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	7.5848	0.0	7.5848	2.7541
No log	2.0	8	5.9180	0.0347	5.9180	2.4327
No log	3.0	12	4.2547	0.0039	4.2547	2.0627
No log	4.0	16	2.6844	0.0	2.6844	1.6384
No log	5.0	20	1.5934	0.0316	1.5934	1.2623
No log	6.0	24	1.2899	0.0316	1.2899	1.1357
No log	7.0	28	2.0946	0.1954	2.0946	1.4473
No log	8.0	32	1.0965	0.0484	1.0965	1.0471
No log	9.0	36	1.8072	0.1751	1.8072	1.3443
No log	10.0	40	1.0002	0.2401	1.0002	1.0001
No log	11.0	44	1.0958	0.2695	1.0958	1.0468
No log	12.0	48	1.3568	0.2192	1.3568	1.1648
No log	13.0	52	0.6872	0.3707	0.6872	0.8290
No log	14.0	56	1.1698	0.2864	1.1698	1.0816
No log	15.0	60	0.7535	0.4084	0.7535	0.8680
No log	16.0	64	1.5680	0.1742	1.5680	1.2522
No log	17.0	68	0.7638	0.3425	0.7638	0.8740
No log	18.0	72	1.5723	0.1916	1.5723	1.2539
No log	19.0	76	1.0879	0.2846	1.0879	1.0430
No log	20.0	80	1.2315	0.2620	1.2315	1.1097
No log	21.0	84	1.1390	0.2447	1.1390	1.0672
No log	22.0	88	0.9356	0.2976	0.9356	0.9673
No log	23.0	92	1.1768	0.2629	1.1768	1.0848
No log	24.0	96	1.1171	0.2806	1.1171	1.0569
No log	25.0	100	1.2312	0.2480	1.2312	1.1096
No log	26.0	104	1.0669	0.2657	1.0669	1.0329
No log	27.0	108	1.2994	0.2121	1.2994	1.1399
No log	28.0	112	1.1549	0.2339	1.1549	1.0747
No log	29.0	116	1.0490	0.2812	1.0490	1.0242
No log	30.0	120	1.6400	0.1977	1.6400	1.2806

genki10/BERT_AugV8_k5_task1_organization_sp060_lw010_fold0

BERT_AugV8_k5_task1_organization_sp060_lw010_fold0