finetuned-electra-base-10pct

cynthiachan/finetuned-electra-base-10pct

finetuned-electra-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 apache-2.0.

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

Downloads · 30 days

2% of all-time downloads

All-time downloads

350

Public

Repo size

871 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin436 MB · 100%

At a glance

Task: Token Classification
Library: transformers
License: apache-2.0
Model type: electra
Access: Public
Created: Aug 30, 2022
Updated: Aug 30, 2022
SHA: eb1ee48e

Try a prompt

Datasets

cynthiachan/FeedRef_10pct

Model card

From the Hugging Face model README

training

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

Loss: 0.1520
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: 0.6154
Domain Recall: 0.6957
Domain F1: 0.6531
Domain Number: 23
Email Precision: 0.5
Email Recall: 0.6667
Email F1: 0.5714
Email Number: 3
Filepath Precision: 0.7010
Filepath Recall: 0.8242
Filepath F1: 0.7577
Filepath Number: 165
Hostname Precision: 0.9231
Hostname Recall: 1.0
Hostname F1: 0.9600
Hostname Number: 12
Ipv4 Precision: 0.7143
Ipv4 Recall: 0.8333
Ipv4 F1: 0.7692
Ipv4 Number: 12
Md5 Precision: 0.6528
Md5 Recall: 0.9038
Md5 F1: 0.7581
Md5 Number: 52
Sha1 Precision: 0.0
Sha1 Recall: 0.0
Sha1 F1: 0.0
Sha1 Number: 7
Sha256 Precision: 0.7692
Sha256 Recall: 0.9091
Sha256 F1: 0.8333
Sha256 Number: 44
Uri Precision: 0.0
Uri Recall: 0.0
Uri F1: 0.0
Uri Number: 1
Overall Precision: 0.6897
Overall Recall: 0.8284
Overall F1: 0.7527
Overall Accuracy: 0.9589

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 Number	Sha256 Precision	Sha256 Recall	Sha256 F1	Sha256 Number	Uri Number	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.5093	0.37	500	0.3512	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	0.2024	0.5091	0.2897	165	0.0	0.0	0.0	12	0.0	0.0	0.0	12	0.1724	0.4808	0.2538	52	7	0.3797	0.6818	0.4878	44	1	0.1844	0.4112	0.2546	0.9163
0.2742	0.75	1000	0.2719	0.0	0.0	0.0	6	0.0	0.0	0.0	11	2	0.4444	0.5217	0.48	23	0.0	0.0	0.0	3	0.4211	0.5333	0.4706	165	0.1111	0.25	0.1538	12	0.5	0.8333	0.625	12	0.6290	0.75	0.6842	52	7	0.4444	0.8182	0.5760	44	1	0.4322	0.5562	0.4864	0.9340
0.2072	1.12	1500	0.2008	0.0	0.0	0.0	6	0.2308	0.2727	0.2500	11	2	0.6842	0.5652	0.6190	23	0.0	0.0	0.0	3	0.4885	0.7758	0.5995	165	0.7857	0.9167	0.8462	12	0.75	0.75	0.75	12	0.6026	0.9038	0.7231	52	7	0.5970	0.9091	0.7207	44	1	0.5363	0.7426	0.6228	0.9484
0.1861	1.5	2000	0.2101	0.0	0.0	0.0	6	0.9091	0.9091	0.9091	11	2	0.5926	0.6957	0.6400	23	0.5	0.3333	0.4	3	0.6345	0.7576	0.6906	165	0.7333	0.9167	0.8148	12	0.8182	0.75	0.7826	12	0.6618	0.8654	0.75	52	7	0.525	0.9545	0.6774	44	1	0.6181	0.7663	0.6843	0.9495
0.1888	1.87	2500	0.1689	1.0	1.0	1.0	6	0.8182	0.8182	0.8182	11	2	0.6818	0.6522	0.6667	23	0.0	0.0	0.0	3	0.5806	0.7636	0.6597	165	0.8462	0.9167	0.8800	12	0.8182	0.75	0.7826	12	0.6486	0.9231	0.7619	52	7	0.6667	0.8636	0.7525	44	1	0.6329	0.7751	0.6968	0.9487
0.1409	2.25	3000	0.1520	1.0	1.0	1.0	6	1.0	1.0	1.0	11	2	0.6154	0.6957	0.6531	23	0.5	0.6667	0.5714	3	0.7010	0.8242	0.7577	165	0.9231	1.0	0.9600	12	0.7143	0.8333	0.7692	12	0.6528	0.9038	0.7581	52	7	0.7692	0.9091	0.8333	44	1	0.6897	0.8284	0.7527	0.9589
0.1248	2.62	3500	0.1716	0.8571	1.0	0.9231	6	1.0	1.0	1.0	11	2	0.84	0.9130	0.8750	23	0.6667	0.6667	0.6667	3	0.8155	0.8303	0.8228	165	0.8571	1.0	0.9231	12	0.75	1.0	0.8571	12	0.7031	0.8654	0.7759	52	7	0.7593	0.9318	0.8367	44	1	0.7928	0.8491	0.82	0.9583
0.1073	3.0	4000	0.1532	0.8571	1.0	0.9231	6	1.0	1.0	1.0	11	2	0.84	0.9130	0.8750	23	0.6667	0.6667	0.6667	3	0.7705	0.8545	0.8103	165	0.8571	1.0	0.9231	12	0.7059	1.0	0.8276	12	0.7313	0.9423	0.8235	52	7	0.7241	0.9545	0.8235	44	1	0.7688	0.8757	0.8188	0.9618

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: electra
License: apache-2.0
Created: Aug 30, 2022
Updated: Aug 30, 2022