README.md

metadata

library_name: transformers
license: apache-2.0
base_model: facebook/convnext-tiny-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: convnext-tiny-224-finetuned-barkley
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Precision
            type: precision
            value: 0.9936145510835913
          - name: Recall
            type: recall
            value: 0.993421052631579
          - name: F1
            type: f1
            value: 0.993419541966282
          - name: Accuracy
            type: accuracy
            value: 0.9939393939393939

convnext-tiny-224-finetuned-barkley

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: 0.0794
• Precision: 0.9936
• Recall: 0.9934
• F1: 0.9934
• Accuracy: 0.9939
• Top1 Accuracy: 0.9934
• Error Rate: 0.0061

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: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy	Top1 Accuracy	Error Rate
1.576	1.0	38	1.5660	0.3007	0.3684	0.2952	0.3479	0.3684	0.6521
1.5469	2.0	76	1.5353	0.3141	0.4079	0.3215	0.3854	0.4079	0.6146
1.5081	3.0	114	1.4782	0.5684	0.4671	0.3961	0.4436	0.4671	0.5564
1.4278	4.0	152	1.3718	0.7088	0.6053	0.5840	0.5866	0.6053	0.4134
1.2938	5.0	190	1.1909	0.8582	0.8355	0.8378	0.8290	0.8355	0.1710
1.0696	6.0	228	0.9353	0.9243	0.9211	0.9215	0.9205	0.9211	0.0795
0.789	7.0	266	0.6347	0.9680	0.9671	0.9673	0.9691	0.9671	0.0309
0.506	8.0	304	0.3910	0.9750	0.9737	0.9739	0.9752	0.9737	0.0248
0.2876	9.0	342	0.2126	0.9808	0.9803	0.9802	0.9814	0.9803	0.0186
0.1722	10.0	380	0.1409	0.9809	0.9803	0.9799	0.9818	0.9803	0.0182
0.1082	11.0	418	0.0794	0.9936	0.9934	0.9934	0.9939	0.9934	0.0061
0.0715	12.0	456	0.0577	0.9936	0.9934	0.9934	0.9939	0.9934	0.0061
0.0492	13.0	494	0.0440	0.9872	0.9868	0.9867	0.9879	0.9868	0.0121

Framework versions

• Transformers 4.45.2
• Pytorch 2.3.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.1