Modelpublic

sms112/euk_roberta_base_essentiality_Network

sourceHugging Facemitupdated 8mo agoView on Hugging Face

0likes5downloads

Model Card

eukrobertabaseessentialityNetwork

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

—Loss: 0.4432
—Accuracy: 0.8
—Precision: 0.7774
—Recall: 0.8409
—F1: 0.8079

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: 50
—evalbatchsize: 50
—seed: 42
—gradientaccumulationsteps: 4
—totaltrainbatch_size: 200
—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: 10
—mixedprecisiontraining: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	57	0.6660	0.7275	0.7839	0.6286	0.6977
No log	2.0	114	0.4785	0.7684	0.7575	0.7898	0.7733
No log	3.0	171	0.4713	0.7861	0.7676	0.8210	0.7934
No log	4.0	228	0.4672	0.7872	0.7625	0.8345	0.7969
No log	5.0	285	0.4651	0.7829	0.7586	0.8303	0.7928
No log	6.0	342	0.4509	0.7890	0.7724	0.8196	0.7953
No log	7.0	399	0.4486	0.7918	0.7811	0.8111	0.7958
No log	8.0	456	0.4441	0.8	0.7760	0.8438	0.8084
1.9510	9.0	513	0.4432	0.8004	0.7776	0.8416	0.8083
1.9510	10.0	570	0.4428	0.8004	0.7835	0.8303	0.8062

Framework versions

—Transformers 5.0.0
—Pytorch 2.9.0+cu128
—Datasets 4.0.0
—Tokenizers 0.22.2