|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: fashion_classifier |
|
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. --> |
|
|
|
# fashion_classifier |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8857 |
|
- Accuracy: 0.8018 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:| |
|
| 2.2283 | 0.9882 | 21 | 2.1148 | 0.4852 | |
|
| 1.853 | 1.9765 | 42 | 1.6702 | 0.7249 | |
|
| 1.4363 | 2.9647 | 63 | 1.3298 | 0.7367 | |
|
| 1.1618 | 4.0 | 85 | 1.1528 | 0.7604 | |
|
| 0.9739 | 4.9882 | 106 | 1.0281 | 0.7811 | |
|
| 0.8778 | 5.9765 | 127 | 0.9325 | 0.7929 | |
|
| 0.8114 | 6.9647 | 148 | 0.9100 | 0.8136 | |
|
| 0.7626 | 8.0 | 170 | 0.9288 | 0.7633 | |
|
| 0.691 | 8.9882 | 191 | 0.9058 | 0.7870 | |
|
| 0.6988 | 9.8824 | 210 | 0.8857 | 0.8018 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.5.0+cu121 |
|
- Datasets 3.0.2 |
|
- Tokenizers 0.19.1 |
|
|
