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	4.6891	0.0317	4.6891	2.1654
No log	2.0	16	1.9483	0.0482	1.9483	1.3958
No log	3.0	24	1.2311	0.0420	1.2311	1.1096
No log	4.0	32	1.2272	0.0445	1.2272	1.1078
No log	5.0	40	1.0779	0.1576	1.0779	1.0382
No log	6.0	48	0.7091	0.3636	0.7091	0.8421
No log	7.0	56	0.7478	0.4113	0.7478	0.8647
No log	8.0	64	0.8300	0.4268	0.8300	0.9110
No log	9.0	72	0.8095	0.4410	0.8095	0.8997
No log	10.0	80	1.2651	0.3397	1.2651	1.1247
No log	11.0	88	1.1104	0.3771	1.1104	1.0537
No log	12.0	96	1.1698	0.3275	1.1698	1.0816
No log	13.0	104	0.8678	0.4082	0.8678	0.9316
No log	14.0	112	1.2281	0.2617	1.2281	1.1082
No log	15.0	120	1.7343	0.2177	1.7343	1.3169
No log	16.0	128	1.3414	0.2845	1.3414	1.1582
No log	17.0	136	1.5058	0.2624	1.5058	1.2271
No log	18.0	144	1.1916	0.3020	1.1916	1.0916
No log	19.0	152	1.5406	0.2539	1.5406	1.2412
No log	20.0	160	1.2182	0.2726	1.2182	1.1037
No log	21.0	168	1.0443	0.2800	1.0443	1.0219
No log	22.0	176	1.0519	0.3263	1.0519	1.0256
No log	23.0	184	0.8335	0.3703	0.8335	0.9130
No log	24.0	192	1.4502	0.2113	1.4502	1.2042

genki10/BERT_AugV8_k10_task1_organization_sp010_lw070_fold4

BERT_AugV8_k10_task1_organization_sp010_lw070_fold4