metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- catbreed
metrics:
- accuracy
model-index:
- name: catbreed
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: catbreed
type: catbreed
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9252136752136753
catbreed
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the catbreed dataset. It achieves the following results on the evaluation set:
- Loss: 0.7210
- Accuracy: 0.9252
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.1329 | 0.99 | 29 | 1.7492 | 0.8376 |
| 1.3437 | 1.98 | 58 | 1.1638 | 0.9038 |
| 0.9266 | 2.97 | 87 | 0.9013 | 0.8974 |
| 0.7274 | 4.0 | 117 | 0.7345 | 0.9338 |
| 0.6652 | 4.96 | 145 | 0.7210 | 0.9252 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3