CoolFace
Modelpublic

derek-thomas/hubert-base-ls960-finetuned-gtzan-efficient-label-smoothed

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes4downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

hubert-base-ls960-finetuned-gtzan-efficient-label-smoothed

This model is a fine-tuned version of facebook/hubert-base-ls960 on the GTZAN dataset. It achieves the following results on the evaluation set:

  • —Loss: 2.2778
  • —Accuracy: 0.84

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: 8
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_ratio: 0.1
  • —num_epochs: 30
  • —labelsmoothingfactor: 0.9

Training results

Training LossEpochStepValidation LossAccuracy
2.29461.01132.29600.42
2.28212.02262.28580.63
2.28423.03392.28480.68
2.26854.04522.28360.71
2.26885.05652.28380.71
2.29016.06782.28040.75
2.26837.07912.28310.7
2.26958.09042.28330.75
2.2689.010172.27930.8
2.283610.011302.28670.68
2.270411.012432.28110.78
2.266512.013562.27830.83
2.266313.014692.27820.85
2.266914.015822.27590.88
2.26615.016952.28000.82
2.26616.018082.27970.82
2.26617.019212.27780.84

Framework versions

  • —Transformers 4.30.2
  • —Pytorch 2.1.0.dev20230627+cu121
  • —Datasets 2.13.1
  • —Tokenizers 0.13.3