semihdervis/cat-emotion-classifier

vit-base-cat-emotions

You can try out the model live here, and check out the GitHub repository for more details.

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the custom dataset dataset. It achieves the following results on the evaluation set:

• Loss: 1.0160
• Accuracy: 0.6353

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: 0.0002
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3361	3.125	100	1.0125	0.6548
0.0723	6.25	200	0.9043	0.7381
0.0321	9.375	300	0.9268	0.7143

Framework versions

• Transformers 4.44.1
• Pytorch 2.2.2+cu118
• Datasets 2.20.0
• Tokenizers 0.19.1