learning_rate: 5e-05
train_batch_size: 16
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
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: cosine_with_restarts
lr_scheduler_warmup_steps: 0.1
num_epochs: 5
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.1117	0.2389	500	0.0483	0.8936	0.9383	0.9154	0.9859
0.0453	0.4778	1000	0.0176	0.9594	0.9769	0.9681	0.9947
0.0294	0.7167	1500	0.0111	0.9749	0.9877	0.9813	0.9968
0.0157	0.9556	2000	0.0089	0.9774	0.9886	0.9830	0.9970
0.0126	1.1945	2500	0.0072	0.9835	0.9896	0.9866	0.9978
0.0098	1.4333	3000	0.0064	0.9854	0.9920	0.9886	0.9980
0.0097	1.6722	3500	0.0053	0.9877	0.9936	0.9906	0.9983
0.0088	1.9111	4000	0.0056	0.9868	0.9916	0.9892	0.9982
0.0057	2.1500	4500	0.0057	0.9882	0.9921	0.9901	0.9983
0.0049	2.3889	5000	0.0055	0.9887	0.9936	0.9911	0.9984
0.0057	2.6278	5500	0.0052	0.9898	0.9946	0.9922	0.9985
0.0050	2.8667	6000	0.0052	0.9888	0.9932	0.9910	0.9984
0.0018	3.1056	6500	0.0051	0.9910	0.9946	0.9928	0.9986
0.0025	3.3445	7000	0.0051	0.9903	0.9950	0.9927	0.9986
0.0018	3.5834	7500	0.0053	0.9912	0.9939	0.9925	0.9986
0.0020	3.8223	8000	0.0049	0.9906	0.9940	0.9923	0.9986

jefftherover/pii-layout-synth-v4

pii-layout-synth-v4