vowelizer_1203_v8

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: 0.0001
• 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
0.0731	1.0	967	0.0292	0.9860	0.9750	0.9805	0.9908
0.0462	2.0	1934	0.0171	0.9916	0.9850	0.9883	0.9945
0.0327	3.0	2901	0.0104	0.9950	0.9907	0.9929	0.9967
0.0243	4.0	3868	0.0063	0.9968	0.9953	0.9960	0.9981
0.0197	5.0	4835	0.0042	0.9979	0.9968	0.9973	0.9987
0.0159	6.0	5802	0.0031	0.9981	0.9979	0.9980	0.9991
0.0132	7.0	6769	0.0018	0.9990	0.9985	0.9988	0.9995
0.0115	8.0	7736	0.0014	0.9991	0.9991	0.9991	0.9996
0.0097	9.0	8703	0.0010	0.9994	0.9994	0.9994	0.9997
0.0082	10.0	9670	0.0007	0.9996	0.9995	0.9996	0.9998
0.0066	11.0	10637	0.0005	0.9998	0.9997	0.9998	0.9999
0.006	12.0	11604	0.0004	0.9998	0.9998	0.9998	0.9999
0.0055	13.0	12571	0.0003	0.9997	0.9997	0.9997	0.9999
0.0047	14.0	13538	0.0002	0.9999	0.9999	0.9999	1.0000
0.004	15.0	14505	0.0002	0.9999	0.9999	0.9999	1.0000
0.0034	16.0	15472	0.0001	0.9999	0.9999	0.9999	1.0000
0.0032	17.0	16439	0.0001	1.0000	1.0000	1.0000	1.0000
0.003	18.0	17406	0.0001	1.0000	1.0000	1.0000	1.0000
0.0027	19.0	18373	0.0001	1.0000	1.0000	1.0000	1.0000
0.0024	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