canine_vowelizer_0701

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: 0.0273
• Precision: 0.9999
• Recall: 1.0000
• F1: 1.0000
• Accuracy: 0.9905

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
0.521	1.0	1951	0.4233	0.9998	0.9999	0.9998	0.8544
0.3948	2.0	3902	0.3227	0.9998	1.0000	0.9999	0.8899
0.3353	3.0	5853	0.2592	0.9999	1.0000	0.9999	0.9116
0.2907	4.0	7804	0.2172	0.9999	0.9999	0.9999	0.9253
0.2503	5.0	9755	0.1823	0.9999	1.0000	0.9999	0.9363
0.2251	6.0	11706	0.1530	0.9999	1.0000	0.9999	0.9460
0.2001	7.0	13657	0.1299	0.9999	1.0000	0.9999	0.9540
0.1757	8.0	15608	0.1081	0.9999	1.0000	0.9999	0.9613
0.1602	9.0	17559	0.0936	0.9999	1.0000	0.9999	0.9665
0.1473	10.0	19510	0.0802	0.9999	1.0000	0.9999	0.9712
0.1319	11.0	21461	0.0700	0.9999	1.0000	1.0000	0.9748
0.1169	12.0	23412	0.0602	0.9999	1.0000	0.9999	0.9783
0.1071	13.0	25363	0.0518	0.9999	1.0000	0.9999	0.9815
0.0985	14.0	27314	0.0455	0.9999	1.0000	1.0000	0.9838
0.0918	15.0	29265	0.0402	0.9999	1.0000	1.0000	0.9859
0.0848	16.0	31216	0.0362	0.9999	1.0000	1.0000	0.9871
0.079	17.0	33167	0.0323	0.9999	1.0000	1.0000	0.9888
0.0728	18.0	35118	0.0295	0.9999	1.0000	1.0000	0.9897
0.0716	19.0	37069	0.0278	0.9999	1.0000	1.0000	0.9904
0.0686	20.0	39020	0.0273	0.9999	1.0000	1.0000	0.9905

Framework versions

• Transformers 4.28.0
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.13.3