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	7	9.0005	0.0018	9.0005	3.0001
No log	2.0	14	4.2757	0.0079	4.2757	2.0678
No log	3.0	21	1.3616	0.0445	1.3616	1.1669
No log	4.0	28	1.3804	0.0507	1.3804	1.1749
No log	5.0	35	2.5524	0.0800	2.5524	1.5976
No log	6.0	42	1.4273	0.2295	1.4273	1.1947
No log	7.0	49	1.3416	0.2122	1.3416	1.1583
No log	8.0	56	1.2169	0.2153	1.2169	1.1031
No log	9.0	63	1.5792	0.1803	1.5792	1.2566
No log	10.0	70	1.9097	0.1602	1.9097	1.3819
No log	11.0	77	1.5795	0.1985	1.5795	1.2568
No log	12.0	84	1.8202	0.1351	1.8202	1.3492
No log	13.0	91	2.3274	0.0952	2.3274	1.5256
No log	14.0	98	1.7344	0.1687	1.7344	1.3170
No log	15.0	105	1.4585	0.2215	1.4585	1.2077
No log	16.0	112	1.2749	0.2841	1.2749	1.1291
No log	17.0	119	1.6176	0.1705	1.6176	1.2719
No log	18.0	126	1.5430	0.1892	1.5430	1.2422
No log	19.0	133	2.0419	0.1330	2.0419	1.4289
No log	20.0	140	2.0100	0.1339	2.0100	1.4177
No log	21.0	147	1.3546	0.2461	1.3546	1.1639
No log	22.0	154	1.2415	0.2480	1.2415	1.1142
No log	23.0	161	1.4474	0.1924	1.4474	1.2031
No log	24.0	168	1.5689	0.1843	1.5689	1.2525
No log	25.0	175	1.7315	0.1826	1.7315	1.3159
No log	26.0	182	1.7916	0.1815	1.7916	1.3385
No log	27.0	189	1.4596	0.1701	1.4596	1.2082
No log	28.0	196	1.5257	0.1814	1.5257	1.2352
No log	29.0	203	1.7928	0.1674	1.7928	1.3390
No log	30.0	210	1.7681	0.1845	1.7681	1.3297
No log	31.0	217	1.4131	0.2083	1.4131	1.1887

genki10/BERT_AugV8_k10_task1_organization_sp030_lw040_fold4

BERT_AugV8_k10_task1_organization_sp030_lw040_fold4