svenbl80/deberta-v3-Base-finetuned-chatdoc-V5

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:

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 750, '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

Train Loss	Validation Loss	Train Accuracy	Epoch
1.0674	0.9894	0.4747	0
0.8423	0.7429	0.7677	1
0.6235	0.5464	0.8485	2
0.5161	0.5676	0.7980	3
0.3811	0.4362	0.8384	4
0.3285	0.4301	0.8384	5
0.2335	0.3137	0.9091	6
0.1674	0.3168	0.8990	7
0.1620	0.3945	0.8788	8
0.1406	0.3096	0.9192	9
0.1153	0.3296	0.8788	10
0.1238	0.3698	0.9091	11
0.0937	0.4387	0.8586	12
0.0703	0.4215	0.8485	13
0.0678	0.3623	0.9192	14
0.0741	0.3697	0.9192	15
0.0308	0.3844	0.9091	16
0.0378	0.3889	0.8990	17
0.0455	0.3695	0.9293	18
0.0347	0.3944	0.8990	19
0.0256	0.4041	0.8889	20
0.0301	0.4120	0.8990	21
0.0429	0.4235	0.8990	22
0.0294	0.4227	0.8889	23
0.0240	0.4275	0.8889	24
0.0206	0.4328	0.8889	25
0.0245	0.4150	0.8990	26
0.0129	0.4065	0.9293	27
0.0149	0.4068	0.9293	28