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	6.9986	0.0018	6.9986	2.6455
No log	2.0	12	3.2986	0.0040	3.2986	1.8162
No log	3.0	18	1.5889	0.0509	1.5889	1.2605
No log	4.0	24	2.5077	0.0633	2.5077	1.5836
No log	5.0	30	1.6784	0.1400	1.6784	1.2955
No log	6.0	36	1.2747	0.0694	1.2747	1.1290
No log	7.0	42	0.8171	0.3794	0.8171	0.9040
No log	8.0	48	0.9671	0.3560	0.9671	0.9834
No log	9.0	54	0.6165	0.4170	0.6165	0.7852
No log	10.0	60	0.7601	0.4553	0.7601	0.8718
No log	11.0	66	1.0216	0.3715	1.0216	1.0107
No log	12.0	72	1.8056	0.1883	1.8056	1.3437
No log	13.0	78	0.8427	0.4465	0.8427	0.9180
No log	14.0	84	0.8376	0.4574	0.8376	0.9152
No log	15.0	90	1.0525	0.3200	1.0526	1.0259
No log	16.0	96	1.1972	0.3434	1.1972	1.0942
No log	17.0	102	0.9160	0.3961	0.9160	0.9571
No log	18.0	108	0.8218	0.4038	0.8218	0.9066
No log	19.0	114	0.9627	0.3569	0.9627	0.9812
No log	20.0	120	1.0769	0.3519	1.0769	1.0377
No log	21.0	126	1.1391	0.3710	1.1391	1.0673
No log	22.0	132	0.8961	0.3750	0.8961	0.9466
No log	23.0	138	0.8416	0.3645	0.8416	0.9174
No log	24.0	144	1.3868	0.2469	1.3868	1.1776
No log	25.0	150	1.4491	0.2486	1.4491	1.2038
No log	26.0	156	0.8228	0.3952	0.8228	0.9071
No log	27.0	162	0.8252	0.4050	0.8252	0.9084
No log	28.0	168	0.9975	0.3413	0.9975	0.9987
No log	29.0	174	0.8458	0.3715	0.8458	0.9197

genki10/BERT_AugV8_k7_task1_organization_sp030_lw050_fold4

BERT_AugV8_k7_task1_organization_sp030_lw050_fold4