Edit model card

resnet-50-shortSleeveCleanedData

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

  • Loss: 0.1103
  • Accuracy: 0.9781

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: 42
  • gradient_accumulation_steps: 7
  • total_train_batch_size: 56
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.01
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.973 1.0 147 0.9371 0.7268
0.6565 2.0 294 0.5520 0.8710
0.4609 3.0 441 0.2983 0.9279
0.3937 4.0 588 0.2051 0.9486
0.3723 5.0 735 0.1521 0.9727
0.3926 6.0 882 0.1490 0.9672
0.3326 7.0 1029 0.1367 0.9650
0.3166 8.0 1176 0.1109 0.9738
0.3492 9.0 1323 0.1108 0.9760
0.3228 10.0 1470 0.1103 0.9781

Framework versions

  • Transformers 4.28.1
  • Pytorch 2.0.0+cu118
  • Datasets 2.12.0
  • Tokenizers 0.13.3
Downloads last month
3

Evaluation results