nielsr/lwdetr-tiny-tray-cart-rf100-lr-20260303-222437

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

lwdetr-tiny-tray-cart-rf100-lr-20260303-222437

This model is a fine-tuned version of AnnaZhang/lwdetr_tiny_60e_coco on an unknown dataset. It achieves the following results on the evaluation set:

• —Loss: 3.9548
• —Map: 0.0
• —Map 50: 0.0001
• —Map 75: 0.0
• —Map Small: 0.0
• —Map Medium: 0.0001
• —Map Large: 0.0
• —Mar 1: 0.0
• —Mar 10: 0.0
• —Mar 100: 0.0027
• —Mar Small: 0.0
• —Mar Medium: 0.0028
• —Mar Large: 0.003
• —Map Tray: 0.0001
• —Mar 100 Tray: 0.0055
• —Map Cart: 0.0
• —Mar 100 Cart: 0.0

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: 0.0008
• —trainbatchsize: 4
• —evalbatchsize: 4
• —seed: 42
• —gradientaccumulationsteps: 4
• —totaltrainbatch_size: 16
• —optimizer: Use adamwtorchfused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: constantwithwarmup
• —lrschedulerwarmup_steps: 4
• —num_epochs: 60

Training results

Framework versions

• —Transformers 5.2.0
• —Pytorch 2.10.0+cu128
• —Datasets 4.6.1
• —Tokenizers 0.22.2