CoolFace
Modelpublic

joshlyman/rtdetrv2-floorplancad-doors

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face
0likes33downloads
Model Card

<!-- 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. -->

rtdetrv2-floorplancad-doors

This model is a fine-tuned version of PekingU/rtdetr_v2_r18vd on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 4.2426

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: 4
  • —evalbatchsize: 4
  • —seed: 42
  • —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • —lrschedulertype: cosine
  • —num_epochs: 6.0
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
9.76880.34442506.3036
7.76110.68875005.2379
6.61111.03317504.6810
6.54561.377410004.5544
6.60301.721812504.5780
6.02462.066115004.4291
6.72102.410517504.4532
5.89832.754820004.4589
5.58333.099222504.3699
5.58803.443525004.3238
5.68373.787927504.3332
5.47634.132230004.2348
5.61794.476632504.2787
5.96734.820935004.2613
6.15635.165337504.2550
5.89835.509640004.2712
5.18295.854042504.2598
5.87216.043564.2426

Framework versions

  • —Transformers 5.6.2
  • —Pytorch 2.11.0+cu130
  • —Datasets 4.8.4
  • —Tokenizers 0.22.2