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	7.5774	0.0	7.5774	2.7527
No log	2.0	8	5.9039	0.0308	5.9039	2.4298
No log	3.0	12	4.2125	0.0039	4.2125	2.0524
No log	4.0	16	2.6225	0.0	2.6225	1.6194
No log	5.0	20	1.5446	0.0316	1.5446	1.2428
No log	6.0	24	1.0403	0.0316	1.0403	1.0199
No log	7.0	28	1.1554	0.0743	1.1554	1.0749
No log	8.0	32	0.8479	0.3653	0.8479	0.9208
No log	9.0	36	0.8010	0.4056	0.8010	0.8950
No log	10.0	40	0.9456	0.2689	0.9456	0.9724
No log	11.0	44	0.7002	0.3617	0.7002	0.8368
No log	12.0	48	0.8157	0.3595	0.8157	0.9032
No log	13.0	52	0.9161	0.3032	0.9161	0.9571
No log	14.0	56	0.7034	0.3589	0.7034	0.8387
No log	15.0	60	0.7246	0.4109	0.7246	0.8513
No log	16.0	64	0.9091	0.4168	0.9091	0.9534
No log	17.0	68	0.7210	0.4661	0.7210	0.8491
No log	18.0	72	0.8857	0.3473	0.8857	0.9411
No log	19.0	76	0.8724	0.3726	0.8724	0.9340
No log	20.0	80	0.7129	0.4263	0.7129	0.8443
No log	21.0	84	0.9215	0.3107	0.9215	0.9599
No log	22.0	88	0.9694	0.3080	0.9694	0.9846
No log	23.0	92	0.8031	0.3561	0.8031	0.8961
No log	24.0	96	0.7921	0.3882	0.7921	0.8900
No log	25.0	100	0.7592	0.4182	0.7592	0.8713
No log	26.0	104	0.8465	0.3568	0.8465	0.9201
No log	27.0	108	0.9071	0.2997	0.9071	0.9524
No log	28.0	112	0.7322	0.4256	0.7322	0.8557
No log	29.0	116	0.8915	0.3594	0.8915	0.9442
No log	30.0	120	1.0464	0.2608	1.0464	1.0229
No log	31.0	124	0.7762	0.3560	0.7762	0.8810
No log	32.0	128	0.8125	0.3923	0.8125	0.9014

genki10/Trial3BERT_AugV8_k5_task1_organization_sp030_lw010_fold0

Trial3BERT_AugV8_k5_task1_organization_sp030_lw010_fold0