results
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.3718
- Accuracy: 0.45
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: 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.8675 | 1.0 | 40 | 1.7931 | 0.3125 |
1.568 | 2.0 | 80 | 1.5873 | 0.3688 |
1.3605 | 3.0 | 120 | 1.5087 | 0.4375 |
1.0784 | 4.0 | 160 | 1.4299 | 0.45 |
0.8568 | 5.0 | 200 | 1.4141 | 0.475 |
0.649 | 6.0 | 240 | 1.4242 | 0.4562 |
0.4787 | 7.0 | 280 | 1.3718 | 0.45 |
0.359 | 8.0 | 320 | 1.3828 | 0.45 |
0.3032 | 9.0 | 360 | 1.3888 | 0.4688 |
0.2782 | 10.0 | 400 | 1.3995 | 0.4437 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0
- Downloads last month
- 34
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for shavirazh/my_first_emotion_classification_model
Base model
google/vit-base-patch16-224-in21k