MoE-leaf-disease-convnextv2-base-1k-224

This model is a fine-tuned version of on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3758
  • Accuracy: 0.8762

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: 2000
  • eval_batch_size: 2000
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8000
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 0.8 2 0.4078 0.8724
No log 2.0 5 0.3771 0.8776
No log 2.8 7 0.3776 0.8762
0.3197 4.0 10 0.3773 0.8762
0.3197 4.8 12 0.3768 0.8762
0.3197 6.0 15 0.3762 0.8762
0.3197 6.8 17 0.3760 0.8762
0.2995 8.0 20 0.3759 0.8762
0.2995 8.8 22 0.3759 0.8762
0.2995 10.0 25 0.3758 0.8762
0.2995 10.8 27 0.3758 0.8762
0.2996 12.0 30 0.3758 0.8762
0.2996 12.8 32 0.3758 0.8762
0.2996 14.0 35 0.3758 0.8762
0.2996 14.8 37 0.3758 0.8762
0.3024 16.0 40 0.3758 0.8762

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.2.1
  • Datasets 2.18.0
  • Tokenizers 0.15.1
Downloads last month
28
Safetensors
Model size
505M params
Tensor type
F32
·
Inference Examples
Inference API (serverless) does not yet support model repos that contain custom code.