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
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: 0.4125
emotion_model
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: 1.6373
- Accuracy: 0.4125
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: 1e-07
- train_batch_size: 10
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.0746 | 1.0 | 64 | 1.6373 | 0.4125 |
1.0732 | 2.0 | 128 | 1.6375 | 0.4125 |
1.0719 | 3.0 | 192 | 1.6372 | 0.4062 |
1.0708 | 4.0 | 256 | 1.6372 | 0.4125 |
1.0698 | 5.0 | 320 | 1.6370 | 0.4062 |
1.0689 | 6.0 | 384 | 1.6368 | 0.4062 |
1.068 | 7.0 | 448 | 1.6367 | 0.4062 |
1.0673 | 8.0 | 512 | 1.6366 | 0.4062 |
1.0666 | 9.0 | 576 | 1.6366 | 0.4062 |
1.066 | 10.0 | 640 | 1.6366 | 0.4062 |
1.0656 | 11.0 | 704 | 1.6365 | 0.4062 |
1.0652 | 12.0 | 768 | 1.6364 | 0.4062 |
1.0649 | 13.0 | 832 | 1.6364 | 0.4062 |
1.0647 | 14.0 | 896 | 1.6364 | 0.4062 |
1.0646 | 15.0 | 960 | 1.6364 | 0.4062 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2