vit-emotion-model
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: 1.1329
- Accuracy: 0.575
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.5767 | 1.0 | 80 | 1.3573 | 0.4875 |
| 0.8289 | 2.0 | 160 | 1.1968 | 0.4938 |
| 0.3138 | 3.0 | 240 | 1.0986 | 0.5687 |
| 0.0858 | 4.0 | 320 | 1.1277 | 0.5687 |
| 0.0471 | 5.0 | 400 | 1.1329 | 0.575 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Tokenizers 0.21.0
- Downloads last month
- 8
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for afidzulinn/vit-emotion-model
Base model
google/vit-base-patch16-224