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	4	6.6036	0.0	6.6024	2.5695
No log	2.0	8	3.7665	0.0	3.7654	1.9405
No log	3.0	12	2.3197	0.0765	2.3188	1.5228
No log	4.0	16	1.5238	0.0202	1.5231	1.2341
No log	5.0	20	1.1748	0.0202	1.1742	1.0836
No log	6.0	24	1.3902	0.0202	1.3895	1.1788
No log	7.0	28	1.4884	0.0266	1.4877	1.2197
No log	8.0	32	1.6731	0.1721	1.6723	1.2932
No log	9.0	36	1.4609	0.1968	1.4606	1.2085
No log	10.0	40	1.7488	0.1143	1.7486	1.3223
No log	11.0	44	2.5367	0.0106	2.5366	1.5927
No log	12.0	48	0.8238	0.3669	0.8244	0.9080
No log	13.0	52	1.7636	0.1445	1.7639	1.3281
No log	14.0	56	2.2445	0.1169	2.2444	1.4981
No log	15.0	60	0.9678	0.3447	0.9682	0.9840
No log	16.0	64	1.1631	0.3021	1.1638	1.0788
No log	17.0	68	1.4532	0.2209	1.4539	1.2058
No log	18.0	72	1.9461	0.0949	1.9464	1.3951
No log	19.0	76	1.1457	0.1999	1.1461	1.0706
No log	20.0	80	2.3170	0.1020	2.3170	1.5222
No log	21.0	84	2.2757	0.0935	2.2756	1.5085
No log	22.0	88	0.9633	0.3557	0.9640	0.9818
No log	23.0	92	1.7936	0.1192	1.7937	1.3393
No log	24.0	96	1.9204	0.1136	1.9204	1.3858
No log	25.0	100	0.9683	0.3438	0.9688	0.9843
No log	26.0	104	1.6882	0.1477	1.6884	1.2994
No log	27.0	108	1.8389	0.1365	1.8390	1.3561

genki10/BERT_AugV8_k5_task1_organization_sp010_lw060_fold3

BERT_AugV8_k5_task1_organization_sp010_lw060_fold3