Add files using upload-large-folder tool

README.md

@@ -0,0 +1,74 @@
+---
+base_model: unsloth/qwen2.5-14b-instruct-unsloth-bnb-4bit
+library_name: peft
+model_name: FactualDPO_qwen25_delta100_last
+tags:
+- base_model:adapter:unsloth/qwen2.5-14b-instruct-unsloth-bnb-4bit
+- dpo
+- lora
+- transformers
+- trl
+- unsloth
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for FactualDPO_qwen25_delta100_last
+
+This model is a fine-tuned version of [unsloth/qwen2.5-14b-instruct-unsloth-bnb-4bit](https://huggingface.co/unsloth/qwen2.5-14b-instruct-unsloth-bnb-4bit).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/vector-institute-aieng/aixpert/runs/3w1sgx6t) 
+
+
+This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
+
+### Framework versions
+
+- PEFT 0.18.0
+- TRL: 0.22.2
+- Transformers: 4.57.1
+- Pytorch: 2.6.0+cu124
+- Datasets: 3.6.0
+- Tokenizers: 0.22.1
+
+## Citations
+
+Cite DPO as:
+
+```bibtex
+@inproceedings{rafailov2023direct,
+    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
+    author       = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
+    year         = 2023,
+    booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
+    url          = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
+    editor       = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
+}
+```
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen2.5-14b-instruct-unsloth-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-100/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/qwen2.5-14b-instruct-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/qwen2.5-14b-instruct-unsloth-bnb-4bit
+- dpo
+- lora
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen2.5-14b-instruct-unsloth-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-100/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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-100/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-100/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-100/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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": 2048,
+  "pad_token": "<|im_end|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,109 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.28444444444444444,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05688888888888889,
+      "grad_norm": 25.723350524902344,
+      "learning_rate": 1.2954545454545456e-07,
+      "logits/chosen": -0.7062767744064331,
+      "logits/rejected": -0.6522080898284912,
+      "logps/chosen": -340.785888671875,
+      "logps/rejected": -653.7647705078125,
+      "loss": 4.7628,
+      "rewards/accuracies": 0.4468750059604645,
+      "rewards/chosen": 0.001610723091289401,
+      "rewards/margins": 0.006242862902581692,
+      "rewards/rejected": -0.004632140044122934,
+      "step": 20
+    },
+    {
+      "epoch": 0.11377777777777778,
+      "grad_norm": 15.587135314941406,
+      "learning_rate": 2.6590909090909093e-07,
+      "logits/chosen": -0.678135871887207,
+      "logits/rejected": -0.6651075482368469,
+      "logps/chosen": -347.43890380859375,
+      "logps/rejected": -708.3135986328125,
+      "loss": 4.8391,
+      "rewards/accuracies": 0.522265613079071,
+      "rewards/chosen": 0.0011627988424152136,
+      "rewards/margins": 0.010068175382912159,
+      "rewards/rejected": -0.008905376307666302,
+      "step": 40
+    },
+    {
+      "epoch": 0.17066666666666666,
+      "grad_norm": 19.355424880981445,
+      "learning_rate": 4.0227272727272725e-07,
+      "logits/chosen": -0.6907597184181213,
+      "logits/rejected": -0.6496841907501221,
+      "logps/chosen": -341.603759765625,
+      "logps/rejected": -661.4761962890625,
+      "loss": 4.863,
+      "rewards/accuracies": 0.528515636920929,
+      "rewards/chosen": -0.0007408790988847613,
+      "rewards/margins": 0.02941317856311798,
+      "rewards/rejected": -0.030154060572385788,
+      "step": 60
+    },
+    {
+      "epoch": 0.22755555555555557,
+      "grad_norm": 22.927623748779297,
+      "learning_rate": 5.386363636363637e-07,
+      "logits/chosen": -0.6875197887420654,
+      "logits/rejected": -0.6486619710922241,
+      "logps/chosen": -345.1783142089844,
+      "logps/rejected": -661.5092163085938,
+      "loss": 4.7676,
+      "rewards/accuracies": 0.61328125,
+      "rewards/chosen": 0.011638931930065155,
+      "rewards/margins": 0.1211162656545639,
+      "rewards/rejected": -0.10947732627391815,
+      "step": 80
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 20.672826766967773,
+      "learning_rate": 6.75e-07,
+      "logits/chosen": -0.6816097497940063,
+      "logits/rejected": -0.6414457559585571,
+      "logps/chosen": -344.27825927734375,
+      "logps/rejected": -658.2562255859375,
+      "loss": 4.56,
+      "rewards/accuracies": 0.647656261920929,
+      "rewards/chosen": 0.04126482084393501,
+      "rewards/margins": 0.30062881112098694,
+      "rewards/rejected": -0.2593640089035034,
+      "step": 100
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 1056,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/qwen2.5-14b-instruct-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/qwen2.5-14b-instruct-unsloth-bnb-4bit
+- dpo
+- lora
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

checkpoint-500/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen2.5-14b-instruct-unsloth-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "gate_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/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-500/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_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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": 2048,
+  "pad_token": "<|im_end|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,409 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.420977777777778,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05688888888888889,
+      "grad_norm": 25.723350524902344,
+      "learning_rate": 1.2954545454545456e-07,
+      "logits/chosen": -0.7062767744064331,
+      "logits/rejected": -0.6522080898284912,
+      "logps/chosen": -340.785888671875,
+      "logps/rejected": -653.7647705078125,
+      "loss": 4.7628,
+      "rewards/accuracies": 0.4468750059604645,
+      "rewards/chosen": 0.001610723091289401,
+      "rewards/margins": 0.006242862902581692,
+      "rewards/rejected": -0.004632140044122934,
+      "step": 20
+    },
+    {
+      "epoch": 0.11377777777777778,
+      "grad_norm": 15.587135314941406,
+      "learning_rate": 2.6590909090909093e-07,
+      "logits/chosen": -0.678135871887207,
+      "logits/rejected": -0.6651075482368469,
+      "logps/chosen": -347.43890380859375,
+      "logps/rejected": -708.3135986328125,
+      "loss": 4.8391,
+      "rewards/accuracies": 0.522265613079071,
+      "rewards/chosen": 0.0011627988424152136,
+      "rewards/margins": 0.010068175382912159,
+      "rewards/rejected": -0.008905376307666302,
+      "step": 40
+    },
+    {
+      "epoch": 0.17066666666666666,
+      "grad_norm": 19.355424880981445,
+      "learning_rate": 4.0227272727272725e-07,
+      "logits/chosen": -0.6907597184181213,
+      "logits/rejected": -0.6496841907501221,
+      "logps/chosen": -341.603759765625,
+      "logps/rejected": -661.4761962890625,
+      "loss": 4.863,
+      "rewards/accuracies": 0.528515636920929,
+      "rewards/chosen": -0.0007408790988847613,
+      "rewards/margins": 0.02941317856311798,
+      "rewards/rejected": -0.030154060572385788,
+      "step": 60
+    },
+    {
+      "epoch": 0.22755555555555557,
+      "grad_norm": 22.927623748779297,
+      "learning_rate": 5.386363636363637e-07,
+      "logits/chosen": -0.6875197887420654,
+      "logits/rejected": -0.6486619710922241,
+      "logps/chosen": -345.1783142089844,
+      "logps/rejected": -661.5092163085938,
+      "loss": 4.7676,
+      "rewards/accuracies": 0.61328125,
+      "rewards/chosen": 0.011638931930065155,
+      "rewards/margins": 0.1211162656545639,
+      "rewards/rejected": -0.10947732627391815,
+      "step": 80
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 20.672826766967773,
+      "learning_rate": 6.75e-07,
+      "logits/chosen": -0.6816097497940063,
+      "logits/rejected": -0.6414457559585571,
+      "logps/chosen": -344.27825927734375,
+      "logps/rejected": -658.2562255859375,
+      "loss": 4.56,
+      "rewards/accuracies": 0.647656261920929,
+      "rewards/chosen": 0.04126482084393501,
+      "rewards/margins": 0.30062881112098694,
+      "rewards/rejected": -0.2593640089035034,
+      "step": 100
+    },
+    {
+      "epoch": 0.3413333333333333,
+      "grad_norm": 13.753314971923828,
+      "learning_rate": 8.113636363636363e-07,
+      "logits/chosen": -0.6626165509223938,
+      "logits/rejected": -0.642012357711792,
+      "logps/chosen": -342.14031982421875,
+      "logps/rejected": -667.3262939453125,
+      "loss": 4.3726,
+      "rewards/accuracies": 0.6734374761581421,
+      "rewards/chosen": 0.10678935050964355,
+      "rewards/margins": 0.6032775640487671,
+      "rewards/rejected": -0.4964882731437683,
+      "step": 120
+    },
+    {
+      "epoch": 0.3982222222222222,
+      "grad_norm": 7.477163791656494,
+      "learning_rate": 9.477272727272726e-07,
+      "logits/chosen": -0.6697568297386169,
+      "logits/rejected": -0.6643576622009277,
+      "logps/chosen": -343.89959716796875,
+      "logps/rejected": -715.9915161132812,
+      "loss": 4.0971,
+      "rewards/accuracies": 0.7171875238418579,
+      "rewards/chosen": 0.21032771468162537,
+      "rewards/margins": 1.4638903141021729,
+      "rewards/rejected": -1.253562569618225,
+      "step": 140
+    },
+    {
+      "epoch": 0.45511111111111113,
+      "grad_norm": 8.21181869506836,
+      "learning_rate": 1.0840909090909092e-06,
+      "logits/chosen": -0.6967095136642456,
+      "logits/rejected": -0.681812047958374,
+      "logps/chosen": -340.03509521484375,
+      "logps/rejected": -682.7234497070312,
+      "loss": 4.1412,
+      "rewards/accuracies": 0.742968738079071,
+      "rewards/chosen": 0.3784622550010681,
+      "rewards/margins": 2.152285099029541,
+      "rewards/rejected": -1.7738231420516968,
+      "step": 160
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 6.915646076202393,
+      "learning_rate": 1.2204545454545454e-06,
+      "logits/chosen": -0.6905465722084045,
+      "logits/rejected": -0.6835938692092896,
+      "logps/chosen": -337.03912353515625,
+      "logps/rejected": -689.4818725585938,
+      "loss": 3.7365,
+      "rewards/accuracies": 0.7515624761581421,
+      "rewards/chosen": 0.5243303775787354,
+      "rewards/margins": 3.7261250019073486,
+      "rewards/rejected": -3.2017948627471924,
+      "step": 180
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 6.492739200592041,
+      "learning_rate": 1.3568181818181818e-06,
+      "logits/chosen": -0.750757098197937,
+      "logits/rejected": -0.7309343814849854,
+      "logps/chosen": -339.7341003417969,
+      "logps/rejected": -700.2279663085938,
+      "loss": 3.7081,
+      "rewards/accuracies": 0.791796863079071,
+      "rewards/chosen": 0.37986624240875244,
+      "rewards/margins": 5.3291778564453125,
+      "rewards/rejected": -4.94931173324585,
+      "step": 200
+    },
+    {
+      "epoch": 0.6257777777777778,
+      "grad_norm": 5.47404670715332,
+      "learning_rate": 1.4931818181818182e-06,
+      "logits/chosen": -0.7830198407173157,
+      "logits/rejected": -0.7797198295593262,
+      "logps/chosen": -347.9498596191406,
+      "logps/rejected": -765.7747192382812,
+      "loss": 3.1446,
+      "rewards/accuracies": 0.7847656011581421,
+      "rewards/chosen": 0.12148561328649521,
+      "rewards/margins": 7.9653730392456055,
+      "rewards/rejected": -7.843888282775879,
+      "step": 220
+    },
+    {
+      "epoch": 0.6826666666666666,
+      "grad_norm": 7.549896240234375,
+      "learning_rate": 1.6295454545454544e-06,
+      "logits/chosen": -0.9069732427597046,
+      "logits/rejected": -0.9081719517707825,
+      "logps/chosen": -359.0387268066406,
+      "logps/rejected": -788.9415283203125,
+      "loss": 2.8459,
+      "rewards/accuracies": 0.801953136920929,
+      "rewards/chosen": -0.5870370268821716,
+      "rewards/margins": 11.03849983215332,
+      "rewards/rejected": -11.625536918640137,
+      "step": 240
+    },
+    {
+      "epoch": 0.7395555555555555,
+      "grad_norm": 6.950064182281494,
+      "learning_rate": 1.7659090909090909e-06,
+      "logits/chosen": -1.0507304668426514,
+      "logits/rejected": -1.0437712669372559,
+      "logps/chosen": -363.00946044921875,
+      "logps/rejected": -855.9450073242188,
+      "loss": 2.3475,
+      "rewards/accuracies": 0.7890625,
+      "rewards/chosen": -1.7975599765777588,
+      "rewards/margins": 15.68769645690918,
+      "rewards/rejected": -17.48525619506836,
+      "step": 260
+    },
+    {
+      "epoch": 0.7964444444444444,
+      "grad_norm": 7.705135822296143,
+      "learning_rate": 1.7984073648922751e-06,
+      "logits/chosen": -1.271202802658081,
+      "logits/rejected": -1.2308619022369385,
+      "logps/chosen": -372.968017578125,
+      "logps/rejected": -874.5939331054688,
+      "loss": 2.0129,
+      "rewards/accuracies": 0.7964843511581421,
+      "rewards/chosen": -2.9631118774414062,
+      "rewards/margins": 19.912986755371094,
+      "rewards/rejected": -22.876102447509766,
+      "step": 280
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 12.216048240661621,
+      "learning_rate": 1.7913403507563104e-06,
+      "logits/chosen": -1.400701880455017,
+      "logits/rejected": -1.363081455230713,
+      "logps/chosen": -379.55963134765625,
+      "logps/rejected": -1006.6408081054688,
+      "loss": 1.8445,
+      "rewards/accuracies": 0.805468738079071,
+      "rewards/chosen": -3.517793655395508,
+      "rewards/margins": 27.90765380859375,
+      "rewards/rejected": -31.42544937133789,
+      "step": 300
+    },
+    {
+      "epoch": 0.9102222222222223,
+      "grad_norm": 5.293786525726318,
+      "learning_rate": 1.7786664064079399e-06,
+      "logits/chosen": -1.4596669673919678,
+      "logits/rejected": -1.4353153705596924,
+      "logps/chosen": -385.25439453125,
+      "logps/rejected": -1005.0475463867188,
+      "loss": 1.5993,
+      "rewards/accuracies": 0.823437511920929,
+      "rewards/chosen": -3.530385971069336,
+      "rewards/margins": 30.658462524414062,
+      "rewards/rejected": -34.18885040283203,
+      "step": 320
+    },
+    {
+      "epoch": 0.9671111111111111,
+      "grad_norm": 5.214448928833008,
+      "learning_rate": 1.7604652566362601e-06,
+      "logits/chosen": -1.4935115575790405,
+      "logits/rejected": -1.4993070363998413,
+      "logps/chosen": -374.81219482421875,
+      "logps/rejected": -1065.3048095703125,
+      "loss": 1.4563,
+      "rewards/accuracies": 0.8140624761581421,
+      "rewards/chosen": -3.6835930347442627,
+      "rewards/margins": 35.69647979736328,
+      "rewards/rejected": -39.38006591796875,
+      "step": 340
+    },
+    {
+      "epoch": 1.0227555555555556,
+      "grad_norm": 5.167357921600342,
+      "learning_rate": 1.7368513948291994e-06,
+      "logits/chosen": -1.5450448989868164,
+      "logits/rejected": -1.5312340259552002,
+      "logps/chosen": -390.2657165527344,
+      "logps/rejected": -1115.527587890625,
+      "loss": 1.4704,
+      "rewards/accuracies": 0.8154951930046082,
+      "rewards/chosen": -3.921747922897339,
+      "rewards/margins": 38.49018096923828,
+      "rewards/rejected": -42.411930084228516,
+      "step": 360
+    },
+    {
+      "epoch": 1.0796444444444444,
+      "grad_norm": 4.9285407066345215,
+      "learning_rate": 1.707973362758804e-06,
+      "logits/chosen": -1.5365326404571533,
+      "logits/rejected": -1.5479919910430908,
+      "logps/chosen": -379.05078125,
+      "logps/rejected": -1110.8424072265625,
+      "loss": 1.524,
+      "rewards/accuracies": 0.815625011920929,
+      "rewards/chosen": -3.505291700363159,
+      "rewards/margins": 39.89087677001953,
+      "rewards/rejected": -43.39616775512695,
+      "step": 380
+    },
+    {
+      "epoch": 1.1365333333333334,
+      "grad_norm": 4.965682029724121,
+      "learning_rate": 1.6740128161869303e-06,
+      "logits/chosen": -1.5383026599884033,
+      "logits/rejected": -1.5448668003082275,
+      "logps/chosen": -375.23004150390625,
+      "logps/rejected": -1089.509033203125,
+      "loss": 1.2728,
+      "rewards/accuracies": 0.83984375,
+      "rewards/chosen": -3.8725147247314453,
+      "rewards/margins": 40.29158401489258,
+      "rewards/rejected": -44.164100646972656,
+      "step": 400
+    },
+    {
+      "epoch": 1.1934222222222222,
+      "grad_norm": 4.170207500457764,
+      "learning_rate": 1.635183382169105e-06,
+      "logits/chosen": -1.6174129247665405,
+      "logits/rejected": -1.598515272140503,
+      "logps/chosen": -385.2093200683594,
+      "logps/rejected": -1157.7808837890625,
+      "loss": 1.2895,
+      "rewards/accuracies": 0.830859363079071,
+      "rewards/chosen": -4.239663600921631,
+      "rewards/margins": 44.047298431396484,
+      "rewards/rejected": -48.28696823120117,
+      "step": 420
+    },
+    {
+      "epoch": 1.2503111111111112,
+      "grad_norm": 4.982669353485107,
+      "learning_rate": 1.5917293152446181e-06,
+      "logits/chosen": -1.6095243692398071,
+      "logits/rejected": -1.6014487743377686,
+      "logps/chosen": -391.41705322265625,
+      "logps/rejected": -1123.428466796875,
+      "loss": 1.3683,
+      "rewards/accuracies": 0.835156261920929,
+      "rewards/chosen": -4.419755458831787,
+      "rewards/margins": 43.6191520690918,
+      "rewards/rejected": -48.03890609741211,
+      "step": 440
+    },
+    {
+      "epoch": 1.3072,
+      "grad_norm": 5.365580081939697,
+      "learning_rate": 1.5439239609660238e-06,
+      "logits/chosen": -1.55153489112854,
+      "logits/rejected": -1.5819648504257202,
+      "logps/chosen": -379.72222900390625,
+      "logps/rejected": -1220.7442626953125,
+      "loss": 1.3303,
+      "rewards/accuracies": 0.8285156488418579,
+      "rewards/chosen": -3.9600634574890137,
+      "rewards/margins": 50.48019790649414,
+      "rewards/rejected": -54.44025421142578,
+      "step": 460
+    },
+    {
+      "epoch": 1.364088888888889,
+      "grad_norm": 5.603168964385986,
+      "learning_rate": 1.492068036433128e-06,
+      "logits/chosen": -1.5621448755264282,
+      "logits/rejected": -1.5893001556396484,
+      "logps/chosen": -379.4105224609375,
+      "logps/rejected": -1226.2530517578125,
+      "loss": 1.3152,
+      "rewards/accuracies": 0.837890625,
+      "rewards/chosen": -3.8145880699157715,
+      "rewards/margins": 50.653114318847656,
+      "rewards/rejected": -54.46770095825195,
+      "step": 480
+    },
+    {
+      "epoch": 1.420977777777778,
+      "grad_norm": 7.285942554473877,
+      "learning_rate": 1.4364877386476803e-06,
+      "logits/chosen": -1.5568413734436035,
+      "logits/rejected": -1.5949300527572632,
+      "logps/chosen": -391.8574523925781,
+      "logps/rejected": -1221.8057861328125,
+      "loss": 1.3131,
+      "rewards/accuracies": 0.837109386920929,
+      "rewards/chosen": -4.1453447341918945,
+      "rewards/margins": 51.3240966796875,
+      "rewards/rejected": -55.46944046020508,
+      "step": 500
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 1056,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-600/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/qwen2.5-14b-instruct-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/qwen2.5-14b-instruct-unsloth-bnb-4bit
+- dpo
+- lora
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

checkpoint-600/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen2.5-14b-instruct-unsloth-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-600/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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-600/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-600/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-600/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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": 2048,
+  "pad_token": "<|im_end|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-600/trainer_state.json

@@ -0,0 +1,484 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.7054222222222222,
+  "eval_steps": 500,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05688888888888889,
+      "grad_norm": 25.723350524902344,
+      "learning_rate": 1.2954545454545456e-07,
+      "logits/chosen": -0.7062767744064331,
+      "logits/rejected": -0.6522080898284912,
+      "logps/chosen": -340.785888671875,
+      "logps/rejected": -653.7647705078125,
+      "loss": 4.7628,
+      "rewards/accuracies": 0.4468750059604645,
+      "rewards/chosen": 0.001610723091289401,
+      "rewards/margins": 0.006242862902581692,
+      "rewards/rejected": -0.004632140044122934,
+      "step": 20
+    },
+    {
+      "epoch": 0.11377777777777778,
+      "grad_norm": 15.587135314941406,
+      "learning_rate": 2.6590909090909093e-07,
+      "logits/chosen": -0.678135871887207,
+      "logits/rejected": -0.6651075482368469,
+      "logps/chosen": -347.43890380859375,
+      "logps/rejected": -708.3135986328125,
+      "loss": 4.8391,
+      "rewards/accuracies": 0.522265613079071,
+      "rewards/chosen": 0.0011627988424152136,
+      "rewards/margins": 0.010068175382912159,
+      "rewards/rejected": -0.008905376307666302,
+      "step": 40
+    },
+    {
+      "epoch": 0.17066666666666666,
+      "grad_norm": 19.355424880981445,
+      "learning_rate": 4.0227272727272725e-07,
+      "logits/chosen": -0.6907597184181213,
+      "logits/rejected": -0.6496841907501221,
+      "logps/chosen": -341.603759765625,
+      "logps/rejected": -661.4761962890625,
+      "loss": 4.863,
+      "rewards/accuracies": 0.528515636920929,
+      "rewards/chosen": -0.0007408790988847613,
+      "rewards/margins": 0.02941317856311798,
+      "rewards/rejected": -0.030154060572385788,
+      "step": 60
+    },
+    {
+      "epoch": 0.22755555555555557,
+      "grad_norm": 22.927623748779297,
+      "learning_rate": 5.386363636363637e-07,
+      "logits/chosen": -0.6875197887420654,
+      "logits/rejected": -0.6486619710922241,
+      "logps/chosen": -345.1783142089844,
+      "logps/rejected": -661.5092163085938,
+      "loss": 4.7676,
+      "rewards/accuracies": 0.61328125,
+      "rewards/chosen": 0.011638931930065155,
+      "rewards/margins": 0.1211162656545639,
+      "rewards/rejected": -0.10947732627391815,
+      "step": 80
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 20.672826766967773,
+      "learning_rate": 6.75e-07,
+      "logits/chosen": -0.6816097497940063,
+      "logits/rejected": -0.6414457559585571,
+      "logps/chosen": -344.27825927734375,
+      "logps/rejected": -658.2562255859375,
+      "loss": 4.56,
+      "rewards/accuracies": 0.647656261920929,
+      "rewards/chosen": 0.04126482084393501,
+      "rewards/margins": 0.30062881112098694,
+      "rewards/rejected": -0.2593640089035034,
+      "step": 100
+    },
+    {
+      "epoch": 0.3413333333333333,
+      "grad_norm": 13.753314971923828,
+      "learning_rate": 8.113636363636363e-07,
+      "logits/chosen": -0.6626165509223938,
+      "logits/rejected": -0.642012357711792,
+      "logps/chosen": -342.14031982421875,
+      "logps/rejected": -667.3262939453125,
+      "loss": 4.3726,
+      "rewards/accuracies": 0.6734374761581421,
+      "rewards/chosen": 0.10678935050964355,
+      "rewards/margins": 0.6032775640487671,
+      "rewards/rejected": -0.4964882731437683,
+      "step": 120
+    },
+    {
+      "epoch": 0.3982222222222222,
+      "grad_norm": 7.477163791656494,
+      "learning_rate": 9.477272727272726e-07,
+      "logits/chosen": -0.6697568297386169,
+      "logits/rejected": -0.6643576622009277,
+      "logps/chosen": -343.89959716796875,
+      "logps/rejected": -715.9915161132812,
+      "loss": 4.0971,
+      "rewards/accuracies": 0.7171875238418579,
+      "rewards/chosen": 0.21032771468162537,
+      "rewards/margins": 1.4638903141021729,
+      "rewards/rejected": -1.253562569618225,
+      "step": 140
+    },
+    {
+      "epoch": 0.45511111111111113,
+      "grad_norm": 8.21181869506836,
+      "learning_rate": 1.0840909090909092e-06,
+      "logits/chosen": -0.6967095136642456,
+      "logits/rejected": -0.681812047958374,
+      "logps/chosen": -340.03509521484375,
+      "logps/rejected": -682.7234497070312,
+      "loss": 4.1412,
+      "rewards/accuracies": 0.742968738079071,
+      "rewards/chosen": 0.3784622550010681,
+      "rewards/margins": 2.152285099029541,
+      "rewards/rejected": -1.7738231420516968,
+      "step": 160
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 6.915646076202393,
+      "learning_rate": 1.2204545454545454e-06,
+      "logits/chosen": -0.6905465722084045,
+      "logits/rejected": -0.6835938692092896,
+      "logps/chosen": -337.03912353515625,
+      "logps/rejected": -689.4818725585938,
+      "loss": 3.7365,
+      "rewards/accuracies": 0.7515624761581421,
+      "rewards/chosen": 0.5243303775787354,
+      "rewards/margins": 3.7261250019073486,
+      "rewards/rejected": -3.2017948627471924,
+      "step": 180
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 6.492739200592041,
+      "learning_rate": 1.3568181818181818e-06,
+      "logits/chosen": -0.750757098197937,
+      "logits/rejected": -0.7309343814849854,
+      "logps/chosen": -339.7341003417969,
+      "logps/rejected": -700.2279663085938,
+      "loss": 3.7081,
+      "rewards/accuracies": 0.791796863079071,
+      "rewards/chosen": 0.37986624240875244,
+      "rewards/margins": 5.3291778564453125,
+      "rewards/rejected": -4.94931173324585,
+      "step": 200
+    },
+    {
+      "epoch": 0.6257777777777778,
+      "grad_norm": 5.47404670715332,
+      "learning_rate": 1.4931818181818182e-06,
+      "logits/chosen": -0.7830198407173157,
+      "logits/rejected": -0.7797198295593262,
+      "logps/chosen": -347.9498596191406,
+      "logps/rejected": -765.7747192382812,
+      "loss": 3.1446,
+      "rewards/accuracies": 0.7847656011581421,
+      "rewards/chosen": 0.12148561328649521,
+      "rewards/margins": 7.9653730392456055,
+      "rewards/rejected": -7.843888282775879,
+      "step": 220
+    },
+    {
+      "epoch": 0.6826666666666666,
+      "grad_norm": 7.549896240234375,
+      "learning_rate": 1.6295454545454544e-06,
+      "logits/chosen": -0.9069732427597046,
+      "logits/rejected": -0.9081719517707825,
+      "logps/chosen": -359.0387268066406,
+      "logps/rejected": -788.9415283203125,
+      "loss": 2.8459,
+      "rewards/accuracies": 0.801953136920929,
+      "rewards/chosen": -0.5870370268821716,
+      "rewards/margins": 11.03849983215332,
+      "rewards/rejected": -11.625536918640137,
+      "step": 240
+    },
+    {
+      "epoch": 0.7395555555555555,
+      "grad_norm": 6.950064182281494,
+      "learning_rate": 1.7659090909090909e-06,
+      "logits/chosen": -1.0507304668426514,
+      "logits/rejected": -1.0437712669372559,
+      "logps/chosen": -363.00946044921875,
+      "logps/rejected": -855.9450073242188,
+      "loss": 2.3475,
+      "rewards/accuracies": 0.7890625,
+      "rewards/chosen": -1.7975599765777588,
+      "rewards/margins": 15.68769645690918,
+      "rewards/rejected": -17.48525619506836,
+      "step": 260
+    },
+    {
+      "epoch": 0.7964444444444444,
+      "grad_norm": 7.705135822296143,
+      "learning_rate": 1.7984073648922751e-06,
+      "logits/chosen": -1.271202802658081,
+      "logits/rejected": -1.2308619022369385,
+      "logps/chosen": -372.968017578125,
+      "logps/rejected": -874.5939331054688,
+      "loss": 2.0129,
+      "rewards/accuracies": 0.7964843511581421,
+      "rewards/chosen": -2.9631118774414062,
+      "rewards/margins": 19.912986755371094,
+      "rewards/rejected": -22.876102447509766,
+      "step": 280
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 12.216048240661621,
+      "learning_rate": 1.7913403507563104e-06,
+      "logits/chosen": -1.400701880455017,
+      "logits/rejected": -1.363081455230713,
+      "logps/chosen": -379.55963134765625,
+      "logps/rejected": -1006.6408081054688,
+      "loss": 1.8445,
+      "rewards/accuracies": 0.805468738079071,
+      "rewards/chosen": -3.517793655395508,
+      "rewards/margins": 27.90765380859375,
+      "rewards/rejected": -31.42544937133789,
+      "step": 300
+    },
+    {
+      "epoch": 0.9102222222222223,
+      "grad_norm": 5.293786525726318,
+      "learning_rate": 1.7786664064079399e-06,
+      "logits/chosen": -1.4596669673919678,
+      "logits/rejected": -1.4353153705596924,
+      "logps/chosen": -385.25439453125,
+      "logps/rejected": -1005.0475463867188,
+      "loss": 1.5993,
+      "rewards/accuracies": 0.823437511920929,
+      "rewards/chosen": -3.530385971069336,
+      "rewards/margins": 30.658462524414062,
+      "rewards/rejected": -34.18885040283203,
+      "step": 320
+    },
+    {
+      "epoch": 0.9671111111111111,
+      "grad_norm": 5.214448928833008,
+      "learning_rate": 1.7604652566362601e-06,
+      "logits/chosen": -1.4935115575790405,
+      "logits/rejected": -1.4993070363998413,
+      "logps/chosen": -374.81219482421875,
+      "logps/rejected": -1065.3048095703125,
+      "loss": 1.4563,
+      "rewards/accuracies": 0.8140624761581421,
+      "rewards/chosen": -3.6835930347442627,
+      "rewards/margins": 35.69647979736328,
+      "rewards/rejected": -39.38006591796875,
+      "step": 340
+    },
+    {
+      "epoch": 1.0227555555555556,
+      "grad_norm": 5.167357921600342,
+      "learning_rate": 1.7368513948291994e-06,
+      "logits/chosen": -1.5450448989868164,
+      "logits/rejected": -1.5312340259552002,
+      "logps/chosen": -390.2657165527344,
+      "logps/rejected": -1115.527587890625,
+      "loss": 1.4704,
+      "rewards/accuracies": 0.8154951930046082,
+      "rewards/chosen": -3.921747922897339,
+      "rewards/margins": 38.49018096923828,
+      "rewards/rejected": -42.411930084228516,
+      "step": 360
+    },
+    {
+      "epoch": 1.0796444444444444,
+      "grad_norm": 4.9285407066345215,
+      "learning_rate": 1.707973362758804e-06,
+      "logits/chosen": -1.5365326404571533,
+      "logits/rejected": -1.5479919910430908,
+      "logps/chosen": -379.05078125,
+      "logps/rejected": -1110.8424072265625,
+      "loss": 1.524,
+      "rewards/accuracies": 0.815625011920929,
+      "rewards/chosen": -3.505291700363159,
+      "rewards/margins": 39.89087677001953,
+      "rewards/rejected": -43.39616775512695,
+      "step": 380
+    },
+    {
+      "epoch": 1.1365333333333334,
+      "grad_norm": 4.965682029724121,
+      "learning_rate": 1.6740128161869303e-06,
+      "logits/chosen": -1.5383026599884033,
+      "logits/rejected": -1.5448668003082275,
+      "logps/chosen": -375.23004150390625,
+      "logps/rejected": -1089.509033203125,
+      "loss": 1.2728,
+      "rewards/accuracies": 0.83984375,
+      "rewards/chosen": -3.8725147247314453,
+      "rewards/margins": 40.29158401489258,
+      "rewards/rejected": -44.164100646972656,
+      "step": 400
+    },
+    {
+      "epoch": 1.1934222222222222,
+      "grad_norm": 4.170207500457764,
+      "learning_rate": 1.635183382169105e-06,
+      "logits/chosen": -1.6174129247665405,
+      "logits/rejected": -1.598515272140503,
+      "logps/chosen": -385.2093200683594,
+      "logps/rejected": -1157.7808837890625,
+      "loss": 1.2895,
+      "rewards/accuracies": 0.830859363079071,
+      "rewards/chosen": -4.239663600921631,
+      "rewards/margins": 44.047298431396484,
+      "rewards/rejected": -48.28696823120117,
+      "step": 420
+    },
+    {
+      "epoch": 1.2503111111111112,
+      "grad_norm": 4.982669353485107,
+      "learning_rate": 1.5917293152446181e-06,
+      "logits/chosen": -1.6095243692398071,
+      "logits/rejected": -1.6014487743377686,
+      "logps/chosen": -391.41705322265625,
+      "logps/rejected": -1123.428466796875,
+      "loss": 1.3683,
+      "rewards/accuracies": 0.835156261920929,
+      "rewards/chosen": -4.419755458831787,
+      "rewards/margins": 43.6191520690918,
+      "rewards/rejected": -48.03890609741211,
+      "step": 440
+    },
+    {
+      "epoch": 1.3072,
+      "grad_norm": 5.365580081939697,
+      "learning_rate": 1.5439239609660238e-06,
+      "logits/chosen": -1.55153489112854,
+      "logits/rejected": -1.5819648504257202,
+      "logps/chosen": -379.72222900390625,
+      "logps/rejected": -1220.7442626953125,
+      "loss": 1.3303,
+      "rewards/accuracies": 0.8285156488418579,
+      "rewards/chosen": -3.9600634574890137,
+      "rewards/margins": 50.48019790649414,
+      "rewards/rejected": -54.44025421142578,
+      "step": 460
+    },
+    {
+      "epoch": 1.364088888888889,
+      "grad_norm": 5.603168964385986,
+      "learning_rate": 1.492068036433128e-06,
+      "logits/chosen": -1.5621448755264282,
+      "logits/rejected": -1.5893001556396484,
+      "logps/chosen": -379.4105224609375,
+      "logps/rejected": -1226.2530517578125,
+      "loss": 1.3152,
+      "rewards/accuracies": 0.837890625,
+      "rewards/chosen": -3.8145880699157715,
+      "rewards/margins": 50.653114318847656,
+      "rewards/rejected": -54.46770095825195,
+      "step": 480
+    },
+    {
+      "epoch": 1.420977777777778,
+      "grad_norm": 7.285942554473877,
+      "learning_rate": 1.4364877386476803e-06,
+      "logits/chosen": -1.5568413734436035,
+      "logits/rejected": -1.5949300527572632,
+      "logps/chosen": -391.8574523925781,
+      "logps/rejected": -1221.8057861328125,
+      "loss": 1.3131,
+      "rewards/accuracies": 0.837109386920929,
+      "rewards/chosen": -4.1453447341918945,
+      "rewards/margins": 51.3240966796875,
+      "rewards/rejected": -55.46944046020508,
+      "step": 500
+    },
+    {
+      "epoch": 1.4778666666666667,
+      "grad_norm": 5.188837051391602,
+      "learning_rate": 1.3775326925880672e-06,
+      "logits/chosen": -1.5099071264266968,
+      "logits/rejected": -1.538757562637329,
+      "logps/chosen": -382.1160888671875,
+      "logps/rejected": -1294.1851806640625,
+      "loss": 1.1844,
+      "rewards/accuracies": 0.8414062261581421,
+      "rewards/chosen": -3.6662063598632812,
+      "rewards/margins": 53.77040481567383,
+      "rewards/rejected": -57.436607360839844,
+      "step": 520
+    },
+    {
+      "epoch": 1.5347555555555554,
+      "grad_norm": 5.107513904571533,
+      "learning_rate": 1.3155737519115306e-06,
+      "logits/chosen": -1.565260887145996,
+      "logits/rejected": -1.5936307907104492,
+      "logps/chosen": -380.9848937988281,
+      "logps/rejected": -1163.626708984375,
+      "loss": 1.2198,
+      "rewards/accuracies": 0.8433593511581421,
+      "rewards/chosen": -3.710998058319092,
+      "rewards/margins": 47.719356536865234,
+      "rewards/rejected": -51.43035125732422,
+      "step": 540
+    },
+    {
+      "epoch": 1.5916444444444444,
+      "grad_norm": 4.466892719268799,
+      "learning_rate": 1.2510006661184866e-06,
+      "logits/chosen": -1.5557365417480469,
+      "logits/rejected": -1.582177996635437,
+      "logps/chosen": -389.8815612792969,
+      "logps/rejected": -1274.912841796875,
+      "loss": 1.1301,
+      "rewards/accuracies": 0.84765625,
+      "rewards/chosen": -4.558670997619629,
+      "rewards/margins": 53.85039520263672,
+      "rewards/rejected": -58.4090690612793,
+      "step": 560
+    },
+    {
+      "epoch": 1.6485333333333334,
+      "grad_norm": 4.823034763336182,
+      "learning_rate": 1.1842196288535226e-06,
+      "logits/chosen": -1.5631791353225708,
+      "logits/rejected": -1.5713732242584229,
+      "logps/chosen": -388.4598693847656,
+      "logps/rejected": -1245.7056884765625,
+      "loss": 1.2336,
+      "rewards/accuracies": 0.84765625,
+      "rewards/chosen": -4.465853691101074,
+      "rewards/margins": 52.74620819091797,
+      "rewards/rejected": -57.212059020996094,
+      "step": 580
+    },
+    {
+      "epoch": 1.7054222222222222,
+      "grad_norm": 4.383596420288086,
+      "learning_rate": 1.115650722765358e-06,
+      "logits/chosen": -1.4939193725585938,
+      "logits/rejected": -1.5414621829986572,
+      "logps/chosen": -392.1934509277344,
+      "logps/rejected": -1259.5296630859375,
+      "loss": 1.1556,
+      "rewards/accuracies": 0.853515625,
+      "rewards/chosen": -4.005014419555664,
+      "rewards/margins": 54.73443603515625,
+      "rewards/rejected": -58.73945236206055,
+      "step": 600
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 1056,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-700/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen2.5-14b-instruct-unsloth-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-700/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-700/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-700/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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": 2048,
+  "pad_token": "<|im_end|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-700/trainer_state.json

@@ -0,0 +1,559 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9898666666666667,
+  "eval_steps": 500,
+  "global_step": 700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05688888888888889,
+      "grad_norm": 25.723350524902344,
+      "learning_rate": 1.2954545454545456e-07,
+      "logits/chosen": -0.7062767744064331,
+      "logits/rejected": -0.6522080898284912,
+      "logps/chosen": -340.785888671875,
+      "logps/rejected": -653.7647705078125,
+      "loss": 4.7628,
+      "rewards/accuracies": 0.4468750059604645,
+      "rewards/chosen": 0.001610723091289401,
+      "rewards/margins": 0.006242862902581692,
+      "rewards/rejected": -0.004632140044122934,
+      "step": 20
+    },
+    {
+      "epoch": 0.11377777777777778,
+      "grad_norm": 15.587135314941406,
+      "learning_rate": 2.6590909090909093e-07,
+      "logits/chosen": -0.678135871887207,
+      "logits/rejected": -0.6651075482368469,
+      "logps/chosen": -347.43890380859375,
+      "logps/rejected": -708.3135986328125,
+      "loss": 4.8391,
+      "rewards/accuracies": 0.522265613079071,
+      "rewards/chosen": 0.0011627988424152136,
+      "rewards/margins": 0.010068175382912159,
+      "rewards/rejected": -0.008905376307666302,
+      "step": 40
+    },
+    {
+      "epoch": 0.17066666666666666,
+      "grad_norm": 19.355424880981445,
+      "learning_rate": 4.0227272727272725e-07,
+      "logits/chosen": -0.6907597184181213,
+      "logits/rejected": -0.6496841907501221,
+      "logps/chosen": -341.603759765625,
+      "logps/rejected": -661.4761962890625,
+      "loss": 4.863,
+      "rewards/accuracies": 0.528515636920929,
+      "rewards/chosen": -0.0007408790988847613,
+      "rewards/margins": 0.02941317856311798,
+      "rewards/rejected": -0.030154060572385788,
+      "step": 60
+    },
+    {
+      "epoch": 0.22755555555555557,
+      "grad_norm": 22.927623748779297,
+      "learning_rate": 5.386363636363637e-07,
+      "logits/chosen": -0.6875197887420654,
+      "logits/rejected": -0.6486619710922241,
+      "logps/chosen": -345.1783142089844,
+      "logps/rejected": -661.5092163085938,
+      "loss": 4.7676,
+      "rewards/accuracies": 0.61328125,
+      "rewards/chosen": 0.011638931930065155,
+      "rewards/margins": 0.1211162656545639,
+      "rewards/rejected": -0.10947732627391815,
+      "step": 80
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 20.672826766967773,
+      "learning_rate": 6.75e-07,
+      "logits/chosen": -0.6816097497940063,
+      "logits/rejected": -0.6414457559585571,
+      "logps/chosen": -344.27825927734375,
+      "logps/rejected": -658.2562255859375,
+      "loss": 4.56,
+      "rewards/accuracies": 0.647656261920929,
+      "rewards/chosen": 0.04126482084393501,
+      "rewards/margins": 0.30062881112098694,
+      "rewards/rejected": -0.2593640089035034,
+      "step": 100
+    },
+    {
+      "epoch": 0.3413333333333333,
+      "grad_norm": 13.753314971923828,
+      "learning_rate": 8.113636363636363e-07,
+      "logits/chosen": -0.6626165509223938,
+      "logits/rejected": -0.642012357711792,
+      "logps/chosen": -342.14031982421875,
+      "logps/rejected": -667.3262939453125,
+      "loss": 4.3726,
+      "rewards/accuracies": 0.6734374761581421,
+      "rewards/chosen": 0.10678935050964355,
+      "rewards/margins": 0.6032775640487671,
+      "rewards/rejected": -0.4964882731437683,
+      "step": 120
+    },
+    {
+      "epoch": 0.3982222222222222,
+      "grad_norm": 7.477163791656494,
+      "learning_rate": 9.477272727272726e-07,
+      "logits/chosen": -0.6697568297386169,
+      "logits/rejected": -0.6643576622009277,
+      "logps/chosen": -343.89959716796875,
+      "logps/rejected": -715.9915161132812,
+      "loss": 4.0971,
+      "rewards/accuracies": 0.7171875238418579,
+      "rewards/chosen": 0.21032771468162537,
+      "rewards/margins": 1.4638903141021729,
+      "rewards/rejected": -1.253562569618225,
+      "step": 140
+    },
+    {
+      "epoch": 0.45511111111111113,
+      "grad_norm": 8.21181869506836,
+      "learning_rate": 1.0840909090909092e-06,
+      "logits/chosen": -0.6967095136642456,
+      "logits/rejected": -0.681812047958374,
+      "logps/chosen": -340.03509521484375,
+      "logps/rejected": -682.7234497070312,
+      "loss": 4.1412,
+      "rewards/accuracies": 0.742968738079071,
+      "rewards/chosen": 0.3784622550010681,
+      "rewards/margins": 2.152285099029541,
+      "rewards/rejected": -1.7738231420516968,
+      "step": 160
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 6.915646076202393,
+      "learning_rate": 1.2204545454545454e-06,
+      "logits/chosen": -0.6905465722084045,
+      "logits/rejected": -0.6835938692092896,
+      "logps/chosen": -337.03912353515625,
+      "logps/rejected": -689.4818725585938,
+      "loss": 3.7365,
+      "rewards/accuracies": 0.7515624761581421,
+      "rewards/chosen": 0.5243303775787354,
+      "rewards/margins": 3.7261250019073486,
+      "rewards/rejected": -3.2017948627471924,
+      "step": 180
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 6.492739200592041,
+      "learning_rate": 1.3568181818181818e-06,
+      "logits/chosen": -0.750757098197937,
+      "logits/rejected": -0.7309343814849854,
+      "logps/chosen": -339.7341003417969,
+      "logps/rejected": -700.2279663085938,
+      "loss": 3.7081,
+      "rewards/accuracies": 0.791796863079071,
+      "rewards/chosen": 0.37986624240875244,
+      "rewards/margins": 5.3291778564453125,
+      "rewards/rejected": -4.94931173324585,
+      "step": 200
+    },
+    {
+      "epoch": 0.6257777777777778,
+      "grad_norm": 5.47404670715332,
+      "learning_rate": 1.4931818181818182e-06,
+      "logits/chosen": -0.7830198407173157,
+      "logits/rejected": -0.7797198295593262,
+      "logps/chosen": -347.9498596191406,
+      "logps/rejected": -765.7747192382812,
+      "loss": 3.1446,
+      "rewards/accuracies": 0.7847656011581421,
+      "rewards/chosen": 0.12148561328649521,
+      "rewards/margins": 7.9653730392456055,
+      "rewards/rejected": -7.843888282775879,
+      "step": 220
+    },
+    {
+      "epoch": 0.6826666666666666,
+      "grad_norm": 7.549896240234375,
+      "learning_rate": 1.6295454545454544e-06,
+      "logits/chosen": -0.9069732427597046,
+      "logits/rejected": -0.9081719517707825,
+      "logps/chosen": -359.0387268066406,
+      "logps/rejected": -788.9415283203125,
+      "loss": 2.8459,
+      "rewards/accuracies": 0.801953136920929,
+      "rewards/chosen": -0.5870370268821716,
+      "rewards/margins": 11.03849983215332,
+      "rewards/rejected": -11.625536918640137,
+      "step": 240
+    },
+    {
+      "epoch": 0.7395555555555555,
+      "grad_norm": 6.950064182281494,
+      "learning_rate": 1.7659090909090909e-06,
+      "logits/chosen": -1.0507304668426514,
+      "logits/rejected": -1.0437712669372559,
+      "logps/chosen": -363.00946044921875,
+      "logps/rejected": -855.9450073242188,
+      "loss": 2.3475,
+      "rewards/accuracies": 0.7890625,
+      "rewards/chosen": -1.7975599765777588,
+      "rewards/margins": 15.68769645690918,
+      "rewards/rejected": -17.48525619506836,
+      "step": 260
+    },
+    {
+      "epoch": 0.7964444444444444,
+      "grad_norm": 7.705135822296143,
+      "learning_rate": 1.7984073648922751e-06,
+      "logits/chosen": -1.271202802658081,
+      "logits/rejected": -1.2308619022369385,
+      "logps/chosen": -372.968017578125,
+      "logps/rejected": -874.5939331054688,
+      "loss": 2.0129,
+      "rewards/accuracies": 0.7964843511581421,
+      "rewards/chosen": -2.9631118774414062,
+      "rewards/margins": 19.912986755371094,
+      "rewards/rejected": -22.876102447509766,
+      "step": 280
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 12.216048240661621,
+      "learning_rate": 1.7913403507563104e-06,
+      "logits/chosen": -1.400701880455017,
+      "logits/rejected": -1.363081455230713,
+      "logps/chosen": -379.55963134765625,
+      "logps/rejected": -1006.6408081054688,
+      "loss": 1.8445,
+      "rewards/accuracies": 0.805468738079071,
+      "rewards/chosen": -3.517793655395508,
+      "rewards/margins": 27.90765380859375,
+      "rewards/rejected": -31.42544937133789,
+      "step": 300
+    },
+    {
+      "epoch": 0.9102222222222223,
+      "grad_norm": 5.293786525726318,
+      "learning_rate": 1.7786664064079399e-06,
+      "logits/chosen": -1.4596669673919678,
+      "logits/rejected": -1.4353153705596924,
+      "logps/chosen": -385.25439453125,
+      "logps/rejected": -1005.0475463867188,
+      "loss": 1.5993,
+      "rewards/accuracies": 0.823437511920929,
+      "rewards/chosen": -3.530385971069336,
+      "rewards/margins": 30.658462524414062,
+      "rewards/rejected": -34.18885040283203,
+      "step": 320
+    },
+    {
+      "epoch": 0.9671111111111111,
+      "grad_norm": 5.214448928833008,
+      "learning_rate": 1.7604652566362601e-06,
+      "logits/chosen": -1.4935115575790405,
+      "logits/rejected": -1.4993070363998413,
+      "logps/chosen": -374.81219482421875,
+      "logps/rejected": -1065.3048095703125,
+      "loss": 1.4563,
+      "rewards/accuracies": 0.8140624761581421,
+      "rewards/chosen": -3.6835930347442627,
+      "rewards/margins": 35.69647979736328,
+      "rewards/rejected": -39.38006591796875,
+      "step": 340
+    },
+    {
+      "epoch": 1.0227555555555556,
+      "grad_norm": 5.167357921600342,
+      "learning_rate": 1.7368513948291994e-06,
+      "logits/chosen": -1.5450448989868164,
+      "logits/rejected": -1.5312340259552002,
+      "logps/chosen": -390.2657165527344,
+      "logps/rejected": -1115.527587890625,
+      "loss": 1.4704,
+      "rewards/accuracies": 0.8154951930046082,
+      "rewards/chosen": -3.921747922897339,
+      "rewards/margins": 38.49018096923828,
+      "rewards/rejected": -42.411930084228516,
+      "step": 360
+    },
+    {
+      "epoch": 1.0796444444444444,
+      "grad_norm": 4.9285407066345215,
+      "learning_rate": 1.707973362758804e-06,
+      "logits/chosen": -1.5365326404571533,
+      "logits/rejected": -1.5479919910430908,
+      "logps/chosen": -379.05078125,
+      "logps/rejected": -1110.8424072265625,
+      "loss": 1.524,
+      "rewards/accuracies": 0.815625011920929,
+      "rewards/chosen": -3.505291700363159,
+      "rewards/margins": 39.89087677001953,
+      "rewards/rejected": -43.39616775512695,
+      "step": 380
+    },
+    {
+      "epoch": 1.1365333333333334,
+      "grad_norm": 4.965682029724121,
+      "learning_rate": 1.6740128161869303e-06,
+      "logits/chosen": -1.5383026599884033,
+      "logits/rejected": -1.5448668003082275,
+      "logps/chosen": -375.23004150390625,
+      "logps/rejected": -1089.509033203125,
+      "loss": 1.2728,
+      "rewards/accuracies": 0.83984375,
+      "rewards/chosen": -3.8725147247314453,
+      "rewards/margins": 40.29158401489258,
+      "rewards/rejected": -44.164100646972656,
+      "step": 400
+    },
+    {
+      "epoch": 1.1934222222222222,
+      "grad_norm": 4.170207500457764,
+      "learning_rate": 1.635183382169105e-06,
+      "logits/chosen": -1.6174129247665405,
+      "logits/rejected": -1.598515272140503,
+      "logps/chosen": -385.2093200683594,
+      "logps/rejected": -1157.7808837890625,
+      "loss": 1.2895,
+      "rewards/accuracies": 0.830859363079071,
+      "rewards/chosen": -4.239663600921631,
+      "rewards/margins": 44.047298431396484,
+      "rewards/rejected": -48.28696823120117,
+      "step": 420
+    },
+    {
+      "epoch": 1.2503111111111112,
+      "grad_norm": 4.982669353485107,
+      "learning_rate": 1.5917293152446181e-06,
+      "logits/chosen": -1.6095243692398071,
+      "logits/rejected": -1.6014487743377686,
+      "logps/chosen": -391.41705322265625,
+      "logps/rejected": -1123.428466796875,
+      "loss": 1.3683,
+      "rewards/accuracies": 0.835156261920929,
+      "rewards/chosen": -4.419755458831787,
+      "rewards/margins": 43.6191520690918,
+      "rewards/rejected": -48.03890609741211,
+      "step": 440
+    },
+    {
+      "epoch": 1.3072,
+      "grad_norm": 5.365580081939697,
+      "learning_rate": 1.5439239609660238e-06,
+      "logits/chosen": -1.55153489112854,
+      "logits/rejected": -1.5819648504257202,
+      "logps/chosen": -379.72222900390625,
+      "logps/rejected": -1220.7442626953125,
+      "loss": 1.3303,
+      "rewards/accuracies": 0.8285156488418579,
+      "rewards/chosen": -3.9600634574890137,
+      "rewards/margins": 50.48019790649414,
+      "rewards/rejected": -54.44025421142578,
+      "step": 460
+    },
+    {
+      "epoch": 1.364088888888889,
+      "grad_norm": 5.603168964385986,
+      "learning_rate": 1.492068036433128e-06,
+      "logits/chosen": -1.5621448755264282,
+      "logits/rejected": -1.5893001556396484,
+      "logps/chosen": -379.4105224609375,
+      "logps/rejected": -1226.2530517578125,
+      "loss": 1.3152,
+      "rewards/accuracies": 0.837890625,
+      "rewards/chosen": -3.8145880699157715,
+      "rewards/margins": 50.653114318847656,
+      "rewards/rejected": -54.46770095825195,
+      "step": 480
+    },
+    {
+      "epoch": 1.420977777777778,
+      "grad_norm": 7.285942554473877,
+      "learning_rate": 1.4364877386476803e-06,
+      "logits/chosen": -1.5568413734436035,
+      "logits/rejected": -1.5949300527572632,
+      "logps/chosen": -391.8574523925781,
+      "logps/rejected": -1221.8057861328125,
+      "loss": 1.3131,
+      "rewards/accuracies": 0.837109386920929,
+      "rewards/chosen": -4.1453447341918945,
+      "rewards/margins": 51.3240966796875,
+      "rewards/rejected": -55.46944046020508,
+      "step": 500
+    },
+    {
+      "epoch": 1.4778666666666667,
+      "grad_norm": 5.188837051391602,
+      "learning_rate": 1.3775326925880672e-06,
+      "logits/chosen": -1.5099071264266968,
+      "logits/rejected": -1.538757562637329,
+      "logps/chosen": -382.1160888671875,
+      "logps/rejected": -1294.1851806640625,
+      "loss": 1.1844,
+      "rewards/accuracies": 0.8414062261581421,
+      "rewards/chosen": -3.6662063598632812,
+      "rewards/margins": 53.77040481567383,
+      "rewards/rejected": -57.436607360839844,
+      "step": 520
+    },
+    {
+      "epoch": 1.5347555555555554,
+      "grad_norm": 5.107513904571533,
+      "learning_rate": 1.3155737519115306e-06,
+      "logits/chosen": -1.565260887145996,
+      "logits/rejected": -1.5936307907104492,
+      "logps/chosen": -380.9848937988281,
+      "logps/rejected": -1163.626708984375,
+      "loss": 1.2198,
+      "rewards/accuracies": 0.8433593511581421,
+      "rewards/chosen": -3.710998058319092,
+      "rewards/margins": 47.719356536865234,
+      "rewards/rejected": -51.43035125732422,
+      "step": 540
+    },
+    {
+      "epoch": 1.5916444444444444,
+      "grad_norm": 4.466892719268799,
+      "learning_rate": 1.2510006661184866e-06,
+      "logits/chosen": -1.5557365417480469,
+      "logits/rejected": -1.582177996635437,
+      "logps/chosen": -389.8815612792969,
+      "logps/rejected": -1274.912841796875,
+      "loss": 1.1301,
+      "rewards/accuracies": 0.84765625,
+      "rewards/chosen": -4.558670997619629,
+      "rewards/margins": 53.85039520263672,
+      "rewards/rejected": -58.4090690612793,
+      "step": 560
+    },
+    {
+      "epoch": 1.6485333333333334,
+      "grad_norm": 4.823034763336182,
+      "learning_rate": 1.1842196288535226e-06,
+      "logits/chosen": -1.5631791353225708,
+      "logits/rejected": -1.5713732242584229,
+      "logps/chosen": -388.4598693847656,
+      "logps/rejected": -1245.7056884765625,
+      "loss": 1.2336,
+      "rewards/accuracies": 0.84765625,
+      "rewards/chosen": -4.465853691101074,
+      "rewards/margins": 52.74620819091797,
+      "rewards/rejected": -57.212059020996094,
+      "step": 580
+    },
+    {
+      "epoch": 1.7054222222222222,
+      "grad_norm": 4.383596420288086,
+      "learning_rate": 1.115650722765358e-06,
+      "logits/chosen": -1.4939193725585938,
+      "logits/rejected": -1.5414621829986572,
+      "logps/chosen": -392.1934509277344,
+      "logps/rejected": -1259.5296630859375,
+      "loss": 1.1556,
+      "rewards/accuracies": 0.853515625,
+      "rewards/chosen": -4.005014419555664,
+      "rewards/margins": 54.73443603515625,
+      "rewards/rejected": -58.73945236206055,
+      "step": 600
+    },
+    {
+      "epoch": 1.7623111111111112,
+      "grad_norm": 4.128599643707275,
+      "learning_rate": 1.0457252769987484e-06,
+      "logits/chosen": -1.4883978366851807,
+      "logits/rejected": -1.5312236547470093,
+      "logps/chosen": -384.2289733886719,
+      "logps/rejected": -1305.6707763671875,
+      "loss": 1.1712,
+      "rewards/accuracies": 0.8433593511581421,
+      "rewards/chosen": -3.6986148357391357,
+      "rewards/margins": 56.77925491333008,
+      "rewards/rejected": -60.477867126464844,
+      "step": 620
+    },
+    {
+      "epoch": 1.8192,
+      "grad_norm": 6.113862037658691,
+      "learning_rate": 9.74883153940886e-07,
+      "logits/chosen": -1.49406099319458,
+      "logits/rejected": -1.5339412689208984,
+      "logps/chosen": -383.2894287109375,
+      "logps/rejected": -1249.376953125,
+      "loss": 1.1426,
+      "rewards/accuracies": 0.86328125,
+      "rewards/chosen": -4.020669937133789,
+      "rewards/margins": 53.08935546875,
+      "rewards/rejected": -57.110023498535156,
+      "step": 640
+    },
+    {
+      "epoch": 1.876088888888889,
+      "grad_norm": 5.948381423950195,
+      "learning_rate": 9.03569982289885e-07,
+      "logits/chosen": -1.5656105279922485,
+      "logits/rejected": -1.5601282119750977,
+      "logps/chosen": -395.3358154296875,
+      "logps/rejected": -1181.269775390625,
+      "loss": 1.1806,
+      "rewards/accuracies": 0.8492187261581421,
+      "rewards/chosen": -4.2404961585998535,
+      "rewards/margins": 49.447227478027344,
+      "rewards/rejected": -53.6877326965332,
+      "step": 660
+    },
+    {
+      "epoch": 1.932977777777778,
+      "grad_norm": 5.629128932952881,
+      "learning_rate": 8.322343538505857e-07,
+      "logits/chosen": -1.5090030431747437,
+      "logits/rejected": -1.533573865890503,
+      "logps/chosen": -383.603759765625,
+      "logps/rejected": -1244.2327880859375,
+      "loss": 1.0988,
+      "rewards/accuracies": 0.866406261920929,
+      "rewards/chosen": -4.081192970275879,
+      "rewards/margins": 53.2569580078125,
+      "rewards/rejected": -57.3381462097168,
+      "step": 680
+    },
+    {
+      "epoch": 1.9898666666666667,
+      "grad_norm": 7.586100101470947,
+      "learning_rate": 7.613250016910891e-07,
+      "logits/chosen": -1.5487099885940552,
+      "logits/rejected": -1.584081768989563,
+      "logps/chosen": -376.0309753417969,
+      "logps/rejected": -1187.498779296875,
+      "loss": 1.2131,
+      "rewards/accuracies": 0.854296863079071,
+      "rewards/chosen": -3.9285030364990234,
+      "rewards/margins": 52.20911407470703,
+      "rewards/rejected": -56.13761520385742,
+      "step": 700
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 1056,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-800/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/qwen2.5-14b-instruct-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/qwen2.5-14b-instruct-unsloth-bnb-4bit
+- dpo
+- lora
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.0

checkpoint-800/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen2.5-14b-instruct-unsloth-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-800/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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-800/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-800/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-800/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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": 2048,
+  "pad_token": "<|im_end|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-800/trainer_state.json

@@ -0,0 +1,634 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.273066666666667,
+  "eval_steps": 500,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05688888888888889,
+      "grad_norm": 25.723350524902344,
+      "learning_rate": 1.2954545454545456e-07,
+      "logits/chosen": -0.7062767744064331,
+      "logits/rejected": -0.6522080898284912,
+      "logps/chosen": -340.785888671875,
+      "logps/rejected": -653.7647705078125,
+      "loss": 4.7628,
+      "rewards/accuracies": 0.4468750059604645,
+      "rewards/chosen": 0.001610723091289401,
+      "rewards/margins": 0.006242862902581692,
+      "rewards/rejected": -0.004632140044122934,
+      "step": 20
+    },
+    {
+      "epoch": 0.11377777777777778,
+      "grad_norm": 15.587135314941406,
+      "learning_rate": 2.6590909090909093e-07,
+      "logits/chosen": -0.678135871887207,
+      "logits/rejected": -0.6651075482368469,
+      "logps/chosen": -347.43890380859375,
+      "logps/rejected": -708.3135986328125,
+      "loss": 4.8391,
+      "rewards/accuracies": 0.522265613079071,
+      "rewards/chosen": 0.0011627988424152136,
+      "rewards/margins": 0.010068175382912159,
+      "rewards/rejected": -0.008905376307666302,
+      "step": 40
+    },
+    {
+      "epoch": 0.17066666666666666,
+      "grad_norm": 19.355424880981445,
+      "learning_rate": 4.0227272727272725e-07,
+      "logits/chosen": -0.6907597184181213,
+      "logits/rejected": -0.6496841907501221,
+      "logps/chosen": -341.603759765625,
+      "logps/rejected": -661.4761962890625,
+      "loss": 4.863,
+      "rewards/accuracies": 0.528515636920929,
+      "rewards/chosen": -0.0007408790988847613,
+      "rewards/margins": 0.02941317856311798,
+      "rewards/rejected": -0.030154060572385788,
+      "step": 60
+    },
+    {
+      "epoch": 0.22755555555555557,
+      "grad_norm": 22.927623748779297,
+      "learning_rate": 5.386363636363637e-07,
+      "logits/chosen": -0.6875197887420654,
+      "logits/rejected": -0.6486619710922241,
+      "logps/chosen": -345.1783142089844,
+      "logps/rejected": -661.5092163085938,
+      "loss": 4.7676,
+      "rewards/accuracies": 0.61328125,
+      "rewards/chosen": 0.011638931930065155,
+      "rewards/margins": 0.1211162656545639,
+      "rewards/rejected": -0.10947732627391815,
+      "step": 80
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 20.672826766967773,
+      "learning_rate": 6.75e-07,
+      "logits/chosen": -0.6816097497940063,
+      "logits/rejected": -0.6414457559585571,
+      "logps/chosen": -344.27825927734375,
+      "logps/rejected": -658.2562255859375,
+      "loss": 4.56,
+      "rewards/accuracies": 0.647656261920929,
+      "rewards/chosen": 0.04126482084393501,
+      "rewards/margins": 0.30062881112098694,
+      "rewards/rejected": -0.2593640089035034,
+      "step": 100
+    },
+    {
+      "epoch": 0.3413333333333333,
+      "grad_norm": 13.753314971923828,
+      "learning_rate": 8.113636363636363e-07,
+      "logits/chosen": -0.6626165509223938,
+      "logits/rejected": -0.642012357711792,
+      "logps/chosen": -342.14031982421875,
+      "logps/rejected": -667.3262939453125,
+      "loss": 4.3726,
+      "rewards/accuracies": 0.6734374761581421,
+      "rewards/chosen": 0.10678935050964355,
+      "rewards/margins": 0.6032775640487671,
+      "rewards/rejected": -0.4964882731437683,
+      "step": 120
+    },
+    {
+      "epoch": 0.3982222222222222,
+      "grad_norm": 7.477163791656494,
+      "learning_rate": 9.477272727272726e-07,
+      "logits/chosen": -0.6697568297386169,
+      "logits/rejected": -0.6643576622009277,
+      "logps/chosen": -343.89959716796875,
+      "logps/rejected": -715.9915161132812,
+      "loss": 4.0971,
+      "rewards/accuracies": 0.7171875238418579,
+      "rewards/chosen": 0.21032771468162537,
+      "rewards/margins": 1.4638903141021729,
+      "rewards/rejected": -1.253562569618225,
+      "step": 140
+    },
+    {
+      "epoch": 0.45511111111111113,
+      "grad_norm": 8.21181869506836,
+      "learning_rate": 1.0840909090909092e-06,
+      "logits/chosen": -0.6967095136642456,
+      "logits/rejected": -0.681812047958374,
+      "logps/chosen": -340.03509521484375,
+      "logps/rejected": -682.7234497070312,
+      "loss": 4.1412,
+      "rewards/accuracies": 0.742968738079071,
+      "rewards/chosen": 0.3784622550010681,
+      "rewards/margins": 2.152285099029541,
+      "rewards/rejected": -1.7738231420516968,
+      "step": 160
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 6.915646076202393,
+      "learning_rate": 1.2204545454545454e-06,
+      "logits/chosen": -0.6905465722084045,
+      "logits/rejected": -0.6835938692092896,
+      "logps/chosen": -337.03912353515625,
+      "logps/rejected": -689.4818725585938,
+      "loss": 3.7365,
+      "rewards/accuracies": 0.7515624761581421,
+      "rewards/chosen": 0.5243303775787354,
+      "rewards/margins": 3.7261250019073486,
+      "rewards/rejected": -3.2017948627471924,
+      "step": 180
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 6.492739200592041,
+      "learning_rate": 1.3568181818181818e-06,
+      "logits/chosen": -0.750757098197937,
+      "logits/rejected": -0.7309343814849854,
+      "logps/chosen": -339.7341003417969,
+      "logps/rejected": -700.2279663085938,
+      "loss": 3.7081,
+      "rewards/accuracies": 0.791796863079071,
+      "rewards/chosen": 0.37986624240875244,
+      "rewards/margins": 5.3291778564453125,
+      "rewards/rejected": -4.94931173324585,
+      "step": 200
+    },
+    {
+      "epoch": 0.6257777777777778,
+      "grad_norm": 5.47404670715332,
+      "learning_rate": 1.4931818181818182e-06,
+      "logits/chosen": -0.7830198407173157,
+      "logits/rejected": -0.7797198295593262,
+      "logps/chosen": -347.9498596191406,
+      "logps/rejected": -765.7747192382812,
+      "loss": 3.1446,
+      "rewards/accuracies": 0.7847656011581421,
+      "rewards/chosen": 0.12148561328649521,
+      "rewards/margins": 7.9653730392456055,
+      "rewards/rejected": -7.843888282775879,
+      "step": 220
+    },
+    {
+      "epoch": 0.6826666666666666,
+      "grad_norm": 7.549896240234375,
+      "learning_rate": 1.6295454545454544e-06,
+      "logits/chosen": -0.9069732427597046,
+      "logits/rejected": -0.9081719517707825,
+      "logps/chosen": -359.0387268066406,
+      "logps/rejected": -788.9415283203125,
+      "loss": 2.8459,
+      "rewards/accuracies": 0.801953136920929,
+      "rewards/chosen": -0.5870370268821716,
+      "rewards/margins": 11.03849983215332,
+      "rewards/rejected": -11.625536918640137,
+      "step": 240
+    },
+    {
+      "epoch": 0.7395555555555555,
+      "grad_norm": 6.950064182281494,
+      "learning_rate": 1.7659090909090909e-06,
+      "logits/chosen": -1.0507304668426514,
+      "logits/rejected": -1.0437712669372559,
+      "logps/chosen": -363.00946044921875,
+      "logps/rejected": -855.9450073242188,
+      "loss": 2.3475,
+      "rewards/accuracies": 0.7890625,
+      "rewards/chosen": -1.7975599765777588,
+      "rewards/margins": 15.68769645690918,
+      "rewards/rejected": -17.48525619506836,
+      "step": 260
+    },
+    {
+      "epoch": 0.7964444444444444,
+      "grad_norm": 7.705135822296143,
+      "learning_rate": 1.7984073648922751e-06,
+      "logits/chosen": -1.271202802658081,
+      "logits/rejected": -1.2308619022369385,
+      "logps/chosen": -372.968017578125,
+      "logps/rejected": -874.5939331054688,
+      "loss": 2.0129,
+      "rewards/accuracies": 0.7964843511581421,
+      "rewards/chosen": -2.9631118774414062,
+      "rewards/margins": 19.912986755371094,
+      "rewards/rejected": -22.876102447509766,
+      "step": 280
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 12.216048240661621,
+      "learning_rate": 1.7913403507563104e-06,
+      "logits/chosen": -1.400701880455017,
+      "logits/rejected": -1.363081455230713,
+      "logps/chosen": -379.55963134765625,
+      "logps/rejected": -1006.6408081054688,
+      "loss": 1.8445,
+      "rewards/accuracies": 0.805468738079071,
+      "rewards/chosen": -3.517793655395508,
+      "rewards/margins": 27.90765380859375,
+      "rewards/rejected": -31.42544937133789,
+      "step": 300
+    },
+    {
+      "epoch": 0.9102222222222223,
+      "grad_norm": 5.293786525726318,
+      "learning_rate": 1.7786664064079399e-06,
+      "logits/chosen": -1.4596669673919678,
+      "logits/rejected": -1.4353153705596924,
+      "logps/chosen": -385.25439453125,
+      "logps/rejected": -1005.0475463867188,
+      "loss": 1.5993,
+      "rewards/accuracies": 0.823437511920929,
+      "rewards/chosen": -3.530385971069336,
+      "rewards/margins": 30.658462524414062,
+      "rewards/rejected": -34.18885040283203,
+      "step": 320
+    },
+    {
+      "epoch": 0.9671111111111111,
+      "grad_norm": 5.214448928833008,
+      "learning_rate": 1.7604652566362601e-06,
+      "logits/chosen": -1.4935115575790405,
+      "logits/rejected": -1.4993070363998413,
+      "logps/chosen": -374.81219482421875,
+      "logps/rejected": -1065.3048095703125,
+      "loss": 1.4563,
+      "rewards/accuracies": 0.8140624761581421,
+      "rewards/chosen": -3.6835930347442627,
+      "rewards/margins": 35.69647979736328,
+      "rewards/rejected": -39.38006591796875,
+      "step": 340
+    },
+    {
+      "epoch": 1.0227555555555556,
+      "grad_norm": 5.167357921600342,
+      "learning_rate": 1.7368513948291994e-06,
+      "logits/chosen": -1.5450448989868164,
+      "logits/rejected": -1.5312340259552002,
+      "logps/chosen": -390.2657165527344,
+      "logps/rejected": -1115.527587890625,
+      "loss": 1.4704,
+      "rewards/accuracies": 0.8154951930046082,
+      "rewards/chosen": -3.921747922897339,
+      "rewards/margins": 38.49018096923828,
+      "rewards/rejected": -42.411930084228516,
+      "step": 360
+    },
+    {
+      "epoch": 1.0796444444444444,
+      "grad_norm": 4.9285407066345215,
+      "learning_rate": 1.707973362758804e-06,
+      "logits/chosen": -1.5365326404571533,
+      "logits/rejected": -1.5479919910430908,
+      "logps/chosen": -379.05078125,
+      "logps/rejected": -1110.8424072265625,
+      "loss": 1.524,
+      "rewards/accuracies": 0.815625011920929,
+      "rewards/chosen": -3.505291700363159,
+      "rewards/margins": 39.89087677001953,
+      "rewards/rejected": -43.39616775512695,
+      "step": 380
+    },
+    {
+      "epoch": 1.1365333333333334,
+      "grad_norm": 4.965682029724121,
+      "learning_rate": 1.6740128161869303e-06,
+      "logits/chosen": -1.5383026599884033,
+      "logits/rejected": -1.5448668003082275,
+      "logps/chosen": -375.23004150390625,
+      "logps/rejected": -1089.509033203125,
+      "loss": 1.2728,
+      "rewards/accuracies": 0.83984375,
+      "rewards/chosen": -3.8725147247314453,
+      "rewards/margins": 40.29158401489258,
+      "rewards/rejected": -44.164100646972656,
+      "step": 400
+    },
+    {
+      "epoch": 1.1934222222222222,
+      "grad_norm": 4.170207500457764,
+      "learning_rate": 1.635183382169105e-06,
+      "logits/chosen": -1.6174129247665405,
+      "logits/rejected": -1.598515272140503,
+      "logps/chosen": -385.2093200683594,
+      "logps/rejected": -1157.7808837890625,
+      "loss": 1.2895,
+      "rewards/accuracies": 0.830859363079071,
+      "rewards/chosen": -4.239663600921631,
+      "rewards/margins": 44.047298431396484,
+      "rewards/rejected": -48.28696823120117,
+      "step": 420
+    },
+    {
+      "epoch": 1.2503111111111112,
+      "grad_norm": 4.982669353485107,
+      "learning_rate": 1.5917293152446181e-06,
+      "logits/chosen": -1.6095243692398071,
+      "logits/rejected": -1.6014487743377686,
+      "logps/chosen": -391.41705322265625,
+      "logps/rejected": -1123.428466796875,
+      "loss": 1.3683,
+      "rewards/accuracies": 0.835156261920929,
+      "rewards/chosen": -4.419755458831787,
+      "rewards/margins": 43.6191520690918,
+      "rewards/rejected": -48.03890609741211,
+      "step": 440
+    },
+    {
+      "epoch": 1.3072,
+      "grad_norm": 5.365580081939697,
+      "learning_rate": 1.5439239609660238e-06,
+      "logits/chosen": -1.55153489112854,
+      "logits/rejected": -1.5819648504257202,
+      "logps/chosen": -379.72222900390625,
+      "logps/rejected": -1220.7442626953125,
+      "loss": 1.3303,
+      "rewards/accuracies": 0.8285156488418579,
+      "rewards/chosen": -3.9600634574890137,
+      "rewards/margins": 50.48019790649414,
+      "rewards/rejected": -54.44025421142578,
+      "step": 460
+    },
+    {
+      "epoch": 1.364088888888889,
+      "grad_norm": 5.603168964385986,
+      "learning_rate": 1.492068036433128e-06,
+      "logits/chosen": -1.5621448755264282,
+      "logits/rejected": -1.5893001556396484,
+      "logps/chosen": -379.4105224609375,
+      "logps/rejected": -1226.2530517578125,
+      "loss": 1.3152,
+      "rewards/accuracies": 0.837890625,
+      "rewards/chosen": -3.8145880699157715,
+      "rewards/margins": 50.653114318847656,
+      "rewards/rejected": -54.46770095825195,
+      "step": 480
+    },
+    {
+      "epoch": 1.420977777777778,
+      "grad_norm": 7.285942554473877,
+      "learning_rate": 1.4364877386476803e-06,
+      "logits/chosen": -1.5568413734436035,
+      "logits/rejected": -1.5949300527572632,
+      "logps/chosen": -391.8574523925781,
+      "logps/rejected": -1221.8057861328125,
+      "loss": 1.3131,
+      "rewards/accuracies": 0.837109386920929,
+      "rewards/chosen": -4.1453447341918945,
+      "rewards/margins": 51.3240966796875,
+      "rewards/rejected": -55.46944046020508,
+      "step": 500
+    },
+    {
+      "epoch": 1.4778666666666667,
+      "grad_norm": 5.188837051391602,
+      "learning_rate": 1.3775326925880672e-06,
+      "logits/chosen": -1.5099071264266968,
+      "logits/rejected": -1.538757562637329,
+      "logps/chosen": -382.1160888671875,
+      "logps/rejected": -1294.1851806640625,
+      "loss": 1.1844,
+      "rewards/accuracies": 0.8414062261581421,
+      "rewards/chosen": -3.6662063598632812,
+      "rewards/margins": 53.77040481567383,
+      "rewards/rejected": -57.436607360839844,
+      "step": 520
+    },
+    {
+      "epoch": 1.5347555555555554,
+      "grad_norm": 5.107513904571533,
+      "learning_rate": 1.3155737519115306e-06,
+      "logits/chosen": -1.565260887145996,
+      "logits/rejected": -1.5936307907104492,
+      "logps/chosen": -380.9848937988281,
+      "logps/rejected": -1163.626708984375,
+      "loss": 1.2198,
+      "rewards/accuracies": 0.8433593511581421,
+      "rewards/chosen": -3.710998058319092,
+      "rewards/margins": 47.719356536865234,
+      "rewards/rejected": -51.43035125732422,
+      "step": 540
+    },
+    {
+      "epoch": 1.5916444444444444,
+      "grad_norm": 4.466892719268799,
+      "learning_rate": 1.2510006661184866e-06,
+      "logits/chosen": -1.5557365417480469,
+      "logits/rejected": -1.582177996635437,
+      "logps/chosen": -389.8815612792969,
+      "logps/rejected": -1274.912841796875,
+      "loss": 1.1301,
+      "rewards/accuracies": 0.84765625,
+      "rewards/chosen": -4.558670997619629,
+      "rewards/margins": 53.85039520263672,
+      "rewards/rejected": -58.4090690612793,
+      "step": 560
+    },
+    {
+      "epoch": 1.6485333333333334,
+      "grad_norm": 4.823034763336182,
+      "learning_rate": 1.1842196288535226e-06,
+      "logits/chosen": -1.5631791353225708,
+      "logits/rejected": -1.5713732242584229,
+      "logps/chosen": -388.4598693847656,
+      "logps/rejected": -1245.7056884765625,
+      "loss": 1.2336,
+      "rewards/accuracies": 0.84765625,
+      "rewards/chosen": -4.465853691101074,
+      "rewards/margins": 52.74620819091797,
+      "rewards/rejected": -57.212059020996094,
+      "step": 580
+    },
+    {
+      "epoch": 1.7054222222222222,
+      "grad_norm": 4.383596420288086,
+      "learning_rate": 1.115650722765358e-06,
+      "logits/chosen": -1.4939193725585938,
+      "logits/rejected": -1.5414621829986572,
+      "logps/chosen": -392.1934509277344,
+      "logps/rejected": -1259.5296630859375,
+      "loss": 1.1556,
+      "rewards/accuracies": 0.853515625,
+      "rewards/chosen": -4.005014419555664,
+      "rewards/margins": 54.73443603515625,
+      "rewards/rejected": -58.73945236206055,
+      "step": 600
+    },
+    {
+      "epoch": 1.7623111111111112,
+      "grad_norm": 4.128599643707275,
+      "learning_rate": 1.0457252769987484e-06,
+      "logits/chosen": -1.4883978366851807,
+      "logits/rejected": -1.5312236547470093,
+      "logps/chosen": -384.2289733886719,
+      "logps/rejected": -1305.6707763671875,
+      "loss": 1.1712,
+      "rewards/accuracies": 0.8433593511581421,
+      "rewards/chosen": -3.6986148357391357,
+      "rewards/margins": 56.77925491333008,
+      "rewards/rejected": -60.477867126464844,
+      "step": 620
+    },
+    {
+      "epoch": 1.8192,
+      "grad_norm": 6.113862037658691,
+      "learning_rate": 9.74883153940886e-07,
+      "logits/chosen": -1.49406099319458,
+      "logits/rejected": -1.5339412689208984,
+      "logps/chosen": -383.2894287109375,
+      "logps/rejected": -1249.376953125,
+      "loss": 1.1426,
+      "rewards/accuracies": 0.86328125,
+      "rewards/chosen": -4.020669937133789,
+      "rewards/margins": 53.08935546875,
+      "rewards/rejected": -57.110023498535156,
+      "step": 640
+    },
+    {
+      "epoch": 1.876088888888889,
+      "grad_norm": 5.948381423950195,
+      "learning_rate": 9.03569982289885e-07,
+      "logits/chosen": -1.5656105279922485,
+      "logits/rejected": -1.5601282119750977,
+      "logps/chosen": -395.3358154296875,
+      "logps/rejected": -1181.269775390625,
+      "loss": 1.1806,
+      "rewards/accuracies": 0.8492187261581421,
+      "rewards/chosen": -4.2404961585998535,
+      "rewards/margins": 49.447227478027344,
+      "rewards/rejected": -53.6877326965332,
+      "step": 660
+    },
+    {
+      "epoch": 1.932977777777778,
+      "grad_norm": 5.629128932952881,
+      "learning_rate": 8.322343538505857e-07,
+      "logits/chosen": -1.5090030431747437,
+      "logits/rejected": -1.533573865890503,
+      "logps/chosen": -383.603759765625,
+      "logps/rejected": -1244.2327880859375,
+      "loss": 1.0988,
+      "rewards/accuracies": 0.866406261920929,
+      "rewards/chosen": -4.081192970275879,
+      "rewards/margins": 53.2569580078125,
+      "rewards/rejected": -57.3381462097168,
+      "step": 680
+    },
+    {
+      "epoch": 1.9898666666666667,
+      "grad_norm": 7.586100101470947,
+      "learning_rate": 7.613250016910891e-07,
+      "logits/chosen": -1.5487099885940552,
+      "logits/rejected": -1.584081768989563,
+      "logps/chosen": -376.0309753417969,
+      "logps/rejected": -1187.498779296875,
+      "loss": 1.2131,
+      "rewards/accuracies": 0.854296863079071,
+      "rewards/chosen": -3.9285030364990234,
+      "rewards/margins": 52.20911407470703,
+      "rewards/rejected": -56.13761520385742,
+      "step": 700
+    },
+    {
+      "epoch": 2.0455111111111113,
+      "grad_norm": 6.459462642669678,
+      "learning_rate": 6.912879774106832e-07,
+      "logits/chosen": -1.5404038429260254,
+      "logits/rejected": -1.5544073581695557,
+      "logps/chosen": -391.65802001953125,
+      "logps/rejected": -1347.5230712890625,
+      "loss": 1.0787,
+      "rewards/accuracies": 0.8526358008384705,
+      "rewards/chosen": -4.6590704917907715,
+      "rewards/margins": 61.01871871948242,
+      "rewards/rejected": -65.67778778076172,
+      "step": 720
+    },
+    {
+      "epoch": 2.1024,
+      "grad_norm": 5.285444736480713,
+      "learning_rate": 6.22563845275411e-07,
+      "logits/chosen": -1.5507022142410278,
+      "logits/rejected": -1.5908031463623047,
+      "logps/chosen": -396.8876647949219,
+      "logps/rejected": -1277.197021484375,
+      "loss": 1.1096,
+      "rewards/accuracies": 0.8589843511581421,
+      "rewards/chosen": -4.302851676940918,
+      "rewards/margins": 56.465980529785156,
+      "rewards/rejected": -60.768829345703125,
+      "step": 740
+    },
+    {
+      "epoch": 2.159288888888889,
+      "grad_norm": 6.371775150299072,
+      "learning_rate": 5.555849108714193e-07,
+      "logits/chosen": -1.502539873123169,
+      "logits/rejected": -1.5360302925109863,
+      "logps/chosen": -388.4836730957031,
+      "logps/rejected": -1289.794677734375,
+      "loss": 1.0641,
+      "rewards/accuracies": 0.868359386920929,
+      "rewards/chosen": -4.061135292053223,
+      "rewards/margins": 56.32740020751953,
+      "rewards/rejected": -60.38853073120117,
+      "step": 760
+    },
+    {
+      "epoch": 2.216177777777778,
+      "grad_norm": 6.24968147277832,
+      "learning_rate": 4.907725017091098e-07,
+      "logits/chosen": -1.5619838237762451,
+      "logits/rejected": -1.5966746807098389,
+      "logps/chosen": -377.2914123535156,
+      "logps/rejected": -1242.04150390625,
+      "loss": 1.0621,
+      "rewards/accuracies": 0.871874988079071,
+      "rewards/chosen": -4.108449459075928,
+      "rewards/margins": 53.869850158691406,
+      "rewards/rejected": -57.978294372558594,
+      "step": 780
+    },
+    {
+      "epoch": 2.273066666666667,
+      "grad_norm": 5.537705898284912,
+      "learning_rate": 4.2853431688430274e-07,
+      "logits/chosen": -1.5212916135787964,
+      "logits/rejected": -1.544816255569458,
+      "logps/chosen": -393.18597412109375,
+      "logps/rejected": -1313.809814453125,
+      "loss": 1.0735,
+      "rewards/accuracies": 0.858203113079071,
+      "rewards/chosen": -4.266919136047363,
+      "rewards/margins": 58.8587646484375,
+      "rewards/rejected": -63.12567901611328,
+      "step": 800
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 1056,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

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_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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": 2048,
+  "pad_token": "<|im_end|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}