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	8.9304	0.0	8.9306	2.9884
No log	2.0	6	7.2613	0.0	7.2617	2.6948
No log	3.0	9	4.7938	0.0080	4.7941	2.1895
No log	4.0	12	3.2715	0.0078	3.2720	1.8089
No log	5.0	15	1.8541	0.1112	1.8546	1.3619
No log	6.0	18	1.2067	0.0318	1.2072	1.0987
No log	7.0	21	1.0548	0.0384	1.0553	1.0273
No log	8.0	24	0.9271	0.1227	0.9276	0.9631
No log	9.0	27	1.0513	0.1290	1.0518	1.0256
No log	10.0	30	0.7368	0.4099	0.7372	0.8586
No log	11.0	33	0.8265	0.3658	0.8269	0.9093
No log	12.0	36	0.8423	0.3858	0.8427	0.9180
No log	13.0	39	0.5779	0.5032	0.5781	0.7603
No log	14.0	42	0.7141	0.4645	0.7144	0.8452
No log	15.0	45	0.7057	0.4721	0.7059	0.8402
No log	16.0	48	0.7134	0.4803	0.7136	0.8448
No log	17.0	51	0.7715	0.4492	0.7718	0.8785
No log	18.0	54	0.8417	0.4586	0.8418	0.9175
No log	19.0	57	0.9687	0.4296	0.9688	0.9843
No log	20.0	60	0.8511	0.4777	0.8511	0.9226
No log	21.0	63	1.5266	0.2618	1.5267	1.2356
No log	22.0	66	0.7264	0.5120	0.7265	0.8524
No log	23.0	69	1.0208	0.3651	1.0210	1.0105
No log	24.0	72	0.7877	0.4843	0.7877	0.8875
No log	25.0	75	0.9299	0.4145	0.9299	0.9643
No log	26.0	78	1.0995	0.3477	1.0994	1.0485
No log	27.0	81	0.8710	0.4090	0.8708	0.9332
No log	28.0	84	1.1652	0.3355	1.1650	1.0794
No log	29.0	87	0.8347	0.4361	0.8346	0.9136
No log	30.0	90	1.3777	0.2857	1.3777	1.1738
No log	31.0	93	0.9714	0.3646	0.9716	0.9857
No log	32.0	96	1.0686	0.2950	1.0689	1.0339
No log	33.0	99	0.9230	0.3733	0.9231	0.9608
No log	34.0	102	1.0610	0.3166	1.0610	1.0301
No log	35.0	105	0.8252	0.4310	0.8252	0.9084
No log	36.0	108	1.5165	0.2602	1.5166	1.2315
No log	37.0	111	0.8930	0.4038	0.8930	0.9450

genki10/BERT_AugV8_k3_task1_organization_sp010_lw060_fold2

BERT_AugV8_k3_task1_organization_sp010_lw060_fold2