git-base-yy
This model is a fine-tuned version of microsoft/git-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5227
- Wer Score: 2.4121
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|---|---|---|---|---|
| 3.6336 | 5.0 | 50 | 4.6676 | 1.2862 |
| 1.318 | 10.0 | 100 | 0.9472 | 0.9491 |
| 0.2607 | 15.0 | 150 | 0.4883 | 0.9379 |
| 0.1207 | 20.0 | 200 | 0.4908 | 0.9526 |
| 0.075 | 25.0 | 250 | 0.4996 | 1.2448 |
| 0.0458 | 30.0 | 300 | 0.5111 | 1.3698 |
| 0.0336 | 35.0 | 350 | 0.5164 | 2.1043 |
| 0.0272 | 40.0 | 400 | 0.5194 | 1.2397 |
| 0.0238 | 45.0 | 450 | 0.5231 | 2.6802 |
| 0.0216 | 50.0 | 500 | 0.5227 | 2.4121 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2