resnet50 / README.md
holylovenia's picture
update model card README.md
e7eb40e
metadata
license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: resnet50
    results: []

resnet50

This model is a fine-tuned version of microsoft/resnet-50 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 8.2042
  • Accuracy: 0.0

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: 0.0001
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 10
  • total_train_batch_size: 320
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
6.8491 1.0 1 8.1612 0.0
6.7309 2.0 2 7.3393 0.0
6.8199 3.0 3 7.9807 0.0
6.8118 4.0 4 8.6801 0.0
6.7573 5.0 5 8.2042 0.0

Framework versions

  • Transformers 4.23.1
  • Pytorch 1.12.1
  • Datasets 2.6.0
  • Tokenizers 0.13.1