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_3Class_Adamax_1e4_20Epoch_Beit-large-224_fold3
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: 0.8452742359846185
Karma_3Class_3Class_Adamax_1e4_20Epoch_Beit-large-224_fold3
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: 1.6691
- Accuracy: 0.8453
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4597 | 1.0 | 2467 | 0.3981 | 0.8379 |
| 0.3536 | 2.0 | 4934 | 0.3996 | 0.8368 |
| 0.1795 | 3.0 | 7401 | 0.4872 | 0.8467 |
| 0.1625 | 4.0 | 9868 | 0.6122 | 0.8475 |
| 0.1107 | 5.0 | 12335 | 0.9789 | 0.8460 |
| 0.0003 | 6.0 | 14802 | 1.0818 | 0.8494 |
| 0.0149 | 7.0 | 17269 | 1.4834 | 0.8465 |
| 0.0 | 8.0 | 19736 | 1.5090 | 0.8474 |
| 0.0 | 9.0 | 22203 | 1.5763 | 0.8462 |
| 0.001 | 10.0 | 24670 | 1.6691 | 0.8453 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.2