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	6.6310	0.0	6.6313	2.5751
No log	2.0	10	3.3020	0.0	3.3025	1.8173
No log	3.0	15	1.8598	0.0577	1.8602	1.3639
No log	4.0	20	1.1748	0.0029	1.1751	1.0840
No log	5.0	25	1.7803	0.0667	1.7805	1.3344
No log	6.0	30	0.9294	0.2329	0.9296	0.9641
No log	7.0	35	0.8200	0.3066	0.8202	0.9056
No log	8.0	40	0.7170	0.3794	0.7172	0.8469
No log	9.0	45	0.7900	0.2403	0.7903	0.8890
No log	10.0	50	0.6169	0.3526	0.6170	0.7855
No log	11.0	55	0.8402	0.3049	0.8404	0.9167
No log	12.0	60	0.5222	0.4827	0.5223	0.7227
No log	13.0	65	0.6340	0.4011	0.6343	0.7964
No log	14.0	70	0.7468	0.4086	0.7474	0.8645
No log	15.0	75	1.2554	0.2844	1.2558	1.1206
No log	16.0	80	0.7567	0.4378	0.7571	0.8701
No log	17.0	85	0.9548	0.2895	0.9550	0.9772
No log	18.0	90	1.3106	0.2024	1.3107	1.1449
No log	19.0	95	1.1383	0.2329	1.1383	1.0669
No log	20.0	100	0.8147	0.3565	0.8148	0.9026
No log	21.0	105	0.9946	0.3482	0.9946	0.9973
No log	22.0	110	1.1129	0.2542	1.1131	1.0550
No log	23.0	115	1.0071	0.2439	1.0073	1.0036
No log	24.0	120	0.9132	0.2951	0.9133	0.9557
No log	25.0	125	0.9159	0.3416	0.9160	0.9571
No log	26.0	130	1.2175	0.2369	1.2177	1.1035
No log	27.0	135	1.1338	0.2353	1.1338	1.0648

genki10/BERT_AugV8_k7_task1_organization_sp060_lw010_fold2

BERT_AugV8_k7_task1_organization_sp060_lw010_fold2