dyhuachi bf3878ace8 [fix] Refactor get_lr function to include min_lr calculation ... 这里的退火算法会让参数里的lr的起始值变成原来lr的1.1倍，作出如下修改		2025-12-06 17:09:51 +08:00
..
train_distill_reason.py	[fix] cuda memory #559	2025-12-01 16:17:43 +08:00
train_distillation.py	[fix] cuda memory #559	2025-12-01 16:17:43 +08:00
train_dpo.py	[fix] cuda memory #559	2025-12-01 16:17:43 +08:00
train_full_sft.py	[fix] cuda memory #559	2025-12-01 16:17:43 +08:00
train_grpo.py	[fix] cuda memory #559	2025-12-01 16:17:43 +08:00
train_lora.py	[feat] release memory	2025-11-27 19:39:49 +08:00
train_ppo.py	[fix] cuda memory #559	2025-12-01 16:17:43 +08:00
train_pretrain.py	[fix] cuda memory #559	2025-12-01 16:17:43 +08:00
train_spo.py	[fix] cuda memory #559	2025-12-01 16:17:43 +08:00
trainer_utils.py	[fix] Refactor get_lr function to include min_lr calculation	2025-12-06 17:09:51 +08:00