{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.45,
  "eval_steps": 500,
  "global_step": 98,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 0.25416667461395265,
      "completions/clipped_ratio": 0.99375,
      "completions/max_length": 128.0,
      "completions/max_terminated_length": 9.8,
      "completions/mean_length": 127.45416717529297,
      "completions/mean_terminated_length": 8.133333587646485,
      "completions/min_length": 107.8,
      "completions/min_terminated_length": 5.4,
      "epoch": 0.125,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": NaN,
      "learning_rate": 6.857142857142857e-06,
      "loss": 0.0,
      "num_tokens": 245160.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/wrapper/mean": 0.0,
      "rewards/wrapper/std": 0.0,
      "step": 5
    },
    {
      "completion_length": 0.20208334922790527,
      "completions/clipped_ratio": 0.9979166666666666,
      "completions/max_length": 128.0,
      "completions/max_terminated_length": 19.4,
      "completions/mean_length": 127.93541717529297,
      "completions/mean_terminated_length": 19.4,
      "completions/min_length": 121.8,
      "completions/min_terminated_length": 19.4,
      "epoch": 0.25,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": NaN,
      "learning_rate": 1.5428571428571428e-05,
      "loss": 0.0,
      "num_tokens": 490341.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/wrapper/mean": 0.0,
      "rewards/wrapper/std": 0.0,
      "step": 10
    },
    {
      "completion_length": 0.23750000800937415,
      "completions/clipped_ratio": 0.9958333333333333,
      "completions/max_length": 128.0,
      "completions/max_terminated_length": 22.8,
      "completions/mean_length": 127.70416717529297,
      "completions/mean_terminated_length": 22.8,
      "completions/min_length": 99.6,
      "completions/min_terminated_length": 22.8,
      "epoch": 0.375,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": NaN,
      "learning_rate": 2.4e-05,
      "loss": 0.0,
      "num_tokens": 735705.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/wrapper/mean": 0.0,
      "rewards/wrapper/std": 0.0,
      "step": 15
    },
    {
      "completion_length": 0.15208333730697632,
      "completions/clipped_ratio": 0.9979166666666668,
      "completions/max_length": 128.0,
      "completions/max_terminated_length": 14.6,
      "completions/mean_length": 127.88541717529297,
      "completions/mean_terminated_length": 14.6,
      "completions/min_length": 117.0,
      "completions/min_terminated_length": 14.6,
      "epoch": 0.5,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": NaN,
      "learning_rate": 3.2571428571428566e-05,
      "loss": 0.0,
      "num_tokens": 981030.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/wrapper/mean": 0.0,
      "rewards/wrapper/std": 0.0,
      "step": 20
    },
    {
      "completion_length": 0.13541666883975267,
      "completions/clipped_ratio": 0.9916666666666668,
      "completions/max_length": 128.0,
      "completions/max_terminated_length": 13.0,
      "completions/mean_length": 127.06875152587891,
      "completions/mean_terminated_length": 13.0,
      "completions/min_length": 38.6,
      "completions/min_terminated_length": 13.0,
      "epoch": 0.625,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": NaN,
      "learning_rate": 4.1142857142857146e-05,
      "loss": 0.0,
      "num_tokens": 1226233.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/wrapper/mean": 0.0,
      "rewards/wrapper/std": 0.0,
      "step": 25
    },
    {
      "completion_length": 0.17291667070239783,
      "completions/clipped_ratio": 0.9958333333333333,
      "completions/max_length": 128.0,
      "completions/max_terminated_length": 16.6,
      "completions/mean_length": 127.63958435058593,
      "completions/mean_terminated_length": 16.6,
      "completions/min_length": 93.4,
      "completions/min_terminated_length": 16.6,
      "epoch": 0.75,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": NaN,
      "learning_rate": 4.971428571428572e-05,
      "loss": 0.0,
      "num_tokens": 1471656.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/wrapper/mean": 0.0,
      "rewards/wrapper/std": 0.0,
      "step": 30
    },
    {
      "completion_length": 0.1708333373069763,
      "completions/clipped_ratio": 0.9979166666666668,
      "completions/max_length": 128.0,
      "completions/max_terminated_length": 16.4,
      "completions/mean_length": 127.90416717529297,
      "completions/mean_terminated_length": 16.4,
      "completions/min_length": 118.8,
      "completions/min_terminated_length": 16.4,
      "epoch": 0.875,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": NaN,
      "learning_rate": 5.8285714285714284e-05,
      "loss": 0.0,
      "num_tokens": 1716970.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/wrapper/mean": 0.0,
      "rewards/wrapper/std": 0.0,
      "step": 35
    },
    {
      "completion_length": 0.0,
      "completions/clipped_ratio": 1.0,
      "completions/max_length": 128.0,
      "completions/max_terminated_length": 0.0,
      "completions/mean_length": 128.0,
      "completions/mean_terminated_length": 0.0,
      "completions/min_length": 128.0,
      "completions/min_terminated_length": 0.0,
      "epoch": 1.0,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": NaN,
      "learning_rate": 5.975456118835079e-05,
      "loss": 0.0,
      "num_tokens": 1962424.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/wrapper/mean": 0.0,
      "rewards/wrapper/std": 0.0,
      "step": 40
    },
    {
      "completion_length": 0.10625,
      "completions/clipped_ratio": 0.9979166666666668,
      "completions/max_length": 128.0,
      "completions/max_terminated_length": 10.2,
      "completions/mean_length": 127.83958435058594,
      "completions/mean_terminated_length": 10.2,
      "completions/min_length": 112.6,
      "completions/min_terminated_length": 10.2,
      "epoch": 1.125,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": NaN,
      "learning_rate": 5.876663613361844e-05,
      "loss": 0.0,
      "num_tokens": 2207607.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/wrapper/mean": 0.0,
      "rewards/wrapper/std": 0.0,
      "step": 45
    },
    {
      "completion_length": 0.01666666716337204,
      "completions/clipped_ratio": 0.9979166666666668,
      "completions/max_length": 128.0,
      "completions/max_terminated_length": 1.6,
      "completions/mean_length": 127.75,
      "completions/mean_terminated_length": 1.6,
      "completions/min_length": 104.0,
      "completions/min_terminated_length": 1.6,
      "epoch": 1.25,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": NaN,
      "learning_rate": 5.705450129187439e-05,
      "loss": 0.0,
      "num_tokens": 2453161.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/wrapper/mean": 0.0,
      "rewards/wrapper/std": 0.0,
      "step": 50
    },
    {
      "completion_length": 0.06041666865348816,
      "completions/clipped_ratio": 0.9979166666666668,
      "completions/max_length": 128.0,
      "completions/max_terminated_length": 5.8,
      "completions/mean_length": 127.79375,
      "completions/mean_terminated_length": 5.8,
      "completions/min_length": 108.2,
      "completions/min_terminated_length": 5.8,
      "epoch": 1.375,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": NaN,
      "learning_rate": 5.467646136167482e-05,
      "loss": 0.0,
      "num_tokens": 2698744.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/wrapper/mean": 0.0,
      "rewards/wrapper/std": 0.0,
      "step": 55
    },
    {
      "completion_length": 0.10625,
      "completions/clipped_ratio": 0.9979166666666668,
      "completions/max_length": 128.0,
      "completions/max_terminated_length": 10.2,
      "completions/mean_length": 127.83958435058594,
      "completions/mean_terminated_length": 10.2,
      "completions/min_length": 112.6,
      "completions/min_terminated_length": 10.2,
      "epoch": 1.5,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": NaN,
      "learning_rate": 5.1713497640698144e-05,
      "loss": 0.0,
      "num_tokens": 2943913.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/wrapper/mean": 0.0,
      "rewards/wrapper/std": 0.0,
      "step": 60
    },
    {
      "completion_length": 0.06875000204890966,
      "completions/clipped_ratio": 0.9958333333333333,
      "completions/max_length": 128.0,
      "completions/max_terminated_length": 6.6,
      "completions/mean_length": 127.53541717529296,
      "completions/mean_terminated_length": 6.6,
      "completions/min_length": 83.4,
      "completions/min_terminated_length": 6.6,
      "epoch": 1.625,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": NaN,
      "learning_rate": 4.826651030477895e-05,
      "loss": 0.0,
      "num_tokens": 3188874.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/wrapper/mean": 0.0,
      "rewards/wrapper/std": 0.0,
      "step": 65
    },
    {
      "completion_length": 0.0,
      "completions/clipped_ratio": 1.0,
      "completions/max_length": 128.0,
      "completions/max_terminated_length": 0.0,
      "completions/mean_length": 128.0,
      "completions/mean_terminated_length": 0.0,
      "completions/min_length": 128.0,
      "completions/min_terminated_length": 0.0,
      "epoch": 1.75,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": NaN,
      "learning_rate": 4.445288237343632e-05,
      "loss": 0.0,
      "num_tokens": 3434112.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/wrapper/mean": 0.0,
      "rewards/wrapper/std": 0.0,
      "step": 70
    },
    {
      "completion_length": 0.16875000800937415,
      "completions/clipped_ratio": 0.9958333333333333,
      "completions/max_length": 128.0,
      "completions/max_terminated_length": 16.2,
      "completions/mean_length": 127.63541717529297,
      "completions/mean_terminated_length": 16.2,
      "completions/min_length": 93.0,
      "completions/min_terminated_length": 16.2,
      "epoch": 1.875,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": NaN,
      "learning_rate": 4.0402482371929574e-05,
      "loss": 0.0,
      "num_tokens": 3679205.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/wrapper/mean": 0.0,
      "rewards/wrapper/std": 0.0,
      "step": 75
    },
    {
      "completion_length": 0.45625,
      "completions/clipped_ratio": 0.9958333333333333,
      "completions/max_length": 128.0,
      "completions/max_terminated_length": 23.2,
      "completions/mean_length": 127.92291717529297,
      "completions/mean_terminated_length": 21.9,
      "completions/min_length": 123.0,
      "completions/min_terminated_length": 20.6,
      "epoch": 2.0,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": NaN,
      "learning_rate": 3.6253241814390675e-05,
      "loss": 0.0,
      "num_tokens": 3924684.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/wrapper/mean": 0.0,
      "rewards/wrapper/std": 0.0,
      "step": 80
    },
    {
      "completion_length": 0.22083334922790526,
      "completions/clipped_ratio": 0.9979166666666666,
      "completions/max_length": 128.0,
      "completions/max_terminated_length": 21.2,
      "completions/mean_length": 127.95416717529297,
      "completions/mean_terminated_length": 21.2,
      "completions/min_length": 123.6,
      "completions/min_terminated_length": 21.2,
      "epoch": 2.125,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": NaN,
      "learning_rate": 3.2146458111541086e-05,
      "loss": 0.0,
      "num_tokens": 4169802.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/wrapper/mean": 0.0,
      "rewards/wrapper/std": 0.0,
      "step": 85
    },
    {
      "completion_length": 0.14166667461395263,
      "completions/clipped_ratio": 0.9979166666666668,
      "completions/max_length": 128.0,
      "completions/max_terminated_length": 13.6,
      "completions/mean_length": 127.875,
      "completions/mean_terminated_length": 13.6,
      "completions/min_length": 116.0,
      "completions/min_terminated_length": 13.6,
      "epoch": 2.25,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": NaN,
      "learning_rate": 2.8221982856837173e-05,
      "loss": 0.0,
      "num_tokens": 4415206.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/wrapper/mean": 0.0,
      "rewards/wrapper/std": 0.0,
      "step": 90
    },
    {
      "completion_length": 0.0,
      "completions/clipped_ratio": 1.0,
      "completions/max_length": 128.0,
      "completions/max_terminated_length": 0.0,
      "completions/mean_length": 128.0,
      "completions/mean_terminated_length": 0.0,
      "completions/min_length": 128.0,
      "completions/min_terminated_length": 0.0,
      "epoch": 2.375,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": NaN,
      "learning_rate": 2.4613459348188633e-05,
      "loss": 0.0,
      "num_tokens": 4660218.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/wrapper/mean": 0.0,
      "rewards/wrapper/std": 0.0,
      "step": 95
    }
  ],
  "logging_steps": 5,
  "max_steps": 120,
  "num_input_tokens_seen": 4807273,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 24,
  "trial_name": null,
  "trial_params": null
}