### model
model_name_or_path: /root/ld/ld_model_pretrain/MiniCPM-1B-sft-bf16/

### method
stage: kto
do_train: true
finetuning_type: full
kto_ftx: 0.1

### ddp
ddp_timeout: 180000000
deepspeed: examples/deepspeed/ds_z2_config.json

### dataset
dataset: kto_harmless
template: cpm
cutoff_len: 1200
max_samples: 500000
overwrite_cache: true
preprocessing_num_workers: 16

### output
output_dir: saves/minicpm/kto
logging_steps: 10
save_steps: 500
plot_loss: true
overwrite_output_dir: true

### train
per_device_train_batch_size: 4
gradient_accumulation_steps: 4
learning_rate: 0.000005
num_train_epochs: 1.0
lr_scheduler_type: cosine
warmup_steps: 0.1
bf16: true

### eval
val_size: 0.1
per_device_eval_batch_size: 16
evaluation_strategy: steps
eval_steps: 500