Modelpublic

sms112/euk_roberta_large_essentiality_Network

sourceHugging Facemitupdated 7mo agoView on Hugging Face

0likes5downloads

Model Card

eukrobertalargeessentialityNetwork

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

—Loss: 0.4307
—Accuracy: 0.8210
—Precision: 0.7886
—Recall: 0.8771
—F1: 0.8305

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: 60
—evalbatchsize: 60
—seed: 42
—gradientaccumulationsteps: 4
—totaltrainbatch_size: 240
—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	Precision	Recall	F1
No log	1.0	47	0.5793	0.7023	0.7021	0.7031	0.7026
No log	2.0	94	0.4761	0.7812	0.7861	0.7727	0.7794
No log	3.0	141	0.4792	0.7769	0.7506	0.8295	0.7881
No log	4.0	188	0.4617	0.7822	0.7641	0.8168	0.7896
No log	5.0	235	0.4748	0.7769	0.7393	0.8558	0.7933
No log	6.0	282	0.4401	0.7961	0.7773	0.8303	0.8029
No log	7.0	329	0.4273	0.7968	0.7828	0.8217	0.8018
No log	8.0	376	0.4282	0.8099	0.7825	0.8587	0.8188
No log	9.0	423	0.4242	0.8099	0.8	0.8267	0.8131
No log	10.0	470	0.4248	0.8089	0.7908	0.8402	0.8147
1.8645	11.0	517	0.4183	0.8139	0.8095	0.8210	0.8152
1.8645	12.0	564	0.4206	0.8195	0.7988	0.8544	0.8257
1.8645	13.0	611	0.4225	0.8178	0.7985	0.8501	0.8235
1.8645	14.0	658	0.4307	0.8210	0.7886	0.8771	0.8305
1.8645	15.0	705	0.4259	0.8163	0.8016	0.8409	0.8208

Framework versions

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