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	5.0702	0.0588	5.0678	2.2512
No log	2.0	16	1.7267	0.0790	1.7251	1.3134
No log	3.0	24	2.1281	0.0982	2.1264	1.4582
No log	4.0	32	1.0165	0.0752	1.0152	1.0076
No log	5.0	40	0.7479	0.3969	0.7467	0.8641
No log	6.0	48	0.8517	0.1833	0.8508	0.9224
No log	7.0	56	0.7229	0.2919	0.7217	0.8495
No log	8.0	64	0.9707	0.1636	0.9699	0.9848
No log	9.0	72	1.1237	0.1666	1.1223	1.0594
No log	10.0	80	1.8111	0.0362	1.8098	1.3453
No log	11.0	88	0.8372	0.3123	0.8360	0.9143
No log	12.0	96	1.1335	0.1832	1.1320	1.0640
No log	13.0	104	1.6061	0.1375	1.6045	1.2667
No log	14.0	112	2.9331	-0.0019	2.9314	1.7121
No log	15.0	120	1.8439	0.0913	1.8424	1.3574
No log	16.0	128	1.5125	0.1260	1.5109	1.2292
No log	17.0	136	1.0875	0.2368	1.0861	1.0422
No log	18.0	144	1.2625	0.1817	1.2610	1.1229
No log	19.0	152	1.6770	0.0896	1.6754	1.2944
No log	20.0	160	1.6108	0.1549	1.6093	1.2686

genki10/BERT_AugV8_k10_task1_organization_sp010_lw070_fold1

BERT_AugV8_k10_task1_organization_sp010_lw070_fold1