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: 0.0001
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
- 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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0034 | 1.0707 | 1500 | 0.0009 |
| 0.0013 | 2.1413 | 3000 | 0.0003 |
| 0.0009 | 3.2120 | 4500 | 0.0002 |
| 0.0003 | 4.2827 | 6000 | 0.0001 |
Framework versions
- Transformers 4.55.4
- Pytorch 2.5.1+cu121
- Tokenizers 0.21.4