--- library_name: transformers license: apache-2.0 base_model: PekingU/rtdetr_r50vd_coco_o365 tags: - generated_from_trainer model-index: - name: rtdetr-r50-cppe5-finetune results: [] --- # rtdetr-r50-cppe5-finetune This model is a fine-tuned version of [PekingU/rtdetr_r50vd_coco_o365](https://huggingface.co/PekingU/rtdetr_r50vd_coco_o365) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 9.8586 - Map: 0.5282 - Map 50: 0.6578 - Map 75: 0.5509 - Map Small: 0.2525 - Map Medium: 0.502 - Map Large: 0.6946 - Mar 1: 0.2808 - Mar 10: 0.617 - Mar 100: 0.7372 - Mar Small: 0.423 - Mar Medium: 0.7109 - Mar Large: 0.8923 - Map Apple: 0.5218 - Mar 100 Apple: 0.7284 - Map Banana: 0.4594 - Mar 100 Banana: 0.7377 - Map Grapes: 0.3957 - Mar 100 Grapes: 0.6437 - Map Orange: 0.5229 - Mar 100 Orange: 0.6667 - Map Pineapple: 0.6214 - Mar 100 Pineapple: 0.8087 - Map Watermelon: 0.648 - Mar 100 Watermelon: 0.8381 ## 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 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: 10 ### Training results | 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 Apple | Mar 100 Apple | Map Banana | Mar 100 Banana | Map Grapes | Mar 100 Grapes | Map Orange | Mar 100 Orange | Map Pineapple | Mar 100 Pineapple | Map Watermelon | Mar 100 Watermelon | |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:---------:|:-------------:|:----------:|:--------------:|:----------:|:--------------:|:----------:|:--------------:|:-------------:|:-----------------:|:--------------:|:------------------:| | 42.2465 | 1.0 | 750 | 11.9797 | 0.3966 | 0.5058 | 0.417 | 0.1431 | 0.3331 | 0.5748 | 0.2443 | 0.5396 | 0.6893 | 0.3383 | 0.656 | 0.8619 | 0.3978 | 0.6735 | 0.3743 | 0.7125 | 0.2978 | 0.5641 | 0.4102 | 0.6402 | 0.4225 | 0.7685 | 0.4771 | 0.7773 | | 15.4425 | 2.0 | 1500 | 10.7905 | 0.4461 | 0.5553 | 0.4689 | 0.1701 | 0.3998 | 0.6131 | 0.2634 | 0.5668 | 0.7036 | 0.3638 | 0.663 | 0.8779 | 0.4239 | 0.6906 | 0.437 | 0.7281 | 0.3405 | 0.6118 | 0.4262 | 0.6468 | 0.5435 | 0.7804 | 0.5053 | 0.7636 | | 14.2856 | 3.0 | 2250 | 9.9898 | 0.4937 | 0.6229 | 0.5166 | 0.2073 | 0.4512 | 0.6644 | 0.2691 | 0.5859 | 0.7224 | 0.4119 | 0.6999 | 0.8802 | 0.4883 | 0.7015 | 0.4771 | 0.7369 | 0.3631 | 0.6162 | 0.4966 | 0.654 | 0.5767 | 0.7971 | 0.5607 | 0.8284 | | 13.0156 | 4.0 | 3000 | 10.1385 | 0.5064 | 0.6308 | 0.5323 | 0.2148 | 0.4725 | 0.6794 | 0.274 | 0.5986 | 0.7294 | 0.4062 | 0.7103 | 0.8853 | 0.4728 | 0.7104 | 0.4569 | 0.738 | 0.3955 | 0.6261 | 0.5067 | 0.6602 | 0.6041 | 0.8011 | 0.6022 | 0.8403 | | 12.4118 | 5.0 | 3750 | 10.0754 | 0.5084 | 0.6286 | 0.533 | 0.2254 | 0.4758 | 0.6844 | 0.2754 | 0.6012 | 0.7305 | 0.3992 | 0.7066 | 0.8904 | 0.4911 | 0.7103 | 0.488 | 0.7457 | 0.3875 | 0.6389 | 0.5065 | 0.6658 | 0.5897 | 0.7855 | 0.588 | 0.8366 | | 11.7444 | 6.0 | 4500 | 10.1131 | 0.5119 | 0.6318 | 0.5379 | 0.209 | 0.477 | 0.6834 | 0.2742 | 0.6055 | 0.7302 | 0.399 | 0.6996 | 0.8898 | 0.4975 | 0.7185 | 0.4644 | 0.7266 | 0.391 | 0.6546 | 0.5165 | 0.6646 | 0.5963 | 0.7989 | 0.6059 | 0.8182 | | 11.3657 | 7.0 | 5250 | 10.4886 | 0.4898 | 0.608 | 0.5144 | 0.2211 | 0.4666 | 0.6488 | 0.2736 | 0.5901 | 0.7258 | 0.3896 | 0.6946 | 0.8869 | 0.4952 | 0.7158 | 0.4309 | 0.7397 | 0.3444 | 0.6269 | 0.5001 | 0.6587 | 0.5822 | 0.7989 | 0.5859 | 0.8151 | | 11.0681 | 8.0 | 6000 | 9.8240 | 0.5251 | 0.652 | 0.5511 | 0.2452 | 0.4984 | 0.6922 | 0.2809 | 0.6129 | 0.7389 | 0.4201 | 0.711 | 0.8945 | 0.5171 | 0.7279 | 0.471 | 0.7451 | 0.3935 | 0.6524 | 0.5214 | 0.6668 | 0.6087 | 0.8011 | 0.6388 | 0.8403 | | 10.7525 | 9.0 | 6750 | 9.8244 | 0.5185 | 0.644 | 0.5425 | 0.2364 | 0.4832 | 0.6893 | 0.2799 | 0.6088 | 0.7399 | 0.4262 | 0.7159 | 0.8938 | 0.5137 | 0.7293 | 0.4548 | 0.753 | 0.3932 | 0.6471 | 0.5181 | 0.6659 | 0.6112 | 0.8047 | 0.6197 | 0.8395 | | 10.5616 | 10.0 | 7500 | 9.8586 | 0.5282 | 0.6578 | 0.5509 | 0.2525 | 0.502 | 0.6946 | 0.2808 | 0.617 | 0.7372 | 0.423 | 0.7109 | 0.8923 | 0.5218 | 0.7284 | 0.4594 | 0.7377 | 0.3957 | 0.6437 | 0.5229 | 0.6667 | 0.6214 | 0.8087 | 0.648 | 0.8381 | ### Framework versions - Transformers 4.53.0.dev0 - Pytorch 2.6.0+cu124 - Datasets 3.6.0 - Tokenizers 0.21.1