learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
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: 150

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	7	6.2375	0.0046	6.2377	2.4975
No log	2.0	14	2.6696	0.0	2.6700	1.6340
No log	3.0	21	1.2826	0.0213	1.2830	1.1327
No log	4.0	28	0.8848	0.1057	0.8851	0.9408
No log	5.0	35	1.1936	0.0029	1.1939	1.0927
No log	6.0	42	0.6603	0.4429	0.6606	0.8128
No log	7.0	49	0.5894	0.4686	0.5896	0.7679
No log	8.0	56	0.7854	0.3256	0.7857	0.8864
No log	9.0	63	0.9487	0.3822	0.9488	0.9741
No log	10.0	70	0.9500	0.2420	0.9506	0.9750
No log	11.0	77	0.7594	0.4045	0.7599	0.8717
No log	12.0	84	0.9987	0.2824	0.9992	0.9996
No log	13.0	91	1.0524	0.2683	1.0530	1.0261
No log	14.0	98	1.0350	0.2651	1.0353	1.0175
No log	15.0	105	0.9306	0.3119	0.9309	0.9649
No log	16.0	112	1.0675	0.2453	1.0679	1.0334
No log	17.0	119	1.0213	0.2602	1.0217	1.0108
No log	18.0	126	1.3961	0.1580	1.3963	1.1817
No log	19.0	133	0.6542	0.4071	0.6545	0.8090
No log	20.0	140	0.6983	0.3721	0.6986	0.8358
No log	21.0	147	0.7841	0.3169	0.7845	0.8857
No log	22.0	154	1.1487	0.2101	1.1490	1.0719

genki10/BERT_AugV8_k10_task1_organization_sp010_lw040_fold2

BERT_AugV8_k10_task1_organization_sp010_lw040_fold2