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	8	4.7496	0.0	4.7476	2.1789
No log	2.0	16	2.3955	0.0114	2.3937	1.5472
No log	3.0	24	1.9842	0.0792	1.9824	1.4080
No log	4.0	32	1.7106	0.0106	1.7089	1.3073
No log	5.0	40	1.1416	0.0390	1.1401	1.0678
No log	6.0	48	0.8838	0.1363	0.8827	0.9395
No log	7.0	56	0.6646	0.3669	0.6636	0.8146
No log	8.0	64	0.8583	0.2242	0.8571	0.9258
No log	9.0	72	0.6920	0.3522	0.6909	0.8312
No log	10.0	80	0.8296	0.3079	0.8285	0.9102
No log	11.0	88	0.8134	0.4114	0.8125	0.9014
No log	12.0	96	1.0300	0.2446	1.0288	1.0143
No log	13.0	104	1.0521	0.2875	1.0508	1.0251
No log	14.0	112	1.0116	0.3258	1.0105	1.0052
No log	15.0	120	1.3496	0.1742	1.3482	1.1611
No log	16.0	128	1.4310	0.2161	1.4298	1.1957
No log	17.0	136	1.5245	0.1186	1.5231	1.2341
No log	18.0	144	1.2242	0.1981	1.2230	1.1059
No log	19.0	152	1.1662	0.2661	1.1649	1.0793
No log	20.0	160	1.2428	0.2597	1.2415	1.1142
No log	21.0	168	1.3563	0.2050	1.3550	1.1641
No log	22.0	176	1.4769	0.1900	1.4758	1.2148
No log	23.0	184	1.1538	0.2640	1.1529	1.0738
No log	24.0	192	1.4230	0.1761	1.4223	1.1926
No log	25.0	200	1.5210	0.1096	1.5199	1.2328
No log	26.0	208	1.4941	0.0787	1.4930	1.2219

genki10/BERT_AugV8_k10_task1_organization_sp020_lw070_fold1

BERT_AugV8_k10_task1_organization_sp020_lw070_fold1