metadata
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: 0.10869565217391304
swiftformer-xs-DMAE
This model is a fine-tuned version of MBZUAI/swiftformer-xs on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 125514790469632.0
- Accuracy: 0.1087
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: 1.5e-05
- 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: 0.01
- num_epochs: 40
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.86 | 3 | 125514790469632.0 | 0.1087 |
| No log | 2.0 | 7 | 125514790469632.0 | 0.1087 |
| 125815215043379.2 | 2.86 | 10 | 125514790469632.0 | 0.1087 |
| 125815215043379.2 | 4.0 | 14 | 125514790469632.0 | 0.1087 |
| 125815215043379.2 | 4.86 | 17 | 125514790469632.0 | 0.1087 |
| 125111108842291.2 | 6.0 | 21 | 125514790469632.0 | 0.1087 |
| 125111108842291.2 | 6.86 | 24 | 125514790469632.0 | 0.1087 |
| 125111108842291.2 | 8.0 | 28 | 125514790469632.0 | 0.1087 |
| 123174816789299.2 | 8.86 | 31 | 125514790469632.0 | 0.1087 |
| 123174816789299.2 | 10.0 | 35 | 125514790469632.0 | 0.1087 |
| 123174816789299.2 | 10.86 | 38 | 125514790469632.0 | 0.1087 |
| 127795517089382.4 | 12.0 | 42 | 125514790469632.0 | 0.1087 |
| 127795517089382.4 | 12.86 | 45 | 125514790469632.0 | 0.1087 |
| 127795517089382.4 | 14.0 | 49 | 125514790469632.0 | 0.1087 |
| 123834899575603.2 | 14.86 | 52 | 125514790469632.0 | 0.1087 |
| 123834899575603.2 | 16.0 | 56 | 125514790469632.0 | 0.1087 |
| 123834899575603.2 | 16.86 | 59 | 125514790469632.0 | 0.1087 |
| 124803052312985.6 | 18.0 | 63 | 125514790469632.0 | 0.1087 |
| 124803052312985.6 | 18.86 | 66 | 125514790469632.0 | 0.1087 |
| 125771218472140.8 | 20.0 | 70 | 125514790469632.0 | 0.1087 |
| 125771218472140.8 | 20.86 | 73 | 125514790469632.0 | 0.1087 |
| 125771218472140.8 | 22.0 | 77 | 125514790469632.0 | 0.1087 |
| 126299284701184.0 | 22.86 | 80 | 125514790469632.0 | 0.1087 |
| 126299284701184.0 | 24.0 | 84 | 125514790469632.0 | 0.1087 |
| 126299284701184.0 | 24.86 | 87 | 125514790469632.0 | 0.1087 |
| 126299271279411.2 | 26.0 | 91 | 125514790469632.0 | 0.1087 |
| 126299271279411.2 | 26.86 | 94 | 125514790469632.0 | 0.1087 |
| 126299271279411.2 | 28.0 | 98 | 125514790469632.0 | 0.1087 |
| 124362979226419.2 | 28.86 | 101 | 125514790469632.0 | 0.1087 |
| 124362979226419.2 | 30.0 | 105 | 125514790469632.0 | 0.1087 |
| 124362979226419.2 | 30.86 | 108 | 125514790469632.0 | 0.1087 |
| 126035251586662.4 | 32.0 | 112 | 125514790469632.0 | 0.1087 |
| 126035251586662.4 | 32.86 | 115 | 125514790469632.0 | 0.1087 |
| 126035251586662.4 | 34.0 | 119 | 125514790469632.0 | 0.1087 |
| 125815215043379.2 | 34.29 | 120 | 125514790469632.0 | 0.1087 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0