english-image-caption-blip
This model is a fine-tuned version of Salesforce/blip-image-captioning-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0130
- Token Accuracy: 0.0696
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: 16
- eval_batch_size: 16
- seed: 42
- 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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Token Accuracy |
|---|---|---|---|---|
| 2.0850 | 1.0 | 203 | 2.0267 | 0.0697 |
| 1.4486 | 2.0 | 406 | 2.0130 | 0.0696 |
| 0.9942 | 3.0 | 609 | 2.1572 | 0.0693 |
| 0.6292 | 4.0 | 812 | 2.2744 | 0.0620 |
| 0.3937 | 5.0 | 1015 | 2.4347 | 0.0559 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.11.0+cu128
- Datasets 5.0.1
- Tokenizers 0.23.1