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	2	8.9076	0.0	8.9076	2.9846
No log	2.0	4	7.8231	0.0	7.8231	2.7970
No log	3.0	6	6.7204	0.0	6.7204	2.5924
No log	4.0	8	5.9222	0.0096	5.9222	2.4335
No log	5.0	10	5.1036	0.0115	5.1036	2.2591
No log	6.0	12	4.2788	0.0039	4.2788	2.0685
No log	7.0	14	3.5009	0.0	3.5009	1.8711
No log	8.0	16	2.7467	0.0	2.7467	1.6573
No log	9.0	18	2.1556	0.0517	2.1556	1.4682
No log	10.0	20	1.7491	0.0316	1.7491	1.3225
No log	11.0	22	1.3604	0.0316	1.3604	1.1664
No log	12.0	24	1.1006	0.0316	1.1006	1.0491
No log	13.0	26	0.9889	0.0316	0.9889	0.9945
No log	14.0	28	0.9012	0.0419	0.9012	0.9493
No log	15.0	30	0.9325	0.0574	0.9325	0.9657
No log	16.0	32	1.3975	0.1659	1.3975	1.1822
No log	17.0	34	1.1421	0.1811	1.1421	1.0687
No log	18.0	36	0.6790	0.5087	0.6790	0.8240
No log	19.0	38	0.9156	0.2997	0.9156	0.9569
No log	20.0	40	1.1147	0.2515	1.1147	1.0558
No log	21.0	42	0.7066	0.4291	0.7066	0.8406
No log	22.0	44	0.6747	0.3515	0.6747	0.8214
No log	23.0	46	0.6502	0.4135	0.6502	0.8063
No log	24.0	48	0.6087	0.3863	0.6087	0.7802
No log	25.0	50	0.6516	0.3597	0.6516	0.8072
No log	26.0	52	0.6326	0.3884	0.6326	0.7954
No log	27.0	54	0.6261	0.4023	0.6261	0.7912
No log	28.0	56	0.6568	0.3684	0.6568	0.8105
No log	29.0	58	0.9194	0.3373	0.9194	0.9589
No log	30.0	60	0.8375	0.3709	0.8375	0.9152
No log	31.0	62	0.8731	0.3846	0.8731	0.9344
No log	32.0	64	1.1869	0.2777	1.1869	1.0895
No log	33.0	66	0.9461	0.3605	0.9461	0.9727

genki10/BERT_AugV8_k1_task1_organization_sp010_lw070_fold0

BERT_AugV8_k1_task1_organization_sp010_lw070_fold0