|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: microsoft/git-base |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: git-base-pokemon |
|
results: [] |
|
--- |
|
|
|
<!-- 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](https://huggingface.co./microsoft/git-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0420 |
|
- Wer Score: 3.8081 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 32 |
|
- optimizer: Use 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 | |
|
|:-------------:|:-------:|:----:|:---------------:|:---------:| |
|
| 5.2468 | 3.5398 | 50 | 4.5809 | 17.1528 | |
|
| 0.7758 | 7.0796 | 100 | 0.4672 | 7.7810 | |
|
| 0.0337 | 10.6195 | 150 | 0.0424 | 2.3531 | |
|
| 0.0089 | 14.1593 | 200 | 0.0401 | 3.3039 | |
|
| 0.0022 | 17.6991 | 250 | 0.0388 | 5.8557 | |
|
| 0.0008 | 21.2389 | 300 | 0.0411 | 4.6740 | |
|
| 0.0004 | 24.7788 | 350 | 0.0410 | 3.8676 | |
|
| 0.0003 | 28.3186 | 400 | 0.0409 | 4.1766 | |
|
| 0.0002 | 31.8584 | 450 | 0.0414 | 4.0136 | |
|
| 0.0002 | 35.3982 | 500 | 0.0414 | 3.9779 | |
|
| 0.0002 | 38.9381 | 550 | 0.0417 | 3.9542 | |
|
| 0.0002 | 42.4779 | 600 | 0.0418 | 3.8913 | |
|
| 0.0002 | 46.0177 | 650 | 0.0420 | 3.8183 | |
|
| 0.0002 | 49.5575 | 700 | 0.0420 | 3.8081 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.3 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.20.3 |
|
|
