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	7	5.3380	0.0025	5.3359	2.3099
No log	2.0	14	3.1013	0.0	3.0995	1.7605
No log	3.0	21	1.6653	0.0	1.6637	1.2899
No log	4.0	28	1.1707	0.0	1.1693	1.0813
No log	5.0	35	1.1817	0.0	1.1801	1.0863
No log	6.0	42	0.8233	0.1834	0.8221	0.9067
No log	7.0	49	0.9160	0.0870	0.9149	0.9565
No log	8.0	56	0.9133	0.1319	0.9124	0.9552
No log	9.0	63	1.1198	0.1349	1.1186	1.0576
No log	10.0	70	1.1622	0.1796	1.1609	1.0775
No log	11.0	77	1.0064	0.2294	1.0054	1.0027
No log	12.0	84	1.1171	0.2362	1.1161	1.0565
No log	13.0	91	0.9696	0.3123	0.9684	0.9840
No log	14.0	98	1.1674	0.2093	1.1660	1.0798
No log	15.0	105	1.0970	0.2378	1.0958	1.0468
No log	16.0	112	1.3945	0.1127	1.3934	1.1804
No log	17.0	119	1.6561	0.1161	1.6548	1.2864
No log	18.0	126	1.0717	0.1826	1.0704	1.0346
No log	19.0	133	1.0965	0.2373	1.0952	1.0465
No log	20.0	140	1.2226	0.2589	1.2209	1.1050
No log	21.0	147	1.2579	0.2182	1.2562	1.1208
No log	22.0	154	1.3017	0.2145	1.3002	1.1402
No log	23.0	161	1.1450	0.2615	1.1436	1.0694
No log	24.0	168	0.9364	0.2430	0.9352	0.9671
No log	25.0	175	0.9921	0.1653	0.9909	0.9954
No log	26.0	182	0.9921	0.1860	0.9909	0.9954
No log	27.0	189	1.0073	0.2839	1.0058	1.0029
No log	28.0	196	1.0965	0.1402	1.0952	1.0465

genki10/BERT_AugV8_k10_task1_organization_sp020_lw040_fold1

BERT_AugV8_k10_task1_organization_sp020_lw040_fold1