learning_rate: 5e-05
train_batch_size: 20
eval_batch_size: 20
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: 2

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.5517	0.1111	50	0.3868	0.844	0.8440
0.4128	0.2222	100	0.3074	0.88	0.8800
0.3387	0.3333	150	0.2962	0.883	0.8829
0.2646	0.4444	200	0.2183	0.932	0.9320
0.4301	0.5556	250	0.3217	0.91	0.9100
0.2126	0.6667	300	0.2051	0.92	0.9197
0.2372	0.7778	350	0.2259	0.912	0.9119
0.2959	0.8889	400	0.1805	0.933	0.9327
0.1747	1.0	450	0.2059	0.937	0.9370
0.1974	1.1111	500	0.1679	0.942	0.9420
0.1445	1.2222	550	0.2515	0.924	0.9239
0.1711	1.3333	600	0.1707	0.932	0.9319
0.1797	1.4444	650	0.1653	0.942	0.9420
0.1149	1.5556	700	0.1419	0.954	0.9540
0.2704	1.6667	750	0.1623	0.942	0.9418
0.1502	1.7778	800	0.1615	0.944	0.9440
0.1408	1.8889	850	0.1126	0.953	0.9530
0.1222	2.0	900	0.1222	0.954	0.9540

Howard881010/longformer-heat_transfer-2epoch

longformer-heat_transfer-2epoch