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	8	8.2281	0.0	8.2265	2.8682
No log	2.0	16	4.6841	0.0038	4.6829	2.1640
No log	3.0	24	2.1310	0.0599	2.1302	1.4595
No log	4.0	32	1.5062	0.0102	1.5056	1.2270
No log	5.0	40	1.0410	0.0645	1.0413	1.0204
No log	6.0	48	0.9628	0.1328	0.9633	0.9815
No log	7.0	56	0.9568	0.0836	0.9574	0.9785
No log	8.0	64	1.0611	0.1216	1.0617	1.0304
No log	9.0	72	1.3068	0.0661	1.3067	1.1431
No log	10.0	80	1.0940	0.0953	1.0940	1.0459
No log	11.0	88	2.6289	-0.0319	2.6275	1.6210
No log	12.0	96	1.6720	0.0019	1.6714	1.2928
No log	13.0	104	1.2509	0.0738	1.2508	1.1184
No log	14.0	112	1.8654	0.0065	1.8650	1.3656
No log	15.0	120	2.1981	0.0040	2.1972	1.4823
No log	16.0	128	1.3106	0.1200	1.3107	1.1449
No log	17.0	136	1.1536	0.1394	1.1538	1.0741
No log	18.0	144	1.1384	0.2053	1.1386	1.0670
No log	19.0	152	1.1289	0.1352	1.1289	1.0625
No log	20.0	160	1.2366	0.1261	1.2367	1.1121
No log	21.0	168	1.2237	0.1264	1.2238	1.1063
No log	22.0	176	1.9815	0.0502	1.9810	1.4075
No log	23.0	184	1.8770	0.0383	1.8764	1.3698
No log	24.0	192	1.3511	0.0920	1.3507	1.1622
No log	25.0	200	1.5147	0.1297	1.5145	1.2307
No log	26.0	208	1.4244	0.0627	1.4241	1.1934
No log	27.0	216	1.9338	0.0062	1.9330	1.3903
No log	28.0	224	2.4042	0.0271	2.4033	1.5503
No log	29.0	232	1.2799	0.0897	1.2796	1.1312
No log	30.0	240	1.7808	0.0024	1.7800	1.3342
No log	31.0	248	1.3307	0.0725	1.3302	1.1534
No log	32.0	256	1.7681	0.0506	1.7675	1.3295
No log	33.0	264	1.9710	0.0488	1.9704	1.4037

genki10/Trial3BERT_AugV8_k10_task1_organization_sp020_lw070_fold3

Trial3BERT_AugV8_k10_task1_organization_sp020_lw070_fold3