canine_vowelizer_0706_v2_retrain_on_0701

This model is a fine-tuned version of Buseak/canine_vowelizer_0706_v2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0015
• Precision: 1.0000
• Recall: 1.0000
• F1: 1.0000
• Accuracy: 0.9996

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	488	0.0264	1.0000	1.0000	1.0000	0.9921
0.0548	2.0	976	0.0165	1.0000	1.0000	1.0000	0.9950
0.0396	3.0	1464	0.0109	1.0000	1.0000	1.0000	0.9966
0.0308	4.0	1952	0.0070	1.0000	1.0000	1.0000	0.9978
0.0243	5.0	2440	0.0047	1.0000	1.0000	1.0000	0.9986
0.0199	6.0	2928	0.0034	1.0000	1.0000	1.0000	0.9991
0.0167	7.0	3416	0.0024	1.0000	1.0000	1.0000	0.9993
0.0136	8.0	3904	0.0020	1.0000	1.0000	1.0000	0.9995
0.0121	9.0	4392	0.0016	1.0000	1.0000	1.0000	0.9996
0.0109	10.0	4880	0.0015	1.0000	1.0000	1.0000	0.9996

Framework versions

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