<!-- 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
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: 0.4492
- Accuracy: 0.9014
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 |
|---|---|---|---|---|
| 1.2401 | 1.0 | 37 | 1.0427 | 0.6582 |
| 0.669 | 2.0 | 74 | 0.5486 | 0.8418 |
| 0.4662 | 3.0 | 111 | 0.4012 | 0.8690 |
| 0.3211 | 4.0 | 148 | 0.5338 | 0.7942 |
| 0.2136 | 5.0 | 185 | 0.3189 | 0.8861 |
| 0.1626 | 6.0 | 222 | 0.4406 | 0.8435 |
| 0.1042 | 7.0 | 259 | 0.3812 | 0.8741 |
| 0.0688 | 8.0 | 296 | 0.3501 | 0.8946 |
| 0.0425 | 9.0 | 333 | 0.3845 | 0.8912 |
| 0.0586 | 10.0 | 370 | 0.3640 | 0.8980 |
| 0.0276 | 11.0 | 407 | 0.3708 | 0.9031 |
| 0.0342 | 12.0 | 444 | 0.3862 | 0.9082 |
| 0.0251 | 13.0 | 481 | 0.5206 | 0.8776 |
| 0.0209 | 14.0 | 518 | 0.4078 | 0.8929 |
| 0.0173 | 15.0 | 555 | 0.4168 | 0.8895 |
| 0.0159 | 16.0 | 592 | 0.4108 | 0.8997 |
| 0.0151 | 17.0 | 629 | 0.4176 | 0.9014 |
| 0.014 | 18.0 | 666 | 0.4228 | 0.9014 |
| 0.0131 | 19.0 | 703 | 0.4266 | 0.9014 |
| 0.0125 | 20.0 | 740 | 0.4301 | 0.9014 |
| 0.012 | 21.0 | 777 | 0.4339 | 0.9014 |
| 0.0115 | 22.0 | 814 | 0.4372 | 0.9014 |
| 0.0111 | 23.0 | 851 | 0.4401 | 0.9014 |
| 0.0107 | 24.0 | 888 | 0.4424 | 0.9014 |
| 0.0101 | 25.0 | 925 | 0.4444 | 0.9014 |
| 0.01 | 26.0 | 962 | 0.4461 | 0.9014 |
| 0.01 | 27.0 | 999 | 0.4475 | 0.9014 |
| 0.0099 | 28.0 | 1036 | 0.4485 | 0.9014 |
| 0.0097 | 29.0 | 1073 | 0.4490 | 0.9014 |
| 0.0097 | 30.0 | 1110 | 0.4492 | 0.9014 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
