debajyotidasgupta's picture
Model save
9873833 verified
metadata
license: apache-2.0
base_model: facebook/convnextv2-base-22k-384
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - f1
model-index:
  - name: convnextv2-base-22k-384
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: F1
            type: f1
            value: 0.9913113141099743

convnextv2-base-22k-384

This model is a fine-tuned version of facebook/convnextv2-base-22k-384 on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0069
  • F1: 0.9913

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: 4
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss F1
0.1521 1.0 202 0.0982 0.8278
0.0664 2.0 404 0.0626 0.9079
0.1053 3.0 606 0.0356 0.9537
0.0432 4.0 808 0.0302 0.9703
0.0552 5.0 1010 0.0114 0.9827
0.0352 6.0 1212 0.0131 0.9824
0.0221 7.0 1414 0.0063 0.9943
0.0018 8.0 1616 0.0169 0.9824
0.0283 9.0 1818 0.0028 0.9971
0.0429 10.0 2020 0.0069 0.9913

Framework versions

  • Transformers 4.37.2
  • Pytorch 1.12.1+cu102
  • Datasets 2.16.1
  • Tokenizers 0.15.1