<!-- 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. -->
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: 0.0398
- Wer Score: 2.6671
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- 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 |
|---|---|---|---|---|
| 7.2207 | 4.17 | 50 | 4.4895 | 18.9161 |
| 2.3481 | 8.33 | 100 | 0.4619 | 11.2245 |
| 0.1405 | 12.5 | 150 | 0.0339 | 1.4348 |
| 0.0167 | 16.67 | 200 | 0.0323 | 2.8026 |
| 0.0055 | 20.83 | 250 | 0.0347 | 2.4503 |
| 0.0021 | 25.0 | 300 | 0.0368 | 3.4684 |
| 0.0015 | 29.17 | 350 | 0.0381 | 2.8477 |
| 0.0012 | 33.33 | 400 | 0.0391 | 2.8452 |
| 0.0011 | 37.5 | 450 | 0.0393 | 2.8052 |
| 0.001 | 41.67 | 500 | 0.0395 | 2.6865 |
| 0.0009 | 45.83 | 550 | 0.0398 | 2.6890 |
| 0.0009 | 50.0 | 600 | 0.0398 | 2.6671 |
Framework versions
- Transformers 4.27.2
- Pytorch 2.0.0+cu117
- Datasets 2.10.1
- Tokenizers 0.13.2
