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	8.2953	0.0	8.2930	2.8798
No log	2.0	6	6.7454	0.0	6.7431	2.5967
No log	3.0	9	5.1154	0.0079	5.1133	2.2613
No log	4.0	12	3.5244	0.0	3.5225	1.8768
No log	5.0	15	2.6047	0.0	2.6029	1.6134
No log	6.0	18	1.9586	0.0645	1.9569	1.3989
No log	7.0	21	1.5523	0.0106	1.5507	1.2453
No log	8.0	24	1.3024	0.0106	1.3009	1.1406
No log	9.0	27	1.2124	0.0211	1.2110	1.1004
No log	10.0	30	1.0884	0.0418	1.0870	1.0426
No log	11.0	33	1.1280	0.1040	1.1265	1.0614
No log	12.0	36	1.9791	0.2468	1.9771	1.4061
No log	13.0	39	0.9651	0.1543	0.9635	0.9816
No log	14.0	42	1.9693	0.1732	1.9667	1.4024
No log	15.0	45	1.0877	0.2134	1.0854	1.0418
No log	16.0	48	0.6722	0.4675	0.6708	0.8190
No log	17.0	51	1.3840	0.1970	1.3814	1.1753
No log	18.0	54	0.7290	0.4488	0.7273	0.8528
No log	19.0	57	0.7189	0.3756	0.7179	0.8473
No log	20.0	60	0.7021	0.5197	0.7006	0.8370
No log	21.0	63	0.6284	0.5193	0.6269	0.7918
No log	22.0	66	0.6692	0.4668	0.6678	0.8172
No log	23.0	69	0.6668	0.5071	0.6652	0.8156
No log	24.0	72	0.9464	0.3743	0.9444	0.9718
No log	25.0	75	0.8366	0.4001	0.8348	0.9137
No log	26.0	78	0.9254	0.2907	0.9235	0.9610
No log	27.0	81	1.1248	0.2182	1.1223	1.0594
No log	28.0	84	1.0483	0.2957	1.0456	1.0226
No log	29.0	87	1.5917	0.2075	1.5887	1.2604
No log	30.0	90	0.8070	0.4499	0.8053	0.8974
No log	31.0	93	1.2422	0.2974	1.2397	1.1134
No log	32.0	96	0.8194	0.4227	0.8175	0.9041
No log	33.0	99	0.8564	0.3863	0.8545	0.9244
No log	34.0	102	1.2640	0.2571	1.2616	1.1232
No log	35.0	105	1.0815	0.2953	1.0792	1.0388

genki10/Trial2BERT_AugV8_k3_task1_organization_sp010_lw070_fold1

Trial2BERT_AugV8_k3_task1_organization_sp010_lw070_fold1