metadata
license: other
base_model: nvidia/mit-b0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: architectural_styles_classifier
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: 0.7252427184466019
architectural_styles_classifier
This model is a fine-tuned version of nvidia/mit-b0 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.0414
- Accuracy: 0.7252
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: 0.0005
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=0.0003
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.7073 | 1.0 | 442 | 1.7346 | 0.4571 |
| 1.737 | 2.0 | 884 | 1.6044 | 0.4873 |
| 1.4039 | 3.0 | 1326 | 1.4456 | 0.5454 |
| 1.222 | 4.0 | 1768 | 1.3590 | 0.5886 |
| 1.2037 | 5.0 | 2210 | 1.2178 | 0.6119 |
| 1.2368 | 6.0 | 2652 | 1.2507 | 0.6189 |
| 1.118 | 7.0 | 3094 | 1.1823 | 0.6337 |
| 0.9895 | 8.0 | 3536 | 1.1384 | 0.6392 |
| 0.8918 | 9.0 | 3978 | 1.1026 | 0.6586 |
| 0.6114 | 10.0 | 4420 | 1.1647 | 0.6447 |
| 0.9911 | 11.0 | 4862 | 1.0066 | 0.6749 |
| 0.6572 | 12.0 | 5304 | 1.0767 | 0.6854 |
| 0.6302 | 13.0 | 5746 | 1.0383 | 0.6908 |
| 0.638 | 14.0 | 6188 | 1.0830 | 0.6963 |
| 0.4971 | 15.0 | 6630 | 1.0871 | 0.6913 |
| 0.4579 | 16.0 | 7072 | 1.1098 | 0.6978 |
| 0.5697 | 17.0 | 7514 | 1.1443 | 0.7012 |
| 0.3527 | 18.0 | 7956 | 1.1090 | 0.7047 |
| 0.3721 | 19.0 | 8398 | 1.1116 | 0.7141 |
| 0.2936 | 20.0 | 8840 | 1.1248 | 0.7181 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.19.1