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	2	10.0933	0.0054	10.0919	3.1768
No log	2.0	4	7.8221	0.0	7.8206	2.7965
No log	3.0	6	6.6524	0.0	6.6511	2.5790
No log	4.0	8	5.2523	0.0157	5.2510	2.2915
No log	5.0	10	4.0878	0.0124	4.0872	2.0217
No log	6.0	12	3.1184	0.0038	3.1171	1.7655
No log	7.0	14	2.4097	0.1591	2.4089	1.5521
No log	8.0	16	2.0091	0.1327	2.0085	1.4172
No log	9.0	18	1.8498	0.0365	1.8489	1.3598
No log	10.0	20	1.4105	0.0365	1.4098	1.1874
No log	11.0	22	1.3762	0.0658	1.3757	1.1729
No log	12.0	24	1.3136	0.0949	1.3132	1.1459
No log	13.0	26	0.9338	0.1485	0.9335	0.9662
No log	14.0	28	0.7811	0.3385	0.7807	0.8836
No log	15.0	30	0.8118	0.3487	0.8114	0.9008
No log	16.0	32	0.9184	0.1931	0.9181	0.9582
No log	17.0	34	1.1109	0.1654	1.1106	1.0539
No log	18.0	36	0.9382	0.3129	0.9379	0.9685
No log	19.0	38	0.7731	0.4213	0.7729	0.8791
No log	20.0	40	0.8721	0.4008	0.8720	0.9338
No log	21.0	42	1.3629	0.2629	1.3628	1.1674
No log	22.0	44	1.3590	0.2683	1.3590	1.1658
No log	23.0	46	0.8321	0.4592	0.8321	0.9122
No log	24.0	48	0.7868	0.4330	0.7869	0.8871
No log	25.0	50	1.4828	0.2370	1.4828	1.2177
No log	26.0	52	1.4087	0.2295	1.4088	1.1869
No log	27.0	54	0.7053	0.4275	0.7056	0.8400
No log	28.0	56	0.6369	0.4530	0.6373	0.7983
No log	29.0	58	0.9506	0.3680	0.9510	0.9752
No log	30.0	60	1.1894	0.3152	1.1898	1.0908
No log	31.0	62	0.7208	0.4321	0.7213	0.8493
No log	32.0	64	0.7776	0.4428	0.7781	0.8821
No log	33.0	66	1.4864	0.2814	1.4869	1.2194
No log	34.0	68	1.3960	0.2899	1.3966	1.1818
No log	35.0	70	0.7511	0.4178	0.7519	0.8671
No log	36.0	72	0.7508	0.4298	0.7517	0.8670
No log	37.0	74	1.0300	0.3583	1.0308	1.0153
No log	38.0	76	1.1773	0.2680	1.1780	1.0853

genki10/Trial2BERT_AugV8_k1_task1_organization_sp010_lw050_fold3

Trial2BERT_AugV8_k1_task1_organization_sp010_lw050_fold3