CoolFace
Modelpublic

kariver/detr-resnet-50_adamw_torch_fused_adam_beta1-0_8_finetuned_food-roboflow

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes7downloads
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. -->

detr-resnet-50adamwtorchfusedadambeta1-08finetunedfood-roboflow

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

  • —Loss: 2.8078

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
  • —trainbatchsize: 16
  • —evalbatchsize: 16
  • —seed: 42
  • —optimizer: Adam with betas=(0.8,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 20
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
6.68971.52506.2985
5.57043.031005.1916
4.36454.551504.0882
3.41156.062003.3534
3.01097.582503.0666
2.88369.093003.0176
2.756410.613502.9294
2.700712.124002.9228
2.703213.644502.8650
2.624815.155002.8833
2.599516.675502.8085
2.561618.186002.7843
2.558219.76502.8078

Framework versions

  • —Transformers 4.35.0
  • —Pytorch 2.1.0+cu118
  • —Datasets 2.14.6
  • —Tokenizers 0.14.1