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	11.4673	0.0317	11.4656	3.3861
No log	2.0	6	8.2764	0.0	8.2752	2.8767
No log	3.0	9	5.6693	0.0404	5.6680	2.3808
No log	4.0	12	3.7404	0.0	3.7394	1.9338
No log	5.0	15	2.5530	0.0507	2.5521	1.5975
No log	6.0	18	1.7904	0.0302	1.7897	1.3378
No log	7.0	21	1.3023	0.0	1.3017	1.1409
No log	8.0	24	1.0815	0.0	1.0810	1.0397
No log	9.0	27	1.0314	0.0102	1.0309	1.0153
No log	10.0	30	1.0018	0.0229	1.0013	1.0006
No log	11.0	33	0.9128	0.1801	0.9124	0.9552
No log	12.0	36	1.1096	0.0393	1.1091	1.0531
No log	13.0	39	1.0495	0.0975	1.0490	1.0242
No log	14.0	42	0.6261	0.4538	0.6260	0.7912
No log	15.0	45	0.8814	0.3211	0.8814	0.9388
No log	16.0	48	0.6227	0.4718	0.6229	0.7893
No log	17.0	51	0.5943	0.4413	0.5946	0.7711
No log	18.0	54	0.5830	0.4887	0.5833	0.7638
No log	19.0	57	0.7555	0.4761	0.7559	0.8694
No log	20.0	60	0.7512	0.4701	0.7517	0.8670
No log	21.0	63	0.5876	0.5307	0.5879	0.7668
No log	22.0	66	1.1121	0.3104	1.1125	1.0548
No log	23.0	69	0.6288	0.5183	0.6292	0.7932
No log	24.0	72	0.7475	0.4869	0.7481	0.8649
No log	25.0	75	1.3125	0.2393	1.3127	1.1457
No log	26.0	78	0.5842	0.5238	0.5844	0.7645
No log	27.0	81	0.8674	0.3716	0.8677	0.9315
No log	28.0	84	1.0716	0.3313	1.0718	1.0353
No log	29.0	87	0.6912	0.4878	0.6915	0.8316
No log	30.0	90	1.0336	0.3272	1.0337	1.0167
No log	31.0	93	0.7556	0.4392	0.7558	0.8694
No log	32.0	96	0.8540	0.3738	0.8543	0.9243
No log	33.0	99	1.0135	0.2836	1.0135	1.0067
No log	34.0	102	0.7333	0.4290	0.7335	0.8564
No log	35.0	105	1.1663	0.2666	1.1663	1.0800
No log	36.0	108	0.6678	0.4851	0.6680	0.8173

genki10/BERT_AugV8_k3_task1_organization_sp040_lw010_fold3

BERT_AugV8_k3_task1_organization_sp040_lw010_fold3