device_recalls_ner_baseline

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

• Loss: 1.0010
• Precision: 0.5161
• Recall: 0.5087
• F1: 0.5124
• Accuracy: 0.7492

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	101	0.6541	0.4257	0.3396	0.3778	0.6959
No log	2.0	202	0.5924	0.4803	0.4754	0.4779	0.7429
No log	3.0	303	0.6068	0.4826	0.5	0.4911	0.7283
No log	4.0	404	0.6778	0.4350	0.5173	0.4726	0.7079
0.501	5.0	505	0.7109	0.4876	0.5101	0.4986	0.7359
0.501	6.0	606	0.7291	0.4929	0.5043	0.4986	0.7448
0.501	7.0	707	0.8655	0.5338	0.4798	0.5053	0.7537
0.501	8.0	808	0.8715	0.5055	0.5275	0.5163	0.7460
0.501	9.0	909	1.0034	0.5027	0.5390	0.5202	0.7467
0.1555	10.0	1010	1.0010	0.5161	0.5087	0.5124	0.7492

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1