Modelpublic

AnonymousCS/xlmr_norwegian_immigration3

sourceHugging Facemitupdated 1y agoView on Hugging Face

0likes6downloads

Model Card

xlmrnorwegianimmigration3

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

—Loss: 0.3159
—Accuracy: 0.9091
—1-f1: 0.8571
—1-recall: 0.8182
—1-precision: 0.9
—Balanced Acc: 0.8864

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: 1e-05
—trainbatchsize: 128
—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
—num_epochs: 15
—mixedprecisiontraining: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	1-f1	1-recall	1-precision	Balanced Acc
0.1747	1.0	2	0.3069	0.9091	0.8571	0.8182	0.9	0.8864
0.2707	2.0	4	0.2797	0.9091	0.8571	0.8182	0.9	0.8864
0.1527	3.0	6	0.2621	0.8788	0.8	0.7273	0.8889	0.8409
0.1886	4.0	8	0.2600	0.8788	0.8	0.7273	0.8889	0.8409
0.1	5.0	10	0.2818	0.9091	0.8571	0.8182	0.9	0.8864
0.0835	6.0	12	0.3159	0.9091	0.8571	0.8182	0.9	0.8864

Framework versions

—Transformers 4.56.0.dev0
—Pytorch 2.8.0+cu126
—Datasets 4.0.0
—Tokenizers 0.21.4