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	5.9308	0.0205	5.9308	2.4353
No log	2.0	16	1.8942	0.1546	1.8942	1.3763
No log	3.0	24	2.2657	0.1508	2.2657	1.5052
No log	4.0	32	1.6470	0.1331	1.6470	1.2833
No log	5.0	40	0.8460	0.3495	0.8460	0.9198
No log	6.0	48	0.7239	0.4472	0.7239	0.8508
No log	7.0	56	0.6609	0.4787	0.6609	0.8130
No log	8.0	64	1.0972	0.2891	1.0972	1.0475
No log	9.0	72	1.1604	0.2957	1.1604	1.0772
No log	10.0	80	1.0379	0.3264	1.0379	1.0188
No log	11.0	88	1.1757	0.2797	1.1757	1.0843
No log	12.0	96	1.1052	0.2965	1.1052	1.0513
No log	13.0	104	0.7505	0.4267	0.7505	0.8663
No log	14.0	112	0.8190	0.4210	0.8190	0.9050
No log	15.0	120	1.0278	0.2757	1.0278	1.0138
No log	16.0	128	0.8547	0.3563	0.8547	0.9245
No log	17.0	136	1.0066	0.3525	1.0066	1.0033
No log	18.0	144	0.7492	0.4158	0.7492	0.8655
No log	19.0	152	0.7771	0.3937	0.7771	0.8816
No log	20.0	160	1.0577	0.2906	1.0577	1.0284
No log	21.0	168	0.7342	0.4079	0.7342	0.8569
No log	22.0	176	0.8192	0.3695	0.8192	0.9051

genki10/BERT_AugV8_k10_task1_organization_sp040_lw040_fold4

BERT_AugV8_k10_task1_organization_sp040_lw040_fold4