Modelpublic

ratish/DBERT_Fault_LR_v2.1

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

0likes8downloads

Model Card

ratish/DBERTFaultLR_v2.1

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

—Train Loss: 0.1501
—Validation Loss: 0.6305
—Train Accuracy: 0.7179
—Epoch: 29

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', 'weightdecay': None, 'clipnorm': None, 'globalclipnorm': None, 'clipvalue': None, 'useema': False, 'emamomentum': 0.99, 'emaoverwritefrequency': None, 'jitcompile': True, 'islegacyoptimizer': False, 'learningrate': {'classname': 'PolynomialDecay', 'config': {'initiallearningrate': 2e-06, 'decaysteps': 9120, 'endlearningrate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta1': 0.9, 'beta2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
—training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
0.6963	0.6916	0.5128	0
0.6774	0.6929	0.5128	1
0.6631	0.7000	0.5128	2
0.6580	0.7070	0.5128	3
0.6409	0.7104	0.5128	4
0.6296	0.7015	0.5128	5
0.6115	0.6866	0.5128	6
0.5940	0.6573	0.5897	7
0.5616	0.6263	0.5897	8
0.5230	0.5886	0.6667	9
0.4890	0.5608	0.7179	10
0.4523	0.5386	0.7436	11
0.4307	0.5424	0.7179	12
0.4013	0.5261	0.7179	13
0.3893	0.4976	0.7436	14
0.3634	0.5459	0.6923	15
0.3337	0.4893	0.7436	16
0.3243	0.5490	0.7179	17
0.3083	0.5091	0.7179	18
0.2815	0.5457	0.7179	19
0.2654	0.5692	0.7179	20
0.2535	0.4808	0.7436	21
0.2504	0.5912	0.6923	22
0.2132	0.6228	0.6923	23
0.1962	0.5834	0.7179	24
0.2136	0.5261	0.7692	25
0.1895	0.6210	0.7179	26
0.1722	0.7140	0.7179	27
0.1580	0.6532	0.6923	28
0.1501	0.6305	0.7179	29

Framework versions

—Transformers 4.28.1
—TensorFlow 2.12.0
—Datasets 2.12.0
—Tokenizers 0.13.3