metadata
license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: Karma_3Class_RMSprop_1-e5_10Epoch_Beit-base-patch16_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: 0.8413276664642785
Karma_3Class_RMSprop_1-e5_10Epoch_Beit-base-patch16_fold3
This model is a fine-tuned version of microsoft/beit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.4124
- Accuracy: 0.8413
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 |
|---|---|---|---|---|
| 0.4 | 1.0 | 2467 | 0.4178 | 0.8301 |
| 0.3541 | 2.0 | 4934 | 0.3989 | 0.8425 |
| 0.2286 | 3.0 | 7401 | 0.4379 | 0.8463 |
| 0.2173 | 4.0 | 9868 | 0.4932 | 0.8420 |
| 0.0599 | 5.0 | 12335 | 0.7103 | 0.8417 |
| 0.0547 | 6.0 | 14802 | 0.9909 | 0.8426 |
| 0.0268 | 7.0 | 17269 | 1.2232 | 0.8431 |
| 0.0075 | 8.0 | 19736 | 1.2967 | 0.8438 |
| 0.02 | 9.0 | 22203 | 1.3707 | 0.8407 |
| 0.0237 | 10.0 | 24670 | 1.4124 | 0.8413 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.14.1