learning_rate: 5e-05
train_batch_size: 32
eval_batch_size: 1
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
lr_scheduler_warmup_steps: 300
num_epochs: 1
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Map	Map 50	Map 75	Map Small	Map Medium	Map Large	Mar 1	Mar 10	Mar 100	Mar Small	Mar Medium	Mar Large	Map Barcode	Mar 100 Barcode
No log	1.0	409	2.5535	0.2266	0.3057	0.2461	0.0009	0.1704	0.2785	0.1718	0.641	0.8307	0.0872	0.8136	0.8521	0.2266	0.8307

benjamintli/dfine-small_barcode-detection

dfine-small_barcode-detection