您尚未登录账户请先登录您的atyun账户，方可使用该功能
您的企业账号申请正在审核中审核通过后即可使用此功能，请耐心等待~
模型:
mrgiraffe/vit-large-dataset-model-v3
任务:
图像分类
许可:
apache-2.0
中文vit-large-dataset-model-v3
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0630
- Accuracy: 0.9850
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0465 | 0.36 | 500 | 0.1289 | 0.9612 |
| 0.0253 | 0.71 | 1000 | 0.0983 | 0.9693 |
| 0.008 | 1.07 | 1500 | 0.0957 | 0.9728 |
| 0.0569 | 1.43 | 2000 | 0.0668 | 0.9793 |
| 0.035 | 1.79 | 2500 | 0.0865 | 0.9752 |
| 0.0034 | 2.14 | 3000 | 0.0748 | 0.9773 |
| 0.0638 | 2.5 | 3500 | 0.0708 | 0.9805 |
| 0.0195 | 2.86 | 4000 | 0.0782 | 0.9821 |
| 0.0012 | 3.21 | 4500 | 0.0739 | 0.9820 |
| 0.0013 | 3.57 | 5000 | 0.0680 | 0.9845 |
| 0.0417 | 3.93 | 5500 | 0.0630 | 0.9850 |
Framework versions
- Transformers 4.22.0.dev0
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1