vit-hybrid-base-bit-384-finetuned-ibird
This model is a fine-tuned version of google/vit-hybrid-base-bit-384 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0200
- Accuracy: 0.9942
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0997 | 1.0 | 565 | 0.0310 | 0.9907 |
| 0.0005 | 2.0 | 1131 | 0.0196 | 0.9951 |
| 0.0014 | 3.0 | 1695 | 0.0200 | 0.9942 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Tokenizers 0.15.2