metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224-in21k-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: 0.8683385579937304
vit-base-patch16-224-in21k-finetuned-FER2013
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.3321
- Accuracy: 0.8683
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.495 | 1.0 | 202 | 0.4660 | 0.7739 |
| 0.4632 | 2.0 | 404 | 0.3820 | 0.8286 |
| 0.4013 | 3.0 | 606 | 0.3562 | 0.8447 |
| 0.3883 | 4.0 | 808 | 0.3426 | 0.8516 |
| 0.3801 | 5.0 | 1010 | 0.3303 | 0.8561 |
| 0.3612 | 6.0 | 1212 | 0.3362 | 0.8558 |
| 0.3504 | 7.0 | 1414 | 0.3302 | 0.8652 |
| 0.3366 | 8.0 | 1616 | 0.3321 | 0.8683 |
| 0.3007 | 9.0 | 1818 | 0.3330 | 0.8666 |
| 0.3089 | 10.0 | 2020 | 0.3327 | 0.8656 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0