roberta-base-finetuned-ner

Sevixdd/roberta-base-finetuned-ner

roberta-base-finetuned-ner is a token classification model from Sevixdd. 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

27% of all-time downloads

All-time downloads

Public

Parameters

124M

6.5 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors496 MB · 99%

At a glance

Task: Token Classification
Library: transformers
License: mit
Model type: roberta
Access: Public
Created: Apr 26, 2024
Updated: Sep 19, 2026
SHA: 8301e097

Try a prompt

Base models

Spaces

Model card

From the Hugging Face model README

roberta-base-finetuned-ner

This model is a fine-tuned version of roberta-base on PLOD-CW and PLOD-filtered datasets. It achieves the following results on the evaluation set:

Loss: 0.1424
Precision: 0.9657
Recall: 0.9608
F1: 0.9633
Accuracy: 0.9594

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: 4
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.1562	0.25	7000	0.1457	0.9547	0.9376	0.9460	0.9407
0.1375	0.5	14000	0.1472	0.9569	0.9414	0.9491	0.9442
0.1371	0.75	21000	0.1331	0.9570	0.9480	0.9524	0.9482
0.1325	0.99	28000	0.1216	0.9603	0.9487	0.9545	0.9501
0.1176	1.24	35000	0.1307	0.9617	0.9468	0.9542	0.9496
0.1191	1.49	42000	0.1230	0.9596	0.9521	0.9558	0.9516
0.116	1.74	49000	0.1341	0.9634	0.9510	0.9572	0.9528
0.1136	1.99	56000	0.1179	0.9582	0.9560	0.9571	0.9527
0.0947	2.24	63000	0.1426	0.9560	0.9544	0.9552	0.9512
0.1009	2.49	70000	0.1155	0.9644	0.9549	0.9596	0.9556
0.0972	2.73	77000	0.1282	0.9654	0.9543	0.9598	0.9556
0.0959	2.98	84000	0.1216	0.9642	0.9566	0.9603	0.9564
0.0847	3.23	91000	0.1222	0.9645	0.9580	0.9612	0.9573
0.0817	3.48	98000	0.1275	0.9648	0.9575	0.9611	0.9571
0.089	3.73	105000	0.1260	0.9661	0.9577	0.9619	0.9580
0.0826	3.98	112000	0.1188	0.9641	0.9593	0.9617	0.9577
0.072	4.23	119000	0.1361	0.9645	0.9598	0.9621	0.9581
0.0648	4.47	126000	0.1377	0.9640	0.9601	0.9620	0.9581
0.0665	4.72	133000	0.1352	0.9655	0.9596	0.9625	0.9586
0.0692	4.97	140000	0.1392	0.9668	0.9593	0.9631	0.9593
0.0545	5.22	147000	0.1470	0.9663	0.9602	0.9633	0.9595
0.0549	5.47	154000	0.1442	0.9652	0.9611	0.9631	0.9593
0.0563	5.72	161000	0.1454	0.9657	0.9609	0.9633	0.9594
0.0647	5.97	168000	0.1424	0.9657	0.9608	0.9633	0.9594

Framework versions

Transformers 4.36.2
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2

Task: Token Classification
Library: transformers
Type: roberta
License: mit
Created: Apr 26, 2024
Updated: Sep 19, 2026