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	5	9.7307	0.0	9.7308	3.1194
No log	2.0	10	6.3530	0.0	6.3532	2.5206
No log	3.0	15	3.6606	0.0	3.6611	1.9134
No log	4.0	20	1.4486	0.0307	1.4491	1.2038
No log	5.0	25	1.0656	0.0107	1.0661	1.0325
No log	6.0	30	1.3796	0.1063	1.3799	1.1747
No log	7.0	35	2.0146	0.1681	2.0138	1.4191
No log	8.0	40	0.8868	0.3471	0.8860	0.9413
No log	9.0	45	1.1156	0.3180	1.1144	1.0556
No log	10.0	50	1.3295	0.3053	1.3280	1.1524
No log	11.0	55	0.9083	0.3683	0.9072	0.9525
No log	12.0	60	0.8616	0.3945	0.8606	0.9277
No log	13.0	65	2.1633	0.1446	2.1623	1.4705
No log	14.0	70	0.8618	0.4348	0.8606	0.9277
No log	15.0	75	1.7110	0.2310	1.7099	1.3076
No log	16.0	80	1.5274	0.2291	1.5268	1.2356
No log	17.0	85	1.5938	0.2119	1.5931	1.2622
No log	18.0	90	1.8515	0.1860	1.8506	1.3604
No log	19.0	95	1.1026	0.2686	1.1021	1.0498
No log	20.0	100	1.1393	0.2695	1.1386	1.0671
No log	21.0	105	1.0098	0.3077	1.0092	1.0046
No log	22.0	110	1.5908	0.1931	1.5903	1.2611
No log	23.0	115	1.2085	0.2556	1.2080	1.0991
No log	24.0	120	1.0360	0.3227	1.0356	1.0176
No log	25.0	125	1.8256	0.1358	1.8253	1.3510
No log	26.0	130	0.8697	0.3598	0.8693	0.9324
No log	27.0	135	1.4253	0.1989	1.4249	1.1937
No log	28.0	140	1.5768	0.1868	1.5765	1.2556
No log	29.0	145	1.1554	0.2442	1.1551	1.0747

genki10/Trial3BERT_AugV8_k7_task1_organization_sp010_lw040_fold2

Trial3BERT_AugV8_k7_task1_organization_sp010_lw040_fold2