<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
vit-large-ai-or-not
This model is a fine-tuned version of facebook/vit-msn-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3500
- Accuracy: 0.8443
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: 2
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.704 | 0.19 | 200 | 0.6005 | 0.6778 |
0.5943 | 0.38 | 400 | 0.5103 | 0.7513 |
0.5213 | 0.57 | 600 | 0.5167 | 0.7444 |
0.5027 | 0.76 | 800 | 0.5525 | 0.7234 |
0.4876 | 0.95 | 1000 | 0.5044 | 0.7347 |
0.425 | 1.15 | 1200 | 0.4078 | 0.8115 |
0.3801 | 1.34 | 1400 | 0.4313 | 0.8217 |
0.3572 | 1.53 | 1600 | 0.3724 | 0.8346 |
0.3456 | 1.72 | 1800 | 0.3486 | 0.8378 |
0.3039 | 1.91 | 2000 | 0.3500 | 0.8443 |
Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2