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	7	5.0796	0.0151	5.0773	2.2533
No log	2.0	14	2.0851	0.2221	2.0835	1.4434
No log	3.0	21	1.3102	0.0	1.3088	1.1440
No log	4.0	28	1.4298	0.0262	1.4283	1.1951
No log	5.0	35	0.9897	0.1450	0.9883	0.9941
No log	6.0	42	0.7032	0.3937	0.7022	0.8380
No log	7.0	49	0.8690	0.1961	0.8681	0.9317
No log	8.0	56	0.8029	0.2865	0.8018	0.8954
No log	9.0	63	1.0620	0.1659	1.0612	1.0301
No log	10.0	70	0.6236	0.4408	0.6227	0.7891
No log	11.0	77	0.7977	0.2851	0.7969	0.8927
No log	12.0	84	0.7624	0.3977	0.7616	0.8727
No log	13.0	91	0.8368	0.2658	0.8361	0.9144
No log	14.0	98	0.5664	0.5273	0.5659	0.7522
No log	15.0	105	0.7402	0.3678	0.7396	0.8600
No log	16.0	112	0.9871	0.1443	0.9865	0.9932
No log	17.0	119	0.9409	0.3444	0.9402	0.9696
No log	18.0	126	0.8650	0.3411	0.8642	0.9296
No log	19.0	133	0.8955	0.3298	0.8949	0.9460
No log	20.0	140	1.5031	0.1646	1.5021	1.2256
No log	21.0	147	1.1546	0.2473	1.1538	1.0741
No log	22.0	154	0.9202	0.3435	0.9194	0.9589
No log	23.0	161	1.1024	0.2187	1.1016	1.0496
No log	24.0	168	0.9552	0.3135	0.9544	0.9770
No log	25.0	175	1.0754	0.2496	1.0745	1.0366
No log	26.0	182	1.2399	0.2878	1.2390	1.1131
No log	27.0	189	0.8803	0.3203	0.8794	0.9378
No log	28.0	196	0.8534	0.3042	0.8526	0.9233
No log	29.0	203	0.9020	0.3168	0.9013	0.9493

genki10/BERT_AugV8_k10_task1_organization_sp010_lw060_fold1

BERT_AugV8_k10_task1_organization_sp010_lw060_fold1