mirror of
https://github.com/wassname/SimPO.git
synced 2026-06-27 16:43:59 +08:00
Yu Meng
48 lines
1.4 KiB
YAML
48 lines
1.4 KiB
YAML
# Model arguments
|
|
model_name_or_path: meta-llama/Meta-Llama-3-8B
|
|
model_revision: main
|
|
torch_dtype: bfloat16
|
|
attn_implementation: flash_attention_2
|
|
|
|
# Data training arguments
|
|
chat_template: "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}"
|
|
dataset_mixer:
|
|
HuggingFaceH4/ultrachat_200k: 1.0
|
|
dataset_splits:
|
|
- train_sft
|
|
- test_sft
|
|
preprocessing_num_workers: 12
|
|
|
|
# SFT trainer config
|
|
bf16: true
|
|
do_eval: true
|
|
evaluation_strategy: steps
|
|
eval_steps: 200
|
|
gradient_accumulation_steps: 4
|
|
gradient_checkpointing: true
|
|
gradient_checkpointing_kwargs:
|
|
use_reentrant: False
|
|
hub_model_id: zephyr-7b-sft-full
|
|
hub_strategy: every_save
|
|
learning_rate: 2.0e-05
|
|
log_level: info
|
|
logging_steps: 5
|
|
logging_strategy: steps
|
|
lr_scheduler_type: cosine
|
|
max_seq_length: 2048
|
|
max_steps: -1
|
|
num_train_epochs: 1
|
|
output_dir: /scratch/gpfs/DANQIC/ym0081/checkpoints_new/llama-3-8b-sft
|
|
run_name: llama-3-8b-sft
|
|
overwrite_output_dir: true
|
|
per_device_eval_batch_size: 8
|
|
per_device_train_batch_size: 8
|
|
push_to_hub: false
|
|
remove_unused_columns: true
|
|
report_to:
|
|
- wandb
|
|
save_strategy: "steps"
|
|
save_steps: 1000000
|
|
save_total_limit: 1
|
|
seed: 42
|
|
warmup_ratio: 0.1 |