metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: Chess
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train[:258]
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.6538461538461539
Chess
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: 0.7292
- Accuracy: 0.6538
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.92 | 3 | 1.0620 | 0.5385 |
| No log | 1.85 | 6 | 0.9886 | 0.5962 |
| No log | 2.77 | 9 | 0.9286 | 0.7115 |
| 0.9947 | 4.0 | 13 | 0.8659 | 0.6731 |
| 0.9947 | 4.92 | 16 | 0.8310 | 0.6731 |
| 0.9947 | 5.85 | 19 | 0.7778 | 0.6731 |
| 0.7638 | 6.77 | 22 | 0.7388 | 0.7115 |
| 0.7638 | 8.0 | 26 | 0.7570 | 0.6731 |
| 0.7638 | 8.92 | 29 | 0.7214 | 0.6923 |
| 0.6277 | 9.23 | 30 | 0.7292 | 0.6538 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2