|
|
---
|
|
|
base_model: MBZUAI/swiftformer-xs
|
|
|
tags:
|
|
|
- generated_from_trainer
|
|
|
datasets:
|
|
|
- imagefolder
|
|
|
metrics:
|
|
|
- accuracy
|
|
|
model-index:
|
|
|
- name: swiftformer-xs-OT
|
|
|
results:
|
|
|
- task:
|
|
|
name: Image Classification
|
|
|
type: image-classification
|
|
|
dataset:
|
|
|
name: imagefolder
|
|
|
type: imagefolder
|
|
|
config: default
|
|
|
split: validation
|
|
|
args: default
|
|
|
metrics:
|
|
|
- name: Accuracy
|
|
|
type: accuracy
|
|
|
value: 0.8548387096774194
|
|
|
---
|
|
|
|
|
|
<!-- 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. -->
|
|
|
|
|
|
# swiftformer-xs-OT
|
|
|
|
|
|
This model is a fine-tuned version of [MBZUAI/swiftformer-xs](https://huggingface.co/MBZUAI/swiftformer-xs) on the imagefolder dataset.
|
|
|
It achieves the following results on the evaluation set:
|
|
|
- Loss: 0.4956
|
|
|
- Accuracy: 0.8548
|
|
|
|
|
|
## 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: 0.0015
|
|
|
- train_batch_size: 16
|
|
|
- eval_batch_size: 16
|
|
|
- seed: 42
|
|
|
- gradient_accumulation_steps: 4
|
|
|
- total_train_batch_size: 64
|
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
|
- lr_scheduler_type: linear
|
|
|
- lr_scheduler_warmup_ratio: 0.1
|
|
|
- num_epochs: 40
|
|
|
|
|
|
### Training results
|
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
|
|
| No log | 0.89 | 4 | 1.3804 | 0.5161 |
|
|
|
| No log | 2.0 | 9 | 1.2554 | 0.5323 |
|
|
|
| 1.3469 | 2.89 | 13 | 0.9725 | 0.6613 |
|
|
|
| 1.3469 | 4.0 | 18 | 0.7086 | 0.7581 |
|
|
|
| 0.9831 | 4.89 | 22 | 0.8856 | 0.7258 |
|
|
|
| 0.9831 | 6.0 | 27 | 0.7724 | 0.7581 |
|
|
|
| 0.7441 | 6.89 | 31 | 0.8190 | 0.7258 |
|
|
|
| 0.7441 | 8.0 | 36 | 0.6897 | 0.7742 |
|
|
|
| 0.6939 | 8.89 | 40 | 0.6599 | 0.7258 |
|
|
|
| 0.6939 | 10.0 | 45 | 0.6288 | 0.7742 |
|
|
|
| 0.6939 | 10.89 | 49 | 0.6333 | 0.7581 |
|
|
|
| 0.5861 | 12.0 | 54 | 0.6206 | 0.7742 |
|
|
|
| 0.5861 | 12.89 | 58 | 0.5263 | 0.7903 |
|
|
|
| 0.5018 | 14.0 | 63 | 0.5836 | 0.8065 |
|
|
|
| 0.5018 | 14.89 | 67 | 0.6125 | 0.7419 |
|
|
|
| 0.4642 | 16.0 | 72 | 0.5431 | 0.8065 |
|
|
|
| 0.4642 | 16.89 | 76 | 0.5893 | 0.8387 |
|
|
|
| 0.4064 | 18.0 | 81 | 0.4997 | 0.8065 |
|
|
|
| 0.4064 | 18.89 | 85 | 0.5474 | 0.7742 |
|
|
|
| 0.4275 | 20.0 | 90 | 0.6748 | 0.7903 |
|
|
|
| 0.4275 | 20.89 | 94 | 0.6369 | 0.7581 |
|
|
|
| 0.4275 | 22.0 | 99 | 0.5610 | 0.7742 |
|
|
|
| 0.373 | 22.89 | 103 | 0.5260 | 0.7903 |
|
|
|
| 0.373 | 24.0 | 108 | 0.5416 | 0.8387 |
|
|
|
| 0.2931 | 24.89 | 112 | 0.5146 | 0.8387 |
|
|
|
| 0.2931 | 26.0 | 117 | 0.5180 | 0.7742 |
|
|
|
| 0.3135 | 26.89 | 121 | 0.5169 | 0.8226 |
|
|
|
| 0.3135 | 28.0 | 126 | 0.5491 | 0.8387 |
|
|
|
| 0.2342 | 28.89 | 130 | 0.5385 | 0.8387 |
|
|
|
| 0.2342 | 30.0 | 135 | 0.5456 | 0.8387 |
|
|
|
| 0.2342 | 30.89 | 139 | 0.4956 | 0.8548 |
|
|
|
| 0.2411 | 32.0 | 144 | 0.5254 | 0.8226 |
|
|
|
| 0.2411 | 32.89 | 148 | 0.5533 | 0.8387 |
|
|
|
| 0.2135 | 34.0 | 153 | 0.5613 | 0.8387 |
|
|
|
| 0.2135 | 34.89 | 157 | 0.5748 | 0.8226 |
|
|
|
| 0.1904 | 35.56 | 160 | 0.5844 | 0.8387 |
|
|
|
|
|
|
|
|
|
### Framework versions
|
|
|
|
|
|
- Transformers 4.36.2
|
|
|
- Pytorch 2.1.2+cu118
|
|
|
- Datasets 2.16.1
|
|
|
- Tokenizers 0.15.0
|
|
|
|
