vit-gpt-person-image-captioning
This model is a fine-tuned version of nlpconnect/vit-gpt2-image-captioning on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0173
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-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.9984 | 312 | 0.0211 |
| 0.0609 | 2.0 | 625 | 0.0194 |
| 0.0609 | 2.9984 | 937 | 0.0183 |
| 0.021 | 4.0 | 1250 | 0.0176 |
| 0.0194 | 4.992 | 1560 | 0.0173 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1