eugenecamus's picture
update model card README.md
e5e819e
|
raw
history blame
1.86 kB
metadata
tags:
  - generated_from_trainer
datasets:
  - beans
metrics:
  - accuracy
model-index:
  - name: resnet-50-base-beans-demo
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: beans
          type: beans
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9699248120300752

resnet-50-base-beans-demo

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

  • Loss: 0.1014
  • Accuracy: 0.9699

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: 0.002
  • 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: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 5.0

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.9524 1.0 130 0.2826 0.8647
0.3596 2.0 260 0.2216 0.9023
0.2419 3.0 390 0.1324 0.9474
0.3248 4.0 520 0.1124 0.9699
0.1557 5.0 650 0.1014 0.9699

Framework versions

  • Transformers 4.19.2
  • Pytorch 1.11.0+cu102
  • Datasets 2.2.1
  • Tokenizers 0.12.1