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	7.5174	0.0	7.5174	2.7418
No log	2.0	8	5.8150	0.0177	5.8150	2.4114
No log	3.0	12	4.1546	0.0039	4.1546	2.0383
No log	4.0	16	2.5282	0.0283	2.5282	1.5900
No log	5.0	20	1.5679	0.0316	1.5679	1.2521
No log	6.0	24	1.3552	0.0316	1.3552	1.1641
No log	7.0	28	1.2973	0.0382	1.2973	1.1390
No log	8.0	32	1.6056	0.1409	1.6056	1.2671
No log	9.0	36	1.4526	0.1429	1.4526	1.2052
No log	10.0	40	0.9051	0.1794	0.9051	0.9514
No log	11.0	44	0.8263	0.3561	0.8263	0.9090
No log	12.0	48	1.0118	0.3307	1.0118	1.0059
No log	13.0	52	0.8767	0.3072	0.8767	0.9363
No log	14.0	56	1.0037	0.2750	1.0037	1.0019
No log	15.0	60	1.0129	0.2505	1.0129	1.0065
No log	16.0	64	0.9845	0.3129	0.9845	0.9922
No log	17.0	68	1.0702	0.3451	1.0702	1.0345
No log	18.0	72	1.0945	0.2949	1.0945	1.0462
No log	19.0	76	1.1265	0.2531	1.1265	1.0614
No log	20.0	80	1.1595	0.2509	1.1595	1.0768
No log	21.0	84	0.9363	0.3791	0.9363	0.9676
No log	22.0	88	1.3031	0.2635	1.3031	1.1415
No log	23.0	92	1.3763	0.2324	1.3763	1.1731
No log	24.0	96	0.9505	0.3656	0.9505	0.9749
No log	25.0	100	1.3395	0.2363	1.3395	1.1574
No log	26.0	104	1.0542	0.3153	1.0542	1.0267
No log	27.0	108	0.9679	0.3396	0.9679	0.9838
No log	28.0	112	1.3665	0.2533	1.3665	1.1690
No log	29.0	116	0.9949	0.2985	0.9949	0.9975
No log	30.0	120	0.9761	0.3265	0.9761	0.9880
No log	31.0	124	1.3503	0.2160	1.3503	1.1620
No log	32.0	128	0.8436	0.3761	0.8436	0.9185
No log	33.0	132	1.3400	0.2397	1.3400	1.1576
No log	34.0	136	0.9131	0.3177	0.9131	0.9556
No log	35.0	140	1.6198	0.1645	1.6198	1.2727
No log	36.0	144	0.8481	0.3278	0.8481	0.9209

genki10/BERT_AugV8_k5_task1_organization_sp020_lw070_fold0

BERT_AugV8_k5_task1_organization_sp020_lw070_fold0