metadata
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Train-Test-Augmentation-V3D-vit-base
results: []
Train-Test-Augmentation-V3D-vit-base
This model is a fine-tuned version of google/vit-base-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5845
- Accuracy: 0.8125
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 |
|---|---|---|---|---|
| 2.1982 | 0.9825 | 28 | 1.4670 | 0.6172 |
| 0.6796 | 2.0 | 57 | 0.6957 | 0.8052 |
| 0.2461 | 2.9825 | 85 | 0.5577 | 0.8255 |
| 0.0778 | 4.0 | 114 | 0.5563 | 0.8108 |
| 0.0243 | 4.9825 | 142 | 0.5745 | 0.8086 |
| 0.013 | 6.0 | 171 | 0.5634 | 0.8137 |
| 0.0096 | 6.9825 | 199 | 0.5765 | 0.8125 |
| 0.0077 | 8.0 | 228 | 0.5802 | 0.8114 |
| 0.0067 | 8.9825 | 256 | 0.5835 | 0.8114 |
| 0.0065 | 9.8246 | 280 | 0.5845 | 0.8125 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1