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: nan
• Accuracy: 0.1

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: 0.0001
• 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: 0.2
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0	1.0	113	nan	0.1
0.0	2.0	226	nan	0.1
0.0	3.0	339	nan	0.1
0.0	4.0	452	nan	0.1
0.0	5.0	565	nan	0.1
0.0	6.0	678	nan	0.1
0.0	7.0	791	nan	0.1
0.0	8.0	904	nan	0.1
0.0	9.0	1017	nan	0.1
0.0	10.0	1130	nan	0.1
0.0	11.0	1243	nan	0.1
0.0	12.0	1356	nan	0.1
0.0	13.0	1469	nan	0.1
0.0	14.0	1582	nan	0.1
0.0	15.0	1695	nan	0.1
0.0	16.0	1808	nan	0.1
0.0	17.0	1921	nan	0.1
0.0	18.0	2034	nan	0.1
0.0	19.0	2147	nan	0.1
0.0	20.0	2260	nan	0.1

Framework versions

• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Datasets 3.0.2
• Tokenizers 0.19.1