metadata

license: apache-2.0
base_model: facebook/convnextv2-base-1k-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: convnextv2-base-1k-224-finetuned-cassava-leaf-disease
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8841121495327103

convnextv2-base-1k-224-finetuned-cassava-leaf-disease

This model is a fine-tuned version of facebook/convnextv2-base-1k-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.3624
Accuracy: 0.8841

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: 360
eval_batch_size: 360
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 1440
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
7.5825	0.96	13	2.5252	0.4874
2.4869	2.0	27	1.0172	0.6388
0.7793	2.96	40	0.6048	0.7925
0.5807	4.0	54	0.4873	0.8327
0.5079	4.96	67	0.4330	0.8514
0.4363	6.0	81	0.4140	0.8668
0.4118	6.96	94	0.3962	0.8743
0.3918	8.0	108	0.3924	0.8748
0.3669	8.96	121	0.3816	0.8822
0.3687	10.0	135	0.3784	0.8776
0.3645	10.96	148	0.3684	0.8846
0.349	12.0	162	0.3706	0.8804
0.3341	12.96	175	0.3678	0.8813
0.3304	14.0	189	0.3618	0.8794
0.3318	14.96	202	0.3677	0.8808
0.3178	16.0	216	0.3626	0.8818
0.3209	16.96	229	0.3606	0.8822
0.3129	18.0	243	0.3615	0.8836
0.3013	18.96	256	0.3627	0.8841
0.3046	19.26	260	0.3624	0.8841

Framework versions

Transformers 4.37.2
Pytorch 2.2.1
Datasets 2.18.0
Tokenizers 0.15.1