neil.ge 9cb07dd1ec perf: enable fused AdamW in pretrain training ... Same fused AdamW optimization as the full SFT script, using the existing device_type variable so the CPU-only path is unaffected. Co-authored-by: TRAE CLI <traecli@bytedance.com>		2026-09-05 19:16:51 +08:00
..
rollout_engine.py	[fix] inference bug	2026-05-03 20:48:48 +08:00
train_agent.py	[fix] ddp exit hang	2026-06-01 17:50:39 +08:00
train_distillation.py	[fix] ddp exit hang	2026-06-01 17:50:39 +08:00
train_dpo.py	[fix] ddp exit hang	2026-06-01 17:50:39 +08:00
train_full_sft.py	perf: enable fused AdamW in full SFT training	2026-09-05 18:37:04 +08:00
train_grpo.py	[fix] ddp exit hang	2026-06-01 17:50:39 +08:00
train_lora.py	[fix] ddp exit hang	2026-06-01 17:50:39 +08:00
train_ppo.py	[refactor] PPO cleanup	2026-07-23 11:11:05 +08:00
train_pretrain.py	perf: enable fused AdamW in pretrain training	2026-09-05 19:16:51 +08:00
train_tokenizer.py	[update] minimind-3	2026-03-25 23:57:45 +08:00
trainer_utils.py	[update] minimind-3	2026-03-25 23:57:45 +08:00