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	8.1282	0.0	8.1282	2.8510
No log	2.0	6	6.7028	0.0	6.7028	2.5890
No log	3.0	9	5.4607	0.0115	5.4607	2.3368
No log	4.0	12	4.2409	0.0039	4.2409	2.0593
No log	5.0	15	3.0509	0.0	3.0509	1.7467
No log	6.0	18	2.0381	0.0740	2.0381	1.4276
No log	7.0	21	1.3659	0.0316	1.3659	1.1687
No log	8.0	24	1.2114	0.0382	1.2114	1.1007
No log	9.0	27	0.9388	0.0382	0.9388	0.9689
No log	10.0	30	1.0099	0.0911	1.0099	1.0049
No log	11.0	33	1.9435	0.1973	1.9435	1.3941
No log	12.0	36	0.7878	0.3790	0.7878	0.8876
No log	13.0	39	0.8172	0.3068	0.8172	0.9040
No log	14.0	42	1.2701	0.1649	1.2701	1.1270
No log	15.0	45	0.9659	0.3116	0.9659	0.9828
No log	16.0	48	1.0835	0.2908	1.0835	1.0409
No log	17.0	51	1.1675	0.2618	1.1675	1.0805
No log	18.0	54	1.1669	0.2565	1.1669	1.0802
No log	19.0	57	0.6832	0.3805	0.6832	0.8266
No log	20.0	60	1.3444	0.2386	1.3444	1.1595
No log	21.0	63	0.8972	0.3643	0.8972	0.9472
No log	22.0	66	1.3866	0.2167	1.3866	1.1775
No log	23.0	69	0.9173	0.3355	0.9173	0.9578
No log	24.0	72	1.3187	0.2156	1.3187	1.1484
No log	25.0	75	0.9031	0.3399	0.9031	0.9503
No log	26.0	78	1.6075	0.1808	1.6075	1.2679
No log	27.0	81	1.1397	0.3102	1.1397	1.0676
No log	28.0	84	1.3982	0.2629	1.3982	1.1824
No log	29.0	87	1.0254	0.3535	1.0254	1.0126
No log	30.0	90	1.5428	0.2218	1.5428	1.2421
No log	31.0	93	1.0276	0.3153	1.0276	1.0137
No log	32.0	96	1.3737	0.2342	1.3737	1.1721
No log	33.0	99	0.9235	0.3577	0.9235	0.9610
No log	34.0	102	1.3353	0.2599	1.3353	1.1555

genki10/BERT_AugV8_k3_task1_organization_sp030_lw040_fold0

BERT_AugV8_k3_task1_organization_sp030_lw040_fold0