vowelizer_1203_v3

This model is a fine-tuned version of Buseak/vowelizer_1203_v2 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
0.0151	1.0	967	0.0037	0.9977	0.9979	0.9978	0.9987
0.0159	2.0	1934	0.0028	0.9982	0.9981	0.9982	0.9991
0.0138	3.0	2901	0.0023	0.9986	0.9984	0.9985	0.9993
0.0121	4.0	3868	0.0017	0.9988	0.9989	0.9989	0.9995
0.0106	5.0	4835	0.0014	0.9988	0.9991	0.9990	0.9996
0.0089	6.0	5802	0.0010	0.9993	0.9993	0.9993	0.9997
0.0084	7.0	6769	0.0009	0.9994	0.9994	0.9994	0.9997
0.0072	8.0	7736	0.0007	0.9995	0.9996	0.9995	0.9998
0.0067	9.0	8703	0.0005	0.9997	0.9997	0.9997	0.9999
0.0057	10.0	9670	0.0004	0.9996	0.9997	0.9997	0.9999
0.005	11.0	10637	0.0004	0.9996	0.9997	0.9997	0.9999
0.0043	12.0	11604	0.0003	0.9997	0.9998	0.9997	0.9999
0.0039	13.0	12571	0.0002	0.9998	0.9998	0.9998	0.9999
0.0034	14.0	13538	0.0002	0.9998	0.9999	0.9999	1.0000
0.0032	15.0	14505	0.0001	0.9999	0.9999	0.9999	1.0000
0.003	16.0	15472	0.0001	0.9999	0.9999	0.9999	1.0000
0.0027	17.0	16439	0.0001	0.9999	0.9999	0.9999	1.0000
0.0022	18.0	17406	0.0001	1.0000	1.0000	1.0000	1.0000
0.002	19.0	18373	0.0001	1.0000	1.0000	1.0000	1.0000
0.0019	20.0	19340	0.0001	1.0000	1.0000	1.0000	1.0000

Framework versions

• Transformers 4.28.0
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.13.3