FredDYyy's picture
End of training
e87c781 verified
metadata
license: apache-2.0
base_model: yuval6967/distilhubert-finetuned-gtzan
tags:
  - generated_from_trainer
datasets:
  - marsyas/gtzan
metrics:
  - accuracy
model-index:
  - name: distilhubert-finetuned-gtzan-music-genre-classification
    results:
      - task:
          name: Audio Classification
          type: audio-classification
        dataset:
          name: GTZAN
          type: marsyas/gtzan
          config: all
          split: train
          args: all
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.935

distilhubert-finetuned-gtzan-music-genre-classification

This model is a fine-tuned version of yuval6967/distilhubert-finetuned-gtzan on the GTZAN dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4478
  • Accuracy: 0.935

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: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 100 0.3000 0.935
No log 2.0 200 0.4770 0.905
No log 3.0 300 0.5666 0.93
No log 4.0 400 0.4572 0.92
0.0298 5.0 500 0.6038 0.9
0.0298 6.0 600 0.4111 0.925
0.0298 7.0 700 0.4528 0.93
0.0298 8.0 800 0.4400 0.94
0.0298 9.0 900 0.4638 0.935
0.0081 10.0 1000 0.4478 0.935

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.1.2
  • Datasets 2.18.0
  • Tokenizers 0.15.2