---
license: other
base_model: google/mobilenet_v2_1.4_224
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Train-Augmentation-mobilenet-v2
  results: []
---

<!-- 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. -->

# Train-Augmentation-mobilenet-v2

This model is a fine-tuned version of [google/mobilenet_v2_1.4_224](https://huggingface.co/google/mobilenet_v2_1.4_224) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2228
- Accuracy: 0.6206

## 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: 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.546         | 0.99  | 93   | 1.5638          | 0.5020   |
| 0.7642        | 2.0   | 187  | 1.6707          | 0.4466   |
| 0.5713        | 2.99  | 280  | 1.5439          | 0.4822   |
| 0.456         | 4.0   | 374  | 1.3120          | 0.5968   |
| 0.3723        | 4.99  | 467  | 0.9863          | 0.6877   |
| 0.2825        | 6.0   | 561  | 1.4513          | 0.5257   |
| 0.2637        | 6.99  | 654  | 1.2236          | 0.6443   |
| 0.1945        | 8.0   | 748  | 1.2310          | 0.5929   |
| 0.198         | 8.99  | 841  | 1.7762          | 0.4862   |
| 0.1494        | 9.95  | 930  | 1.2228          | 0.6206   |


### Framework versions

- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.15.2