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	7.0857	0.0	7.0857	2.6619
No log	2.0	10	4.9357	0.0115	4.9357	2.2216
No log	3.0	15	2.9118	0.0	2.9118	1.7064
No log	4.0	20	1.4788	0.0316	1.4788	1.2161
No log	5.0	25	1.0692	0.0212	1.0692	1.0340
No log	6.0	30	0.9809	0.0316	0.9809	0.9904
No log	7.0	35	0.8422	0.2716	0.8422	0.9177
No log	8.0	40	0.7096	0.3348	0.7096	0.8424
No log	9.0	45	0.6307	0.3572	0.6307	0.7942
No log	10.0	50	0.5913	0.3725	0.5913	0.7690
No log	11.0	55	0.6837	0.3066	0.6837	0.8268
No log	12.0	60	0.6040	0.4044	0.6040	0.7772
No log	13.0	65	0.6271	0.4202	0.6271	0.7919
No log	14.0	70	0.5711	0.4344	0.5711	0.7557
No log	15.0	75	0.6055	0.4513	0.6055	0.7781
No log	16.0	80	0.6200	0.4974	0.6200	0.7874
No log	17.0	85	0.7231	0.4022	0.7231	0.8504
No log	18.0	90	0.8438	0.3293	0.8438	0.9186
No log	19.0	95	0.8340	0.2861	0.8340	0.9132
No log	20.0	100	0.6172	0.4589	0.6172	0.7856
No log	21.0	105	0.8027	0.3079	0.8027	0.8959
No log	22.0	110	0.9406	0.2308	0.9406	0.9699
No log	23.0	115	0.7198	0.3758	0.7198	0.8484
No log	24.0	120	0.6724	0.4860	0.6724	0.8200
No log	25.0	125	0.6873	0.4128	0.6873	0.8291
No log	26.0	130	0.7671	0.3980	0.7671	0.8758
No log	27.0	135	0.9492	0.2270	0.9492	0.9743
No log	28.0	140	0.8894	0.1792	0.8894	0.9431
No log	29.0	145	0.6952	0.3466	0.6952	0.8338
No log	30.0	150	0.6507	0.4720	0.6507	0.8067
No log	31.0	155	0.6619	0.4214	0.6619	0.8135

genki10/Trial3BERT_AugV8_k7_task1_organization_sp040_lw010_fold0

Trial3BERT_AugV8_k7_task1_organization_sp040_lw010_fold0