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	6.2462	0.0363	6.2466	2.4993
No log	2.0	16	2.6964	0.0123	2.6969	1.6422
No log	3.0	24	1.4769	0.0475	1.4774	1.2155
No log	4.0	32	1.4086	0.0727	1.4089	1.1870
No log	5.0	40	1.2801	0.1058	1.2803	1.1315
No log	6.0	48	1.8969	0.1418	1.8969	1.3773
No log	7.0	56	1.3211	0.1537	1.3212	1.1494
No log	8.0	64	2.2138	0.1390	2.2125	1.4875
No log	9.0	72	2.5516	0.1064	2.5510	1.5972
No log	10.0	80	2.2097	0.1346	2.2090	1.4863
No log	11.0	88	1.3693	0.1693	1.3686	1.1699
No log	12.0	96	2.2807	0.1241	2.2802	1.5100
No log	13.0	104	1.4513	0.1853	1.4506	1.2044
No log	14.0	112	2.6301	0.0867	2.6297	1.6216
No log	15.0	120	1.8613	0.1428	1.8607	1.3641
No log	16.0	128	2.1473	0.1316	2.1468	1.4652
No log	17.0	136	2.2348	0.1391	2.2342	1.4947
No log	18.0	144	1.6949	0.1790	1.6942	1.3016
No log	19.0	152	1.8120	0.1628	1.8115	1.3459
No log	20.0	160	1.8037	0.1492	1.8031	1.3428
No log	21.0	168	1.9717	0.1444	1.9710	1.4039
No log	22.0	176	2.2054	0.1613	2.2046	1.4848
No log	23.0	184	2.1793	0.1254	2.1786	1.4760
No log	24.0	192	1.5665	0.1603	1.5659	1.2514
No log	25.0	200	1.8656	0.1628	1.8647	1.3656
No log	26.0	208	1.9227	0.1622	1.9216	1.3862
No log	27.0	216	1.9632	0.1373	1.9622	1.4008
No log	28.0	224	1.6156	0.1607	1.6146	1.2707

genki10/BERT_AugV8_k10_task1_organization_sp060_lw040_fold2

BERT_AugV8_k10_task1_organization_sp060_lw040_fold2