70B_full.yaml

# Config for multi-device full finetuning in full_finetune_distributed.py
# using a Llama3.1 70B Instruct model
#
# This config assumes that you've run the following command before launching
# this run:
#   tune download meta-llama/Meta-Llama-3.1-70B-Instruct --output-dir /tmp/Meta-Llama-3.1-70B-Instruct --ignore-patterns "original/consolidated*"
#
# To launch on 8 devices, run the following command from root:
#   tune run --nproc_per_node 8 full_finetune_distributed --config llama3_1/70B_full
#
# You can add specific overrides through the command line. For example
# to override the checkpointer directory while launching training
# you can run:
#   tune run --nproc_per_node 8 full_finetune_distributed --config llama3_1/70B_full checkpointer.checkpoint_dir=<YOUR_CHECKPOINT_DIR>
#
# This config is only tested on an 8xA100 machine.
#
# !!!!!!!!!!!!!
# !!!!!!!!!!!!!
# ATTENTION: It will only work with pytorch>=2.5 (nightlies). For other pytorch versions, it will OOM, even on 8xA100.
# !!!!!!!!!!!!!
# !!!!!!!!!!!!!

# Tokenizer
tokenizer:
  _component_: torchtune.models.llama3.llama3_tokenizer
  path: /tmp/Meta-Llama-3.1-70B-Instruct/original/tokenizer.model
  max_seq_len: null

# Dataset
dataset:
  _component_: torchtune.datasets.alpaca_dataset
seed: null
shuffle: True

# Model Arguments
model:
  _component_: torchtune.models.llama3_1.llama3_1_70b

checkpointer:
  _component_: torchtune.training.FullModelHFCheckpointer
  checkpoint_dir: /tmp/Meta-Llama-3.1-70B-Instruct/
  checkpoint_files: [
    model-00001-of-00030.safetensors,
    model-00002-of-00030.safetensors,
    model-00003-of-00030.safetensors,
    model-00004-of-00030.safetensors,
    model-00005-of-00030.safetensors,
    model-00006-of-00030.safetensors,
    model-00007-of-00030.safetensors,
    model-00008-of-00030.safetensors,
    model-00009-of-00030.safetensors,
    model-00010-of-00030.safetensors,
    model-00011-of-00030.safetensors,
    model-00012-of-00030.safetensors,
    model-00013-of-00030.safetensors,
    model-00014-of-00030.safetensors,
    model-00015-of-00030.safetensors,
    model-00016-of-00030.safetensors,
    model-00017-of-00030.safetensors,
    model-00018-of-00030.safetensors,
    model-00019-of-00030.safetensors,
    model-00020-of-00030.safetensors,
    model-00021-of-00030.safetensors,
    model-00022-of-00030.safetensors,
    model-00023-of-00030.safetensors,
    model-00024-of-00030.safetensors,
    model-00025-of-00030.safetensors,
    model-00026-of-00030.safetensors,
    model-00027-of-00030.safetensors,
    model-00028-of-00030.safetensors,
    model-00029-of-00030.safetensors,
    model-00030-of-00030.safetensors,
  ]
  recipe_checkpoint: null
  output_dir: /tmp/Meta-Llama-3.1-70B-Instruct/
  model_type: LLAMA3
resume_from_checkpoint: False

# Fine-tuning arguments
batch_size: 2
epochs: 3

optimizer:
  _component_: torch.optim.AdamW
  lr: 2e-5
  # Note: highly recommended to use fused=True optimizer flag
  # with CPU offload for faster optimizer step.
  fused: True

loss:
  _component_: torchtune.modules.loss.CEWithChunkedOutputLoss
max_steps_per_epoch: null
gradient_accumulation_steps: 1


# Training env
device: cuda

# Memory management
enable_activation_checkpointing: True
custom_sharded_layers: ['tok_embeddings', 'output']
fsdp_cpu_offload: True
compile: False # set it to True for better memory and performance

# Reduced precision
dtype: bf16

# Logging
metric_logger:
  _component_: torchtune.training.metric_logging.DiskLogger
  log_dir: ${output_dir}
output_dir: /tmp/full-llama3_1-finetune
log_every_n_steps: 1
log_peak_memory_stats: False