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	10.4015	0.0016	10.3995	3.2248
No log	2.0	4	7.8116	0.0	7.8101	2.7947
No log	3.0	6	6.1520	-0.0179	6.1506	2.4800
No log	4.0	8	4.7260	0.0076	4.7248	2.1737
No log	5.0	10	3.6980	0.0	3.6969	1.9227
No log	6.0	12	2.9700	0.0	2.9691	1.7231
No log	7.0	14	2.6260	0.0281	2.6250	1.6202
No log	8.0	16	2.0976	0.0284	2.0967	1.4480
No log	9.0	18	1.7124	0.0184	1.7117	1.3083
No log	10.0	20	1.3918	0.0202	1.3911	1.1795
No log	11.0	22	1.1542	0.0202	1.1535	1.0740
No log	12.0	24	1.0255	0.0248	1.0249	1.0124
No log	13.0	26	0.9466	0.1237	0.9462	0.9727
No log	14.0	28	1.1036	0.0832	1.1033	1.0504
No log	15.0	30	1.0634	0.1422	1.0632	1.0311
No log	16.0	32	0.8325	0.2869	0.8324	0.9124
No log	17.0	34	1.0356	0.2691	1.0356	1.0177
No log	18.0	36	1.4551	0.2113	1.4552	1.2063
No log	19.0	38	0.7246	0.4642	0.7248	0.8513
No log	20.0	40	0.7920	0.4608	0.7922	0.8901
No log	21.0	42	2.0034	0.1948	2.0038	1.4156
No log	22.0	44	1.8941	0.2065	1.8947	1.3765
No log	23.0	46	0.7172	0.4704	0.7178	0.8472
No log	24.0	48	0.6706	0.4474	0.6711	0.8192
No log	25.0	50	0.8551	0.4450	0.8557	0.9251
No log	26.0	52	0.8245	0.4587	0.8251	0.9084
No log	27.0	54	1.0125	0.3856	1.0131	1.0065
No log	28.0	56	0.7779	0.4408	0.7784	0.8823
No log	29.0	58	0.8333	0.4528	0.8337	0.9131
No log	30.0	60	1.4516	0.2970	1.4519	1.2050
No log	31.0	62	1.9168	0.2133	1.9169	1.3845
No log	32.0	64	1.1845	0.3061	1.1846	1.0884
No log	33.0	66	0.8582	0.4134	0.8584	0.9265
No log	34.0	68	0.8460	0.3942	0.8462	0.9199
No log	35.0	70	1.3913	0.2343	1.3914	1.1796
No log	36.0	72	1.0780	0.2464	1.0782	1.0384
No log	37.0	74	0.8843	0.3916	0.8846	0.9405
No log	38.0	76	0.8812	0.3853	0.8815	0.9389

genki10/BERT_AugV8_k1_task1_organization_sp020_lw040_fold3

BERT_AugV8_k1_task1_organization_sp020_lw040_fold3