facial_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: 1.2427
• Accuracy: 0.5563

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	40	1.8904	0.3125
No log	2.0	80	1.6093	0.4437
No log	3.0	120	1.4846	0.4813
No log	4.0	160	1.4352	0.5437
No log	5.0	200	1.3533	0.5
No log	6.0	240	1.3076	0.5188
No log	7.0	280	1.2484	0.55
No log	8.0	320	1.2073	0.5875
No log	9.0	360	1.2465	0.5687
No log	10.0	400	1.2770	0.5188

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.2