BilalMuftuoglu's picture
End of training
8370ef5 verified
---
license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: beit-base-patch16-224-hasta-55-fold1
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.6111111111111112
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# beit-base-patch16-224-hasta-55-fold1
This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9506
- Accuracy: 0.6111
## 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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 100
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-------:|:----:|:---------------:|:--------:|
| No log | 0.5714 | 1 | 1.1111 | 0.4722 |
| No log | 1.7143 | 3 | 1.2067 | 0.2222 |
| No log | 2.8571 | 5 | 1.1273 | 0.3889 |
| No log | 4.0 | 7 | 1.0384 | 0.4444 |
| No log | 4.5714 | 8 | 1.1017 | 0.4167 |
| 1.0728 | 5.7143 | 10 | 1.1338 | 0.3889 |
| 1.0728 | 6.8571 | 12 | 0.9428 | 0.5 |
| 1.0728 | 8.0 | 14 | 1.0236 | 0.5 |
| 1.0728 | 8.5714 | 15 | 0.9506 | 0.6111 |
| 1.0728 | 9.7143 | 17 | 0.9171 | 0.6111 |
| 1.0728 | 10.8571 | 19 | 1.1098 | 0.4722 |
| 0.9628 | 12.0 | 21 | 0.9111 | 0.6111 |
| 0.9628 | 12.5714 | 22 | 0.9954 | 0.5556 |
| 0.9628 | 13.7143 | 24 | 1.1014 | 0.5833 |
| 0.9628 | 14.8571 | 26 | 0.9581 | 0.5556 |
| 0.9628 | 16.0 | 28 | 1.0735 | 0.5278 |
| 0.9628 | 16.5714 | 29 | 1.1480 | 0.5556 |
| 0.833 | 17.7143 | 31 | 1.0334 | 0.5833 |
| 0.833 | 18.8571 | 33 | 0.9554 | 0.5833 |
| 0.833 | 20.0 | 35 | 1.2890 | 0.5833 |
| 0.833 | 20.5714 | 36 | 1.3330 | 0.5 |
| 0.833 | 21.7143 | 38 | 1.0786 | 0.5556 |
| 0.7274 | 22.8571 | 40 | 1.1173 | 0.5 |
| 0.7274 | 24.0 | 42 | 1.1471 | 0.5 |
| 0.7274 | 24.5714 | 43 | 1.1779 | 0.5 |
| 0.7274 | 25.7143 | 45 | 1.2391 | 0.5278 |
| 0.7274 | 26.8571 | 47 | 1.2273 | 0.5556 |
| 0.7274 | 28.0 | 49 | 1.1947 | 0.4722 |
| 0.6321 | 28.5714 | 50 | 1.2452 | 0.5278 |
| 0.6321 | 29.7143 | 52 | 1.1783 | 0.4722 |
| 0.6321 | 30.8571 | 54 | 1.2355 | 0.5278 |
| 0.6321 | 32.0 | 56 | 1.1921 | 0.5 |
| 0.6321 | 32.5714 | 57 | 1.1682 | 0.5 |
| 0.6321 | 33.7143 | 59 | 1.2613 | 0.5556 |
| 0.5586 | 34.8571 | 61 | 1.2683 | 0.5833 |
| 0.5586 | 36.0 | 63 | 1.2235 | 0.5278 |
| 0.5586 | 36.5714 | 64 | 1.2214 | 0.5833 |
| 0.5586 | 37.7143 | 66 | 1.0498 | 0.5556 |
| 0.5586 | 38.8571 | 68 | 1.0474 | 0.5833 |
| 0.4814 | 40.0 | 70 | 1.2388 | 0.5833 |
| 0.4814 | 40.5714 | 71 | 1.2826 | 0.5556 |
| 0.4814 | 41.7143 | 73 | 1.1847 | 0.5556 |
| 0.4814 | 42.8571 | 75 | 1.0760 | 0.5278 |
| 0.4814 | 44.0 | 77 | 1.0788 | 0.5833 |
| 0.4814 | 44.5714 | 78 | 1.0894 | 0.5833 |
| 0.4638 | 45.7143 | 80 | 1.2232 | 0.6111 |
| 0.4638 | 46.8571 | 82 | 1.2743 | 0.5833 |
| 0.4638 | 48.0 | 84 | 1.2030 | 0.6111 |
| 0.4638 | 48.5714 | 85 | 1.1366 | 0.5833 |
| 0.4638 | 49.7143 | 87 | 1.0802 | 0.5833 |
| 0.4638 | 50.8571 | 89 | 1.1044 | 0.6111 |
| 0.3833 | 52.0 | 91 | 1.1679 | 0.6111 |
| 0.3833 | 52.5714 | 92 | 1.1905 | 0.6111 |
| 0.3833 | 53.7143 | 94 | 1.2243 | 0.6111 |
| 0.3833 | 54.8571 | 96 | 1.2445 | 0.5833 |
| 0.3833 | 56.0 | 98 | 1.2267 | 0.6111 |
| 0.3833 | 56.5714 | 99 | 1.2180 | 0.6111 |
| 0.3405 | 57.1429 | 100 | 1.2154 | 0.6111 |
### Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1