7B_full.yaml

# This config uses hyperparameters based on small set of experiments and information
# available on various forums. These are not meant to replicate the numbers
# from the paper
#
# Run this config on 4 GPUs using the following:
# tune run --nproc_per_node 4 full_finetune_distributed --config mistral/7B_full

# Tokenizer
tokenizer:
  _component_: torchtune.models.mistral.mistral_tokenizer
  path: /tmp/Mistral-7B-v0.1/tokenizer.model

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

# Model Arguments
model:
  _component_: torchtune.models.mistral.mistral_7b

checkpointer:
  _component_: torchtune.utils.FullModelHFCheckpointer
  checkpoint_dir: /tmp/Mistral-7B-v0.1
  checkpoint_files: [
    pytorch_model-00001-of-00002.bin,
    pytorch_model-00002-of-00002.bin
  ]
  recipe_checkpoint: null
  output_dir: /tmp/Mistral-7B-v0.1/
  model_type: MISTRAL
resume_from_checkpoint: False

# Fine-tuning arguments
batch_size: 2
epochs: 3
optimizer:
  _component_: torch.optim.AdamW
  lr: 5e-6
loss:
  _component_: torch.nn.CrossEntropyLoss
max_steps_per_epoch: null
gradient_accumulation_steps: 1


# Training env
device: cuda

# Distributed
cpu_offload: False

# Memory management
enable_activation_checkpointing: True

# Reduced precision
dtype: bf16

# Logging
metric_logger:
  _component_: torchtune.utils.metric_logging.DiskLogger
  log_dir: ${output_dir}
output_dir: /tmp/Mistral-7B-v0.1/
log_every_n_steps: null