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	7.8235	0.0	7.8221	2.7968
No log	2.0	8	4.3471	0.0114	4.3460	2.0847
No log	3.0	12	2.5483	0.0861	2.5475	1.5961
No log	4.0	16	1.4261	0.0365	1.4254	1.1939
No log	5.0	20	1.9478	0.0997	1.9471	1.3954
No log	6.0	24	1.0510	0.0463	1.0507	1.0250
No log	7.0	28	1.1906	0.0623	1.1906	1.0911
No log	8.0	32	1.2089	0.1149	1.2092	1.0997
No log	9.0	36	0.7381	0.4075	0.7389	0.8596
No log	10.0	40	0.9783	0.3416	0.9795	0.9897
No log	11.0	44	1.4186	0.2563	1.4199	1.1916
No log	12.0	48	2.1681	0.1543	2.1695	1.4729
No log	13.0	52	1.4646	0.2488	1.4658	1.2107
No log	14.0	56	1.6116	0.2148	1.6126	1.2699
No log	15.0	60	1.9401	0.1344	1.9412	1.3933
No log	16.0	64	1.4256	0.1963	1.4267	1.1944
No log	17.0	68	1.1994	0.2561	1.2003	1.0956
No log	18.0	72	2.0784	0.1086	2.0790	1.4419
No log	19.0	76	2.1297	0.1097	2.1305	1.4596
No log	20.0	80	1.5390	0.2167	1.5400	1.2409
No log	21.0	84	1.5804	0.1976	1.5813	1.2575
No log	22.0	88	1.1548	0.2889	1.1558	1.0751
No log	23.0	92	2.4867	0.0869	2.4874	1.5771
No log	24.0	96	1.1991	0.2758	1.2003	1.0956

genki10/BERT_AugV8_k5_task1_organization_sp060_lw010_fold3

BERT_AugV8_k5_task1_organization_sp060_lw010_fold3