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	9.9997	0.0065	9.9982	3.1620
No log	2.0	8	5.9691	0.0381	5.9678	2.4429
No log	3.0	12	3.1973	0.0076	3.1964	1.7879
No log	4.0	16	1.9501	0.1061	1.9494	1.3962
No log	5.0	20	1.1615	0.0365	1.1609	1.0775
No log	6.0	24	0.8718	0.3091	0.8714	0.9335
No log	7.0	28	0.9440	0.0824	0.9437	0.9715
No log	8.0	32	0.8941	0.1987	0.8941	0.9456
No log	9.0	36	0.6831	0.4686	0.6834	0.8267
No log	10.0	40	0.7589	0.4075	0.7598	0.8717
No log	11.0	44	0.6152	0.4052	0.6157	0.7847
No log	12.0	48	0.5672	0.4487	0.5677	0.7535
No log	13.0	52	0.5994	0.4882	0.6000	0.7746
No log	14.0	56	1.2518	0.2709	1.2522	1.1190
No log	15.0	60	0.5855	0.5447	0.5859	0.7655
No log	16.0	64	1.9505	0.1675	1.9511	1.3968
No log	17.0	68	0.8510	0.4389	0.8516	0.9228
No log	18.0	72	1.1620	0.2995	1.1626	1.0782
No log	19.0	76	0.6128	0.4987	0.6134	0.7832
No log	20.0	80	1.5256	0.2344	1.5261	1.2353
No log	21.0	84	1.0052	0.2849	1.0057	1.0028
No log	22.0	88	0.6196	0.4541	0.6202	0.7875
No log	23.0	92	1.4141	0.2168	1.4144	1.1893
No log	24.0	96	0.6293	0.4500	0.6298	0.7936
No log	25.0	100	1.1209	0.2924	1.1213	1.0589
No log	26.0	104	0.7633	0.3976	0.7637	0.8739
No log	27.0	108	1.3820	0.2469	1.3823	1.1757
No log	28.0	112	0.9074	0.3476	0.9078	0.9528
No log	29.0	116	1.1826	0.2882	1.1828	1.0876
No log	30.0	120	0.6645	0.4494	0.6649	0.8154

genki10/Trial3BERT_AugV8_k5_task1_organization_sp010_lw020_fold3

Trial3BERT_AugV8_k5_task1_organization_sp010_lw020_fold3