emotion_recognition

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: 1.1376
• Accuracy: 0.6062

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
• 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
No log	1.0	20	1.3456	0.4813
No log	2.0	40	1.3147	0.5188
No log	3.0	60	1.2345	0.5563
No log	4.0	80	1.2281	0.5625
No log	5.0	100	1.1851	0.5687
No log	6.0	120	1.1911	0.5563
No log	7.0	140	1.1834	0.5813
No log	8.0	160	1.1682	0.5875
No log	9.0	180	1.2359	0.55
No log	10.0	200	1.1850	0.5563
No log	11.0	220	1.1877	0.5687
No log	12.0	240	1.1546	0.5687
No log	13.0	260	1.1694	0.5813
No log	14.0	280	1.2401	0.5875
No log	15.0	300	1.1899	0.575

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1