Epipaca / README.md
CocoNutZENG's picture
Update README.md
4a90e25 verified
metadata
license: apache-2.0
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: hfl/llama-3-chinese-8b-instruct
model-index:
  - name: checkpoints
    results: []

Epipaca

Epipaca

  1. This is the cross-languadge LLM adapter design for epilepsy-care instuction, with support both Mandarin and English.
  2. It is finetune by Epilepsy_Synthetics dataset.
    ** Notice: Haven't validate yet. Use with care. **

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0001
  • train_batch_size: 1
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 2
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.03
  • num_epochs: 2

Training results

Framework versions

  • PEFT 0.11.1
  • Transformers 4.40.2
  • Pytorch 2.2.1
  • Datasets 2.19.1
  • Tokenizers 0.19.1