<!-- 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-10-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: 1.0394
- Accuracy: 0.5341
- F1: 0.5594
- Precision: 0.6150
- Recall: 0.5341
- Balanced Acc: 0.5953
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 |
|---|---|---|---|---|---|---|---|---|
| 1.9691 | 1.0 | 7 | 1.7584 | 0.0602 | 0.0728 | 0.4161 | 0.0602 | 0.2178 |
| 1.56 | 2.0 | 14 | 1.8865 | 0.0897 | 0.0247 | 0.0939 | 0.0897 | 0.3678 |
| 1.33 | 3.0 | 21 | 1.3672 | 0.2963 | 0.2522 | 0.5156 | 0.2963 | 0.4141 |
| 1.2723 | 4.0 | 28 | 1.4817 | 0.2228 | 0.2416 | 0.4965 | 0.2228 | 0.4325 |
| 1.1859 | 5.0 | 35 | 1.1677 | 0.5718 | 0.5096 | 0.5195 | 0.5718 | 0.4399 |
| 1.1096 | 6.0 | 42 | 1.5286 | 0.1962 | 0.1350 | 0.5681 | 0.1962 | 0.4552 |
| 1.0883 | 7.0 | 49 | 1.1433 | 0.5023 | 0.4934 | 0.4923 | 0.5023 | 0.4510 |
| 1.0607 | 8.0 | 56 | 1.4241 | 0.1568 | 0.1094 | 0.5564 | 0.1568 | 0.4480 |
| 1.1037 | 9.0 | 63 | 1.1371 | 0.5145 | 0.5089 | 0.5204 | 0.5145 | 0.4713 |
| 1.0329 | 10.0 | 70 | 1.3295 | 0.2593 | 0.2175 | 0.5928 | 0.2593 | 0.4888 |
| 0.9997 | 11.0 | 77 | 1.1507 | 0.4797 | 0.5002 | 0.5376 | 0.4797 | 0.5066 |
| 0.9617 | 12.0 | 84 | 1.2754 | 0.3368 | 0.3414 | 0.5459 | 0.3368 | 0.4881 |
| 0.9426 | 13.0 | 91 | 1.1981 | 0.4028 | 0.4538 | 0.5986 | 0.4028 | 0.5212 |
| 0.8711 | 14.0 | 98 | 1.2266 | 0.3900 | 0.4039 | 0.6016 | 0.3900 | 0.5217 |
| 0.8657 | 15.0 | 105 | 1.1702 | 0.4323 | 0.4733 | 0.5906 | 0.4323 | 0.5490 |
| 0.8563 | 16.0 | 112 | 1.0296 | 0.5463 | 0.5644 | 0.5987 | 0.5463 | 0.5711 |
| 0.8169 | 17.0 | 119 | 1.1235 | 0.4635 | 0.4948 | 0.6174 | 0.4635 | 0.5841 |
| 0.8108 | 18.0 | 126 | 1.0102 | 0.5527 | 0.5731 | 0.6144 | 0.5527 | 0.5840 |
| 0.7864 | 19.0 | 133 | 1.1249 | 0.4797 | 0.5137 | 0.6134 | 0.4797 | 0.5878 |
| 0.7608 | 20.0 | 140 | 1.0394 | 0.5341 | 0.5594 | 0.6150 | 0.5341 | 0.5953 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
