metadata
license: apache-2.0
base_model: microsoft/beit-large-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: Boya3_3Class_Adamax_1e4_20Epoch_Beit-large-224_fold1
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8352520841603811
Boya3_3Class_Adamax_1e4_20Epoch_Beit-large-224_fold1
This model is a fine-tuned version of microsoft/beit-large-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.0801
- Accuracy: 0.8353
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- 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 |
---|---|---|---|---|
0.3718 | 1.0 | 632 | 0.4472 | 0.8178 |
0.3269 | 2.0 | 1264 | 0.4279 | 0.8277 |
0.2591 | 3.0 | 1896 | 0.4872 | 0.8345 |
0.0914 | 4.0 | 2528 | 0.8541 | 0.8404 |
0.0115 | 5.0 | 3160 | 1.0801 | 0.8353 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.2