Downloads · 30 days
6
18% of all-time downloads
organamnist-vit-base-finetuned
selmamalak/organamnist-vit-base-finetuned
organamnist-vit-base-finetuned is a machine learning model from selmamalak. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
33
Public
Repo size
24 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.4 MB · 96%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- May 18, 2024
- Updated
- May 18, 2024
- SHA
- 24c86b03
Base models
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
organamnist-vit-base-finetuned
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the medmnist-v2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2008
- Accuracy: 0.9327
- Precision: 0.9399
- Recall: 0.9301
- F1: 0.9334
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 |
|---|---|---|---|---|---|---|---|
| 0.5558 | 1.0 | 540 | 0.1876 | 0.9393 | 0.9603 | 0.9474 | 0.9511 |
| 0.6069 | 2.0 | 1081 | 0.0805 | 0.9729 | 0.9688 | 0.9699 | 0.9689 |
| 0.535 | 3.0 | 1621 | 0.1914 | 0.9359 | 0.9427 | 0.9353 | 0.9355 |
| 0.5937 | 4.0 | 2162 | 0.1707 | 0.9401 | 0.9486 | 0.9109 | 0.9235 |
| 0.5324 | 5.0 | 2702 | 0.0839 | 0.9701 | 0.9747 | 0.9700 | 0.9719 |
| 0.4667 | 6.0 | 3243 | 0.1210 | 0.9593 | 0.9563 | 0.9481 | 0.9505 |
| 0.411 | 7.0 | 3783 | 0.1491 | 0.9490 | 0.9636 | 0.9542 | 0.9574 |
| 0.3235 | 8.0 | 4324 | 0.0523 | 0.9826 | 0.9858 | 0.9840 | 0.9848 |
| 0.3329 | 9.0 | 4864 | 0.0468 | 0.9821 | 0.9854 | 0.9827 | 0.9839 |
| 0.2559 | 9.99 | 5400 | 0.0495 | 0.9827 | 0.9865 | 0.9843 | 0.9852 |
Framework versions
- PEFT 0.11.1
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
- Library
- peft
- License
- apache-2.0
- Created
- May 18, 2024
- Updated
- May 18, 2024