bert-base-uncased-finetuned-ner

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1691
• Precision: 0.9011
• Recall: 0.8913
• F1: 0.8962
• Accuracy: 0.9696

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	13	1.3502	0.125	0.0217	0.0370	0.7293
No log	2.0	26	0.8543	0.2432	0.0978	0.1395	0.8065
No log	3.0	39	0.5831	0.4556	0.4457	0.4505	0.8652
No log	4.0	52	0.4247	0.6495	0.6848	0.6667	0.9185
No log	5.0	65	0.3273	0.7474	0.7717	0.7594	0.95
No log	6.0	78	0.2706	0.8021	0.8370	0.8191	0.9587
No log	7.0	91	0.2278	0.8804	0.8804	0.8804	0.9663
No log	8.0	104	0.2166	0.8901	0.8804	0.8852	0.9663
No log	9.0	117	0.2013	0.8804	0.8804	0.8804	0.9663
No log	10.0	130	0.1881	0.8817	0.8913	0.8865	0.9674
No log	11.0	143	0.1835	0.8817	0.8913	0.8865	0.9674
No log	12.0	156	0.1754	0.9011	0.8913	0.8962	0.9696
No log	13.0	169	0.1740	0.9011	0.8913	0.8962	0.9696
No log	14.0	182	0.1676	0.9011	0.8913	0.8962	0.9696
No log	15.0	195	0.1660	0.9011	0.8913	0.8962	0.9696
No log	16.0	208	0.1678	0.9011	0.8913	0.8962	0.9696
No log	17.0	221	0.1692	0.9011	0.8913	0.8962	0.9696
No log	18.0	234	0.1701	0.9011	0.8913	0.8962	0.9696
No log	19.0	247	0.1692	0.9011	0.8913	0.8962	0.9696
No log	20.0	260	0.1691	0.9011	0.8913	0.8962	0.9696

Framework versions

• Transformers 4.40.2
• Pytorch 2.3.0+cpu
• Datasets 2.19.1
• Tokenizers 0.19.1