Boya3_3Class_RMSprop_1e5_20Epoch_Beit-large-224_fold5
This model is a fine-tuned version of microsoft/beit-large-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.5966
- Accuracy: 0.8419
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- 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 |
---|---|---|---|---|
0.3221 | 1.0 | 632 | 0.4174 | 0.8201 |
0.3949 | 2.0 | 1264 | 0.4102 | 0.8236 |
0.2149 | 3.0 | 1896 | 0.5617 | 0.8403 |
0.1037 | 4.0 | 2528 | 0.7488 | 0.8411 |
0.0902 | 5.0 | 3160 | 0.9759 | 0.8339 |
0.0457 | 6.0 | 3792 | 1.2673 | 0.8411 |
0.0051 | 7.0 | 4424 | 1.4733 | 0.8403 |
0.0063 | 8.0 | 5056 | 1.5705 | 0.8272 |
0.0 | 9.0 | 5688 | 1.5778 | 0.8446 |
0.0 | 10.0 | 6320 | 1.5966 | 0.8419 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.2
- Downloads last month
- 0