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	6.2633	0.0198	6.2635	2.5027
No log	2.0	10	3.2761	0.0	3.2765	1.8101
No log	3.0	15	1.6736	0.0318	1.6741	1.2939
No log	4.0	20	1.2002	0.0	1.2007	1.0958
No log	5.0	25	1.3985	0.0318	1.3988	1.1827
No log	6.0	30	1.2676	0.0813	1.2678	1.1260
No log	7.0	35	2.2999	0.0825	2.2994	1.5164
No log	8.0	40	0.9534	0.2723	0.9533	0.9764
No log	9.0	45	1.8791	0.0724	1.8785	1.3706
No log	10.0	50	1.7456	0.0719	1.7445	1.3208
No log	11.0	55	1.7547	0.0572	1.7540	1.3244
No log	12.0	60	1.7976	0.0620	1.7966	1.3404
No log	13.0	65	1.8231	0.0912	1.8216	1.3497
No log	14.0	70	2.0156	0.1724	2.0138	1.4191
No log	15.0	75	2.8759	0.0845	2.8742	1.6954
No log	16.0	80	1.4317	0.1846	1.4304	1.1960
No log	17.0	85	1.2632	0.2156	1.2619	1.1233
No log	18.0	90	1.7874	0.1395	1.7861	1.3364
No log	19.0	95	2.8790	0.0384	2.8772	1.6962
No log	20.0	100	1.4617	0.1264	1.4601	1.2084
No log	21.0	105	1.4178	0.1249	1.4166	1.1902
No log	22.0	110	1.3376	0.1495	1.3364	1.1560
No log	23.0	115	2.6656	0.0404	2.6641	1.6322

genki10/BERT_AugV8_k7_task1_organization_sp010_lw060_fold2

BERT_AugV8_k7_task1_organization_sp010_lw060_fold2