metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: dog-emotion-classifier
results: []
dog-emotion-classifier
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7653
- Accuracy: 0.8612
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.5 | 100 | 0.5477 | 0.795 |
| No log | 1.0 | 200 | 0.4834 | 0.83 |
| No log | 1.5 | 300 | 0.4944 | 0.8263 |
| No log | 2.0 | 400 | 0.5020 | 0.8187 |
| 0.4298 | 2.5 | 500 | 0.5745 | 0.83 |
| 0.4298 | 3.0 | 600 | 0.6207 | 0.8187 |
| 0.4298 | 3.5 | 700 | 0.5745 | 0.85 |
| 0.4298 | 4.0 | 800 | 0.7309 | 0.84 |
| 0.4298 | 4.5 | 900 | 0.7073 | 0.835 |
| 0.0585 | 5.0 | 1000 | 0.6339 | 0.8538 |
| 0.0585 | 5.5 | 1100 | 0.7294 | 0.8413 |
| 0.0585 | 6.0 | 1200 | 0.7083 | 0.8562 |
| 0.0585 | 6.5 | 1300 | 0.7272 | 0.8588 |
| 0.0585 | 7.0 | 1400 | 0.7358 | 0.8588 |
| 0.0042 | 7.5 | 1500 | 0.7447 | 0.86 |
| 0.0042 | 8.0 | 1600 | 0.7517 | 0.86 |
| 0.0042 | 8.5 | 1700 | 0.7581 | 0.8612 |
| 0.0042 | 9.0 | 1800 | 0.7620 | 0.8612 |
| 0.0042 | 9.5 | 1900 | 0.7645 | 0.8612 |
| 0.0012 | 10.0 | 2000 | 0.7653 | 0.8612 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1