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	9.0331	0.0	9.0331	3.0055
No log	2.0	4	8.1170	0.0	8.1170	2.8490
No log	3.0	6	6.7869	0.0	6.7869	2.6052
No log	4.0	8	6.2915	-0.0099	6.2915	2.5083
No log	5.0	10	5.2849	0.0112	5.2849	2.2989
No log	6.0	12	4.5260	0.0039	4.5260	2.1274
No log	7.0	14	3.8283	0.0039	3.8283	1.9566
No log	8.0	16	3.0756	0.0	3.0756	1.7537
No log	9.0	18	2.4557	-0.0052	2.4557	1.5671
No log	10.0	20	1.8463	0.0511	1.8463	1.3588
No log	11.0	22	1.5962	0.0382	1.5962	1.2634
No log	12.0	24	1.2311	0.0316	1.2311	1.1096
No log	13.0	26	1.0406	0.0316	1.0406	1.0201
No log	14.0	28	1.4934	0.0873	1.4934	1.2221
No log	15.0	30	2.0299	0.1836	2.0299	1.4247
No log	16.0	32	1.4464	0.1070	1.4464	1.2027
No log	17.0	34	0.7052	0.4360	0.7052	0.8398
No log	18.0	36	0.6811	0.4119	0.6811	0.8253
No log	19.0	38	0.9231	0.1800	0.9231	0.9608
No log	20.0	40	1.6929	0.1745	1.6929	1.3011
No log	21.0	42	1.2859	0.1646	1.2859	1.1340
No log	22.0	44	0.7041	0.4467	0.7041	0.8391
No log	23.0	46	0.6874	0.4555	0.6874	0.8291
No log	24.0	48	1.0558	0.2506	1.0558	1.0275
No log	25.0	50	1.2480	0.2378	1.2480	1.1171
No log	26.0	52	0.8917	0.3475	0.8917	0.9443
No log	27.0	54	0.6939	0.3612	0.6939	0.8330
No log	28.0	56	0.7054	0.3734	0.7054	0.8399
No log	29.0	58	1.0255	0.3178	1.0255	1.0127
No log	30.0	60	1.0685	0.2846	1.0685	1.0337
No log	31.0	62	0.7563	0.3444	0.7563	0.8696
No log	32.0	64	0.7480	0.3425	0.7480	0.8649
No log	33.0	66	0.8954	0.3110	0.8954	0.9463
No log	34.0	68	1.3650	0.2395	1.3650	1.1683
No log	35.0	70	1.2257	0.2813	1.2257	1.1071
No log	36.0	72	0.9056	0.3334	0.9056	0.9516
No log	37.0	74	1.0302	0.3360	1.0302	1.0150
No log	38.0	76	1.4768	0.2040	1.4768	1.2153

genki10/Trial3BERT_AugV8_k1_task1_organization_sp020_lw070_fold0

Trial3BERT_AugV8_k1_task1_organization_sp020_lw070_fold0