README.md

metadata

license: mit
base_model: microsoft/phi-2
tags:
  - generated_from_trainer
datasets:
  - mc4
model-index:
  - name: laft_bur_phi
    results: []

Paper and Citation

Paper: Prompt, Translate, Fine-Tune, Re-Initialize, or Instruction-Tune? Adapting LLMs for In-Context Learning in Low-Resource Languages

@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_bur_phi

This model is a fine-tuned version of microsoft/phi-2 on the mc4 my dataset. It achieves the following results on the evaluation set:

• Loss: 0.5361

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
0.5307	1.0	24415	0.5873
0.7911	2.0	48830	0.5612
0.3645	3.0	73245	0.5288
0.4859	4.0	97660	0.5031
0.4305	5.0	122075	0.4964
0.3455	6.0	146490	0.5361

Framework versions

• Transformers 4.44.0
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.19.1