<!-- 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. -->
378A1_results_2
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5007
- Accuracy: 0.8861
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2051 | 1.0 | 37 | 1.0438 | 0.6429 |
| 0.6643 | 2.0 | 74 | 0.6103 | 0.7925 |
| 0.4615 | 3.0 | 111 | 0.4720 | 0.8435 |
| 0.3136 | 4.0 | 148 | 0.3668 | 0.8776 |
| 0.278 | 5.0 | 185 | 0.3650 | 0.8622 |
| 0.1875 | 6.0 | 222 | 0.3705 | 0.8690 |
| 0.1215 | 7.0 | 259 | 0.4093 | 0.8741 |
| 0.0885 | 8.0 | 296 | 0.3428 | 0.9014 |
| 0.0497 | 9.0 | 333 | 0.3854 | 0.8759 |
| 0.0348 | 10.0 | 370 | 0.4291 | 0.8707 |
| 0.0301 | 11.0 | 407 | 0.4464 | 0.8895 |
| 0.0246 | 12.0 | 444 | 0.4208 | 0.8929 |
| 0.0218 | 13.0 | 481 | 0.4256 | 0.8912 |
| 0.0198 | 14.0 | 518 | 0.4300 | 0.8878 |
| 0.0179 | 15.0 | 555 | 0.4403 | 0.8861 |
| 0.0165 | 16.0 | 592 | 0.4481 | 0.8861 |
| 0.0155 | 17.0 | 629 | 0.4554 | 0.8878 |
| 0.0146 | 18.0 | 666 | 0.4632 | 0.8878 |
| 0.0137 | 19.0 | 703 | 0.4691 | 0.8844 |
| 0.0129 | 20.0 | 740 | 0.4747 | 0.8861 |
| 0.0125 | 21.0 | 777 | 0.4792 | 0.8844 |
| 0.0119 | 22.0 | 814 | 0.4840 | 0.8844 |
| 0.0113 | 23.0 | 851 | 0.4875 | 0.8861 |
| 0.0111 | 24.0 | 888 | 0.4924 | 0.8844 |
| 0.0108 | 25.0 | 925 | 0.4947 | 0.8844 |
| 0.0105 | 26.0 | 962 | 0.4966 | 0.8844 |
| 0.0104 | 27.0 | 999 | 0.4988 | 0.8861 |
| 0.0102 | 28.0 | 1036 | 0.4997 | 0.8861 |
| 0.0101 | 29.0 | 1073 | 0.5005 | 0.8861 |
| 0.01 | 30.0 | 1110 | 0.5007 | 0.8861 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
