ViperEkura 9bcd696580 fix: token-level ratio and prompt masking in GRPO strategy ... - Mask prompt tokens to 0 so their logprobs excluded from ratio/KL - Switch to token-level ratio + PPO clipping via reduction='none' - Slice response token logprobs from full sequence output - Replace k3 KL estimator with non-negative k1 estimator - Fix epsilon from finifo.eps (~1e-38) to 1e-8 - Remove unused 'reduction' param from GRPOStrategy.__init__ - Clarify offline batch semantics in docstring - Add 11 unit tests for masking, advantage, KL, sync, clipping - Sync training.md and architecture.md docs		2026-07-12 21:24:09 +08:00
..
__init__.py	chore : 升级 torch 2.11.0+cu128，移除自定义 Muon，修复 gloo device_id	2026-06-27 16:10:37 +08:00
metric_util.py	refactor : grad_norm 指标简化，clip_grad_norm 移至 executor	2026-06-30 14:59:43 +08:00
schedule.py	fix: scheduler division-by-zero, loss_mask bool	2026-07-03 22:04:55 +08:00
strategy.py	fix: token-level ratio and prompt masking in GRPO strategy	2026-07-12 21:24:09 +08:00
train_callback.py	fix: set tqdm postfix before update so first step shows metrics	2026-07-07 00:14:13 +08:00
train_context.py	refactor : replace iteration with consumed_samples	2026-06-30 18:42:42 +08:00
trainer.py	refactor: merge validation into MetricCallback, simplify progress bar to optimizer steps	2026-07-03 21:43:08 +08:00