learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
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: 3

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.4169	0.1139	200	0.1422	0.7777	0.8371	0.8063	0.9615
0.1456	0.2278	400	0.1122	0.8338	0.8805	0.8565	0.9683
0.1401	0.3417	600	0.1092	0.8702	0.8958	0.8828	0.9705
0.0962	0.4556	800	0.0911	0.8845	0.9179	0.9009	0.9763
0.1064	0.5695	1000	0.0774	0.9027	0.9305	0.9164	0.9799
0.0741	0.6834	1200	0.0821	0.9020	0.9281	0.9149	0.9795
0.0770	0.7973	1400	0.0733	0.9071	0.9313	0.9190	0.9809
0.0699	0.9112	1600	0.0664	0.9164	0.9320	0.9242	0.9817
0.0770	1.0251	1800	0.0676	0.9125	0.9377	0.9250	0.9825
0.0462	1.1390	2000	0.0621	0.9268	0.9440	0.9353	0.9843
0.0426	1.2528	2200	0.0657	0.9251	0.9436	0.9343	0.9845
0.0389	1.3667	2400	0.0709	0.9196	0.9399	0.9297	0.9836
0.0397	1.4806	2600	0.0714	0.9230	0.9426	0.9327	0.9836
0.0453	1.5945	2800	0.0657	0.9206	0.9403	0.9303	0.9834
0.0410	1.7084	3000	0.0640	0.9302	0.9440	0.9370	0.9847
0.0367	1.8223	3200	0.0642	0.9242	0.9461	0.9351	0.9842
0.0380	1.9362	3400	0.0702	0.9265	0.9441	0.9352	0.9839
0.0202	2.0501	3600	0.0687	0.9328	0.9482	0.9404	0.9852
0.0199	2.1640	3800	0.0708	0.9252	0.9475	0.9362	0.9848
0.0218	2.2779	4000	0.0736	0.9339	0.9458	0.9398	0.9850
0.0221	2.3918	4200	0.0726	0.9259	0.9436	0.9347	0.9839
0.0190	2.5057	4400	0.0681	0.9324	0.9450	0.9386	0.9852
0.0154	2.6196	4600	0.0645	0.9292	0.9480	0.9385	0.9855
0.0240	2.7335	4800	0.0641	0.9335	0.9475	0.9404	0.9858
0.0228	2.8474	5000	0.0636	0.9321	0.9478	0.9399	0.9859
0.0172	2.9613	5200	0.0637	0.9333	0.9488	0.9410	0.9860
0.0172	3.0	5268	0.0638	0.9338	0.9492	0.9414	0.9860

YarBar/bert-finetuned-ner-3ep

bert-finetuned-ner-3ep