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	6	5.5576	0.0400	5.5553	2.3570
No log	2.0	12	2.7917	0.0	2.7900	1.6703
No log	3.0	18	1.6097	0.0211	1.6080	1.2681
No log	4.0	24	1.4422	0.0017	1.4405	1.2002
No log	5.0	30	1.3420	-0.0209	1.3403	1.1577
No log	6.0	36	1.2670	0.0344	1.2656	1.1250
No log	7.0	42	0.9193	0.0819	0.9182	0.9582
No log	8.0	48	1.2144	-0.0141	1.2130	1.1014
No log	9.0	54	1.0662	0.1158	1.0651	1.0320
No log	10.0	60	1.8399	-0.0361	1.8386	1.3560
No log	11.0	66	1.5351	0.0390	1.5340	1.2386
No log	12.0	72	1.1621	0.2271	1.1613	1.0776
No log	13.0	78	1.3350	0.1864	1.3345	1.1552
No log	14.0	84	1.4909	0.0775	1.4898	1.2206
No log	15.0	90	1.9570	-0.0145	1.9556	1.3984
No log	16.0	96	1.5167	0.1130	1.5158	1.2312
No log	17.0	102	1.3242	0.1447	1.3236	1.1505
No log	18.0	108	2.4283	-0.0815	2.4267	1.5578
No log	19.0	114	1.2833	0.1254	1.2823	1.1324
No log	20.0	120	1.2324	0.1462	1.2316	1.1098
No log	21.0	126	1.4772	0.1167	1.4759	1.2149
No log	22.0	132	1.6326	0.0780	1.6313	1.2772
No log	23.0	138	1.5154	0.0849	1.5143	1.2306
No log	24.0	144	1.1820	0.2075	1.1811	1.0868
No log	25.0	150	1.8399	0.0509	1.8385	1.3559
No log	26.0	156	1.5277	0.0221	1.5266	1.2355
No log	27.0	162	1.3047	0.1139	1.3036	1.1417

genki10/BERT_AugV8_k7_task1_organization_sp060_lw030_fold1

BERT_AugV8_k7_task1_organization_sp060_lw030_fold1