|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: pogona-vitticeps-gender |
|
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. --> |
|
|
|
# pogona-vitticeps-gender |
|
|
|
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: 0.5663 |
|
- Accuracy: 0.7812 |
|
|
|
## 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: 4e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 64 |
|
- 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: 50 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 1.1028 | 1.0 | 2 | 1.1062 | 0.2812 | |
|
| 1.0972 | 2.0 | 4 | 1.1082 | 0.3125 | |
|
| 1.0793 | 3.0 | 6 | 1.0692 | 0.5312 | |
|
| 1.0529 | 4.0 | 8 | 1.0578 | 0.625 | |
|
| 1.0178 | 5.0 | 10 | 1.0288 | 0.625 | |
|
| 0.9809 | 6.0 | 12 | 0.9988 | 0.6562 | |
|
| 0.9422 | 7.0 | 14 | 0.9936 | 0.6562 | |
|
| 0.8692 | 8.0 | 16 | 0.9761 | 0.625 | |
|
| 0.8503 | 9.0 | 18 | 0.9326 | 0.5938 | |
|
| 0.8128 | 10.0 | 20 | 0.9236 | 0.6562 | |
|
| 0.777 | 11.0 | 22 | 0.8541 | 0.75 | |
|
| 0.7407 | 12.0 | 24 | 0.8744 | 0.6562 | |
|
| 0.692 | 13.0 | 26 | 0.8412 | 0.6875 | |
|
| 0.6779 | 14.0 | 28 | 0.8611 | 0.6562 | |
|
| 0.6261 | 15.0 | 30 | 0.8213 | 0.625 | |
|
| 0.609 | 16.0 | 32 | 0.7389 | 0.7188 | |
|
| 0.5905 | 17.0 | 34 | 0.7421 | 0.7188 | |
|
| 0.5337 | 18.0 | 36 | 0.7651 | 0.6875 | |
|
| 0.5091 | 19.0 | 38 | 0.7201 | 0.75 | |
|
| 0.5178 | 20.0 | 40 | 0.7424 | 0.7188 | |
|
| 0.4757 | 21.0 | 42 | 0.7573 | 0.6562 | |
|
| 0.4548 | 22.0 | 44 | 0.7531 | 0.6562 | |
|
| 0.4494 | 23.0 | 46 | 0.7185 | 0.7188 | |
|
| 0.4627 | 24.0 | 48 | 0.6587 | 0.7188 | |
|
| 0.423 | 25.0 | 50 | 0.6426 | 0.75 | |
|
| 0.403 | 26.0 | 52 | 0.6525 | 0.75 | |
|
| 0.3734 | 27.0 | 54 | 0.6733 | 0.75 | |
|
| 0.38 | 28.0 | 56 | 0.6736 | 0.75 | |
|
| 0.3702 | 29.0 | 58 | 0.7211 | 0.6875 | |
|
| 0.3563 | 30.0 | 60 | 0.7263 | 0.6562 | |
|
| 0.336 | 31.0 | 62 | 0.6676 | 0.6875 | |
|
| 0.3131 | 32.0 | 64 | 0.6923 | 0.6875 | |
|
| 0.3214 | 33.0 | 66 | 0.6137 | 0.75 | |
|
| 0.3271 | 34.0 | 68 | 0.6708 | 0.8125 | |
|
| 0.3253 | 35.0 | 70 | 0.5912 | 0.75 | |
|
| 0.283 | 36.0 | 72 | 0.6332 | 0.7188 | |
|
| 0.2874 | 37.0 | 74 | 0.6345 | 0.7188 | |
|
| 0.2818 | 38.0 | 76 | 0.7593 | 0.6875 | |
|
| 0.2774 | 39.0 | 78 | 0.6817 | 0.7188 | |
|
| 0.2482 | 40.0 | 80 | 0.6784 | 0.6875 | |
|
| 0.261 | 41.0 | 82 | 0.6631 | 0.7188 | |
|
| 0.2945 | 42.0 | 84 | 0.6438 | 0.75 | |
|
| 0.2734 | 43.0 | 86 | 0.7086 | 0.75 | |
|
| 0.2536 | 44.0 | 88 | 0.6380 | 0.7188 | |
|
| 0.2643 | 45.0 | 90 | 0.6723 | 0.6562 | |
|
| 0.2273 | 46.0 | 92 | 0.6775 | 0.7188 | |
|
| 0.235 | 47.0 | 94 | 0.6876 | 0.7188 | |
|
| 0.2642 | 48.0 | 96 | 0.6382 | 0.7188 | |
|
| 0.2467 | 49.0 | 98 | 0.6701 | 0.7188 | |
|
| 0.2382 | 50.0 | 100 | 0.5663 | 0.7812 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.3 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
|
|
