metadata

license: apache-2.0
base_model: microsoft/beit-base-patch16-224-pt22k-ft22k
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: Train-Test-Augmentation-V4-beit-base
    results: []

Train-Test-Augmentation-V4-beit-base

This model is a fine-tuned version of microsoft/beit-base-patch16-224-pt22k-ft22k on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.4701
Accuracy: 0.8557

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: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6584	1.0	55	0.6744	0.7946
0.2762	2.0	110	0.5429	0.8234
0.1144	3.0	165	0.5259	0.8336
0.0487	4.0	220	0.5111	0.8404
0.0218	5.0	275	0.4701	0.8557

Framework versions

Transformers 4.39.3
Pytorch 2.1.2
Datasets 2.19.1
Tokenizers 0.15.2