metadata
license: mit
base_model: microsoft/git-base
tags:
- generated_from_trainer
model-index:
- name: git-base-naruto
results: []
git-base-naruto
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: 1.8334
- Wer Score: 11.2335
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|---|---|---|---|---|
| 6.6454 | 7.1429 | 50 | 4.4251 | 9.3656 |
| 3.0445 | 14.2857 | 100 | 1.8334 | 11.2335 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1