Modelpublic

PathofthePeople/TrainedLocation

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

0likes6downloads

Model Card

TrainedLocation

This model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

—Loss: 0.0090
—Accuracy: 0.9967

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:

—learning_rate: 2e-05
—trainbatchsize: 16
—evalbatchsize: 16
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	38	0.2576	0.905
No log	2.0	76	0.1648	0.9433
No log	3.0	114	0.1230	0.965
No log	4.0	152	0.0910	0.9717
No log	5.0	190	0.0732	0.9767
No log	6.0	228	0.0623	0.9767
No log	7.0	266	0.0355	0.99
No log	8.0	304	0.0291	0.9883
No log	9.0	342	0.0246	0.99
No log	10.0	380	0.0217	0.9917
No log	11.0	418	0.0148	0.995
No log	12.0	456	0.0148	0.995
No log	13.0	494	0.0118	0.995
0.1064	14.0	532	0.0103	0.9967
0.1064	15.0	570	0.0101	0.9967
0.1064	16.0	608	0.0095	0.9967
0.1064	17.0	646	0.0099	0.9967
0.1064	18.0	684	0.0092	0.9967
0.1064	19.0	722	0.0089	0.9967
0.1064	20.0	760	0.0090	0.9967

Framework versions

—Transformers 4.38.1
—Pytorch 2.2.1
—Datasets 2.19.0
—Tokenizers 0.15.2