config.yaml

# lightning.pytorch==2.0.0
seed_everything: 42
trainer:
  accelerator: auto
  strategy: auto
  devices: auto
  num_nodes: 1
  precision: 16-mixed
  logger:
    class_path: lightning.pytorch.loggers.TensorBoardLogger
    init_args:
      save_dir: /work/home/hj36wegi/scratch/data/goemotions/llama2_sft_template1
      version: null
  callbacks:
    - class_path: lightning.pytorch.callbacks.ModelCheckpoint
      init_args:
        save_top_k: -1
        save_weights_only: false
    - class_path: lightning.pytorch.callbacks.LearningRateMonitor
      init_args:
        logging_interval: step
  fast_dev_run: null
  max_epochs: null
  min_epochs: null
  max_steps: -1
  min_steps: null
  max_time: null
  limit_train_batches: null
  limit_val_batches: null
  limit_test_batches: null
  limit_predict_batches: null
  overfit_batches: 0.0
  val_check_interval: null
  check_val_every_n_epoch: 1
  num_sanity_val_steps: null
  log_every_n_steps: 10
  enable_checkpointing: null
  enable_progress_bar: null
  enable_model_summary: null
  accumulate_grad_batches: 1
  gradient_clip_val: null
  gradient_clip_algorithm: null
  deterministic: null
  benchmark: true
  inference_mode: true
  use_distributed_sampler: true
  profiler: null
  detect_anomaly: false
  barebones: false
  plugins: null
  sync_batchnorm: false
  reload_dataloaders_every_n_epochs: 0
  default_root_dir: null
model:
  model_name_or_path: meta-llama/Llama-2-7b-hf
  load_in_8bit: false
  load_in_4bit: true
  use_peft: true
  lora_r: 64
  lora_alpha: 16
  lr: 2.0e-05
  adam_epsilon: 1.0e-08
  warmup_steps: 0
  weight_decay: 0.0
data:
  batch_size: 4
ckpt_path: null