quynh_deberta-v3-Base-finetuned-AI_req_1

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: 0.0260
• Train Accuracy: 0.9918
• Validation Loss: 1.1900
• Validation Accuracy: 0.7810
• 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
0.8121	0.6690	0.6778	0.7524	0
0.5487	0.8049	0.5841	0.7810	1
0.4181	0.8420	0.4797	0.8000	2
0.3674	0.8462	0.5794	0.7905	3
0.3232	0.8654	0.5766	0.7810	4
0.2762	0.8887	0.6246	0.8000	5
0.2165	0.9148	0.5751	0.7429	6
0.1623	0.9464	0.6580	0.8000	7
0.1645	0.9464	0.7932	0.7810	8
0.1231	0.9574	1.0112	0.8095	9
0.1089	0.9574	0.8745	0.7619	10
0.0587	0.9794	0.9496	0.7905	11
0.0260	0.9918	1.1900	0.7810	12

Framework versions

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