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	9.6022	0.0	9.6003	3.0984
No log	2.0	8	8.4488	0.0	8.4471	2.9064
No log	3.0	12	6.6919	0.0	6.6904	2.5866
No log	4.0	16	4.9792	0.0097	4.9782	2.2312
No log	5.0	20	3.3786	0.0	3.3776	1.8378
No log	6.0	24	2.3373	0.1039	2.3364	1.5285
No log	7.0	28	1.4363	0.0302	1.4357	1.1982
No log	8.0	32	1.1045	0.0102	1.1040	1.0507
No log	9.0	36	0.8968	0.2051	0.8965	0.9468
No log	10.0	40	1.0610	0.0524	1.0606	1.0299
No log	11.0	44	0.6976	0.4846	0.6975	0.8352
No log	12.0	48	1.3053	0.2058	1.3052	1.1425
No log	13.0	52	0.6428	0.4978	0.6433	0.8021
No log	14.0	56	0.6138	0.5410	0.6144	0.7838
No log	15.0	60	0.5841	0.5597	0.5848	0.7647
No log	16.0	64	0.5706	0.5732	0.5715	0.7560
No log	17.0	68	0.6185	0.5869	0.6193	0.7870
No log	18.0	72	0.8111	0.5280	0.8115	0.9008
No log	19.0	76	0.8806	0.4862	0.8808	0.9385
No log	20.0	80	0.7120	0.5568	0.7127	0.8442
No log	21.0	84	1.2976	0.3358	1.2978	1.1392
No log	22.0	88	0.6804	0.5480	0.6812	0.8253
No log	23.0	92	1.1191	0.3957	1.1195	1.0581
No log	24.0	96	0.6721	0.5280	0.6727	0.8202
No log	25.0	100	1.0469	0.4010	1.0472	1.0233
No log	26.0	104	0.9770	0.4283	0.9774	0.9886
No log	27.0	108	0.6679	0.5318	0.6683	0.8175
No log	28.0	112	0.9707	0.4146	0.9709	0.9853
No log	29.0	116	0.7887	0.4712	0.7891	0.8883
No log	30.0	120	0.6657	0.5350	0.6661	0.8162
No log	31.0	124	1.0865	0.4076	1.0868	1.0425
No log	32.0	128	0.6468	0.5565	0.6473	0.8046

genki10/Trial3BERT_AugV8_k5_task1_organization_sp010_lw010_fold3

Trial3BERT_AugV8_k5_task1_organization_sp010_lw010_fold3