metadata
library_name: transformers
license: apache-2.0
base_model: timm/levit_128.fb_dist_in1k
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: levit_128.fb_dist_in1k-finetuned-stroke-binary
results: []
levit_128.fb_dist_in1k-finetuned-stroke-binary
This model is a fine-tuned version of timm/levit_128.fb_dist_in1k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: nan
- Accuracy: 0.6974
- F1: 0.7014
- Precision: 0.7298
- Recall: 0.6974
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 36
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.695 | 0.6202 | 100 | nan | 0.5364 | 0.5421 | 0.5541 | 0.5364 |
| 0.6804 | 1.2357 | 200 | nan | 0.5798 | 0.5833 | 0.6278 | 0.5798 |
| 0.6821 | 1.8558 | 300 | nan | 0.6232 | 0.6280 | 0.6413 | 0.6232 |
| 0.6726 | 2.4713 | 400 | nan | 0.6671 | 0.6711 | 0.6829 | 0.6671 |
| 0.6546 | 3.0868 | 500 | nan | 0.7024 | 0.7021 | 0.7018 | 0.7024 |
| 0.647 | 3.7070 | 600 | nan | 0.7065 | 0.7093 | 0.7159 | 0.7065 |
| 0.6263 | 4.3225 | 700 | nan | 0.6956 | 0.6991 | 0.7096 | 0.6956 |
| 0.6112 | 4.9426 | 800 | nan | 0.6766 | 0.6807 | 0.7123 | 0.6766 |
| 0.5704 | 5.5581 | 900 | nan | 0.6974 | 0.7014 | 0.7298 | 0.6974 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.6.0+cu124
- Datasets 3.4.0
- Tokenizers 0.21.0