lyrics_detect

This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6254
• Accuracy: 0.6

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 128
• total_train_batch_size: 128
• 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

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.9956	7	0.6137	0.71
0.6734	1.9911	14	0.5822	0.71
0.6594	2.9867	21	0.6136	0.72
0.6594	3.9822	28	0.6369	0.72
0.6299	4.9778	35	0.6399	0.62
0.6204	5.9733	42	0.6647	0.56
0.6204	6.9689	49	0.6278	0.66
0.6156	7.9644	56	0.6578	0.67
0.6261	8.96	63	0.6107	0.65
0.5914	9.9556	70	0.6254	0.6

Framework versions

• Transformers 4.43.4
• Pytorch 2.3.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1