vowelizer_1203_v6

This model is a fine-tuned version of Buseak/vowelizer_1203_v5 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
0.0291	1.0	967	0.0115	0.9928	0.9936	0.9932	0.9965
0.0184	2.0	1934	0.0058	0.9969	0.9962	0.9965	0.9982
0.0133	3.0	2901	0.0035	0.9980	0.9976	0.9978	0.9989
0.0097	4.0	3868	0.0023	0.9984	0.9985	0.9985	0.9993
0.0082	5.0	4835	0.0016	0.9989	0.9989	0.9989	0.9995
0.007	6.0	5802	0.0010	0.9993	0.9993	0.9993	0.9997
0.0055	7.0	6769	0.0008	0.9993	0.9993	0.9993	0.9997
0.005	8.0	7736	0.0006	0.9996	0.9996	0.9996	0.9998
0.0042	9.0	8703	0.0004	0.9998	0.9998	0.9998	0.9999
0.0036	10.0	9670	0.0003	0.9998	0.9998	0.9998	0.9999
0.0032	11.0	10637	0.0002	0.9998	0.9999	0.9998	0.9999
0.0029	12.0	11604	0.0001	0.9999	0.9999	0.9999	1.0000
0.0023	13.0	12571	0.0001	0.9999	0.9999	0.9999	1.0000
0.0021	14.0	13538	0.0001	0.9999	0.9999	0.9999	1.0000
0.0019	15.0	14505	0.0001	1.0000	1.0000	1.0000	1.0000
0.0017	16.0	15472	0.0000	1.0000	1.0000	1.0000	1.0000
0.0014	17.0	16439	0.0000	1.0000	1.0000	1.0000	1.0000
0.0013	18.0	17406	0.0000	1.0000	1.0000	1.0000	1.0000
0.0012	19.0	18373	0.0000	1.0000	1.0000	1.0000	1.0000
0.0011	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