bert-finetuned-ner

This model is a fine-tuned version of bert-base-cased on the wnut_17 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4362
• Precision: 0.5254
• Recall: 0.3160
• F1: 0.3947
• Accuracy: 0.9351
• Corporation Precision: 0.1833
• Corporation Recall: 0.1667
• Corporation F1: 0.1746
• Creative-work Precision: 0.4308
• Creative-work Recall: 0.1972
• Creative-work F1: 0.2705
• Group Precision: 0.3467
• Group Recall: 0.1576
• Group F1: 0.2167
• Location Precision: 0.55
• Location Recall: 0.44
• Location F1: 0.4889
• Person Precision: 0.8008
• Person Recall: 0.4592
• Person F1: 0.5837
• Product Precision: 0.1566
• Product Recall: 0.1024
• Product F1: 0.1238
• B-corporation Precision: 0.3256
• B-corporation Recall: 0.2121
• B-corporation F1: 0.2569
• B-creative-work Precision: 0.76
• B-creative-work Recall: 0.2676
• B-creative-work F1: 0.3958
• B-group Precision: 0.5179
• B-group Recall: 0.1758
• B-group F1: 0.2624
• B-location Precision: 0.6792
• B-location Recall: 0.48
• B-location F1: 0.5625
• B-person Precision: 0.8615
• B-person Recall: 0.4639
• B-person F1: 0.6030
• B-product Precision: 0.4468
• B-product Recall: 0.1654
• B-product F1: 0.2414
• I-corporation Precision: 0.2889
• I-corporation Recall: 0.2364
• I-corporation F1: 0.26
• I-creative-work Precision: 0.45
• I-creative-work Recall: 0.2093
• I-creative-work F1: 0.2857
• I-group Precision: 0.2549
• I-group Recall: 0.1150
• I-group F1: 0.1585
• I-location Precision: 0.5606
• I-location Recall: 0.3895
• I-location F1: 0.4596
• I-person Precision: 0.7564
• I-person Recall: 0.3512
• I-person F1: 0.4797
• I-product Precision: 0.1972
• I-product Recall: 0.1157
• I-product F1: 0.1458

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy	Corporation Precision	Corporation Recall	Corporation F1	Creative-work Precision	Creative-work Recall	Creative-work F1	Group Precision	Group Recall	Group F1	Location Precision	Location Recall	Location F1	Person Precision	Person Recall	Person F1	Product Precision	Product Recall	Product F1	B-corporation Precision	B-corporation Recall	B-corporation F1	B-creative-work Precision	B-creative-work Recall	B-creative-work F1	B-group Precision	B-group Recall	B-group F1	B-location Precision	B-location Recall	B-location F1	B-person Precision	B-person Recall	B-person F1	B-product Precision	B-product Recall	B-product F1	I-corporation Precision	I-corporation Recall	I-corporation F1	I-creative-work Precision	I-creative-work Recall	I-creative-work F1	I-group Precision	I-group Recall	I-group F1	I-location Precision	I-location Recall	I-location F1	I-person Precision	I-person Recall	I-person F1	I-product Precision	I-product Recall	I-product F1
No log	1.0	425	0.3879	0.5038	0.2484	0.3327	0.9296	0.0714	0.0455	0.0556	0.1429	0.0070	0.0134	0.1667	0.0909	0.1176	0.4583	0.3667	0.4074	0.7569	0.4499	0.5643	0.0556	0.0079	0.0138	0.3333	0.1364	0.1935	1.0	0.0282	0.0548	0.4722	0.1030	0.1692	0.6162	0.4067	0.4900	0.9037	0.4592	0.6090	0.5	0.0157	0.0305	0.1111	0.0545	0.0732	0.5	0.0155	0.0301	0.12	0.0796	0.0957	0.4595	0.3579	0.4024	0.7108	0.3512	0.4701	0.125	0.0165	0.0292
0.196	2.0	850	0.4338	0.5712	0.2864	0.3815	0.9328	0.2174	0.2273	0.2222	0.4762	0.1408	0.2174	0.35	0.0848	0.1366	0.5727	0.42	0.4846	0.7992	0.4452	0.5719	0.1463	0.0472	0.0714	0.3208	0.2576	0.2857	0.8065	0.1761	0.2890	0.6	0.0909	0.1579	0.7216	0.4667	0.5668	0.8807	0.4476	0.5935	0.6522	0.1181	0.2	0.2917	0.2545	0.2718	0.6	0.1860	0.2840	0.2857	0.0708	0.1135	0.5625	0.3789	0.4528	0.7566	0.3423	0.4713	0.1765	0.0496	0.0774
0.0785	3.0	1275	0.4362	0.5254	0.3160	0.3947	0.9351	0.1833	0.1667	0.1746	0.4308	0.1972	0.2705	0.3467	0.1576	0.2167	0.55	0.44	0.4889	0.8008	0.4592	0.5837	0.1566	0.1024	0.1238	0.3256	0.2121	0.2569	0.76	0.2676	0.3958	0.5179	0.1758	0.2624	0.6792	0.48	0.5625	0.8615	0.4639	0.6030	0.4468	0.1654	0.2414	0.2889	0.2364	0.26	0.45	0.2093	0.2857	0.2549	0.1150	0.1585	0.5606	0.3895	0.4596	0.7564	0.3512	0.4797	0.1972	0.1157	0.1458

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1