metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- image_folder
metrics:
- accuracy
model-index:
- name: beit-base-patch16-224-pt22k-ft22k-finetuned-FER2013
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: image_folder
type: image_folder
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.6879136189481017
beit-base-patch16-224-pt22k-ft22k-finetuned-FER2013
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: 0.8504
- Accuracy: 0.6879
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: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.1617 | 1.0 | 202 | 1.0081 | 0.6270 |
1.0604 | 2.0 | 404 | 0.9516 | 0.6524 |
0.998 | 3.0 | 606 | 0.8857 | 0.6809 |
0.9971 | 4.0 | 808 | 0.8504 | 0.6879 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1