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	8.0351	0.0018	8.0351	2.8346
No log	2.0	8	4.9764	0.0500	4.9764	2.2308
No log	3.0	12	3.1400	0.0113	3.1400	1.7720
No log	4.0	16	1.9536	0.1249	1.9536	1.3977
No log	5.0	20	1.0960	0.0316	1.0960	1.0469
No log	6.0	24	0.8891	0.1338	0.8891	0.9429
No log	7.0	28	0.8854	0.2904	0.8854	0.9409
No log	8.0	32	1.2113	0.2365	1.2113	1.1006
No log	9.0	36	0.6828	0.4930	0.6828	0.8263
No log	10.0	40	0.9173	0.3672	0.9173	0.9577
No log	11.0	44	0.6308	0.4388	0.6308	0.7942
No log	12.0	48	0.6314	0.4366	0.6314	0.7946
No log	13.0	52	0.6745	0.4650	0.6745	0.8213
No log	14.0	56	0.6194	0.4633	0.6194	0.7870
No log	15.0	60	0.6668	0.4743	0.6668	0.8166
No log	16.0	64	0.7108	0.5022	0.7108	0.8431
No log	17.0	68	1.1775	0.3900	1.1775	1.0851
No log	18.0	72	0.7185	0.5238	0.7185	0.8476
No log	19.0	76	1.2284	0.3701	1.2284	1.1083
No log	20.0	80	0.8194	0.4971	0.8194	0.9052
No log	21.0	84	0.7790	0.4873	0.7790	0.8826
No log	22.0	88	0.6644	0.4999	0.6644	0.8151
No log	23.0	92	0.9872	0.4165	0.9872	0.9936
No log	24.0	96	0.6263	0.5108	0.6263	0.7914
No log	25.0	100	0.7474	0.5010	0.7474	0.8645
No log	26.0	104	0.9142	0.4187	0.9142	0.9561
No log	27.0	108	0.8954	0.4465	0.8954	0.9462
No log	28.0	112	0.9211	0.4307	0.9211	0.9597
No log	29.0	116	0.7131	0.5131	0.7131	0.8445
No log	30.0	120	0.7548	0.4903	0.7548	0.8688
No log	31.0	124	1.0853	0.3421	1.0853	1.0418
No log	32.0	128	0.7827	0.5056	0.7827	0.8847
No log	33.0	132	0.6629	0.4963	0.6629	0.8142

genki10/Trial2BERT_AugV8_k5_task1_organization_sp010_lw020_fold4

Trial2BERT_AugV8_k5_task1_organization_sp010_lw020_fold4