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	8.4033	0.0	8.4034	2.8989
No log	2.0	14	5.6110	0.0255	5.6113	2.3688
No log	3.0	21	2.8472	0.0	2.8477	1.6875
No log	4.0	28	1.3557	0.0213	1.3561	1.1645
No log	5.0	35	0.8710	0.0700	0.8714	0.9335
No log	6.0	42	0.8989	0.0893	0.8992	0.9483
No log	7.0	49	1.0182	0.2810	1.0178	1.0089
No log	8.0	56	0.7179	0.3848	0.7175	0.8470
No log	9.0	63	0.8856	0.3420	0.8850	0.9407
No log	10.0	70	2.0192	0.1648	2.0188	1.4209
No log	11.0	77	1.1600	0.2599	1.1597	1.0769
No log	12.0	84	1.2253	0.3146	1.2246	1.1066
No log	13.0	91	0.8655	0.3730	0.8649	0.9300
No log	14.0	98	0.7405	0.4079	0.7402	0.8603
No log	15.0	105	0.9094	0.3374	0.9092	0.9535
No log	16.0	112	1.4145	0.1932	1.4144	1.1893
No log	17.0	119	1.7604	0.1448	1.7603	1.3268
No log	18.0	126	1.5403	0.1855	1.5398	1.2409
No log	19.0	133	1.2772	0.2100	1.2768	1.1300
No log	20.0	140	2.0732	0.1323	2.0728	1.4397
No log	21.0	147	0.8322	0.3392	0.8317	0.9120
No log	22.0	154	1.0084	0.2958	1.0081	1.0040
No log	23.0	161	0.9563	0.2863	0.9562	0.9779
No log	24.0	168	1.2733	0.2523	1.2729	1.1282
No log	25.0	175	1.6302	0.2033	1.6298	1.2766
No log	26.0	182	1.6409	0.1705	1.6409	1.2810
No log	27.0	189	1.5234	0.1579	1.5232	1.2342
No log	28.0	196	1.5736	0.1827	1.5733	1.2543
No log	29.0	203	1.5481	0.1786	1.5478	1.2441

genki10/BERT_AugV8_k10_task1_organization_sp040_lw010_fold2

BERT_AugV8_k10_task1_organization_sp040_lw010_fold2