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: 18

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	F1 Micro	Precision Macro	Precision Micro	Recall Macro	Recall Micro
0.3673	1.0	93	0.2453	0.9284	0.1919	0.4850	0.2701	0.4678	0.1872	0.5035
0.2176	2.0	186	0.1888	0.9439	0.2591	0.5149	0.3936	0.6230	0.2298	0.4388
0.1418	3.0	279	0.1454	0.9666	0.3554	0.725	0.4120	0.7902	0.3577	0.6697
0.0859	4.0	372	0.1238	0.9750	0.4365	0.7789	0.6084	0.8540	0.3946	0.7159
0.0607	5.0	465	0.1136	0.9766	0.4979	0.7965	0.5945	0.8606	0.4781	0.7413
0.0413	6.0	558	0.1103	0.9827	0.4995	0.8608	0.6097	0.9629	0.4415	0.7783
0.0309	7.0	651	0.1109	0.9821	0.5654	0.8558	0.6379	0.8842	0.5439	0.8291
0.0237	8.0	744	0.1056	0.9847	0.6330	0.8721	0.7169	0.9227	0.5923	0.8268
0.0154	9.0	837	0.1009	0.9858	0.6639	0.8816	0.7079	0.9352	0.6422	0.8337
0.0096	10.0	930	0.1003	0.9881	0.6783	0.9047	0.7250	0.9470	0.6494	0.8661
0.0078	11.0	1023	0.1000	0.9889	0.7661	0.9144	0.8075	0.9571	0.7524	0.8753
0.0052	12.0	1116	0.1046	0.9890	0.7563	0.9166	0.7940	0.9619	0.7561	0.8753
0.0041	13.0	1209	0.1022	0.9892	0.7804	0.9177	0.8255	0.9644	0.7570	0.8753
0.0021	14.0	1302	0.0994	0.9887	0.7602	0.9133	0.7959	0.9547	0.7534	0.8753
0.0018	15.0	1395	0.1043	0.9895	0.7903	0.9212	0.8431	0.9694	0.7572	0.8776
0.0016	16.0	1488	0.1059	0.9898	0.7901	0.9235	0.8434	0.9744	0.7572	0.8776
0.0014	17.0	1581	0.1063	0.9898	0.7924	0.9235	0.8472	0.9744	0.7572	0.8776
0.001	18.0	1674	0.1052	0.9895	0.7899	0.9212	0.8429	0.9694	0.7572	0.8776

codymd/bert-base-uncased-grammar-ner

bert-base-uncased-grammar-ner