CoolFace
Modelpublic

ramsri818/ast-finetuned-gtzan

sourceHugging Facebsd-3-clauseupdated 3y agoView on Hugging Face
0likes15downloads
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. -->

ast-finetuned-gtzan

This model is a fine-tuned version of MIT/ast-finetuned-audioset-10-10-0.4593 on the GTZAN dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.4436
  • —Accuracy: 0.93

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: 4
  • —evalbatchsize: 4
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —lrschedulerwarmup_ratio: 0.1
  • —num_epochs: 20

Training results

Training LossEpochStepValidation LossAccuracy
0.00011.02250.55460.89
1.2042.04500.94840.81
0.47193.06750.74170.85
0.01324.09000.71010.9
0.05275.011250.81700.86
0.06.013500.64060.93
0.30997.015750.84260.84
0.08.018000.91730.89
0.09.020250.71420.9
0.060210.022500.47180.92
0.000311.024750.98600.9
0.000112.027000.59180.91
0.013.029250.48860.92
0.014.031500.45620.93
0.015.033750.43600.94
0.016.036000.44330.94
0.017.038250.44540.94
0.018.040500.44540.94
0.019.042750.44340.93
0.020.045000.44360.93

Framework versions

  • —Transformers 4.32.0.dev0
  • —Pytorch 2.0.1+cu118
  • —Datasets 2.14.2
  • —Tokenizers 0.13.3