tumul31/rtdetr-v2-r50-cardamage-40ep

<!-- 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. -->

rtdetr-v2-r50-cardamage-40ep

This model is a fine-tuned version of PekingU/rtdetr_r50vd on an unknown dataset. It achieves the following results on the evaluation set:

• —eval_loss: 12.7731
• —evalmodelpreparation_time: 0.0097
• —eval_map: 0.2093
• —evalmap50: 0.404
• —evalmap75: 0.1925
• —evalmapsmall: 0.0168
• —evalmapmedium: 0.0853
• —evalmaplarge: 0.2916
• —evalmar1: 0.3526
• —evalmar10: 0.4898
• —evalmar100: 0.5314
• —evalmarsmall: 0.0167
• —evalmarmedium: 0.2585
• —evalmarlarge: 0.6342
• —evalmapcar-parts: -1.0
• —evalmar100_car-parts: -1.0
• —evalmapBonet: 0.1129
• —evalmar100_Bonet: 0.3364
• —evalmapBumper: 0.128
• —evalmar100_Bumper: 0.4396
• —evalmapDoor: 0.1729
• —evalmar100_Door: 0.6609
• —evalmapHeadlight: 0.1512
• —evalmar100_Headlight: 0.4947
• —evalmapMirror: 0.2436
• —evalmar100_Mirror: 0.5529
• —evalmapTailight: 0.345
• —evalmar100_Tailight: 0.575
• —evalmapWindshield: 0.3114
• —evalmar100_Windshield: 0.66
• —eval_runtime: 10.9627
• —evalsamplesper_second: 14.048
• —evalstepsper_second: 1.824
• —step: 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: 5e-05
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 300
• —num_epochs: 40
• —mixedprecisiontraining: Native AMP

Framework versions

• —Transformers 4.47.0
• —Pytorch 2.5.1+cu121
• —Datasets 3.2.0
• —Tokenizers 0.21.0