metadata
library_name: transformers
license: bsd-3-clause
base_model: Salesforce/blip-image-captioning-base
tags:
- generated_from_trainer
model-index:
- name: blip-finetuned-kag100
results: []
blip-finetuned-kag100
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: 0.7098
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: 2e-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Use 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: 50
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3371 | 1.1130 | 50 | 1.0989 |
| 0.9289 | 2.2260 | 100 | 0.8548 |
| 0.7662 | 3.3390 | 150 | 0.8150 |
| 0.677 | 4.4520 | 200 | 0.7596 |
| 0.6306 | 5.5650 | 250 | 0.7650 |
| 0.61 | 6.6780 | 300 | 0.7456 |
| 0.5978 | 7.7910 | 350 | 0.7098 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0