canine_deasciifier_final_0701_v8

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

• Loss: 0.0340
• Precision: 0.9153
• Recall: 0.9338
• F1: 0.9244
• Accuracy: 0.9918

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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	488	0.0903	0.6868	0.7578	0.7205	0.9660
0.2413	2.0	976	0.0562	0.8068	0.8466	0.8262	0.9800
0.0812	3.0	1464	0.0409	0.8669	0.8674	0.8672	0.9854
0.052	4.0	1952	0.0381	0.8664	0.8971	0.8815	0.9870
0.0377	5.0	2440	0.0370	0.8738	0.9038	0.8886	0.9877
0.0291	6.0	2928	0.0314	0.9071	0.9088	0.9079	0.9900
0.0234	7.0	3416	0.0340	0.8867	0.9191	0.9026	0.9892
0.0196	8.0	3904	0.0325	0.9030	0.9242	0.9135	0.9905
0.0158	9.0	4392	0.0319	0.9109	0.9266	0.9187	0.9911
0.0132	10.0	4880	0.0329	0.9087	0.9318	0.9201	0.9913
0.0113	11.0	5368	0.0331	0.9045	0.9315	0.9178	0.9910
0.0099	12.0	5856	0.0337	0.9088	0.9314	0.9200	0.9913
0.0083	13.0	6344	0.0346	0.9133	0.9357	0.9244	0.9917
0.0081	14.0	6832	0.0332	0.9167	0.9324	0.9245	0.9918
0.0071	15.0	7320	0.0340	0.9153	0.9338	0.9244	0.9918

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0