smids_3x_beit_base_rms_001_fold1
This model is a fine-tuned version of microsoft/beit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.7807
- Accuracy: 0.7579
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: 0.001
- 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 |
---|---|---|---|---|
1.1042 | 1.0 | 226 | 1.0981 | 0.3456 |
0.942 | 2.0 | 452 | 0.9022 | 0.5275 |
0.8328 | 3.0 | 678 | 0.9600 | 0.4691 |
0.8702 | 4.0 | 904 | 0.9083 | 0.5543 |
0.8313 | 5.0 | 1130 | 0.8171 | 0.5760 |
0.8558 | 6.0 | 1356 | 0.8467 | 0.5342 |
0.7514 | 7.0 | 1582 | 0.7612 | 0.6277 |
0.7839 | 8.0 | 1808 | 0.7968 | 0.5659 |
0.7602 | 9.0 | 2034 | 0.7655 | 0.6210 |
0.7694 | 10.0 | 2260 | 0.7429 | 0.6060 |
0.7166 | 11.0 | 2486 | 0.7968 | 0.5626 |
0.7048 | 12.0 | 2712 | 0.8272 | 0.6077 |
0.6745 | 13.0 | 2938 | 0.8054 | 0.5993 |
0.7185 | 14.0 | 3164 | 0.7867 | 0.6194 |
0.7264 | 15.0 | 3390 | 0.7701 | 0.6377 |
0.6767 | 16.0 | 3616 | 0.7383 | 0.6144 |
0.6006 | 17.0 | 3842 | 0.8677 | 0.6077 |
0.6721 | 18.0 | 4068 | 0.7460 | 0.6361 |
0.6352 | 19.0 | 4294 | 0.7492 | 0.6127 |
0.642 | 20.0 | 4520 | 0.7712 | 0.6160 |
0.6647 | 21.0 | 4746 | 0.7257 | 0.6544 |
0.6408 | 22.0 | 4972 | 0.7629 | 0.6611 |
0.7655 | 23.0 | 5198 | 0.7723 | 0.6127 |
0.7074 | 24.0 | 5424 | 0.6879 | 0.6928 |
0.6919 | 25.0 | 5650 | 0.6962 | 0.6828 |
0.698 | 26.0 | 5876 | 0.7479 | 0.6361 |
0.641 | 27.0 | 6102 | 0.7653 | 0.6644 |
0.6417 | 28.0 | 6328 | 0.7791 | 0.6594 |
0.6123 | 29.0 | 6554 | 0.7195 | 0.6761 |
0.5918 | 30.0 | 6780 | 0.6991 | 0.6995 |
0.5562 | 31.0 | 7006 | 0.6938 | 0.6978 |
0.6293 | 32.0 | 7232 | 0.6564 | 0.7145 |
0.5615 | 33.0 | 7458 | 0.7421 | 0.6878 |
0.5411 | 34.0 | 7684 | 0.6688 | 0.7145 |
0.4483 | 35.0 | 7910 | 0.7701 | 0.6962 |
0.4776 | 36.0 | 8136 | 0.6349 | 0.7412 |
0.4775 | 37.0 | 8362 | 0.6430 | 0.7262 |
0.4854 | 38.0 | 8588 | 0.7095 | 0.7078 |
0.4208 | 39.0 | 8814 | 0.6254 | 0.7412 |
0.3846 | 40.0 | 9040 | 0.6645 | 0.7396 |
0.3663 | 41.0 | 9266 | 0.6430 | 0.7563 |
0.3616 | 42.0 | 9492 | 0.6767 | 0.7462 |
0.3863 | 43.0 | 9718 | 0.6432 | 0.7596 |
0.2608 | 44.0 | 9944 | 0.6472 | 0.7563 |
0.4159 | 45.0 | 10170 | 0.6400 | 0.7663 |
0.333 | 46.0 | 10396 | 0.6911 | 0.7613 |
0.2718 | 47.0 | 10622 | 0.7119 | 0.7696 |
0.2639 | 48.0 | 10848 | 0.7421 | 0.7596 |
0.236 | 49.0 | 11074 | 0.7543 | 0.7613 |
0.2672 | 50.0 | 11300 | 0.7807 | 0.7579 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2
- Downloads last month
- 0