metadata
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit_epochs5_batch32_lr5e-05_size224_tiles10_seed1_q3_dropout_v2
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: 0.9474666666666667
vit_epochs5_batch32_lr5e-05_size224_tiles10_seed1_q3_dropout_v2
This model was trained from scratch on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2693
- Accuracy: 0.9475
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 |
---|---|---|---|---|
0.0722 | 1.0 | 469 | 0.1562 | 0.9413 |
0.0062 | 2.0 | 938 | 0.2430 | 0.9371 |
0.0043 | 3.0 | 1407 | 0.2117 | 0.948 |
0.0025 | 4.0 | 1876 | 0.2428 | 0.9501 |
0.0014 | 5.0 | 2345 | 0.2693 | 0.9475 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1