<!-- 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-1-pretrain-20-epochss
This model is a fine-tuned version of koobear/masked-1-pretraining-20-epochss on the image_folder dataset. It achieves the following results on the evaluation set:
- Loss: 1.4722
- Accuracy: 0.7812
- F1: 0.7809
- Precision: 0.8379
- Recall: 0.7812
- Balanced Acc: 0.7181
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 |
|---|---|---|---|---|---|---|---|---|
| 1.6438 | 1.0 | 1 | 1.6248 | 0.0498 | 0.0489 | 0.3965 | 0.0498 | 0.0915 |
| 1.6138 | 2.0 | 2 | 1.6060 | 0.1192 | 0.1293 | 0.6208 | 0.1192 | 0.1902 |
| 1.5899 | 3.0 | 3 | 1.5914 | 0.2141 | 0.2341 | 0.6395 | 0.2141 | 0.2859 |
| 1.5681 | 4.0 | 4 | 1.5778 | 0.3166 | 0.3422 | 0.6426 | 0.3166 | 0.3844 |
| 1.539 | 5.0 | 5 | 1.5657 | 0.3970 | 0.4186 | 0.6650 | 0.3970 | 0.4577 |
| 1.5344 | 6.0 | 6 | 1.5544 | 0.4780 | 0.4981 | 0.7126 | 0.4780 | 0.5397 |
| 1.526 | 7.0 | 7 | 1.5436 | 0.5289 | 0.5497 | 0.7341 | 0.5289 | 0.5701 |
| 1.4868 | 8.0 | 8 | 1.5329 | 0.5949 | 0.6131 | 0.7560 | 0.5949 | 0.6069 |
| 1.5297 | 9.0 | 9 | 1.5239 | 0.6389 | 0.6543 | 0.7703 | 0.6389 | 0.6319 |
| 1.4746 | 10.0 | 10 | 1.5157 | 0.6736 | 0.6869 | 0.7942 | 0.6736 | 0.6649 |
| 1.4595 | 11.0 | 11 | 1.5080 | 0.6979 | 0.7083 | 0.8063 | 0.6979 | 0.6754 |
| 1.4811 | 12.0 | 12 | 1.5015 | 0.7147 | 0.7226 | 0.8064 | 0.7147 | 0.6853 |
| 1.4692 | 13.0 | 13 | 1.4956 | 0.7367 | 0.7418 | 0.8159 | 0.7367 | 0.6947 |
| 1.4475 | 14.0 | 14 | 1.4901 | 0.7448 | 0.7498 | 0.8184 | 0.7448 | 0.6976 |
| 1.4885 | 15.0 | 15 | 1.4853 | 0.7541 | 0.7582 | 0.8252 | 0.7541 | 0.7058 |
| 1.4141 | 16.0 | 16 | 1.4810 | 0.7616 | 0.7653 | 0.8291 | 0.7616 | 0.7082 |
| 1.5434 | 17.0 | 17 | 1.4778 | 0.7685 | 0.7714 | 0.8349 | 0.7685 | 0.7124 |
| 1.4061 | 18.0 | 18 | 1.4751 | 0.7731 | 0.7747 | 0.8359 | 0.7731 | 0.7164 |
| 1.4251 | 19.0 | 19 | 1.4732 | 0.7784 | 0.7788 | 0.8375 | 0.7784 | 0.7187 |
| 1.434 | 20.0 | 20 | 1.4722 | 0.7812 | 0.7809 | 0.8379 | 0.7812 | 0.7181 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
