[2026-10-17 15:53:16.726 launcher] common.py:290 - EXEC: export PYTHONUNBUFFERED=1 && ray start --head --node-ip-address 127.0.0.1 --num-gpus 1 --disable-usage-stats
(CommandActor pid=2546) [2026-10-17 15:54:38] Load weight end. elapsed=5.85 s, type=Qwen3ForCausalLM, avail mem=94.82 GB, mem usage=1.40 GB.
(CommandActor pid=2546) [2026-10-17 15:54:40] KV Cache is allocated. dtype: torch.bfloat16, #tokens: 345645, K size: 18.46 GB, V size: 18.46 GB
(RolloutExecutor pid=2545) [2026-10-17 15:56:15.547 rollout_executor] metrics.py:94 - perf 0: {'rollout/raw_reward_unfiltered': 0.62890625, 'rollout/num_training_samples': 256, 'rollout/episode_raw_reward': 0.62890625, 'rollout/episode_response_length/mean': 739.92578125, 'rollout/episode_response_length/median': 759.5, 'rollout/episode_response_length/max': 1024, 'rollout/episode_response_length/min': 259, 'rollout/episode_total_response_length/mean': 739.92578125, 'rollout/response_len/mean': 739.92578125, 'rollout/response_len/median': 759.5, 'rollout/response_len/max': 1024, 'rollout/response_len/min': 259, 'rollout/zero_std/count_1': 7, 'rollout/zero_std/count_0': 3, 'rollout/zero_std/all_zero_percentage': 0.09375, 'rollout/zero_std/all_one_percentage': 0.21875, 'rollout/prefix_cache_hit_rate': 0.24518696778970753, 'rollout/avg_cached_tokens_per_sample': 20.6953125, 'rollout/repetition_frac': 0.0, 'rollout/truncated_ratio': 0.3203125, 'rollout/weight_version/mean': 1.0, 'rollout/weight_version/median': 1.0, 'rollout/weight_version/max': 1, 'rollout/weight_version/min': 1, 'rollout/weight_version/mixed_version_ratio': 0.0, 'perf/rollout_time': 61.951833724975586, 'perf/tokens_per_gpu_per_sec': 3057.5527568869334, 'perf/longest_sample_tokens_per_sec': 16.52896998248462, 'perf/effective_tokens_per_gpu_per_sec': 3057.5527568869334, 'perf/longest_effective_sample_tokens_per_sec': 16.52896998248462}
(FSDPTrainRayActor pid=2551) [2026-10-17 15:56:48.271 actor_cell00000_rank00000] log_utils.py:125 - rollout 0: {'rollout/response_lengths': 739.92578125, 'rollout/rewards': -1.6298145055770874e-09, 'rollout/truncated': 0.3203125, 'rollout/rollout_log_probs': -0.42945602536201477, 'rollout/raw_reward': 0.62890625, 'rollout/total_lengths': 824.33203125, 'rollout/log_probs': -0.43026646971702576, 'rollout/entropy': 0.43224966526031494, 'rollout/advantages': 4.656612873077393e-10, 'rollout/returns': 4.656612873077393e-10}
(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}
(FSDPTrainRayActor pid=2551) [2026-10-17 15:58:15.688 actor_cell00000_rank00000] perf.py:56 - perf 0: {'perf/sleep_time': 2.1116080284118652, 'perf/update_weights_implementation_time': 0.2867567539215088, 'perf/finalize_and_resume_engines_time': 0.008184432983398438, 'perf/update_weights_time': 0.6647534370422363, 'perf/wake_up_time': 0.46197986602783203, 'perf/train_wait_time': 114.306077003479, 'perf/log_probs_time': 31.45381236076355, 'perf/actor_train_time': 87.41598510742188, 'perf/train_time': 118.98886632919312, 'perf/log_probs_tflops': 8.302134463722124, 'perf/actor_train_tflops': 8.96176297601111, 'perf/actor_train_tok_per_s': 2414.0779256868777, 'perf/step_time': 233.29494333267212, 'perf/wait_time_ratio': 0.48996380020325475}