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	9.0355	0.0018	9.0329	3.0055
No log	2.0	4	8.2895	0.0	8.2871	2.8787
No log	3.0	6	7.3099	0.0	7.3076	2.7033
No log	4.0	8	6.1967	0.0	6.1944	2.4889
No log	5.0	10	5.1903	0.0079	5.1882	2.2778
No log	6.0	12	4.3282	0.0	4.3262	2.0800
No log	7.0	14	3.6393	0.0	3.6374	1.9072
No log	8.0	16	3.0089	0.0	3.0070	1.7341
No log	9.0	18	2.4917	0.0	2.4899	1.5779
No log	10.0	20	2.0159	0.0530	2.0141	1.4192
No log	11.0	22	1.6324	0.0418	1.6308	1.2770
No log	12.0	24	1.3331	0.0315	1.3316	1.1539
No log	13.0	26	1.2025	0.0106	1.2011	1.0959
No log	14.0	28	1.0128	0.0315	1.0114	1.0057
No log	15.0	30	0.9121	0.0545	0.9107	0.9543
No log	16.0	32	0.8064	0.4005	0.8052	0.8973
No log	17.0	34	0.7413	0.4496	0.7401	0.8603
No log	18.0	36	1.1252	0.2217	1.1238	1.0601
No log	19.0	38	0.7446	0.4595	0.7434	0.8622
No log	20.0	40	0.7240	0.3298	0.7230	0.8503
No log	21.0	42	0.6520	0.3986	0.6509	0.8068
No log	22.0	44	1.2350	0.2803	1.2335	1.1106
No log	23.0	46	1.6392	0.2094	1.6375	1.2797
No log	24.0	48	0.7407	0.3998	0.7392	0.8598
No log	25.0	50	0.7518	0.3673	0.7506	0.8664
No log	26.0	52	1.8641	0.0835	1.8628	1.3648
No log	27.0	54	1.8679	0.0860	1.8668	1.3663
No log	28.0	56	0.8986	0.2240	0.8975	0.9473
No log	29.0	58	0.8925	0.2127	0.8917	0.9443
No log	30.0	60	0.8772	0.2281	0.8761	0.9360
No log	31.0	62	1.4981	0.1361	1.4965	1.2233
No log	32.0	64	2.1072	0.0646	2.1058	1.4511
No log	33.0	66	1.6330	0.0670	1.6316	1.2774
No log	34.0	68	1.1434	0.1314	1.1423	1.0688

genki10/BERT_AugV8_k1_task1_organization_sp020_lw010_fold1

BERT_AugV8_k1_task1_organization_sp020_lw010_fold1