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	3	8.1424	0.0	8.1423	2.8535
No log	2.0	6	5.4467	0.0340	5.4470	2.3339
No log	3.0	9	3.8812	0.0	3.8815	1.9701
No log	4.0	12	2.7408	0.0	2.7412	1.6557
No log	5.0	15	1.8694	0.0615	1.8698	1.3674
No log	6.0	18	1.4758	0.0107	1.4761	1.2150
No log	7.0	21	1.2015	0.0107	1.2018	1.0963
No log	8.0	24	1.0202	0.0107	1.0205	1.0102
No log	9.0	27	1.7766	-0.0062	1.7767	1.3329
No log	10.0	30	0.8023	0.3264	0.8026	0.8959
No log	11.0	33	0.8835	0.3160	0.8836	0.9400
No log	12.0	36	0.7102	0.4432	0.7104	0.8428
No log	13.0	39	0.7106	0.3716	0.7107	0.8430
No log	14.0	42	0.6286	0.3710	0.6287	0.7929
No log	15.0	45	0.8555	0.3620	0.8551	0.9247
No log	16.0	48	0.5286	0.4631	0.5285	0.7270
No log	17.0	51	0.8810	0.3374	0.8807	0.9384
No log	18.0	54	0.7820	0.3688	0.7819	0.8842
No log	19.0	57	0.9066	0.3370	0.9063	0.9520
No log	20.0	60	0.7003	0.4517	0.7001	0.8367
No log	21.0	63	1.1314	0.3048	1.1308	1.0634
No log	22.0	66	0.7666	0.3793	0.7664	0.8754
No log	23.0	69	1.1096	0.2306	1.1091	1.0532
No log	24.0	72	0.8721	0.3402	0.8722	0.9339
No log	25.0	75	1.3024	0.0706	1.3023	1.1412
No log	26.0	78	0.8118	0.3569	0.8120	0.9011
No log	27.0	81	1.1193	0.1766	1.1192	1.0579
No log	28.0	84	0.7755	0.3870	0.7754	0.8806
No log	29.0	87	1.3419	0.2068	1.3415	1.1583
No log	30.0	90	0.8039	0.3512	0.8037	0.8965
No log	31.0	93	1.3435	0.1784	1.3431	1.1589

genki10/BERT_AugV8_k3_task1_organization_sp020_lw060_fold2

BERT_AugV8_k3_task1_organization_sp020_lw060_fold2