{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 40,
  "global_step": 138,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0140625,
      "completions/max_length": 1536.0,
      "completions/max_terminated_length": 1497.0,
      "completions/mean_length": 308.80625,
      "completions/mean_terminated_length": 291.344287109375,
      "completions/min_length": 25.2,
      "completions/min_terminated_length": 25.2,
      "epoch": 0.07246376811594203,
      "grad_norm": 0.27501779794692993,
      "learning_rate": 5.714285714285714e-07,
      "loss": 0.0259,
      "num_tokens": 690620.0,
      "reward": 0.4875,
      "reward_std": 0.21356593072414398,
      "rewards/accuracy_reward": 0.0984375,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 0.8765625,
      "rewards/mean_confidence_reward": 0.0,
      "step": 5
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0109375,
      "completions/max_length": 1536.0,
      "completions/max_terminated_length": 1428.2,
      "completions/mean_length": 349.8296875,
      "completions/mean_terminated_length": 336.7182922363281,
      "completions/min_length": 33.8,
      "completions/min_terminated_length": 33.8,
      "epoch": 0.14492753623188406,
      "grad_norm": 0.14502760767936707,
      "learning_rate": 1e-06,
      "loss": 0.0129,
      "num_tokens": 1416263.0,
      "reward": 0.50703125,
      "reward_std": 0.16023073196411133,
      "rewards/accuracy_reward": 0.08125,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 0.9328125,
      "rewards/mean_confidence_reward": 0.0,
      "step": 10
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0125,
      "completions/max_length": 1402.8,
      "completions/max_terminated_length": 1264.2,
      "completions/mean_length": 338.2734375,
      "completions/mean_terminated_length": 323.1208435058594,
      "completions/min_length": 20.6,
      "completions/min_terminated_length": 20.6,
      "epoch": 0.21739130434782608,
      "grad_norm": 0.1979260891675949,
      "learning_rate": 1e-06,
      "loss": 0.0245,
      "num_tokens": 2155438.0,
      "reward": 0.53828125,
      "reward_std": 0.14823363423347474,
      "rewards/accuracy_reward": 0.1140625,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 0.9625,
      "rewards/mean_confidence_reward": 0.0,
      "step": 15
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.015625,
      "completions/max_length": 1446.6,
      "completions/max_terminated_length": 1301.8,
      "completions/mean_length": 291.4609375,
      "completions/mean_terminated_length": 271.94463500976565,
      "completions/min_length": 13.8,
      "completions/min_terminated_length": 13.8,
      "epoch": 0.2898550724637681,
      "grad_norm": 0.28274068236351013,
      "learning_rate": 1e-06,
      "loss": 0.0417,
      "num_tokens": 2854917.0,
      "reward": 0.58046875,
      "reward_std": 0.18900540471076965,
      "rewards/accuracy_reward": 0.1859375,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 0.975,
      "rewards/mean_confidence_reward": 0.0,
      "step": 20
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.009375,
      "completions/max_length": 1347.4,
      "completions/max_terminated_length": 1151.4,
      "completions/mean_length": 208.1703125,
      "completions/mean_terminated_length": 196.9493621826172,
      "completions/min_length": 13.4,
      "completions/min_terminated_length": 13.4,
      "epoch": 0.36231884057971014,
      "grad_norm": 149.1219482421875,
      "learning_rate": 1e-06,
      "loss": 0.0523,
      "num_tokens": 3492298.0,
      "reward": 0.60859375,
      "reward_std": 0.19136763513088226,
      "rewards/accuracy_reward": 0.2328125,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 0.984375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 25
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.003125,
      "completions/max_length": 1008.0,
      "completions/max_terminated_length": 1000.2,
      "completions/mean_length": 68.496875,
      "completions/mean_terminated_length": 65.34157257080078,
      "completions/min_length": 13.6,
      "completions/min_terminated_length": 13.6,
      "epoch": 0.43478260869565216,
      "grad_norm": 1.2910770177841187,
      "learning_rate": 1e-06,
      "loss": 0.0493,
      "num_tokens": 4027912.0,
      "reward": 0.684375,
      "reward_std": 0.2268119275569916,
      "rewards/accuracy_reward": 0.3828125,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 0.9859375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 30
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 87.4,
      "completions/max_terminated_length": 87.4,
      "completions/mean_length": 14.571875,
      "completions/mean_terminated_length": 14.571875,
      "completions/min_length": 13.6,
      "completions/min_terminated_length": 13.6,
      "epoch": 0.5072463768115942,
      "grad_norm": 0.6825551986694336,
      "learning_rate": 1e-06,
      "loss": 0.0027,
      "num_tokens": 4553134.0,
      "reward": 0.740625,
      "reward_std": 0.17117000222206116,
      "rewards/accuracy_reward": 0.4828125,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 0.9984375,
      "rewards/mean_confidence_reward": 0.0,
      "step": 35
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 0.5797101449275363,
      "grad_norm": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 5073238.0,
      "reward": 0.784375,
      "reward_std": 0.02448901943862438,
      "rewards/accuracy_reward": 0.56875,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 40
    },
    {
      "epoch": 0.5797101449275363,
      "eval_completions/clipped_ratio": 0.0,
      "eval_completions/max_length": 14.202898550724637,
      "eval_completions/max_terminated_length": 14.202898550724637,
      "eval_completions/mean_length": 14.02536231884058,
      "eval_completions/mean_terminated_length": 14.02536231884058,
      "eval_completions/min_length": 14.0,
      "eval_completions/min_terminated_length": 14.0,
      "eval_loss": 0.0,
      "eval_num_tokens": 5073238.0,
      "eval_reward": 0.769927536231884,
      "eval_reward_std": 0.0,
      "eval_rewards/accuracy_reward": 0.5398550724637681,
      "eval_rewards/brier_reward": 0.0,
      "eval_rewards/confidence_one_or_zero": 0.0,
      "eval_rewards/format_reward": 1.0,
      "eval_rewards/mean_confidence_reward": 0.0,
      "eval_runtime": 56.5872,
      "eval_samples_per_second": 4.877,
      "eval_steps_per_second": 0.619,
      "step": 40
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 0.6521739130434783,
      "grad_norm": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 5571742.0,
      "reward": 0.81875,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.6375,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 45
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 0.7246376811594203,
      "grad_norm": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 6072454.0,
      "reward": 0.8,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.6,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 50
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 0.7971014492753623,
      "grad_norm": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 6566110.0,
      "reward": 0.85,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.7,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 55
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 0.8695652173913043,
      "grad_norm": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 7074102.0,
      "reward": 0.7375,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.475,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 60
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 0.9420289855072463,
      "grad_norm": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 7593598.0,
      "reward": 0.85,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.7,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 65
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 1.0144927536231885,
      "grad_norm": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 8094718.0,
      "reward": 0.8,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.6,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 70
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 1.0869565217391304,
      "grad_norm": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 8618702.0,
      "reward": 0.81875,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.6375,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 75
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 1.1594202898550725,
      "grad_norm": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 9121166.0,
      "reward": 0.8375,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.675,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 80
    },
    {
      "epoch": 1.1594202898550725,
      "eval_completions/clipped_ratio": 0.0,
      "eval_completions/max_length": 14.0,
      "eval_completions/max_terminated_length": 14.0,
      "eval_completions/mean_length": 13.997282608695652,
      "eval_completions/mean_terminated_length": 13.997282608695652,
      "eval_completions/min_length": 13.978260869565217,
      "eval_completions/min_terminated_length": 13.978260869565217,
      "eval_loss": 0.0,
      "eval_num_tokens": 9121166.0,
      "eval_reward": 0.7697010869565217,
      "eval_reward_std": 0.0006404952618522921,
      "eval_rewards/accuracy_reward": 0.5398550724637681,
      "eval_rewards/brier_reward": 0.0,
      "eval_rewards/confidence_one_or_zero": 0.0,
      "eval_rewards/format_reward": 0.9995471014492754,
      "eval_rewards/mean_confidence_reward": 0.0,
      "eval_runtime": 55.1546,
      "eval_samples_per_second": 5.004,
      "eval_steps_per_second": 0.635,
      "step": 80
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 1.2318840579710144,
      "grad_norm": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 9636118.0,
      "reward": 0.8,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.6,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 85
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 1.3043478260869565,
      "grad_norm": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 10160798.0,
      "reward": 0.80625,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.6125,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 90
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 1.3768115942028984,
      "grad_norm": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 10661622.0,
      "reward": 0.83125,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.6625,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 95
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 1.4492753623188406,
      "grad_norm": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 11183702.0,
      "reward": 0.76875,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.5375,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 100
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 1.5217391304347827,
      "grad_norm": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 11697894.0,
      "reward": 0.8125,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.625,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 105
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 1.5942028985507246,
      "grad_norm": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 12207526.0,
      "reward": 0.80625,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.6125,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 110
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 1.6666666666666665,
      "grad_norm": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 12718326.0,
      "reward": 0.85625,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.7125,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 115
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 1.7391304347826086,
      "grad_norm": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 13241574.0,
      "reward": 0.74375,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.4875,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 120
    },
    {
      "epoch": 1.7391304347826086,
      "eval_completions/clipped_ratio": 0.0,
      "eval_completions/max_length": 14.0,
      "eval_completions/max_terminated_length": 14.0,
      "eval_completions/mean_length": 14.0,
      "eval_completions/mean_terminated_length": 14.0,
      "eval_completions/min_length": 14.0,
      "eval_completions/min_terminated_length": 14.0,
      "eval_loss": 0.0,
      "eval_num_tokens": 13241574.0,
      "eval_reward": 0.769927536231884,
      "eval_reward_std": 0.0,
      "eval_rewards/accuracy_reward": 0.5398550724637681,
      "eval_rewards/brier_reward": 0.0,
      "eval_rewards/confidence_one_or_zero": 0.0,
      "eval_rewards/format_reward": 1.0,
      "eval_rewards/mean_confidence_reward": 0.0,
      "eval_runtime": 55.0566,
      "eval_samples_per_second": 5.013,
      "eval_steps_per_second": 0.636,
      "step": 120
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 1.8115942028985508,
      "grad_norm": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 13743174.0,
      "reward": 0.83125,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.6625,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 125
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 1.8840579710144927,
      "grad_norm": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 14260630.0,
      "reward": 0.7875,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.575,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 130
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 1.9565217391304348,
      "grad_norm": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 14759926.0,
      "reward": 0.81875,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.6375,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 135
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 14.0,
      "completions/max_terminated_length": 14.0,
      "completions/mean_length": 14.0,
      "completions/mean_terminated_length": 14.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 2.0,
      "num_tokens": 15050678.0,
      "reward": 0.7916666666666666,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.5833333333333334,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 1.0,
      "rewards/mean_confidence_reward": 0.0,
      "step": 138,
      "total_flos": 0.0,
      "train_loss": 0.007580966351256854,
      "train_runtime": 2994.2909,
      "train_samples_per_second": 0.737,
      "train_steps_per_second": 0.046
    }
  ],
  "logging_steps": 5,
  "max_steps": 138,
  "num_input_tokens_seen": 15050678,
  "num_train_epochs": 2,
  "save_steps": 40,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}