bert-base-cased-finetuned-ner

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

• Loss: nan
• Precision: 0.7641
• Recall: 0.8182
• F1: 0.7902
• Accuracy: 0.9615

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
No log	1.0	432	nan	0.6807	0.7773	0.7258	0.9450
0.3019	2.0	864	nan	0.7244	0.7725	0.7476	0.9531
0.0871	3.0	1296	nan	0.7352	0.8192	0.7749	0.9571
0.0527	4.0	1728	nan	0.7455	0.7864	0.7654	0.9557
0.031	5.0	2160	nan	0.7334	0.7976	0.7642	0.9544
0.0223	6.0	2592	nan	0.7703	0.8343	0.8010	0.9624
0.0171	7.0	3024	nan	0.7279	0.8119	0.7676	0.9569
0.0171	8.0	3456	nan	0.7609	0.8067	0.7831	0.9613
0.012	9.0	3888	nan	0.7585	0.8152	0.7858	0.9608
0.0097	10.0	4320	nan	0.7641	0.8182	0.7902	0.9615

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0