metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: plant-seedlings-model
    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: 0.954140127388535

plant-seedlings-model

This model is a fine-tuned version of microsoft/beit-base-patch16-224-pt22k-ft22k on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.2858
Accuracy: 0.9541

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: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.2496	1.27	500	1.2172	0.5637
0.7542	2.54	1000	0.8994	0.6898
0.6158	3.82	1500	0.6794	0.7720
0.4306	5.09	2000	0.4715	0.8331
0.3066	6.36	2500	0.4127	0.8567
0.2851	7.63	3000	0.3460	0.8803
0.3096	8.91	3500	0.2714	0.9019
0.1086	10.18	4000	0.2760	0.9268
0.1209	11.45	4500	0.2881	0.9229
0.1036	12.72	5000	0.2566	0.9357
0.0716	13.99	5500	0.2792	0.9382
0.0168	15.27	6000	0.2604	0.9376
0.0004	16.54	6500	0.3676	0.9363
0.0017	17.81	7000	0.2969	0.9529
0.0005	19.08	7500	0.2858	0.9541

Framework versions

Transformers 4.28.1
Pytorch 2.0.0+cu118
Datasets 2.11.0
Tokenizers 0.13.3