---
library_name: transformers
license: apache-2.0
base_model: mlx-vision/regnet_y_400mf-mlxim
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: regnet_y_400mf-mlxim-finetuned-chest_xray-pneumonia
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: imagefolder
      type: imagefolder
      config: default
      split: train
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.8706896551724138
---

<!-- 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. -->

# regnet_y_400mf-mlxim-finetuned-chest_xray-pneumonia

This model is a fine-tuned version of [mlx-vision/regnet_y_400mf-mlxim](https://huggingface.co/mlx-vision/regnet_y_400mf-mlxim) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3384
- Accuracy: 0.8707

## 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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.4107        | 1.0   | 74   | 0.6099          | 0.6830   |
| 0.3186        | 2.0   | 148  | 0.5402          | 0.7452   |
| 0.3731        | 3.0   | 222  | 0.3384          | 0.8707   |


### Framework versions

- Transformers 4.57.1
- Pytorch 2.9.0+cpu
- Datasets 4.4.1
- Tokenizers 0.22.1