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	5	8.2663	0.0	8.2664	2.8751
No log	2.0	10	5.0307	0.0250	5.0312	2.2430
No log	3.0	15	2.8281	0.0055	2.8287	1.6819
No log	4.0	20	1.4254	0.0318	1.4260	1.1941
No log	5.0	25	1.2130	0.0551	1.2135	1.1016
No log	6.0	30	1.8390	0.1334	1.8395	1.3563
No log	7.0	35	1.4597	0.0897	1.4602	1.2084
No log	8.0	40	0.8561	0.3117	0.8563	0.9254
No log	9.0	45	0.7025	0.4292	0.7027	0.8383
No log	10.0	50	0.6276	0.4395	0.6277	0.7923
No log	11.0	55	0.6393	0.4190	0.6395	0.7997
No log	12.0	60	0.8940	0.4085	0.8941	0.9456
No log	13.0	65	0.6120	0.4077	0.6118	0.7822
No log	14.0	70	0.9954	0.1904	0.9955	0.9978
No log	15.0	75	0.6075	0.4611	0.6072	0.7793
No log	16.0	80	0.8900	0.3926	0.8898	0.9433
No log	17.0	85	0.6885	0.5156	0.6884	0.8297
No log	18.0	90	0.7141	0.4191	0.7141	0.8450
No log	19.0	95	0.7615	0.4226	0.7614	0.8726
No log	20.0	100	0.7392	0.4767	0.7390	0.8596
No log	21.0	105	0.7177	0.4446	0.7176	0.8471
No log	22.0	110	0.9048	0.3511	0.9047	0.9512
No log	23.0	115	0.8987	0.3240	0.8986	0.9479
No log	24.0	120	0.8873	0.3757	0.8871	0.9419
No log	25.0	125	0.7143	0.4206	0.7141	0.8451
No log	26.0	130	0.7323	0.4197	0.7322	0.8557
No log	27.0	135	0.9041	0.4169	0.9038	0.9507
No log	28.0	140	1.0167	0.3623	1.0164	1.0082
No log	29.0	145	0.9171	0.3869	0.9169	0.9576
No log	30.0	150	0.8032	0.4463	0.8031	0.8961
No log	31.0	155	1.0594	0.3548	1.0592	1.0292
No log	32.0	160	0.8715	0.3760	0.8714	0.9335

genki10/BERT_AugV8_k7_task1_organization_sp030_lw040_fold2

BERT_AugV8_k7_task1_organization_sp030_lw040_fold2