Modelpublic

anushkat/DistilGPT2-Beatles-Spotify-FinalVersion

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

0likes9downloads

Model Card

DistilGPT2-Beatles-Spotify-FinalVersion

This model is a fine-tuned version of wvangils/DistilGPT2-Beatles-Lyrics-finetuned on the None dataset. It achieves the following results on the evaluation set:

—Loss: 1.8839

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: 5e-05
—trainbatchsize: 2
—evalbatchsize: 16
—seed: 42
—gradientaccumulationsteps: 4
—totaltrainbatch_size: 8
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—lrschedulerwarmup_steps: 1
—training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
2.1125	0.0	25	1.9245
2.1035	0.0	50	1.9315
2.1064	0.0	75	1.9184
2.0874	0.0	100	1.9101
2.0948	0.0	125	1.9143
2.1088	0.0	150	1.8953
2.0612	0.01	175	1.9130
2.0828	0.01	200	1.9046
2.0676	0.01	225	1.8950
2.072	0.01	250	1.9092
2.0748	0.01	275	1.8814
2.0769	0.01	300	1.8948
2.068	0.01	325	1.8921
2.0513	0.01	350	1.8904
2.0686	0.01	375	1.8794
2.0702	0.01	400	1.8800
2.059	0.01	425	1.8780
2.0562	0.01	450	1.8841
2.0705	0.01	475	1.8824
2.0675	0.02	500	1.8839

Framework versions

—PEFT 0.8.2
—Transformers 4.38.1
—Pytorch 1.13.1
—Datasets 2.17.0
—Tokenizers 0.15.2