metadata
license: apache-2.0
base_model: microsoft/beit-base-patch16-224-pt22k-ft22k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: finetuned-FER2013
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.6788575409265064
finetuned-FER2013
This model is a fine-tuned version of microsoft/beit-base-patch16-224-pt22k-ft22k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.8812
- Accuracy: 0.6789
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-06
- 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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.5466 | 1.0 | 202 | 1.5022 | 0.4500 |
| 1.3372 | 2.0 | 404 | 1.1727 | 0.5632 |
| 1.2372 | 3.0 | 606 | 1.0636 | 0.6075 |
| 1.2096 | 4.0 | 808 | 1.0200 | 0.6116 |
| 1.145 | 5.0 | 1010 | 0.9769 | 0.6325 |
| 1.1589 | 6.0 | 1212 | 0.9515 | 0.6405 |
| 1.0752 | 7.0 | 1414 | 0.9395 | 0.6458 |
| 1.0524 | 8.0 | 1616 | 0.9331 | 0.6458 |
| 1.0829 | 9.0 | 1818 | 0.9173 | 0.6573 |
| 1.0219 | 10.0 | 2020 | 0.9114 | 0.6597 |
| 0.9986 | 11.0 | 2222 | 0.9034 | 0.6580 |
| 1.013 | 12.0 | 2424 | 0.9004 | 0.6656 |
| 1.0133 | 13.0 | 2626 | 0.8940 | 0.6628 |
| 1.0064 | 14.0 | 2828 | 0.8916 | 0.6649 |
| 0.9858 | 15.0 | 3030 | 0.8882 | 0.6733 |
| 0.9863 | 16.0 | 3232 | 0.8850 | 0.6740 |
| 1.0058 | 17.0 | 3434 | 0.8856 | 0.6747 |
| 0.9637 | 18.0 | 3636 | 0.8852 | 0.6722 |
| 0.9803 | 19.0 | 3838 | 0.8829 | 0.6754 |
| 0.9356 | 20.0 | 4040 | 0.8812 | 0.6789 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0