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: 1.1901
• Accuracy: 0.5687

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	1.9937	0.225
No log	2.0	40	1.7466	0.4188
No log	3.0	60	1.5370	0.5375
No log	4.0	80	1.4797	0.5125
No log	5.0	100	1.3531	0.55
No log	6.0	120	1.3115	0.5687
No log	7.0	140	1.2982	0.5375
No log	8.0	160	1.2543	0.5437
No log	9.0	180	1.2666	0.525
No log	10.0	200	1.2427	0.5312
No log	11.0	220	1.2100	0.5687
No log	12.0	240	1.2494	0.5375
No log	13.0	260	1.2266	0.5625
No log	14.0	280	1.2360	0.5437
No log	15.0	300	1.1901	0.5687

Framework versions

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