Hugging Face's logo

JamesJenkins
/
ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan

Audio Classification
TensorBoard
Safetensors
audio-spectrogram-transformer
Generated from Trainer
Eval Results
Model card Files Metrics Community
ast-finetuned-audioset-10-10-0.4593-finetuned-gtzan / README.md
JamesJenkins's picture
JamesJenkins
End of training
e2d9a45 verified
preview code
|
raw
history blame
3.41 kB
metadata
license: bsd-3-clause
base_model: MIT/ast-finetuned-audioset-10-10-0.4593
tags:
  - generated_from_trainer
datasets:
  - marsyas/gtzan
metrics:
  - accuracy
  - f1
model-index:
  - name: ast-finetuned-audioset-10-10-0.4593-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: 0.86
          - name: F1
            type: f1
            value: 0.8599999999999999

ast-finetuned-audioset-10-10-0.4593-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: 0.7149
  • Accuracy: 0.86
  • F1: 0.8600

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: 2
  • eval_batch_size: 2
  • seed: 2024
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 20
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
0.6891 0.9956 112 0.6422 0.76 0.76
0.7267 2.0 225 0.8163 0.78 0.78
0.7077 2.9956 337 0.7802 0.8 0.8000
0.1884 4.0 450 0.6157 0.87 0.87
0.0209 4.9956 562 0.7885 0.84 0.8400
0.117 6.0 675 0.6744 0.85 0.85
0.0098 6.9956 787 0.6213 0.85 0.85
0.0002 8.0 900 1.0599 0.82 0.82
0.0001 8.9956 1012 0.7052 0.86 0.8600
0.0001 10.0 1125 0.6891 0.85 0.85
0.0001 10.9956 1237 0.6718 0.86 0.8600
0.0001 12.0 1350 0.6712 0.85 0.85
0.0001 12.9956 1462 0.6942 0.86 0.8600
0.0001 14.0 1575 0.7002 0.86 0.8600
0.0176 14.9956 1687 0.7053 0.86 0.8600
0.0001 16.0 1800 0.7140 0.86 0.8600
0.0001 16.9956 1912 0.7089 0.86 0.8600
0.0 18.0 2025 0.7120 0.86 0.8600
0.0628 18.9956 2137 0.7162 0.86 0.8600
0.0037 19.9111 2240 0.7149 0.86 0.8600

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1