learning_rate: 3e-05
train_batch_size: 64
eval_batch_size: 256
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
lr_scheduler_warmup_steps: 0.2
num_epochs: 2

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.5313	0.0880	200	0.1628	0.5264	0.2550	0.3436	0.9829
0.1195	0.1759	400	0.0978	0.3785	0.3809	0.3797	0.9839
0.0874	0.2639	600	0.0872	0.4427	0.4355	0.4391	0.9851
0.0798	0.3518	800	0.0877	0.4226	0.4947	0.4558	0.9849
0.0729	0.4398	1000	0.0800	0.4871	0.5264	0.5060	0.9869
0.0697	0.5277	1200	0.0749	0.5180	0.5316	0.5247	0.9874
0.0654	0.6157	1400	0.0763	0.4933	0.5562	0.5229	0.9875
0.0620	0.7036	1600	0.0732	0.5273	0.5621	0.5441	0.9876
0.0613	0.7916	1800	0.0735	0.5089	0.5694	0.5375	0.9872
0.0588	0.8795	2000	0.0702	0.5649	0.5642	0.5646	0.9886
0.0558	0.9675	2200	0.0710	0.5326	0.5756	0.5533	0.9880
0.0505	1.0554	2400	0.0759	0.5550	0.5806	0.5675	0.9880
0.0463	1.1434	2600	0.0715	0.5764	0.5782	0.5773	0.9891
0.0472	1.2313	2800	0.0712	0.5838	0.5564	0.5698	0.9888
0.0459	1.3193	3000	0.0704	0.5758	0.5820	0.5789	0.9888
0.0449	1.4072	3200	0.0729	0.5702	0.5940	0.5819	0.9885
0.0454	1.4952	3400	0.0711	0.5831	0.5992	0.5911	0.9890
0.0438	1.5831	3600	0.0702	0.5793	0.5933	0.5863	0.9887
0.0437	1.6711	3800	0.0699	0.5831	0.5867	0.5849	0.9890
0.0449	1.7590	4000	0.0688	0.5731	0.5978	0.5852	0.9890
0.0434	1.8470	4200	0.0705	0.5767	0.5969	0.5866	0.9890
0.0446	1.9349	4400	0.0689	0.5825	0.5924	0.5874	0.9891
0.0446	2.0	4548	0.0688	0.5802	0.5914	0.5858	0.9891

YarBar/bert-finetuned-ner-18-squad

bert-finetuned-ner-18-squad