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	3	8.1226	0.0	8.1226	2.8500
No log	2.0	6	6.7715	0.0	6.7715	2.6022
No log	3.0	9	5.4785	0.0115	5.4785	2.3406
No log	4.0	12	4.2744	0.0039	4.2744	2.0675
No log	5.0	15	3.0657	0.0	3.0657	1.7509
No log	6.0	18	2.0522	0.0575	2.0522	1.4326
No log	7.0	21	1.6546	0.0316	1.6546	1.2863
No log	8.0	24	1.1692	0.0316	1.1692	1.0813
No log	9.0	27	1.1701	0.0484	1.1701	1.0817
No log	10.0	30	1.3962	0.0689	1.3962	1.1816
No log	11.0	33	1.2465	0.0921	1.2465	1.1165
No log	12.0	36	1.0430	0.1238	1.0430	1.0213
No log	13.0	39	1.4364	0.2050	1.4364	1.1985
No log	14.0	42	0.8258	0.3671	0.8258	0.9087
No log	15.0	45	0.9838	0.3260	0.9838	0.9919
No log	16.0	48	0.6900	0.4112	0.6900	0.8307
No log	17.0	51	0.9668	0.3017	0.9668	0.9833
No log	18.0	54	0.7381	0.3369	0.7381	0.8591
No log	19.0	57	1.9549	0.1615	1.9549	1.3982
No log	20.0	60	0.7921	0.3341	0.7921	0.8900
No log	21.0	63	0.8072	0.3285	0.8072	0.8984
No log	22.0	66	1.4948	0.1956	1.4948	1.2226
No log	23.0	69	0.8279	0.3835	0.8279	0.9099
No log	24.0	72	1.3343	0.2400	1.3343	1.1551
No log	25.0	75	0.9610	0.3481	0.9610	0.9803
No log	26.0	78	1.3406	0.2532	1.3406	1.1578
No log	27.0	81	0.9393	0.3323	0.9393	0.9692
No log	28.0	84	1.1439	0.2876	1.1439	1.0696
No log	29.0	87	1.5301	0.2140	1.5301	1.2370
No log	30.0	90	0.8840	0.3836	0.8840	0.9402
No log	31.0	93	1.1414	0.2569	1.1414	1.0684

genki10/BERT_AugV8_k3_task1_organization_sp020_lw060_fold0

BERT_AugV8_k3_task1_organization_sp020_lw060_fold0