jingyaogong f659b55761 [fix] residual step order

2026-09-23 00:07:30 +08:00

..

rollout_engine.py

[fix] keep agent rollout token-aligned #850

2026-09-10 11:44:05 +08:00

train_agent.py

fix: update residual gradients before saving final checkpoints

2026-09-21 23:24:55 -07:00

train_distillation.py

fix: update residual gradients before saving final checkpoints

2026-09-21 23:24:55 -07:00

train_dpo.py

fix: update residual gradients before saving final checkpoints

2026-09-21 23:24:55 -07:00

train_full_sft.py

fix: update residual gradients before saving final checkpoints

2026-09-21 23:24:55 -07:00

train_grpo.py

[fix] residual step order

2026-09-23 00:07:30 +08:00

train_lora.py

fix: update residual gradients before saving final checkpoints

2026-09-21 23:24:55 -07:00

train_ppo.py

[update] trim redundant comments

2026-09-20 20:33:40 +08:00

train_pretrain.py

fix: update residual gradients before saving final checkpoints

2026-09-21 23:24:55 -07:00

train_tokenizer.py

[fix] train_tokenizer 读预训练语料时产出 0 条文本，静默训出空词表

2026-09-20 10:33:51 +08:00

trainer_utils.py

[update] simplify safe math eval

2026-09-14 23:55:32 +08:00