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	8.7330	0.0019	8.7330	2.9552
No log	2.0	4	6.2328	0.0022	6.2328	2.4966
No log	3.0	6	4.7293	0.0177	4.7293	2.1747
No log	4.0	8	3.9648	0.0089	3.9648	1.9912
No log	5.0	10	3.5824	0.0040	3.5824	1.8927
No log	6.0	12	2.4119	0.0876	2.4119	1.5530
No log	7.0	14	2.0126	0.1190	2.0126	1.4187
No log	8.0	16	1.6285	0.0445	1.6285	1.2761
No log	9.0	18	1.2961	0.0342	1.2961	1.1385
No log	10.0	20	1.0667	0.0420	1.0667	1.0328
No log	11.0	22	0.9894	0.0547	0.9894	0.9947
No log	12.0	24	1.0261	0.0968	1.0261	1.0130
No log	13.0	26	0.9157	0.1556	0.9157	0.9569
No log	14.0	28	1.0624	0.1617	1.0624	1.0307
No log	15.0	30	0.8444	0.3403	0.8444	0.9189
No log	16.0	32	0.9859	0.2911	0.9859	0.9929
No log	17.0	34	0.8694	0.3339	0.8694	0.9324
No log	18.0	36	1.1424	0.3298	1.1424	1.0688
No log	19.0	38	1.2033	0.3081	1.2033	1.0969
No log	20.0	40	0.8880	0.3877	0.8880	0.9423
No log	21.0	42	0.8851	0.3938	0.8851	0.9408
No log	22.0	44	1.0715	0.3640	1.0715	1.0352
No log	23.0	46	1.3755	0.2728	1.3755	1.1728
No log	24.0	48	1.2479	0.2988	1.2479	1.1171
No log	25.0	50	1.6721	0.2259	1.6721	1.2931
No log	26.0	52	1.3989	0.2752	1.3989	1.1828
No log	27.0	54	1.2205	0.3270	1.2205	1.1047
No log	28.0	56	1.2355	0.3262	1.2355	1.1115
No log	29.0	58	1.2296	0.3387	1.2296	1.1089
No log	30.0	60	1.1253	0.3816	1.1253	1.0608
No log	31.0	62	1.2290	0.3514	1.2290	1.1086
No log	32.0	64	1.1393	0.3881	1.1393	1.0674
No log	33.0	66	1.3732	0.3159	1.3732	1.1718
No log	34.0	68	1.2524	0.3240	1.2524	1.1191
No log	35.0	70	1.1123	0.3379	1.1123	1.0546
No log	36.0	72	1.1184	0.3273	1.1184	1.0575

genki10/BERT_AugV8_k1_task1_organization_sp040_lw040_fold4

BERT_AugV8_k1_task1_organization_sp040_lw040_fold4