distilhubert-finetuned-gtzan-bs-8

This model is a fine-tuned version of ntu-spml/distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6841
  • 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
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 15

Training results

Training Loss Epoch Step Validation Loss Accuracy
2.0984 1.0 113 1.9609 0.47
1.4296 2.0 226 1.3195 0.67
1.09 3.0 339 0.9894 0.72
0.9233 4.0 452 0.8749 0.75
0.6404 5.0 565 0.7553 0.78
0.3805 6.0 678 0.7402 0.77
0.4079 7.0 791 0.5268 0.84
0.1812 8.0 904 0.5418 0.85
0.1942 9.0 1017 0.4633 0.86
0.033 10.0 1130 0.6342 0.84
0.0155 11.0 1243 0.6264 0.84
0.1256 12.0 1356 0.6804 0.85
0.0095 13.0 1469 0.6653 0.83
0.0084 14.0 1582 0.6737 0.84
0.0088 15.0 1695 0.6841 0.84

Framework versions

  • Transformers 4.32.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.3
  • Tokenizers 0.13.3
Downloads last month
16
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for DrishtiSharma/distilhubert-finetuned-gtzan-bs-8

Finetuned
(404)
this model

Dataset used to train DrishtiSharma/distilhubert-finetuned-gtzan-bs-8

Evaluation results