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	4	9.7615	0.0	9.7590	3.1239
No log	2.0	8	6.6846	0.0	6.6824	2.5850
No log	3.0	12	4.4076	0.0	4.4056	2.0990
No log	4.0	16	2.8216	0.0	2.8198	1.6792
No log	5.0	20	1.7342	0.0211	1.7326	1.3163
No log	6.0	24	1.2176	0.0	1.2160	1.1027
No log	7.0	28	1.0405	0.0	1.0389	1.0193
No log	8.0	32	1.2372	0.0543	1.2351	1.1113
No log	9.0	36	1.0589	0.1227	1.0567	1.0279
No log	10.0	40	0.8875	0.2488	0.8856	0.9410
No log	11.0	44	0.8974	0.2820	0.8956	0.9463
No log	12.0	48	0.9976	0.2501	0.9956	0.9978
No log	13.0	52	1.2901	0.1597	1.2876	1.1347
No log	14.0	56	1.2293	0.2232	1.2269	1.1076
No log	15.0	60	1.7096	0.1798	1.7068	1.3064
No log	16.0	64	1.1991	0.2545	1.1967	1.0940
No log	17.0	68	1.5244	0.1796	1.5217	1.2336
No log	18.0	72	1.1131	0.2321	1.1108	1.0540
No log	19.0	76	1.2368	0.2256	1.2344	1.1110
No log	20.0	80	1.3863	0.2355	1.3836	1.1763
No log	21.0	84	1.0656	0.2604	1.0634	1.0312
No log	22.0	88	1.2243	0.2656	1.2218	1.1053
No log	23.0	92	1.1561	0.2530	1.1537	1.0741
No log	24.0	96	1.5404	0.1994	1.5376	1.2400
No log	25.0	100	1.1215	0.2294	1.1192	1.0579
No log	26.0	104	1.3641	0.2286	1.3614	1.1668

genki10/BERT_AugV8_k5_task1_organization_sp060_lw010_fold1

BERT_AugV8_k5_task1_organization_sp060_lw010_fold1