bert-finetuned-ner

This model is a fine-tuned version of BAAI/bge-small-en-v1.5 on an unknown dataset. It achieves the following results on the evaluation set:

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 20

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.9570	1.0	625	0.3470	0.7751	0.8251	0.7993	0.9634
0.3367	2.0	1250	0.2192	0.8630	0.8957	0.8790	0.9765
0.2215	3.0	1875	0.1803	0.8666	0.9100	0.8878	0.9784
0.1293	4.0	2500	0.1673	0.8847	0.9177	0.9009	0.9809
0.1005	5.0	3125	0.1636	0.8974	0.9217	0.9094	0.9814
0.0790	6.0	3750	0.1583	0.8963	0.9224	0.9092	0.9818
0.0720	7.0	4375	0.1656	0.8986	0.9261	0.9121	0.9813
0.0524	8.0	5000	0.1709	0.9035	0.9246	0.9139	0.9823
0.0454	9.0	5625	0.1695	0.9051	0.9280	0.9164	0.9825
0.0409	10.0	6250	0.1735	0.9018	0.9285	0.9149	0.9819
0.0385	11.0	6875	0.1768	0.9016	0.9256	0.9135	0.9822
0.0319	12.0	7500	0.1800	0.9068	0.9305	0.9185	0.9824
0.0278	13.0	8125	0.1821	0.9074	0.9290	0.9181	0.9827
0.0236	14.0	8750	0.1793	0.9100	0.9290	0.9194	0.9830
0.0230	15.0	9375	0.1850	0.9038	0.9283	0.9159	0.9827