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	8.4750	0.0	8.4753	2.9112
No log	2.0	6	5.4559	0.0131	5.4563	2.3359
No log	3.0	9	3.7650	0.0039	3.7655	1.9405
No log	4.0	12	2.7958	0.0022	2.7963	1.6722
No log	5.0	15	1.7898	0.0213	1.7904	1.3381
No log	6.0	18	1.2753	0.0107	1.2760	1.1296
No log	7.0	21	1.0099	0.0107	1.0103	1.0051
No log	8.0	24	0.9428	0.0216	0.9432	0.9712
No log	9.0	27	1.3464	0.0602	1.3469	1.1605
No log	10.0	30	0.7361	0.3745	0.7364	0.8581
No log	11.0	33	1.0998	0.1023	1.1001	1.0489
No log	12.0	36	0.7588	0.3103	0.7590	0.8712
No log	13.0	39	1.9257	0.0939	1.9262	1.3879
No log	14.0	42	1.3528	0.1619	1.3532	1.1633
No log	15.0	45	0.6380	0.3877	0.6381	0.7988
No log	16.0	48	1.4776	0.1667	1.4780	1.2157
No log	17.0	51	0.8279	0.3671	0.8280	0.9099
No log	18.0	54	1.2698	0.2510	1.2701	1.1270
No log	19.0	57	1.1763	0.2662	1.1767	1.0848
No log	20.0	60	0.7843	0.3497	0.7845	0.8857
No log	21.0	63	0.7799	0.3581	0.7801	0.8832
No log	22.0	66	1.2335	0.1836	1.2336	1.1107
No log	23.0	69	0.7597	0.4038	0.7597	0.8716
No log	24.0	72	1.1902	0.1903	1.1901	1.0909
No log	25.0	75	0.8350	0.3715	0.8350	0.9138
No log	26.0	78	1.1090	0.2554	1.1091	1.0531
No log	27.0	81	0.7985	0.3371	0.7985	0.8936
No log	28.0	84	1.1341	0.2150	1.1343	1.0650
No log	29.0	87	0.8920	0.2867	0.8921	0.9445
No log	30.0	90	0.9358	0.2553	0.9360	0.9675
No log	31.0	93	1.1384	0.1842	1.1387	1.0671
No log	32.0	96	0.7547	0.3775	0.7548	0.8688
No log	33.0	99	1.6308	0.1532	1.6313	1.2772
No log	34.0	102	1.3327	0.1619	1.3331	1.1546
No log	35.0	105	0.7425	0.3664	0.7427	0.8618
No log	36.0	108	1.4527	0.1372	1.4531	1.2055
No log	37.0	111	0.7693	0.3709	0.7694	0.8772
No log	38.0	114	0.9996	0.2237	0.9999	1.0000

genki10/BERT_AugV8_k3_task1_organization_sp010_lw050_fold2

BERT_AugV8_k3_task1_organization_sp010_lw050_fold2