russellyq/Qwen2.5-VL-7B-Instruct-SFT-2e

qwen2_5vl-7b-2e

This model is a fine-tuned version of /research/d7/gds/qyan24/model_weights/Qwen2.5-VL-7B-Instruct on the Med-R1-SFT 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: 2e-05
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 8
• 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: 0.15
• num_epochs: 2.0

Training results

Framework versions

• Transformers 4.55.0
• Pytorch 2.5.1+cu121
• Datasets 3.6.0
• Tokenizers 0.21.1