Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
organa-deit-base-finetuned
This model is a fine-tuned version of facebook/deit-base-patch16-224 on the medmnist-v2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1968
- Accuracy: 0.9353
- Precision: 0.9421
- Recall: 0.9348
- F1: 0.9371
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: 0.005
- 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
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
0.5926 | 1.0 | 324 | 0.1470 | 0.9522 | 0.9522 | 0.9506 | 0.9490 |
0.5555 | 2.0 | 648 | 0.1204 | 0.9661 | 0.9631 | 0.9653 | 0.9631 |
0.5618 | 3.0 | 972 | 0.0541 | 0.9800 | 0.9820 | 0.9830 | 0.9820 |
0.4652 | 4.0 | 1297 | 0.0970 | 0.9738 | 0.9804 | 0.9790 | 0.9791 |
0.4107 | 5.0 | 1621 | 0.0811 | 0.9753 | 0.9788 | 0.9798 | 0.9788 |
0.369 | 6.0 | 1945 | 0.0463 | 0.9815 | 0.9822 | 0.9798 | 0.9803 |
0.339 | 7.0 | 2269 | 0.0332 | 0.9923 | 0.9920 | 0.9935 | 0.9927 |
0.3287 | 8.0 | 2594 | 0.0468 | 0.9861 | 0.9877 | 0.9893 | 0.9883 |
0.2578 | 9.0 | 2918 | 0.0491 | 0.9892 | 0.9923 | 0.9930 | 0.9925 |
0.2282 | 9.99 | 3240 | 0.0373 | 0.9892 | 0.9917 | 0.9930 | 0.9922 |
Framework versions
- PEFT 0.9.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 271
Unable to determine this model’s pipeline type. Check the
docs
.