Modelpublic

Kuongan/CS221-xlm-roberta-base-ibo-finetuned-finetuned-ibo-tapt

sourceHugging Facemitupdated 2y agoView on Hugging Face

0likes11downloads

Model Card

CS221-xlm-roberta-base-ibo-finetuned-finetuned-ibo-tapt

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

—Loss: 0.1694
—F1: 0.7677
—Roc Auc: 0.8528
—Accuracy: 0.7699

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: 32
—evalbatchsize: 32
—seed: 42
—optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
—lrschedulertype: cosine
—lrschedulerwarmup_steps: 100
—num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.1739	1.0	189	0.1357	0.6677	0.8181	0.7630
0.166	2.0	378	0.1356	0.6722	0.8248	0.7605
0.1227	3.0	567	0.1471	0.6908	0.8371	0.7494
0.1219	4.0	756	0.1466	0.7224	0.8437	0.7511
0.0952	5.0	945	0.1497	0.7004	0.8227	0.7528
0.0933	6.0	1134	0.1584	0.7512	0.8503	0.7588
0.0773	7.0	1323	0.1620	0.7149	0.8358	0.7553
0.06	8.0	1512	0.1588	0.7455	0.8533	0.7553
0.0635	9.0	1701	0.1716	0.7552	0.8634	0.7648
0.0433	10.0	1890	0.1780	0.7448	0.8459	0.7545
0.0436	11.0	2079	0.1694	0.7677	0.8528	0.7699
0.0317	12.0	2268	0.1769	0.7557	0.8516	0.7639
0.0324	13.0	2457	0.1790	0.7644	0.8584	0.7682
0.0288	14.0	2646	0.1832	0.7612	0.8567	0.7716

Framework versions

—Transformers 4.47.0
—Pytorch 2.5.1+cu121
—Datasets 3.2.0
—Tokenizers 0.21.0