metadata
license: mit
base_model: shi-labs/nat-mini-in1k-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: msi_mini
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: 0.6228683254123567
msi_mini
This model is a fine-tuned version of shi-labs/nat-mini-in1k-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.5314
- Accuracy: 0.6229
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
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.428 | 1.0 | 2015 | 0.8665 | 0.6079 |
| 0.3163 | 2.0 | 4031 | 1.0921 | 0.6169 |
| 0.2805 | 3.0 | 6047 | 1.1998 | 0.6082 |
| 0.2251 | 4.0 | 8063 | 1.2788 | 0.6126 |
| 0.1988 | 5.0 | 10078 | 1.3336 | 0.6121 |
| 0.1794 | 6.0 | 12094 | 1.3361 | 0.6224 |
| 0.1724 | 7.0 | 14110 | 1.5478 | 0.6097 |
| 0.1739 | 8.0 | 16126 | 1.6165 | 0.6169 |
| 0.1637 | 9.0 | 18141 | 1.5974 | 0.6134 |
| 0.1667 | 10.0 | 20150 | 1.5314 | 0.6229 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0