finetuned-roberta-base-10pct

cynthiachan/finetuned-roberta-base-10pct

finetuned-roberta-base-10pct is a token classification model from cynthiachan. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as mit.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

2% of all-time downloads

All-time downloads

385

Public

Repo size

993 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin496 MB · 99%

At a glance

Task: Token Classification
Library: transformers
License: mit
Model type: roberta
Access: Public
Created: Aug 29, 2022
Updated: Aug 30, 2022
SHA: 5d97f1e8

Try a prompt

Datasets

cynthiachan/FeedRef_10pct

Model card

From the Hugging Face model README

training

This model is a fine-tuned version of roberta-base on the cynthiachan/FeedRef_10pct dataset. It achieves the following results on the evaluation set:

Loss: 0.1033
Attackid Precision: 1.0
Attackid Recall: 1.0
Attackid F1: 1.0
Attackid Number: 6
Cve Precision: 1.0
Cve Recall: 1.0
Cve F1: 1.0
Cve Number: 11
Defenderthreat Precision: 0.0
Defenderthreat Recall: 0.0
Defenderthreat F1: 0.0
Defenderthreat Number: 2
Domain Precision: 0.8636
Domain Recall: 0.8261
Domain F1: 0.8444
Domain Number: 23
Email Precision: 1.0
Email Recall: 1.0
Email F1: 1.0
Email Number: 3
Filepath Precision: 0.8108
Filepath Recall: 0.9091
Filepath F1: 0.8571
Filepath Number: 165
Hostname Precision: 0.9231
Hostname Recall: 1.0
Hostname F1: 0.9600
Hostname Number: 12
Ipv4 Precision: 0.9167
Ipv4 Recall: 0.9167
Ipv4 F1: 0.9167
Ipv4 Number: 12
Md5 Precision: 0.875
Md5 Recall: 0.9423
Md5 F1: 0.9074
Md5 Number: 52
Sha1 Precision: 0.75
Sha1 Recall: 0.8571
Sha1 F1: 0.8000
Sha1 Number: 7
Sha256 Precision: 0.8
Sha256 Recall: 1.0
Sha256 F1: 0.8889
Sha256 Number: 44
Uri Precision: 0.0
Uri Recall: 0.0
Uri F1: 0.0
Uri Number: 1
Overall Precision: 0.8383
Overall Recall: 0.9201
Overall F1: 0.8773
Overall Accuracy: 0.9816

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: 5e-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: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Attackid Precision	Attackid Recall	Attackid F1	Attackid Number	Cve Precision	Cve Recall	Cve F1	Cve Number	Defenderthreat Number	Domain Precision	Domain Recall	Domain F1	Domain Number	Email Precision	Email Recall	Email F1	Email Number	Filepath Precision	Filepath Recall	Filepath F1	Filepath Number	Hostname Precision	Hostname Recall	Hostname F1	Hostname Number	Ipv4 Precision	Ipv4 Recall	Ipv4 F1	Ipv4 Number	Md5 Precision	Md5 Recall	Md5 F1	Md5 Number	Sha1 Precision	Sha1 Recall	Sha1 F1	Sha1 Number	Sha256 Precision	Sha256 Recall	Sha256 F1	Sha256 Number	Uri Number	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.4353	0.37	500	0.3525	0.0	0.0	0.0	6	0.0	0.0	0.0	11	2	0.0	0.0	0.0	23	0.0	0.0	0.0	3	0.3984	0.6182	0.4846	165	0.0714	0.3333	0.1176	12	0.0	0.0	0.0	12	0.8936	0.8077	0.8485	52	0.0	0.0	0.0	7	0.4937	0.8864	0.6341	44	1	0.4156	0.5533	0.4746	0.9459
0.2089	0.75	1000	0.1812	0.0	0.0	0.0	6	0.9	0.8182	0.8571	11	2	0.15	0.2609	0.1905	23	0.0	0.0	0.0	3	0.6432	0.7758	0.7033	165	0.0	0.0	0.0	12	0.6471	0.9167	0.7586	12	0.7143	0.8654	0.7826	52	0.0	0.0	0.0	7	0.5286	0.8409	0.6491	44	1	0.5315	0.6982	0.6036	0.9626
0.1453	1.12	1500	0.1374	0.75	0.5	0.6	6	0.9167	1.0	0.9565	11	2	0.5135	0.8261	0.6333	23	0.0	0.0	0.0	3	0.6863	0.8485	0.7588	165	0.7	0.5833	0.6364	12	0.6667	0.6667	0.6667	12	0.8167	0.9423	0.8750	52	0.0	0.0	0.0	7	0.8333	0.9091	0.8696	44	1	0.7048	0.8195	0.7579	0.9745
0.1277	1.5	2000	0.1400	1.0	1.0	1.0	6	1.0	1.0	1.0	11	2	0.7273	0.6957	0.7111	23	0.2	0.3333	0.25	3	0.7181	0.8182	0.7649	165	0.9167	0.9167	0.9167	12	0.7857	0.9167	0.8462	12	0.8167	0.9423	0.8750	52	0.0	0.0	0.0	7	0.8302	1.0	0.9072	44	1	0.7634	0.8402	0.8000	0.9735
0.1074	1.87	2500	0.1101	1.0	1.0	1.0	6	1.0	1.0	1.0	11	2	0.72	0.7826	0.7500	23	0.2857	0.6667	0.4	3	0.7554	0.8424	0.7966	165	0.8571	1.0	0.9231	12	0.8182	0.75	0.7826	12	0.9259	0.9615	0.9434	52	0.0	0.0	0.0	7	0.6833	0.9318	0.7885	44	1	0.7660	0.8521	0.8067	0.9762
0.0758	2.25	3000	0.1161	1.0	1.0	1.0	6	1.0	1.0	1.0	11	2	0.9091	0.8696	0.8889	23	0.5	0.6667	0.5714	3	0.8251	0.9152	0.8678	165	1.0	1.0	1.0	12	1.0	0.6667	0.8	12	0.9259	0.9615	0.9434	52	1.0	0.5714	0.7273	7	0.8958	0.9773	0.9348	44	1	0.8722	0.9083	0.8899	0.9814
0.064	2.62	3500	0.1275	1.0	1.0	1.0	6	0.8333	0.9091	0.8696	11	2	0.8947	0.7391	0.8095	23	1.0	1.0	1.0	3	0.8418	0.9030	0.8713	165	0.8571	1.0	0.9231	12	1.0	0.75	0.8571	12	0.9245	0.9423	0.9333	52	0.6667	0.5714	0.6154	7	0.8113	0.9773	0.8866	44	1	0.8580	0.8935	0.8754	0.9793
0.0522	3.0	4000	0.1033	1.0	1.0	1.0	6	1.0	1.0	1.0	11	2	0.8636	0.8261	0.8444	23	1.0	1.0	1.0	3	0.8108	0.9091	0.8571	165	0.9231	1.0	0.9600	12	0.9167	0.9167	0.9167	12	0.875	0.9423	0.9074	52	0.75	0.8571	0.8000	7	0.8	1.0	0.8889	44	1	0.8383	0.9201	0.8773	0.9816

Framework versions

Transformers 4.21.2
Pytorch 1.12.1+cu102
Datasets 2.4.0
Tokenizers 0.12.1

Task: Token Classification
Library: transformers
Type: roberta
License: mit
Created: Aug 29, 2022
Updated: Aug 30, 2022