|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: mosaicml/mpt-7b |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- mozilla-foundation/common_voice_11_0 |
|
|
model-index: |
|
|
- name: laft_lug_mpt |
|
|
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. --> |
|
|
|
|
|
# Paper and Citation |
|
|
Paper: [Prompt, Translate, Fine-Tune, Re-Initialize, or Instruction-Tune? Adapting LLMs for In-Context Learning in Low-Resource Languages |
|
|
](https://arxiv.org/abs/2506.19187) |
|
|
``` |
|
|
@misc{toukmaji2025prompttranslatefinetunereinitialize, |
|
|
title={Prompt, Translate, Fine-Tune, Re-Initialize, or Instruction-Tune? Adapting LLMs for In-Context Learning in Low-Resource Languages}, |
|
|
author={Christopher Toukmaji and Jeffrey Flanigan}, |
|
|
year={2025}, |
|
|
eprint={2506.19187}, |
|
|
archivePrefix={arXiv}, |
|
|
primaryClass={cs.CL}, |
|
|
url={https://arxiv.org/abs/2506.19187}, |
|
|
} |
|
|
``` |
|
|
|
|
|
# laft_lug_mpt |
|
|
|
|
|
This model is a fine-tuned version of [mosaicml/mpt-7b](https://huggingface.co/mosaicml/mpt-7b) on the mozilla-foundation/common_voice_11_0 lg dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 2.9695 |
|
|
|
|
|
## 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: 0.0003 |
|
|
- train_batch_size: 1 |
|
|
- eval_batch_size: 1 |
|
|
- seed: 42 |
|
|
- distributed_type: multi-GPU |
|
|
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05 |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_steps: 2000 |
|
|
- num_epochs: 6.0 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 2.7969 | 1.0 | 1510 | 2.6259 | |
|
|
| 2.2344 | 2.0 | 3020 | 2.3295 | |
|
|
| 2.0781 | 3.0 | 4530 | 2.2022 | |
|
|
| 1.7266 | 4.0 | 6040 | 2.2305 | |
|
|
| 0.7852 | 5.0 | 7550 | 2.6690 | |
|
|
| 0.3105 | 6.0 | 9060 | 2.9695 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.44.0 |
|
|
- Pytorch 2.4.0+cu121 |
|
|
- Datasets 2.20.0 |
|
|
- Tokenizers 0.19.1 |
|
|
|
