Modelpublic

phunganhsang/Revision_DomainPho_LexClsXLM_MetaXLM_Data11k

sourceHugging Faceagpl-3.0updated 7mo agoView on Hugging Face

0likes

Model Card

RevisionDomainPhoLexClsXLMMetaXLMData11k

This model is a fine-tuned version of phunganhsang/Revision_Pho_Lexical_46kClsXlm on an unknown dataset. It achieves the following results on the evaluation set:

—Loss: 0.5446
—Accuracy: 0.8529
—F1: 0.8483

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 OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
—lrschedulertype: linear
—num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.2778	100	0.4087	0.8592	0.8542
No log	0.5556	200	0.3482	0.8582	0.8526
No log	0.8333	300	0.4136	0.8428	0.8389
0.2395	1.1111	400	0.4193	0.8405	0.8364
0.2395	1.3889	500	0.4510	0.8471	0.8429
0.2395	1.6667	600	0.4770	0.8457	0.8412
0.2395	1.9444	700	0.3986	0.8560	0.8510
0.1545	2.2222	800	0.4249	0.8583	0.8529
0.1545	2.5	900	0.5015	0.8465	0.8422
0.1545	2.7778	1000	0.5615	0.8455	0.8412
0.1144	3.0556	1100	0.5518	0.8390	0.8352
0.1144	3.3333	1200	0.5011	0.8574	0.8527
0.1144	3.6111	1300	0.5309	0.8493	0.8449
0.1144	3.8889	1400	0.4946	0.8588	0.8541
0.0799	4.1667	1500	0.4780	0.8608	0.8560
0.0799	4.4444	1600	0.5148	0.8594	0.8547
0.0799	4.7222	1700	0.5721	0.8465	0.8422
0.0546	5.0	1800	0.5446	0.8529	0.8483

Framework versions

—Transformers 5.3.0
—Pytorch 2.9.0+cu126
—Datasets 4.0.0
—Tokenizers 0.22.2