metadata
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit_epochs5_batch32_lr5e-05_size224_tiles1_seed1_vit_lr
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.5736
vit_epochs5_batch32_lr5e-05_size224_tiles1_seed1_vit_lr
This model was trained from scratch on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.6761
- Accuracy: 0.5736
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.6952 | 1.0 | 469 | 0.6928 | 0.4971 |
0.6736 | 2.0 | 938 | 0.6844 | 0.5552 |
0.66 | 3.0 | 1407 | 0.6900 | 0.5523 |
0.6937 | 4.0 | 1876 | 0.6770 | 0.5789 |
0.6723 | 5.0 | 2345 | 0.6761 | 0.5736 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.1