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	9.1715	0.0	9.1715	3.0285
No log	2.0	4	7.9111	0.0	7.9111	2.8127
No log	3.0	6	7.0038	0.0	7.0038	2.6465
No log	4.0	8	6.2665	-0.0004	6.2665	2.5033
No log	5.0	10	5.6075	0.0204	5.6075	2.3680
No log	6.0	12	4.8513	0.0115	4.8513	2.2026
No log	7.0	14	4.3964	0.0077	4.3964	2.0968
No log	8.0	16	3.5046	0.0	3.5046	1.8721
No log	9.0	18	2.9632	0.0	2.9632	1.7214
No log	10.0	20	2.3245	0.0864	2.3245	1.5246
No log	11.0	22	1.8392	0.0484	1.8392	1.3562
No log	12.0	24	1.4523	0.0316	1.4523	1.2051
No log	13.0	26	1.1976	0.0316	1.1976	1.0943
No log	14.0	28	1.0124	0.0316	1.0124	1.0062
No log	15.0	30	0.8910	0.0316	0.8910	0.9439
No log	16.0	32	0.8885	0.1158	0.8885	0.9426
No log	17.0	34	0.7679	0.3925	0.7679	0.8763
No log	18.0	36	0.7747	0.3599	0.7747	0.8802
No log	19.0	38	0.7475	0.4074	0.7475	0.8646
No log	20.0	40	1.1276	0.3093	1.1276	1.0619
No log	21.0	42	0.8491	0.4532	0.8491	0.9215
No log	22.0	44	0.6235	0.4799	0.6235	0.7896
No log	23.0	46	0.8586	0.4461	0.8586	0.9266
No log	24.0	48	0.9838	0.4186	0.9838	0.9919
No log	25.0	50	0.7639	0.4460	0.7639	0.8740
No log	26.0	52	0.7735	0.4322	0.7735	0.8795
No log	27.0	54	0.9350	0.3911	0.9350	0.9670
No log	28.0	56	0.7189	0.4421	0.7189	0.8479
No log	29.0	58	0.7727	0.3953	0.7727	0.8790
No log	30.0	60	1.0866	0.2857	1.0866	1.0424
No log	31.0	62	0.8036	0.3292	0.8036	0.8965
No log	32.0	64	0.7885	0.3279	0.7885	0.8880
No log	33.0	66	0.7668	0.3484	0.7668	0.8757
No log	34.0	68	1.0816	0.2576	1.0816	1.0400
No log	35.0	70	0.8757	0.3117	0.8757	0.9358
No log	36.0	72	0.7179	0.3714	0.7179	0.8473
No log	37.0	74	1.0248	0.2920	1.0248	1.0123

genki10/Trial3BERT_AugV8_k1_task1_organization_sp040_lw010_fold0

Trial3BERT_AugV8_k1_task1_organization_sp040_lw010_fold0