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	9.1722	0.0	9.1722	3.0286
No log	2.0	4	7.7099	0.0	7.7099	2.7767
No log	3.0	6	6.8716	0.0	6.8716	2.6214
No log	4.0	8	6.2299	-0.0138	6.2299	2.4960
No log	5.0	10	5.2948	0.0115	5.2948	2.3010
No log	6.0	12	4.5069	0.0039	4.5069	2.1230
No log	7.0	14	3.8186	0.0	3.8186	1.9541
No log	8.0	16	3.0522	0.0	3.0522	1.7471
No log	9.0	18	2.3718	0.1103	2.3718	1.5401
No log	10.0	20	1.8261	0.0419	1.8261	1.3513
No log	11.0	22	1.4981	0.0316	1.4981	1.2240
No log	12.0	24	1.3165	0.0484	1.3165	1.1474
No log	13.0	26	1.1659	0.0484	1.1659	1.0798
No log	14.0	28	0.9463	0.0484	0.9463	0.9728
No log	15.0	30	1.3325	0.1179	1.3325	1.1544
No log	16.0	32	1.5450	0.1734	1.5450	1.2430
No log	17.0	34	0.9330	0.1515	0.9330	0.9659
No log	18.0	36	0.7625	0.4495	0.7625	0.8732
No log	19.0	38	1.2547	0.1706	1.2547	1.1201
No log	20.0	40	1.4788	0.1767	1.4788	1.2161
No log	21.0	42	0.7986	0.3797	0.7986	0.8937
No log	22.0	44	0.7776	0.3645	0.7776	0.8818
No log	23.0	46	1.1216	0.2714	1.1216	1.0591
No log	24.0	48	1.3617	0.2250	1.3617	1.1669
No log	25.0	50	0.9242	0.3377	0.9242	0.9614
No log	26.0	52	0.7498	0.3979	0.7498	0.8659
No log	27.0	54	0.7199	0.4168	0.7199	0.8484
No log	28.0	56	0.9328	0.3396	0.9328	0.9658
No log	29.0	58	0.9436	0.3563	0.9436	0.9714
No log	30.0	60	0.7279	0.4110	0.7279	0.8532
No log	31.0	62	0.7599	0.4094	0.7599	0.8717
No log	32.0	64	1.0128	0.3400	1.0128	1.0064
No log	33.0	66	0.8818	0.3817	0.8818	0.9391

genki10/BERT_AugV8_k1_task1_organization_sp030_lw050_fold0

BERT_AugV8_k1_task1_organization_sp030_lw050_fold0