distil-ast-audioset-finetuned-gtzan

This model is a fine-tuned version of bookbot/distil-ast-audioset on the GTZAN dataset. It achieves the following results on the evaluation set:

• Loss: 0.3707
• Accuracy: 0.88

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: 3e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7768	0.9912	28	0.4780	0.85
0.4124	1.9823	56	0.4763	0.87
0.2095	2.9735	84	0.4231	0.89
0.0874	4.0	113	0.4250	0.87
0.0406	4.9912	141	0.4068	0.87
0.0205	5.9823	169	0.3918	0.88
0.0082	6.9735	197	0.3604	0.89
0.0082	8.0	226	0.3804	0.89
0.0059	8.9912	254	0.3821	0.87
0.004	9.9115	280	0.3707	0.88

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1
• Datasets 3.0.0
• Tokenizers 0.19.1