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	8.0866	0.0	8.0843	2.8433
No log	2.0	14	4.3125	0.0	4.3105	2.0762
No log	3.0	21	1.6812	0.0583	1.6796	1.2960
No log	4.0	28	0.9000	0.0327	0.8988	0.9480
No log	5.0	35	0.8887	0.1318	0.8874	0.9420
No log	6.0	42	0.9473	0.2489	0.9459	0.9726
No log	7.0	49	0.6846	0.3269	0.6838	0.8269
No log	8.0	56	0.7007	0.4207	0.7002	0.8368
No log	9.0	63	0.6847	0.4796	0.6842	0.8272
No log	10.0	70	1.0619	0.3839	1.0615	1.0303
No log	11.0	77	0.9307	0.3702	0.9303	0.9645
No log	12.0	84	1.2030	0.2913	1.2027	1.0967
No log	13.0	91	1.4072	0.2452	1.4068	1.1861
No log	14.0	98	0.8703	0.3531	0.8697	0.9326
No log	15.0	105	1.0058	0.3352	1.0050	1.0025
No log	16.0	112	1.3334	0.2827	1.3328	1.1545
No log	17.0	119	1.1268	0.3106	1.1260	1.0612
No log	18.0	126	1.0014	0.3658	1.0008	1.0004
No log	19.0	133	1.0562	0.3734	1.0556	1.0274
No log	20.0	140	0.8886	0.3980	0.8881	0.9424
No log	21.0	147	0.7103	0.4675	0.7098	0.8425
No log	22.0	154	0.7614	0.4102	0.7609	0.8723
No log	23.0	161	1.1228	0.3145	1.1222	1.0593
No log	24.0	168	1.1014	0.3095	1.1008	1.0492

genki10/Trial3BERT_AugV8_k10_task1_organization_sp020_lw030_fold1

Trial3BERT_AugV8_k10_task1_organization_sp020_lw030_fold1