learning_rate: 2e-05
train_batch_size: 32
eval_batch_size: 64
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 500
num_epochs: 5
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.0655	0.2320	1000	0.0643	0.9826	0.9876	0.9747	0.9811
0.0395	0.4640	2000	0.0356	0.9890	0.9916	0.9845	0.9881
0.0347	0.6961	3000	0.0350	0.9893	0.9949	0.9819	0.9883
0.0248	0.9281	4000	0.0298	0.9913	0.9976	0.9836	0.9906
0.0090	1.1601	5000	0.0330	0.9919	0.9896	0.9929	0.9912
0.0149	1.3921	6000	0.0210	0.9945	0.9949	0.9932	0.9940
0.0181	1.6241	7000	0.0230	0.9935	0.9937	0.9923	0.9930
0.0164	1.8561	8000	0.0207	0.9952	0.9935	0.9961	0.9948
0.0049	2.0882	9000	0.0177	0.9961	0.9947	0.9970	0.9958
0.0103	2.3202	10000	0.0175	0.9959	0.9958	0.9952	0.9955
0.0107	2.5522	11000	0.0222	0.9946	0.9952	0.9932	0.9942
0.0065	2.7842	12000	0.0188	0.9957	0.9947	0.9961	0.9954
0.0020	3.0162	13000	0.0165	0.9964	0.9953	0.9970	0.9961
0.0057	3.2483	14000	0.0177	0.9961	0.9947	0.9970	0.9958
0.0059	3.4803	15000	0.0195	0.9961	0.9952	0.9964	0.9958
0.0032	3.7123	16000	0.0195	0.9956	0.9949	0.9955	0.9952
0.0023	3.9443	17000	0.0188	0.9961	0.9958	0.9958	0.9958
0.0019	4.1763	18000	0.0195	0.9959	0.9952	0.9958	0.9955
0.0009	4.4084	19000	0.0202	0.9963	0.9958	0.9961	0.9960
0.0014	4.6404	20000	0.0213	0.9963	0.9958	0.9961	0.9960
0.0026	4.8724	21000	0.0213	0.9963	0.9958	0.9961	0.9960
0.0023	5.0	21550	0.0213	0.9963	0.9958	0.9961	0.9960

av-codes/prompt-injection-detector-v3-mixed

prompt-injection-detector-v3-mixed