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	8.1361	0.0	8.1361	2.8524
No log	2.0	6	6.6550	0.0	6.6550	2.5797
No log	3.0	9	5.3898	0.0112	5.3898	2.3216
No log	4.0	12	4.1454	0.0039	4.1454	2.0360
No log	5.0	15	2.9877	0.0	2.9877	1.7285
No log	6.0	18	2.0035	0.0511	2.0035	1.4154
No log	7.0	21	1.3988	0.0316	1.3988	1.1827
No log	8.0	24	1.0891	0.0316	1.0891	1.0436
No log	9.0	27	1.3611	0.0575	1.3611	1.1666
No log	10.0	30	1.0147	0.1102	1.0147	1.0073
No log	11.0	33	0.7515	0.3778	0.7515	0.8669
No log	12.0	36	0.9154	0.3181	0.9154	0.9567
No log	13.0	39	0.8859	0.3167	0.8859	0.9412
No log	14.0	42	0.6448	0.5098	0.6448	0.8030
No log	15.0	45	1.5840	0.1877	1.5840	1.2586
No log	16.0	48	0.7503	0.4168	0.7503	0.8662
No log	17.0	51	0.7847	0.4082	0.7847	0.8858
No log	18.0	54	0.8571	0.3840	0.8571	0.9258
No log	19.0	57	0.8537	0.3546	0.8537	0.9240
No log	20.0	60	0.7640	0.3432	0.7640	0.8741
No log	21.0	63	1.1188	0.2791	1.1188	1.0577
No log	22.0	66	0.7886	0.3451	0.7886	0.8880
No log	23.0	69	1.1796	0.2741	1.1796	1.0861
No log	24.0	72	0.8473	0.3370	0.8473	0.9205
No log	25.0	75	1.4412	0.1782	1.4412	1.2005
No log	26.0	78	0.8010	0.3482	0.8010	0.8950
No log	27.0	81	0.9066	0.3080	0.9066	0.9522
No log	28.0	84	1.7304	0.1192	1.7304	1.3154
No log	29.0	87	0.9084	0.3194	0.9084	0.9531

genki10/BERT_AugV8_k3_task1_organization_sp020_lw010_fold0

BERT_AugV8_k3_task1_organization_sp020_lw010_fold0