{
  "model": "Qwen/Qwen3-0.6B",
  "trainer": "async-grpo",
  "experiment": "first-command",
  "env_url": "http://ip-26-0-168-52.ec2.internal:8000",
  "vllm_server_url": "http://ip-26-0-168-95.ec2.internal:8000",
  "hub_model_id": "burtenshaw/terminus-pi-trl-async-grpo",
  "trackio_project": "terminus-pi-trl",
  "report_to": "trackio",
  "push_to_hub": true,
  "run_name": "terminus-async-grpo-22179048",
  "max_inflight_tasks": 2,
  "output_dir": "/fsx/benjamin_burtenshaw/OpenEnv-codex-terminus-pi-trl-space/examples/end_to_end/tbench2_pi_trl/logs/output-22179048",
  "train_result": {
    "train_runtime": 189.2986,
    "train_samples_per_second": 0.127,
    "train_steps_per_second": 0.063,
    "total_flos": 69970898190336.0,
    "train_loss": 0.0,
    "epoch": 1.0
  },
  "log_history": [
    {
      "loss": 0.0,
      "grad_norm": 0.0,
      "learning_rate": 5.833333333333334e-07,
      "ratio": 0.9964810609817505,
      "kl": 7.434934377670288e-05,
      "entropy": 0.033603236079216,
      "clip_ratio": 0.0,
      "reward": 1.0,
      "reward_std": 0.0,
      "rewards/terminus_reward": 1.0,
      "tools/call_frequency": 4.0,
      "tools/failure_frequency": 0.0,
      "generation_tok_per_s": 60.3897705078125,
      "scoring_time_ms": 117.16629791259766,
      "wait_scoring_ms": 68.45825958251953,
      "buffer_qsize": 6.0,
      "queue_wait_time_s": 4.076957702636719e-05,
      "completions/mean_length": 55.0,
      "training_tok/s": 6.806692854321114,
      "forward_time_s": 0.07218480110168457,
      "train_seq_len": 1104.0,
      "weight_sync_time_s": 0.13250494003295898,
      "epoch": 0.5,
      "step": 6
    },
    {
      "loss": 0.0,
      "grad_norm": 0.0,
      "learning_rate": 5e-07,
      "ratio": 0.9964810609817505,
      "kl": 7.434934377670288e-05,
      "entropy": 0.033603236079216,
      "clip_ratio": 0.0,
      "reward": 1.0,
      "reward_std": 0.0,
      "rewards/terminus_reward": 1.0,
      "tools/call_frequency": 4.0,
      "tools/failure_frequency": 0.0,
      "generation_tok_per_s": 63.50257110595703,
      "scoring_time_ms": 112.0641860961914,
      "wait_scoring_ms": 65.2970199584961,
      "buffer_qsize": 8.0,
      "queue_wait_time_s": 4.649162292480469e-05,
      "completions/mean_length": 55.0,
      "training_tok/s": 7.36189168170205,
      "forward_time_s": 0.0719459056854248,
      "train_seq_len": 1104.0,
      "weight_sync_time_s": 0.13101506233215332,
      "epoch": 0.5833333333333334,
      "step": 7
    },
    {
      "loss": 0.0,
      "grad_norm": 0.0,
      "learning_rate": 4.1666666666666667e-07,
      "ratio": 0.9969766139984131,
      "kl": 6.689117435598746e-05,
      "entropy": 0.03523017838597298,
      "clip_ratio": 0.0,
      "reward": 1.0,
      "reward_std": 0.0,
      "rewards/terminus_reward": 1.0,
      "tools/call_frequency": 4.0,
      "tools/failure_frequency": 0.0,
      "generation_tok_per_s": 74.39502716064453,
      "scoring_time_ms": 69.75615692138672,
      "wait_scoring_ms": 69.68431854248047,
      "buffer_qsize": 30.0,
      "queue_wait_time_s": 1.728534698486328e-05,
      "completions/mean_length": 54.0,
      "training_tok/s": 7.294061649219052,
      "forward_time_s": 0.06849026679992676,
      "train_seq_len": 1102.0,
      "weight_sync_time_s": 0.14867115020751953,
      "epoch": 0.6666666666666666,
      "step": 8
    },
    {
      "loss": 0.0,
      "grad_norm": 0.0,
      "learning_rate": 3.333333333333333e-07,
      "ratio": 0.9962551593780518,
      "kl": 9.892778325593099e-05,
      "entropy": 0.046233903616666794,
      "clip_ratio": 0.0,
      "reward": 1.0,
      "reward_std": 0.0,
      "rewards/terminus_reward": 1.0,
      "tools/call_frequency": 4.0,
      "tools/failure_frequency": 0.0,
      "generation_tok_per_s": 75.64350891113281,
      "scoring_time_ms": 209.5857391357422,
      "wait_scoring_ms": 63.70707702636719,
      "buffer_qsize": 52.0,
      "queue_wait_time_s": 1.7404556274414062e-05,
      "completions/mean_length": 54.5,
      "training_tok/s": 7.281059343739894,
      "forward_time_s": 0.07220792770385742,
      "train_seq_len": 1103.0,
      "weight_sync_time_s": 0.13945603370666504,
      "epoch": 0.75,
      "step": 9
    },
    {
      "loss": 0.0,
      "grad_norm": 0.0,
      "learning_rate": 2.5e-07,
      "ratio": 0.9962551593780518,
      "kl": 9.892778325593099e-05,
      "entropy": 0.046233903616666794,
      "clip_ratio": 0.0,
      "reward": 1.0,
      "reward_std": 0.0,
      "rewards/terminus_reward": 1.0,
      "tools/call_frequency": 4.0,
      "tools/failure_frequency": 0.0,
      "generation_tok_per_s": 76.56906127929688,
      "scoring_time_ms": 236.5457305908203,
      "wait_scoring_ms": 75.78178405761719,
      "buffer_qsize": 72.0,
      "queue_wait_time_s": 2.372264862060547e-05,
      "completions/mean_length": 54.5,
      "training_tok/s": 7.482828130727307,
      "forward_time_s": 0.07097864151000977,
      "train_seq_len": 1103.0,
      "weight_sync_time_s": 0.13311219215393066,
      "epoch": 0.8333333333333334,
      "step": 10
    },
    {
      "loss": 0.0,
      "grad_norm": 0.0,
      "learning_rate": 1.6666666666666665e-07,
      "ratio": 0.9964330792427063,
      "kl": 7.718314009252936e-05,
      "entropy": 0.033603236079216,
      "clip_ratio": 0.0,
      "reward": 1.0,
      "reward_std": 0.0,
      "rewards/terminus_reward": 1.0,
      "tools/call_frequency": 4.0,
      "tools/failure_frequency": 0.0,
      "generation_tok_per_s": 77.19235229492188,
      "scoring_time_ms": 125.87603759765625,
      "wait_scoring_ms": 60.385467529296875,
      "buffer_qsize": 90.0,
      "queue_wait_time_s": 2.276897430419922e-05,
      "completions/mean_length": 55.0,
      "training_tok/s": 7.519044330838157,
      "forward_time_s": 0.07587862014770508,
      "train_seq_len": 1104.0,
      "weight_sync_time_s": 0.15876269340515137,
      "epoch": 0.9166666666666666,
      "step": 11
    },
    {
      "loss": 0.0,
      "grad_norm": 0.0,
      "learning_rate": 8.333333333333333e-08,
      "ratio": 0.9964810609817505,
      "kl": 7.434934377670288e-05,
      "entropy": 0.033603236079216,
      "clip_ratio": 0.0,
      "reward": 1.0,
      "reward_std": 0.0,
      "rewards/terminus_reward": 1.0,
      "tools/call_frequency": 4.0,
      "tools/failure_frequency": 0.0,
      "generation_tok_per_s": 77.44713592529297,
      "scoring_time_ms": 170.81890869140625,
      "wait_scoring_ms": 62.718727111816406,
      "buffer_qsize": 112.0,
      "queue_wait_time_s": 2.2172927856445312e-05,
      "completions/mean_length": 55.0,
      "training_tok/s": 7.1332620460814224,
      "forward_time_s": 0.07349634170532227,
      "train_seq_len": 1104.0,
      "weight_sync_time_s": 0.13324546813964844,
      "epoch": 1.0,
      "step": 12
    },
    {
      "train_runtime": 189.2986,
      "train_samples_per_second": 0.127,
      "train_steps_per_second": 0.063,
      "total_flos": 69970898190336.0,
      "train_loss": 0.0,
      "epoch": 1.0,
      "step": 12
    }
  ]
}