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	9.2135	0.0	9.2109	3.0349
No log	2.0	6	5.8601	0.0244	5.8581	2.4203
No log	3.0	9	3.7444	0.0	3.7429	1.9347
No log	4.0	12	2.6206	0.0	2.6188	1.6183
No log	5.0	15	1.9159	0.0592	1.9142	1.3836
No log	6.0	18	1.3726	0.0	1.3711	1.1709
No log	7.0	21	1.2267	0.0	1.2253	1.1069
No log	8.0	24	0.9310	0.1245	0.9298	0.9643
No log	9.0	27	0.9639	0.0735	0.9627	0.9812
No log	10.0	30	1.6947	-0.0128	1.6930	1.3011
No log	11.0	33	0.7900	0.4308	0.7889	0.8882
No log	12.0	36	0.7903	0.4046	0.7893	0.8884
No log	13.0	39	0.7842	0.3885	0.7830	0.8849
No log	14.0	42	1.4622	-0.0846	1.4606	1.2085
No log	15.0	45	1.1450	-0.0143	1.1438	1.0695
No log	16.0	48	0.8121	0.1879	0.8111	0.9006
No log	17.0	51	0.9630	0.2580	0.9620	0.9808
No log	18.0	54	0.8843	0.3139	0.8835	0.9399
No log	19.0	57	0.8518	0.2628	0.8510	0.9225
No log	20.0	60	1.2451	0.0760	1.2440	1.1154
No log	21.0	63	0.8308	0.3617	0.8301	0.9111
No log	22.0	66	0.8677	0.3915	0.8671	0.9312
No log	23.0	69	1.1814	0.2157	1.1804	1.0865
No log	24.0	72	0.9775	0.3297	0.9768	0.9883
No log	25.0	75	0.9327	0.3444	0.9319	0.9653
No log	26.0	78	0.7930	0.4061	0.7922	0.8901

genki10/BERT_AugV8_k3_task1_organization_sp040_lw010_fold1

BERT_AugV8_k3_task1_organization_sp040_lw010_fold1