ryan_model314_3 / README.md
rshrott's picture
Model save
6eed9bf verified
|
raw
history blame
2.29 kB
metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
model-index:
  - name: ryan_model314_3
    results: []

ryan_model314_3

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2783
  • Na Accuracy: 0.9389
  • Ordinal Mae: 0.8154

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: 4
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Na Accuracy Ordinal Mae
0.3676 0.05 100 0.3423 0.9274 1.1293
0.3329 0.09 200 0.3136 0.9314 1.0706
0.3134 0.14 300 0.3302 0.9166 1.1220
0.314 0.19 400 0.2992 0.9256 0.8202
0.2965 0.23 500 0.3198 0.9249 1.2210
0.3068 0.28 600 0.2673 0.9372 1.1036
0.2824 0.32 700 0.2922 0.9372 1.4977
0.2914 0.37 800 0.2798 0.9384 0.7789
0.2968 0.42 900 0.2710 0.9369 0.9694
0.2433 0.46 1000 0.2652 0.9372 1.0212
0.2438 0.51 1100 0.2783 0.9389 0.8154

Framework versions

  • Transformers 4.39.1
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2