zhangyiss/mlx-examples
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx-examples.git synced 2025-07-19 17:41:11 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

print func name

Browse Source
This commit is contained in:
Goekdeniz-Guelmez 2025-02-03 19:47:40 +01:00
parent 40bca770ae
commit 06f9c29c94
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
llms/mlx_lm/tuner/grpo_trainer.py
View File

@ -309,13 +309,14 @@ def grpo_loss(
# Collect reward metrics
reward_metrics = {}
for i, reward_func in enumerate(reward_funcs):
func_name = reward_func.__name__
func_rewards = mx.array(reward_func(
prompts=expanded_prompts,
completions=all_completion_texts,
answer=expanded_answers
))
reward_metrics[f'reward_func_{i}_mean'] = mx.mean(func_rewards)
reward_metrics[f'reward_func_{i}_std'] = mx.std(func_rewards)
reward_metrics[f'{func_name}_mean'] = mx.mean(func_rewards)
reward_metrics[f'{func_name}_std'] = mx.std(func_rewards)
# Clean up
del all_completions