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: 0.0429
- Wer Score: 0.4194
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: 2
- total_train_batch_size: 4
- 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 |
|---|---|---|---|---|
| 7.3552 | 3.7 | 50 | 4.5162 | 22.5645 |
| 2.3387 | 7.41 | 100 | 0.4370 | 0.3871 |
| 0.1271 | 11.11 | 150 | 0.0361 | 0.3871 |
| 0.0162 | 14.81 | 200 | 0.0361 | 0.4194 |
| 0.0112 | 18.52 | 250 | 0.0381 | 0.4355 |
| 0.0098 | 22.22 | 300 | 0.0393 | 0.4355 |
| 0.0088 | 25.93 | 350 | 0.0399 | 0.4516 |
| 0.0085 | 29.63 | 400 | 0.0424 | 0.4516 |
| 0.0076 | 33.33 | 450 | 0.0399 | 0.4194 |
| 0.007 | 37.04 | 500 | 0.0422 | 0.4516 |
| 0.0064 | 40.74 | 550 | 0.0421 | 0.4355 |
| 0.0059 | 44.44 | 600 | 0.0434 | 0.4355 |
| 0.0056 | 48.15 | 650 | 0.0429 | 0.4194 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.2+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2