metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: ARSL_letters_model-7epochs
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: 0.8821428571428571
ARSL_letters_model-7epochs
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.8704
- Accuracy: 0.8821
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: 1e-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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.2553 | 1.0 | 35 | 2.2824 | 0.7679 |
| 2.1368 | 2.0 | 70 | 2.1504 | 0.8393 |
| 2.0462 | 3.0 | 105 | 2.0528 | 0.8464 |
| 1.9789 | 4.0 | 140 | 1.9739 | 0.8839 |
| 1.915 | 5.0 | 175 | 1.9463 | 0.8375 |
| 1.8912 | 6.0 | 210 | 1.9037 | 0.85 |
| 1.8794 | 7.0 | 245 | 1.8704 | 0.8821 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1