Hugging Face's logo

intelli-zen
/
detr_cppe5_object_detection

Object Detection
Transformers
PyTorch
detr
Generated from Trainer
Model card Files
xet
Community
1
detr_cppe5_object_detection / README.md
qgyd2021's picture
qgyd2021
End of training
1d91bfa
preview code
|
raw
history blame
1.88 kB
metadata
license: apache-2.0
base_model: qgyd2021/detr_cppe5_object_detection
tags:
  - generated_from_trainer
datasets:
  - cppe5
model-index:
  - name: detr_cppe5_object_detection
    results: []

detr_cppe5_object_detection

This model is a fine-tuned version of qgyd2021/detr_cppe5_object_detection on the cppe5 dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0746

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: 1e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • total_train_batch_size: 16
  • total_eval_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 30

Training results

Training Loss Epoch Step Validation Loss
0.8928 3.17 200 1.0594
0.8862 6.35 400 1.1216
0.8231 9.52 600 1.1138
0.786 12.7 800 1.0857
0.8132 15.87 1000 1.0550
0.8111 19.05 1200 1.0563
0.7927 22.22 1400 1.1003
0.7805 25.4 1600 1.0950
0.7332 28.57 1800 1.0746

Framework versions

  • Transformers 4.33.0
  • Pytorch 2.0.0
  • Datasets 2.1.0
  • Tokenizers 0.13.3