charlie1108's picture
End of training
a0339f6 verified
metadata
license: apache-2.0
base_model: pedromatias97/genre-recognizer-finetuned-gtzan_dset
tags:
  - generated_from_trainer
datasets:
  - marsyas/gtzan
metrics:
  - accuracy
model-index:
  - name: genre-recognizer-finetuned-gtzan_dset-finetuned-gtzan
    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: 0.94

genre-recognizer-finetuned-gtzan_dset-finetuned-gtzan

This model is a fine-tuned version of pedromatias97/genre-recognizer-finetuned-gtzan_dset on the GTZAN dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1555
  • Accuracy: 0.94

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: 9e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 39
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.3279 0.9956 14 0.2587 0.91
0.1625 1.9911 28 0.1822 0.95
0.1047 2.9867 42 0.1555 0.94

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.2
  • Tokenizers 0.19.1