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	6.4138	0.0043	6.4127	2.5323
No log	2.0	14	2.2999	0.1545	2.2992	1.5163
No log	3.0	21	1.0097	0.0102	1.0093	1.0046
No log	4.0	28	1.0792	0.0074	1.0785	1.0385
No log	5.0	35	0.8484	0.2346	0.8479	0.9208
No log	6.0	42	0.9121	0.2582	0.9117	0.9549
No log	7.0	49	0.7104	0.3329	0.7107	0.8430
No log	8.0	56	0.6405	0.4059	0.6408	0.8005
No log	9.0	63	0.8443	0.3320	0.8438	0.9186
No log	10.0	70	2.0050	0.0872	2.0034	1.4154
No log	11.0	77	1.3934	0.1908	1.3921	1.1799
No log	12.0	84	0.7578	0.4082	0.7575	0.8704
No log	13.0	91	0.7325	0.4601	0.7327	0.8560
No log	14.0	98	0.7406	0.4390	0.7405	0.8605
No log	15.0	105	0.7637	0.3951	0.7635	0.8738
No log	16.0	112	1.3050	0.2296	1.3040	1.1419
No log	17.0	119	1.3449	0.2407	1.3441	1.1593
No log	18.0	126	1.7994	0.1276	1.7981	1.3409
No log	19.0	133	0.6986	0.4595	0.6987	0.8359
No log	20.0	140	1.0077	0.3223	1.0070	1.0035
No log	21.0	147	1.4791	0.1793	1.4779	1.2157
No log	22.0	154	0.9683	0.3020	0.9677	0.9837
No log	23.0	161	1.2299	0.2695	1.2290	1.1086
No log	24.0	168	1.0220	0.2795	1.0215	1.0107
No log	25.0	175	1.2080	0.2393	1.2071	1.0987
No log	26.0	182	1.4504	0.1765	1.4494	1.2039
No log	27.0	189	0.8588	0.3539	0.8584	0.9265
No log	28.0	196	1.0427	0.2610	1.0420	1.0208

genki10/Trial3BERT_AugV8_k10_task1_organization_sp010_lw030_fold3

Trial3BERT_AugV8_k10_task1_organization_sp010_lw030_fold3