metadata

license: apache-2.0
base_model: facebook/convnext-tiny-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: finetuned-Leukemia-cell
    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: 0.9661654135338346

finetuned-Leukemia-cell

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

Loss: 0.1249
Accuracy: 0.9662

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: 0.0002
train_batch_size: 32
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 50
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3396	2.94	100	0.2611	0.9060
0.2488	5.88	200	0.2651	0.9173
0.1783	8.82	300	0.1906	0.9323
0.0837	11.76	400	0.1773	0.9511
0.0934	14.71	500	0.2027	0.9361
0.1283	17.65	600	0.0602	0.9737
0.06	20.59	700	0.1383	0.9624
0.024	23.53	800	0.0773	0.9737
0.0446	26.47	900	0.1669	0.9549
0.0342	29.41	1000	0.1320	0.9624
0.0458	32.35	1100	0.1128	0.9662
0.0394	35.29	1200	0.2099	0.9436
0.0593	38.24	1300	0.0890	0.9774
0.0346	41.18	1400	0.1216	0.9662
0.0535	44.12	1500	0.1303	0.9662
0.0139	47.06	1600	0.1195	0.9624
0.0476	50.0	1700	0.1249	0.9662

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0