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	12.3876	0.0003	12.3853	3.5193
No log	2.0	4	10.0854	0.0	10.0836	3.1755
No log	3.0	6	8.3285	0.0	8.3270	2.8856
No log	4.0	8	6.6446	0.0	6.6432	2.5774
No log	5.0	10	5.3420	0.0114	5.3407	2.3110
No log	6.0	12	4.5236	0.0038	4.5224	2.1266
No log	7.0	14	3.5103	0.0	3.5093	1.8733
No log	8.0	16	2.9920	0.0	2.9911	1.7295
No log	9.0	18	2.4277	0.1429	2.4270	1.5579
No log	10.0	20	2.0080	0.0811	2.0073	1.4168
No log	11.0	22	1.7159	0.0202	1.7151	1.3096
No log	12.0	24	1.4853	0.0102	1.4846	1.2184
No log	13.0	26	1.3528	0.0365	1.3523	1.1629
No log	14.0	28	1.3868	0.0488	1.3863	1.1774
No log	15.0	30	1.0994	0.0266	1.0990	1.0483
No log	16.0	32	0.9551	0.0102	0.9546	0.9770
No log	17.0	34	0.8592	0.3220	0.8588	0.9267
No log	18.0	36	0.9158	0.1485	0.9155	0.9568
No log	19.0	38	0.9861	0.1547	0.9859	0.9929
No log	20.0	40	0.6910	0.4646	0.6908	0.8311
No log	21.0	42	0.6774	0.4874	0.6773	0.8230
No log	22.0	44	1.3011	0.2557	1.3010	1.1406
No log	23.0	46	1.4226	0.2614	1.4227	1.1928
No log	24.0	48	0.9715	0.3915	0.9716	0.9857
No log	25.0	50	1.1647	0.3488	1.1649	1.0793
No log	26.0	52	1.5293	0.2560	1.5296	1.2368
No log	27.0	54	1.4284	0.2887	1.4289	1.1954
No log	28.0	56	0.8916	0.4404	0.8921	0.9445
No log	29.0	58	0.9939	0.4139	0.9946	0.9973
No log	30.0	60	1.6732	0.2354	1.6741	1.2939
No log	31.0	62	1.0965	0.3712	1.0973	1.0475
No log	32.0	64	0.7940	0.4271	0.7947	0.8915
No log	33.0	66	1.3744	0.2957	1.3752	1.1727
No log	34.0	68	1.7825	0.2177	1.7832	1.3353
No log	35.0	70	1.3501	0.2898	1.3508	1.1622
No log	36.0	72	0.7858	0.4765	0.7865	0.8869

genki10/Trial2BERT_AugV8_k1_task1_organization_sp010_lw030_fold3

Trial2BERT_AugV8_k1_task1_organization_sp010_lw030_fold3