jobbert-base-cased-ner

This model is a fine-tuned version of jjzha/jobbert-base-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3789
• Job Title precision: 0.7916
• Job Title recall: 0.8721
• Job Title f1: 0.8299
• Loc precision: 0.8572
• Loc recall: 0.9506
• Loc f1: 0.9015
• Org precision: 0.6727
• Org recall: 0.7458
• Org f1: 0.7074
• Misc precision: 0.6893
• Misc recall: 0.6587
• Misc f1: 0.6736
• Precision: 0.7772
• Recall: 0.8551
• F1: 0.8143
• Accuracy: 0.8680

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	Job Title precision	Job Title recall	Job Title f1	Loc precision	Loc recall	Loc f1	Org precision	Org recall	Org f1	Misc precision	Misc recall	Misc f1	Precision	Recall	F1	Accuracy
No log	1.0	308	0.3896	0.7827	0.8394	0.8101	0.8813	0.8856	0.8835	0.6865	0.7151	0.7005	0.6730	0.6041	0.6367	0.7800	0.8148	0.7970	0.8577
0.4672	2.0	616	0.3789	0.7916	0.8721	0.8299	0.8572	0.9506	0.9015	0.6727	0.7458	0.7074	0.6893	0.6587	0.6736	0.7772	0.8551	0.8143	0.8680
0.4672	3.0	924	0.4067	0.7800	0.8876	0.8304	0.8560	0.9443	0.8980	0.6928	0.7026	0.6977	0.6006	0.7440	0.6646	0.7730	0.8549	0.8119	0.8651

Framework versions

• Transformers 4.28.1
• Pytorch 1.7.1+cu110
• Datasets 2.12.0
• Tokenizers 0.13.2