quynh_deberta-v3-Base-finetuned-AI_req_5

This model is a fine-tuned version of microsoft/deberta-v3-Base on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0813
• Train Accuracy: 0.9739
• Validation Loss: 0.9358
• Validation Accuracy: 0.8190
• Epoch: 12

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': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2730, '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}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
0.8536	0.6181	0.7137	0.6952	0
0.6579	0.7349	0.5152	0.8190	1
0.5153	0.7830	0.4833	0.8571	2
0.4369	0.8022	0.5064	0.8286	3
0.3922	0.8255	0.6123	0.7905	4
0.3616	0.8352	0.4985	0.8381	5
0.3034	0.8640	0.5926	0.8000	6
0.3187	0.8654	0.5392	0.8286	7
0.2134	0.9080	0.5991	0.8095	8
0.2041	0.9148	0.8289	0.8190	9
0.1532	0.9464	0.7176	0.8381	10
0.1690	0.9313	0.8189	0.8190	11
0.0813	0.9739	0.9358	0.8190	12

Framework versions

• Transformers 4.28.0
• TensorFlow 2.9.1
• Datasets 2.16.1
• Tokenizers 0.13.3