Edit model card

vowelizer_1203_v10

This model is a fine-tuned version of Buseak/vowelizer_1203_v9 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
0.0383 1.0 967 0.0127 0.9939 0.9893 0.9916 0.9961
0.0237 2.0 1934 0.0064 0.9967 0.9950 0.9959 0.9980
0.016 3.0 2901 0.0039 0.9978 0.9966 0.9972 0.9987
0.0119 4.0 3868 0.0024 0.9987 0.9982 0.9985 0.9993
0.0097 5.0 4835 0.0016 0.9990 0.9989 0.9990 0.9995
0.0078 6.0 5802 0.0012 0.9992 0.9993 0.9992 0.9996
0.0064 7.0 6769 0.0007 0.9996 0.9995 0.9996 0.9998
0.0056 8.0 7736 0.0007 0.9997 0.9996 0.9996 0.9998
0.005 9.0 8703 0.0004 0.9998 0.9997 0.9997 0.9999
0.0042 10.0 9670 0.0004 0.9997 0.9997 0.9997 0.9999
0.0037 11.0 10637 0.0002 0.9999 0.9998 0.9999 0.9999
0.0031 12.0 11604 0.0002 0.9999 0.9999 0.9999 1.0000
0.0026 13.0 12571 0.0001 0.9999 1.0000 0.9999 1.0000
0.0024 14.0 13538 0.0001 0.9999 0.9999 0.9999 1.0000
0.002 15.0 14505 0.0001 1.0000 1.0000 1.0000 1.0000
0.0019 16.0 15472 0.0000 1.0000 1.0000 1.0000 1.0000
0.0017 17.0 16439 0.0000 1.0000 1.0000 1.0000 1.0000
0.0014 18.0 17406 0.0000 1.0000 1.0000 1.0000 1.0000
0.0011 19.0 18373 0.0000 1.0000 1.0000 1.0000 1.0000
0.0012 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
4
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.