7B_lora.yaml

# Config for multi-device LoRA finetuning in lora_finetune_distributed.py
# using a Llama2 7B model
#
# This config assumes that you've run the following command before launching
# this run:
#   tune download meta-llama/Llama-2-7b-hf --output-dir /tmp/Llama-2-7b-hf --hf-token <HF_TOKEN>
#
# To launch on 2 devices, run the following command from root:
#   tune run --nnodes 1 --nproc_per_node 2 lora_finetune_distributed --config llama2/7B_lora
#
# You can add specific overrides through the command line. For example
# to override the checkpointer directory while launching training
# you can run:
#   tune run --nnodes 1 --nproc_per_node 2 lora_finetune_distributed --config llama2/7B_lora checkpointer.checkpoint_dir=<YOUR_CHECKPOINT_DIR>
#
# This config works best when the model is being fine-tuned on 2+ GPUs.
# For single device LoRA finetuning please use 7B_lora_single_device.yaml
# or 7B_qlora_single_device.yaml


# Model Arguments
model:
  _component_: torchtune.models.llama2.lora_llama2_7b
  lora_attn_modules: ['q_proj', 'v_proj']
  apply_lora_to_mlp: False
  apply_lora_to_output: False
  lora_rank: 8
  lora_alpha: 16

tokenizer:
  _component_: torchtune.models.llama2.llama2_tokenizer
  path: /tmp/Llama-2-7b-hf/tokenizer.model

checkpointer:
  _component_: torchtune.utils.FullModelHFCheckpointer
  checkpoint_dir: /tmp/Llama-2-7b-hf
  checkpoint_files: [
    pytorch_model-00001-of-00002.bin,
    pytorch_model-00002-of-00002.bin
  ]
  adapter_checkpoint: null
  recipe_checkpoint: null
  output_dir: /tmp/Llama-2-7b-hf
  model_type: LLAMA2
resume_from_checkpoint: False

# Dataset and Sampler
dataset:
  _component_: torchtune.datasets.alpaca_cleaned_dataset
  train_on_input: True
seed: null
shuffle: True
batch_size: 2

# Optimizer and Scheduler
optimizer:
  _component_: torch.optim.AdamW
  weight_decay: 0.01
  lr: 3e-4
lr_scheduler:
  _component_: torchtune.modules.get_cosine_schedule_with_warmup
  num_warmup_steps: 100

loss:
  _component_: torch.nn.CrossEntropyLoss

# Training
epochs: 1
max_steps_per_epoch: null
gradient_accumulation_steps: 32

# Logging
output_dir: /tmp/lora_finetune_output
metric_logger:
  _component_: torchtune.utils.metric_logging.DiskLogger
  log_dir: ${output_dir}
log_every_n_steps: null

# Environment
device: cuda
dtype: bf16
enable_activation_checkpointing: False