basil-k-aji-dev 9c088dd3a5 [fix] route RL trainer forward through DDP so gradients all-reduce ... train_grpo.py, train_ppo.py and train_agent.py wrap the policy in DistributedDataParallel but run the loss-bearing forward through .module, bypassing the wrapper. DDP arms its gradient all-reduce hooks inside DistributedDataParallel.forward(), so calling .module directly means backward() performs no all-reduce: every rank steps on purely local gradients and the replicas silently diverge. Only rank 0 is saved, so multi-GPU RL training quietly degrades to single-GPU training on 1/N of the data with no error. The supervised trainers are unaffected; they already call the wrapped module. no_grad uses of .module (rollout generation, checkpoint saving) are left untouched, where unwrapping is correct. Single-GPU behaviour is unchanged: with no process group, model is the bare module and these calls are identical to before.		2026-09-14 14:54:07 +05:30
..
rollout_engine.py	[fix] keep agent rollout token-aligned #850	2026-09-10 11:44:05 +08:00
train_agent.py	[fix] route RL trainer forward through DDP so gradients all-reduce	2026-09-14 14:54:07 +05:30
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	[update] remove expert args	2026-09-04 22:16:38 +08:00
train_grpo.py	[fix] route RL trainer forward through DDP so gradients all-reduce	2026-09-14 14:54:07 +05:30
train_lora.py	[fix] ddp exit hang	2026-06-01 17:50:39 +08:00
train_ppo.py	[fix] route RL trainer forward through DDP so gradients all-reduce	2026-09-14 14:54:07 +05:30
train_pretrain.py	[update] remove expert args	2026-09-04 22:16:38 +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