<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
beit-base-patch16-224-pt22k-ft22k-finetuned-FER2013-5e-05
This model is a fine-tuned version of microsoft/beit-base-patch16-224-pt22k-ft22k on the image_folder dataset. It achieves the following results on the evaluation set:
- Loss: 0.8610
- Accuracy: 0.6833
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1691 | 1.0 | 224 | 0.9764 | 0.6310 |
| 1.0304 | 2.0 | 448 | 0.8965 | 0.6666 |
| 0.9844 | 3.0 | 672 | 0.8610 | 0.6833 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1
