metadata
license: apache-2.0
base_model: microsoft/beit-large-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: Karma_3Class_RMSprop_1e5_20Epoch_Beit-large-224_fold5
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: 0.8569544486151973
Karma_3Class_RMSprop_1e5_20Epoch_Beit-large-224_fold5
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: 1.6698
- Accuracy: 0.8570
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: 1e-05
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3948 | 1.0 | 2468 | 0.3604 | 0.8516 |
| 0.2875 | 2.0 | 4936 | 0.3421 | 0.8614 |
| 0.1919 | 3.0 | 7404 | 0.4622 | 0.8576 |
| 0.1141 | 4.0 | 9872 | 0.7162 | 0.8544 |
| 0.0511 | 5.0 | 12340 | 0.9479 | 0.8535 |
| 0.0188 | 6.0 | 14808 | 1.2229 | 0.8574 |
| 0.0493 | 7.0 | 17276 | 1.4475 | 0.8511 |
| 0.0016 | 8.0 | 19744 | 1.5383 | 0.8569 |
| 0.0398 | 9.0 | 22212 | 1.6405 | 0.8576 |
| 0.0001 | 10.0 | 24680 | 1.6698 | 0.8570 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.2