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	9.5544	0.0	9.5542	3.0910
No log	2.0	14	4.3386	0.0078	4.3389	2.0830
No log	3.0	21	1.4813	0.0318	1.4817	1.2173
No log	4.0	28	1.3458	0.0602	1.3463	1.1603
No log	5.0	35	1.4460	0.0590	1.4464	1.2026
No log	6.0	42	1.7130	0.1753	1.7132	1.3089
No log	7.0	49	0.7929	0.4037	0.7928	0.8904
No log	8.0	56	0.8731	0.3651	0.8727	0.9342
No log	9.0	63	1.2856	0.2907	1.2850	1.1336
No log	10.0	70	1.2660	0.2870	1.2656	1.1250
No log	11.0	77	1.9923	0.1750	1.9920	1.4114
No log	12.0	84	1.5340	0.2244	1.5339	1.2385
No log	13.0	91	1.3451	0.2353	1.3451	1.1598
No log	14.0	98	1.9980	0.1468	1.9980	1.4135
No log	15.0	105	1.6360	0.1613	1.6360	1.2791
No log	16.0	112	1.3555	0.2332	1.3554	1.1642
No log	17.0	119	1.3622	0.2065	1.3622	1.1671
No log	18.0	126	2.1652	0.1325	2.1653	1.4715
No log	19.0	133	1.9282	0.1598	1.9281	1.3886
No log	20.0	140	1.2900	0.1933	1.2900	1.1358
No log	21.0	147	1.2578	0.2188	1.2577	1.1215
No log	22.0	154	1.6623	0.1505	1.6624	1.2893

genki10/BERT_AugV8_k10_task1_organization_sp020_lw040_fold2

BERT_AugV8_k10_task1_organization_sp020_lw040_fold2