Upload run qwen3_4b_eval_aware on 2025-10-25T22:30:51.946276Z

.gitattributes

@@ -38,3 +38,5 @@ qwen3_4b_bw96x4_dpo_ipo_b005_lr5e6_acc2/checkpoint-160/tokenizer.json filter=lfs
 qwen3_4b_bw96x4_dpo_ipo_b005_lr5e6_acc2/checkpoint-190/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen3_4b_bw96x4_dpo_ipo_b005_lr5e6_acc2/checkpoint-80/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen3_4b_bw96x4_dpo_ipo_b005_lr5e6_acc2/dpo_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen3_4b_eval_aware/checkpoint-32/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen3_4b_eval_aware/dpo_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen3_4b_eval_aware/checkpoint-32/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-4B-Thinking-2507
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Thinking-2507
+- 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

qwen3_4b_eval_aware/checkpoint-32/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Thinking-2507",
+  "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": [
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen3_4b_eval_aware/checkpoint-32/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bca19a61d584af3d4e051bdde7c5f4b4c9470d34b0c3dd3669566cf0aa0c1b24
+size 132187888

qwen3_4b_eval_aware/checkpoint-32/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
+}

qwen3_4b_eval_aware/checkpoint-32/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<think>\n' }}
+{%- endif %}

qwen3_4b_eval_aware/checkpoint-32/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a178154b05157df67ecd072585672f37f13c28e7285facefd683001aac93ecf
+size 264673227

qwen3_4b_eval_aware/checkpoint-32/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dd7671ce88d469c49c0530724ac76b2306574002d1ecd1ca9294e41621fd96a
+size 14917

qwen3_4b_eval_aware/checkpoint-32/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3246ef1170ccca541a03b89ad6f20e01c51eb6834a2c2211c78c71c70f896879
+size 14917

qwen3_4b_eval_aware/checkpoint-32/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a873edb088ab5375860da6f7ca28d9a12eead3ab160a0aba3ea3b08e3f37d3
+size 1465

qwen3_4b_eval_aware/checkpoint-32/special_tokens_map.json

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

qwen3_4b_eval_aware/checkpoint-32/tokenizer.json

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

qwen3_4b_eval_aware/checkpoint-32/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": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen3_4b_eval_aware/checkpoint-32/trainer_state.json

@@ -0,0 +1,514 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5079365079365079,
+  "eval_steps": 50,
+  "global_step": 32,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015873015873015872,
+      "grad_norm": 73.43138122558594,
+      "learning_rate": 0.0,
+      "logits/chosen": -2.1276862621307373,
+      "logits/rejected": -2.3007192611694336,
+      "logps/chosen": -0.837126612663269,
+      "logps/rejected": -1.6845022439956665,
+      "loss": 100.575,
+      "rewards/accuracies": 0.4375,
+      "rewards/chosen": 0.009719086810946465,
+      "rewards/margins": -0.0013557381462305784,
+      "rewards/rejected": 0.011074826121330261,
+      "step": 1
+    },
+    {
+      "epoch": 0.031746031746031744,
+      "grad_norm": 61.139373779296875,
+      "learning_rate": 5e-06,
+      "logits/chosen": -2.224215030670166,
+      "logits/rejected": -2.4488682746887207,
+      "logps/chosen": -0.8742778301239014,
+      "logps/rejected": -1.7331535816192627,
+      "loss": 100.7677,
+      "rewards/accuracies": 0.59375,
+      "rewards/chosen": 0.01031375490128994,
+      "rewards/margins": -0.0017672583926469088,
+      "rewards/rejected": 0.01208101399242878,
+      "step": 2
+    },
+    {
+      "epoch": 0.047619047619047616,
+      "grad_norm": 61.41340255737305,
+      "learning_rate": 4.987173308479738e-06,
+      "logits/chosen": -2.124711036682129,
+      "logits/rejected": -2.3129348754882812,
+      "logps/chosen": -0.9234221577644348,
+      "logps/rejected": -1.6303091049194336,
+      "loss": 99.4497,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": 0.011429570615291595,
+      "rewards/margins": 0.0015148655511438847,
+      "rewards/rejected": 0.009914705529808998,
+      "step": 3
+    },
+    {
+      "epoch": 0.06349206349206349,
+      "grad_norm": 57.868431091308594,
+      "learning_rate": 4.948824853131237e-06,
+      "logits/chosen": -2.1755993366241455,
+      "logits/rejected": -2.4359540939331055,
+      "logps/chosen": -0.948157548904419,
+      "logps/rejected": -1.5917528867721558,
+      "loss": 99.2299,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": 0.010555782355368137,
+      "rewards/margins": 0.0021268429700285196,
+      "rewards/rejected": 0.008428940549492836,
+      "step": 4
+    },
+    {
+      "epoch": 0.07936507936507936,
+      "grad_norm": 70.2706298828125,
+      "learning_rate": 4.8853481410001225e-06,
+      "logits/chosen": -2.1221580505371094,
+      "logits/rejected": -2.396707057952881,
+      "logps/chosen": -0.8689298629760742,
+      "logps/rejected": -1.8071589469909668,
+      "loss": 97.5463,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": 0.011419497430324554,
+      "rewards/margins": 0.006311982404440641,
+      "rewards/rejected": 0.0051075154915452,
+      "step": 5
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 72.50617980957031,
+      "learning_rate": 4.797394529050577e-06,
+      "logits/chosen": -2.2033004760742188,
+      "logits/rejected": -2.463660955429077,
+      "logps/chosen": -1.182050347328186,
+      "logps/rejected": -1.72629976272583,
+      "loss": 99.1601,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": 0.008959097787737846,
+      "rewards/margins": 0.0024480693973600864,
+      "rewards/rejected": 0.006511027924716473,
+      "step": 6
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 76.10721588134766,
+      "learning_rate": 4.685866540361456e-06,
+      "logits/chosen": -2.1102092266082764,
+      "logits/rejected": -2.3653409481048584,
+      "logps/chosen": -0.9124682545661926,
+      "logps/rejected": -1.835811972618103,
+      "loss": 96.8503,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 0.011616631411015987,
+      "rewards/margins": 0.0080842524766922,
+      "rewards/rejected": 0.003532378701493144,
+      "step": 7
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 74.28392028808594,
+      "learning_rate": 4.551908603018191e-06,
+      "logits/chosen": -2.2063632011413574,
+      "logits/rejected": -2.4340498447418213,
+      "logps/chosen": -0.8536584973335266,
+      "logps/rejected": -1.8901478052139282,
+      "loss": 96.4469,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 0.011865518987178802,
+      "rewards/margins": 0.00912485271692276,
+      "rewards/rejected": 0.0027406662702560425,
+      "step": 8
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 77.02012634277344,
+      "learning_rate": 4.396895306731978e-06,
+      "logits/chosen": -2.2196762561798096,
+      "logits/rejected": -2.465085744857788,
+      "logps/chosen": -0.9492424726486206,
+      "logps/rejected": -1.854007363319397,
+      "loss": 97.0908,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 0.009380538947880268,
+      "rewards/margins": 0.0075874775648117065,
+      "rewards/rejected": 0.0017930612666532397,
+      "step": 9
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": 67.13955688476562,
+      "learning_rate": 4.222417297689217e-06,
+      "logits/chosen": -2.233217239379883,
+      "logits/rejected": -2.3442227840423584,
+      "logps/chosen": -0.8550275564193726,
+      "logps/rejected": -1.7330424785614014,
+      "loss": 96.7183,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 0.009713666513562202,
+      "rewards/margins": 0.008466679602861404,
+      "rewards/rejected": 0.0012469873763620853,
+      "step": 10
+    },
+    {
+      "epoch": 0.1746031746031746,
+      "grad_norm": 91.1172103881836,
+      "learning_rate": 4.030264956369158e-06,
+      "logits/chosen": -2.281071186065674,
+      "logits/rejected": -2.683786392211914,
+      "logps/chosen": -1.244257926940918,
+      "logps/rejected": -1.9201724529266357,
+      "loss": 98.4084,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": 0.008490300737321377,
+      "rewards/margins": 0.004535912536084652,
+      "rewards/rejected": 0.0039543891325592995,
+      "step": 11
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 86.38648223876953,
+      "learning_rate": 3.8224100258174066e-06,
+      "logits/chosen": -2.2776074409484863,
+      "logits/rejected": -2.5513505935668945,
+      "logps/chosen": -0.8422654867172241,
+      "logps/rejected": -2.005890369415283,
+      "loss": 94.6299,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 0.010762966237962246,
+      "rewards/margins": 0.013820413500070572,
+      "rewards/rejected": -0.0030574467964470387,
+      "step": 12
+    },
+    {
+      "epoch": 0.20634920634920634,
+      "grad_norm": 84.03218078613281,
+      "learning_rate": 3.600985378894086e-06,
+      "logits/chosen": -2.2474443912506104,
+      "logits/rejected": -2.3934414386749268,
+      "logps/chosen": -0.8881982564926147,
+      "logps/rejected": -1.8603103160858154,
+      "loss": 93.1583,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": 0.012732166796922684,
+      "rewards/margins": 0.01756295934319496,
+      "rewards/rejected": -0.004830792546272278,
+      "step": 13
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 108.10200500488281,
+      "learning_rate": 3.3682631321120507e-06,
+      "logits/chosen": -2.1857571601867676,
+      "logits/rejected": -2.470634937286377,
+      "logps/chosen": -0.8621047735214233,
+      "logps/rejected": -1.9189422130584717,
+      "loss": 93.5056,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 0.010991780087351799,
+      "rewards/margins": 0.016812698915600777,
+      "rewards/rejected": -0.00582092022523284,
+      "step": 14
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 98.29182434082031,
+      "learning_rate": 3.1266313306468018e-06,
+      "logits/chosen": -2.2839250564575195,
+      "logits/rejected": -2.4881529808044434,
+      "logps/chosen": -0.8307325839996338,
+      "logps/rejected": -2.0696005821228027,
+      "loss": 91.4297,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": 0.011583537794649601,
+      "rewards/margins": 0.0221419557929039,
+      "rewards/rejected": -0.0105584179982543,
+      "step": 15
+    },
+    {
+      "epoch": 0.25396825396825395,
+      "grad_norm": 89.91815948486328,
+      "learning_rate": 2.878569443761442e-06,
+      "logits/chosen": -2.2810075283050537,
+      "logits/rejected": -2.4519784450531006,
+      "logps/chosen": -0.967061460018158,
+      "logps/rejected": -1.9306243658065796,
+      "loss": 93.0875,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 0.011699460446834564,
+      "rewards/margins": 0.017987482249736786,
+      "rewards/rejected": -0.006288021802902222,
+      "step": 16
+    },
+    {
+      "epoch": 0.2698412698412698,
+      "grad_norm": 98.6678237915039,
+      "learning_rate": 2.626622922096782e-06,
+      "logits/chosen": -2.1972618103027344,
+      "logits/rejected": -2.514512538909912,
+      "logps/chosen": -0.8174502849578857,
+      "logps/rejected": -2.0018463134765625,
+      "loss": 91.7179,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 0.012017913162708282,
+      "rewards/margins": 0.02163715288043022,
+      "rewards/rejected": -0.00961923785507679,
+      "step": 17
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 107.2076644897461,
+      "learning_rate": 2.3733770779032185e-06,
+      "logits/chosen": -2.1779308319091797,
+      "logits/rejected": -2.548816442489624,
+      "logps/chosen": -0.9282850027084351,
+      "logps/rejected": -2.0622897148132324,
+      "loss": 92.204,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 0.008969704620540142,
+      "rewards/margins": 0.020185772329568863,
+      "rewards/rejected": -0.01121606770902872,
+      "step": 18
+    },
+    {
+      "epoch": 0.30158730158730157,
+      "grad_norm": 109.00663757324219,
+      "learning_rate": 2.1214305562385592e-06,
+      "logits/chosen": -2.3157405853271484,
+      "logits/rejected": -2.756890058517456,
+      "logps/chosen": -1.0933113098144531,
+      "logps/rejected": -1.983035683631897,
+      "loss": 94.0657,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": 0.009589027613401413,
+      "rewards/margins": 0.0157773494720459,
+      "rewards/rejected": -0.00618832278996706,
+      "step": 19
+    },
+    {
+      "epoch": 0.31746031746031744,
+      "grad_norm": 108.45767974853516,
+      "learning_rate": 1.8733686693531986e-06,
+      "logits/chosen": -2.285343647003174,
+      "logits/rejected": -2.600506544113159,
+      "logps/chosen": -0.9763903617858887,
+      "logps/rejected": -2.109158992767334,
+      "loss": 91.7136,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 0.00986174400895834,
+      "rewards/margins": 0.02157197892665863,
+      "rewards/rejected": -0.011710233986377716,
+      "step": 20
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 117.7738265991211,
+      "learning_rate": 1.6317368678879497e-06,
+      "logits/chosen": -2.3075315952301025,
+      "logits/rejected": -2.4838249683380127,
+      "logps/chosen": -0.8424920439720154,
+      "logps/rejected": -2.226480007171631,
+      "loss": 88.9044,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": 0.012006192468106747,
+      "rewards/margins": 0.028795666992664337,
+      "rewards/rejected": -0.016789473593235016,
+      "step": 21
+    },
+    {
+      "epoch": 0.3492063492063492,
+      "grad_norm": 112.16304779052734,
+      "learning_rate": 1.3990146211059141e-06,
+      "logits/chosen": -2.247889995574951,
+      "logits/rejected": -2.383714199066162,
+      "logps/chosen": -0.8421880006790161,
+      "logps/rejected": -2.0365967750549316,
+      "loss": 89.443,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": 0.011269833892583847,
+      "rewards/margins": 0.02741769701242447,
+      "rewards/rejected": -0.016147863119840622,
+      "step": 22
+    },
+    {
+      "epoch": 0.36507936507936506,
+      "grad_norm": 111.17552185058594,
+      "learning_rate": 1.1775899741825947e-06,
+      "logits/chosen": -2.2497000694274902,
+      "logits/rejected": -2.543438673019409,
+      "logps/chosen": -0.8720284104347229,
+      "logps/rejected": -2.1090431213378906,
+      "loss": 89.9094,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 0.009760284796357155,
+      "rewards/margins": 0.02622319757938385,
+      "rewards/rejected": -0.016462914645671844,
+      "step": 23
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 107.88399505615234,
+      "learning_rate": 9.697350436308428e-07,
+      "logits/chosen": -2.311974048614502,
+      "logits/rejected": -2.7802984714508057,
+      "logps/chosen": -1.1230542659759521,
+      "logps/rejected": -2.2263827323913574,
+      "loss": 92.3867,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": 0.008571119979023933,
+      "rewards/margins": 0.020269405096769333,
+      "rewards/rejected": -0.011698286980390549,
+      "step": 24
+    },
+    {
+      "epoch": 0.3968253968253968,
+      "grad_norm": 120.28370666503906,
+      "learning_rate": 7.775827023107835e-07,
+      "logits/chosen": -2.3289241790771484,
+      "logits/rejected": -2.556213855743408,
+      "logps/chosen": -0.8880805969238281,
+      "logps/rejected": -2.184584140777588,
+      "loss": 88.1746,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 0.0129635538905859,
+      "rewards/margins": 0.030874282121658325,
+      "rewards/rejected": -0.017910730093717575,
+      "step": 25
+    },
+    {
+      "epoch": 0.4126984126984127,
+      "grad_norm": 120.5097427368164,
+      "learning_rate": 6.031046932680229e-07,
+      "logits/chosen": -2.3363046646118164,
+      "logits/rejected": -2.7970316410064697,
+      "logps/chosen": -0.9201133847236633,
+      "logps/rejected": -2.2373695373535156,
+      "loss": 89.4875,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 0.010034371167421341,
+      "rewards/margins": 0.027558699250221252,
+      "rewards/rejected": -0.017524326220154762,
+      "step": 26
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 129.77806091308594,
+      "learning_rate": 4.480913969818099e-07,
+      "logits/chosen": -2.1930630207061768,
+      "logits/rejected": -2.461454391479492,
+      "logps/chosen": -0.9183363914489746,
+      "logps/rejected": -2.2184934616088867,
+      "loss": 87.5978,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 0.011562383733689785,
+      "rewards/margins": 0.03248335421085358,
+      "rewards/rejected": -0.020920973271131516,
+      "step": 27
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 115.09199523925781,
+      "learning_rate": 3.141334596385448e-07,
+      "logits/chosen": -2.2993292808532715,
+      "logits/rejected": -2.6102182865142822,
+      "logps/chosen": -1.1710147857666016,
+      "logps/rejected": -2.1261191368103027,
+      "loss": 90.0134,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 0.011231327429413795,
+      "rewards/margins": 0.026527734473347664,
+      "rewards/rejected": -0.015296407975256443,
+      "step": 28
+    },
+    {
+      "epoch": 0.4603174603174603,
+      "grad_norm": 118.78372192382812,
+      "learning_rate": 2.026054709494235e-07,
+      "logits/chosen": -2.333754062652588,
+      "logits/rejected": -2.62929630279541,
+      "logps/chosen": -0.9108929634094238,
+      "logps/rejected": -2.1907613277435303,
+      "loss": 89.9962,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": 0.010885003954172134,
+      "rewards/margins": 0.02634887769818306,
+      "rewards/rejected": -0.015463873744010925,
+      "step": 29
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 110.0257568359375,
+      "learning_rate": 1.1465185899987797e-07,
+      "logits/chosen": -2.2572035789489746,
+      "logits/rejected": -2.7623817920684814,
+      "logps/chosen": -1.2265293598175049,
+      "logps/rejected": -2.117170810699463,
+      "loss": 92.3271,
+      "rewards/accuracies": 0.84375,
+      "rewards/chosen": 0.008401270024478436,
+      "rewards/margins": 0.02065230906009674,
+      "rewards/rejected": -0.012251039035618305,
+      "step": 30
+    },
+    {
+      "epoch": 0.49206349206349204,
+      "grad_norm": 117.9716796875,
+      "learning_rate": 5.117514686876379e-08,
+      "logits/chosen": -2.2369933128356934,
+      "logits/rejected": -2.41340970993042,
+      "logps/chosen": -0.865552544593811,
+      "logps/rejected": -2.1379382610321045,
+      "loss": 88.3245,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 0.010352165438234806,
+      "rewards/margins": 0.030595146119594574,
+      "rewards/rejected": -0.020242983475327492,
+      "step": 31
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 112.72372436523438,
+      "learning_rate": 1.2826691520262114e-08,
+      "logits/chosen": -2.328519344329834,
+      "logits/rejected": -2.624027729034424,
+      "logps/chosen": -1.000898838043213,
+      "logps/rejected": -2.1262588500976562,
+      "loss": 89.0441,
+      "rewards/accuracies": 0.90625,
+      "rewards/chosen": 0.012559703551232815,
+      "rewards/margins": 0.028640277683734894,
+      "rewards/rejected": -0.016080575063824654,
+      "step": 32
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 32,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

qwen3_4b_eval_aware/checkpoint-32/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2cb43d7832dfc00b4ac9cdb2d7c2ad54c74704a446b31f6aa858e68b714f472
+size 6737

qwen3_4b_eval_aware/dpo_model/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-4B-Thinking-2507
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Thinking-2507
+- 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

qwen3_4b_eval_aware/dpo_model/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Thinking-2507",
+  "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": [
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen3_4b_eval_aware/dpo_model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bca19a61d584af3d4e051bdde7c5f4b4c9470d34b0c3dd3669566cf0aa0c1b24
+size 132187888

qwen3_4b_eval_aware/dpo_model/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
+}

qwen3_4b_eval_aware/dpo_model/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<think>\n' }}
+{%- endif %}

qwen3_4b_eval_aware/dpo_model/special_tokens_map.json

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

qwen3_4b_eval_aware/dpo_model/tokenizer.json

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

qwen3_4b_eval_aware/dpo_model/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": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen3_4b_eval_aware/train_config.json

@@ -0,0 +1,199 @@
+{
+  "output_dir": "qwen/second_stage/runs/qwen3_4b_dpo_eager_fixed",
+  "overwrite_output_dir": false,
+  "do_train": false,
+  "do_eval": true,
+  "do_predict": false,
+  "eval_strategy": "steps",
+  "prediction_loss_only": false,
+  "per_device_train_batch_size": 8,
+  "per_device_eval_batch_size": 8,
+  "per_gpu_train_batch_size": null,
+  "per_gpu_eval_batch_size": null,
+  "gradient_accumulation_steps": 2,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "torch_empty_cache_steps": null,
+  "learning_rate": 5e-06,
+  "weight_decay": 0.05,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1.0,
+  "num_train_epochs": 0.5,
+  "max_steps": -1,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": {},
+  "warmup_ratio": 0.03,
+  "warmup_steps": 0,
+  "log_level": "passive",
+  "log_level_replica": "warning",
+  "log_on_each_node": true,
+  "logging_dir": "qwen/second_stage/runs/qwen3_4b_dpo_eager_fixed/runs/Oct25_21-47-13_6c15deb18540",
+  "logging_strategy": "steps",
+  "logging_first_step": false,
+  "logging_steps": 1,
+  "logging_nan_inf_filter": true,
+  "save_strategy": "steps",
+  "save_steps": 50,
+  "save_total_limit": 10,
+  "save_safetensors": true,
+  "save_on_each_node": false,
+  "save_only_model": false,
+  "restore_callback_states_from_checkpoint": false,
+  "no_cuda": false,
+  "use_cpu": false,
+  "use_mps_device": false,
+  "seed": 42,
+  "data_seed": null,
+  "jit_mode_eval": false,
+  "use_ipex": false,
+  "bf16": true,
+  "fp16": false,
+  "fp16_opt_level": "O1",
+  "half_precision_backend": "auto",
+  "bf16_full_eval": false,
+  "fp16_full_eval": false,
+  "tf32": null,
+  "local_rank": 0,
+  "ddp_backend": null,
+  "tpu_num_cores": null,
+  "tpu_metrics_debug": false,
+  "debug": [],
+  "dataloader_drop_last": false,
+  "eval_steps": 50,
+  "dataloader_num_workers": 0,
+  "dataloader_prefetch_factor": null,
+  "past_index": -1,
+  "run_name": "qwen3_4b_dpo_eager_fixed",
+  "disable_tqdm": false,
+  "remove_unused_columns": false,
+  "label_names": null,
+  "load_best_model_at_end": true,
+  "metric_for_best_model": "eval_loss",
+  "greater_is_better": false,
+  "ignore_data_skip": false,
+  "fsdp": [],
+  "fsdp_min_num_params": 0,
+  "fsdp_config": {
+    "min_num_params": 0,
+    "xla": false,
+    "xla_fsdp_v2": false,
+    "xla_fsdp_grad_ckpt": false
+  },
+  "fsdp_transformer_layer_cls_to_wrap": null,
+  "accelerator_config": {
+    "split_batches": false,
+    "dispatch_batches": null,
+    "even_batches": true,
+    "use_seedable_sampler": true,
+    "non_blocking": false,
+    "gradient_accumulation_kwargs": null
+  },
+  "deepspeed": null,
+  "label_smoothing_factor": 0.0,
+  "optim": "adamw_torch_fused",
+  "optim_args": null,
+  "adafactor": false,
+  "group_by_length": false,
+  "length_column_name": "length",
+  "report_to": [
+    "wandb"
+  ],
+  "ddp_find_unused_parameters": false,
+  "ddp_bucket_cap_mb": null,
+  "ddp_broadcast_buffers": null,
+  "dataloader_pin_memory": true,
+  "dataloader_persistent_workers": false,
+  "skip_memory_metrics": true,
+  "use_legacy_prediction_loop": false,
+  "push_to_hub": false,
+  "resume_from_checkpoint": null,
+  "hub_model_id": null,
+  "hub_strategy": "every_save",
+  "hub_token": "<HUB_TOKEN>",
+  "hub_private_repo": null,
+  "hub_always_push": false,
+  "hub_revision": null,
+  "gradient_checkpointing": true,
+  "gradient_checkpointing_kwargs": {
+    "use_reentrant": false
+  },
+  "include_inputs_for_metrics": false,
+  "include_for_metrics": [],
+  "eval_do_concat_batches": true,
+  "fp16_backend": "auto",
+  "push_to_hub_model_id": null,
+  "push_to_hub_organization": null,
+  "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
+  "mp_parameters": "",
+  "auto_find_batch_size": false,
+  "full_determinism": false,
+  "torchdynamo": null,
+  "ray_scope": "last",
+  "ddp_timeout": 1800,
+  "torch_compile": false,
+  "torch_compile_backend": null,
+  "torch_compile_mode": null,
+  "include_tokens_per_second": false,
+  "include_num_input_tokens_seen": false,
+  "neftune_noise_alpha": null,
+  "optim_target_modules": null,
+  "batch_eval_metrics": false,
+  "eval_on_start": false,
+  "use_liger_kernel": false,
+  "liger_kernel_config": null,
+  "eval_use_gather_object": false,
+  "average_tokens_across_devices": true,
+  "model_init_kwargs": null,
+  "ref_model_init_kwargs": null,
+  "model_adapter_name": null,
+  "ref_adapter_name": null,
+  "force_use_ref_model": false,
+  "disable_dropout": true,
+  "use_logits_to_keep": false,
+  "dataset_num_proc": null,
+  "padding_value": null,
+  "label_pad_token_id": -100,
+  "max_prompt_length": null,
+  "max_completion_length": null,
+  "max_length": null,
+  "truncation_mode": "keep_end",
+  "padding_free": false,
+  "precompute_ref_log_probs": false,
+  "precompute_ref_batch_size": null,
+  "tools": null,
+  "loss_type": "ipo",
+  "beta": 0.05,
+  "f_divergence_type": "reverse_kl",
+  "f_alpha_divergence_coef": 1.0,
+  "reference_free": false,
+  "label_smoothing": 0.0,
+  "use_weighting": false,
+  "rpo_alpha": null,
+  "discopop_tau": 0.05,
+  "sync_ref_model": false,
+  "ref_model_mixup_alpha": 0.6,
+  "ref_model_sync_steps": 512,
+  "generate_during_eval": false,
+  "model_name": "Qwen/Qwen3-4B-Thinking-2507",
+  "dataset_path": "qwen/second_stage/data/dpo_pairs_filt_final.clean.jsonl",
+  "num_train_pairs": 2014,
+  "validation_ratio": 0.02,
+  "use_lora": true,
+  "lora_adapter_repo": "qwen/second_stage/models/checkpoint-4465",
+  "lora_r": 16,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "lora_bias": "none",
+  "lora_target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "gradient_checkpointing_use_reentrant": false
+}