RoBERTa-CyNER – AI Model by Cyber-ThreaD | AlphaNeural AI

You can deploy this model and start earning money today!

Cyber-ThreaD/
RoBERTa-CyNER

like

0

token-classification

generated_from_trainer

FacebookAI/roberta-base

autotrain_compatible

endpoints_compatible

Views

No views yet

dnrti_our

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

Loss: 0.0737
Precision: 0.7870
Recall: 0.7880
F1: 0.7875
Accuracy: 0.9836

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
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.13	1.42	500	0.0886	0.7138	0.7548	0.7337	0.9796
0.0421	2.84	1000	0.0737	0.7870	0.7880	0.7875	0.9836
0.0249	4.26	1500	0.0855	0.7655	0.7714	0.7684	0.9822
0.0167	5.68	2000	0.0946	0.7554	0.8008	0.7774	0.9826
0.0104	7.1	2500	0.0976	0.7540	0.7829	0.7682	0.9820
0.0066	8.52	3000	0.1024	0.7742	0.8059	0.7897	0.9836
0.0044	9.94	3500	0.1069	0.7764	0.7982	0.7872	0.9833

Framework versions

Transformers 4.36.0.dev0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1