metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: beit-large-patch16-224-finetuned-eurosat-50
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: Augmented-Final
split: train
args: Augmented-Final
metrics:
- name: Accuracy
type: accuracy
value: 0.9856115107913669
beit-large-patch16-224-finetuned-eurosat-50
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: 0.0568
- Accuracy: 0.9856
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-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.9
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.7148 | 1.0 | 122 | 1.6402 | 0.3916 |
| 1.1543 | 2.0 | 244 | 1.0718 | 0.6208 |
| 0.8948 | 3.0 | 366 | 0.7228 | 0.7564 |
| 0.6348 | 4.0 | 488 | 0.5327 | 0.8160 |
| 0.647 | 5.0 | 610 | 0.4081 | 0.8551 |
| 0.3244 | 6.0 | 732 | 0.2965 | 0.9096 |
| 0.305 | 7.0 | 854 | 0.2515 | 0.9342 |
| 0.3522 | 8.0 | 976 | 0.1667 | 0.9568 |
| 0.1782 | 9.0 | 1098 | 0.1494 | 0.9568 |
| 0.1849 | 10.0 | 1220 | 0.0972 | 0.9712 |
| 0.1814 | 11.0 | 1342 | 0.0559 | 0.9846 |
| 0.1682 | 12.0 | 1464 | 0.0568 | 0.9856 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3