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	9.1321	0.0018	9.1321	3.0219
No log	2.0	12	6.2764	0.0	6.2764	2.5053
No log	3.0	18	3.2901	0.0	3.2901	1.8139
No log	4.0	24	1.7327	0.0213	1.7327	1.3163
No log	5.0	30	1.0562	0.0213	1.0562	1.0277
No log	6.0	36	1.0618	0.0622	1.0618	1.0305
No log	7.0	42	1.0191	0.2568	1.0191	1.0095
No log	8.0	48	0.6202	0.5296	0.6202	0.7875
No log	9.0	54	1.2013	0.3489	1.2013	1.0960
No log	10.0	60	1.0316	0.3559	1.0316	1.0157
No log	11.0	66	1.6029	0.2753	1.6029	1.2661
No log	12.0	72	1.4025	0.2998	1.4025	1.1843
No log	13.0	78	1.0077	0.3892	1.0077	1.0038
No log	14.0	84	1.0516	0.3943	1.0516	1.0255
No log	15.0	90	1.2161	0.3871	1.2161	1.1028
No log	16.0	96	1.1736	0.3835	1.1736	1.0833
No log	17.0	102	1.6871	0.2359	1.6871	1.2989
No log	18.0	108	0.6921	0.5364	0.6921	0.8319
No log	19.0	114	0.8041	0.4655	0.8041	0.8967
No log	20.0	120	1.1788	0.3266	1.1788	1.0857
No log	21.0	126	1.0861	0.3539	1.0861	1.0421
No log	22.0	132	1.3213	0.3122	1.3213	1.1495
No log	23.0	138	1.2438	0.3142	1.2438	1.1152
No log	24.0	144	0.9461	0.3867	0.9461	0.9727
No log	25.0	150	1.1063	0.3168	1.1063	1.0518
No log	26.0	156	1.1044	0.3495	1.1044	1.0509
No log	27.0	162	1.0618	0.3474	1.0618	1.0304
No log	28.0	168	1.0497	0.3465	1.0497	1.0246
No log	29.0	174	1.0400	0.3770	1.0400	1.0198
No log	30.0	180	1.1378	0.3376	1.1378	1.0667
No log	31.0	186	1.1114	0.3866	1.1114	1.0542
No log	32.0	192	0.9298	0.4154	0.9298	0.9643
No log	33.0	198	0.8106	0.4481	0.8106	0.9003

genki10/BERT_AugV8_k10_task1_organization_sp020_lw010_fold4

BERT_AugV8_k10_task1_organization_sp020_lw010_fold4