metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: emotion_classification
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: 0.525
emotion_classification
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: 1.4174
- Accuracy: 0.525
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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0777 | 1.0 | 10 | 2.0583 | 0.1812 |
| 2.0139 | 2.0 | 20 | 1.9850 | 0.2687 |
| 1.8654 | 3.0 | 30 | 1.8583 | 0.3063 |
| 1.7044 | 4.0 | 40 | 1.7314 | 0.3937 |
| 1.5957 | 5.0 | 50 | 1.6253 | 0.4125 |
| 1.5016 | 6.0 | 60 | 1.5818 | 0.3812 |
| 1.4279 | 7.0 | 70 | 1.5329 | 0.45 |
| 1.347 | 8.0 | 80 | 1.5491 | 0.425 |
| 1.3019 | 9.0 | 90 | 1.4662 | 0.5125 |
| 1.236 | 10.0 | 100 | 1.4375 | 0.5 |
| 1.1922 | 11.0 | 110 | 1.4149 | 0.5062 |
| 1.1551 | 12.0 | 120 | 1.4065 | 0.5125 |
| 1.1501 | 13.0 | 130 | 1.3861 | 0.5125 |
| 1.1258 | 14.0 | 140 | 1.3940 | 0.5312 |
| 1.1036 | 15.0 | 150 | 1.4022 | 0.5125 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1