canine_vowelizer_0706_v4

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: 0.1450
• Precision: 1.0000
• Recall: 1.0
• F1: 1.0000
• Accuracy: 0.9775

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: 4
• eval_batch_size: 4
• 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
0.1088	1.0	1951	0.1144	0.9999	1.0	1.0000	0.9628
0.1009	2.0	3902	0.1023	0.9999	1.0	1.0000	0.9657
0.0917	3.0	5853	0.0985	1.0000	1.0	1.0000	0.9690
0.0757	4.0	7804	0.0928	1.0000	1.0000	1.0000	0.9712
0.0635	5.0	9755	0.0932	0.9999	1.0	1.0000	0.9725
0.0542	6.0	11706	0.0943	0.9999	1.0000	1.0000	0.9735
0.0453	7.0	13657	0.0980	1.0000	1.0000	1.0000	0.9738
0.0369	8.0	15608	0.1037	1.0000	1.0	1.0000	0.9750
0.0308	9.0	17559	0.1056	1.0000	1.0000	1.0000	0.9747
0.0275	10.0	19510	0.1138	1.0000	1.0	1.0000	0.9757
0.0222	11.0	21461	0.1187	1.0000	1.0	1.0000	0.9757
0.0185	12.0	23412	0.1201	1.0000	1.0000	1.0000	0.9761
0.0166	13.0	25363	0.1239	1.0000	1.0000	1.0000	0.9764
0.0146	14.0	27314	0.1302	1.0000	1.0	1.0000	0.9768
0.0112	15.0	29265	0.1351	1.0000	1.0000	1.0000	0.9768
0.0104	16.0	31216	0.1386	1.0000	1.0	1.0000	0.9769
0.0092	17.0	33167	0.1379	1.0000	1.0	1.0000	0.9771
0.0079	18.0	35118	0.1453	1.0000	1.0	1.0000	0.9771
0.0071	19.0	37069	0.1444	1.0000	1.0	1.0000	0.9775
0.0067	20.0	39020	0.1450	1.0000	1.0	1.0000	0.9775

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.0
• Tokenizers 0.13.3