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	3	11.1429	0.0340	11.1412	3.3378
No log	2.0	6	7.4817	0.0	7.4803	2.7350
No log	3.0	9	5.2361	0.0264	5.2349	2.2880
No log	4.0	12	3.3810	0.0	3.3800	1.8385
No log	5.0	15	2.2979	0.0855	2.2970	1.5156
No log	6.0	18	1.6744	0.0401	1.6736	1.2937
No log	7.0	21	1.7543	0.0202	1.7534	1.3242
No log	8.0	24	1.6791	0.0202	1.6782	1.2955
No log	9.0	27	1.2708	0.0202	1.2702	1.1270
No log	10.0	30	1.0779	0.0401	1.0773	1.0379
No log	11.0	33	1.6575	0.0952	1.6568	1.2872
No log	12.0	36	0.8514	0.3465	0.8511	0.9226
No log	13.0	39	0.7571	0.4542	0.7570	0.8700
No log	14.0	42	0.7667	0.4401	0.7668	0.8756
No log	15.0	45	0.7597	0.4641	0.7599	0.8717
No log	16.0	48	0.7513	0.4227	0.7516	0.8669
No log	17.0	51	0.7327	0.3964	0.7331	0.8562
No log	18.0	54	0.8191	0.3738	0.8196	0.9053
No log	19.0	57	1.1504	0.2634	1.1507	1.0727
No log	20.0	60	1.0851	0.3117	1.0854	1.0418
No log	21.0	63	1.1496	0.3032	1.1499	1.0723
No log	22.0	66	1.1395	0.3141	1.1398	1.0676
No log	23.0	69	1.0214	0.3205	1.0217	1.0108
No log	24.0	72	1.3952	0.2292	1.3952	1.1812
No log	25.0	75	1.0882	0.3056	1.0886	1.0434
No log	26.0	78	1.1070	0.3016	1.1074	1.0523
No log	27.0	81	1.1486	0.2310	1.1488	1.0718
No log	28.0	84	0.9582	0.3580	0.9587	0.9791
No log	29.0	87	1.3551	0.2357	1.3553	1.1642
No log	30.0	90	0.8802	0.4068	0.8806	0.9384

genki10/BERT_AugV8_k3_task1_organization_sp020_lw070_fold3

BERT_AugV8_k3_task1_organization_sp020_lw070_fold3