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	8.1343	0.0	8.1343	2.8521
No log	2.0	6	6.7153	0.0	6.7153	2.5914
No log	3.0	9	5.4572	0.0115	5.4572	2.3361
No log	4.0	12	4.2190	0.0039	4.2190	2.0540
No log	5.0	15	3.0193	0.0	3.0193	1.7376
No log	6.0	18	2.0801	0.0800	2.0801	1.4423
No log	7.0	21	1.4060	0.0316	1.4060	1.1858
No log	8.0	24	1.0253	0.0316	1.0253	1.0126
No log	9.0	27	0.9162	0.0316	0.9162	0.9572
No log	10.0	30	0.8962	0.2263	0.8962	0.9467
No log	11.0	33	0.7670	0.4500	0.7670	0.8758
No log	12.0	36	1.1799	0.2791	1.1799	1.0862
No log	13.0	39	0.6066	0.5344	0.6066	0.7788
No log	14.0	42	0.8754	0.3907	0.8754	0.9356
No log	15.0	45	1.0613	0.3559	1.0613	1.0302
No log	16.0	48	0.6447	0.4182	0.6447	0.8029
No log	17.0	51	0.9670	0.3309	0.9670	0.9834
No log	18.0	54	0.6684	0.4040	0.6684	0.8176
No log	19.0	57	0.6834	0.4019	0.6834	0.8267
No log	20.0	60	0.7613	0.3670	0.7613	0.8725
No log	21.0	63	0.8292	0.3802	0.8292	0.9106
No log	22.0	66	0.8906	0.3691	0.8906	0.9437
No log	23.0	69	0.9065	0.3895	0.9065	0.9521
No log	24.0	72	1.0241	0.3567	1.0241	1.0120
No log	25.0	75	0.8279	0.3989	0.8279	0.9099
No log	26.0	78	1.4776	0.1980	1.4776	1.2156
No log	27.0	81	0.9273	0.3300	0.9273	0.9630
No log	28.0	84	0.8093	0.4043	0.8093	0.8996

genki10/Trial3BERT_AugV8_k3_task1_organization_sp050_lw010_fold0

Trial3BERT_AugV8_k3_task1_organization_sp050_lw010_fold0