pkr7098's picture
End of training
1a98e5d verified
metadata
base_model: google/vit-base-patch16-224-in21k
library_name: peft
license: apache-2.0
metrics:
  - accuracy
tags:
  - image-classification
  - vision
  - generated_from_trainer
model-index:
  - name: only-lora-beans-vit-base-patch16-224-in21k
    results: []

only-lora-beans-vit-base-patch16-224-in21k

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

  • Loss: 0.5106
  • Accuracy: 0.7970

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: 8
  • eval_batch_size: 8
  • seed: 1337
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • num_epochs: 10.0

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.094 1.0 130 1.0091 0.5188
1.0 2.0 260 0.8809 0.6090
0.8928 3.0 390 0.8694 0.6391
0.7179 4.0 520 0.6974 0.7143
0.6783 5.0 650 0.6698 0.7519
0.7052 6.0 780 0.6212 0.7519
0.608 7.0 910 0.7637 0.7068
0.6457 8.0 1040 0.5296 0.8195
0.5747 9.0 1170 0.5106 0.7970
0.5294 10.0 1300 0.7640 0.6917

Framework versions

  • PEFT 0.12.1.dev0
  • Transformers 4.44.0
  • Pytorch 2.4.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1