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	9.8950	0.0018	9.8950	3.1456
No log	2.0	8	6.7686	0.0	6.7686	2.6017
No log	3.0	12	4.4800	0.0079	4.4800	2.1166
No log	4.0	16	2.8380	0.0040	2.8380	1.6846
No log	5.0	20	1.6081	0.0420	1.6081	1.2681
No log	6.0	24	1.2574	0.0316	1.2574	1.1213
No log	7.0	28	1.1992	0.0420	1.1992	1.0951
No log	8.0	32	1.7628	0.1539	1.7628	1.3277
No log	9.0	36	1.0699	0.0900	1.0699	1.0344
No log	10.0	40	1.1350	0.1584	1.1350	1.0653
No log	11.0	44	0.7501	0.3539	0.7501	0.8661
No log	12.0	48	0.7306	0.4327	0.7306	0.8548
No log	13.0	52	0.6424	0.4481	0.6424	0.8015
No log	14.0	56	0.6994	0.4242	0.6994	0.8363
No log	15.0	60	0.9502	0.3616	0.9502	0.9748
No log	16.0	64	0.6484	0.4953	0.6484	0.8053
No log	17.0	68	0.8318	0.4132	0.8318	0.9120
No log	18.0	72	0.9807	0.3977	0.9807	0.9903
No log	19.0	76	0.7197	0.4903	0.7197	0.8484
No log	20.0	80	0.8765	0.3763	0.8765	0.9362
No log	21.0	84	0.7117	0.4553	0.7117	0.8436
No log	22.0	88	1.0575	0.3344	1.0575	1.0283
No log	23.0	92	0.8795	0.3757	0.8795	0.9378
No log	24.0	96	0.7224	0.4366	0.7224	0.8500
No log	25.0	100	0.8483	0.4216	0.8483	0.9210
No log	26.0	104	0.6804	0.4521	0.6804	0.8249
No log	27.0	108	1.2396	0.2812	1.2396	1.1134
No log	28.0	112	0.6494	0.4864	0.6494	0.8058
No log	29.0	116	1.2698	0.2466	1.2698	1.1269
No log	30.0	120	0.6770	0.4309	0.6770	0.8228
No log	31.0	124	1.0640	0.2976	1.0640	1.0315

genki10/BERT_AugV8_k5_task1_organization_sp020_lw070_fold4

BERT_AugV8_k5_task1_organization_sp020_lw070_fold4