beit-base-patch16-224-pt22k-ft22k-finetuned-FER2013-7e-05-finetuned-FER2013-7e-05
This model is a fine-tuned version of lixiqi/beit-base-patch16-224-pt22k-ft22k-finetuned-FER2013-7e-05 on the image_folder dataset. It achieves the following results on the evaluation set:
- Loss: 1.5659
- Accuracy: 0.5260
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: 7e-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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6537 | 0.97 | 14 | 1.4980 | 0.4683 |
| 1.4325 | 1.97 | 28 | 1.4777 | 0.5040 |
| 1.1532 | 2.97 | 42 | 1.5007 | 0.4960 |
| 1.0428 | 3.97 | 56 | 1.5480 | 0.4890 |
| 0.8716 | 4.97 | 70 | 1.5659 | 0.5260 |
| 0.892 | 5.97 | 84 | 1.6132 | 0.4960 |
| 0.8109 | 6.97 | 98 | 1.5895 | 0.5167 |
| 0.7413 | 7.97 | 112 | 1.6271 | 0.5202 |
| 0.765 | 8.97 | 126 | 1.5991 | 0.5040 |
| 0.6575 | 9.97 | 140 | 1.6041 | 0.4960 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1
- Downloads last month
- 14
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.