Soulaimen's picture
update model card README.md
73596f8
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: resnet-50-bottomCleanedData
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9761634506242906

resnet-50-bottomCleanedData

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: 0.0822
  • Accuracy: 0.9762

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: 50

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.3323 1.0 141 1.3319 0.5187
1.1302 2.0 283 1.1059 0.5335
0.8793 2.99 424 0.7848 0.7094
0.7652 4.0 566 0.7255 0.7219
0.7708 4.99 707 0.5280 0.8173
0.6153 6.0 849 0.4221 0.8490
0.5895 7.0 991 0.4015 0.8570
0.5617 8.0 1132 0.2998 0.9001
0.517 9.0 1274 0.2737 0.9160
0.5366 9.99 1415 0.2229 0.9240
0.4645 11.0 1557 0.2038 0.9330
0.4114 11.99 1698 0.1851 0.9376
0.4528 13.0 1840 0.1796 0.9432
0.4182 14.0 1982 0.1578 0.9523
0.432 15.0 2123 0.1660 0.9421
0.4442 16.0 2265 0.1401 0.9557
0.4059 16.99 2406 0.1332 0.9591
0.3498 18.0 2548 0.1431 0.9535
0.3869 18.99 2689 0.1237 0.9512
0.3639 20.0 2831 0.1193 0.9603
0.3819 21.0 2973 0.1234 0.9557
0.3491 22.0 3114 0.1207 0.9569
0.3259 23.0 3256 0.1234 0.9591
0.3199 23.99 3397 0.1028 0.9659
0.3398 25.0 3539 0.1010 0.9603
0.3108 25.99 3680 0.1015 0.9671
0.3417 27.0 3822 0.1080 0.9614
0.3835 28.0 3964 0.1056 0.9591
0.3336 29.0 4105 0.1011 0.9637
0.3035 30.0 4247 0.0972 0.9614
0.2559 30.99 4388 0.0941 0.9659
0.378 32.0 4530 0.0963 0.9603
0.2932 32.99 4671 0.0916 0.9716
0.3072 34.0 4813 0.0917 0.9671
0.3081 35.0 4955 0.1025 0.9625
0.2724 36.0 5096 0.0874 0.9671
0.2621 37.0 5238 0.0847 0.9705
0.3521 37.99 5379 0.0829 0.9728
0.2883 39.0 5521 0.0860 0.9728
0.2617 39.99 5662 0.0898 0.9682
0.2893 41.0 5804 0.0877 0.9671
0.2994 42.0 5946 0.0822 0.9762
0.2483 43.0 6087 0.0834 0.9705
0.301 44.0 6229 0.0883 0.9694
0.2648 44.99 6370 0.0834 0.9705
0.2902 46.0 6512 0.0879 0.9648
0.299 46.99 6653 0.0843 0.9694
0.2726 48.0 6795 0.0920 0.9659
0.3252 49.0 6937 0.0857 0.9716
0.274 49.8 7050 0.0813 0.9762

Framework versions

  • Transformers 4.28.1
  • Pytorch 2.0.0+cu118
  • Datasets 2.12.0
  • Tokenizers 0.13.3