metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: weather-base
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: dataset
split: train
args: dataset
metrics:
- name: Accuracy
type: accuracy
value: 0.9358600583090378
weather-base
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: 0.2184
- Accuracy: 0.9359
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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: 0.1
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3368 | 1.0 | 171 | 0.2780 | 0.9009 |
| 0.2129 | 2.0 | 342 | 0.2333 | 0.9300 |
| 0.1827 | 3.0 | 513 | 0.2440 | 0.9213 |
| 0.1475 | 4.0 | 684 | 0.2306 | 0.9315 |
| 0.1284 | 5.0 | 855 | 0.2192 | 0.9359 |
| 0.0526 | 6.0 | 1026 | 0.2184 | 0.9359 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2