tonyassi's picture
End of training
2d36e29
|
raw
history blame
2.07 kB
metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: fashion-clothing-decade
    results: []

fashion-clothing-decade

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8451
  • Accuracy: 0.7485

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: 5e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.9496 0.98 31 1.1401 0.6766
0.7981 2.0 63 1.0490 0.6926
0.6665 2.98 94 1.0096 0.6766
0.5422 4.0 126 0.9923 0.6886
0.4987 4.98 157 0.9207 0.7285
0.447 6.0 189 0.9480 0.6866
0.3892 6.98 220 0.9274 0.7026
0.3632 8.0 252 0.8786 0.7445
0.3886 8.98 283 0.8331 0.7645
0.3778 9.84 310 0.8451 0.7485

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.6
  • Tokenizers 0.14.1