metadata
license: apache-2.0
base_model: microsoft/beit-base-patch16-224-pt22k-ft22k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_40x_beit_base_f5
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: 0.9512195121951219
hushem_40x_beit_base_f5
This model is a fine-tuned version of microsoft/beit-base-patch16-224-pt22k-ft22k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2681
- Accuracy: 0.9512
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0802 | 1.0 | 110 | 0.6945 | 0.8049 |
| 0.028 | 2.0 | 220 | 0.5751 | 0.9024 |
| 0.002 | 3.0 | 330 | 0.3641 | 0.9268 |
| 0.0009 | 4.0 | 440 | 0.5616 | 0.8780 |
| 0.0004 | 5.0 | 550 | 0.2822 | 0.9024 |
| 0.0003 | 6.0 | 660 | 0.7387 | 0.8537 |
| 0.0018 | 7.0 | 770 | 0.1999 | 0.9512 |
| 0.0001 | 8.0 | 880 | 0.3046 | 0.9512 |
| 0.0011 | 9.0 | 990 | 0.2897 | 0.9268 |
| 0.0002 | 10.0 | 1100 | 0.2681 | 0.9512 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1