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	4	8.7128	0.0	8.7102	2.9513
No log	2.0	8	5.0411	0.0382	5.0389	2.2447
No log	3.0	12	2.8012	0.0	2.7995	1.6732
No log	4.0	16	1.6572	0.0482	1.6555	1.2867
No log	5.0	20	1.1526	0.0106	1.1511	1.0729
No log	6.0	24	1.3299	0.0515	1.3281	1.1525
No log	7.0	28	1.1450	0.1176	1.1431	1.0692
No log	8.0	32	1.0689	0.1414	1.0670	1.0330
No log	9.0	36	0.8061	0.2794	0.8047	0.8971
No log	10.0	40	0.7908	0.3948	0.7891	0.8883
No log	11.0	44	1.0305	0.1931	1.0297	1.0147
No log	12.0	48	0.9629	0.2220	0.9615	0.9806
No log	13.0	52	0.7042	0.3625	0.7029	0.8384
No log	14.0	56	0.8048	0.3570	0.8033	0.8963
No log	15.0	60	1.2421	0.1915	1.2402	1.1136
No log	16.0	64	0.9741	0.2732	0.9727	0.9863
No log	17.0	68	1.0738	0.3614	1.0721	1.0354
No log	18.0	72	0.9556	0.3119	0.9542	0.9768
No log	19.0	76	1.2897	0.1636	1.2877	1.1348
No log	20.0	80	1.4416	0.1820	1.4396	1.1998
No log	21.0	84	1.1519	0.2466	1.1503	1.0725
No log	22.0	88	1.6682	0.1580	1.6666	1.2910
No log	23.0	92	1.1039	0.2607	1.1026	1.0501
No log	24.0	96	1.1407	0.2061	1.1394	1.0674
No log	25.0	100	1.0971	0.2014	1.0958	1.0468

genki10/BERT_AugV8_k5_task1_organization_sp030_lw050_fold1

BERT_AugV8_k5_task1_organization_sp030_lw050_fold1