README.md

metadata

license: other
base_model: google/mobilenet_v2_1.0_224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: mobilenet_v2_1.0_224-finetuned-32bs-0.01lr
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: test
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9206560874783305

mobilenet_v2_1.0_224-finetuned-32bs-0.01lr

This model is a fine-tuned version of google/mobilenet_v2_1.0_224 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.2230
• Accuracy: 0.9207

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: 0.01
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 512
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.99	53	0.3603	0.8745
No log	1.99	107	0.2323	0.9183
No log	2.96	159	0.2230	0.9207

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3