roberta-base-finetuned-ner

lobrien001/roberta-base-finetuned-ner

roberta-base-finetuned-ner is a token classification model from lobrien001. 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

Public

Parameters

124M

154 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 10, 2024
Updated: Apr 24, 2024
SHA: cc073ff5

Try a prompt

Base models

Model card

From the Hugging Face model README

roberta-base-finetuned-ner

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

Loss: 1.1738
Precision: 0.6666
Recall: 0.7036
F1: 0.6846
Accuracy: 0.6664

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
No log	0.19	50	1.3378	0.2046	0.2159	0.2101	0.2062
No log	0.37	100	1.3271	0.2419	0.2553	0.2484	0.2431
No log	0.56	150	1.3164	0.2741	0.2893	0.2815	0.2753
No log	0.75	200	1.3061	0.3090	0.3261	0.3173	0.3100
No log	0.93	250	1.2965	0.3373	0.3560	0.3464	0.3381
No log	1.12	300	1.2872	0.3726	0.3932	0.3826	0.3734
No log	1.31	350	1.2783	0.4027	0.4251	0.4136	0.4034
No log	1.49	400	1.2697	0.4327	0.4567	0.4444	0.4333
No log	1.68	450	1.2613	0.4565	0.4818	0.4688	0.4569
1.2812	1.87	500	1.2537	0.4768	0.5032	0.4897	0.4774
1.2812	2.05	550	1.2464	0.4971	0.5247	0.5105	0.4975
1.2812	2.24	600	1.2394	0.5185	0.5472	0.5324	0.5189
1.2812	2.43	650	1.2328	0.5341	0.5637	0.5485	0.5345
1.2812	2.61	700	1.2266	0.5480	0.5784	0.5628	0.5484
1.2812	2.8	750	1.2208	0.5630	0.5942	0.5782	0.5634
1.2812	2.99	800	1.2153	0.5771	0.6091	0.5927	0.5773
1.2812	3.17	850	1.2100	0.5903	0.6230	0.6062	0.5905
1.2812	3.36	900	1.2051	0.5993	0.6325	0.6155	0.5995
1.2812	3.54	950	1.2008	0.6128	0.6468	0.6294	0.6128
1.2012	3.73	1000	1.1967	0.6202	0.6546	0.6370	0.6200
1.2012	3.92	1050	1.1931	0.6264	0.6611	0.6433	0.6262
1.2012	4.1	1100	1.1896	0.6352	0.6704	0.6523	0.6350
1.2012	4.29	1150	1.1865	0.6426	0.6782	0.6599	0.6424
1.2012	4.48	1200	1.1838	0.6467	0.6825	0.6641	0.6465
1.2012	4.66	1250	1.1814	0.6529	0.6890	0.6705	0.6526
1.2012	4.85	1300	1.1794	0.6568	0.6932	0.6745	0.6565
1.2012	5.04	1350	1.1777	0.6598	0.6964	0.6776	0.6596
1.2012	5.22	1400	1.1763	0.6617	0.6984	0.6795	0.6615
1.2012	5.41	1450	1.1752	0.6635	0.7003	0.6814	0.6633
1.1618	5.6	1500	1.1744	0.6652	0.7020	0.6831	0.6650
1.1618	5.78	1550	1.1740	0.6660	0.7029	0.6839	0.6658
1.1618	5.97	1600	1.1738	0.6666	0.7036	0.6846	0.6664

Framework versions

Transformers 4.36.2
Pytorch 2.2.1+cu121
Datasets 2.19.0
Tokenizers 0.15.2

Task: Token Classification
Library: transformers
Type: roberta
License: mit
Created: Apr 10, 2024
Updated: Apr 24, 2024