metadata

library_name: transformers
license: apache-2.0
base_model: PekingU/rtdetr_r50vd_coco_o365
tags:
  - generated_from_trainer
model-index:
  - name: cppe-5
    results: []

cppe-5

This model is a fine-tuned version of PekingU/rtdetr_r50vd_coco_o365 on an unknown dataset. It achieves the following results on the evaluation set:

eval_loss: 125.0968
eval_model_preparation_time: 0.0034
eval_map: 0.0
eval_map_50: 0.0003
eval_map_75: 0.0
eval_map_small: 0.0
eval_map_medium: 0.0001
eval_map_large: 0.0002
eval_mar_1: 0.0013
eval_mar_10: 0.0027
eval_mar_100: 0.0076
eval_mar_small: 0.0
eval_mar_medium: 0.0146
eval_mar_large: 0.0218
eval_map_Coverall: 0.0
eval_mar_100_Coverall: 0.0072
eval_map_Face_Shield: 0.0
eval_mar_100_Face_Shield: 0.0025
eval_map_Gloves: 0.0001
eval_mar_100_Gloves: 0.0004
eval_map_Goggles: 0.0
eval_mar_100_Goggles: 0.0108
eval_map_Mask: 0.0
eval_mar_100_Mask: 0.0169
eval_runtime: 3.3548
eval_samples_per_second: 44.713
eval_steps_per_second: 5.664
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: 0.0001
train_batch_size: 2
eval_batch_size: 8
seed: 42
optimizer: Use 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: 120

Framework versions

Transformers 4.53.0.dev0
Pytorch 2.5.1
Datasets 3.2.0
Tokenizers 0.21.1