quynh_deberta-v3-Base-finetuned-AI_req_4

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: 0.0138
• Train Accuracy: 0.9959
• Validation Loss: 1.1850
• Validation Accuracy: 0.8000
• Epoch: 17

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
0.8537	0.6415	0.7848	0.6476	0
0.6839	0.7459	0.8610	0.6190	1
0.5477	0.7816	0.8801	0.7048	2
0.4614	0.8091	0.7547	0.7143	3
0.3993	0.8297	0.6578	0.7714	4
0.4027	0.8407	0.7150	0.7524	5
0.3852	0.8420	0.8414	0.7238	6
0.2948	0.8819	0.6340	0.8000	7
0.2254	0.9107	0.9173	0.7048	8
0.1818	0.9409	0.7314	0.7905	9
0.1022	0.9698	1.0474	0.6571	10
0.0873	0.9643	0.9123	0.7714	11
0.0529	0.9808	1.1258	0.8000	12
0.0766	0.9794	0.9509	0.7905	13
0.0305	0.9931	1.0909	0.7714	14
0.0221	0.9959	1.1400	0.7810	15
0.0163	0.9959	1.2631	0.7905	16
0.0138	0.9959	1.1850	0.8000	17

Framework versions

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