metadata
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224
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: 0.8
vit-base-patch16-224
This model was trained from scratch on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.5546
- Accuracy: 0.8
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-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 8 | 0.5546 | 0.8 |
| 0.5945 | 2.0 | 16 | 0.5409 | 0.8 |
| 0.5832 | 3.0 | 24 | 0.5467 | 0.8 |
| 0.5338 | 4.0 | 32 | 0.5518 | 0.8 |
| 0.5513 | 5.0 | 40 | 0.5602 | 0.8 |
| 0.5513 | 6.0 | 48 | 0.5607 | 0.7333 |
| 0.5417 | 7.0 | 56 | 0.5707 | 0.7333 |
| 0.5343 | 8.0 | 64 | 0.5748 | 0.7333 |
| 0.5379 | 9.0 | 72 | 0.5736 | 0.7333 |
| 0.5137 | 10.0 | 80 | 0.5730 | 0.7333 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1