|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: dental_classification_model_010424_2 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# dental_classification_model_010424_2 |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5837 |
|
- Accuracy: 0.8142 |
|
|
|
## 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: 50 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.9273 | 0.99 | 41 | 1.9166 | 0.2281 | |
|
| 1.8096 | 2.0 | 83 | 1.7653 | 0.3716 | |
|
| 1.6373 | 2.99 | 124 | 1.5785 | 0.4486 | |
|
| 1.4996 | 4.0 | 166 | 1.4273 | 0.5060 | |
|
| 1.3441 | 4.99 | 207 | 1.2730 | 0.5891 | |
|
| 1.1677 | 6.0 | 249 | 1.1615 | 0.6254 | |
|
| 0.9809 | 6.99 | 290 | 1.1033 | 0.6254 | |
|
| 0.8292 | 8.0 | 332 | 0.9928 | 0.6873 | |
|
| 0.8035 | 8.99 | 373 | 0.8762 | 0.7402 | |
|
| 0.6982 | 10.0 | 415 | 0.8117 | 0.7341 | |
|
| 0.6992 | 10.99 | 456 | 0.7667 | 0.7749 | |
|
| 0.5601 | 12.0 | 498 | 0.7563 | 0.7568 | |
|
| 0.5358 | 12.99 | 539 | 0.7178 | 0.7749 | |
|
| 0.569 | 14.0 | 581 | 0.7356 | 0.7553 | |
|
| 0.4503 | 14.99 | 622 | 0.6535 | 0.8051 | |
|
| 0.4509 | 16.0 | 664 | 0.6755 | 0.7855 | |
|
| 0.5127 | 16.99 | 705 | 0.6431 | 0.7976 | |
|
| 0.425 | 18.0 | 747 | 0.6362 | 0.8006 | |
|
| 0.3968 | 18.99 | 788 | 0.5821 | 0.8157 | |
|
| 0.398 | 20.0 | 830 | 0.6355 | 0.7900 | |
|
| 0.4468 | 20.99 | 871 | 0.5103 | 0.8323 | |
|
| 0.429 | 22.0 | 913 | 0.6056 | 0.8051 | |
|
| 0.3332 | 22.99 | 954 | 0.5681 | 0.8233 | |
|
| 0.3431 | 24.0 | 996 | 0.5186 | 0.8263 | |
|
| 0.3052 | 24.99 | 1037 | 0.5993 | 0.8036 | |
|
| 0.3495 | 26.0 | 1079 | 0.5837 | 0.8142 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
