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	5	6.5036	0.0081	6.5036	2.5502
No log	2.0	10	3.2452	0.0040	3.2452	1.8015
No log	3.0	15	1.7850	0.0420	1.7850	1.3360
No log	4.0	20	1.0501	0.0212	1.0501	1.0247
No log	5.0	25	1.6482	0.0445	1.6482	1.2838
No log	6.0	30	0.8391	0.1677	0.8391	0.9160
No log	7.0	35	1.2409	0.0447	1.2409	1.1139
No log	8.0	40	0.7869	0.3004	0.7869	0.8871
No log	9.0	45	0.6683	0.4099	0.6683	0.8175
No log	10.0	50	0.6055	0.4365	0.6055	0.7781
No log	11.0	55	0.9195	0.4212	0.9195	0.9589
No log	12.0	60	0.6356	0.4821	0.6356	0.7973
No log	13.0	65	1.0267	0.3797	1.0267	1.0133
No log	14.0	70	0.9843	0.3618	0.9843	0.9921
No log	15.0	75	0.6908	0.5003	0.6908	0.8312
No log	16.0	80	1.7475	0.2326	1.7475	1.3219
No log	17.0	85	0.8488	0.4210	0.8488	0.9213
No log	18.0	90	0.9393	0.3468	0.9393	0.9692
No log	19.0	95	1.1476	0.3312	1.1476	1.0712
No log	20.0	100	0.8637	0.4007	0.8637	0.9294
No log	21.0	105	0.8641	0.3799	0.8641	0.9296
No log	22.0	110	1.2883	0.2659	1.2883	1.1350
No log	23.0	115	0.9540	0.3883	0.9540	0.9767
No log	24.0	120	0.8681	0.4194	0.8681	0.9317
No log	25.0	125	0.7217	0.4814	0.7217	0.8495
No log	26.0	130	1.7220	0.2338	1.7220	1.3123
No log	27.0	135	1.0622	0.3674	1.0622	1.0306
No log	28.0	140	0.8927	0.4252	0.8927	0.9448
No log	29.0	145	0.9477	0.3762	0.9477	0.9735
No log	30.0	150	1.0528	0.3671	1.0528	1.0261

genki10/BERT_AugV8_k7_task1_organization_sp040_lw010_fold4

BERT_AugV8_k7_task1_organization_sp040_lw010_fold4