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	11.2923	0.0065	11.2923	3.3604
No log	2.0	6	8.2850	0.0018	8.2850	2.8784
No log	3.0	9	5.1759	0.0399	5.1759	2.2751
No log	4.0	12	3.1302	0.0118	3.1302	1.7692
No log	5.0	15	2.2293	0.0953	2.2293	1.4931
No log	6.0	18	1.5703	0.0445	1.5703	1.2531
No log	7.0	21	1.1525	0.0316	1.1525	1.0735
No log	8.0	24	0.8787	0.1759	0.8787	0.9374
No log	9.0	27	0.7938	0.4138	0.7938	0.8910
No log	10.0	30	0.8111	0.2765	0.8111	0.9006
No log	11.0	33	0.7580	0.4342	0.7580	0.8706
No log	12.0	36	1.9085	0.2774	1.9085	1.3815
No log	13.0	39	1.4337	0.2935	1.4337	1.1974
No log	14.0	42	0.6345	0.4897	0.6345	0.7965
No log	15.0	45	0.9084	0.2744	0.9084	0.9531
No log	16.0	48	1.0062	0.3002	1.0062	1.0031
No log	17.0	51	0.7136	0.5095	0.7136	0.8448
No log	18.0	54	1.0175	0.4219	1.0175	1.0087
No log	19.0	57	0.8949	0.3438	0.8949	0.9460
No log	20.0	60	0.7540	0.4401	0.7540	0.8683
No log	21.0	63	0.8932	0.3819	0.8932	0.9451
No log	22.0	66	0.7761	0.4667	0.7761	0.8809
No log	23.0	69	0.9015	0.4325	0.9015	0.9495
No log	24.0	72	0.7484	0.4845	0.7484	0.8651
No log	25.0	75	1.3638	0.2431	1.3638	1.1678
No log	26.0	78	0.9632	0.3251	0.9632	0.9815
No log	27.0	81	0.7940	0.4436	0.7940	0.8911
No log	28.0	84	1.3661	0.2388	1.3661	1.1688
No log	29.0	87	0.8496	0.3767	0.8496	0.9218
No log	30.0	90	0.8474	0.4153	0.8474	0.9205
No log	31.0	93	1.0918	0.3558	1.0918	1.0449
No log	32.0	96	0.7635	0.4438	0.7635	0.8738

genki10/Trial3BERT_AugV8_k3_task1_organization_sp010_lw030_fold4

Trial3BERT_AugV8_k3_task1_organization_sp010_lw030_fold4