Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 qwen2_5vl_rlhf_v_lora_dpo-7b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2_vl_rlhf_v_lora_dpo-2b/checkpoint-180/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2_vl_rlhf_v_lora_dpo-2b/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen2_vl_rlhf_v_lora_dpo-2b/README.md

@@ -0,0 +1,62 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen2-VL-2B-Instruct
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: dpo
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# dpo
+
+This model is a fine-tuned version of [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct) on the rlhf_v dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.52.4
+- Pytorch 2.7.1+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.1

qwen2_vl_rlhf_v_lora_dpo-2b/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

qwen2_vl_rlhf_v_lora_dpo-2b/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d56e76c9d150c6c0c77d9f6ce097888b0147152fe6af25dc475e221e1b99eab
+size 295494816

qwen2_vl_rlhf_v_lora_dpo-2b/added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

qwen2_vl_rlhf_v_lora_dpo-2b/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 7.844666471245414e+16,
+    "train_loss": 0.4875543488396539,
+    "train_runtime": 1128.0649,
+    "train_samples_per_second": 5.082,
+    "train_steps_per_second": 0.16
+}

qwen2_vl_rlhf_v_lora_dpo-2b/chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

qwen2_vl_rlhf_v_lora_dpo-2b/checkpoint-180/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-VL-2B-Instruct
+library_name: peft
+---
+
+# 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 0.15.2

qwen2_vl_rlhf_v_lora_dpo-2b/checkpoint-180/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

qwen2_vl_rlhf_v_lora_dpo-2b/checkpoint-180/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d56e76c9d150c6c0c77d9f6ce097888b0147152fe6af25dc475e221e1b99eab
+size 295494816

qwen2_vl_rlhf_v_lora_dpo-2b/checkpoint-180/added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

qwen2_vl_rlhf_v_lora_dpo-2b/checkpoint-180/chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

qwen2_vl_rlhf_v_lora_dpo-2b/checkpoint-180/preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

qwen2_vl_rlhf_v_lora_dpo-2b/checkpoint-180/special_tokens_map.json

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

qwen2_vl_rlhf_v_lora_dpo-2b/checkpoint-180/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

qwen2_vl_rlhf_v_lora_dpo-2b/checkpoint-180/tokenizer_config.json

@@ -0,0 +1,144 @@
+{
+  "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
+    }
+  },
+  "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen2_vl_rlhf_v_lora_dpo-2b/checkpoint-180/trainer_state.json

@@ -0,0 +1,304 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05578800557880056,
+      "grad_norm": 2.860931873321533,
+      "learning_rate": 2.5e-06,
+      "logits/chosen": -2.474816083908081,
+      "logits/rejected": -2.453963279724121,
+      "logps/chosen": -128.38099670410156,
+      "logps/rejected": -109.41753387451172,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.3968750238418579,
+      "rewards/chosen": 0.001760072773322463,
+      "rewards/margins": 0.00045003072591498494,
+      "rewards/rejected": 0.001310042105615139,
+      "step": 10
+    },
+    {
+      "epoch": 0.11157601115760112,
+      "grad_norm": 2.9104843139648438,
+      "learning_rate": 4.999529926121254e-06,
+      "logits/chosen": -2.4625372886657715,
+      "logits/rejected": -2.4530725479125977,
+      "logps/chosen": -131.52423095703125,
+      "logps/rejected": -113.1307373046875,
+      "loss": 0.6815,
+      "rewards/accuracies": 0.643750011920929,
+      "rewards/chosen": 0.0510186143219471,
+      "rewards/margins": 0.024514026939868927,
+      "rewards/rejected": 0.026504583656787872,
+      "step": 20
+    },
+    {
+      "epoch": 0.16736401673640167,
+      "grad_norm": 2.504241704940796,
+      "learning_rate": 4.943334645626589e-06,
+      "logits/chosen": -2.5088911056518555,
+      "logits/rejected": -2.493192672729492,
+      "logps/chosen": -126.16400909423828,
+      "logps/rejected": -106.37702941894531,
+      "loss": 0.6393,
+      "rewards/accuracies": 0.809374988079071,
+      "rewards/chosen": 0.16201359033584595,
+      "rewards/margins": 0.11706265807151794,
+      "rewards/rejected": 0.044950924813747406,
+      "step": 30
+    },
+    {
+      "epoch": 0.22315202231520223,
+      "grad_norm": 2.0195651054382324,
+      "learning_rate": 4.7955402672006855e-06,
+      "logits/chosen": -2.5330772399902344,
+      "logits/rejected": -2.5044496059417725,
+      "logps/chosen": -125.81680297851562,
+      "logps/rejected": -109.11861419677734,
+      "loss": 0.582,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": 0.34658801555633545,
+      "rewards/margins": 0.26886501908302307,
+      "rewards/rejected": 0.07772301137447357,
+      "step": 40
+    },
+    {
+      "epoch": 0.2789400278940028,
+      "grad_norm": 1.6576199531555176,
+      "learning_rate": 4.561687510272767e-06,
+      "logits/chosen": -2.541248321533203,
+      "logits/rejected": -2.521062135696411,
+      "logps/chosen": -127.09805297851562,
+      "logps/rejected": -109.91564178466797,
+      "loss": 0.5502,
+      "rewards/accuracies": 0.8031250238418579,
+      "rewards/chosen": 0.37349846959114075,
+      "rewards/margins": 0.37017664313316345,
+      "rewards/rejected": 0.0033218171447515488,
+      "step": 50
+    },
+    {
+      "epoch": 0.33472803347280333,
+      "grad_norm": 1.558912754058838,
+      "learning_rate": 4.250543369417921e-06,
+      "logits/chosen": -2.5748090744018555,
+      "logits/rejected": -2.5500807762145996,
+      "logps/chosen": -134.46868896484375,
+      "logps/rejected": -121.32772827148438,
+      "loss": 0.5172,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": 0.3788844347000122,
+      "rewards/margins": 0.49704888463020325,
+      "rewards/rejected": -0.11816444993019104,
+      "step": 60
+    },
+    {
+      "epoch": 0.3905160390516039,
+      "grad_norm": 1.467755675315857,
+      "learning_rate": 3.8737724451770155e-06,
+      "logits/chosen": -2.5774624347686768,
+      "logits/rejected": -2.545295238494873,
+      "logps/chosen": -129.34988403320312,
+      "logps/rejected": -114.44097900390625,
+      "loss": 0.4988,
+      "rewards/accuracies": 0.840624988079071,
+      "rewards/chosen": 0.24869322776794434,
+      "rewards/margins": 0.5921556949615479,
+      "rewards/rejected": -0.3434625267982483,
+      "step": 70
+    },
+    {
+      "epoch": 0.44630404463040446,
+      "grad_norm": 1.3876789808273315,
+      "learning_rate": 3.4454996454291066e-06,
+      "logits/chosen": -2.551975727081299,
+      "logits/rejected": -2.527541399002075,
+      "logps/chosen": -128.46864318847656,
+      "logps/rejected": -116.39413452148438,
+      "loss": 0.4751,
+      "rewards/accuracies": 0.840624988079071,
+      "rewards/chosen": 0.03311532735824585,
+      "rewards/margins": 0.6590868830680847,
+      "rewards/rejected": -0.6259715557098389,
+      "step": 80
+    },
+    {
+      "epoch": 0.502092050209205,
+      "grad_norm": 1.6014125347137451,
+      "learning_rate": 2.9817806513702247e-06,
+      "logits/chosen": -2.5798611640930176,
+      "logits/rejected": -2.5456395149230957,
+      "logps/chosen": -132.5531005859375,
+      "logps/rejected": -120.17030334472656,
+      "loss": 0.445,
+      "rewards/accuracies": 0.8281250596046448,
+      "rewards/chosen": 0.09921170771121979,
+      "rewards/margins": 0.8374041318893433,
+      "rewards/rejected": -0.7381923198699951,
+      "step": 90
+    },
+    {
+      "epoch": 0.5578800557880056,
+      "grad_norm": 1.496268391609192,
+      "learning_rate": 2.5e-06,
+      "logits/chosen": -2.53275990486145,
+      "logits/rejected": -2.503383159637451,
+      "logps/chosen": -134.9202117919922,
+      "logps/rejected": -121.64453125,
+      "loss": 0.4395,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -0.1287640631198883,
+      "rewards/margins": 0.8397741317749023,
+      "rewards/rejected": -0.9685381650924683,
+      "step": 100
+    },
+    {
+      "epoch": 0.6136680613668062,
+      "grad_norm": 1.5027269124984741,
+      "learning_rate": 2.0182193486297757e-06,
+      "logits/chosen": -2.578484535217285,
+      "logits/rejected": -2.5407819747924805,
+      "logps/chosen": -126.85921478271484,
+      "logps/rejected": -113.92669677734375,
+      "loss": 0.4229,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": -0.16769157350063324,
+      "rewards/margins": 0.9286925196647644,
+      "rewards/rejected": -1.096384048461914,
+      "step": 110
+    },
+    {
+      "epoch": 0.6694560669456067,
+      "grad_norm": 2.104522705078125,
+      "learning_rate": 1.5545003545708942e-06,
+      "logits/chosen": -2.494055986404419,
+      "logits/rejected": -2.4781241416931152,
+      "logps/chosen": -141.3282012939453,
+      "logps/rejected": -132.56051635742188,
+      "loss": 0.438,
+      "rewards/accuracies": 0.8343750238418579,
+      "rewards/chosen": -0.41872626543045044,
+      "rewards/margins": 0.8836610317230225,
+      "rewards/rejected": -1.3023872375488281,
+      "step": 120
+    },
+    {
+      "epoch": 0.7252440725244073,
+      "grad_norm": 1.509999394416809,
+      "learning_rate": 1.1262275548229852e-06,
+      "logits/chosen": -2.5574772357940674,
+      "logits/rejected": -2.5306344032287598,
+      "logps/chosen": -130.0627899169922,
+      "logps/rejected": -120.96627807617188,
+      "loss": 0.4291,
+      "rewards/accuracies": 0.8656250238418579,
+      "rewards/chosen": -0.3607045114040375,
+      "rewards/margins": 0.9651679992675781,
+      "rewards/rejected": -1.3258726596832275,
+      "step": 130
+    },
+    {
+      "epoch": 0.7810320781032078,
+      "grad_norm": 1.61195969581604,
+      "learning_rate": 7.494566305820788e-07,
+      "logits/chosen": -2.5046210289001465,
+      "logits/rejected": -2.4775137901306152,
+      "logps/chosen": -132.37576293945312,
+      "logps/rejected": -124.72081756591797,
+      "loss": 0.4313,
+      "rewards/accuracies": 0.8437500596046448,
+      "rewards/chosen": -0.30062463879585266,
+      "rewards/margins": 0.9153996109962463,
+      "rewards/rejected": -1.2160242795944214,
+      "step": 140
+    },
+    {
+      "epoch": 0.8368200836820083,
+      "grad_norm": 1.608431339263916,
+      "learning_rate": 4.383124897272331e-07,
+      "logits/chosen": -2.50140643119812,
+      "logits/rejected": -2.4647293090820312,
+      "logps/chosen": -138.96994018554688,
+      "logps/rejected": -127.98197174072266,
+      "loss": 0.3867,
+      "rewards/accuracies": 0.8843750357627869,
+      "rewards/chosen": -0.21217168867588043,
+      "rewards/margins": 1.1278855800628662,
+      "rewards/rejected": -1.340057373046875,
+      "step": 150
+    },
+    {
+      "epoch": 0.8926080892608089,
+      "grad_norm": 1.35207200050354,
+      "learning_rate": 2.044597327993153e-07,
+      "logits/chosen": -2.531005382537842,
+      "logits/rejected": -2.5070996284484863,
+      "logps/chosen": -140.26632690429688,
+      "logps/rejected": -130.41412353515625,
+      "loss": 0.3867,
+      "rewards/accuracies": 0.8687499761581421,
+      "rewards/chosen": -0.38485491275787354,
+      "rewards/margins": 1.1035683155059814,
+      "rewards/rejected": -1.4884231090545654,
+      "step": 160
+    },
+    {
+      "epoch": 0.9483960948396095,
+      "grad_norm": 1.389344573020935,
+      "learning_rate": 5.6665354373411085e-08,
+      "logits/chosen": -2.4752674102783203,
+      "logits/rejected": -2.440335273742676,
+      "logps/chosen": -136.71250915527344,
+      "logps/rejected": -130.11831665039062,
+      "loss": 0.4042,
+      "rewards/accuracies": 0.8531249761581421,
+      "rewards/chosen": -0.35802966356277466,
+      "rewards/margins": 1.0405131578445435,
+      "rewards/rejected": -1.398542881011963,
+      "step": 170
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.70027095079422,
+      "learning_rate": 4.700738787466463e-10,
+      "logits/chosen": -2.5242204666137695,
+      "logits/rejected": -2.4968087673187256,
+      "logps/chosen": -129.76283264160156,
+      "logps/rejected": -122.41654968261719,
+      "loss": 0.3551,
+      "rewards/accuracies": 0.9020270705223083,
+      "rewards/chosen": -0.517316460609436,
+      "rewards/margins": 1.016798496246338,
+      "rewards/rejected": -1.5341150760650635,
+      "step": 180
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 180,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.844666471245414e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

qwen2_vl_rlhf_v_lora_dpo-2b/checkpoint-180/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83faf60bcedee665de6a3558bb3cbbbad31e2828abf7efe2ae5a667aab0e616d
+size 6161

qwen2_vl_rlhf_v_lora_dpo-2b/checkpoint-180/video_preprocessor_config.json

@@ -0,0 +1,86 @@
+{
+  "_valid_kwargs_names": [
+    "do_convert_rgb",
+    "do_resize",
+    "size",
+    "size_divisor",
+    "default_to_square",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "do_center_crop",
+    "crop_size",
+    "data_format",
+    "input_data_format",
+    "device",
+    "min_pixels",
+    "max_pixels",
+    "patch_size",
+    "temporal_patch_size",
+    "merge_size"
+  ],
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "model_valid_processing_keys": [
+    "do_convert_rgb",
+    "do_resize",
+    "size",
+    "size_divisor",
+    "default_to_square",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "do_center_crop",
+    "crop_size",
+    "data_format",
+    "input_data_format",
+    "device",
+    "min_pixels",
+    "max_pixels",
+    "patch_size",
+    "temporal_patch_size",
+    "merge_size"
+  ],
+  "patch_size": 14,
+  "processor_class": "Qwen2VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "size_divisor": null,
+  "temporal_patch_size": 2,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}

qwen2_vl_rlhf_v_lora_dpo-2b/preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

qwen2_vl_rlhf_v_lora_dpo-2b/special_tokens_map.json

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

qwen2_vl_rlhf_v_lora_dpo-2b/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

qwen2_vl_rlhf_v_lora_dpo-2b/tokenizer_config.json

@@ -0,0 +1,144 @@
+{
+  "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
+    }
+  },
+  "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen2_vl_rlhf_v_lora_dpo-2b/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 7.844666471245414e+16,
+    "train_loss": 0.4875543488396539,
+    "train_runtime": 1128.0649,
+    "train_samples_per_second": 5.082,
+    "train_steps_per_second": 0.16
+}

qwen2_vl_rlhf_v_lora_dpo-2b/trainer_log.jsonl

@@ -0,0 +1,19 @@
+{"current_steps": 10, "total_steps": 180, "loss": 0.6931, "accuracy": 0.3968750238418579, "lr": 2.5e-06, "epoch": 0.05578800557880056, "percentage": 5.56, "elapsed_time": "0:00:54", "remaining_time": "0:15:23"}
+{"current_steps": 20, "total_steps": 180, "loss": 0.6815, "accuracy": 0.643750011920929, "lr": 4.999529926121254e-06, "epoch": 0.11157601115760112, "percentage": 11.11, "elapsed_time": "0:01:50", "remaining_time": "0:14:44"}
+{"current_steps": 30, "total_steps": 180, "loss": 0.6393, "accuracy": 0.809374988079071, "lr": 4.943334645626589e-06, "epoch": 0.16736401673640167, "percentage": 16.67, "elapsed_time": "0:02:42", "remaining_time": "0:13:32"}
+{"current_steps": 40, "total_steps": 180, "loss": 0.582, "accuracy": 0.8187500238418579, "lr": 4.7955402672006855e-06, "epoch": 0.22315202231520223, "percentage": 22.22, "elapsed_time": "0:03:35", "remaining_time": "0:12:33"}
+{"current_steps": 50, "total_steps": 180, "loss": 0.5502, "accuracy": 0.8031250238418579, "lr": 4.561687510272767e-06, "epoch": 0.2789400278940028, "percentage": 27.78, "elapsed_time": "0:04:24", "remaining_time": "0:11:26"}
+{"current_steps": 60, "total_steps": 180, "loss": 0.5172, "accuracy": 0.824999988079071, "lr": 4.250543369417921e-06, "epoch": 0.33472803347280333, "percentage": 33.33, "elapsed_time": "0:05:18", "remaining_time": "0:10:36"}
+{"current_steps": 70, "total_steps": 180, "loss": 0.4988, "accuracy": 0.840624988079071, "lr": 3.8737724451770155e-06, "epoch": 0.3905160390516039, "percentage": 38.89, "elapsed_time": "0:06:08", "remaining_time": "0:09:39"}
+{"current_steps": 80, "total_steps": 180, "loss": 0.4751, "accuracy": 0.840624988079071, "lr": 3.4454996454291066e-06, "epoch": 0.44630404463040446, "percentage": 44.44, "elapsed_time": "0:06:57", "remaining_time": "0:08:41"}
+{"current_steps": 90, "total_steps": 180, "loss": 0.445, "accuracy": 0.8281250596046448, "lr": 2.9817806513702247e-06, "epoch": 0.502092050209205, "percentage": 50.0, "elapsed_time": "0:07:47", "remaining_time": "0:07:47"}
+{"current_steps": 100, "total_steps": 180, "loss": 0.4395, "accuracy": 0.875, "lr": 2.5e-06, "epoch": 0.5578800557880056, "percentage": 55.56, "elapsed_time": "0:08:39", "remaining_time": "0:06:55"}
+{"current_steps": 110, "total_steps": 180, "loss": 0.4229, "accuracy": 0.862500011920929, "lr": 2.0182193486297757e-06, "epoch": 0.6136680613668062, "percentage": 61.11, "elapsed_time": "0:09:27", "remaining_time": "0:06:00"}
+{"current_steps": 120, "total_steps": 180, "loss": 0.438, "accuracy": 0.8343750238418579, "lr": 1.5545003545708942e-06, "epoch": 0.6694560669456067, "percentage": 66.67, "elapsed_time": "0:10:23", "remaining_time": "0:05:11"}
+{"current_steps": 130, "total_steps": 180, "loss": 0.4291, "accuracy": 0.8656250238418579, "lr": 1.1262275548229852e-06, "epoch": 0.7252440725244073, "percentage": 72.22, "elapsed_time": "0:11:14", "remaining_time": "0:04:19"}
+{"current_steps": 140, "total_steps": 180, "loss": 0.4313, "accuracy": 0.8437500596046448, "lr": 7.494566305820788e-07, "epoch": 0.7810320781032078, "percentage": 77.78, "elapsed_time": "0:12:05", "remaining_time": "0:03:27"}
+{"current_steps": 150, "total_steps": 180, "loss": 0.3867, "accuracy": 0.8843750357627869, "lr": 4.383124897272331e-07, "epoch": 0.8368200836820083, "percentage": 83.33, "elapsed_time": "0:13:28", "remaining_time": "0:02:41"}
+{"current_steps": 160, "total_steps": 180, "loss": 0.3867, "accuracy": 0.8687499761581421, "lr": 2.044597327993153e-07, "epoch": 0.8926080892608089, "percentage": 88.89, "elapsed_time": "0:15:15", "remaining_time": "0:01:54"}
+{"current_steps": 170, "total_steps": 180, "loss": 0.4042, "accuracy": 0.8531249761581421, "lr": 5.6665354373411085e-08, "epoch": 0.9483960948396095, "percentage": 94.44, "elapsed_time": "0:17:14", "remaining_time": "0:01:00"}
+{"current_steps": 180, "total_steps": 180, "loss": 0.3551, "accuracy": 0.9020270705223083, "lr": 4.700738787466463e-10, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:18:46", "remaining_time": "0:00:00"}
+{"current_steps": 180, "total_steps": 180, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:18:48", "remaining_time": "0:00:00"}

qwen2_vl_rlhf_v_lora_dpo-2b/trainer_state.json

@@ -0,0 +1,313 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05578800557880056,
+      "grad_norm": 2.860931873321533,
+      "learning_rate": 2.5e-06,
+      "logits/chosen": -2.474816083908081,
+      "logits/rejected": -2.453963279724121,
+      "logps/chosen": -128.38099670410156,
+      "logps/rejected": -109.41753387451172,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.3968750238418579,
+      "rewards/chosen": 0.001760072773322463,
+      "rewards/margins": 0.00045003072591498494,
+      "rewards/rejected": 0.001310042105615139,
+      "step": 10
+    },
+    {
+      "epoch": 0.11157601115760112,
+      "grad_norm": 2.9104843139648438,
+      "learning_rate": 4.999529926121254e-06,
+      "logits/chosen": -2.4625372886657715,
+      "logits/rejected": -2.4530725479125977,
+      "logps/chosen": -131.52423095703125,
+      "logps/rejected": -113.1307373046875,
+      "loss": 0.6815,
+      "rewards/accuracies": 0.643750011920929,
+      "rewards/chosen": 0.0510186143219471,
+      "rewards/margins": 0.024514026939868927,
+      "rewards/rejected": 0.026504583656787872,
+      "step": 20
+    },
+    {
+      "epoch": 0.16736401673640167,
+      "grad_norm": 2.504241704940796,
+      "learning_rate": 4.943334645626589e-06,
+      "logits/chosen": -2.5088911056518555,
+      "logits/rejected": -2.493192672729492,
+      "logps/chosen": -126.16400909423828,
+      "logps/rejected": -106.37702941894531,
+      "loss": 0.6393,
+      "rewards/accuracies": 0.809374988079071,
+      "rewards/chosen": 0.16201359033584595,
+      "rewards/margins": 0.11706265807151794,
+      "rewards/rejected": 0.044950924813747406,
+      "step": 30
+    },
+    {
+      "epoch": 0.22315202231520223,
+      "grad_norm": 2.0195651054382324,
+      "learning_rate": 4.7955402672006855e-06,
+      "logits/chosen": -2.5330772399902344,
+      "logits/rejected": -2.5044496059417725,
+      "logps/chosen": -125.81680297851562,
+      "logps/rejected": -109.11861419677734,
+      "loss": 0.582,
+      "rewards/accuracies": 0.8187500238418579,
+      "rewards/chosen": 0.34658801555633545,
+      "rewards/margins": 0.26886501908302307,
+      "rewards/rejected": 0.07772301137447357,
+      "step": 40
+    },
+    {
+      "epoch": 0.2789400278940028,
+      "grad_norm": 1.6576199531555176,
+      "learning_rate": 4.561687510272767e-06,
+      "logits/chosen": -2.541248321533203,
+      "logits/rejected": -2.521062135696411,
+      "logps/chosen": -127.09805297851562,
+      "logps/rejected": -109.91564178466797,
+      "loss": 0.5502,
+      "rewards/accuracies": 0.8031250238418579,
+      "rewards/chosen": 0.37349846959114075,
+      "rewards/margins": 0.37017664313316345,
+      "rewards/rejected": 0.0033218171447515488,
+      "step": 50
+    },
+    {
+      "epoch": 0.33472803347280333,
+      "grad_norm": 1.558912754058838,
+      "learning_rate": 4.250543369417921e-06,
+      "logits/chosen": -2.5748090744018555,
+      "logits/rejected": -2.5500807762145996,
+      "logps/chosen": -134.46868896484375,
+      "logps/rejected": -121.32772827148438,
+      "loss": 0.5172,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": 0.3788844347000122,
+      "rewards/margins": 0.49704888463020325,
+      "rewards/rejected": -0.11816444993019104,
+      "step": 60
+    },
+    {
+      "epoch": 0.3905160390516039,
+      "grad_norm": 1.467755675315857,
+      "learning_rate": 3.8737724451770155e-06,
+      "logits/chosen": -2.5774624347686768,
+      "logits/rejected": -2.545295238494873,
+      "logps/chosen": -129.34988403320312,
+      "logps/rejected": -114.44097900390625,
+      "loss": 0.4988,
+      "rewards/accuracies": 0.840624988079071,
+      "rewards/chosen": 0.24869322776794434,
+      "rewards/margins": 0.5921556949615479,
+      "rewards/rejected": -0.3434625267982483,
+      "step": 70
+    },
+    {
+      "epoch": 0.44630404463040446,
+      "grad_norm": 1.3876789808273315,
+      "learning_rate": 3.4454996454291066e-06,
+      "logits/chosen": -2.551975727081299,
+      "logits/rejected": -2.527541399002075,
+      "logps/chosen": -128.46864318847656,
+      "logps/rejected": -116.39413452148438,
+      "loss": 0.4751,
+      "rewards/accuracies": 0.840624988079071,
+      "rewards/chosen": 0.03311532735824585,
+      "rewards/margins": 0.6590868830680847,
+      "rewards/rejected": -0.6259715557098389,
+      "step": 80
+    },
+    {
+      "epoch": 0.502092050209205,
+      "grad_norm": 1.6014125347137451,
+      "learning_rate": 2.9817806513702247e-06,
+      "logits/chosen": -2.5798611640930176,
+      "logits/rejected": -2.5456395149230957,
+      "logps/chosen": -132.5531005859375,
+      "logps/rejected": -120.17030334472656,
+      "loss": 0.445,
+      "rewards/accuracies": 0.8281250596046448,
+      "rewards/chosen": 0.09921170771121979,
+      "rewards/margins": 0.8374041318893433,
+      "rewards/rejected": -0.7381923198699951,
+      "step": 90
+    },
+    {
+      "epoch": 0.5578800557880056,
+      "grad_norm": 1.496268391609192,
+      "learning_rate": 2.5e-06,
+      "logits/chosen": -2.53275990486145,
+      "logits/rejected": -2.503383159637451,
+      "logps/chosen": -134.9202117919922,
+      "logps/rejected": -121.64453125,
+      "loss": 0.4395,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -0.1287640631198883,
+      "rewards/margins": 0.8397741317749023,
+      "rewards/rejected": -0.9685381650924683,
+      "step": 100
+    },
+    {
+      "epoch": 0.6136680613668062,
+      "grad_norm": 1.5027269124984741,
+      "learning_rate": 2.0182193486297757e-06,
+      "logits/chosen": -2.578484535217285,
+      "logits/rejected": -2.5407819747924805,
+      "logps/chosen": -126.85921478271484,
+      "logps/rejected": -113.92669677734375,
+      "loss": 0.4229,
+      "rewards/accuracies": 0.862500011920929,
+      "rewards/chosen": -0.16769157350063324,
+      "rewards/margins": 0.9286925196647644,
+      "rewards/rejected": -1.096384048461914,
+      "step": 110
+    },
+    {
+      "epoch": 0.6694560669456067,
+      "grad_norm": 2.104522705078125,
+      "learning_rate": 1.5545003545708942e-06,
+      "logits/chosen": -2.494055986404419,
+      "logits/rejected": -2.4781241416931152,
+      "logps/chosen": -141.3282012939453,
+      "logps/rejected": -132.56051635742188,
+      "loss": 0.438,
+      "rewards/accuracies": 0.8343750238418579,
+      "rewards/chosen": -0.41872626543045044,
+      "rewards/margins": 0.8836610317230225,
+      "rewards/rejected": -1.3023872375488281,
+      "step": 120
+    },
+    {
+      "epoch": 0.7252440725244073,
+      "grad_norm": 1.509999394416809,
+      "learning_rate": 1.1262275548229852e-06,
+      "logits/chosen": -2.5574772357940674,
+      "logits/rejected": -2.5306344032287598,
+      "logps/chosen": -130.0627899169922,
+      "logps/rejected": -120.96627807617188,
+      "loss": 0.4291,
+      "rewards/accuracies": 0.8656250238418579,
+      "rewards/chosen": -0.3607045114040375,
+      "rewards/margins": 0.9651679992675781,
+      "rewards/rejected": -1.3258726596832275,
+      "step": 130
+    },
+    {
+      "epoch": 0.7810320781032078,
+      "grad_norm": 1.61195969581604,
+      "learning_rate": 7.494566305820788e-07,
+      "logits/chosen": -2.5046210289001465,
+      "logits/rejected": -2.4775137901306152,
+      "logps/chosen": -132.37576293945312,
+      "logps/rejected": -124.72081756591797,
+      "loss": 0.4313,
+      "rewards/accuracies": 0.8437500596046448,
+      "rewards/chosen": -0.30062463879585266,
+      "rewards/margins": 0.9153996109962463,
+      "rewards/rejected": -1.2160242795944214,
+      "step": 140
+    },
+    {
+      "epoch": 0.8368200836820083,
+      "grad_norm": 1.608431339263916,
+      "learning_rate": 4.383124897272331e-07,
+      "logits/chosen": -2.50140643119812,
+      "logits/rejected": -2.4647293090820312,
+      "logps/chosen": -138.96994018554688,
+      "logps/rejected": -127.98197174072266,
+      "loss": 0.3867,
+      "rewards/accuracies": 0.8843750357627869,
+      "rewards/chosen": -0.21217168867588043,
+      "rewards/margins": 1.1278855800628662,
+      "rewards/rejected": -1.340057373046875,
+      "step": 150
+    },
+    {
+      "epoch": 0.8926080892608089,
+      "grad_norm": 1.35207200050354,
+      "learning_rate": 2.044597327993153e-07,
+      "logits/chosen": -2.531005382537842,
+      "logits/rejected": -2.5070996284484863,
+      "logps/chosen": -140.26632690429688,
+      "logps/rejected": -130.41412353515625,
+      "loss": 0.3867,
+      "rewards/accuracies": 0.8687499761581421,
+      "rewards/chosen": -0.38485491275787354,
+      "rewards/margins": 1.1035683155059814,
+      "rewards/rejected": -1.4884231090545654,
+      "step": 160
+    },
+    {
+      "epoch": 0.9483960948396095,
+      "grad_norm": 1.389344573020935,
+      "learning_rate": 5.6665354373411085e-08,
+      "logits/chosen": -2.4752674102783203,
+      "logits/rejected": -2.440335273742676,
+      "logps/chosen": -136.71250915527344,
+      "logps/rejected": -130.11831665039062,
+      "loss": 0.4042,
+      "rewards/accuracies": 0.8531249761581421,
+      "rewards/chosen": -0.35802966356277466,
+      "rewards/margins": 1.0405131578445435,
+      "rewards/rejected": -1.398542881011963,
+      "step": 170
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.70027095079422,
+      "learning_rate": 4.700738787466463e-10,
+      "logits/chosen": -2.5242204666137695,
+      "logits/rejected": -2.4968087673187256,
+      "logps/chosen": -129.76283264160156,
+      "logps/rejected": -122.41654968261719,
+      "loss": 0.3551,
+      "rewards/accuracies": 0.9020270705223083,
+      "rewards/chosen": -0.517316460609436,
+      "rewards/margins": 1.016798496246338,
+      "rewards/rejected": -1.5341150760650635,
+      "step": 180
+    },
+    {
+      "epoch": 1.0,
+      "step": 180,
+      "total_flos": 7.844666471245414e+16,
+      "train_loss": 0.4875543488396539,
+      "train_runtime": 1128.0649,
+      "train_samples_per_second": 5.082,
+      "train_steps_per_second": 0.16
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 180,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.844666471245414e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

qwen2_vl_rlhf_v_lora_dpo-2b/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83faf60bcedee665de6a3558bb3cbbbad31e2828abf7efe2ae5a667aab0e616d
+size 6161

qwen2_vl_rlhf_v_lora_dpo-2b/video_preprocessor_config.json

@@ -0,0 +1,86 @@
+{
+  "_valid_kwargs_names": [
+    "do_convert_rgb",
+    "do_resize",
+    "size",
+    "size_divisor",
+    "default_to_square",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "do_center_crop",
+    "crop_size",
+    "data_format",
+    "input_data_format",
+    "device",
+    "min_pixels",
+    "max_pixels",
+    "patch_size",
+    "temporal_patch_size",
+    "merge_size"
+  ],
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "model_valid_processing_keys": [
+    "do_convert_rgb",
+    "do_resize",
+    "size",
+    "size_divisor",
+    "default_to_square",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_pad",
+    "do_center_crop",
+    "crop_size",
+    "data_format",
+    "input_data_format",
+    "device",
+    "min_pixels",
+    "max_pixels",
+    "patch_size",
+    "temporal_patch_size",
+    "merge_size"
+  ],
+  "patch_size": 14,
+  "processor_class": "Qwen2VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "size_divisor": null,
+  "temporal_patch_size": 2,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}