<!-- 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. -->
vit-base-patch16-224-Trial006-YEL_STEM1
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0334
- Accuracy: 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: 5e-05
- train_batch_size: 60
- eval_batch_size: 60
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 240
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.8184 | 0.89 | 2 | 0.6184 | 0.7143 |
0.7378 | 1.78 | 4 | 0.5789 | 0.7143 |
0.676 | 2.67 | 6 | 0.7147 | 0.4464 |
0.6727 | 4.0 | 9 | 0.5448 | 0.7321 |
0.5761 | 4.89 | 11 | 0.4879 | 0.7857 |
0.6253 | 5.78 | 13 | 0.6192 | 0.6964 |
0.5719 | 6.67 | 15 | 0.4303 | 0.7679 |
0.4861 | 8.0 | 18 | 0.4442 | 0.8393 |
0.4713 | 8.89 | 20 | 0.3913 | 0.8571 |
0.4802 | 9.78 | 22 | 0.2951 | 0.8393 |
0.4324 | 10.67 | 24 | 0.3657 | 0.8393 |
0.3898 | 12.0 | 27 | 0.2257 | 0.9107 |
0.3763 | 12.89 | 29 | 0.2231 | 0.9107 |
0.3513 | 13.78 | 31 | 0.2590 | 0.875 |
0.3358 | 14.67 | 33 | 0.1898 | 0.9286 |
0.3302 | 16.0 | 36 | 0.1274 | 0.9643 |
0.2961 | 16.89 | 38 | 0.1054 | 0.9821 |
0.2989 | 17.78 | 40 | 0.1052 | 0.9643 |
0.2177 | 18.67 | 42 | 0.1028 | 0.9821 |
0.2436 | 20.0 | 45 | 0.1266 | 0.9286 |
0.244 | 20.89 | 47 | 0.0766 | 0.9821 |
0.2429 | 21.78 | 49 | 0.0709 | 0.9821 |
0.2201 | 22.67 | 51 | 0.0592 | 0.9821 |
0.2337 | 24.0 | 54 | 0.0852 | 0.9643 |
0.2009 | 24.89 | 56 | 0.0334 | 1.0 |
0.1789 | 25.78 | 58 | 0.0295 | 1.0 |
0.1945 | 26.67 | 60 | 0.0391 | 1.0 |
0.21 | 28.0 | 63 | 0.0459 | 0.9821 |
0.1757 | 28.89 | 65 | 0.0214 | 1.0 |
0.1959 | 29.78 | 67 | 0.0216 | 1.0 |
0.1817 | 30.67 | 69 | 0.0209 | 1.0 |
0.1995 | 32.0 | 72 | 0.0209 | 1.0 |
0.1581 | 32.89 | 74 | 0.0283 | 1.0 |
0.2138 | 33.78 | 76 | 0.0206 | 1.0 |
0.2028 | 34.67 | 78 | 0.0142 | 1.0 |
0.1365 | 36.0 | 81 | 0.0196 | 1.0 |
0.1574 | 36.89 | 83 | 0.0418 | 0.9821 |
0.1716 | 37.78 | 85 | 0.0464 | 0.9821 |
0.1671 | 38.67 | 87 | 0.0215 | 1.0 |
0.1252 | 40.0 | 90 | 0.0105 | 1.0 |
0.1912 | 40.89 | 92 | 0.0103 | 1.0 |
0.1734 | 41.78 | 94 | 0.0116 | 1.0 |
0.1195 | 42.67 | 96 | 0.0138 | 1.0 |
0.2142 | 44.0 | 99 | 0.0149 | 1.0 |
0.1756 | 44.44 | 100 | 0.0149 | 1.0 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 1.12.1
- Datasets 2.12.0
- Tokenizers 0.13.1