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	9.8803	0.0	9.8777	3.1429
No log	2.0	6	8.5074	0.0	8.5050	2.9163
No log	3.0	9	6.1849	0.0	6.1827	2.4865
No log	4.0	12	4.5241	0.0040	4.5220	2.1265
No log	5.0	15	3.1005	0.0	3.0987	1.7603
No log	6.0	18	1.9344	0.0315	1.9328	1.3902
No log	7.0	21	1.1911	0.0	1.1897	1.0907
No log	8.0	24	1.0618	0.0106	1.0604	1.0298
No log	9.0	27	0.9848	0.0117	0.9835	0.9917
No log	10.0	30	1.2768	0.1105	1.2752	1.1293
No log	11.0	33	1.0524	0.1585	1.0509	1.0252
No log	12.0	36	1.1397	0.1857	1.1381	1.0668
No log	13.0	39	1.0129	0.2508	1.0113	1.0057
No log	14.0	42	1.4825	0.1671	1.4805	1.2168
No log	15.0	45	0.8716	0.3369	0.8700	0.9327
No log	16.0	48	1.4877	0.1779	1.4854	1.2188
No log	17.0	51	0.7820	0.3723	0.7810	0.8838
No log	18.0	54	1.2322	0.2378	1.2303	1.1092
No log	19.0	57	0.8243	0.3610	0.8232	0.9073
No log	20.0	60	1.6826	0.1259	1.6804	1.2963
No log	21.0	63	1.2579	0.2195	1.2561	1.1208
No log	22.0	66	1.7878	0.1315	1.7854	1.3362
No log	23.0	69	1.2458	0.2445	1.2440	1.1154
No log	24.0	72	1.3340	0.2095	1.3321	1.1542
No log	25.0	75	1.2146	0.2585	1.2127	1.1012
No log	26.0	78	1.5301	0.1756	1.5278	1.2360
No log	27.0	81	1.2785	0.2104	1.2764	1.1298
No log	28.0	84	1.3053	0.2051	1.3033	1.1416
No log	29.0	87	1.5093	0.1698	1.5072	1.2277
No log	30.0	90	1.1779	0.2384	1.1762	1.0845
No log	31.0	93	1.7735	0.1518	1.7712	1.3309
No log	32.0	96	1.5668	0.1774	1.5646	1.2509

genki10/BERT_AugV8_k3_task1_organization_sp020_lw030_fold1

BERT_AugV8_k3_task1_organization_sp020_lw030_fold1