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	12.8477	0.0	12.8455	3.5841
No log	2.0	6	10.9734	-0.0015	10.9714	3.3123
No log	3.0	9	7.6486	0.0	7.6468	2.7653
No log	4.0	12	5.2897	0.0175	5.2883	2.2996
No log	5.0	15	3.8585	0.0	3.8574	1.9640
No log	6.0	18	2.4688	0.1029	2.4679	1.5710
No log	7.0	21	1.4751	0.0401	1.4745	1.2143
No log	8.0	24	1.1948	0.0102	1.1943	1.0928
No log	9.0	27	0.9430	0.0722	0.9426	0.9709
No log	10.0	30	1.4646	0.0925	1.4641	1.2100
No log	11.0	33	0.9001	0.1820	0.8997	0.9485
No log	12.0	36	0.9458	0.1375	0.9453	0.9723
No log	13.0	39	1.4076	0.1513	1.4073	1.1863
No log	14.0	42	2.1236	0.1233	2.1234	1.4572
No log	15.0	45	1.0217	0.2608	1.0219	1.0109
No log	16.0	48	2.4324	0.1176	2.4325	1.5597
No log	17.0	51	0.9177	0.3403	0.9182	0.9582
No log	18.0	54	1.1420	0.2715	1.1425	1.0689
No log	19.0	57	2.1200	0.1531	2.1204	1.4562
No log	20.0	60	0.8265	0.3498	0.8272	0.9095
No log	21.0	63	1.2693	0.2745	1.2702	1.1270
No log	22.0	66	2.0475	0.1327	2.0484	1.4312
No log	23.0	69	1.4315	0.2322	1.4324	1.1968
No log	24.0	72	1.9517	0.1329	1.9526	1.3974
No log	25.0	75	1.3444	0.2243	1.3452	1.1598
No log	26.0	78	2.1915	0.1373	2.1921	1.4806
No log	27.0	81	1.2255	0.2971	1.2261	1.1073
No log	28.0	84	1.3536	0.2907	1.3541	1.1636
No log	29.0	87	2.2465	0.1356	2.2469	1.4990
No log	30.0	90	1.1835	0.2845	1.1840	1.0881
No log	31.0	93	2.3712	0.1057	2.3718	1.5401
No log	32.0	96	2.2230	0.1016	2.2236	1.4912
No log	33.0	99	1.5063	0.1873	1.5070	1.2276
No log	34.0	102	2.5575	0.1036	2.5582	1.5994
No log	35.0	105	1.6821	0.2044	1.6829	1.2973

genki10/BERT_AugV8_k3_task1_organization_sp020_lw040_fold3

BERT_AugV8_k3_task1_organization_sp020_lw040_fold3