metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: stripes
results: []
stripes
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2177
- Accuracy: 0.9194
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 | 0.9032 | 7 | 0.6456 | 0.7742 |
| 0.6684 | 1.9355 | 15 | 0.4995 | 0.8629 |
| 0.4818 | 2.9677 | 23 | 0.3788 | 0.8629 |
| 0.3026 | 4.0 | 31 | 0.2881 | 0.9113 |
| 0.3026 | 4.9032 | 38 | 0.2530 | 0.9032 |
| 0.1806 | 5.9355 | 46 | 0.2359 | 0.9194 |
| 0.1161 | 6.9677 | 54 | 0.2288 | 0.9194 |
| 0.0894 | 8.0 | 62 | 0.2043 | 0.9435 |
| 0.0894 | 8.9032 | 69 | 0.2042 | 0.9355 |
| 0.0723 | 9.0323 | 70 | 0.2177 | 0.9194 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1