examples/llm_finetune/phi/phi_4_squad.yaml

# Copyright (c) 2025, NVIDIA CORPORATION.  All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.


step_scheduler:
  global_batch_size: 32
  local_batch_size: 4
  ckpt_every_steps: 50
  val_every_steps: 50  # will run every x number of gradient steps
  max_steps: 100

dist_env:
  backend: nccl
  timeout_minutes: 1

rng:
  _target_: nemo_automodel.components.training.rng.StatefulRNG
  seed: 1111
  ranked: true

model:
  _target_: nemo_automodel.NeMoAutoModelForCausalLM.from_pretrained
  pretrained_model_name_or_path: microsoft/phi-4
  torch_dtype: bf16
  trust_remote_code: true

checkpoint:
  enabled: false
  checkpoint_dir: checkpoints/
  model_save_format: safetensors
  save_consolidated: false 

distributed:
  _target_: nemo_automodel.components.distributed.fsdp2.FSDP2Manager
  dp_size: none
  tp_size: 2
  cp_size: 1
  sequence_parallel: false


loss_fn:
  _target_: nemo_automodel.components.loss.masked_ce.MaskedCrossEntropy

dataset:
  _target_: nemo_automodel.components.datasets.llm.squad.make_squad_dataset
  dataset_name: rajpurkar/squad
  split: train

packed_sequence:
  # Set packed_sequence_size > 0 to run with packed sequences
  packed_sequence_size: 0

dataloader:
  _target_: torchdata.stateful_dataloader.StatefulDataLoader
  collate_fn: nemo_automodel.components.datasets.utils.default_collater
  shuffle: true


validation_dataset:
  _target_: nemo_automodel.components.datasets.llm.squad.make_squad_dataset
  dataset_name: rajpurkar/squad
  split: validation

validation_dataloader:
  _target_: torchdata.stateful_dataloader.StatefulDataLoader
  collate_fn: nemo_automodel.components.datasets.utils.default_collater
  
optimizer:
  _target_: torch.optim.Adam
  betas: [0.9, 0.999]
  eps: 1e-8
  lr: 1.0e-5
  weight_decay: 0
  # min_lr: 1.0e-5

# Uncomment and configure for W&B logging
# wandb:
#   project: <your_wandb_project>
#   entity: <your_wandb_entity>
#   name: <your_wandb_exp_name>
#   save_dir: <your_wandb_save_dir> 