logps/rejected": -188.3767547607422,
+      "loss": 0.2081,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.9701582789421082,
+      "rewards/margins": 12.480576515197754,
+      "rewards/rejected": -11.510419845581055,
+      "step": 260
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.19003595411777496,
+      "learning_rate": 2.5666666666666666e-05,
+      "logits/chosen": -3.374302625656128,
+      "logits/rejected": -3.0488531589508057,
+      "logps/chosen": -57.8838996887207,
+      "logps/rejected": -193.90777587890625,
+      "loss": 0.3035,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": -0.37895283102989197,
+      "rewards/margins": 11.51020622253418,
+      "rewards/rejected": -11.889159202575684,
+      "step": 270
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.16604876518249512,
+      "learning_rate": 2.4555555555555557e-05,
+      "logits/chosen": -3.1895713806152344,
+      "logits/rejected": -2.834735870361328,
+      "logps/chosen": -52.5036735534668,
+      "logps/rejected": -177.6607666015625,
+      "loss": 0.2516,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": 0.857752799987793,
+      "rewards/margins": 10.699987411499023,
+      "rewards/rejected": -9.84223461151123,
+      "step": 280
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.14234374463558197,
+      "learning_rate": 2.3444444444444448e-05,
+      "logits/chosen": -3.344165086746216,
+      "logits/rejected": -3.020646572113037,
+      "logps/chosen": -41.34022903442383,
+      "logps/rejected": -178.89938354492188,
+      "loss": 0.2602,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": 1.0710757970809937,
+      "rewards/margins": 11.487492561340332,
+      "rewards/rejected": -10.416417121887207,
+      "step": 290
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.1858437955379486,
+      "learning_rate": 2.2333333333333335e-05,
+      "logits/chosen": -3.0915908813476562,
+      "logits/rejected": -2.762167453765869,
+      "logps/chosen": -41.24951171875,
+      "logps/rejected": -172.49880981445312,
+      "loss": 0.2256,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.1378252506256104,
+      "rewards/margins": 10.839186668395996,
+      "rewards/rejected": -9.701360702514648,
+      "step": 300
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.2519996762275696,
+      "learning_rate": 2.1222222222222223e-05,
+      "logits/chosen": -3.076692581176758,
+      "logits/rejected": -2.7446165084838867,
+      "logps/chosen": -50.308746337890625,
+      "logps/rejected": -204.6868896484375,
+      "loss": 0.165,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 0.4235803484916687,
+      "rewards/margins": 13.201803207397461,
+      "rewards/rejected": -12.778223037719727,
+      "step": 310
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.3874475657939911,
+      "learning_rate": 2.011111111111111e-05,
+      "logits/chosen": -3.646862030029297,
+      "logits/rejected": -3.424621105194092,
+      "logps/chosen": -52.49565505981445,
+      "logps/rejected": -167.20236206054688,
+      "loss": 0.2347,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.23652243614196777,
+      "rewards/margins": 9.693285942077637,
+      "rewards/rejected": -9.456764221191406,
+      "step": 320
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.2814558148384094,
+      "learning_rate": 1.9e-05,
+      "logits/chosen": -3.1871893405914307,
+      "logits/rejected": -2.7857449054718018,
+      "logps/chosen": -50.25436782836914,
+      "logps/rejected": -183.965087890625,
+      "loss": 0.269,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.5717954039573669,
+      "rewards/margins": 11.194442749023438,
+      "rewards/rejected": -10.622648239135742,
+      "step": 330
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.2564876973628998,
+      "learning_rate": 1.788888888888889e-05,
+      "logits/chosen": -3.328599452972412,
+      "logits/rejected": -2.8498024940490723,
+      "logps/chosen": -40.71959686279297,
+      "logps/rejected": -194.56871032714844,
+      "loss": 0.1908,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 1.3430808782577515,
+      "rewards/margins": 13.080599784851074,
+      "rewards/rejected": -11.737520217895508,
+      "step": 340
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.2628025412559509,
+      "learning_rate": 1.677777777777778e-05,
+      "logits/chosen": -4.046440124511719,
+      "logits/rejected": -3.7269904613494873,
+      "logps/chosen": -46.230613708496094,
+      "logps/rejected": -186.4309539794922,
+      "loss": 0.2016,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 0.4831501543521881,
+      "rewards/margins": 11.869375228881836,
+      "rewards/rejected": -11.386224746704102,
+      "step": 350
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.22657158970832825,
+      "learning_rate": 1.5666666666666667e-05,
+      "logits/chosen": -3.75866961479187,
+      "logits/rejected": -3.361738681793213,
+      "logps/chosen": -49.731544494628906,
+      "logps/rejected": -203.48196411132812,
+      "loss": 0.165,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 0.7678171992301941,
+      "rewards/margins": 12.776975631713867,
+      "rewards/rejected": -12.009159088134766,
+      "step": 360
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.2632221281528473,
+      "learning_rate": 1.4555555555555556e-05,
+      "logits/chosen": -3.995814561843872,
+      "logits/rejected": -3.644721508026123,
+      "logps/chosen": -48.3692626953125,
+      "logps/rejected": -201.17593383789062,
+      "loss": 0.1649,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 0.5727468729019165,
+      "rewards/margins": 12.856643676757812,
+      "rewards/rejected": -12.283895492553711,
+      "step": 370
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.1788269430398941,
+      "learning_rate": 1.3444444444444445e-05,
+      "logits/chosen": -3.70817494392395,
+      "logits/rejected": -3.3923275470733643,
+      "logps/chosen": -40.871490478515625,
+      "logps/rejected": -171.85128784179688,
+      "loss": 0.2101,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 0.9809708595275879,
+      "rewards/margins": 11.068758010864258,
+      "rewards/rejected": -10.087786674499512,
+      "step": 380
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.14607764780521393,
+      "learning_rate": 1.2333333333333334e-05,
+      "logits/chosen": -3.0384268760681152,
+      "logits/rejected": -2.7124972343444824,
+      "logps/chosen": -36.8101806640625,
+      "logps/rejected": -163.4900360107422,
+      "loss": 0.26,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 1.447727084159851,
+      "rewards/margins": 10.76397705078125,
+      "rewards/rejected": -9.316250801086426,
+      "step": 390
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.21636660397052765,
+      "learning_rate": 1.1222222222222224e-05,
+      "logits/chosen": -3.6440536975860596,
+      "logits/rejected": -3.278002977371216,
+      "logps/chosen": -41.639305114746094,
+      "logps/rejected": -200.2166290283203,
+      "loss": 0.1822,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 1.6405818462371826,
+      "rewards/margins": 13.554621696472168,
+      "rewards/rejected": -11.914040565490723,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:620ad83214f09c07b562685e5c4a615d6dc192dd64a1fa24d684c1e7a11a842b
+size 6929

checkpoint-500/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
+- dpo
+- lora
+- transformers
+- trl
+- 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 0.18.1

checkpoint-500/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": true,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6952f5c0dfff8585a8d94ad0267e7bf11f1889ecfabee07044add3fa8dfe753
+size 533009160

checkpoint-500/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-500/chat_template.jinja

@@ -0,0 +1,86 @@
+{%- 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' }}
+{%- endif %}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:550e0408c8b86cef24d5e012431c7c714e9ad7cc94ba7fd546154828d7a00296
+size 272956501

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c800b778fa7e115e4c34de8529902de8b61c9a1b4bab3eb8295d06dafff030e
+size 14645

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3105ebe8471f9890c3eb1f20cc0f2520fa5fdb0128474bbc87e607b2ec7c53dc
+size 1465

checkpoint-500/special_tokens_map.json

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

checkpoint-500/tokenizer.json

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

checkpoint-500/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": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,784 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "grad_norm": 8.528485298156738,
+      "learning_rate": 9e-06,
+      "logits/chosen": 2.054985523223877,
+      "logits/rejected": 1.9033839702606201,
+      "logps/chosen": -23.966228485107422,
+      "logps/rejected": -53.68938446044922,
+      "loss": 0.5192,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": 3.1913700103759766,
+      "rewards/margins": 0.7934623956680298,
+      "rewards/rejected": 2.3979074954986572,
+      "step": 10
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.4699181616306305,
+      "learning_rate": 1.9e-05,
+      "logits/chosen": 2.652074098587036,
+      "logits/rejected": 2.6142349243164062,
+      "logps/chosen": -19.591583251953125,
+      "logps/rejected": -71.51148986816406,
+      "loss": 0.2992,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 3.1300272941589355,
+      "rewards/margins": 2.6587636470794678,
+      "rewards/rejected": 0.47126370668411255,
+      "step": 20
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 6.240016937255859,
+      "learning_rate": 2.9e-05,
+      "logits/chosen": 3.368675947189331,
+      "logits/rejected": 3.328001022338867,
+      "logps/chosen": -21.065635681152344,
+      "logps/rejected": -97.60667419433594,
+      "loss": 0.2464,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 3.2080636024475098,
+      "rewards/margins": 5.249109745025635,
+      "rewards/rejected": -2.041045904159546,
+      "step": 30
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.10691515356302261,
+      "learning_rate": 3.9000000000000006e-05,
+      "logits/chosen": 2.1906957626342773,
+      "logits/rejected": 2.274221658706665,
+      "logps/chosen": -17.63897132873535,
+      "logps/rejected": -90.91486358642578,
+      "loss": 0.2946,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 3.081021785736084,
+      "rewards/margins": 5.548964500427246,
+      "rewards/rejected": -2.467942714691162,
+      "step": 40
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6372888088226318,
+      "learning_rate": 4.9e-05,
+      "logits/chosen": 0.6477093696594238,
+      "logits/rejected": 0.833999752998352,
+      "logps/chosen": -29.2796630859375,
+      "logps/rejected": -124.37042236328125,
+      "loss": 0.2171,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 2.3345980644226074,
+      "rewards/margins": 7.417657375335693,
+      "rewards/rejected": -5.083059310913086,
+      "step": 50
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.571674108505249,
+      "learning_rate": 4.9e-05,
+      "logits/chosen": 2.270029067993164,
+      "logits/rejected": 2.524890899658203,
+      "logps/chosen": -27.73245620727539,
+      "logps/rejected": -103.86787414550781,
+      "loss": 0.2655,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 2.1670007705688477,
+      "rewards/margins": 5.720990180969238,
+      "rewards/rejected": -3.5539894104003906,
+      "step": 60
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.6424742937088013,
+      "learning_rate": 4.7888888888888886e-05,
+      "logits/chosen": 1.0871316194534302,
+      "logits/rejected": 1.31881582736969,
+      "logps/chosen": -35.905784606933594,
+      "logps/rejected": -127.39874267578125,
+      "loss": 0.2822,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 2.1068429946899414,
+      "rewards/margins": 7.130377769470215,
+      "rewards/rejected": -5.02353572845459,
+      "step": 70
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.2139262557029724,
+      "learning_rate": 4.677777777777778e-05,
+      "logits/chosen": 1.289627194404602,
+      "logits/rejected": 1.5509237051010132,
+      "logps/chosen": -37.245338439941406,
+      "logps/rejected": -143.37571716308594,
+      "loss": 0.2551,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 1.7066528797149658,
+      "rewards/margins": 8.251852989196777,
+      "rewards/rejected": -6.545199394226074,
+      "step": 80
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 9.060225486755371,
+      "learning_rate": 4.566666666666667e-05,
+      "logits/chosen": -0.21008212864398956,
+      "logits/rejected": 0.13004381954669952,
+      "logps/chosen": -34.545066833496094,
+      "logps/rejected": -136.86561584472656,
+      "loss": 0.2398,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 2.3621673583984375,
+      "rewards/margins": 8.225154876708984,
+      "rewards/rejected": -5.862987041473389,
+      "step": 90
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.8874521255493164,
+      "learning_rate": 4.4555555555555555e-05,
+      "logits/chosen": 0.8144568204879761,
+      "logits/rejected": 1.1611213684082031,
+      "logps/chosen": -41.461158752441406,
+      "logps/rejected": -139.0437469482422,
+      "loss": 0.2243,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.0751674175262451,
+      "rewards/margins": 7.963423728942871,
+      "rewards/rejected": -6.8882575035095215,
+      "step": 100
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.21037925779819489,
+      "learning_rate": 4.344444444444445e-05,
+      "logits/chosen": -0.559118390083313,
+      "logits/rejected": -0.11641822755336761,
+      "logps/chosen": -47.142601013183594,
+      "logps/rejected": -150.99496459960938,
+      "loss": 0.2594,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": 0.32266765832901,
+      "rewards/margins": 8.18213939666748,
+      "rewards/rejected": -7.859471321105957,
+      "step": 110
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.33475127816200256,
+      "learning_rate": 4.233333333333334e-05,
+      "logits/chosen": -0.39622828364372253,
+      "logits/rejected": -0.1825840175151825,
+      "logps/chosen": -46.026100158691406,
+      "logps/rejected": -142.27127075195312,
+      "loss": 0.2442,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 0.987580418586731,
+      "rewards/margins": 7.525818824768066,
+      "rewards/rejected": -6.538238525390625,
+      "step": 120
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.12689562141895294,
+      "learning_rate": 4.1222222222222224e-05,
+      "logits/chosen": -0.23490352928638458,
+      "logits/rejected": 0.27892929315567017,
+      "logps/chosen": -33.58977508544922,
+      "logps/rejected": -144.8148956298828,
+      "loss": 0.2096,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.9526748657226562,
+      "rewards/margins": 8.64609146118164,
+      "rewards/rejected": -6.693416595458984,
+      "step": 130
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.12881708145141602,
+      "learning_rate": 4.011111111111111e-05,
+      "logits/chosen": -1.1939542293548584,
+      "logits/rejected": -0.9672979116439819,
+      "logps/chosen": -37.64386749267578,
+      "logps/rejected": -125.4320068359375,
+      "loss": 0.2528,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 2.0000433921813965,
+      "rewards/margins": 6.926792144775391,
+      "rewards/rejected": -4.926749229431152,
+      "step": 140
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.21873943507671356,
+      "learning_rate": 3.9000000000000006e-05,
+      "logits/chosen": -1.780418038368225,
+      "logits/rejected": -1.4915210008621216,
+      "logps/chosen": -35.17759704589844,
+      "logps/rejected": -136.65286254882812,
+      "loss": 0.2278,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 1.875436544418335,
+      "rewards/margins": 8.086755752563477,
+      "rewards/rejected": -6.211319923400879,
+      "step": 150
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.053676556795835495,
+      "learning_rate": 3.7888888888888894e-05,
+      "logits/chosen": -1.770747423171997,
+      "logits/rejected": -1.2938441038131714,
+      "logps/chosen": -29.032825469970703,
+      "logps/rejected": -138.14309692382812,
+      "loss": 0.2089,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 2.1548972129821777,
+      "rewards/margins": 8.57084846496582,
+      "rewards/rejected": -6.41594934463501,
+      "step": 160
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.31680184602737427,
+      "learning_rate": 3.677777777777778e-05,
+      "logits/chosen": -1.9017817974090576,
+      "logits/rejected": -1.6287091970443726,
+      "logps/chosen": -32.30609893798828,
+      "logps/rejected": -135.4978485107422,
+      "loss": 0.1837,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 2.9330215454101562,
+      "rewards/margins": 8.456713676452637,
+      "rewards/rejected": -5.5236921310424805,
+      "step": 170
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.12343556433916092,
+      "learning_rate": 3.566666666666667e-05,
+      "logits/chosen": -2.0771210193634033,
+      "logits/rejected": -1.8654956817626953,
+      "logps/chosen": -38.074161529541016,
+      "logps/rejected": -140.7716522216797,
+      "loss": 0.2189,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.6962649822235107,
+      "rewards/margins": 8.185938835144043,
+      "rewards/rejected": -6.4896745681762695,
+      "step": 180
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.16018041968345642,
+      "learning_rate": 3.4555555555555556e-05,
+      "logits/chosen": -2.5613696575164795,
+      "logits/rejected": -2.160233736038208,
+      "logps/chosen": -35.08837127685547,
+      "logps/rejected": -174.58566284179688,
+      "loss": 0.1491,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 1.949218511581421,
+      "rewards/margins": 11.258779525756836,
+      "rewards/rejected": -9.309560775756836,
+      "step": 190
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.166445016860962,
+      "learning_rate": 3.3444444444444443e-05,
+      "logits/chosen": -3.0443778038024902,
+      "logits/rejected": -2.7526583671569824,
+      "logps/chosen": -40.106178283691406,
+      "logps/rejected": -151.62503051757812,
+      "loss": 0.2624,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.3750978708267212,
+      "rewards/margins": 9.279211044311523,
+      "rewards/rejected": -7.904112339019775,
+      "step": 200
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.3322606384754181,
+      "learning_rate": 3.233333333333333e-05,
+      "logits/chosen": -2.9914917945861816,
+      "logits/rejected": -2.5901548862457275,
+      "logps/chosen": -43.788307189941406,
+      "logps/rejected": -210.02102661132812,
+      "loss": 0.2258,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.1431424617767334,
+      "rewards/margins": 13.883976936340332,
+      "rewards/rejected": -12.740835189819336,
+      "step": 210
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.2920965850353241,
+      "learning_rate": 3.1222222222222225e-05,
+      "logits/chosen": -2.3677401542663574,
+      "logits/rejected": -1.9734885692596436,
+      "logps/chosen": -36.96697235107422,
+      "logps/rejected": -187.7698211669922,
+      "loss": 0.2081,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 1.8709278106689453,
+      "rewards/margins": 12.740228652954102,
+      "rewards/rejected": -10.86929988861084,
+      "step": 220
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.15863250195980072,
+      "learning_rate": 3.0111111111111113e-05,
+      "logits/chosen": -1.819131851196289,
+      "logits/rejected": -1.4921624660491943,
+      "logps/chosen": -41.595420837402344,
+      "logps/rejected": -186.645751953125,
+      "loss": 0.1995,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 0.9655638933181763,
+      "rewards/margins": 12.226719856262207,
+      "rewards/rejected": -11.26115608215332,
+      "step": 230
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.0697341114282608,
+      "learning_rate": 2.9e-05,
+      "logits/chosen": -2.357139825820923,
+      "logits/rejected": -1.888144850730896,
+      "logps/chosen": -52.9119987487793,
+      "logps/rejected": -263.25390625,
+      "loss": 0.1824,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 0.7968165874481201,
+      "rewards/margins": 18.26348304748535,
+      "rewards/rejected": -17.466665267944336,
+      "step": 240
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8565608859062195,
+      "learning_rate": 2.788888888888889e-05,
+      "logits/chosen": -2.9249751567840576,
+      "logits/rejected": -2.6594655513763428,
+      "logps/chosen": -49.89072799682617,
+      "logps/rejected": -190.1117401123047,
+      "loss": 0.2175,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.047927260398864746,
+      "rewards/margins": 11.593302726745605,
+      "rewards/rejected": -11.54537582397461,
+      "step": 250
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.4322703778743744,
+      "learning_rate": 2.677777777777778e-05,
+      "logits/chosen": -2.591165781021118,
+      "logits/rejected": -2.2559447288513184,
+      "logps/chosen": -42.47401428222656,
+      "logps/rejected": -188.3767547607422,
+      "loss": 0.2081,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.9701582789421082,
+      "rewards/margins": 12.480576515197754,
+      "rewards/rejected": -11.510419845581055,
+      "step": 260
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.19003595411777496,
+      "learning_rate": 2.5666666666666666e-05,
+      "logits/chosen": -3.374302625656128,
+      "logits/rejected": -3.0488531589508057,
+      "logps/chosen": -57.8838996887207,
+      "logps/rejected": -193.90777587890625,
+      "loss": 0.3035,
+      "rewards/accuracies": 0.5874999761581421,
+      "rewards/chosen": -0.37895283102989197,
+      "rewards/margins": 11.51020622253418,
+      "rewards/rejected": -11.889159202575684,
+      "step": 270
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.16604876518249512,
+      "learning_rate": 2.4555555555555557e-05,
+      "logits/chosen": -3.1895713806152344,
+      "logits/rejected": -2.834735870361328,
+      "logps/chosen": -52.5036735534668,
+      "logps/rejected": -177.6607666015625,
+      "loss": 0.2516,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": 0.857752799987793,
+      "rewards/margins": 10.699987411499023,
+      "rewards/rejected": -9.84223461151123,
+      "step": 280
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.14234374463558197,
+      "learning_rate": 2.3444444444444448e-05,
+      "logits/chosen": -3.344165086746216,
+      "logits/rejected": -3.020646572113037,
+      "logps/chosen": -41.34022903442383,
+      "logps/rejected": -178.89938354492188,
+      "loss": 0.2602,
+      "rewards/accuracies": 0.637499988079071,
+      "rewards/chosen": 1.0710757970809937,
+      "rewards/margins": 11.487492561340332,
+      "rewards/rejected": -10.416417121887207,
+      "step": 290
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.1858437955379486,
+      "learning_rate": 2.2333333333333335e-05,
+      "logits/chosen": -3.0915908813476562,
+      "logits/rejected": -2.762167453765869,
+      "logps/chosen": -41.24951171875,
+      "logps/rejected": -172.49880981445312,
+      "loss": 0.2256,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.1378252506256104,
+      "rewards/margins": 10.839186668395996,
+      "rewards/rejected": -9.701360702514648,
+      "step": 300
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.2519996762275696,
+      "learning_rate": 2.1222222222222223e-05,
+      "logits/chosen": -3.076692581176758,
+      "logits/rejected": -2.7446165084838867,
+      "logps/chosen": -50.308746337890625,
+      "logps/rejected": -204.6868896484375,
+      "loss": 0.165,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 0.4235803484916687,
+      "rewards/margins": 13.201803207397461,
+      "rewards/rejected": -12.778223037719727,
+      "step": 310
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.3874475657939911,
+      "learning_rate": 2.011111111111111e-05,
+      "logits/chosen": -3.646862030029297,
+      "logits/rejected": -3.424621105194092,
+      "logps/chosen": -52.49565505981445,
+      "logps/rejected": -167.20236206054688,
+      "loss": 0.2347,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 0.23652243614196777,
+      "rewards/margins": 9.693285942077637,
+      "rewards/rejected": -9.456764221191406,
+      "step": 320
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.2814558148384094,
+      "learning_rate": 1.9e-05,
+      "logits/chosen": -3.1871893405914307,
+      "logits/rejected": -2.7857449054718018,
+      "logps/chosen": -50.25436782836914,
+      "logps/rejected": -183.965087890625,
+      "loss": 0.269,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.5717954039573669,
+      "rewards/margins": 11.194442749023438,
+      "rewards/rejected": -10.622648239135742,
+      "step": 330
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.2564876973628998,
+      "learning_rate": 1.788888888888889e-05,
+      "logits/chosen": -3.328599452972412,
+      "logits/rejected": -2.8498024940490723,
+      "logps/chosen": -40.71959686279297,
+      "logps/rejected": -194.56871032714844,
+      "loss": 0.1908,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 1.3430808782577515,
+      "rewards/margins": 13.080599784851074,
+      "rewards/rejected": -11.737520217895508,
+      "step": 340
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.2628025412559509,
+      "learning_rate": 1.677777777777778e-05,
+      "logits/chosen": -4.046440124511719,
+      "logits/rejected": -3.7269904613494873,
+      "logps/chosen": -46.230613708496094,
+      "logps/rejected": -186.4309539794922,
+      "loss": 0.2016,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 0.4831501543521881,
+      "rewards/margins": 11.869375228881836,
+      "rewards/rejected": -11.386224746704102,
+      "step": 350
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.22657158970832825,
+      "learning_rate": 1.5666666666666667e-05,
+      "logits/chosen": -3.75866961479187,
+      "logits/rejected": -3.361738681793213,
+      "logps/chosen": -49.731544494628906,
+      "logps/rejected": -203.48196411132812,
+      "loss": 0.165,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": 0.7678171992301941,
+      "rewards/margins": 12.776975631713867,
+      "rewards/rejected": -12.009159088134766,
+      "step": 360
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.2632221281528473,
+      "learning_rate": 1.4555555555555556e-05,
+      "logits/chosen": -3.995814561843872,
+      "logits/rejected": -3.644721508026123,
+      "logps/chosen": -48.3692626953125,
+      "logps/rejected": -201.17593383789062,
+      "loss": 0.1649,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": 0.5727468729019165,
+      "rewards/margins": 12.856643676757812,
+      "rewards/rejected": -12.283895492553711,
+      "step": 370
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.1788269430398941,
+      "learning_rate": 1.3444444444444445e-05,
+      "logits/chosen": -3.70817494392395,
+      "logits/rejected": -3.3923275470733643,
+      "logps/chosen": -40.871490478515625,
+      "logps/rejected": -171.85128784179688,
+      "loss": 0.2101,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": 0.9809708595275879,
+      "rewards/margins": 11.068758010864258,
+      "rewards/rejected": -10.087786674499512,
+      "step": 380
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.14607764780521393,
+      "learning_rate": 1.2333333333333334e-05,
+      "logits/chosen": -3.0384268760681152,
+      "logits/rejected": -2.7124972343444824,
+      "logps/chosen": -36.8101806640625,
+      "logps/rejected": -163.4900360107422,
+      "loss": 0.26,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 1.447727084159851,
+      "rewards/margins": 10.76397705078125,
+      "rewards/rejected": -9.316250801086426,
+      "step": 390
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.21636660397052765,
+      "learning_rate": 1.1222222222222224e-05,
+      "logits/chosen": -3.6440536975860596,
+      "logits/rejected": -3.278002977371216,
+      "logps/chosen": -41.639305114746094,
+      "logps/rejected": -200.2166290283203,
+      "loss": 0.1822,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 1.6405818462371826,
+      "rewards/margins": 13.554621696472168,
+      "rewards/rejected": -11.914040565490723,
+      "step": 400
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.11900901794433594,
+      "learning_rate": 1.0111111111111111e-05,
+      "logits/chosen": -3.0452122688293457,
+      "logits/rejected": -2.5407042503356934,
+      "logps/chosen": -37.94886016845703,
+      "logps/rejected": -153.2200469970703,
+      "loss": 0.2347,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 1.7741081714630127,
+      "rewards/margins": 9.864465713500977,
+      "rewards/rejected": -8.090356826782227,
+      "step": 410
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.05728014558553696,
+      "learning_rate": 9e-06,
+      "logits/chosen": -3.795870304107666,
+      "logits/rejected": -3.469318389892578,
+      "logps/chosen": -34.80308151245117,
+      "logps/rejected": -195.09146118164062,
+      "loss": 0.1996,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": 1.8775447607040405,
+      "rewards/margins": 13.589404106140137,
+      "rewards/rejected": -11.711858749389648,
+      "step": 420
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 0.153469517827034,
+      "learning_rate": 7.88888888888889e-06,
+      "logits/chosen": -3.887744426727295,
+      "logits/rejected": -3.5376434326171875,
+      "logps/chosen": -34.76511001586914,
+      "logps/rejected": -146.95310974121094,
+      "loss": 0.2602,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": 1.5828745365142822,
+      "rewards/margins": 9.252839088439941,
+      "rewards/rejected": -7.669964790344238,
+      "step": 430
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.16263523697853088,
+      "learning_rate": 6.777777777777779e-06,
+      "logits/chosen": -3.6285464763641357,
+      "logits/rejected": -3.208299160003662,
+      "logps/chosen": -29.505624771118164,
+      "logps/rejected": -147.29527282714844,
+      "loss": 0.269,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 2.1386911869049072,
+      "rewards/margins": 9.6033296585083,
+      "rewards/rejected": -7.464638710021973,
+      "step": 440
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.01779480278491974,
+      "learning_rate": 5.666666666666667e-06,
+      "logits/chosen": -3.886363983154297,
+      "logits/rejected": -3.3980984687805176,
+      "logps/chosen": -37.660362243652344,
+      "logps/rejected": -191.5253143310547,
+      "loss": 0.2082,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": 1.585105538368225,
+      "rewards/margins": 12.881246566772461,
+      "rewards/rejected": -11.296142578125,
+      "step": 450
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.21525858342647552,
+      "learning_rate": 4.555555555555556e-06,
+      "logits/chosen": -3.215524673461914,
+      "logits/rejected": -2.8312759399414062,
+      "logps/chosen": -39.14852523803711,
+      "logps/rejected": -190.01809692382812,
+      "loss": 0.165,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 1.5289268493652344,
+      "rewards/margins": 12.520524978637695,
+      "rewards/rejected": -10.991598129272461,
+      "step": 460
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.19355317950248718,
+      "learning_rate": 3.4444444444444444e-06,
+      "logits/chosen": -3.51098895072937,
+      "logits/rejected": -3.231642484664917,
+      "logps/chosen": -39.47585678100586,
+      "logps/rejected": -193.40306091308594,
+      "loss": 0.2182,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 1.1096737384796143,
+      "rewards/margins": 12.903974533081055,
+      "rewards/rejected": -11.79430103302002,
+      "step": 470
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.20150351524353027,
+      "learning_rate": 2.3333333333333336e-06,
+      "logits/chosen": -3.484516143798828,
+      "logits/rejected": -3.1024327278137207,
+      "logps/chosen": -42.00218963623047,
+      "logps/rejected": -183.51300048828125,
+      "loss": 0.1822,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": 1.525578260421753,
+      "rewards/margins": 11.946281433105469,
+      "rewards/rejected": -10.420703887939453,
+      "step": 480
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.011142472736537457,
+      "learning_rate": 1.2222222222222223e-06,
+      "logits/chosen": -3.6615467071533203,
+      "logits/rejected": -3.2794384956359863,
+      "logps/chosen": -41.063148498535156,
+      "logps/rejected": -208.94747924804688,
+      "loss": 0.1647,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": 1.4969767332077026,
+      "rewards/margins": 14.444828987121582,
+      "rewards/rejected": -12.947853088378906,
+      "step": 490
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.214690163731575,
+      "learning_rate": 1.1111111111111112e-07,
+      "logits/chosen": -3.919487714767456,
+      "logits/rejected": -3.6030335426330566,
+      "logps/chosen": -34.534332275390625,
+      "logps/rejected": -180.12123107910156,
+      "loss": 0.2348,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": 2.082820177078247,
+      "rewards/margins": 12.23314094543457,
+      "rewards/rejected": -10.150321006774902,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:620ad83214f09c07b562685e5c4a615d6dc192dd64a1fa24d684c1e7a11a842b
+size 6929

special_tokens_map.json

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

tokenizer.json

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

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": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}