distilhubert-finetuned-gtzan

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: 0.6210
  • Accuracy: 0.87

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
2.1281 1.0 113 1.9810 0.46
1.4934 2.0 226 1.3605 0.62
1.1668 3.0 339 0.9967 0.75
0.9904 4.0 452 0.8179 0.74
0.7369 5.0 565 0.6686 0.84
0.5161 6.0 678 0.6022 0.8
0.5269 7.0 791 0.5942 0.85
0.2076 8.0 904 0.5678 0.86
0.3907 9.0 1017 0.5466 0.85
0.2112 10.0 1130 0.5610 0.86
0.0678 11.0 1243 0.5933 0.87
0.063 12.0 1356 0.6582 0.81
0.0342 13.0 1469 0.6052 0.88
0.0209 14.0 1582 0.6139 0.88
0.021 15.0 1695 0.6210 0.87

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.3
  • Tokenizers 0.13.3
Downloads last month
32
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 JFuellem/distilhubert-finetuned-gtzan

Finetuned
(409)
this model

Dataset used to train JFuellem/distilhubert-finetuned-gtzan

Evaluation results