learning_rate: 5e-05
train_batch_size: 24
eval_batch_size: 24
seed: 42
optimizer: Use 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: 12

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	F1 Micro	Precision Macro	Precision Micro	Recall Macro	Recall Micro
0.0121	1.0	93	0.1199	0.9821	0.8430	0.8430	0.9373	0.9373	0.7660	0.7660
0.0124	2.0	186	0.0898	0.9832	0.8448	0.8448	0.8435	0.8435	0.8462	0.8462
0.0176	3.0	279	0.0690	0.9871	0.8797	0.8797	0.9051	0.9051	0.8558	0.8558
0.0182	4.0	372	0.0805	0.9858	0.8793	0.8793	0.9078	0.9078	0.8526	0.8526
0.01	5.0	465	0.0816	0.9824	0.8465	0.8465	0.8198	0.8198	0.875	0.875
0.0075	6.0	558	0.0887	0.9866	0.8867	0.8867	0.8954	0.8954	0.8782	0.8782
0.0038	7.0	651	0.1157	0.9839	0.8701	0.8701	0.8502	0.8502	0.8910	0.8910
0.0031	8.0	744	0.1000	0.9877	0.9034	0.9034	0.9231	0.9231	0.8846	0.8846
0.0017	9.0	837	0.1097	0.9877	0.9010	0.9010	0.9286	0.9286	0.875	0.875
0.0013	10.0	930	0.1044	0.9894	0.9161	0.9161	0.9613	0.9613	0.875	0.875
0.001	11.0	1023	0.1069	0.9889	0.9118	0.9118	0.9481	0.9481	0.8782	0.8782
0.0003	12.0	1116	0.1085	0.9887	0.9103	0.9103	0.9448	0.9448	0.8782	0.8782

codymd/bert-base-uncased-grammar-ner-generic

bert-base-uncased-grammar-ner-generic