BLIP_Captioning
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: 1.3617
- Bleu: 1.0
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 3
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|---|---|---|---|---|
| 1.3635 | 1.0 | 779 | 1.3968 | 1.0 |
| 1.3618 | 2.0 | 1558 | 1.3618 | 1.0 |
| 1.3617 | 3.0 | 2337 | 1.3617 | 1.0 |
Framework versions
- Transformers 4.55.4
- Pytorch 2.7.1+cu118
- Datasets 4.1.1
- Tokenizers 0.21.4
- Downloads last month
- 9
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Vrjb/BLIP_Captioning
Base model
Salesforce/blip-image-captioning-base