From 6bac0780bc441d581e8cbfc52da5886f15b451e5 Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Mon, 17 Feb 2025 22:30:13 -0800 Subject: [PATCH] Update rl_replacements.py --- unsloth/models/rl_replacements.py | 1 + 1 file changed, 1 insertion(+) diff --git a/unsloth/models/rl_replacements.py b/unsloth/models/rl_replacements.py index decaf32096..3b23e8bacf 100644 --- a/unsloth/models/rl_replacements.py +++ b/unsloth/models/rl_replacements.py @@ -239,6 +239,7 @@ def grpo_trainer_compute_loss(function_name, function): ref_per_token_logps, per_token_logps, input_ids, completion_mask, self.beta, advantages, bsz, ) else: + print(self.args.unsloth_num_chunks, end = ",") loss, completion_length, mean_kl = grpo_accumulated_loss( self, _input_ids, logits_to_keep, completion_mask, advantages, n_chunks = self.args.unsloth_num_chunks,