examples/extras/apollo/llama3_full_sft.yaml

### model
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
trust_remote_code: true

### method
stage: sft
do_train: true
finetuning_type: full
use_apollo: true
apollo_layerwise: true  # choices: [true, false], use false for DDP training
apollo_target: all
apollo_rank: 128
apollo_scale: 32.0
apollo_scale_type: channel

### dataset
dataset: identity,alpaca_en_demo
template: llama3
cutoff_len: 2048
max_samples: 1000
overwrite_cache: true
preprocessing_num_workers: 16
dataloader_num_workers: 4

### output
output_dir: saves/llama3-8b/full/sft
logging_steps: 10
save_steps: 500
plot_loss: true
overwrite_output_dir: true
save_only_model: false
report_to: none  # choices: [none, wandb, tensorboard, swanlab, mlflow]

### train
per_device_train_batch_size: 1
gradient_accumulation_steps: 1  # use 1 for layerwise apollo
learning_rate: 1.0e-5
num_train_epochs: 3.0
lr_scheduler_type: cosine
warmup_ratio: 0.1
pure_bf16: true
ddp_timeout: 180000000

### eval
# val_size: 0.1
# per_device_eval_batch_size: 1
# eval_strategy: steps
# eval_steps: 500