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	8.1012	-0.0002	8.0984	2.8458
No log	2.0	6	5.1569	0.0253	5.1548	2.2704
No log	3.0	9	3.7942	0.0	3.7922	1.9474
No log	4.0	12	2.4773	-0.0006	2.4755	1.5734
No log	5.0	15	1.7206	0.0	1.7190	1.3111
No log	6.0	18	1.2991	0.0	1.2976	1.1391
No log	7.0	21	1.0234	0.0	1.0221	1.0110
No log	8.0	24	0.8625	0.0876	0.8612	0.9280
No log	9.0	27	0.9850	0.2449	0.9835	0.9917
No log	10.0	30	0.9559	0.2994	0.9544	0.9769
No log	11.0	33	0.8975	0.3951	0.8959	0.9465
No log	12.0	36	1.4830	0.2964	1.4810	1.2170
No log	13.0	39	0.7500	0.4450	0.7485	0.8652
No log	14.0	42	1.2376	0.2926	1.2358	1.1117
No log	15.0	45	1.1065	0.3084	1.1049	1.0511
No log	16.0	48	0.7790	0.4536	0.7781	0.8821
No log	17.0	51	1.2401	0.3455	1.2385	1.1129
No log	18.0	54	0.7280	0.4645	0.7269	0.8526
No log	19.0	57	0.8770	0.4309	0.8760	0.9360
No log	20.0	60	1.0397	0.3708	1.0390	1.0193
No log	21.0	63	1.3723	0.2693	1.3709	1.1708
No log	22.0	66	1.0375	0.4172	1.0367	1.0182
No log	23.0	69	1.0302	0.4333	1.0297	1.0147
No log	24.0	72	1.3010	0.3054	1.2995	1.1400
No log	25.0	75	1.1652	0.3511	1.1649	1.0793
No log	26.0	78	1.0926	0.3338	1.0915	1.0447
No log	27.0	81	1.1197	0.3204	1.1188	1.0577
No log	28.0	84	1.1230	0.3113	1.1220	1.0592
No log	29.0	87	1.0201	0.4068	1.0194	1.0096
No log	30.0	90	1.2546	0.3023	1.2535	1.1196
No log	31.0	93	0.9381	0.4512	0.9374	0.9682
No log	32.0	96	1.2524	0.2592	1.2513	1.1186
No log	33.0	99	1.0229	0.3975	1.0222	1.0110

genki10/Trial2BERT_AugV8_k3_task1_organization_sp010_lw030_fold1

Trial2BERT_AugV8_k3_task1_organization_sp010_lw030_fold1