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	10.4606	0.0	10.4605	3.2343
No log	2.0	6	8.6302	0.0	8.6300	2.9377
No log	3.0	9	6.0637	0.0201	6.0641	2.4625
No log	4.0	12	4.4781	0.0039	4.4785	2.1163
No log	5.0	15	3.2081	0.0	3.2087	1.7913
No log	6.0	18	2.2745	0.1844	2.2749	1.5083
No log	7.0	21	1.5392	0.0213	1.5397	1.2408
No log	8.0	24	1.5183	0.0714	1.5186	1.2323
No log	9.0	27	1.1429	0.0213	1.1434	1.0693
No log	10.0	30	1.3815	0.1082	1.3817	1.1755
No log	11.0	33	1.5021	0.1457	1.5024	1.2257
No log	12.0	36	0.8792	0.1059	0.8795	0.9378
No log	13.0	39	1.1845	0.1625	1.1848	1.0885
No log	14.0	42	0.8660	0.3552	0.8661	0.9306
No log	15.0	45	0.6190	0.5044	0.6189	0.7867
No log	16.0	48	0.7409	0.4150	0.7407	0.8606
No log	17.0	51	0.5933	0.4624	0.5932	0.7702
No log	18.0	54	0.7781	0.3562	0.7780	0.8820
No log	19.0	57	0.6045	0.4245	0.6044	0.7775
No log	20.0	60	0.7138	0.4055	0.7136	0.8448
No log	21.0	63	0.6711	0.4470	0.6709	0.8191
No log	22.0	66	0.8479	0.3701	0.8479	0.9208
No log	23.0	69	0.7030	0.4369	0.7032	0.8385
No log	24.0	72	0.7870	0.3720	0.7871	0.8872
No log	25.0	75	0.6963	0.4651	0.6961	0.8343
No log	26.0	78	0.9779	0.3129	0.9778	0.9888
No log	27.0	81	0.6035	0.4832	0.6032	0.7767
No log	28.0	84	0.9839	0.2765	0.9838	0.9919
No log	29.0	87	0.6678	0.4814	0.6677	0.8171
No log	30.0	90	0.9155	0.3208	0.9155	0.9568

genki10/BERT_AugV8_k3_task1_organization_sp060_lw040_fold2

BERT_AugV8_k3_task1_organization_sp060_lw040_fold2