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	11.7014	-0.0050	11.6985	3.4203
No log	2.0	8	8.1709	0.0	8.1685	2.8581
No log	3.0	12	5.2231	0.0162	5.2210	2.2849
No log	4.0	16	3.5930	0.0	3.5910	1.8950
No log	5.0	20	1.9991	0.0714	1.9974	1.4133
No log	6.0	24	1.6047	0.0315	1.6029	1.2661
No log	7.0	28	1.6114	0.0211	1.6098	1.2688
No log	8.0	32	1.5342	0.0568	1.5325	1.2380
No log	9.0	36	2.2022	0.0750	2.2001	1.4833
No log	10.0	40	1.8100	0.0837	1.8079	1.3446
No log	11.0	44	3.1101	-0.0098	3.1079	1.7629
No log	12.0	48	2.0643	-0.0093	2.0626	1.4362
No log	13.0	52	2.1337	-0.0202	2.1321	1.4602
No log	14.0	56	2.4092	0.0259	2.4077	1.5517
No log	15.0	60	3.4895	0.0026	3.4883	1.8677
No log	16.0	64	3.5711	-0.0213	3.5699	1.8894
No log	17.0	68	2.2113	0.0112	2.2105	1.4868
No log	18.0	72	4.2675	-0.0213	4.2661	2.0655
No log	19.0	76	3.6042	-0.0127	3.6030	1.8982
No log	20.0	80	2.6115	0.0326	2.6105	1.6157
No log	21.0	84	2.8144	0.0076	2.8132	1.6773
No log	22.0	88	2.8153	0.0065	2.8143	1.6776
No log	23.0	92	2.8656	0.0295	2.8645	1.6925
No log	24.0	96	2.5194	0.0161	2.5183	1.5869
No log	25.0	100	2.6668	0.0142	2.6657	1.6327

genki10/Trial3BERT_AugV8_k5_task1_organization_sp020_lw070_fold1

Trial3BERT_AugV8_k5_task1_organization_sp020_lw070_fold1