quynh_deberta-v3-Base-finetuned-AI_req_2

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: 0.0324
• Train Accuracy: 0.9959
• Validation Loss: 0.9053
• Validation Accuracy: 0.8286
• Epoch: 14

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
0.8413	0.6593	0.7133	0.7143	0
0.6659	0.75	0.5795	0.8000	1
0.5713	0.7692	0.5171	0.8476	2
0.4814	0.7967	0.4655	0.8381	3
0.4366	0.8118	0.4368	0.8476	4
0.3888	0.8228	0.4844	0.8190	5
0.3282	0.8571	0.5208	0.8286	6
0.2678	0.8723	0.5297	0.8381	7
0.2422	0.8970	0.6020	0.8190	8
0.2069	0.9272	0.6953	0.7429	9
0.1441	0.9519	0.6943	0.7524	10
0.1426	0.9492	0.6897	0.8190	11
0.0947	0.9725	0.9910	0.8000	12
0.0536	0.9835	0.9079	0.8095	13
0.0324	0.9959	0.9053	0.8286	14

Framework versions

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