Edit model card

convnext-tiny-finetuned-beans

This model is a fine-tuned version of facebook/convnext-tiny-224 on the beans dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1255
  • Accuracy: 0.9609

pic

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: 32
  • eval_batch_size: 32
  • seed: 7171
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 37 0.6175 0.8828
No log 2.0 74 0.2307 0.9609
0.5237 3.0 111 0.1406 0.9531
0.5237 4.0 148 0.1165 0.9688
0.5237 5.0 185 0.1255 0.9609

Framework versions

  • Transformers 4.18.0
  • Pytorch 1.10.0+cu111
  • Datasets 2.1.0
  • Tokenizers 0.12.1
Downloads last month
41
Hosted inference API
Drag image file here or click to browse from your device
This model can be loaded on the Inference API on-demand.

Dataset used to train mrm8488/convnext-tiny-finetuned-beans

Evaluation results