wonwonn/diversifier_generated_adapter

1---2library_name: peft3license: other4base_model: Qwen/Qwen2.5-VL-7B-Instruct5tags:6- base_model:adapter:Qwen/Qwen2.5-VL-7B-Instruct7- llama-factory8- lora9- transformers10pipeline_tag: text-generation11model-index:12- name: Qwen2.5-VL-7B-diversifier-sft-generated13  results: []14---15 16<!-- This model card has been generated automatically according to the information the Trainer had access to. You17should probably proofread and complete it, then remove this comment. -->18 19# Qwen2.5-VL-7B-diversifier-sft-generated20 21This model is a fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) on the diversifier_sft_generated dataset.22 23## Model description24 25More information needed26 27## Intended uses & limitations28 29More information needed30 31## Training and evaluation data32 33More information needed34 35## Training procedure36 37### Training hyperparameters38 39The following hyperparameters were used during training:40- learning_rate: 2e-0641- train_batch_size: 242- eval_batch_size: 843- seed: 4244- distributed_type: multi-GPU45- gradient_accumulation_steps: 246- total_train_batch_size: 447- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments48- lr_scheduler_type: cosine49- lr_scheduler_warmup_steps: 0.0550- num_epochs: 251 52### Training results53 54 55 56### Framework versions57 58- PEFT 0.18.159- Transformers 5.2.060- Pytorch 2.5.1+cu12461- Datasets 4.0.062- Tokenizers 0.22.2