You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

Qwen2vl_instruct_medical_impresstion_full

This model is a fine-tuned version of Qwen/Qwen2-VL-7B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3023

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: 3e-05
  • train_batch_size: 20
  • eval_batch_size: 20
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 7
  • total_train_batch_size: 140
  • total_eval_batch_size: 140
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 0.03
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss
0.1323 3.2258 100 0.1730
0.1093 6.4516 200 0.1813
0.0928 9.6774 300 0.1988
0.0776 12.9032 400 0.2168
0.0528 16.1290 500 0.2736
0.0493 19.3548 600 0.3023

Framework versions

  • Transformers 4.51.3
  • Pytorch 2.8.0.dev20250507+cu128
  • Datasets 3.5.0
  • Tokenizers 0.21.1
Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for THP2903/Qwen2vl_7b_instruct_medical_impresstion_full_all

Base model

Qwen/Qwen2-VL-7B
Finetuned
(594)
this model