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	7.4561	0.0	7.4561	2.7306
No log	2.0	8	5.7163	0.0116	5.7163	2.3909
No log	3.0	12	3.9968	0.0039	3.9968	1.9992
No log	4.0	16	2.3762	0.0698	2.3762	1.5415
No log	5.0	20	1.4291	0.0316	1.4291	1.1955
No log	6.0	24	0.9521	0.0316	0.9521	0.9758
No log	7.0	28	0.9294	0.0884	0.9294	0.9641
No log	8.0	32	0.9919	0.0490	0.9919	0.9960
No log	9.0	36	1.0691	0.2238	1.0691	1.0340
No log	10.0	40	0.7673	0.3437	0.7673	0.8760
No log	11.0	44	0.7980	0.3467	0.7980	0.8933
No log	12.0	48	0.7710	0.3689	0.7710	0.8781
No log	13.0	52	0.7028	0.2956	0.7028	0.8383
No log	14.0	56	0.6193	0.3778	0.6193	0.7869
No log	15.0	60	0.7672	0.2971	0.7672	0.8759
No log	16.0	64	0.9391	0.2729	0.9391	0.9691
No log	17.0	68	0.9063	0.3355	0.9063	0.9520
No log	18.0	72	1.0910	0.3057	1.0910	1.0445
No log	19.0	76	0.9350	0.3711	0.9350	0.9670
No log	20.0	80	1.0480	0.2351	1.0480	1.0237
No log	21.0	84	0.9946	0.2740	0.9946	0.9973
No log	22.0	88	0.9642	0.3222	0.9642	0.9819
No log	23.0	92	1.3223	0.1839	1.3223	1.1499
No log	24.0	96	0.9194	0.3456	0.9194	0.9589
No log	25.0	100	0.8620	0.3366	0.8620	0.9284
No log	26.0	104	0.9045	0.2922	0.9045	0.9511
No log	27.0	108	0.8612	0.3039	0.8612	0.9280
No log	28.0	112	0.8831	0.3023	0.8831	0.9397
No log	29.0	116	0.8202	0.3245	0.8202	0.9057

genki10/Trial3BERT_AugV8_k5_task1_organization_sp020_lw010_fold0

Trial3BERT_AugV8_k5_task1_organization_sp020_lw010_fold0