423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 11:50:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

support SimPO #3900

Browse Source
This commit is contained in:
hiyouga
2024-05-26 23:46:33 +08:00
parent 063f91cc80
commit cb63b32986
19 changed files with 145 additions and 339 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llamafactory/train/kto/trainer.py
View File

@@ -50,10 +50,10 @@ class CustomKTOTrainer(KTOTrainer):
self._stored_metrics = defaultdict(lambda: defaultdict(list))
# kto hyperparams
self.beta = finetuning_args.kto_beta
self.beta = finetuning_args.pref_beta
self.desirable_weight = finetuning_args.kto_chosen_weight
self.undesirable_weight = finetuning_args.kto_rejected_weight
self.ftx_gamma = finetuning_args.kto_ftx
self.ftx_gamma = finetuning_args.pref_ftx
Trainer.__init__(self, model=model, **kwargs)
if not hasattr(self, "accelerator"):