|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: git-base-xr |
|
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-xr |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0641 |
|
- Bleu: 9.4387 |
|
|
|
## 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: 50 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:| |
|
| 3.5821 | 5.26 | 50 | 1.2163 | 4.6142 | |
|
| 0.8599 | 10.53 | 100 | 0.8719 | 10.5680 | |
|
| 0.5491 | 15.79 | 150 | 0.8546 | 9.7374 | |
|
| 0.3605 | 21.05 | 200 | 0.8975 | 10.2395 | |
|
| 0.2409 | 26.32 | 250 | 0.9652 | 9.8718 | |
|
| 0.1664 | 31.58 | 300 | 1.0042 | 11.7264 | |
|
| 0.1234 | 36.84 | 350 | 1.0462 | 10.5668 | |
|
| 0.1002 | 42.11 | 400 | 1.0569 | 9.7232 | |
|
| 0.0876 | 47.37 | 450 | 1.0641 | 9.4387 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.3 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.14.7 |
|
- Tokenizers 0.13.3 |
|
|
