my_awesome_mingliangqiangu_model
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1140
- Accuracy: 0.9981
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.7575 | 0.99 | 67 | 1.3989 | 0.9287 |
| 0.4806 | 2.0 | 135 | 0.4502 | 0.9935 |
| 0.2902 | 2.99 | 202 | 0.2922 | 0.9944 |
| 0.2073 | 4.0 | 270 | 0.2118 | 0.9981 |
| 0.1975 | 4.99 | 337 | 0.1831 | 0.9963 |
| 0.1514 | 6.0 | 405 | 0.1576 | 0.9935 |
| 0.1282 | 6.99 | 472 | 0.1290 | 1.0 |
| 0.1224 | 8.0 | 540 | 0.1317 | 0.9963 |
| 0.1147 | 8.99 | 607 | 0.1127 | 1.0 |
| 0.1129 | 9.93 | 670 | 0.1140 | 0.9981 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3