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	9.1999	0.0018	9.1999	3.0331
No log	2.0	8	5.6492	0.0520	5.6492	2.3768
No log	3.0	12	2.9541	0.0118	2.9541	1.7188
No log	4.0	16	1.5908	0.0420	1.5908	1.2613
No log	5.0	20	1.0851	0.0420	1.0851	1.0417
No log	6.0	24	1.8474	0.1835	1.8474	1.3592
No log	7.0	28	1.0009	0.0420	1.0009	1.0004
No log	8.0	32	1.4823	0.1886	1.4823	1.2175
No log	9.0	36	0.9536	0.1763	0.9536	0.9765
No log	10.0	40	0.9344	0.3389	0.9344	0.9667
No log	11.0	44	0.8681	0.3984	0.8681	0.9317
No log	12.0	48	0.6470	0.4889	0.6470	0.8044
No log	13.0	52	0.7046	0.4716	0.7046	0.8394
No log	14.0	56	0.6243	0.4376	0.6243	0.7901
No log	15.0	60	0.7776	0.4331	0.7776	0.8818
No log	16.0	64	0.7190	0.4937	0.7190	0.8480
No log	17.0	68	0.6997	0.5545	0.6997	0.8365
No log	18.0	72	0.9597	0.4804	0.9597	0.9796
No log	19.0	76	0.7206	0.5452	0.7206	0.8489
No log	20.0	80	0.7886	0.4783	0.7886	0.8880
No log	21.0	84	0.7698	0.4692	0.7698	0.8774
No log	22.0	88	0.8041	0.4637	0.8041	0.8967
No log	23.0	92	0.9024	0.4573	0.9024	0.9499
No log	24.0	96	0.8141	0.4680	0.8141	0.9023
No log	25.0	100	0.6769	0.4988	0.6769	0.8227
No log	26.0	104	0.7918	0.4526	0.7918	0.8898
No log	27.0	108	0.9086	0.4023	0.9086	0.9532
No log	28.0	112	0.7332	0.5038	0.7332	0.8562
No log	29.0	116	0.6965	0.5275	0.6965	0.8346
No log	30.0	120	1.0252	0.3773	1.0252	1.0125
No log	31.0	124	0.6796	0.5299	0.6796	0.8244
No log	32.0	128	0.6741	0.5070	0.6741	0.8210

genki10/BERT_AugV8_k5_task1_organization_sp030_lw050_fold4

BERT_AugV8_k5_task1_organization_sp030_lw050_fold4