metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - fashion_mnist_quality_drift
metrics:
  - accuracy
  - f1
model-index:
  - name: resnet-50-fashion-mnist-quality-drift
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: fashion_mnist_quality_drift
          type: fashion_mnist_quality_drift
          config: default
          split: training
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.73
          - name: F1
            type: f1
            value: 0.7289360255705818

resnet-50-fashion-mnist-quality-drift

This model is a fine-tuned version of microsoft/resnet-50 on the fashion_mnist_quality_drift dataset. It achieves the following results on the evaluation set:

Loss: 0.7473
Accuracy: 0.73
F1: 0.7289

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.5138	1.0	750	0.9237	0.684	0.6826
0.9377	2.0	1500	0.7861	0.722	0.7253
0.8276	3.0	2250	0.7473	0.73	0.7289

Framework versions

Transformers 4.21.0
Pytorch 1.12.0+cu113
Datasets 2.4.0
Tokenizers 0.12.1