Akhil123/emotions_classifier

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

• Train Loss: 2.0827
• Validation Loss: 2.0793
• Train Accuracy: 0.1437
• Epoch: 19

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:

• optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0003, 'decay_steps': 12800, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
1.9720	1.6874	0.225	0
2.0874	2.0802	0.125	1
2.0744	2.0407	0.2313	2
2.0540	2.0760	0.1688	3
2.1039	2.0796	0.1125	4
2.0813	2.0794	0.1187	5
2.0802	2.0797	0.1187	6
2.0793	2.0790	0.125	7
2.0657	2.0128	0.2	8
2.0724	2.0920	0.125	9
2.0896	2.0744	0.1187	10
2.0844	2.0824	0.1187	11
2.0819	2.0755	0.125	12
2.0614	2.0392	0.1562	13
2.0676	2.0812	0.1187	14
2.0810	2.0792	0.1187	15
2.0826	2.0813	0.1187	16
2.0788	2.0770	0.15	17
2.0797	2.0733	0.125	18
2.0827	2.0793	0.1437	19

Framework versions

• Transformers 4.31.0
• TensorFlow 2.12.0
• Datasets 2.14.4
• Tokenizers 0.13.3