metadata

license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
  - generated_from_trainer
datasets:
  - gtzan
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: music-genre-detector-finetuned-gtzan_dset
    results:
      - task:
          name: Audio Classification
          type: audio-classification
        dataset:
          name: GTZAN
          type: gtzan
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9298245614035088
          - name: Precision
            type: precision
            value: 0.9292447472185437
          - name: Recall
            type: recall
            value: 0.9298245614035088
          - name: F1
            type: f1
            value: 0.9293437948869628

music-genre-detector-finetuned-gtzan_dset

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: 0.2288
Accuracy: 0.9298
Precision: 0.9292
Recall: 0.9298
F1: 0.9293

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: 42
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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
2.2522	0.98	49	1.6370	0.6090	0.6189	0.6090	0.5764
1.2901	1.98	99	0.9974	0.7556	0.7655	0.7556	0.7426
1.0046	2.99	149	0.6645	0.8195	0.8226	0.8195	0.8162
0.5952	3.99	199	0.5054	0.8459	0.8561	0.8459	0.8460
0.3596	4.99	249	0.3729	0.9023	0.9117	0.9023	0.9041
0.2534	5.99	299	0.2953	0.9073	0.9088	0.9073	0.9075
0.1413	7.0	349	0.2545	0.9223	0.9229	0.9223	0.9216
0.0759	8.0	399	0.2593	0.9198	0.9209	0.9198	0.9190
0.0491	8.98	448	0.2288	0.9298	0.9292	0.9298	0.9293
0.0355	9.82	490	0.2392	0.9223	0.9231	0.9223	0.9221

Framework versions

Transformers 4.33.1
Pytorch 1.10.2+cu111
Datasets 2.14.5
Tokenizers 0.13.3