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	2	8.8038	0.0	8.8038	2.9671
No log	2.0	4	7.5704	0.0	7.5704	2.7514
No log	3.0	6	7.0766	0.0	7.0766	2.6602
No log	4.0	8	6.0332	0.0052	6.0332	2.4563
No log	5.0	10	5.2300	0.0115	5.2300	2.2869
No log	6.0	12	4.3900	0.0039	4.3900	2.0952
No log	7.0	14	3.7189	0.0	3.7189	1.9284
No log	8.0	16	2.8962	0.0	2.8962	1.7018
No log	9.0	18	2.2425	0.0744	2.2425	1.4975
No log	10.0	20	1.9021	0.0601	1.9021	1.3792
No log	11.0	22	1.4116	0.0316	1.4116	1.1881
No log	12.0	24	1.1853	0.0316	1.1853	1.0887
No log	13.0	26	0.9628	0.0316	0.9628	0.9812
No log	14.0	28	0.9746	0.0484	0.9746	0.9872
No log	15.0	30	0.8340	0.2763	0.8340	0.9132
No log	16.0	32	0.7313	0.4254	0.7313	0.8552
No log	17.0	34	1.5215	0.1998	1.5215	1.2335
No log	18.0	36	1.2319	0.2376	1.2319	1.1099
No log	19.0	38	0.6393	0.4521	0.6393	0.7995
No log	20.0	40	0.6447	0.4465	0.6447	0.8029
No log	21.0	42	1.2964	0.2186	1.2964	1.1386
No log	22.0	44	1.8965	0.1658	1.8965	1.3771
No log	23.0	46	1.0349	0.3440	1.0349	1.0173
No log	24.0	48	0.8013	0.3805	0.8013	0.8951
No log	25.0	50	1.7920	0.1735	1.7920	1.3387
No log	26.0	52	1.8091	0.1719	1.8091	1.3450
No log	27.0	54	1.0521	0.3049	1.0521	1.0257
No log	28.0	56	0.8253	0.3501	0.8253	0.9084
No log	29.0	58	0.9308	0.3206	0.9308	0.9648
No log	30.0	60	1.0509	0.2822	1.0509	1.0252
No log	31.0	62	0.9857	0.2990	0.9857	0.9928
No log	32.0	64	1.2245	0.2665	1.2245	1.1066
No log	33.0	66	0.7957	0.3921	0.7957	0.8920
No log	34.0	68	1.0036	0.3165	1.0036	1.0018

genki10/Trial3BERT_AugV8_k1_task1_organization_sp020_lw060_fold0

Trial3BERT_AugV8_k1_task1_organization_sp020_lw060_fold0