wendys-llc/rtdetr-v2-r50-chkbx

rtdetr-v2-r50-cppe5-finetune-2

This model is a fine-tuned version of PekingU/rtdetr_v2_r50vd on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 6.5817
• eval_map: 0.6377
• eval_map_50: 0.9261
• eval_map_75: 0.7461
• eval_map_small: 0.5601
• eval_map_medium: 0.781
• eval_map_large: 0.7309
• eval_mar_1: 0.235
• eval_mar_10: 0.5687
• eval_mar_100: 0.7408
• eval_mar_small: 0.6721
• eval_mar_medium: 0.855
• eval_mar_large: 0.8479
• eval_map_checked-unchecked: -1.0
• eval_mar_100_checked-unchecked: -1.0
• eval_map_checked: 0.6635
• eval_mar_100_checked: 0.7876
• eval_map_unchecked: 0.6118
• eval_mar_100_unchecked: 0.694
• eval_runtime: 7.4046
• eval_samples_per_second: 17.151
• eval_steps_per_second: 2.161
• epoch: 11.0
• step: 990

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• 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: 40

Framework versions

• Transformers 4.56.0
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.0