src/config.yaml

task: llm-sft
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
project_name: llama
log: tensorboard
backend: local

data:
  path: baryshych/platma
  train_split: train
  valid_split: null
  chat_template: null
  column_mapping:
    text_column: text

params:
  block_size: 1024
  lr: 1e-4
  warmup_ratio: 0.1
  weight_decay: 0.01
  epochs: 1
  batch_size: 2
  gradient_accumulation: 8
  mixed_precision: fp16
  peft: True
  quantization: null
  lora_r: 16
  lora_alpha: 32
  lora_dropout: 0.05
  unsloth: False
  optimizer: paged_adamw_8bit
  target_modules: all-linear
  padding: right
  optimizer: paged_adamw_8bit
  scheduler: cosine

hub:
  username: baryshych
  token: ${HF_ACCESS_TOKEN}
  push_to_hub: True