This model is a fine-tuned version of benjipeng/distilhubert-finetuned-gtzan on the GTZAN dataset. It achieves the following results on the evaluation set:

Loss: 0.6143
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: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8153	1.0	113	0.7412	0.8
0.6209	2.0	226	0.8662	0.75
0.3642	3.0	339	0.5880	0.84
0.2077	4.0	452	0.6017	0.85
0.1658	5.0	565	0.5087	0.87
0.0209	6.0	678	0.6488	0.85
0.1971	7.0	791	0.5813	0.87
0.0047	8.0	904	0.6143	0.86

Framework versions

Transformers 4.34.1
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1

benjipeng/distilhubert-finetuned-gtzan-finetuned-gtzan

distilhubert-finetuned-gtzan-finetuned-gtzan

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

benjipeng/
distilhubert-finetuned-gtzan-finetuned-gtzan