README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: vowelizer_1203_v11
    results: []

vowelizer_1203_v11

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: 0.0001
• 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
0.0659	1.0	967	0.0290	0.9908	0.9845	0.9877	0.9920
0.0394	2.0	1934	0.0166	0.9950	0.9921	0.9936	0.9955
0.0271	3.0	2901	0.0098	0.9967	0.9958	0.9963	0.9974
0.0202	4.0	3868	0.0059	0.9981	0.9978	0.9979	0.9984
0.0152	5.0	4835	0.0037	0.9989	0.9982	0.9985	0.9991
0.0119	6.0	5802	0.0026	0.9992	0.9989	0.9990	0.9993
0.01	7.0	6769	0.0017	0.9995	0.9992	0.9994	0.9996
0.0077	8.0	7736	0.0013	0.9995	0.9995	0.9995	0.9997
0.0062	9.0	8703	0.0009	0.9996	0.9997	0.9997	0.9998
0.0062	10.0	9670	0.0006	0.9998	0.9998	0.9998	0.9999
0.0051	11.0	10637	0.0006	0.9998	0.9997	0.9998	0.9999
0.0043	12.0	11604	0.0004	0.9999	0.9999	0.9999	0.9999
0.0036	13.0	12571	0.0003	0.9999	0.9999	0.9999	0.9999
0.0031	14.0	13538	0.0002	0.9999	0.9999	0.9999	1.0000
0.0027	15.0	14505	0.0002	1.0000	1.0000	1.0000	1.0000
0.0025	16.0	15472	0.0001	1.0000	0.9999	0.9999	1.0000
0.0021	17.0	16439	0.0001	1.0000	1.0000	1.0000	1.0000
0.0019	18.0	17406	0.0001	1.0000	1.0000	1.0000	1.0000
0.0017	19.0	18373	0.0001	1.0000	1.0000	1.0000	1.0000
0.0016	20.0	19340	0.0001	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