|
--- |
|
library_name: transformers |
|
license: other |
|
base_model: apple/mobilevit-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: my_food_model |
|
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. --> |
|
|
|
# my_food_model |
|
|
|
This model is a fine-tuned version of [apple/mobilevit-small](https://huggingface.co./apple/mobilevit-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0492 |
|
- Accuracy: 0.7236 |
|
|
|
## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 25 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| 4.4987 | 1.0 | 592 | 4.4835 | 0.1002 | |
|
| 3.6382 | 2.0 | 1184 | 3.4318 | 0.2707 | |
|
| 2.9497 | 3.0 | 1776 | 2.5897 | 0.3945 | |
|
| 2.586 | 4.0 | 2368 | 2.1261 | 0.4824 | |
|
| 2.2806 | 5.0 | 2960 | 1.8201 | 0.5501 | |
|
| 2.0928 | 6.0 | 3552 | 1.6291 | 0.5896 | |
|
| 1.9839 | 7.0 | 4144 | 1.4954 | 0.6145 | |
|
| 1.8465 | 8.0 | 4736 | 1.4209 | 0.6333 | |
|
| 1.6939 | 9.0 | 5328 | 1.3486 | 0.6493 | |
|
| 1.6212 | 10.0 | 5920 | 1.2959 | 0.6616 | |
|
| 1.6672 | 11.0 | 6512 | 1.2299 | 0.6744 | |
|
| 1.5973 | 12.0 | 7104 | 1.2018 | 0.6871 | |
|
| 1.5419 | 13.0 | 7696 | 1.1750 | 0.6928 | |
|
| 1.5003 | 14.0 | 8288 | 1.1297 | 0.7017 | |
|
| 1.4908 | 15.0 | 8880 | 1.1184 | 0.7030 | |
|
| 1.4033 | 16.0 | 9472 | 1.0983 | 0.7125 | |
|
| 1.4015 | 17.0 | 10064 | 1.0832 | 0.7159 | |
|
| 1.3651 | 18.0 | 10656 | 1.0728 | 0.7134 | |
|
| 1.3698 | 19.0 | 11248 | 1.0678 | 0.7166 | |
|
| 1.4136 | 20.0 | 11840 | 1.0541 | 0.7217 | |
|
| 1.4679 | 21.0 | 12432 | 1.0542 | 0.7208 | |
|
| 1.3328 | 22.0 | 13024 | 1.0466 | 0.7253 | |
|
| 1.2773 | 23.0 | 13616 | 1.0655 | 0.7188 | |
|
| 1.342 | 24.0 | 14208 | 1.0471 | 0.7236 | |
|
| 1.3437 | 25.0 | 14800 | 1.0492 | 0.7236 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.1 |
|
- Pytorch 2.4.0 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.20.0 |
|
|
