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	6	6.4582	0.0036	6.4588	2.5414
No log	2.0	12	3.0326	0.0039	3.0331	1.7416
No log	3.0	18	1.7117	0.1010	1.7123	1.3085
No log	4.0	24	1.3582	0.0776	1.3587	1.1656
No log	5.0	30	1.2126	0.1490	1.2127	1.1012
No log	6.0	36	0.6469	0.4141	0.6469	0.8043
No log	7.0	42	0.9421	0.3589	0.9417	0.9704
No log	8.0	48	1.4606	0.2484	1.4600	1.2083
No log	9.0	54	0.6966	0.4612	0.6962	0.8344
No log	10.0	60	1.0075	0.3287	1.0066	1.0033
No log	11.0	66	1.5387	0.2189	1.5376	1.2400
No log	12.0	72	1.3784	0.2311	1.3773	1.1736
No log	13.0	78	1.6206	0.2008	1.6194	1.2726
No log	14.0	84	1.6778	0.2143	1.6771	1.2950
No log	15.0	90	1.2045	0.2894	1.2042	1.0974
No log	16.0	96	1.4502	0.2355	1.4500	1.2042
No log	17.0	102	1.8238	0.1608	1.8232	1.3503
No log	18.0	108	2.0656	0.1311	2.0651	1.4370
No log	19.0	114	1.3754	0.2509	1.3748	1.1725
No log	20.0	120	1.3388	0.2532	1.3382	1.1568
No log	21.0	126	2.0272	0.1513	2.0267	1.4236
No log	22.0	132	1.5025	0.2093	1.5019	1.2255
No log	23.0	138	1.4031	0.2293	1.4025	1.1843
No log	24.0	144	1.6455	0.1912	1.6450	1.2826

genki10/BERT_AugV8_k7_task1_organization_sp010_lw070_fold2

BERT_AugV8_k7_task1_organization_sp010_lw070_fold2