learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 15

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.4793	1.0	625	0.1832	0.7331	0.7711	0.7516	0.9571
0.1758	2.0	1250	0.1122	0.8628	0.8955	0.8789	0.9760
0.115	3.0	1875	0.0933	0.8581	0.9095	0.8830	0.9778
0.0664	4.0	2500	0.0860	0.8858	0.9192	0.9022	0.9806
0.0521	5.0	3125	0.0810	0.8911	0.9217	0.9062	0.9812
0.0417	6.0	3750	0.0780	0.8988	0.9207	0.9096	0.9814
0.0389	7.0	4375	0.0828	0.8896	0.9239	0.9065	0.9808
0.0288	8.0	5000	0.0835	0.9010	0.9251	0.9129	0.9819
0.0239	9.0	5625	0.0835	0.9027	0.9278	0.9151	0.9819
0.0226	10.0	6250	0.0843	0.8997	0.9256	0.9125	0.9818
0.0211	11.0	6875	0.0848	0.9057	0.9273	0.9163	0.9820
0.0181	12.0	7500	0.0855	0.8971	0.9276	0.9121	0.9818
0.0172	13.0	8125	0.0855	0.9052	0.9271	0.9160	0.9826

DanMaks11/bert-finetuned-ner

bert-finetuned-ner