wav2vec2-base-100k-gtzan-music-genres-finetuned-gtzan

This model is a fine-tuned version of m3hrdadfi/wav2vec2-base-100k-gtzan-music-genres on the GTZAN dataset. It achieves the following results on the evaluation set:

• Loss: 0.6843
• Accuracy: 0.98

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
• gradient_accumulation_steps: 8
• 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: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.1932	0.9976	53	2.1037	0.82
1.9212	1.9953	106	1.8040	0.8267
1.6379	2.9929	159	1.5650	0.8667
1.4604	3.9906	212	1.3201	0.9267
1.2249	4.9882	265	1.1253	0.94
1.075	5.9859	318	0.9814	0.96
0.911	6.9835	371	0.8447	0.9667
0.852	8.0	425	0.7628	0.9667
0.7625	8.9976	478	0.7117	0.9733
0.7099	9.9765	530	0.6843	0.98

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1