# Runs the full_finetune.py recipe
#
# To launch, run the following command from root:
#    tune --nnodes 1 --nproc_per_node 1 --config alpaca_llama2_full_finetune --override model_checkpoint=<your_checkpoint_dir> ...

# Dataset and Dataloader
dataset: yahma/alpaca-cleaned
seed: 42
shuffle: True

# Checkpointing
# Removed for now given poor upload speeds for checkpoints
# hf_repo_id: laurencer/Llama7b-Alpaca-Tune-4epochs-WithColoring
#checkpoint_every_n_steps: 3500 # 6k steps per epoch

# Model Arguments
# Assumes the script is run from within torchtune-colorful-llama/colorful
model_checkpoint: ../model/llama2_native.tune
tokenizer_checkpoint: ../model/tokenizer.model

color_layer_initialization: zeros
norm_before_color_layer: True

# Fine-tuning arguments
compile: True
batch_size: 8
lr: 2e-5
epochs: 4
optimizer: SGD
loss: CrossEntropyLoss
output_dir: output/alpaca-colorful-llama2-finetune
device: cuda
dtype: bf16
enable_fsdp: False
enable_activation_checkpointing: True
resume_from_checkpoint: False

# Logging arguments
metric_logger_type: wandb
project: colorful-llama