ChrisToukmaji's picture
Update README.md
54936ee verified
metadata
base_model: final_models/focus_tha_phi_after_focus_reinit
tags:
  - generated_from_trainer
datasets:
  - mc4
model-index:
  - name: focus_tha_phi_focus_trained
    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}, 
}

focus_tha_phi_focus_trained

This model is a fine-tuned version of final_models/focus_tha_phi_after_focus_reinit on the mc4 th dataset. It achieves the following results on the evaluation set:

  • Loss: 2.7209

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
3.009 1.0 24415 3.3975
3.4002 2.0 48830 3.2588
3.5914 3.0 73245 3.1160
2.593 4.0 97660 2.8634
0.9305 5.0 122075 2.6987
2.268 6.0 146490 2.7209

Framework versions

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