Modelpublic

Svetlana0303/Regression_xlnet_NOaug_MSEloss

sourceHugging Facemitupdated 3y agoView on Hugging Face

0likes24downloads

Model Card

RegressionxlnetNOaug_MSEloss

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

—Loss: 0.6460
—Mse: 0.6460
—Mae: 0.7041
—R2: -0.1893
—Accuracy: 0.2632

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: 1e-12
—trainbatchsize: 4
—evalbatchsize: 4
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Mse	Mae	R2	Accuracy
No log	1.0	33	0.7342	0.7342	0.7706	-1.1938	0.2703
No log	2.0	66	0.7342	0.7342	0.7706	-1.1938	0.2703
No log	3.0	99	0.7342	0.7342	0.7706	-1.1938	0.2703
No log	4.0	132	0.7342	0.7342	0.7706	-1.1938	0.2703
No log	5.0	165	0.7342	0.7342	0.7706	-1.1938	0.2703
No log	6.0	198	0.7342	0.7342	0.7706	-1.1938	0.2703
No log	7.0	231	0.7342	0.7342	0.7706	-1.1938	0.2703
No log	8.0	264	0.7342	0.7342	0.7706	-1.1938	0.2703
No log	9.0	297	0.7342	0.7342	0.7706	-1.1938	0.2703
No log	10.0	330	0.7342	0.7342	0.7706	-1.1938	0.2703
No log	11.0	363	0.7342	0.7342	0.7706	-1.1938	0.2703
No log	12.0	396	0.7342	0.7342	0.7706	-1.1938	0.2703
No log	13.0	429	0.7342	0.7342	0.7706	-1.1938	0.2703
No log	14.0	462	0.7342	0.7342	0.7706	-1.1938	0.2703
No log	15.0	495	0.7342	0.7342	0.7706	-1.1938	0.2703

Framework versions

—Transformers 4.28.1
—Pytorch 2.0.0+cu118
—Datasets 2.12.0
—Tokenizers 0.13.3