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: 0.5120
• 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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 12
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.1876	0.9912	56	2.0708	0.45
1.5886	2.0	113	1.5004	0.56
1.208	2.9912	169	1.2087	0.64
0.9477	4.0	226	1.0389	0.7
0.7717	4.9912	282	0.7855	0.8
0.6776	6.0	339	0.7336	0.81
0.5734	6.9912	395	0.6742	0.83
0.4696	8.0	452	0.5968	0.85
0.3647	8.9912	508	0.5672	0.85
0.3598	10.0	565	0.5478	0.86
0.2732	10.9912	621	0.5595	0.84
0.3225	11.8938	672	0.5120	0.87

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1