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	3	7.5719	0.0	7.5705	2.7514
No log	2.0	6	5.4514	0.0451	5.4505	2.3346
No log	3.0	9	4.0609	0.0076	4.0594	2.0148
No log	4.0	12	2.7415	0.0003	2.7406	1.6555
No log	5.0	15	1.9752	0.0463	1.9743	1.4051
No log	6.0	18	1.3582	0.0365	1.3575	1.1651
No log	7.0	21	0.9569	0.0202	0.9564	0.9780
No log	8.0	24	1.0577	0.0549	1.0574	1.0283
No log	9.0	27	0.9629	0.1062	0.9627	0.9812
No log	10.0	30	1.0719	0.1793	1.0719	1.0353
No log	11.0	33	1.1908	0.2284	1.1909	1.0913
No log	12.0	36	0.7961	0.3873	0.7965	0.8924
No log	13.0	39	1.1649	0.2857	1.1653	1.0795
No log	14.0	42	0.6715	0.4683	0.6719	0.8197
No log	15.0	45	1.2858	0.2543	1.2861	1.1341
No log	16.0	48	0.6652	0.4486	0.6656	0.8158
No log	17.0	51	0.7102	0.4371	0.7106	0.8430
No log	18.0	54	1.3310	0.2640	1.3312	1.1538
No log	19.0	57	0.7048	0.4560	0.7052	0.8398
No log	20.0	60	0.9219	0.3737	0.9224	0.9604
No log	21.0	63	1.1411	0.3300	1.1416	1.0685
No log	22.0	66	0.6922	0.5064	0.6927	0.8323
No log	23.0	69	0.6956	0.5236	0.6960	0.8343
No log	24.0	72	1.1446	0.3314	1.1449	1.0700
No log	25.0	75	0.6825	0.5143	0.6829	0.8263
No log	26.0	78	0.9130	0.3644	0.9133	0.9557
No log	27.0	81	0.7666	0.4344	0.7670	0.8758
No log	28.0	84	0.8203	0.4255	0.8205	0.9058
No log	29.0	87	0.8881	0.3940	0.8883	0.9425
No log	30.0	90	0.9711	0.3702	0.9712	0.9855
No log	31.0	93	1.0674	0.3239	1.0675	1.0332
No log	32.0	96	0.8303	0.4365	0.8305	0.9113
No log	33.0	99	1.1231	0.3145	1.1232	1.0598
No log	34.0	102	0.8890	0.3947	0.8892	0.9430
No log	35.0	105	0.8652	0.4157	0.8654	0.9303
No log	36.0	108	0.9357	0.3639	0.9359	0.9674
No log	37.0	111	0.7476	0.4813	0.7478	0.8647
No log	38.0	114	1.1475	0.2916	1.1475	1.0712

genki10/Trial3BERT_AugV8_k3_task1_organization_sp020_lw010_fold3

Trial3BERT_AugV8_k3_task1_organization_sp020_lw010_fold3