electra-base-discriminator-finetuned-ner-cadec

mireiaplalis/electra-base-discriminator-finetuned-ner-cadec

electra-base-discriminator-finetuned-ner-cadec is a token classification model from mireiaplalis. 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

21% of all-time downloads

All-time downloads

Public

Parameters

109M

4.4 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors436 MB · 100%

At a glance

Task: Token Classification
Library: transformers
License: apache-2.0
Model type: electra
Access: Public
Created: Dec 6, 2023
Updated: Dec 6, 2023
SHA: 1c3239cf

Try a prompt

Base models

google/electra-base-discriminator

Model card

From the Hugging Face model README

electra-base-discriminator-finetuned-ner-cadec

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

Loss: 0.2903
Precision: 0.6312
Recall: 0.6966
F1: 0.6623
Accuracy: 0.9274
Adr Precision: 0.6070
Adr Recall: 0.6972
Adr F1: 0.6490
Disease Precision: 0.125
Disease Recall: 0.1579
Disease F1: 0.1395
Drug Precision: 0.9464
Drug Recall: 0.9636
Drug F1: 0.9550
Finding Precision: 0.1961
Finding Recall: 0.2222
Finding F1: 0.2083
Symptom Precision: 0.4
Symptom Recall: 0.2222
Symptom F1: 0.2857
B-adr Precision: 0.7540
B-adr Recall: 0.8119
B-adr F1: 0.7819
B-disease Precision: 0.1667
B-disease Recall: 0.1579
B-disease F1: 0.1622
B-drug Precision: 0.9760
B-drug Recall: 0.9879
B-drug F1: 0.9819
B-finding Precision: 0.275
B-finding Recall: 0.2444
B-finding F1: 0.2588
B-symptom Precision: 0.5
B-symptom Recall: 0.24
B-symptom F1: 0.3243
I-adr Precision: 0.6175
I-adr Recall: 0.7020
I-adr F1: 0.6570
I-disease Precision: 0.15
I-disease Recall: 0.2308
I-disease F1: 0.1818
I-drug Precision: 0.9521
I-drug Recall: 0.9636
I-drug F1: 0.9578
I-finding Precision: 0.1622
I-finding Recall: 0.1875
I-finding F1: 0.1739
I-symptom Precision: 0.5
I-symptom Recall: 0.15
I-symptom F1: 0.2308
Macro Avg F1: 0.4710
Weighted Avg F1: 0.7273

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

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy	Adr Precision	Adr Recall	Adr F1	Disease Precision	Disease Recall	Disease F1	Drug Precision	Drug Recall	Drug F1	Finding Precision	Finding Recall	Finding F1	Symptom Precision	Symptom Recall	Symptom F1	B-adr Precision	B-adr Recall	B-adr F1	B-disease Precision	B-disease Recall	B-disease F1	B-drug Precision	B-drug Recall	B-drug F1	B-finding Precision	B-finding Recall	B-finding F1	B-symptom Precision	B-symptom Recall	B-symptom F1	I-adr Precision	I-adr Recall	I-adr F1	I-disease Precision	I-disease Recall	I-disease F1	I-drug Precision	I-drug Recall	I-drug F1	I-finding Precision	I-finding Recall	I-finding F1	I-symptom Precision	I-symptom Recall	I-symptom F1	Macro Avg F1	Weighted Avg F1
No log	1.0	127	0.2748	0.5316	0.6617	0.5895	0.9167	0.4583	0.6862	0.5496	0.0	0.0	0.0	0.8619	0.9455	0.9017	0.0	0.0	0.0	0.0	0.0	0.0	0.6301	0.8369	0.7189	0.0	0.0	0.0	0.9527	0.9758	0.9641	0.0	0.0	0.0	0.0	0.0	0.0	0.4811	0.6755	0.5620	0.0	0.0	0.0	0.8674	0.9515	0.9075	0.0	0.0	0.0	0.0	0.0	0.0	0.3152	0.6433
No log	2.0	254	0.2396	0.5670	0.6604	0.6101	0.9205	0.5198	0.6752	0.5874	0.0625	0.1053	0.0784	0.9349	0.9576	0.9461	0.0417	0.0222	0.0290	0.0	0.0	0.0	0.6992	0.8119	0.7513	0.3077	0.2105	0.25	0.9759	0.9818	0.9789	0.3333	0.0444	0.0784	0.0	0.0	0.0	0.5524	0.6865	0.6122	0.0690	0.1538	0.0952	0.9405	0.9576	0.9489	0.25	0.1875	0.2143	0.0	0.0	0.0	0.3929	0.6881
No log	3.0	381	0.2432	0.6237	0.6767	0.6491	0.9273	0.5965	0.6972	0.6430	0.1163	0.2632	0.1613	0.9006	0.9333	0.9167	0.1667	0.0667	0.0952	0.0	0.0	0.0	0.7559	0.8023	0.7784	0.1786	0.2632	0.2128	0.9702	0.9879	0.9790	0.2667	0.0889	0.1333	0.0	0.0	0.0	0.6216	0.7108	0.6632	0.1951	0.6154	0.2963	0.9112	0.9333	0.9222	0.1429	0.0312	0.0513	0.0	0.0	0.0	0.4036	0.7100
0.2876	4.0	508	0.2490	0.6259	0.6829	0.6531	0.9254	0.5981	0.6936	0.6423	0.0833	0.1053	0.0930	0.9286	0.9455	0.9369	0.2083	0.2222	0.2151	0.5	0.0370	0.0690	0.7425	0.8023	0.7712	0.1905	0.2105	0.2	0.9760	0.9879	0.9819	0.3226	0.2222	0.2632	0.5	0.04	0.0741	0.6112	0.6976	0.6515	0.1429	0.1538	0.1481	0.9341	0.9455	0.9398	0.2368	0.2812	0.2571	0.0	0.0	0.0	0.4287	0.7145
0.2876	5.0	635	0.2609	0.6175	0.6854	0.6497	0.9255	0.5915	0.6936	0.6385	0.0851	0.2105	0.1212	0.9412	0.9697	0.9552	0.1481	0.0889	0.1111	0.5	0.1111	0.1818	0.7336	0.8138	0.7716	0.125	0.2105	0.1569	0.9760	0.9879	0.9819	0.2174	0.1111	0.1471	0.5	0.12	0.1935	0.6109	0.6932	0.6494	0.1860	0.6154	0.2857	0.9467	0.9697	0.9581	0.1	0.0312	0.0476	0.0	0.0	0.0	0.4192	0.7105
0.2876	6.0	762	0.2648	0.6192	0.6941	0.6545	0.9254	0.5938	0.7028	0.6437	0.1111	0.1579	0.1304	0.9290	0.9515	0.9401	0.2083	0.2222	0.2151	0.3333	0.1111	0.1667	0.7388	0.8196	0.7771	0.1579	0.1579	0.1579	0.9702	0.9879	0.9790	0.3077	0.2667	0.2857	0.5556	0.2	0.2941	0.6120	0.6998	0.6529	0.1304	0.2308	0.1667	0.9345	0.9515	0.9429	0.1389	0.1562	0.1471	0.0	0.0	0.0	0.4403	0.7187
0.2876	7.0	889	0.2722	0.6435	0.6941	0.6679	0.9280	0.6141	0.7009	0.6547	0.1364	0.1579	0.1463	0.9345	0.9515	0.9429	0.2326	0.2222	0.2273	0.4444	0.1481	0.2222	0.7567	0.8177	0.7860	0.1579	0.1579	0.1579	0.9760	0.9879	0.9819	0.2973	0.2444	0.2683	0.5	0.16	0.2424	0.6206	0.6932	0.6548	0.1875	0.2308	0.2069	0.9401	0.9515	0.9458	0.2059	0.2188	0.2121	1.0	0.1	0.1818	0.4638	0.7260
0.1075	8.0	1016	0.2843	0.6282	0.6941	0.6595	0.9253	0.5956	0.6917	0.6401	0.1364	0.1579	0.1463	0.9464	0.9636	0.9550	0.2245	0.2444	0.2340	0.4615	0.2222	0.3	0.7407	0.8061	0.7721	0.1667	0.1579	0.1622	0.9760	0.9879	0.9819	0.3158	0.2667	0.2892	0.5	0.24	0.3243	0.5950	0.6777	0.6336	0.1579	0.2308	0.1875	0.9578	0.9636	0.9607	0.1579	0.1875	0.1714	0.75	0.15	0.2500	0.4733	0.7181
0.1075	9.0	1143	0.2876	0.6353	0.6916	0.6623	0.9266	0.5968	0.6899	0.64	0.15	0.1579	0.1538	0.9464	0.9636	0.9550	0.2439	0.2222	0.2326	0.4615	0.2222	0.3	0.7381	0.8061	0.7706	0.1667	0.1579	0.1622	0.9760	0.9879	0.9819	0.3143	0.2444	0.2750	0.5	0.24	0.3243	0.6023	0.6821	0.6398	0.1875	0.2308	0.2069	0.9578	0.9636	0.9607	0.1875	0.1875	0.1875	1.0	0.2	0.3333	0.4842	0.7207
0.1075	10.0	1270	0.2903	0.6312	0.6966	0.6623	0.9274	0.6070	0.6972	0.6490	0.125	0.1579	0.1395	0.9464	0.9636	0.9550	0.1961	0.2222	0.2083	0.4	0.2222	0.2857	0.7540	0.8119	0.7819	0.1667	0.1579	0.1622	0.9760	0.9879	0.9819	0.275	0.2444	0.2588	0.5	0.24	0.3243	0.6175	0.7020	0.6570	0.15	0.2308	0.1818	0.9521	0.9636	0.9578	0.1622	0.1875	0.1739	0.5	0.15	0.2308	0.4710	0.7273

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

Task: Token Classification
Library: transformers
Type: electra
License: apache-2.0
Created: Dec 6, 2023
Updated: Dec 6, 2023