### model
model_name_or_path: llm-jp/llm-jp-3-3.7b-instruct

### method
stage: sft
do_train: true
finetuning_type: full
deepspeed: examples/deepspeed/ds_z3_config.json
enable_liger_kernel: true

### dataset
dataset: longwriter
template: alpaca_ja
cutoff_len: 32768
overwrite_cache: true
preprocessing_num_workers: 16

### output
output_dir: saves/llm_jp/full/sft
logging_steps: 1
save_steps: 500
plot_loss: true
overwrite_output_dir: true

### train
per_device_train_batch_size: 2
gradient_accumulation_steps: 1
learning_rate: 1.0e-5
optim: adamw_bnb_8bit
num_train_epochs: 2.0
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: true
ddp_timeout: 180000000

### eval
val_size: 0.01
per_device_eval_batch_size: 1
eval_strategy: steps
eval_steps: 500

### logging
report_to: wandb