metadata

license: apache-2.0
base_model: moreover18/vit-base-patch16-224-in21k-YB
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: vit-part1-friends
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9381107491856677

vit-part1-friends

This model is a fine-tuned version of moreover18/vit-base-patch16-224-in21k-YB on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.2036
Accuracy: 0.9381

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: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1627	1.3	50	0.2258	0.9202
0.1183	2.6	100	0.2148	0.9235
0.1223	3.9	150	0.2055	0.9267
0.0992	5.19	200	0.1976	0.9332
0.0824	6.49	250	0.2036	0.9381

Framework versions

Transformers 4.37.1
Pytorch 1.12.1+cu116
Datasets 2.4.0
Tokenizers 0.15.1