Modelpublic

nandysoham/Gregorian_calendar-theme-finetuned-overfinetuned

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face

0likes13downloads

Model Card

nandysoham/Gregorian_calendar-theme-finetuned-overfinetuned

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

—Train Loss: 0.1838
—Train End Logits Accuracy: 0.9500
—Train Start Logits Accuracy: 0.9688
—Validation Loss: 2.0017
—Validation End Logits Accuracy: 0.5238
—Validation Start Logits Accuracy: 0.4762
—Epoch: 8

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', 'learningrate': {'classname': 'PolynomialDecay', 'config': {'initiallearningrate': 2e-05, 'decaysteps': 100, 'endlearningrate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
—training_precision: float32

Training results

Train Loss	Train End Logits Accuracy	Train Start Logits Accuracy	Validation Loss	Validation End Logits Accuracy	Validation Start Logits Accuracy	Epoch
2.2861	0.3688	0.4062	1.6038	0.5952	0.5714	0
1.2774	0.5938	0.5938	1.4240	0.5952	0.5714	1
0.8752	0.7000	0.7375	1.4402	0.5952	0.5476	2
0.5245	0.8250	0.8438	1.5027	0.6429	0.5952	3
0.4132	0.8313	0.8938	1.6252	0.5714	0.5	4
0.3140	0.9000	0.9062	1.7524	0.5476	0.4762	5
0.2534	0.9688	0.9312	1.8646	0.5238	0.4762	6
0.1999	0.9500	0.9563	1.9513	0.5238	0.4762	7
0.1838	0.9500	0.9688	2.0017	0.5238	0.4762	8

Framework versions

—Transformers 4.25.1
—TensorFlow 2.9.2
—Datasets 2.8.0
—Tokenizers 0.13.2