<!-- 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_STEM4
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: 0.0193
- 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 |
|---|---|---|---|---|
| 0.8061 | 0.57 | 1 | 0.8989 | 0.4783 |
| 0.6757 | 1.71 | 3 | 0.6933 | 0.5217 |
| 0.6655 | 2.86 | 5 | 0.6010 | 0.6957 |
| 0.5596 | 4.0 | 7 | 0.6537 | 0.6087 |
| 0.5836 | 4.57 | 8 | 0.5276 | 0.7609 |
| 0.5274 | 5.71 | 10 | 0.4952 | 0.6739 |
| 0.456 | 6.86 | 12 | 0.4371 | 0.7826 |
| 0.4057 | 8.0 | 14 | 0.3455 | 0.8696 |
| 0.368 | 8.57 | 15 | 0.3090 | 0.8913 |
| 0.3073 | 9.71 | 17 | 0.2462 | 0.9130 |
| 0.2393 | 10.86 | 19 | 0.1956 | 0.9565 |
| 0.183 | 12.0 | 21 | 0.1661 | 0.9348 |
| 0.231 | 12.57 | 22 | 0.1375 | 0.9348 |
| 0.1548 | 13.71 | 24 | 0.1097 | 0.9565 |
| 0.1838 | 14.86 | 26 | 0.0939 | 0.9565 |
| 0.1392 | 16.0 | 28 | 0.0768 | 0.9783 |
| 0.1728 | 16.57 | 29 | 0.0741 | 0.9783 |
| 0.1554 | 17.71 | 31 | 0.0724 | 0.9783 |
| 0.1449 | 18.86 | 33 | 0.0945 | 0.9783 |
| 0.1693 | 20.0 | 35 | 0.0474 | 0.9783 |
| 0.1273 | 20.57 | 36 | 0.0343 | 0.9783 |
| 0.1244 | 21.71 | 38 | 0.0420 | 0.9783 |
| 0.1005 | 22.86 | 40 | 0.0193 | 1.0 |
| 0.1245 | 24.0 | 42 | 0.0234 | 1.0 |
| 0.1498 | 24.57 | 43 | 0.0192 | 1.0 |
| 0.1259 | 25.71 | 45 | 0.0135 | 1.0 |
| 0.1406 | 26.86 | 47 | 0.0188 | 1.0 |
| 0.1231 | 28.0 | 49 | 0.0175 | 1.0 |
| 0.1206 | 28.57 | 50 | 0.0171 | 1.0 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 1.12.1
- Datasets 2.12.0
- Tokenizers 0.13.1
