medical-caption-model-v1
This model is a fine-tuned version of nlpconnect/vit-gpt2-image-captioning on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.0189
- Bleu: 0.0332
- Meteor: 5.8196
- Rougel: 10.2378
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-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- 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: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Meteor | Rougel |
|---|---|---|---|---|---|---|
| 5.1913 | 2.0 | 200 | 5.2321 | 0.0396 | 7.0115 | 10.6658 |
| 4.6615 | 4.0 | 400 | 4.9947 | 0.0495 | 6.1088 | 10.9570 |
| 4.3567 | 6.0 | 600 | 4.9261 | 0.0384 | 5.7674 | 11.0691 |
| 4.0884 | 8.0 | 800 | 4.9632 | 0.0344 | 5.9190 | 10.6889 |
| 3.9311 | 10.0 | 1000 | 5.0189 | 0.0332 | 5.8196 | 10.2378 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0