<!-- 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. -->
masked-10-pretraining-20-epoch
This model is a fine-tuned version of koobear/cam16-no-train-mask-final-50-epochs on the image_folder dataset. It achieves the following results on the evaluation set:
- Loss: 1.3976
- Accuracy: 0.8571
- F1: 0.8889
- Precision: 0.9286
- Recall: 0.8571
- Balanced Acc: 0.6
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 |
|---|---|---|---|---|---|---|---|---|
| 1.645 | 1.0 | 1 | 1.6272 | 0.1429 | 0.1905 | 0.2857 | 0.1429 | 0.0833 |
| 1.557 | 2.0 | 2 | 1.6087 | 0.2143 | 0.2637 | 0.3429 | 0.2143 | 0.125 |
| 1.4815 | 3.0 | 3 | 1.5879 | 0.2857 | 0.4048 | 0.7857 | 0.2857 | 0.1917 |
| 1.4203 | 4.0 | 4 | 1.5646 | 0.4286 | 0.5272 | 0.8333 | 0.4286 | 0.2750 |
| 1.3708 | 5.0 | 5 | 1.5429 | 0.5 | 0.5762 | 0.8469 | 0.5 | 0.3167 |
| 1.3266 | 6.0 | 6 | 1.5260 | 0.5714 | 0.6612 | 0.8469 | 0.5714 | 0.3833 |
| 1.2864 | 7.0 | 7 | 1.5133 | 0.5714 | 0.6612 | 0.8469 | 0.5714 | 0.3833 |
| 1.2511 | 8.0 | 8 | 1.5016 | 0.6429 | 0.7250 | 0.8469 | 0.6429 | 0.45 |
| 1.2195 | 9.0 | 9 | 1.4893 | 0.6429 | 0.7250 | 0.8469 | 0.6429 | 0.45 |
| 1.1908 | 10.0 | 10 | 1.4755 | 0.6429 | 0.7250 | 0.8469 | 0.6429 | 0.45 |
| 1.1644 | 11.0 | 11 | 1.4614 | 0.7143 | 0.7746 | 0.8469 | 0.7143 | 0.5167 |
| 1.1407 | 12.0 | 12 | 1.4481 | 0.7143 | 0.8073 | 0.9286 | 0.7143 | 0.5167 |
| 1.1199 | 13.0 | 13 | 1.4363 | 0.7143 | 0.8073 | 0.9286 | 0.7143 | 0.5167 |
| 1.1017 | 14.0 | 14 | 1.4266 | 0.8571 | 0.8889 | 0.9286 | 0.8571 | 0.6 |
| 1.0858 | 15.0 | 15 | 1.4186 | 0.8571 | 0.8889 | 0.9286 | 0.8571 | 0.6 |
| 1.0719 | 16.0 | 16 | 1.4119 | 0.8571 | 0.8889 | 0.9286 | 0.8571 | 0.6 |
| 1.0602 | 17.0 | 17 | 1.4064 | 0.8571 | 0.8889 | 0.9286 | 0.8571 | 0.6 |
| 1.0508 | 18.0 | 18 | 1.4022 | 0.8571 | 0.8889 | 0.9286 | 0.8571 | 0.6 |
| 1.0437 | 19.0 | 19 | 1.3992 | 0.8571 | 0.8889 | 0.9286 | 0.8571 | 0.6 |
| 1.0388 | 20.0 | 20 | 1.3976 | 0.8571 | 0.8889 | 0.9286 | 0.8571 | 0.6 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
