beit-base-patch16-224-pt22k-finetuned-IDRiD
This model is a fine-tuned version of microsoft/beit-base-patch16-224-pt22k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1881
- Accuracy: 0.5714
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 3 | 1.5369 | 0.4762 |
| No log | 2.0 | 6 | 1.4999 | 0.3333 |
| No log | 3.0 | 9 | 1.3085 | 0.4524 |
| 1.6051 | 4.0 | 12 | 1.3072 | 0.4524 |
| 1.6051 | 5.0 | 15 | 1.2578 | 0.5238 |
| 1.6051 | 6.0 | 18 | 1.2376 | 0.5476 |
| 1.3665 | 7.0 | 21 | 1.2073 | 0.5714 |
| 1.3665 | 8.0 | 24 | 1.1972 | 0.5714 |
| 1.3665 | 9.0 | 27 | 1.1942 | 0.5714 |
| 1.3024 | 10.0 | 30 | 1.1881 | 0.5714 |
Framework versions
- Transformers 4.30.0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.13.3