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	2	12.1317	0.0050	12.1321	3.4831
No log	2.0	4	10.0546	0.0018	10.0548	3.1709
No log	3.0	6	8.3893	0.0018	8.3896	2.8965
No log	4.0	8	6.9164	0.0	6.9169	2.6300
No log	5.0	10	5.1601	0.0189	5.1606	2.2717
No log	6.0	12	3.7377	0.0039	3.7383	1.9335
No log	7.0	14	2.9568	0.0039	2.9573	1.7197
No log	8.0	16	2.4365	0.0097	2.4369	1.5611
No log	9.0	18	1.8705	0.0213	1.8710	1.3679
No log	10.0	20	1.3790	0.0213	1.3795	1.1745
No log	11.0	22	1.1856	0.0107	1.1860	1.0890
No log	12.0	24	1.0608	0.0213	1.0612	1.0302
No log	13.0	26	0.9570	0.0345	0.9574	0.9785
No log	14.0	28	1.0166	0.0590	1.0169	1.0084
No log	15.0	30	0.9806	0.1376	0.9809	0.9904
No log	16.0	32	1.3307	0.2094	1.3311	1.1537
No log	17.0	34	0.9850	0.2616	0.9853	0.9926
No log	18.0	36	0.9722	0.2799	0.9725	0.9861
No log	19.0	38	1.5522	0.2139	1.5523	1.2459
No log	20.0	40	1.0850	0.2534	1.0849	1.0416
No log	21.0	42	0.7578	0.3823	0.7575	0.8704
No log	22.0	44	1.2003	0.2051	1.1996	1.0953
No log	23.0	46	1.1663	0.2257	1.1655	1.0796
No log	24.0	48	0.8633	0.3004	0.8626	0.9288
No log	25.0	50	1.4849	0.1971	1.4842	1.2183
No log	26.0	52	1.0921	0.2897	1.0914	1.0447
No log	27.0	54	0.8723	0.3305	0.8715	0.9336
No log	28.0	56	1.9825	0.1349	1.9815	1.4076
No log	29.0	58	1.9227	0.1520	1.9216	1.3862
No log	30.0	60	0.8183	0.3495	0.8176	0.9042
No log	31.0	62	0.7593	0.3692	0.7589	0.8712
No log	32.0	64	1.1302	0.2805	1.1299	1.0630
No log	33.0	66	2.0310	0.1475	2.0307	1.4250
No log	34.0	68	1.6717	0.2167	1.6712	1.2928
No log	35.0	70	0.9548	0.3338	0.9541	0.9768
No log	36.0	72	1.2153	0.2585	1.2145	1.1021

genki10/Trial2BERT_AugV8_k1_task1_organization_sp010_lw070_fold2

Trial2BERT_AugV8_k1_task1_organization_sp010_lw070_fold2