metadata

license: apache-2.0
base_model: bookbot/distil-ast-audioset
tags:
  - generated_from_trainer
datasets:
  - marsyas/gtzan
metrics:
  - accuracy
model-index:
  - name: distil-ast-audioset-finetuned-gtzan
    results:
      - task:
          name: Audio Classification
          type: audio-classification
        dataset:
          name: GTZAN
          type: marsyas/gtzan
          config: train
          split: train
          args: train
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.92

distil-ast-audioset-finetuned-gtzan

This model is a fine-tuned version of bookbot/distil-ast-audioset on the GTZAN dataset. It achieves the following results on the evaluation set:

Loss: 0.3742
Accuracy: 0.92

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.0362	1.0	113	0.8029	0.75
0.7068	2.0	226	0.4494	0.86
0.3458	3.0	339	0.5926	0.78
0.1416	4.0	452	0.5162	0.89
0.1134	5.0	565	0.6216	0.84
0.003	6.0	678	0.5221	0.9
0.3177	7.0	791	0.3742	0.92
0.0002	8.0	904	0.5134	0.91
0.0022	9.0	1017	0.6814	0.86
0.0002	10.0	1130	0.5605	0.9
0.0001	11.0	1243	0.4976	0.9
0.0105	12.0	1356	0.5841	0.89
0.0001	13.0	1469	0.4664	0.89
0.0	14.0	1582	0.5755	0.89
0.0	15.0	1695	0.4913	0.9
0.0001	16.0	1808	0.4877	0.9
0.0	17.0	1921	0.4855	0.9
0.0	18.0	2034	0.4859	0.9
0.0	19.0	2147	0.4862	0.9
0.0	20.0	2260	0.4865	0.9

Framework versions

Transformers 4.32.0.dev0
Pytorch 2.0.1+cu118
Datasets 2.14.4
Tokenizers 0.13.3