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
- -