|
---
|
|
base_model: MBZUAI/swiftformer-xs
|
|
tags:
|
|
- generated_from_trainer
|
|
datasets:
|
|
- imagefolder
|
|
metrics:
|
|
- accuracy
|
|
model-index:
|
|
- name: swiftformer-xs-DMAE
|
|
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: 0.7391304347826086
|
|
---
|
|
|
|
<!-- 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-DMAE
|
|
|
|
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: 0.8596
|
|
- Accuracy: 0.7391
|
|
|
|
## 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 | 0.86 | 3 | 1.3836 | 0.4565 |
|
|
| No log | 2.0 | 7 | 1.3327 | 0.6522 |
|
|
| 1.3567 | 2.86 | 10 | 1.1681 | 0.6522 |
|
|
| 1.3567 | 4.0 | 14 | 1.0440 | 0.5652 |
|
|
| 1.3567 | 4.86 | 17 | 1.0462 | 0.6304 |
|
|
| 1.0903 | 6.0 | 21 | 0.9294 | 0.5870 |
|
|
| 1.0903 | 6.86 | 24 | 0.9572 | 0.6522 |
|
|
| 1.0903 | 8.0 | 28 | 0.9286 | 0.6739 |
|
|
| 1.0969 | 8.86 | 31 | 0.9229 | 0.6304 |
|
|
| 1.0969 | 10.0 | 35 | 0.9061 | 0.6522 |
|
|
| 1.0969 | 10.86 | 38 | 0.8341 | 0.6739 |
|
|
| 0.8923 | 12.0 | 42 | 0.8786 | 0.6739 |
|
|
| 0.8923 | 12.86 | 45 | 0.8596 | 0.7391 |
|
|
| 0.8923 | 14.0 | 49 | 0.8902 | 0.7174 |
|
|
| 0.7289 | 14.86 | 52 | 0.8024 | 0.6739 |
|
|
| 0.7289 | 16.0 | 56 | 0.9341 | 0.7174 |
|
|
| 0.7289 | 16.86 | 59 | 1.0464 | 0.7174 |
|
|
| 0.6609 | 18.0 | 63 | 0.9923 | 0.6087 |
|
|
| 0.6609 | 18.86 | 66 | 0.8225 | 0.7174 |
|
|
| 0.6527 | 20.0 | 70 | 0.8748 | 0.6957 |
|
|
| 0.6527 | 20.86 | 73 | 0.8052 | 0.6739 |
|
|
| 0.6527 | 22.0 | 77 | 0.8861 | 0.6957 |
|
|
| 0.493 | 22.86 | 80 | 0.9555 | 0.6957 |
|
|
| 0.493 | 24.0 | 84 | 1.0336 | 0.6739 |
|
|
| 0.493 | 24.86 | 87 | 0.9961 | 0.6957 |
|
|
| 0.4088 | 26.0 | 91 | 1.0400 | 0.6957 |
|
|
| 0.4088 | 26.86 | 94 | 1.0536 | 0.6957 |
|
|
| 0.4088 | 28.0 | 98 | 1.1388 | 0.6739 |
|
|
| 0.4047 | 28.86 | 101 | 1.2295 | 0.6522 |
|
|
| 0.4047 | 30.0 | 105 | 1.2627 | 0.6522 |
|
|
| 0.4047 | 30.86 | 108 | 1.2372 | 0.6739 |
|
|
| 0.3681 | 32.0 | 112 | 1.2919 | 0.6522 |
|
|
| 0.3681 | 32.86 | 115 | 1.2453 | 0.6522 |
|
|
| 0.3681 | 34.0 | 119 | 1.2612 | 0.6739 |
|
|
| 0.353 | 34.29 | 120 | 1.2611 | 0.6957 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.36.2
|
|
- Pytorch 2.1.2+cu118
|
|
- Datasets 2.16.1
|
|
- Tokenizers 0.15.0
|
|
|
