metadata
base_model: d071696/vit-finetune-scrap
tags:
- image-classification
- image-feature-extraction
- image-to-text
- generated_from_trainer
datasets:
- arrow
metrics:
- accuracy
model-index:
- name: vit-finetune-scrap
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: d071696/scraps1
type: arrow
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.954983922829582
vit-finetune-scrap
This model is a fine-tuned version of d071696/vit-finetune-scrap on the d071696/scraps1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1588
- Accuracy: 0.9550
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1672 | 0.64 | 100 | 0.2250 | 0.9486 |
| 0.1277 | 1.28 | 200 | 0.2467 | 0.9373 |
| 0.0253 | 1.92 | 300 | 0.1588 | 0.9550 |
| 0.0224 | 2.56 | 400 | 0.1691 | 0.9534 |
| 0.0321 | 3.21 | 500 | 0.1751 | 0.9566 |
| 0.0112 | 3.85 | 600 | 0.1805 | 0.9550 |
Framework versions
- Transformers 4.39.0
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2