pretrained_result
This model is a fine-tuned version of motheecreator/vit-Facial-Expression-Recognition on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.6537
- Accuracy: 0.7843
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.6131 | 0.9904 | 90 | 0.6537 | 0.7843 |
0.5963 | 1.9904 | 180 | 0.6502 | 0.7824 |
0.5716 | 2.9904 | 270 | 0.6506 | 0.7783 |
0.5616 | 3.9904 | 360 | 0.6429 | 0.7821 |
0.5272 | 4.9904 | 450 | 0.6516 | 0.7772 |
0.5064 | 5.9904 | 540 | 0.6446 | 0.7764 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.6.0+cu126
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 39
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.