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	6.7155	0.0	6.7155	2.5914
No log	2.0	8	4.0215	0.0040	4.0215	2.0054
No log	3.0	12	2.3997	0.0636	2.3997	1.5491
No log	4.0	16	1.5078	0.0212	1.5078	1.2279
No log	5.0	20	1.0567	0.0212	1.0567	1.0279
No log	6.0	24	2.3272	0.0331	2.3272	1.5255
No log	7.0	28	1.2649	0.1661	1.2649	1.1247
No log	8.0	32	1.1875	0.0227	1.1875	1.0897
No log	9.0	36	1.2325	0.0368	1.2325	1.1102
No log	10.0	40	1.5197	0.0316	1.5197	1.2328
No log	11.0	44	1.6279	0.1768	1.6279	1.2759
No log	12.0	48	1.6693	0.1405	1.6693	1.2920
No log	13.0	52	1.1353	0.2981	1.1353	1.0655
No log	14.0	56	1.4168	0.2129	1.4168	1.1903
No log	15.0	60	0.9748	0.3687	0.9748	0.9873
No log	16.0	64	0.9392	0.3979	0.9392	0.9691
No log	17.0	68	1.4498	0.2733	1.4498	1.2041
No log	18.0	72	0.8615	0.4414	0.8615	0.9282
No log	19.0	76	1.6558	0.2301	1.6558	1.2868
No log	20.0	80	0.8632	0.4538	0.8632	0.9291
No log	21.0	84	1.5874	0.2763	1.5874	1.2599
No log	22.0	88	0.8861	0.4518	0.8861	0.9413
No log	23.0	92	1.8371	0.1989	1.8371	1.3554
No log	24.0	96	0.9920	0.3977	0.9920	0.9960
No log	25.0	100	2.3651	0.1405	2.3651	1.5379
No log	26.0	104	1.0943	0.3505	1.0943	1.0461
No log	27.0	108	1.6309	0.2286	1.6309	1.2771
No log	28.0	112	1.2405	0.2909	1.2405	1.1138
No log	29.0	116	1.1124	0.2838	1.1124	1.0547
No log	30.0	120	1.6526	0.1783	1.6526	1.2855
No log	31.0	124	1.2512	0.2645	1.2512	1.1186
No log	32.0	128	1.2420	0.2777	1.2420	1.1144
No log	33.0	132	1.3294	0.2658	1.3294	1.1530
No log	34.0	136	1.0402	0.3557	1.0402	1.0199
No log	35.0	140	1.7092	0.2099	1.7092	1.3074

genki10/Trial3BERT_AugV8_k5_task1_organization_sp050_lw010_fold4

Trial3BERT_AugV8_k5_task1_organization_sp050_lw010_fold4