canine_vowelizer_0706_v2

This model is a fine-tuned version of google/canine-s on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0003
• 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: 2
• eval_batch_size: 2
• 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
0.161	1.0	3902	0.1236	0.9999	1.0000	0.9999	0.9578
0.1197	2.0	7804	0.0883	1.0000	1.0000	1.0000	0.9689
0.0978	3.0	11706	0.0626	1.0000	1.0000	1.0000	0.9779
0.0808	4.0	15608	0.0454	1.0000	1.0000	1.0000	0.9838
0.0668	5.0	19510	0.0320	1.0000	1.0000	1.0000	0.9885
0.0524	6.0	23412	0.0219	1.0000	1.0000	1.0000	0.9921
0.042	7.0	27314	0.0150	1.0000	1.0000	1.0000	0.9946
0.0348	8.0	31216	0.0109	1.0000	1.0000	1.0000	0.9961
0.0286	9.0	35118	0.0072	1.0000	1.0000	1.0000	0.9974
0.025	10.0	39020	0.0049	1.0000	1.0000	1.0000	0.9983
0.0183	11.0	42922	0.0035	1.0000	1.0000	1.0000	0.9988
0.0157	12.0	46824	0.0025	1.0000	1.0000	1.0000	0.9992
0.0113	13.0	50726	0.0016	1.0000	1.0000	1.0000	0.9995
0.0097	14.0	54628	0.0012	1.0000	1.0000	1.0000	0.9996
0.0081	15.0	58530	0.0008	1.0000	1.0000	1.0000	0.9998
0.0071	16.0	62432	0.0007	1.0000	1.0000	1.0000	0.9998
0.0054	17.0	66334	0.0005	1.0000	1.0000	1.0000	0.9999
0.0044	18.0	70236	0.0004	1.0000	1.0000	1.0000	0.9999
0.0053	19.0	74138	0.0003	1.0000	1.0000	1.0000	1.0000
0.0039	20.0	78040	0.0003	1.0000	1.0000	1.0000	1.0000

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3