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	10.1843	0.0023	10.1843	3.1913
No log	2.0	4	7.3171	0.0018	7.3171	2.7050
No log	3.0	6	5.6198	-0.0025	5.6198	2.3706
No log	4.0	8	5.4082	-0.0265	5.4082	2.3255
No log	5.0	10	3.6494	0.0040	3.6494	1.9103
No log	6.0	12	3.3613	0.0040	3.3613	1.8334
No log	7.0	14	2.6165	0.0040	2.6165	1.6175
No log	8.0	16	2.1193	0.0553	2.1193	1.4558
No log	9.0	18	1.6580	0.0316	1.6580	1.2876
No log	10.0	20	1.3434	0.0316	1.3434	1.1591
No log	11.0	22	1.2057	0.0381	1.2057	1.0980
No log	12.0	24	1.0572	0.0381	1.0572	1.0282
No log	13.0	26	0.9489	0.0407	0.9489	0.9741
No log	14.0	28	0.8910	0.1578	0.8910	0.9439
No log	15.0	30	0.8361	0.3448	0.8361	0.9144
No log	16.0	32	1.3160	0.2207	1.3160	1.1472
No log	17.0	34	1.2375	0.2898	1.2375	1.1124
No log	18.0	36	0.6970	0.5411	0.6970	0.8349
No log	19.0	38	0.7146	0.5408	0.7146	0.8453
No log	20.0	40	1.6659	0.2378	1.6659	1.2907
No log	21.0	42	2.1379	0.2273	2.1379	1.4622
No log	22.0	44	1.2114	0.3150	1.2114	1.1006
No log	23.0	46	0.6778	0.5398	0.6778	0.8233
No log	24.0	48	0.7811	0.4146	0.7811	0.8838
No log	25.0	50	1.2315	0.3096	1.2315	1.1097
No log	26.0	52	1.9848	0.2287	1.9848	1.4088
No log	27.0	54	1.4748	0.2797	1.4748	1.2144
No log	28.0	56	0.5958	0.5135	0.5958	0.7719
No log	29.0	58	0.5735	0.5002	0.5735	0.7573
No log	30.0	60	0.6275	0.4958	0.6275	0.7921
No log	31.0	62	0.5978	0.4986	0.5978	0.7732
No log	32.0	64	0.6111	0.4947	0.6111	0.7817
No log	33.0	66	0.6264	0.5014	0.6264	0.7914

genki10/Trial3BERT_AugV8_k1_task1_organization_sp020_lw060_fold4

Trial3BERT_AugV8_k1_task1_organization_sp020_lw060_fold4