title: the step 0 line of the trainer
source: manuals/miles-101/capture/gpu/out-gb10/plain-first-step.log
lines: 6-6
lang: text
note: Read the loss, the clip fraction, the ppo_kl, the gap, the KL and the gradient norm.
---
(FSDPTrainRayActor pid=2551) [2026-10-17 15:58:15.687 actor_cell00000_rank00000] log_utils.py:554 - step 0: {'train/loss': -4.656612873077393e-10, 'train/pg_loss': -4.656612873077393e-10, 'train/entropy_loss': 0.0, 'train/pg_clipfrac': 0.0, 'train/ppo_kl': 0.0, 'train/ess_ratio': 1.0, 'train/train_rollout_logprob_abs_diff': 0.015336457639932632, 'train/train_rollout_kl': 0.0006840902497060597, 'train/grad_norm': 0.5216571092605591, 'train/lr-pg_0': 1e-06, 'train/step': 0}
