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	10.2632	0.0018	10.2632	3.2036
No log	2.0	6	8.6120	0.0018	8.6120	2.9346
No log	3.0	9	6.0321	0.0068	6.0321	2.4560
No log	4.0	12	4.3963	0.0079	4.3963	2.0967
No log	5.0	15	3.1463	0.0040	3.1463	1.7738
No log	6.0	18	2.0252	0.0871	2.0252	1.4231
No log	7.0	21	1.3693	0.0420	1.3693	1.1702
No log	8.0	24	1.2523	0.0420	1.2523	1.1190
No log	9.0	27	1.3339	0.0937	1.3339	1.1549
No log	10.0	30	1.5403	0.1607	1.5403	1.2411
No log	11.0	33	1.6191	0.1886	1.6191	1.2725
No log	12.0	36	1.9260	0.1837	1.9260	1.3878
No log	13.0	39	1.2298	0.1763	1.2298	1.1090
No log	14.0	42	2.3041	0.1069	2.3041	1.5179
No log	15.0	45	1.0832	0.2428	1.0832	1.0408
No log	16.0	48	1.6270	0.2077	1.6270	1.2755
No log	17.0	51	1.3100	0.2614	1.3100	1.1445
No log	18.0	54	1.4185	0.2406	1.4185	1.1910
No log	19.0	57	1.4758	0.2274	1.4758	1.2148
No log	20.0	60	1.1627	0.3427	1.1627	1.0783
No log	21.0	63	2.0481	0.1838	2.0481	1.4311
No log	22.0	66	1.5240	0.2679	1.5240	1.2345
No log	23.0	69	1.9321	0.1729	1.9321	1.3900
No log	24.0	72	1.1132	0.3328	1.1132	1.0551
No log	25.0	75	2.2853	0.1178	2.2853	1.5117
No log	26.0	78	1.2582	0.2863	1.2582	1.1217
No log	27.0	81	2.1046	0.1067	2.1046	1.4507
No log	28.0	84	1.2813	0.2557	1.2813	1.1319
No log	29.0	87	1.9701	0.1310	1.9701	1.4036
No log	30.0	90	1.4356	0.2405	1.4356	1.1982
No log	31.0	93	2.2671	0.1154	2.2671	1.5057
No log	32.0	96	1.3078	0.2595	1.3078	1.1436
No log	33.0	99	2.3730	0.1139	2.3730	1.5405
No log	34.0	102	1.4643	0.2296	1.4643	1.2101
No log	35.0	105	1.5844	0.1644	1.5844	1.2587

genki10/BERT_AugV8_k3_task1_organization_sp020_lw070_fold4

BERT_AugV8_k3_task1_organization_sp020_lw070_fold4