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	5	9.3913	0.0	9.3895	3.0642
No log	2.0	10	7.5701	0.0	7.5685	2.7511
No log	3.0	15	5.3462	0.0160	5.3451	2.3120
No log	4.0	20	3.2663	0.0	3.2654	1.8070
No log	5.0	25	1.9325	0.0574	1.9319	1.3899
No log	6.0	30	1.0891	0.0102	1.0886	1.0434
No log	7.0	35	0.8779	0.3557	0.8775	0.9368
No log	8.0	40	1.0286	0.0463	1.0283	1.0141
No log	9.0	45	0.8693	0.2882	0.8690	0.9322
No log	10.0	50	0.6982	0.3366	0.6983	0.8356
No log	11.0	55	0.7141	0.2612	0.7143	0.8452
No log	12.0	60	0.7527	0.2779	0.7530	0.8678
No log	13.0	65	0.6920	0.3350	0.6924	0.8321
No log	14.0	70	0.5826	0.4495	0.5825	0.7632
No log	15.0	75	0.7739	0.4010	0.7740	0.8798
No log	16.0	80	0.6404	0.5013	0.6403	0.8002
No log	17.0	85	0.6081	0.5232	0.6082	0.7798
No log	18.0	90	0.7206	0.4505	0.7207	0.8489
No log	19.0	95	0.7358	0.4683	0.7358	0.8578
No log	20.0	100	0.7924	0.3989	0.7923	0.8901
No log	21.0	105	1.1560	0.2732	1.1559	1.0751
No log	22.0	110	0.7205	0.4835	0.7207	0.8489
No log	23.0	115	0.7920	0.4003	0.7921	0.8900
No log	24.0	120	0.7929	0.3972	0.7930	0.8905
No log	25.0	125	0.7862	0.4127	0.7862	0.8867
No log	26.0	130	0.7083	0.4744	0.7085	0.8417
No log	27.0	135	0.7420	0.4616	0.7421	0.8615
No log	28.0	140	0.8471	0.3815	0.8469	0.9203
No log	29.0	145	0.8676	0.4205	0.8675	0.9314
No log	30.0	150	0.6644	0.4977	0.6646	0.8152
No log	31.0	155	0.6642	0.4925	0.6644	0.8151
No log	32.0	160	0.8152	0.4171	0.8154	0.9030

genki10/Trial3BERT_AugV8_k7_task1_organization_sp010_lw030_fold3

Trial3BERT_AugV8_k7_task1_organization_sp010_lw030_fold3