Edit model card

vowelizer_1203_v9

This model is a fine-tuned version of Buseak/vowelizer_1203_v6 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0000
  • Precision: 1.0000
  • Recall: 1.0000
  • F1: 1.0000
  • Accuracy: 1.0000

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: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.0516 1.0 967 0.0195 0.9907 0.9827 0.9867 0.9941
0.0318 2.0 1934 0.0109 0.9950 0.9901 0.9925 0.9967
0.0225 3.0 2901 0.0065 0.9960 0.9950 0.9955 0.9980
0.017 4.0 3868 0.0037 0.9981 0.9968 0.9975 0.9988
0.013 5.0 4835 0.0026 0.9986 0.9980 0.9983 0.9992
0.0103 6.0 5802 0.0018 0.9989 0.9988 0.9989 0.9995
0.0091 7.0 6769 0.0012 0.9992 0.9990 0.9991 0.9996
0.0073 8.0 7736 0.0009 0.9994 0.9992 0.9993 0.9997
0.0065 9.0 8703 0.0006 0.9996 0.9996 0.9996 0.9998
0.0057 10.0 9670 0.0004 0.9997 0.9997 0.9997 0.9999
0.0045 11.0 10637 0.0003 0.9997 0.9997 0.9997 0.9999
0.004 12.0 11604 0.0003 0.9999 0.9998 0.9998 0.9999
0.0035 13.0 12571 0.0002 0.9998 0.9998 0.9998 0.9999
0.003 14.0 13538 0.0002 0.9999 0.9999 0.9999 1.0000
0.0029 15.0 14505 0.0001 0.9999 0.9999 0.9999 1.0000
0.0024 16.0 15472 0.0001 1.0000 0.9999 0.9999 1.0000
0.0021 17.0 16439 0.0001 0.9999 0.9999 0.9999 1.0000
0.0019 18.0 17406 0.0001 1.0000 1.0000 1.0000 1.0000
0.0018 19.0 18373 0.0000 1.0000 1.0000 1.0000 1.0000
0.0015 20.0 19340 0.0000 1.0000 1.0000 1.0000 1.0000

Framework versions

  • Transformers 4.28.0
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.13.3
Downloads last month
6
Inference Examples
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.