amyeroberts's picture
amyeroberts HF staff
update model card README.md
f4104fe
|
raw
history blame
No virus
3.87 kB
metadata
license: apache-2.0
base_model: facebook/detr-resnet-50
tags:
  - object-detection
  - vision
  - generated_from_trainer
model-index:
  - name: detr-resnet-50-base-coco
    results: []

detr-resnet-50-base-coco

This model is a fine-tuned version of facebook/detr-resnet-50 on the detection-datasets/coco dataset. It achieves the following results on the evaluation set:

  • Loss: 6388.0259

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
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 1337
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 50.0

Training results

Training Loss Epoch Step Validation Loss
No log 1.0 4 6397.6270
No log 2.0 8 6396.9526
6175.4402 3.0 12 6396.9136
6175.4402 4.0 16 6396.2993
6291.4262 5.0 20 6395.5557
6291.4262 6.0 24 6394.5957
6291.4262 7.0 28 6393.7290
6228.9867 8.0 32 6393.1914
6228.9867 9.0 36 6392.2837
6087.3184 10.0 40 6391.6709
6087.3184 11.0 44 6390.7271
6087.3184 12.0 48 6389.6670
6263.3945 13.0 52 6389.4907
6263.3945 14.0 56 6388.8540
6378.8203 15.0 60 6388.6978
6378.8203 16.0 64 6388.6611
6378.8203 17.0 68 6388.5430
6319.1008 18.0 72 6388.4219
6319.1008 19.0 76 6388.5059
6258.6707 20.0 80 6388.3950
6258.6707 21.0 84 6388.3042
6258.6707 22.0 88 6388.2788
6290.5227 23.0 92 6388.2700
6290.5227 24.0 96 6388.3994
6450.2746 25.0 100 6388.4180
6450.2746 26.0 104 6388.2329
6450.2746 27.0 108 6388.3062
6321.6988 28.0 112 6388.2568
6321.6988 29.0 116 6388.1333
6468.3922 30.0 120 6388.1660
6468.3922 31.0 124 6388.1528
6468.3922 32.0 128 6388.1211
6305.5602 33.0 132 6388.0972
6305.5602 34.0 136 6388.0776
6349.5672 35.0 140 6388.0493
6349.5672 36.0 144 6388.0317
6349.5672 37.0 148 6388.0259
6244.9891 38.0 152 6388.0371
6244.9891 39.0 156 6388.0273
6383.7191 40.0 160 6388.1465
6383.7191 41.0 164 6388.2505
6383.7191 42.0 168 6388.1260
6260.3203 43.0 172 6388.0518
6260.3203 44.0 176 6388.0322
6254.6055 45.0 180 6388.0625
6254.6055 46.0 184 6388.0688
6254.6055 47.0 188 6388.0601
6351.991 48.0 192 6388.0825
6351.991 49.0 196 6388.0938
6209.7984 50.0 200 6388.0923

Framework versions

  • Transformers 4.32.0.dev0
  • Pytorch 2.0.0+cu117
  • Datasets 2.13.1
  • Tokenizers 0.13.3