ihanif/distilhubert-music-gtzan-classification

distilhubert-music-classification

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: 0.7110
• Accuracy: 0.86

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: 16

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.1284	1.0	113	1.9802	0.5
1.435	2.0	226	1.3403	0.65
1.0235	3.0	339	0.9941	0.74
0.8973	4.0	452	0.9184	0.69
0.7312	5.0	565	0.6918	0.79
0.4306	6.0	678	0.6343	0.78
0.4204	7.0	791	0.6174	0.83
0.1326	8.0	904	0.5888	0.83
0.0766	9.0	1017	0.5939	0.84
0.0308	10.0	1130	0.7191	0.86
0.0318	11.0	1243	0.7308	0.84
0.0657	12.0	1356	0.7222	0.81
0.0096	13.0	1469	0.7075	0.84
0.0077	14.0	1582	0.7268	0.84
0.0073	15.0	1695	0.6957	0.85
0.0066	16.0	1808	0.7110	0.86

Framework versions

• Transformers 4.31.0.dev0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.13.3