chordektomie / README.md
Anguuuuus's picture
End of training
a6abf02 verified
metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: chordektomie
    results: []

chordektomie

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: 0.3610
  • Accuracy: 0.9091

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: 16
  • eval_batch_size: 16
  • 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: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.694 1.0 6 0.6934 0.5909
0.656 2.0 12 0.6910 0.4545
0.5986 3.0 18 0.5668 0.8182
0.4783 4.0 24 0.4786 0.9091
0.3821 5.0 30 0.4230 0.8636
0.2763 6.0 36 0.4426 0.8182
0.2312 7.0 42 0.3846 0.8636
0.1928 8.0 48 0.3662 0.8636
0.1642 9.0 54 0.3672 0.9091
0.1565 10.0 60 0.3610 0.9091

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.17.0
  • Tokenizers 0.15.1