metadata
library_name: transformers
license: bsd-3-clause
base_model: Salesforce/blip-image-captioning-base
tags:
- generated_from_trainer
model-index:
- name: BLIP_Captioning
results: []
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: 0.0201
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: 2
- eval_batch_size: 1
- seed: 42
- 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
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.047 | 0.0446 | 500 | 0.0336 |
| 0.0379 | 0.0892 | 1000 | 0.0419 |
| 0.0285 | 0.1339 | 1500 | 0.0247 |
| 0.0247 | 0.1785 | 2000 | 0.0254 |
| 0.0244 | 0.2231 | 2500 | 0.0238 |
| 0.0242 | 0.2677 | 3000 | 0.0240 |
| 0.0239 | 0.3124 | 3500 | 0.0234 |
| 0.0243 | 0.3570 | 4000 | 0.0235 |
| 0.0502 | 0.4016 | 4500 | 0.0350 |
| 0.0236 | 0.4462 | 5000 | 0.0227 |
| 0.0228 | 0.4909 | 5500 | 0.0228 |
| 0.0225 | 0.5355 | 6000 | 0.0249 |
| 0.0232 | 0.5801 | 6500 | 0.0846 |
| 0.0222 | 0.6247 | 7000 | 0.0223 |
| 0.023 | 0.6693 | 7500 | 0.0213 |
| 0.0217 | 0.7140 | 8000 | 0.0211 |
| 0.0212 | 0.7586 | 8500 | 0.0210 |
| 0.0213 | 0.8032 | 9000 | 0.0207 |
| 0.0217 | 0.8478 | 9500 | 0.0204 |
| 0.0203 | 0.8925 | 10000 | 0.0208 |
| 0.0205 | 0.9371 | 10500 | 0.0206 |
| 0.0207 | 0.9817 | 11000 | 0.0201 |
Framework versions
- Transformers 4.55.4
- Pytorch 2.1.2+cu121
- Tokenizers 0.21.4