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	6	8.6554	0.0	8.6529	2.9416
No log	2.0	12	6.2729	0.0	6.2706	2.5041
No log	3.0	18	3.9664	0.0	3.9644	1.9911
No log	4.0	24	3.0100	0.0	3.0079	1.7343
No log	5.0	30	1.5913	0.0315	1.5898	1.2609
No log	6.0	36	1.0903	0.0	1.0889	1.0435
No log	7.0	42	1.8557	0.1308	1.8541	1.3616
No log	8.0	48	0.8193	0.3639	0.8181	0.9045
No log	9.0	54	0.8367	0.3461	0.8357	0.9141
No log	10.0	60	0.7511	0.3069	0.7502	0.8661
No log	11.0	66	1.0521	0.2536	1.0509	1.0251
No log	12.0	72	2.2372	0.1198	2.2360	1.4953
No log	13.0	78	1.2889	0.2961	1.2876	1.1347
No log	14.0	84	0.8154	0.4702	0.8144	0.9024
No log	15.0	90	2.3894	0.1336	2.3882	1.5454
No log	16.0	96	1.2594	0.3078	1.2580	1.1216
No log	17.0	102	1.0829	0.3098	1.0815	1.0400
No log	18.0	108	1.2699	0.2570	1.2684	1.1262
No log	19.0	114	1.5190	0.2224	1.5172	1.2317
No log	20.0	120	1.4688	0.2053	1.4671	1.2112
No log	21.0	126	1.6061	0.1577	1.6045	1.2667
No log	22.0	132	1.5481	0.2682	1.5467	1.2437
No log	23.0	138	1.2956	0.3119	1.2944	1.1377
No log	24.0	144	1.4574	0.2751	1.4560	1.2066
No log	25.0	150	0.8813	0.3815	0.8801	0.9381
No log	26.0	156	1.2048	0.2676	1.2034	1.0970
No log	27.0	162	2.0331	0.1497	2.0313	1.4252
No log	28.0	168	0.9291	0.3540	0.9279	0.9633
No log	29.0	174	1.0247	0.2709	1.0235	1.0117

genki10/BERT_AugV8_k7_task1_organization_sp040_lw030_fold1

BERT_AugV8_k7_task1_organization_sp040_lw030_fold1