Edit model card

convnextv2-base-22k-384-finetuned-cassava-leaf-disease

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: 0.3755
  • Accuracy: 0.8785

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: 140
  • eval_batch_size: 140
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 560
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 16

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.7713 0.99 34 0.5754 0.7949
0.3953 2.0 69 0.3769 0.8650
0.3478 2.99 103 0.3717 0.8673
0.3296 4.0 138 0.3696 0.8752
0.3058 4.99 172 0.3387 0.8808
0.2791 6.0 207 0.3480 0.8804
0.2541 6.99 241 0.3483 0.8799
0.247 8.0 276 0.3590 0.8743
0.2395 8.99 310 0.3505 0.8794
0.2139 10.0 345 0.3702 0.8766
0.2116 10.99 379 0.3702 0.8766
0.204 12.0 414 0.3661 0.8762
0.183 12.99 448 0.3705 0.8776
0.1856 14.0 483 0.3861 0.8780
0.1641 14.99 517 0.3758 0.8766
0.1784 15.77 544 0.3755 0.8785

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.2.1
  • Datasets 2.18.0
  • Tokenizers 0.15.1
Downloads last month
15
Safetensors
Model size
87.7M params
Tensor type
F32
·

Finetuned from

Evaluation results