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	9.2723	0.0	9.2698	3.0446
No log	2.0	6	8.6542	0.0	8.6517	2.9414
No log	3.0	9	7.3019	0.0	7.2996	2.7018
No log	4.0	12	6.1902	0.0	6.1879	2.4876
No log	5.0	15	4.9551	0.0118	4.9530	2.2255
No log	6.0	18	3.7495	0.0	3.7475	1.9359
No log	7.0	21	2.8728	0.0	2.8709	1.6944
No log	8.0	24	2.0716	0.1089	2.0699	1.4387
No log	9.0	27	1.4895	0.0315	1.4880	1.2198
No log	10.0	30	1.1622	0.0	1.1608	1.0774
No log	11.0	33	0.9378	0.0106	0.9365	0.9677
No log	12.0	36	0.8805	0.0905	0.8792	0.9377
No log	13.0	39	0.7475	0.4383	0.7464	0.8639
No log	14.0	42	1.2251	0.1333	1.2239	1.1063
No log	15.0	45	1.3880	0.2073	1.3868	1.1776
No log	16.0	48	0.7666	0.4326	0.7657	0.8750
No log	17.0	51	1.4205	0.2354	1.4196	1.1915
No log	18.0	54	0.6755	0.4270	0.6747	0.8214
No log	19.0	57	0.7897	0.3813	0.7890	0.8882
No log	20.0	60	1.1075	0.3812	1.1071	1.0522
No log	21.0	63	0.9446	0.4456	0.9446	0.9719
No log	22.0	66	1.5470	0.2514	1.5468	1.2437
No log	23.0	69	1.1299	0.3313	1.1294	1.0627
No log	24.0	72	1.2414	0.3354	1.2409	1.1140
No log	25.0	75	1.9959	0.1861	1.9952	1.4125
No log	26.0	78	1.3031	0.3255	1.3025	1.1413
No log	27.0	81	1.8178	0.1872	1.8169	1.3479
No log	28.0	84	1.0184	0.3599	1.0175	1.0087
No log	29.0	87	1.2883	0.3012	1.2875	1.1347
No log	30.0	90	1.6562	0.2326	1.6555	1.2867
No log	31.0	93	1.0577	0.3719	1.0571	1.0282
No log	32.0	96	1.6187	0.2649	1.6181	1.2720
No log	33.0	99	0.9748	0.3719	0.9741	0.9870
No log	34.0	102	1.3310	0.2852	1.3302	1.1533
No log	35.0	105	0.9972	0.3778	0.9966	0.9983
No log	36.0	108	2.1187	0.1917	2.1181	1.4554

genki10/Trial3BERT_AugV8_k3_task1_organization_sp040_lw010_fold1

Trial3BERT_AugV8_k3_task1_organization_sp040_lw010_fold1