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	8.7362	0.0018	8.7362	2.9557
No log	2.0	6	6.1135	0.0118	6.1135	2.4726
No log	3.0	9	4.0014	0.0040	4.0014	2.0004
No log	4.0	12	2.8075	0.0040	2.8075	1.6756
No log	5.0	15	2.9217	-0.0120	2.9217	1.7093
No log	6.0	18	1.3470	0.0212	1.3470	1.1606
No log	7.0	21	1.0839	0.0212	1.0839	1.0411
No log	8.0	24	0.9911	0.0158	0.9911	0.9956
No log	9.0	27	0.9955	0.0474	0.9955	0.9978
No log	10.0	30	0.7599	0.3698	0.7599	0.8717
No log	11.0	33	1.1557	0.2127	1.1557	1.0750
No log	12.0	36	0.6778	0.4703	0.6778	0.8233
No log	13.0	39	1.4432	0.2261	1.4432	1.2013
No log	14.0	42	1.1830	0.2734	1.1830	1.0876
No log	15.0	45	0.7045	0.4254	0.7045	0.8394
No log	16.0	48	1.3562	0.2242	1.3562	1.1645
No log	17.0	51	0.6563	0.4632	0.6563	0.8101
No log	18.0	54	0.7253	0.4214	0.7253	0.8517
No log	19.0	57	1.5580	0.2122	1.5580	1.2482
No log	20.0	60	0.6577	0.4628	0.6577	0.8110
No log	21.0	63	0.5850	0.5163	0.5850	0.7649
No log	22.0	66	1.1601	0.3235	1.1601	1.0771
No log	23.0	69	0.9288	0.4051	0.9288	0.9637
No log	24.0	72	0.7846	0.4240	0.7846	0.8858
No log	25.0	75	1.3004	0.2375	1.3004	1.1404
No log	26.0	78	1.1518	0.2562	1.1518	1.0732
No log	27.0	81	0.9319	0.3427	0.9319	0.9654
No log	28.0	84	2.2148	0.0835	2.2148	1.4882
No log	29.0	87	2.2919	0.0841	2.2919	1.5139
No log	30.0	90	0.9309	0.3876	0.9309	0.9648
No log	31.0	93	1.3299	0.2699	1.3299	1.1532
No log	32.0	96	2.2157	0.0985	2.2157	1.4885
No log	33.0	99	1.0036	0.3028	1.0036	1.0018
No log	34.0	102	0.8995	0.2681	0.8995	0.9484
No log	35.0	105	1.6935	0.1983	1.6935	1.3013
No log	36.0	108	1.2583	0.2604	1.2583	1.1217

genki10/BERT_AugV8_k3_task1_organization_sp010_lw040_fold4

BERT_AugV8_k3_task1_organization_sp010_lw040_fold4