metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: microsoft/beit-base-patch16-224-pt22k-ft22k
datasets:
- medmnist-v2
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: organsmnist-beit-base-finetuned
results: []
organsmnist-beit-base-finetuned
This model is a fine-tuned version of microsoft/beit-base-patch16-224-pt22k-ft22k on the medmnist-v2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4609
- Accuracy: 0.8240
- Precision: 0.7895
- Recall: 0.7821
- F1: 0.7852
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 |
|---|---|---|---|---|---|---|---|
| 0.9608 | 1.0 | 218 | 0.6055 | 0.7765 | 0.7235 | 0.7233 | 0.7007 |
| 0.9984 | 2.0 | 436 | 0.4812 | 0.8067 | 0.7265 | 0.7321 | 0.7114 |
| 0.8265 | 3.0 | 654 | 0.3726 | 0.8520 | 0.8005 | 0.7713 | 0.7683 |
| 0.7938 | 4.0 | 872 | 0.3913 | 0.8507 | 0.7812 | 0.7831 | 0.7554 |
| 0.8149 | 5.0 | 1090 | 0.3676 | 0.8532 | 0.7687 | 0.8002 | 0.7702 |
| 0.6737 | 6.0 | 1308 | 0.3305 | 0.8675 | 0.8306 | 0.8117 | 0.7934 |
| 0.5695 | 7.0 | 1526 | 0.2481 | 0.9029 | 0.8546 | 0.8469 | 0.8321 |
| 0.5857 | 8.0 | 1744 | 0.2912 | 0.8923 | 0.8464 | 0.8356 | 0.8340 |
| 0.4834 | 9.0 | 1962 | 0.2658 | 0.8997 | 0.8428 | 0.8410 | 0.8286 |
| 0.5287 | 10.0 | 2180 | 0.2590 | 0.9050 | 0.8524 | 0.8468 | 0.8468 |
Framework versions
- PEFT 0.11.1
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2