metadata

license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
datasets:
  - food101
metrics:
  - accuracy
base_model: google/vit-base-patch16-224-in21k
model-index:
  - name: ft-vit-base-patch16-224-in21k-on-food101-lora
    results: []

ft-vit-base-patch16-224-in21k-on-food101-lora

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the food101 dataset. It achieves the following results on the evaluation set:

Loss: 0.2242
Accuracy: 0.932

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: 0.005
train_batch_size: 64
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 256
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.2628	0.96	17	0.3024	0.912
0.2236	1.92	34	0.2242	0.932

Framework versions

PEFT 0.7.1
Transformers 4.36.2
Pytorch 2.0.0
Datasets 2.1.0
Tokenizers 0.15.0