README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: canine_vowelizer_0701_retrain
    results: []

canine_vowelizer_0701_retrain

This model is a fine-tuned version of Buseak/canine_vowelizer_0701 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0066
• Precision: 1.0000
• Recall: 1.0000
• F1: 1.0000
• Accuracy: 0.9980

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0816	1.0	976	0.0322	1.0000	1.0000	1.0000	0.9891
0.0776	2.0	1952	0.0273	0.9999	1.0000	1.0000	0.9906
0.0694	3.0	2928	0.0228	0.9999	1.0000	1.0000	0.9924
0.0617	4.0	3904	0.0181	1.0000	1.0000	1.0000	0.9939
0.0559	5.0	4880	0.0144	1.0000	1.0000	1.0000	0.9952
0.0477	6.0	5856	0.0120	1.0000	1.0000	1.0000	0.9962
0.0438	7.0	6832	0.0098	1.0000	1.0000	1.0000	0.9969
0.0397	8.0	7808	0.0080	1.0000	1.0000	1.0000	0.9975
0.0365	9.0	8784	0.0071	1.0000	1.0000	1.0000	0.9978
0.0328	10.0	9760	0.0066	1.0000	1.0000	1.0000	0.9980

Framework versions

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