<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
vit-base-patch16-224-in21k
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8014
- F1: 0.9731
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: 48
- eval_batch_size: 48
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 10 | 1.6255 | 0.6918 |
| No log | 2.0 | 20 | 1.4526 | 0.8397 |
| No log | 3.0 | 30 | 1.3031 | 0.8858 |
| No log | 4.0 | 40 | 1.1643 | 0.9118 |
| No log | 5.0 | 50 | 1.0448 | 0.9464 |
| No log | 6.0 | 60 | 0.9549 | 0.9597 |
| No log | 7.0 | 70 | 0.8845 | 0.9662 |
| No log | 8.0 | 80 | 0.8467 | 0.9662 |
| No log | 9.0 | 90 | 0.8094 | 0.9731 |
| No log | 10.0 | 100 | 0.8014 | 0.9731 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
