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	8.1321	0.0	8.1321	2.8517
No log	2.0	6	6.8396	0.0	6.8396	2.6153
No log	3.0	9	5.5694	0.0112	5.5694	2.3600
No log	4.0	12	4.3528	0.0039	4.3528	2.0863
No log	5.0	15	3.1386	0.0	3.1386	1.7716
No log	6.0	18	2.0962	0.0776	2.0962	1.4478
No log	7.0	21	1.6356	0.0382	1.6356	1.2789
No log	8.0	24	1.2934	0.0382	1.2934	1.1373
No log	9.0	27	2.1364	0.1464	2.1364	1.4616
No log	10.0	30	1.2192	0.0955	1.2192	1.1042
No log	11.0	33	1.6368	0.1392	1.6368	1.2794
No log	12.0	36	1.2795	0.1068	1.2795	1.1311
No log	13.0	39	1.0578	0.2404	1.0578	1.0285
No log	14.0	42	1.5138	0.2052	1.5138	1.2304
No log	15.0	45	0.9710	0.2931	0.9710	0.9854
No log	16.0	48	1.3772	0.1890	1.3772	1.1736
No log	17.0	51	0.9834	0.2682	0.9834	0.9917
No log	18.0	54	1.4674	0.1858	1.4674	1.2114
No log	19.0	57	1.3471	0.1913	1.3471	1.1606
No log	20.0	60	1.3626	0.1588	1.3626	1.1673
No log	21.0	63	1.7977	0.1461	1.7977	1.3408
No log	22.0	66	1.6690	0.1607	1.6690	1.2919
No log	23.0	69	1.3093	0.2055	1.3093	1.1442
No log	24.0	72	1.7993	0.1611	1.7993	1.3414
No log	25.0	75	1.3906	0.1582	1.3906	1.1793
No log	26.0	78	1.5773	0.1472	1.5773	1.2559
No log	27.0	81	1.4096	0.1977	1.4096	1.1873
No log	28.0	84	1.6918	0.1786	1.6918	1.3007
No log	29.0	87	1.0605	0.2713	1.0605	1.0298
No log	30.0	90	1.7594	0.1510	1.7594	1.3264

genki10/BERT_AugV8_k3_task1_organization_sp060_lw040_fold0

BERT_AugV8_k3_task1_organization_sp060_lw040_fold0