<!-- 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-base-patch16-224-finetuned-memes-v3
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.3862
- Accuracy: 0.8478
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: 0.00012
- 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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5649 | 0.99 | 40 | 0.6342 | 0.7488 |
| 0.3083 | 1.99 | 80 | 0.4146 | 0.8423 |
| 0.1563 | 2.99 | 120 | 0.3900 | 0.8547 |
| 0.0827 | 3.99 | 160 | 0.3862 | 0.8478 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.1
