|
--- |
|
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: 0.0391 |
|
- Wer Score: 2.3433 |
|
|
|
## 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: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer Score | |
|
|:-------------:|:------:|:----:|:---------------:|:---------:| |
|
| No log | 2.0833 | 25 | 0.0365 | 3.3472 | |
|
| 0.0022 | 4.1667 | 50 | 0.0383 | 2.3199 | |
|
| 0.0022 | 6.25 | 75 | 0.0384 | 2.8114 | |
|
| 0.0005 | 8.3333 | 100 | 0.0391 | 2.3433 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.19.1 |
|
|
