smids_10x_beit_large_adamax_00001_fold3
This model is a fine-tuned version of microsoft/beit-large-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.7342
- Accuracy: 0.93
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1234 | 1.0 | 750 | 0.2380 | 0.9133 |
| 0.0658 | 2.0 | 1500 | 0.2732 | 0.9317 |
| 0.0204 | 3.0 | 2250 | 0.3498 | 0.9217 |
| 0.0213 | 4.0 | 3000 | 0.4104 | 0.925 |
| 0.0054 | 5.0 | 3750 | 0.4509 | 0.9317 |
| 0.0002 | 6.0 | 4500 | 0.5343 | 0.9233 |
| 0.0104 | 7.0 | 5250 | 0.5450 | 0.9267 |
| 0.0001 | 8.0 | 6000 | 0.6214 | 0.9217 |
| 0.0002 | 9.0 | 6750 | 0.5669 | 0.9333 |
| 0.0 | 10.0 | 7500 | 0.5842 | 0.9233 |
| 0.0003 | 11.0 | 8250 | 0.5405 | 0.9267 |
| 0.0007 | 12.0 | 9000 | 0.6365 | 0.9233 |
| 0.0 | 13.0 | 9750 | 0.6437 | 0.9267 |
| 0.0006 | 14.0 | 10500 | 0.6868 | 0.92 |
| 0.0 | 15.0 | 11250 | 0.6484 | 0.93 |
| 0.0 | 16.0 | 12000 | 0.6945 | 0.925 |
| 0.0 | 17.0 | 12750 | 0.6473 | 0.925 |
| 0.0 | 18.0 | 13500 | 0.7329 | 0.9233 |
| 0.0 | 19.0 | 14250 | 0.6697 | 0.9283 |
| 0.0 | 20.0 | 15000 | 0.7054 | 0.9317 |
| 0.0 | 21.0 | 15750 | 0.7229 | 0.9267 |
| 0.0001 | 22.0 | 16500 | 0.6657 | 0.9267 |
| 0.0 | 23.0 | 17250 | 0.6845 | 0.925 |
| 0.0 | 24.0 | 18000 | 0.7071 | 0.9233 |
| 0.0 | 25.0 | 18750 | 0.7119 | 0.9267 |
| 0.0 | 26.0 | 19500 | 0.7250 | 0.9283 |
| 0.0 | 27.0 | 20250 | 0.7491 | 0.93 |
| 0.0 | 28.0 | 21000 | 0.7325 | 0.9267 |
| 0.0 | 29.0 | 21750 | 0.7225 | 0.93 |
| 0.0 | 30.0 | 22500 | 0.7702 | 0.93 |
| 0.0 | 31.0 | 23250 | 0.7702 | 0.93 |
| 0.0 | 32.0 | 24000 | 0.7279 | 0.93 |
| 0.0 | 33.0 | 24750 | 0.7215 | 0.9283 |
| 0.0 | 34.0 | 25500 | 0.7215 | 0.9267 |
| 0.0 | 35.0 | 26250 | 0.7456 | 0.9267 |
| 0.0 | 36.0 | 27000 | 0.7430 | 0.9267 |
| 0.0 | 37.0 | 27750 | 0.7363 | 0.9283 |
| 0.0 | 38.0 | 28500 | 0.7489 | 0.93 |
| 0.0 | 39.0 | 29250 | 0.7854 | 0.9267 |
| 0.0 | 40.0 | 30000 | 0.7378 | 0.9283 |
| 0.0 | 41.0 | 30750 | 0.7334 | 0.93 |
| 0.0 | 42.0 | 31500 | 0.7235 | 0.9333 |
| 0.0 | 43.0 | 32250 | 0.7203 | 0.93 |
| 0.0 | 44.0 | 33000 | 0.7319 | 0.9267 |
| 0.0 | 45.0 | 33750 | 0.7326 | 0.93 |
| 0.0 | 46.0 | 34500 | 0.7443 | 0.93 |
| 0.0 | 47.0 | 35250 | 0.7511 | 0.93 |
| 0.0 | 48.0 | 36000 | 0.7575 | 0.93 |
| 0.0 | 49.0 | 36750 | 0.7357 | 0.93 |
| 0.0 | 50.0 | 37500 | 0.7342 | 0.93 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2