<!-- 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. -->
wbc-50-no-pretrain-20-epoch
This model is a fine-tuned version of on the image_folder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2332
- Accuracy: 0.9242
- F1: 0.9261
- Precision: 0.9300
- Recall: 0.9242
- Balanced Acc: 0.9151
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Balanced Acc |
|---|---|---|---|---|---|---|---|---|
| 1.4968 | 1.0 | 33 | 1.4491 | 0.1944 | 0.1423 | 0.5006 | 0.1944 | 0.4518 |
| 1.1574 | 2.0 | 66 | 1.3673 | 0.1412 | 0.1404 | 0.5307 | 0.1412 | 0.4260 |
| 1.033 | 3.0 | 99 | 0.9817 | 0.5463 | 0.5675 | 0.6190 | 0.5463 | 0.5766 |
| 0.9143 | 4.0 | 132 | 0.9104 | 0.5804 | 0.5876 | 0.6191 | 0.5804 | 0.5774 |
| 0.8368 | 5.0 | 165 | 0.8826 | 0.6296 | 0.6329 | 0.6712 | 0.6296 | 0.6500 |
| 0.7829 | 6.0 | 198 | 0.7040 | 0.6939 | 0.6594 | 0.7159 | 0.6939 | 0.6571 |
| 0.7056 | 7.0 | 231 | 0.6170 | 0.7859 | 0.7851 | 0.7890 | 0.7859 | 0.7280 |
| 0.6557 | 8.0 | 264 | 0.6008 | 0.7882 | 0.7983 | 0.8202 | 0.7882 | 0.7753 |
| 0.5582 | 9.0 | 297 | 0.5804 | 0.7911 | 0.8025 | 0.8314 | 0.7911 | 0.7998 |
| 0.4719 | 10.0 | 330 | 0.5979 | 0.7737 | 0.7951 | 0.8400 | 0.7737 | 0.7876 |
| 0.4114 | 11.0 | 363 | 0.3667 | 0.8611 | 0.8680 | 0.8892 | 0.8611 | 0.8331 |
| 0.3405 | 12.0 | 396 | 0.3542 | 0.8692 | 0.8756 | 0.8903 | 0.8692 | 0.8530 |
| 0.2789 | 13.0 | 429 | 0.5196 | 0.8027 | 0.8138 | 0.8585 | 0.8027 | 0.8586 |
| 0.2626 | 14.0 | 462 | 0.2900 | 0.9034 | 0.9068 | 0.9140 | 0.9034 | 0.8909 |
| 0.2267 | 15.0 | 495 | 0.3343 | 0.8686 | 0.8768 | 0.8966 | 0.8686 | 0.8881 |
| 0.2126 | 16.0 | 528 | 0.2933 | 0.8929 | 0.8986 | 0.9117 | 0.8929 | 0.8908 |
| 0.1987 | 17.0 | 561 | 0.2587 | 0.9190 | 0.9206 | 0.9236 | 0.9190 | 0.8970 |
| 0.1617 | 18.0 | 594 | 0.2382 | 0.9190 | 0.9215 | 0.9269 | 0.9190 | 0.9127 |
| 0.1433 | 19.0 | 627 | 0.2195 | 0.9248 | 0.9265 | 0.9305 | 0.9248 | 0.9068 |
| 0.1294 | 20.0 | 660 | 0.2332 | 0.9242 | 0.9261 | 0.9300 | 0.9242 | 0.9151 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
