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	8.8636	0.0	8.8636	2.9772
No log	2.0	4	8.0086	0.0	8.0086	2.8299
No log	3.0	6	6.9535	0.0	6.9535	2.6369
No log	4.0	8	6.3978	-0.0118	6.3978	2.5294
No log	5.0	10	5.4493	0.0112	5.4493	2.3344
No log	6.0	12	4.7400	0.0039	4.7400	2.1772
No log	7.0	14	3.9075	0.0	3.9075	1.9767
No log	8.0	16	3.2726	0.0	3.2726	1.8090
No log	9.0	18	2.4924	0.0449	2.4924	1.5787
No log	10.0	20	1.9388	0.0316	1.9388	1.3924
No log	11.0	22	1.6318	0.0316	1.6318	1.2774
No log	12.0	24	1.3150	0.0316	1.3150	1.1467
No log	13.0	26	1.1369	0.0316	1.1369	1.0663
No log	14.0	28	0.9602	0.0316	0.9602	0.9799
No log	15.0	30	1.3103	0.0627	1.3103	1.1447
No log	16.0	32	1.6033	0.1121	1.6033	1.2662
No log	17.0	34	1.2709	0.0778	1.2709	1.1273
No log	18.0	36	0.7234	0.3730	0.7234	0.8505
No log	19.0	38	0.7037	0.3533	0.7037	0.8389
No log	20.0	40	0.7894	0.3896	0.7894	0.8885
No log	21.0	42	1.1399	0.0960	1.1399	1.0677
No log	22.0	44	0.9949	0.1694	0.9949	0.9974
No log	23.0	46	0.7528	0.3789	0.7528	0.8676
No log	24.0	48	0.8228	0.3802	0.8228	0.9071
No log	25.0	50	1.3379	0.2305	1.3379	1.1567
No log	26.0	52	1.2864	0.2521	1.2864	1.1342
No log	27.0	54	0.8327	0.3568	0.8327	0.9125
No log	28.0	56	0.7103	0.3426	0.7103	0.8428
No log	29.0	58	0.9240	0.3034	0.9240	0.9613
No log	30.0	60	0.9152	0.2990	0.9152	0.9566
No log	31.0	62	0.7196	0.3420	0.7196	0.8483
No log	32.0	64	0.8431	0.3341	0.8431	0.9182
No log	33.0	66	0.9404	0.2963	0.9404	0.9697
No log	34.0	68	0.8274	0.3537	0.8274	0.9096
No log	35.0	70	1.0569	0.2929	1.0569	1.0280

genki10/BERT_AugV8_k1_task1_organization_sp020_lw060_fold0

BERT_AugV8_k1_task1_organization_sp020_lw060_fold0