metadata

license: apache-2.0
base_model: facebook/data2vec-vision-base-ft1k
tags:
  - generated_from_trainer
model-index:
  - name: imagenet1k
    results: []
datasets:
  - mrm8488/ImageNet1K-val
  - mrm8488/ImageNet1K-train
  - imagenet-1k
language:
  - en
metrics:
  - accuracy
pipeline_tag: image-classification

imagenet1k

This model is a fine-tuned version of facebook/data2vec-vision-base-ft1k on Imagenet1k. It achieves the following results on the evaluation set:

eval_loss: 0.7310
eval_accuracy: 0.8355
eval_runtime: 921.304
eval_samples_per_second: 54.271
eval_steps_per_second: 1.697

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: 32
eval_batch_size: 32
seed: 1
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 7

Framework versions

Transformers 4.40.0
Pytorch 2.2.1+cu121
Datasets 2.19.0
Tokenizers 0.19.1