obscura/minimind
1
0
Fork 0
mirror of https://github.com/jingyaogong/minimind.git synced 2026-09-01 17:29:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

[fix] sampler-ddp

Browse Source
This commit is contained in:
jingyaogong
2025-10-23 15:03:19 +08:00
parent fa7dff8291
commit 463044e92a
9 changed files with 9 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
trainer/train_distill_reason.py
+1
View File
@@ -213,4 +213,5 @@ if __name__ == "__main__":
iter_per_epoch = len(train_loader)
for epoch in range(args.epochs):
train_sampler and train_sampler.set_epoch(epoch)
train_epoch(epoch, wandb)
trainer/train_distillation.py
+1
View File
@@ -262,4 +262,5 @@ if __name__ == "__main__":
iter_per_epoch = len(train_loader)
for epoch in range(args.epochs):
train_sampler and train_sampler.set_epoch(epoch)
train_epoch(epoch, wandb)
trainer/train_dpo.py
+1
View File
@@ -245,4 +245,5 @@ if __name__ == "__main__":
iter_per_epoch = len(train_loader)
for epoch in range(args.epochs):
train_sampler and train_sampler.set_epoch(epoch)
train_epoch(epoch, wandb)
trainer/train_full_sft.py
+1
View File
@@ -199,4 +199,5 @@ if __name__ == "__main__":
iter_per_epoch = len(train_loader)
for epoch in range(args.epochs):
train_sampler and train_sampler.set_epoch(epoch)
train_epoch(epoch, wandb)
trainer/train_grpo.py
+1
View File
@@ -313,4 +313,5 @@ if __name__ == "__main__":
model = DistributedDataParallel(model, device_ids=[ddp_local_rank])
for epoch in range(args.epochs):
train_sampler and train_sampler.set_epoch(epoch)
grpo_train_epoch(epoch, wandb)
trainer/train_lora.py
+1
View File
@@ -205,4 +205,5 @@ if __name__ == "__main__":
iter_per_epoch = len(train_loader)
for epoch in range(args.epochs):
train_sampler and train_sampler.set_epoch(epoch)
train_epoch(epoch, wandb)
trainer/train_ppo.py
+1
View File
@@ -367,6 +367,7 @@ if __name__ == "__main__":
old_actor_model.to(args.device)
for epoch in range(args.epochs):
train_sampler and train_sampler.set_epoch(epoch)
ppo_train_epoch(epoch, wandb, old_actor_model, ref_model, actor_scheduler, critic_scheduler)
if ddp:
trainer/train_pretrain.py
+1
View File
@@ -197,4 +197,5 @@ if __name__ == "__main__":
iter_per_epoch = len(train_loader)
for epoch in range(args.epochs):
train_sampler and train_sampler.set_epoch(epoch)
train_epoch(epoch, wandb)
trainer/train_spo.py
+1
View File
@@ -364,4 +364,5 @@ if __name__ == "__main__":
value_tracker = AutoAdaptiveValueTracker(rho_mode='kl', rho_const=0.9, D_half=0.06, clip_lower=0.5, clip_upper=0.96)
for epoch in range(args.epochs):
train_sampler and train_sampler.set_epoch(epoch)
spo_train_epoch(epoch, wandb, value_tracker)