<!-- 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-1-pretraining-20-epochss
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: 0.3779
- Accuracy: 1.0
- F1: 1.0
- Precision: 1.0
- Recall: 1.0
- Balanced Acc: 1.0
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: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|---|---|---|---|
| 0.65 | 1.0 | 1 | 0.6614 | 0.5 | 0.3333 | 0.25 | 0.5 | 0.5 |
| 0.5064 | 2.0 | 2 | 0.5984 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.4062 | 3.0 | 3 | 0.5350 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.3265 | 4.0 | 4 | 0.4852 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.2658 | 5.0 | 5 | 0.4530 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.2209 | 6.0 | 6 | 0.4314 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.1908 | 7.0 | 7 | 0.4156 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.1702 | 8.0 | 8 | 0.4056 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.1534 | 9.0 | 9 | 0.4005 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.1384 | 10.0 | 10 | 0.3986 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.1268 | 11.0 | 11 | 0.3983 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.118 | 12.0 | 12 | 0.3984 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.1112 | 13.0 | 13 | 0.3976 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.1057 | 14.0 | 14 | 0.3956 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.101 | 15.0 | 15 | 0.3924 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0971 | 16.0 | 16 | 0.3888 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0938 | 17.0 | 17 | 0.3850 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0912 | 18.0 | 18 | 0.3817 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0892 | 19.0 | 19 | 0.3792 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0878 | 20.0 | 20 | 0.3779 | 1.0 | 1.0 | 1.0 | 1.0 | 1.0 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0+cpu
- Datasets 2.1.0
- Tokenizers 0.13.3
