metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: pokemon_classification
results: []
pokemon_classification
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0586
- Accuracy: 0.9071
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 4.3925 | 1.0 | 350 | 4.0653 | 0.6705 |
| 3.2005 | 2.0 | 700 | 3.1602 | 0.8227 |
| 2.3615 | 3.0 | 1050 | 2.4281 | 0.8656 |
| 1.5369 | 4.0 | 1400 | 1.8786 | 0.8821 |
| 1.0741 | 5.0 | 1750 | 1.4818 | 0.9014 |
| 0.7094 | 6.0 | 2100 | 1.2335 | 0.9014 |
| 0.544 | 7.0 | 2450 | 1.0976 | 0.9042 |
| 0.4622 | 8.0 | 2800 | 1.0586 | 0.9071 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.0