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	7	7.5860	0.0021	7.5852	2.7541
No log	2.0	14	3.7649	0.0114	3.7642	1.9402
No log	3.0	21	1.6562	0.0869	1.6556	1.2867
No log	4.0	28	1.1278	0.0202	1.1272	1.0617
No log	5.0	35	1.4271	-0.0265	1.4262	1.1942
No log	6.0	42	1.4429	-0.0507	1.4423	1.2010
No log	7.0	49	0.7150	0.3549	0.7151	0.8456
No log	8.0	56	0.7548	0.2379	0.7548	0.8688
No log	9.0	63	0.9680	0.1555	0.9682	0.9840
No log	10.0	70	0.9301	0.2301	0.9303	0.9645
No log	11.0	77	0.9743	0.2571	0.9743	0.9871
No log	12.0	84	1.2895	-0.0180	1.2897	1.1357
No log	13.0	91	1.9349	-0.1801	1.9345	1.3908
No log	14.0	98	1.5910	-0.0812	1.5906	1.2612
No log	15.0	105	1.8677	-0.2055	1.8674	1.3665
No log	16.0	112	1.7094	-0.1565	1.7092	1.3074
No log	17.0	119	1.4455	-0.0317	1.4461	1.2025
No log	18.0	126	1.2204	0.0679	1.2208	1.1049
No log	19.0	133	1.2240	0.0741	1.2244	1.1065
No log	20.0	140	1.3670	-0.0477	1.3674	1.1694
No log	21.0	147	1.1580	0.1167	1.1585	1.0763
No log	22.0	154	1.3408	-0.0077	1.3409	1.1580

genki10/BERT_AugV8_k10_task1_organization_sp020_lw040_fold3

BERT_AugV8_k10_task1_organization_sp020_lw040_fold3