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	6.8295	0.0	6.8296	2.6134
No log	2.0	8	3.9140	0.0039	3.9144	1.9785
No log	3.0	12	2.5196	0.0234	2.5201	1.5875
No log	4.0	16	1.4850	0.0107	1.4856	1.2188
No log	5.0	20	1.1827	0.0107	1.1833	1.0878
No log	6.0	24	0.9532	0.0117	0.9536	0.9765
No log	7.0	28	0.7652	0.3339	0.7656	0.8750
No log	8.0	32	0.9715	0.1723	0.9720	0.9859
No log	9.0	36	0.5888	0.3918	0.5890	0.7675
No log	10.0	40	1.1641	0.2109	1.1646	1.0792
No log	11.0	44	0.5631	0.5394	0.5632	0.7505
No log	12.0	48	0.7985	0.4116	0.7986	0.8936
No log	13.0	52	0.6795	0.4613	0.6795	0.8243
No log	14.0	56	0.5731	0.5006	0.5731	0.7570
No log	15.0	60	0.5292	0.5222	0.5290	0.7273
No log	16.0	64	0.7781	0.4670	0.7781	0.8821
No log	17.0	68	0.8461	0.3841	0.8462	0.9199
No log	18.0	72	0.6420	0.5131	0.6415	0.8009
No log	19.0	76	0.9355	0.3821	0.9353	0.9671
No log	20.0	80	0.5940	0.4985	0.5936	0.7705
No log	21.0	84	0.9963	0.2833	0.9964	0.9982
No log	22.0	88	0.6116	0.4976	0.6116	0.7820
No log	23.0	92	0.9272	0.3523	0.9274	0.9630
No log	24.0	96	0.8735	0.3729	0.8736	0.9347
No log	25.0	100	0.5765	0.5327	0.5764	0.7592
No log	26.0	104	0.8847	0.3520	0.8847	0.9406

genki10/Trial3BERT_AugV8_k5_task1_organization_sp010_lw010_fold2

Trial3BERT_AugV8_k5_task1_organization_sp010_lw010_fold2