vit_epochs5_batch32_lr5e-05_size224_tiles2_seed1_q3_dropout_local
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the Dogs_vs_Cats dataset. It achieves the following results on the evaluation set:
- Loss: 0.0505
- Accuracy: 0.9899
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.0038 | 1.0 | 469 | 0.0833 | 0.9781 |
0.0011 | 2.0 | 938 | 0.0683 | 0.9856 |
0.0006 | 3.0 | 1407 | 0.0505 | 0.9899 |
0.0005 | 4.0 | 1876 | 0.0540 | 0.9899 |
0.0005 | 5.0 | 2345 | 0.0551 | 0.9899 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.2.2
- Datasets 2.18.0
- Tokenizers 0.19.1
- Downloads last month
- 1