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	9.6175	0.0	9.6149	3.1008
No log	2.0	8	6.9908	0.0	6.9886	2.6436
No log	3.0	12	4.6129	0.0040	4.6109	2.1473
No log	4.0	16	2.6533	0.0	2.6516	1.6284
No log	5.0	20	1.3137	0.0	1.3123	1.1455
No log	6.0	24	0.9728	0.0	0.9715	0.9856
No log	7.0	28	1.0268	0.0158	1.0255	1.0127
No log	8.0	32	0.9031	0.1403	0.9019	0.9497
No log	9.0	36	1.0569	0.1924	1.0556	1.0274
No log	10.0	40	0.8366	0.3989	0.8357	0.9142
No log	11.0	44	0.9974	0.3444	0.9966	0.9983
No log	12.0	48	0.9717	0.3202	0.9709	0.9853
No log	13.0	52	1.0375	0.2071	1.0371	1.0184
No log	14.0	56	1.3383	0.2639	1.3373	1.1564
No log	15.0	60	0.7406	0.4425	0.7401	0.8603
No log	16.0	64	1.9495	0.1928	1.9480	1.3957
No log	17.0	68	0.8119	0.4242	0.8117	0.9009
No log	18.0	72	1.0312	0.3171	1.0304	1.0151
No log	19.0	76	0.9216	0.3957	0.9210	0.9597
No log	20.0	80	1.0893	0.3456	1.0883	1.0432
No log	21.0	84	0.8470	0.4301	0.8462	0.9199
No log	22.0	88	1.0811	0.3099	1.0798	1.0391
No log	23.0	92	1.0274	0.3375	1.0261	1.0130
No log	24.0	96	1.0623	0.3146	1.0611	1.0301
No log	25.0	100	1.1978	0.2338	1.1964	1.0938
No log	26.0	104	1.0302	0.2607	1.0291	1.0144
No log	27.0	108	0.9565	0.3421	0.9557	0.9776
No log	28.0	112	1.0190	0.3465	1.0179	1.0089
No log	29.0	116	1.1108	0.2946	1.1096	1.0534
No log	30.0	120	1.0159	0.3675	1.0147	1.0073

genki10/Trial3BERT_AugV8_k5_task1_organization_sp010_lw030_fold1

Trial3BERT_AugV8_k5_task1_organization_sp010_lw030_fold1