metadata
library_name: transformers
license: mit
base_model: Salesforce/blip2-opt-2.7b
tags:
- generated_from_trainer
model-index:
- name: blip-gqa-ft2
results: []
blip-gqa-ft2
This model is a fine-tuned version of Salesforce/blip2-opt-2.7b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.3643
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: 12
- eval_batch_size: 12
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 48
- optimizer: Use OptimizerNames.ADAMW_TORCH 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 |
|---|---|---|---|
| 2.3951 | 1.0 | 834 | 2.3899 |
| 2.1612 | 2.0 | 1668 | 2.3136 |
| 1.9679 | 3.0 | 2502 | 2.3081 |
| 1.6637 | 4.0 | 3336 | 2.4092 |
| 1.3671 | 5.0 | 4170 | 2.5614 |
| 1.0208 | 6.0 | 5004 | 2.8319 |
| 0.7236 | 7.0 | 5838 | 3.1588 |
| 0.4731 | 8.0 | 6672 | 3.5582 |
| 0.3325 | 9.0 | 7506 | 3.9899 |
| 0.2296 | 9.9886 | 8330 | 4.3643 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.5.1+cu121
- Datasets 3.5.0
- Tokenizers 0.21.1