learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
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: 10

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.2051	1.0	1252	0.1253	0.9721	0.9762	0.9742	0.9715
0.0965	2.0	2504	0.0894	0.9796	0.9810	0.9803	0.9787
0.0661	3.0	3756	0.0815	0.9818	0.9828	0.9823	0.9803
0.0462	4.0	5008	0.0835	0.9822	0.9821	0.9822	0.9806
0.0365	5.0	6260	0.0827	0.9823	0.9828	0.9826	0.9803
0.0307	6.0	7512	0.0839	0.9829	0.9840	0.9834	0.9814
0.0203	7.0	8764	0.0845	0.9842	0.9844	0.9843	0.9825
0.0211	8.0	10016	0.0845	0.9842	0.9850	0.9846	0.9828
0.0164	9.0	11268	0.0866	0.9833	0.9842	0.9837	0.9820
0.018	10.0	12520	0.0863	0.9838	0.9851	0.9845	0.9826

vdoninav/bert-finetuned-ner-conll2003

bert-finetuned-ner-conll2003