CynthiaCR/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: 1.3846
• Validation Loss: 1.6122
• Train Accuracy: 0.2687
• 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
2.0363	2.0960	0.1	0
2.0822	2.1254	0.0813	1
1.9916	1.9392	0.2062	2
1.9223	1.8385	0.1688	3
1.8213	1.7294	0.2313	4
1.6940	1.6953	0.2625	5
1.7153	1.6009	0.3187	6
1.5788	1.6385	0.275	7
1.5359	1.5635	0.3438	8
1.4768	1.6180	0.325	9
1.4746	1.6063	0.3125	10
1.5163	1.5641	0.3625	11
1.4692	1.5722	0.3063	12
1.4468	1.7363	0.35	13
1.7116	1.7531	0.2687	14
1.5334	1.5908	0.2562	15
1.4988	1.5169	0.3312	16
1.4605	1.5041	0.2812	17
1.3545	1.4824	0.3187	18
1.3846	1.6122	0.2687	19

Framework versions

• Transformers 4.29.2
• TensorFlow 2.12.0
• Datasets 2.12.0
• Tokenizers 0.13.3