Alimuddin's picture
End of training
fe4c423
|
raw
history blame
2.36 kB
metadata
license: apache-2.0
base_model: facebook/convnext-large-224-22k-1k
tags:
  - generated_from_trainer
datasets:
  - amazonian_fish_classifier_data
metrics:
  - accuracy
model-index:
  - name: image_classification
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: amazonian_fish_classifier_data
          type: amazonian_fish_classifier_data
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9120521172638436

image_classification

This model is a fine-tuned version of facebook/convnext-large-224-22k-1k on the amazonian_fish_classifier_data dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3093
  • Accuracy: 0.9121

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: 0.0001
  • train_batch_size: 17
  • eval_batch_size: 17
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 145 0.8373 0.7655
No log 2.0 290 0.6874 0.8160
No log 3.0 435 0.5101 0.8502
0.7333 4.0 580 0.4626 0.8762
0.7333 5.0 725 0.4813 0.8648
0.7333 6.0 870 0.4393 0.8795
0.317 7.0 1015 0.3943 0.8925
0.317 8.0 1160 0.3961 0.8909
0.317 9.0 1305 0.3469 0.9039
0.317 10.0 1450 0.3773 0.8893

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3