<!-- 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. -->
vitmae_largeFunny6
This model is a fine-tuned version of facebook/vit-mae-large on the image_folder dataset. It achieves the following results on the evaluation set:
- Loss: 0.6590
- Accuracy: 0.7002
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: 1e-05
- train_batch_size: 8
- 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
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.6606 | 0.52 | 100 | 0.6562 | 0.6531 |
0.6114 | 1.05 | 200 | 0.6299 | 0.6552 |
0.6432 | 1.57 | 300 | 0.6161 | 0.6724 |
0.4627 | 2.09 | 400 | 0.6547 | 0.6574 |
0.4367 | 2.62 | 500 | 0.6211 | 0.6938 |
0.4754 | 3.14 | 600 | 0.6795 | 0.6660 |
0.335 | 3.66 | 700 | 0.6590 | 0.7002 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3