Edit model card

musicaudio-outputs

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

  • Loss: 0.8706
  • Accuracy: 0.25

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: 1e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • 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: 6

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 2 0.8776 0.125
0.4966 2.0 4 0.8590 0.125
0.4966 3.0 6 0.8707 0.0
0.4718 4.0 8 0.8794 0.125
0.4718 5.0 10 0.8705 0.25
0.4606 6.0 12 0.8706 0.25

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
74
Safetensors
Model size
94.6M params
Tensor type
F32
·
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Finetuned from

Evaluation results