Resnet152-5e-5 / README.md
vuongnhathien's picture
Model save
39e36f1 verified
metadata
license: apache-2.0
base_model: microsoft/resnet-152
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: Resnet152-5e-5
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.7614314115308151

Resnet152-5e-5

This model is a fine-tuned version of microsoft/resnet-152 on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8255
  • Accuracy: 0.7614

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: 64
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
3.2352 1.0 275 2.9196 0.1984
2.5896 2.0 550 1.9631 0.4736
1.8864 3.0 825 1.3420 0.6231
1.5969 4.0 1100 1.1232 0.6918
1.465 5.0 1375 0.9717 0.7213
1.371 6.0 1650 0.9014 0.7483
1.2795 7.0 1925 0.8566 0.7491
1.2448 8.0 2200 0.8272 0.7594
1.2234 9.0 2475 0.8145 0.7630
1.2143 10.0 2750 0.8255 0.7614

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.1.2
  • Datasets 2.18.0
  • Tokenizers 0.15.2