metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: 21BAI1229
results: []
21BAI1229
This model is a fine-tuned version of google/vit-base-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4078
- Accuracy: 0.8734
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.6034 | 0.9873 | 39 | 2.0544 | 0.4520 |
| 1.4429 | 2.0 | 79 | 0.7736 | 0.7849 |
| 0.8307 | 2.9873 | 118 | 0.5456 | 0.8413 |
| 0.6814 | 4.0 | 158 | 0.4881 | 0.8516 |
| 0.6199 | 4.9873 | 197 | 0.4614 | 0.8528 |
| 0.5578 | 6.0 | 237 | 0.4419 | 0.8615 |
| 0.5198 | 6.9873 | 276 | 0.4485 | 0.8603 |
| 0.4811 | 8.0 | 316 | 0.4355 | 0.8659 |
| 0.4568 | 8.9873 | 355 | 0.4182 | 0.8651 |
| 0.4268 | 10.0 | 395 | 0.4094 | 0.8702 |
| 0.4281 | 10.9873 | 434 | 0.4158 | 0.8706 |
| 0.4143 | 12.0 | 474 | 0.4078 | 0.8734 |
| 0.4009 | 12.9873 | 513 | 0.4066 | 0.8714 |
| 0.3642 | 14.0 | 553 | 0.4131 | 0.8683 |
| 0.3659 | 14.9873 | 592 | 0.4047 | 0.8726 |
| 0.3487 | 16.0 | 632 | 0.4054 | 0.8710 |
| 0.35 | 16.9873 | 671 | 0.4107 | 0.8722 |
| 0.3291 | 18.0 | 711 | 0.4099 | 0.8698 |
| 0.338 | 18.9873 | 750 | 0.4063 | 0.8718 |
| 0.3419 | 19.7468 | 780 | 0.4066 | 0.8702 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3