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	8.1824	0.0	8.1824	2.8605
No log	2.0	6	5.0496	0.0109	5.0496	2.2471
No log	3.0	9	3.3551	0.0040	3.3551	1.8317
No log	4.0	12	2.9167	0.0040	2.9167	1.7078
No log	5.0	15	1.7583	0.0445	1.7583	1.3260
No log	6.0	18	1.2818	0.0212	1.2818	1.1322
No log	7.0	21	1.0392	0.0212	1.0392	1.0194
No log	8.0	24	0.9833	0.0489	0.9833	0.9916
No log	9.0	27	0.9321	0.0957	0.9321	0.9655
No log	10.0	30	0.9489	0.0962	0.9489	0.9741
No log	11.0	33	0.8293	0.4601	0.8293	0.9106
No log	12.0	36	1.0543	0.3402	1.0543	1.0268
No log	13.0	39	0.9430	0.3220	0.9430	0.9711
No log	14.0	42	1.1953	0.1918	1.1953	1.0933
No log	15.0	45	0.9429	0.3617	0.9429	0.9710
No log	16.0	48	1.0814	0.3464	1.0814	1.0399
No log	17.0	51	0.9447	0.4427	0.9447	0.9720
No log	18.0	54	1.5971	0.2825	1.5971	1.2638
No log	19.0	57	1.1033	0.4043	1.1033	1.0504
No log	20.0	60	1.4624	0.3004	1.4624	1.2093
No log	21.0	63	1.1444	0.3836	1.1444	1.0698
No log	22.0	66	1.1949	0.3501	1.1949	1.0931
No log	23.0	69	1.1154	0.3456	1.1154	1.0561
No log	24.0	72	1.4104	0.3019	1.4104	1.1876
No log	25.0	75	1.2564	0.3091	1.2564	1.1209
No log	26.0	78	1.3749	0.2502	1.3749	1.1726

genki10/BERT_AugV8_k3_task1_organization_sp020_lw030_fold4

BERT_AugV8_k3_task1_organization_sp020_lw030_fold4