learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	1.0	100	0.1152	0.96	0.9724	0.9930	0.9527
No log	2.0	200	0.0961	0.975	0.9829	0.9931	0.9730
No log	3.0	300	0.1059	0.97	0.9796	0.9863	0.9730
No log	4.0	400	0.1345	0.965	0.9763	0.9796	0.9730
0.1250	5.0	500	0.1514	0.96	0.9728	0.9795	0.9662
0.1250	6.0	600	0.1505	0.96	0.9728	0.9795	0.9662
0.1250	7.0	700	0.1775	0.955	0.9695	0.9728	0.9662
0.1250	8.0	800	0.2043	0.955	0.9691	0.9860	0.9527
0.1250	9.0	900	0.1685	0.96	0.9728	0.9795	0.9662
0.0156	10.0	1000	0.1714	0.96	0.9728	0.9795	0.9662

thedavidhackett/distilbert-base-uncased-police-nonprofit-classifier

results