distilhubert-finetuned-gtzan

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: 1.0924
• Accuracy: 0.87

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: 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: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.7495	1.0	450	1.7168	0.52
1.1633	2.0	900	1.0515	0.66
0.3792	3.0	1350	0.7312	0.73
0.5365	4.0	1800	0.9707	0.75
0.0234	5.0	2250	1.1124	0.75
0.0039	6.0	2700	0.9717	0.82
0.1781	7.0	3150	1.0491	0.82
0.0009	8.0	3600	1.1946	0.83
0.0007	9.0	4050	1.1116	0.84
0.0004	10.0	4500	1.0814	0.85
0.0004	11.0	4950	1.1160	0.85
0.0003	12.0	5400	1.1082	0.85
0.0003	13.0	5850	1.1311	0.86
0.0002	14.0	6300	1.1159	0.86
0.0003	15.0	6750	1.0924	0.87

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2