git-base-pokemon
This model is a fine-tuned version of microsoft/git-base on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.4530
- Wer Score: 16.5809
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: 128
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|---|---|---|---|---|
| 7.2955 | 16.67 | 50 | 5.0105 | 21.4433 |
| 3.6221 | 33.33 | 100 | 2.2745 | 21.3860 |
| 1.8264 | 50.0 | 150 | 1.4530 | 16.5809 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.0a0+d321be6
- Datasets 2.11.0
- Tokenizers 0.13.3