metadata

library_name: transformers
license: apache-2.0
base_model: facebook/convnext-tiny-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: convnext-tiny-224-finetuned-papsmear
    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: 0.8529411764705882

convnext-tiny-224-finetuned-papsmear

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: 0.4485
Accuracy: 0.8529

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.4789	0.9935	38	1.4474	0.3235
1.2481	1.9869	76	1.0898	0.6397
0.9694	2.9804	114	0.9261	0.6471
0.8414	4.0	153	0.8016	0.7059
0.7675	4.9935	191	0.7258	0.7426
0.7131	5.9869	229	0.7147	0.7353
0.5973	6.9804	267	0.7040	0.7353
0.5543	8.0	306	0.6064	0.7941
0.4903	8.9935	344	0.5418	0.8382
0.3942	9.9869	382	0.5043	0.8456
0.3721	10.9804	420	0.4922	0.8456
0.4036	12.0	459	0.4944	0.8309
0.3444	12.9935	497	0.4760	0.8529
0.3385	13.9869	535	0.4597	0.8603
0.3161	14.9020	570	0.4485	0.8529

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.0
Tokenizers 0.19.1