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	9.8399	0.0	9.8381	3.1366
No log	2.0	8	6.1127	0.0369	6.1113	2.4721
No log	3.0	12	3.8091	0.0	3.8081	1.9514
No log	4.0	16	2.5212	0.0819	2.5204	1.5876
No log	5.0	20	1.6102	0.0102	1.6095	1.2687
No log	6.0	24	1.3131	0.0302	1.3126	1.1457
No log	7.0	28	0.9497	0.1117	0.9491	0.9742
No log	8.0	32	0.9000	0.2155	0.8997	0.9485
No log	9.0	36	1.0219	0.1099	1.0217	1.0108
No log	10.0	40	0.9267	0.2658	0.9265	0.9626
No log	11.0	44	0.9925	0.3666	0.9924	0.9962
No log	12.0	48	1.7256	0.2470	1.7252	1.3135
No log	13.0	52	1.3525	0.3004	1.3522	1.1628
No log	14.0	56	1.3833	0.3027	1.3828	1.1759
No log	15.0	60	1.8487	0.2381	1.8476	1.3593
No log	16.0	64	1.0559	0.3979	1.0554	1.0273
No log	17.0	68	1.4325	0.3129	1.4318	1.1966
No log	18.0	72	1.1057	0.3833	1.1051	1.0512
No log	19.0	76	1.1910	0.3419	1.1903	1.0910
No log	20.0	80	1.3988	0.2856	1.3980	1.1824
No log	21.0	84	1.1886	0.3386	1.1882	1.0900
No log	22.0	88	1.2465	0.3407	1.2461	1.1163
No log	23.0	92	1.1015	0.3630	1.1013	1.0494
No log	24.0	96	1.7193	0.2262	1.7187	1.3110
No log	25.0	100	1.3503	0.2858	1.3498	1.1618
No log	26.0	104	1.1207	0.3533	1.1203	1.0585
No log	27.0	108	1.4646	0.2799	1.4641	1.2100
No log	28.0	112	1.7664	0.2368	1.7656	1.3288
No log	29.0	116	1.0499	0.3683	1.0495	1.0245
No log	30.0	120	2.3371	0.1444	2.3359	1.5284
No log	31.0	124	1.0037	0.3672	1.0033	1.0016

genki10/Trial3BERT_AugV8_k5_task1_organization_sp020_lw010_fold3

Trial3BERT_AugV8_k5_task1_organization_sp020_lw010_fold3