mirror of
https://github.com/RYDE-WORK/MiniCPM.git
synced 2026-01-19 12:53:36 +08:00
42 lines
778 B
YAML
42 lines
778 B
YAML
### model
|
|
model_name_or_path: /root/ld/ld_model_pretrained/miniCPM-bf16/
|
|
|
|
### method
|
|
stage: sft
|
|
do_train: true
|
|
finetuning_type: full
|
|
|
|
### ddp
|
|
ddp_timeout: 180000000
|
|
deepspeed: examples/deepspeed/ds_z2_config.json
|
|
|
|
### dataset
|
|
dataset: glaive_toolcall_en,glaive_toolcall_zh
|
|
template: cpm
|
|
cutoff_len: 1800
|
|
max_samples: 500000
|
|
overwrite_cache: true
|
|
preprocessing_num_workers: 16
|
|
|
|
### output
|
|
output_dir: saves/minicpm/fuction_call
|
|
logging_steps: 10
|
|
save_strategy: epoch
|
|
plot_loss: true
|
|
overwrite_output_dir: true
|
|
|
|
### train
|
|
per_device_train_batch_size: 2
|
|
gradient_accumulation_steps: 4
|
|
learning_rate: 0.0001
|
|
num_train_epochs: 3.0
|
|
lr_scheduler_type: cosine
|
|
warmup_steps: 0.1
|
|
bf16: true
|
|
|
|
### eval
|
|
val_size: 0.1
|
|
per_device_eval_batch_size: 4
|
|
evaluation_strategy: steps
|
|
eval_steps: 500
|