metadata
license: apache-2.0
base_model: facebook/dino-vits8
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: dino-vits8-musinsa
results: []
dino-vits8-musinsa
This model is a fine-tuned version of facebook/dino-vits8 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1692
- Precision: 0.9579
- Recall: 0.9576
- F1: 0.9575
- Accuracy: 0.9576
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: 5e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 202 | 0.1408 | 0.9513 | 0.9494 | 0.9498 | 0.9494 |
| No log | 2.0 | 404 | 0.1328 | 0.9563 | 0.9558 | 0.9560 | 0.9558 |
| 0.1129 | 3.0 | 606 | 0.1692 | 0.9579 | 0.9576 | 0.9575 | 0.9576 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Tokenizers 0.19.1