metadata
library_name: transformers
base_model: carlosleao/vit-Facial-Expression-Recognition
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-Facial-Expression-Recognition
results: []
vit-Facial-Expression-Recognition
This model is a fine-tuned version of carlosleao/vit-Facial-Expression-Recognition on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5831
- Accuracy: 0.4234
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.7711 | 2.0833 | 100 | 1.7038 | 0.3915 |
| 1.5964 | 4.1667 | 200 | 1.5836 | 0.3957 |
| 1.5002 | 6.25 | 300 | 1.5438 | 0.4113 |
| 1.3591 | 8.3333 | 400 | 1.5690 | 0.4016 |
| 1.1821 | 10.4167 | 500 | 1.5831 | 0.4234 |
| 0.9323 | 12.5 | 600 | 1.7256 | 0.3960 |
| 0.7237 | 14.5833 | 700 | 1.8623 | 0.3954 |
| 0.5376 | 16.6667 | 800 | 2.0238 | 0.3742 |
| 0.363 | 18.75 | 900 | 2.1839 | 0.3462 |
| 0.238 | 20.8333 | 1000 | 2.2616 | 0.3602 |
| 0.1686 | 22.9167 | 1100 | 2.3515 | 0.3758 |
| 0.0952 | 25.0 | 1200 | 2.4730 | 0.3836 |
| 0.0526 | 27.0833 | 1300 | 2.5531 | 0.3898 |
| 0.0399 | 29.1667 | 1400 | 2.5901 | 0.3778 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.0+cu124
- Datasets 3.0.2
- Tokenizers 0.20.1