metadata
license: apache-2.0
base_model: pradanaadn/vit-emotional-classifier
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-emotional-classifier
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: 0.65625
vit-emotional-classifier
This model is a fine-tuned version of pradanaadn/vit-emotional-classifier on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.1495
- Accuracy: 0.6562
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4801 | 0.5 | 20 | 1.2238 | 0.5875 |
| 0.4681 | 1.0 | 40 | 1.2062 | 0.6188 |
| 0.3414 | 1.5 | 60 | 1.1674 | 0.6 |
| 0.2972 | 2.0 | 80 | 1.1362 | 0.6125 |
| 0.2503 | 2.5 | 100 | 1.1508 | 0.6 |
| 0.1872 | 3.0 | 120 | 1.1495 | 0.6562 |
| 0.1929 | 3.5 | 140 | 1.1998 | 0.5875 |
| 0.1883 | 4.0 | 160 | 1.2023 | 0.5938 |
| 0.1729 | 4.5 | 180 | 1.2130 | 0.6 |
| 0.2007 | 5.0 | 200 | 1.2021 | 0.5813 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1