Modelpublic

DPhO05/roberta-natf-technical-debt-fix

sourceHugging Facemitupdated 6mo agoView on Hugging Face

0likes2downloads

Model Card

roberta-natf-technical-debt-fix

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

—Loss: 0.1310
—Accuracy: 0.9778
—Precision: 0.8361
—Recall: 0.9205
—F1: 0.8763
—F1 Macro: 0.9320

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
—trainbatchsize: 64
—evalbatchsize: 128
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
—lrschedulertype: linear
—lrschedulerwarmup_steps: 500
—num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	F1 Macro
0.0913	1.0	539	0.0814	0.9736	0.8156	0.8930	0.8526	0.9190
0.0841	2.0	1078	0.0631	0.9789	0.8820	0.8685	0.8752	0.9318
0.0585	3.0	1617	0.0636	0.9770	0.8385	0.9052	0.8706	0.9290
0.0387	4.0	2156	0.0771	0.9783	0.8408	0.9205	0.8788	0.9335
0.0270	5.0	2695	0.0795	0.9796	0.8807	0.8807	0.8807	0.9348
0.0268	6.0	3234	0.0970	0.9781	0.8671	0.8777	0.8723	0.9302
0.0172	7.0	3773	0.1224	0.9789	0.875	0.8777	0.8763	0.9324
0.0137	8.0	4312	0.1310	0.9778	0.8361	0.9205	0.8763	0.9320

Framework versions

—Transformers 5.2.0
—Pytorch 2.9.0+cu126
—Datasets 4.0.0
—Tokenizers 0.22.2