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	5	7.0571	0.0	7.0571	2.6565
No log	2.0	10	4.9040	0.0115	4.9040	2.2145
No log	3.0	15	2.8390	0.0	2.8390	1.6849
No log	4.0	20	1.4392	0.0316	1.4392	1.1997
No log	5.0	25	1.1581	0.0316	1.1581	1.0762
No log	6.0	30	0.8243	0.2821	0.8243	0.9079
No log	7.0	35	1.3619	0.1062	1.3619	1.1670
No log	8.0	40	0.6928	0.2546	0.6928	0.8323
No log	9.0	45	0.8737	0.2727	0.8737	0.9347
No log	10.0	50	0.8430	0.3469	0.8430	0.9182
No log	11.0	55	0.6235	0.3341	0.6235	0.7896
No log	12.0	60	0.6539	0.3976	0.6539	0.8087
No log	13.0	65	1.4008	0.2291	1.4008	1.1835
No log	14.0	70	0.7252	0.4009	0.7252	0.8516
No log	15.0	75	1.1412	0.2310	1.1412	1.0683
No log	16.0	80	1.0529	0.2757	1.0529	1.0261
No log	17.0	85	0.8504	0.3437	0.8504	0.9222
No log	18.0	90	0.9750	0.2988	0.9750	0.9874
No log	19.0	95	1.0605	0.2530	1.0605	1.0298
No log	20.0	100	0.9532	0.3143	0.9532	0.9763
No log	21.0	105	1.1107	0.2410	1.1107	1.0539
No log	22.0	110	0.9731	0.2422	0.9731	0.9865
No log	23.0	115	0.8567	0.2961	0.8567	0.9256
No log	24.0	120	1.0393	0.2679	1.0393	1.0195
No log	25.0	125	0.9366	0.2830	0.9366	0.9678
No log	26.0	130	0.9899	0.3071	0.9899	0.9950
No log	27.0	135	0.8688	0.3381	0.8688	0.9321
No log	28.0	140	0.9303	0.2496	0.9303	0.9645
No log	29.0	145	0.9029	0.3032	0.9029	0.9502

genki10/BERT_AugV8_k7_task1_organization_sp020_lw030_fold0

BERT_AugV8_k7_task1_organization_sp020_lw030_fold0