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	10.0960	0.0	10.0935	3.1770
No log	2.0	6	8.6785	0.0	8.6762	2.9455
No log	3.0	9	6.0652	0.0	6.0631	2.4623
No log	4.0	12	4.5824	0.0	4.5804	2.1402
No log	5.0	15	3.3250	0.0	3.3231	1.8229
No log	6.0	18	2.2918	0.0759	2.2901	1.5133
No log	7.0	21	1.6067	0.0	1.6051	1.2669
No log	8.0	24	1.2864	0.0	1.2849	1.1335
No log	9.0	27	1.1940	0.0106	1.1924	1.0920
No log	10.0	30	1.1996	0.0554	1.1979	1.0945
No log	11.0	33	1.0246	0.0253	1.0228	1.0113
No log	12.0	36	1.1772	0.1661	1.1750	1.0840
No log	13.0	39	0.9830	0.2465	0.9810	0.9904
No log	14.0	42	0.7597	0.3247	0.7582	0.8708
No log	15.0	45	0.8568	0.3330	0.8549	0.9246
No log	16.0	48	0.8078	0.3580	0.8062	0.8979
No log	17.0	51	0.8683	0.3296	0.8666	0.9309
No log	18.0	54	0.9314	0.3262	0.9295	0.9641
No log	19.0	57	1.1803	0.2546	1.1780	1.0854
No log	20.0	60	1.1551	0.2627	1.1529	1.0737
No log	21.0	63	1.0222	0.3445	1.0202	1.0100
No log	22.0	66	1.2111	0.2746	1.2088	1.0994
No log	23.0	69	1.1532	0.2713	1.1510	1.0728
No log	24.0	72	1.2602	0.2749	1.2577	1.1215
No log	25.0	75	1.1556	0.2445	1.1533	1.0739
No log	26.0	78	1.5059	0.2114	1.5033	1.2261
No log	27.0	81	1.2214	0.2842	1.2191	1.1041
No log	28.0	84	1.3584	0.2254	1.3560	1.1645
No log	29.0	87	1.1784	0.2105	1.1763	1.0846
No log	30.0	90	1.2166	0.2051	1.2145	1.1020
No log	31.0	93	1.1220	0.2946	1.1199	1.0583

genki10/BERT_AugV8_k3_task1_organization_sp030_lw050_fold1

BERT_AugV8_k3_task1_organization_sp030_lw050_fold1