NiloofarMomeni's picture
End of training
21c6bb4 verified
|
raw
history blame
3.25 kB
metadata
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
  - generated_from_trainer
datasets:
  - marsyas/gtzan
metrics:
  - accuracy
model-index:
  - name: distilhubert-finetuned-VD
    results:
      - task:
          name: Audio Classification
          type: audio-classification
        dataset:
          name: GTZAN
          type: marsyas/gtzan
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8933256172839507

distilhubert-finetuned-VD

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: 0.7226
  • Accuracy: 0.8933

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: 10
  • eval_batch_size: 10
  • 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: 25
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.3302 1.0 195 0.3716 0.8800
0.6059 2.0 390 0.5195 0.8090
0.4938 3.0 585 1.0102 0.6260
0.836 4.0 780 1.1662 0.6742
0.2234 5.0 975 0.6792 0.8389
0.1444 6.0 1170 0.9137 0.8239
0.2986 7.0 1365 0.7987 0.8623
0.0004 8.0 1560 1.5075 0.7687
0.0005 9.0 1755 0.7226 0.8933
0.0002 10.0 1950 0.8246 0.8829
0.0002 11.0 2145 1.4227 0.8129
0.0001 12.0 2340 1.0478 0.8665
0.0001 13.0 2535 1.3328 0.8322
0.0001 14.0 2730 1.3480 0.8347
0.0001 15.0 2925 1.3559 0.8370
0.0 16.0 3120 1.3589 0.8407
0.0 17.0 3315 1.3706 0.8410
0.0 18.0 3510 1.3831 0.8410
0.0 19.0 3705 1.3954 0.8410
0.0 20.0 3900 1.4027 0.8412
0.0 21.0 4095 1.4132 0.8409
0.0 22.0 4290 1.4218 0.8407
0.0 23.0 4485 1.4272 0.8407
0.0 24.0 4680 1.4321 0.8399
0.0 25.0 4875 1.4337 0.8399

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.2.2+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2