metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: emotion_model_1
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: 0.44375
emotion_model_1
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: 1.5356
- Accuracy: 0.4437
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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 |
|---|---|---|---|---|
| 2.0785 | 1.0 | 10 | 2.0617 | 0.125 |
| 2.0054 | 2.0 | 20 | 1.9826 | 0.275 |
| 1.8694 | 3.0 | 30 | 1.8516 | 0.325 |
| 1.7212 | 4.0 | 40 | 1.7082 | 0.3812 |
| 1.6101 | 5.0 | 50 | 1.6297 | 0.4375 |
| 1.5409 | 6.0 | 60 | 1.5981 | 0.4188 |
| 1.4801 | 7.0 | 70 | 1.5526 | 0.4437 |
| 1.433 | 8.0 | 80 | 1.5574 | 0.4813 |
| 1.4056 | 9.0 | 90 | 1.5094 | 0.5062 |
| 1.3797 | 10.0 | 100 | 1.5232 | 0.4688 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1