Upload DPO fine-tuned Qwen model

.gitattributes

@@ -33,3 +33,5 @@ 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-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,38 @@
+---
+license: apache-2.0
+base_model: unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit
+tags:
+- dpo
+- qwen
+- lmsys
+- mt-bench
+datasets:
+- lmsys/lmsys-arena-human-preference-55k
+language:
+- en
+---
+
+# Qwen3-8B DPO LMSYS
+
+This model is a DPO fine-tuned version of Qwen2.5-1.5B-Instruct, trained on the LMSYS Arena Human Preference dataset.
+
+## Training Details
+- **Base Model**: unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit
+- **Training Method**: Direct Preference Optimization (DPO)
+- **Dataset**: LMSYS Arena Human Preference 55k
+- **Training Steps**: 60
+- **Beta**: 0.1
+
+## MT-Bench-101 Results
+- DPO Score: Check results.json
+- Improvement over SFT baseline: Check results.json
+
+## Usage
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("subbuc/qwen3-8b-dpo-lmsys")
+tokenizer = AutoTokenizer.from_pretrained("subbuc/qwen3-8b-dpo-lmsys")
+
+# Your inference code here
+```

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5241b98e87f1073fe3db936e028be8d1f4f197df74b7df50cc2fdca2619ec06
+size 61380432

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 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-500/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-8B
+- dpo
+- lora
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-500/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-8B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "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:a5241b98e87f1073fe3db936e028be8d1f4f197df74b7df50cc2fdca2619ec06
+size 61380432

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 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f186d0210749a1d3cbd4ae548e2fac90acd25f314e4de663088f109ba0010753
+size 122930379

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea11996454b5587fcf33ae0ab5cf14b2031bf5f53f8c2ed5a48e87de31e29c84
+size 14645

checkpoint-500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19b0a154cf50d071d1c349720102c7099d4aba2d5e797b0f73729b3f5b9d52b4
+size 1383

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 +1,25 @@
+{
+  "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": "<|im_end|>"
+}

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 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,944 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 50,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.336705207824707,
+      "learning_rate": 4.5e-06,
+      "logits/chosen": 0.2884472906589508,
+      "logits/rejected": 0.40965142846107483,
+      "logps/chosen": -355.646728515625,
+      "logps/rejected": -305.0962219238281,
+      "loss": 0.6936,
+      "rewards/accuracies": 0.4000000059604645,
+      "rewards/chosen": 0.0013779326109215617,
+      "rewards/margins": -0.0006383258732967079,
+      "rewards/rejected": 0.0020162579603493214,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 6.066710472106934,
+      "learning_rate": 9.5e-06,
+      "logits/chosen": 0.14486190676689148,
+      "logits/rejected": 0.27484434843063354,
+      "logps/chosen": -345.3768005371094,
+      "logps/rejected": -362.3075866699219,
+      "loss": 0.6939,
+      "rewards/accuracies": 0.4833333492279053,
+      "rewards/chosen": 0.011982182040810585,
+      "rewards/margins": -0.0012166720116510987,
+      "rewards/rejected": 0.01319885440170765,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 4.703575611114502,
+      "learning_rate": 1.45e-05,
+      "logits/chosen": 0.10680116713047028,
+      "logits/rejected": -0.018802711740136147,
+      "logps/chosen": -325.0574951171875,
+      "logps/rejected": -256.40966796875,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.5666666626930237,
+      "rewards/chosen": 0.023517221212387085,
+      "rewards/margins": 0.0013313140952959657,
+      "rewards/rejected": 0.022185906767845154,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 5.95698881149292,
+      "learning_rate": 1.9500000000000003e-05,
+      "logits/chosen": 0.23321613669395447,
+      "logits/rejected": 0.29815709590911865,
+      "logps/chosen": -414.88934326171875,
+      "logps/rejected": -364.77337646484375,
+      "loss": 0.6867,
+      "rewards/accuracies": 0.5333333611488342,
+      "rewards/chosen": 0.08108480274677277,
+      "rewards/margins": 0.01509697176516056,
+      "rewards/rejected": 0.06598783284425735,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 6.212809085845947,
+      "learning_rate": 2.45e-05,
+      "logits/chosen": 0.05829133838415146,
+      "logits/rejected": 0.26185548305511475,
+      "logps/chosen": -376.5933532714844,
+      "logps/rejected": -321.00665283203125,
+      "loss": 0.6879,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": 0.11275690793991089,
+      "rewards/margins": 0.012456582859158516,
+      "rewards/rejected": 0.10030031204223633,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "eval_logits/chosen": 0.037971604615449905,
+      "eval_logits/rejected": 0.29195430874824524,
+      "eval_logps/chosen": -384.281005859375,
+      "eval_logps/rejected": -340.8085021972656,
+      "eval_loss": 0.6827343106269836,
+      "eval_rewards/accuracies": 0.5526315569877625,
+      "eval_rewards/chosen": 0.17324700951576233,
+      "eval_rewards/margins": 0.028422411531209946,
+      "eval_rewards/rejected": 0.1448245793581009,
+      "eval_runtime": 111.1391,
+      "eval_samples_per_second": 2.699,
+      "eval_steps_per_second": 0.342,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 6.0398640632629395,
+      "learning_rate": 2.95e-05,
+      "logits/chosen": -0.11122157424688339,
+      "logits/rejected": -0.00746047031134367,
+      "logps/chosen": -408.02142333984375,
+      "logps/rejected": -358.9617614746094,
+      "loss": 0.6761,
+      "rewards/accuracies": 0.5833333134651184,
+      "rewards/chosen": 0.2293107807636261,
+      "rewards/margins": 0.041216298937797546,
+      "rewards/rejected": 0.18809448182582855,
+      "step": 60
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 7.345890998840332,
+      "learning_rate": 3.45e-05,
+      "logits/chosen": 0.24562212824821472,
+      "logits/rejected": 0.27121594548225403,
+      "logps/chosen": -431.5135803222656,
+      "logps/rejected": -357.45062255859375,
+      "loss": 0.6816,
+      "rewards/accuracies": 0.5833333730697632,
+      "rewards/chosen": 0.36051273345947266,
+      "rewards/margins": 0.04433435946702957,
+      "rewards/rejected": 0.3161783814430237,
+      "step": 70
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 5.378597736358643,
+      "learning_rate": 3.9500000000000005e-05,
+      "logits/chosen": -0.055510133504867554,
+      "logits/rejected": 0.06074449419975281,
+      "logps/chosen": -349.5056457519531,
+      "logps/rejected": -298.19189453125,
+      "loss": 0.6674,
+      "rewards/accuracies": 0.5166666507720947,
+      "rewards/chosen": 0.4240848124027252,
+      "rewards/margins": 0.0907500609755516,
+      "rewards/rejected": 0.333334743976593,
+      "step": 80
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 5.009306907653809,
+      "learning_rate": 4.4500000000000004e-05,
+      "logits/chosen": 0.460761696100235,
+      "logits/rejected": 0.3970041871070862,
+      "logps/chosen": -343.3364562988281,
+      "logps/rejected": -346.8429870605469,
+      "loss": 0.6964,
+      "rewards/accuracies": 0.5666666626930237,
+      "rewards/chosen": 0.4095408320426941,
+      "rewards/margins": 0.03334635868668556,
+      "rewards/rejected": 0.37619444727897644,
+      "step": 90
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 6.515726089477539,
+      "learning_rate": 4.9500000000000004e-05,
+      "logits/chosen": 0.10559816658496857,
+      "logits/rejected": 0.21364697813987732,
+      "logps/chosen": -418.237060546875,
+      "logps/rejected": -369.6095275878906,
+      "loss": 0.6765,
+      "rewards/accuracies": 0.5666666626930237,
+      "rewards/chosen": 0.40842658281326294,
+      "rewards/margins": 0.059928763657808304,
+      "rewards/rejected": 0.34849780797958374,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "eval_logits/chosen": 0.06404649466276169,
+      "eval_logits/rejected": 0.307973176240921,
+      "eval_logps/chosen": -382.68243408203125,
+      "eval_logps/rejected": -339.8092041015625,
+      "eval_loss": 0.6607274413108826,
+      "eval_rewards/accuracies": 0.6414473652839661,
+      "eval_rewards/chosen": 0.33310821652412415,
+      "eval_rewards/margins": 0.08835449069738388,
+      "eval_rewards/rejected": 0.24475376307964325,
+      "eval_runtime": 110.7672,
+      "eval_samples_per_second": 2.708,
+      "eval_steps_per_second": 0.343,
+      "step": 100
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 5.3176984786987305,
+      "learning_rate": 4.8875e-05,
+      "logits/chosen": 0.2970436215400696,
+      "logits/rejected": 0.26611050963401794,
+      "logps/chosen": -400.3771667480469,
+      "logps/rejected": -406.6891174316406,
+      "loss": 0.7081,
+      "rewards/accuracies": 0.4166666567325592,
+      "rewards/chosen": 0.19517870247364044,
+      "rewards/margins": -0.013467788696289062,
+      "rewards/rejected": 0.2086464911699295,
+      "step": 110
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 7.095144271850586,
+      "learning_rate": 4.7625000000000006e-05,
+      "logits/chosen": -0.06270237267017365,
+      "logits/rejected": 0.049232300370931625,
+      "logps/chosen": -377.08111572265625,
+      "logps/rejected": -326.0290832519531,
+      "loss": 0.687,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -0.038210123777389526,
+      "rewards/margins": 0.03700611740350723,
+      "rewards/rejected": -0.07521622627973557,
+      "step": 120
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 5.485899925231934,
+      "learning_rate": 4.6375e-05,
+      "logits/chosen": 0.2947315573692322,
+      "logits/rejected": 0.30565229058265686,
+      "logps/chosen": -432.36138916015625,
+      "logps/rejected": -352.40203857421875,
+      "loss": 0.6736,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 0.17748937010765076,
+      "rewards/margins": 0.07449595630168915,
+      "rewards/rejected": 0.1029934287071228,
+      "step": 130
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 7.982489109039307,
+      "learning_rate": 4.5125e-05,
+      "logits/chosen": 0.22027187049388885,
+      "logits/rejected": 0.12688283622264862,
+      "logps/chosen": -400.2425842285156,
+      "logps/rejected": -338.5372009277344,
+      "loss": 0.6942,
+      "rewards/accuracies": 0.5166666507720947,
+      "rewards/chosen": 0.52669757604599,
+      "rewards/margins": 0.03541693836450577,
+      "rewards/rejected": 0.4912806451320648,
+      "step": 140
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.92340612411499,
+      "learning_rate": 4.3875e-05,
+      "logits/chosen": 0.4400368332862854,
+      "logits/rejected": 0.6112634539604187,
+      "logps/chosen": -373.4757995605469,
+      "logps/rejected": -313.86419677734375,
+      "loss": 0.6812,
+      "rewards/accuracies": 0.5500000715255737,
+      "rewards/chosen": 0.6615363955497742,
+      "rewards/margins": 0.07090020179748535,
+      "rewards/rejected": 0.590636134147644,
+      "step": 150
+    },
+    {
+      "epoch": 0.3,
+      "eval_logits/chosen": 0.18306924402713776,
+      "eval_logits/rejected": 0.41837078332901,
+      "eval_logps/chosen": -377.95928955078125,
+      "eval_logps/rejected": -335.8048400878906,
+      "eval_loss": 0.6639418601989746,
+      "eval_rewards/accuracies": 0.5921052694320679,
+      "eval_rewards/chosen": 0.8054203391075134,
+      "eval_rewards/margins": 0.16022570431232452,
+      "eval_rewards/rejected": 0.6451946496963501,
+      "eval_runtime": 110.7635,
+      "eval_samples_per_second": 2.708,
+      "eval_steps_per_second": 0.343,
+      "step": 150
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 5.507699489593506,
+      "learning_rate": 4.2625000000000006e-05,
+      "logits/chosen": 0.06238343566656113,
+      "logits/rejected": 0.2610507011413574,
+      "logps/chosen": -354.340576171875,
+      "logps/rejected": -313.094482421875,
+      "loss": 0.6718,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": 0.7900612354278564,
+      "rewards/margins": 0.11699613183736801,
+      "rewards/rejected": 0.6730651259422302,
+      "step": 160
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 5.172399997711182,
+      "learning_rate": 4.1375e-05,
+      "logits/chosen": 0.14939634501934052,
+      "logits/rejected": 0.008766859769821167,
+      "logps/chosen": -388.7623291015625,
+      "logps/rejected": -325.0237731933594,
+      "loss": 0.6338,
+      "rewards/accuracies": 0.5833333730697632,
+      "rewards/chosen": 0.9776442646980286,
+      "rewards/margins": 0.25690537691116333,
+      "rewards/rejected": 0.7207388877868652,
+      "step": 170
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 9.718168258666992,
+      "learning_rate": 4.0125e-05,
+      "logits/chosen": 0.14167270064353943,
+      "logits/rejected": 0.18558117747306824,
+      "logps/chosen": -312.6748046875,
+      "logps/rejected": -317.16265869140625,
+      "loss": 0.739,
+      "rewards/accuracies": 0.5166666507720947,
+      "rewards/chosen": 0.5937276482582092,
+      "rewards/margins": -0.014927273616194725,
+      "rewards/rejected": 0.6086549162864685,
+      "step": 180
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 4.4349751472473145,
+      "learning_rate": 3.8875e-05,
+      "logits/chosen": -0.034669190645217896,
+      "logits/rejected": 0.22868581116199493,
+      "logps/chosen": -349.32037353515625,
+      "logps/rejected": -321.3941955566406,
+      "loss": 0.6525,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.5615012645721436,
+      "rewards/margins": 0.1495741307735443,
+      "rewards/rejected": 0.41192713379859924,
+      "step": 190
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.693329811096191,
+      "learning_rate": 3.7625e-05,
+      "logits/chosen": 0.15313725173473358,
+      "logits/rejected": 0.11542512476444244,
+      "logps/chosen": -438.50701904296875,
+      "logps/rejected": -376.7723388671875,
+      "loss": 0.6622,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": 0.4796217978000641,
+      "rewards/margins": 0.11786258220672607,
+      "rewards/rejected": 0.3617592453956604,
+      "step": 200
+    },
+    {
+      "epoch": 0.4,
+      "eval_logits/chosen": 0.07203032821416855,
+      "eval_logits/rejected": 0.2990891635417938,
+      "eval_logps/chosen": -381.4584045410156,
+      "eval_logps/rejected": -339.5525207519531,
+      "eval_loss": 0.6342300772666931,
+      "eval_rewards/accuracies": 0.6776315569877625,
+      "eval_rewards/chosen": 0.45550742745399475,
+      "eval_rewards/margins": 0.18508483469486237,
+      "eval_rewards/rejected": 0.2704225778579712,
+      "eval_runtime": 110.7746,
+      "eval_samples_per_second": 2.708,
+      "eval_steps_per_second": 0.343,
+      "step": 200
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 5.154126167297363,
+      "learning_rate": 3.6375e-05,
+      "logits/chosen": 0.14750126004219055,
+      "logits/rejected": 0.3790293335914612,
+      "logps/chosen": -354.99249267578125,
+      "logps/rejected": -334.5828857421875,
+      "loss": 0.6564,
+      "rewards/accuracies": 0.6166666746139526,
+      "rewards/chosen": 0.4125402569770813,
+      "rewards/margins": 0.1406583935022354,
+      "rewards/rejected": 0.2718818485736847,
+      "step": 210
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 6.265260696411133,
+      "learning_rate": 3.5125e-05,
+      "logits/chosen": 0.15185442566871643,
+      "logits/rejected": 0.2718904912471771,
+      "logps/chosen": -410.98809814453125,
+      "logps/rejected": -363.15625,
+      "loss": 0.6678,
+      "rewards/accuracies": 0.6166666746139526,
+      "rewards/chosen": 0.6292893290519714,
+      "rewards/margins": 0.11445705592632294,
+      "rewards/rejected": 0.5148323178291321,
+      "step": 220
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.842378616333008,
+      "learning_rate": 3.3875000000000003e-05,
+      "logits/chosen": 0.0003437995910644531,
+      "logits/rejected": 0.03505432978272438,
+      "logps/chosen": -397.8294372558594,
+      "logps/rejected": -355.87109375,
+      "loss": 0.6957,
+      "rewards/accuracies": 0.550000011920929,
+      "rewards/chosen": 0.8057634234428406,
+      "rewards/margins": 0.10026631504297256,
+      "rewards/rejected": 0.705497145652771,
+      "step": 230
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.746981620788574,
+      "learning_rate": 3.2625e-05,
+      "logits/chosen": 0.12059871107339859,
+      "logits/rejected": 0.32741162180900574,
+      "logps/chosen": -381.552734375,
+      "logps/rejected": -325.18353271484375,
+      "loss": 0.6424,
+      "rewards/accuracies": 0.6833332777023315,
+      "rewards/chosen": 0.6556231379508972,
+      "rewards/margins": 0.172928124666214,
+      "rewards/rejected": 0.4826950132846832,
+      "step": 240
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 9.265108108520508,
+      "learning_rate": 3.1375e-05,
+      "logits/chosen": -0.1159602627158165,
+      "logits/rejected": 0.2552518844604492,
+      "logps/chosen": -376.2705078125,
+      "logps/rejected": -324.96026611328125,
+      "loss": 0.6247,
+      "rewards/accuracies": 0.6833333373069763,
+      "rewards/chosen": 0.8996511697769165,
+      "rewards/margins": 0.2674979567527771,
+      "rewards/rejected": 0.6321532726287842,
+      "step": 250
+    },
+    {
+      "epoch": 0.5,
+      "eval_logits/chosen": 0.1787189394235611,
+      "eval_logits/rejected": 0.39825698733329773,
+      "eval_logps/chosen": -376.6689758300781,
+      "eval_logps/rejected": -335.21923828125,
+      "eval_loss": 0.6513052582740784,
+      "eval_rewards/accuracies": 0.625,
+      "eval_rewards/chosen": 0.9344526529312134,
+      "eval_rewards/margins": 0.23070192337036133,
+      "eval_rewards/rejected": 0.703750729560852,
+      "eval_runtime": 110.728,
+      "eval_samples_per_second": 2.709,
+      "eval_steps_per_second": 0.343,
+      "step": 250
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.690427303314209,
+      "learning_rate": 3.0125000000000004e-05,
+      "logits/chosen": 0.1452471762895584,
+      "logits/rejected": 0.41113168001174927,
+      "logps/chosen": -405.30914306640625,
+      "logps/rejected": -415.18988037109375,
+      "loss": 0.6646,
+      "rewards/accuracies": 0.6500000357627869,
+      "rewards/chosen": 1.1738603115081787,
+      "rewards/margins": 0.22889454662799835,
+      "rewards/rejected": 0.9449657201766968,
+      "step": 260
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 4.981466293334961,
+      "learning_rate": 2.8875e-05,
+      "logits/chosen": 0.28828543424606323,
+      "logits/rejected": 0.5267751812934875,
+      "logps/chosen": -389.50616455078125,
+      "logps/rejected": -327.06707763671875,
+      "loss": 0.662,
+      "rewards/accuracies": 0.5833333730697632,
+      "rewards/chosen": 0.9076725244522095,
+      "rewards/margins": 0.21977980434894562,
+      "rewards/rejected": 0.687892735004425,
+      "step": 270
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 6.570380687713623,
+      "learning_rate": 2.7625e-05,
+      "logits/chosen": 0.11337950080633163,
+      "logits/rejected": 0.17990311980247498,
+      "logps/chosen": -405.74981689453125,
+      "logps/rejected": -312.7770690917969,
+      "loss": 0.5859,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": 1.1182396411895752,
+      "rewards/margins": 0.39417314529418945,
+      "rewards/rejected": 0.7240666151046753,
+      "step": 280
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 6.601053237915039,
+      "learning_rate": 2.6375e-05,
+      "logits/chosen": 0.2042328119277954,
+      "logits/rejected": 0.28559383749961853,
+      "logps/chosen": -372.4433288574219,
+      "logps/rejected": -358.509033203125,
+      "loss": 0.6985,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.9518572688102722,
+      "rewards/margins": 0.1677892506122589,
+      "rewards/rejected": 0.7840681076049805,
+      "step": 290
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 5.195039749145508,
+      "learning_rate": 2.5124999999999997e-05,
+      "logits/chosen": 0.37824949622154236,
+      "logits/rejected": 0.29513710737228394,
+      "logps/chosen": -385.41351318359375,
+      "logps/rejected": -311.15765380859375,
+      "loss": 0.669,
+      "rewards/accuracies": 0.6333333253860474,
+      "rewards/chosen": 0.6893835067749023,
+      "rewards/margins": 0.19085724651813507,
+      "rewards/rejected": 0.4985261857509613,
+      "step": 300
+    },
+    {
+      "epoch": 0.6,
+      "eval_logits/chosen": 0.0961572527885437,
+      "eval_logits/rejected": 0.3124571740627289,
+      "eval_logps/chosen": -379.28277587890625,
+      "eval_logps/rejected": -338.0162048339844,
+      "eval_loss": 0.6259491443634033,
+      "eval_rewards/accuracies": 0.6743420958518982,
+      "eval_rewards/chosen": 0.673072099685669,
+      "eval_rewards/margins": 0.24901530146598816,
+      "eval_rewards/rejected": 0.4240567088127136,
+      "eval_runtime": 110.7031,
+      "eval_samples_per_second": 2.71,
+      "eval_steps_per_second": 0.343,
+      "step": 300
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 8.175043106079102,
+      "learning_rate": 2.3875e-05,
+      "logits/chosen": 0.23413066565990448,
+      "logits/rejected": 0.22633250057697296,
+      "logps/chosen": -381.376220703125,
+      "logps/rejected": -319.7635803222656,
+      "loss": 0.6727,
+      "rewards/accuracies": 0.5833333730697632,
+      "rewards/chosen": 0.6574802994728088,
+      "rewards/margins": 0.14561817049980164,
+      "rewards/rejected": 0.5118621587753296,
+      "step": 310
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 11.002555847167969,
+      "learning_rate": 2.2625e-05,
+      "logits/chosen": 0.07112519443035126,
+      "logits/rejected": 0.10473679006099701,
+      "logps/chosen": -312.57354736328125,
+      "logps/rejected": -294.7325134277344,
+      "loss": 0.6895,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": 0.4420788884162903,
+      "rewards/margins": 0.10067237913608551,
+      "rewards/rejected": 0.3414064943790436,
+      "step": 320
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 5.530636310577393,
+      "learning_rate": 2.1375e-05,
+      "logits/chosen": 0.03359542042016983,
+      "logits/rejected": 0.1980469524860382,
+      "logps/chosen": -368.728271484375,
+      "logps/rejected": -314.3133239746094,
+      "loss": 0.7041,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": 0.4892043173313141,
+      "rewards/margins": 0.07970868051052094,
+      "rewards/rejected": 0.40949565172195435,
+      "step": 330
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.663439750671387,
+      "learning_rate": 2.0125e-05,
+      "logits/chosen": 0.12911926209926605,
+      "logits/rejected": -0.05956228822469711,
+      "logps/chosen": -277.42279052734375,
+      "logps/rejected": -266.2348937988281,
+      "loss": 0.6537,
+      "rewards/accuracies": 0.5833333730697632,
+      "rewards/chosen": 0.4134989380836487,
+      "rewards/margins": 0.160436749458313,
+      "rewards/rejected": 0.2530621886253357,
+      "step": 340
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 7.686208724975586,
+      "learning_rate": 1.8875e-05,
+      "logits/chosen": 0.07862328737974167,
+      "logits/rejected": 0.07282784581184387,
+      "logps/chosen": -344.50140380859375,
+      "logps/rejected": -294.981689453125,
+      "loss": 0.615,
+      "rewards/accuracies": 0.6166666746139526,
+      "rewards/chosen": 0.46334782242774963,
+      "rewards/margins": 0.27687573432922363,
+      "rewards/rejected": 0.18647213280200958,
+      "step": 350
+    },
+    {
+      "epoch": 0.7,
+      "eval_logits/chosen": 0.05921909585595131,
+      "eval_logits/rejected": 0.2736007273197174,
+      "eval_logps/chosen": -380.28326416015625,
+      "eval_logps/rejected": -339.1015625,
+      "eval_loss": 0.6189608573913574,
+      "eval_rewards/accuracies": 0.6809210777282715,
+      "eval_rewards/chosen": 0.573022186756134,
+      "eval_rewards/margins": 0.25749993324279785,
+      "eval_rewards/rejected": 0.3155222237110138,
+      "eval_runtime": 110.7731,
+      "eval_samples_per_second": 2.708,
+      "eval_steps_per_second": 0.343,
+      "step": 350
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 5.948915004730225,
+      "learning_rate": 1.7625e-05,
+      "logits/chosen": 0.004181022755801678,
+      "logits/rejected": 0.17382146418094635,
+      "logps/chosen": -407.7164611816406,
+      "logps/rejected": -324.44140625,
+      "loss": 0.6017,
+      "rewards/accuracies": 0.6333333253860474,
+      "rewards/chosen": 0.6991059184074402,
+      "rewards/margins": 0.36650750041007996,
+      "rewards/rejected": 0.332598477602005,
+      "step": 360
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 8.058575630187988,
+      "learning_rate": 1.6375e-05,
+      "logits/chosen": 0.23957493901252747,
+      "logits/rejected": 0.08459005504846573,
+      "logps/chosen": -388.26007080078125,
+      "logps/rejected": -317.60614013671875,
+      "loss": 0.6179,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.7810655236244202,
+      "rewards/margins": 0.2609333395957947,
+      "rewards/rejected": 0.5201321840286255,
+      "step": 370
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 7.975735187530518,
+      "learning_rate": 1.5125e-05,
+      "logits/chosen": 0.39950278401374817,
+      "logits/rejected": 0.47223711013793945,
+      "logps/chosen": -395.3121032714844,
+      "logps/rejected": -350.27203369140625,
+      "loss": 0.6522,
+      "rewards/accuracies": 0.6500000357627869,
+      "rewards/chosen": 0.5671259164810181,
+      "rewards/margins": 0.16634422540664673,
+      "rewards/rejected": 0.40078169107437134,
+      "step": 380
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 5.167679309844971,
+      "learning_rate": 1.3875000000000002e-05,
+      "logits/chosen": 0.010129046626389027,
+      "logits/rejected": 0.2368415892124176,
+      "logps/chosen": -382.8428039550781,
+      "logps/rejected": -314.33636474609375,
+      "loss": 0.5346,
+      "rewards/accuracies": 0.7666667103767395,
+      "rewards/chosen": 0.7397487759590149,
+      "rewards/margins": 0.4875487685203552,
+      "rewards/rejected": 0.2521999478340149,
+      "step": 390
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.4159698486328125,
+      "learning_rate": 1.2625e-05,
+      "logits/chosen": 0.26140496134757996,
+      "logits/rejected": 0.40830284357070923,
+      "logps/chosen": -345.0839538574219,
+      "logps/rejected": -333.39727783203125,
+      "loss": 0.7407,
+      "rewards/accuracies": 0.5666666626930237,
+      "rewards/chosen": 0.540732741355896,
+      "rewards/margins": 0.11584854125976562,
+      "rewards/rejected": 0.42488422989845276,
+      "step": 400
+    },
+    {
+      "epoch": 0.8,
+      "eval_logits/chosen": 0.11569666862487793,
+      "eval_logits/rejected": 0.3240755498409271,
+      "eval_logps/chosen": -378.1927490234375,
+      "eval_logps/rejected": -337.3643493652344,
+      "eval_loss": 0.6259213089942932,
+      "eval_rewards/accuracies": 0.6710526347160339,
+      "eval_rewards/chosen": 0.7820738554000854,
+      "eval_rewards/margins": 0.29283180832862854,
+      "eval_rewards/rejected": 0.4892421066761017,
+      "eval_runtime": 110.7795,
+      "eval_samples_per_second": 2.708,
+      "eval_steps_per_second": 0.343,
+      "step": 400
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 3.0558745861053467,
+      "learning_rate": 1.1375e-05,
+      "logits/chosen": 0.052801378071308136,
+      "logits/rejected": 0.28615111112594604,
+      "logps/chosen": -305.16424560546875,
+      "logps/rejected": -311.2315368652344,
+      "loss": 0.7429,
+      "rewards/accuracies": 0.5666666626930237,
+      "rewards/chosen": 0.4710526466369629,
+      "rewards/margins": 0.03450847044587135,
+      "rewards/rejected": 0.43654412031173706,
+      "step": 410
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 7.435867786407471,
+      "learning_rate": 1.0125e-05,
+      "logits/chosen": 0.041792333126068115,
+      "logits/rejected": 0.17477649450302124,
+      "logps/chosen": -421.61370849609375,
+      "logps/rejected": -367.0201110839844,
+      "loss": 0.6739,
+      "rewards/accuracies": 0.6166666746139526,
+      "rewards/chosen": 0.728044331073761,
+      "rewards/margins": 0.22441256046295166,
+      "rewards/rejected": 0.5036317706108093,
+      "step": 420
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 6.1076765060424805,
+      "learning_rate": 8.875e-06,
+      "logits/chosen": 0.2842518091201782,
+      "logits/rejected": 0.39951667189598083,
+      "logps/chosen": -426.9200744628906,
+      "logps/rejected": -346.2352600097656,
+      "loss": 0.6611,
+      "rewards/accuracies": 0.5833333730697632,
+      "rewards/chosen": 0.647419810295105,
+      "rewards/margins": 0.18299394845962524,
+      "rewards/rejected": 0.46442586183547974,
+      "step": 430
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 6.9140119552612305,
+      "learning_rate": 7.625e-06,
+      "logits/chosen": 0.1984386146068573,
+      "logits/rejected": 0.19356411695480347,
+      "logps/chosen": -400.2377624511719,
+      "logps/rejected": -339.1898498535156,
+      "loss": 0.6277,
+      "rewards/accuracies": 0.6500000357627869,
+      "rewards/chosen": 0.6189283728599548,
+      "rewards/margins": 0.2557988464832306,
+      "rewards/rejected": 0.36312955617904663,
+      "step": 440
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.161813735961914,
+      "learning_rate": 6.375000000000001e-06,
+      "logits/chosen": -0.20740225911140442,
+      "logits/rejected": -0.04994301125407219,
+      "logps/chosen": -338.45245361328125,
+      "logps/rejected": -317.4515075683594,
+      "loss": 0.6085,
+      "rewards/accuracies": 0.6166667342185974,
+      "rewards/chosen": 0.6934888362884521,
+      "rewards/margins": 0.31230005621910095,
+      "rewards/rejected": 0.3811888098716736,
+      "step": 450
+    },
+    {
+      "epoch": 0.9,
+      "eval_logits/chosen": 0.101429283618927,
+      "eval_logits/rejected": 0.31124716997146606,
+      "eval_logps/chosen": -378.19146728515625,
+      "eval_logps/rejected": -337.322998046875,
+      "eval_loss": 0.6227030158042908,
+      "eval_rewards/accuracies": 0.6776315569877625,
+      "eval_rewards/chosen": 0.7822019457817078,
+      "eval_rewards/margins": 0.28882354497909546,
+      "eval_rewards/rejected": 0.4933784008026123,
+      "eval_runtime": 110.747,
+      "eval_samples_per_second": 2.709,
+      "eval_steps_per_second": 0.343,
+      "step": 450
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 9.481136322021484,
+      "learning_rate": 5.125e-06,
+      "logits/chosen": 0.22967512905597687,
+      "logits/rejected": 0.469778835773468,
+      "logps/chosen": -368.9932556152344,
+      "logps/rejected": -301.64935302734375,
+      "loss": 0.6316,
+      "rewards/accuracies": 0.7166666984558105,
+      "rewards/chosen": 0.6519312858581543,
+      "rewards/margins": 0.2591342329978943,
+      "rewards/rejected": 0.39279705286026,
+      "step": 460
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 5.284605979919434,
+      "learning_rate": 3.875e-06,
+      "logits/chosen": -0.15741905570030212,
+      "logits/rejected": -0.07267796993255615,
+      "logps/chosen": -413.9580078125,
+      "logps/rejected": -352.0941467285156,
+      "loss": 0.6124,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": 0.9669933319091797,
+      "rewards/margins": 0.3869830369949341,
+      "rewards/rejected": 0.5800102949142456,
+      "step": 470
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 6.971217632293701,
+      "learning_rate": 2.625e-06,
+      "logits/chosen": 0.2067793607711792,
+      "logits/rejected": 0.10978493839502335,
+      "logps/chosen": -378.26171875,
+      "logps/rejected": -322.6770324707031,
+      "loss": 0.6398,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": 0.8436048626899719,
+      "rewards/margins": 0.2645290493965149,
+      "rewards/rejected": 0.5790757536888123,
+      "step": 480
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 4.2455949783325195,
+      "learning_rate": 1.3750000000000002e-06,
+      "logits/chosen": 0.355533629655838,
+      "logits/rejected": 0.5946205258369446,
+      "logps/chosen": -393.5543518066406,
+      "logps/rejected": -336.9477844238281,
+      "loss": 0.642,
+      "rewards/accuracies": 0.6166666746139526,
+      "rewards/chosen": 0.7117866277694702,
+      "rewards/margins": 0.19295310974121094,
+      "rewards/rejected": 0.5188335180282593,
+      "step": 490
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.31891393661499,
+      "learning_rate": 1.2500000000000002e-07,
+      "logits/chosen": 0.09795437753200531,
+      "logits/rejected": 0.1788286566734314,
+      "logps/chosen": -352.4245910644531,
+      "logps/rejected": -358.0443115234375,
+      "loss": 0.7074,
+      "rewards/accuracies": 0.533333420753479,
+      "rewards/chosen": 0.7603829503059387,
+      "rewards/margins": 0.06259284913539886,
+      "rewards/rejected": 0.6977900266647339,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_logits/chosen": 0.10699369758367538,
+      "eval_logits/rejected": 0.31676366925239563,
+      "eval_logps/chosen": -377.9751892089844,
+      "eval_logps/rejected": -337.1114196777344,
+      "eval_loss": 0.623928427696228,
+      "eval_rewards/accuracies": 0.6710526347160339,
+      "eval_rewards/chosen": 0.8038315176963806,
+      "eval_rewards/margins": 0.2892968952655792,
+      "eval_rewards/rejected": 0.5145345330238342,
+      "eval_runtime": 110.7474,
+      "eval_samples_per_second": 2.709,
+      "eval_steps_per_second": 0.343,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "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": 6,
+  "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:aa1df34eab5c4775a41133724939f4a42d2f1b9419ec37eb124d8d1896c04ec4
+size 6865

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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": "<|im_end|>"
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa1df34eab5c4775a41133724939f4a42d2f1b9419ec37eb124d8d1896c04ec4
+size 6865