{
  "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": 0.01875,
      "completions/max_length": 1405.0,
      "completions/max_terminated_length": 1158.0,
      "completions/mean_length": 358.45,
      "completions/mean_terminated_length": 336.098583984375,
      "completions/min_length": 33.4,
      "completions/min_terminated_length": 33.4,
      "epoch": 0.07246376811594203,
      "grad_norm": 0.22498725354671478,
      "learning_rate": 5.714285714285714e-07,
      "loss": 0.014,
      "num_tokens": 361516.0,
      "reward": 0.4796875,
      "reward_std": 0.11398765742778778,
      "rewards/accuracy_reward": 0.046875,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 0.9125,
      "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": 0.01875,
      "completions/max_length": 1536.0,
      "completions/max_terminated_length": 1195.8,
      "completions/mean_length": 355.30625,
      "completions/mean_terminated_length": 332.8796875,
      "completions/min_length": 40.6,
      "completions/min_terminated_length": 40.6,
      "epoch": 0.14492753623188406,
      "grad_norm": 0.16890129446983337,
      "learning_rate": 1e-06,
      "loss": 0.0076,
      "num_tokens": 726410.0,
      "reward": 0.4609375,
      "reward_std": 0.1016180694103241,
      "rewards/accuracy_reward": 0.01875,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 0.903125,
      "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": 0.021875,
      "completions/max_length": 1459.2,
      "completions/max_terminated_length": 1183.0,
      "completions/mean_length": 382.175,
      "completions/mean_terminated_length": 355.565283203125,
      "completions/min_length": 44.6,
      "completions/min_terminated_length": 44.6,
      "epoch": 0.21739130434782608,
      "grad_norm": 0.1477378010749817,
      "learning_rate": 1e-06,
      "loss": 0.0139,
      "num_tokens": 1110366.0,
      "reward": 0.4859375,
      "reward_std": 0.0945812076330185,
      "rewards/accuracy_reward": 0.034375,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 0.9375,
      "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": 0.021875,
      "completions/max_length": 1519.6,
      "completions/max_terminated_length": 1327.0,
      "completions/mean_length": 367.028125,
      "completions/mean_terminated_length": 340.75071411132814,
      "completions/min_length": 29.0,
      "completions/min_terminated_length": 29.0,
      "epoch": 0.2898550724637681,
      "grad_norm": 0.1407293826341629,
      "learning_rate": 1e-06,
      "loss": 0.0156,
      "num_tokens": 1484607.0,
      "reward": 0.4953125,
      "reward_std": 0.061836542934179305,
      "rewards/accuracy_reward": 0.028125,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 0.9625,
      "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": 0.021875,
      "completions/max_length": 1424.0,
      "completions/max_terminated_length": 1269.2,
      "completions/mean_length": 345.625,
      "completions/mean_terminated_length": 319.861376953125,
      "completions/min_length": 13.6,
      "completions/min_terminated_length": 13.6,
      "epoch": 0.36231884057971014,
      "grad_norm": 0.24553127586841583,
      "learning_rate": 1e-06,
      "loss": 0.0156,
      "num_tokens": 1847603.0,
      "reward": 0.5125,
      "reward_std": 0.09752618968486786,
      "rewards/accuracy_reward": 0.065625,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 0.959375,
      "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": 0.00625,
      "completions/max_length": 1176.8,
      "completions/max_terminated_length": 897.2,
      "completions/mean_length": 110.48125,
      "completions/mean_terminated_length": 101.89906005859375,
      "completions/min_length": 13.0,
      "completions/min_terminated_length": 13.0,
      "epoch": 0.43478260869565216,
      "grad_norm": 0.6328610777854919,
      "learning_rate": 1e-06,
      "loss": 0.0167,
      "num_tokens": 2129165.0,
      "reward": 0.5296875,
      "reward_std": 0.08058654218912124,
      "rewards/accuracy_reward": 0.075,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 0.984375,
      "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": 0.003125,
      "completions/max_length": 472.4,
      "completions/max_terminated_length": 326.6,
      "completions/mean_length": 25.5875,
      "completions/mean_terminated_length": 20.871031951904296,
      "completions/min_length": 13.8,
      "completions/min_terminated_length": 13.8,
      "epoch": 0.5072463768115942,
      "grad_norm": 0.45740750432014465,
      "learning_rate": 1e-06,
      "loss": 0.0081,
      "num_tokens": 2395621.0,
      "reward": 0.559375,
      "reward_std": 0.11064529567956924,
      "rewards/accuracy_reward": 0.128125,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 0.990625,
      "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": 39.8,
      "completions/max_terminated_length": 39.8,
      "completions/mean_length": 14.575,
      "completions/mean_terminated_length": 14.575,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 0.5797101449275363,
      "grad_norm": 0.646138608455658,
      "learning_rate": 1e-06,
      "loss": 0.0023,
      "num_tokens": 2656177.0,
      "reward": 0.6015625,
      "reward_std": 0.13850158601999282,
      "rewards/accuracy_reward": 0.20625,
      "rewards/brier_reward": 0.0,
      "rewards/confidence_one_or_zero": 0.0,
      "rewards/format_reward": 0.996875,
      "rewards/mean_confidence_reward": 0.0,
      "step": 40
    },
    {
      "epoch": 0.5797101449275363,
      "eval_completions/clipped_ratio": 0.0,
      "eval_completions/max_length": 14.58695652173913,
      "eval_completions/max_terminated_length": 14.58695652173913,
      "eval_completions/mean_length": 14.07336956521739,
      "eval_completions/mean_terminated_length": 14.07336956521739,
      "eval_completions/min_length": 14.0,
      "eval_completions/min_terminated_length": 14.0,
      "eval_loss": 0.0,
      "eval_num_tokens": 2656177.0,
      "eval_reward": 0.6019021739130435,
      "eval_reward_std": 0.14245554740014282,
      "eval_rewards/accuracy_reward": 0.20471014492753623,
      "eval_rewards/brier_reward": 0.0,
      "eval_rewards/confidence_one_or_zero": 0.0,
      "eval_rewards/format_reward": 0.9990942028985508,
      "eval_rewards/mean_confidence_reward": 0.0,
      "eval_runtime": 28.3508,
      "eval_samples_per_second": 9.735,
      "eval_steps_per_second": 1.235,
      "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": 0.34094905853271484,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 2905749.0,
      "reward": 0.6109375,
      "reward_std": 0.1269684612751007,
      "rewards/accuracy_reward": 0.221875,
      "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": 0.6670905351638794,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 3156425.0,
      "reward": 0.6265625,
      "reward_std": 0.08366719409823417,
      "rewards/accuracy_reward": 0.253125,
      "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": 0.15868930518627167,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "num_tokens": 3403573.0,
      "reward": 0.678125,
      "reward_std": 0.04471687823534012,
      "rewards/accuracy_reward": 0.35625,
      "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": 3657889.0,
      "reward": 0.6125,
      "reward_std": 0.00625,
      "rewards/accuracy_reward": 0.225,
      "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": 3917957.0,
      "reward": 0.6609375,
      "reward_std": 0.003125,
      "rewards/accuracy_reward": 0.321875,
      "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": 4168837.0,
      "reward": 0.64375,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.2875,
      "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": 13.996875,
      "completions/mean_terminated_length": 13.996875,
      "completions/min_length": 13.8,
      "completions/min_terminated_length": 13.8,
      "epoch": 1.0869565217391304,
      "grad_norm": 0.0,
      "learning_rate": 1e-06,
      "loss": -0.0001,
      "num_tokens": 4431148.0,
      "reward": 0.6671875,
      "reward_std": 0.003125,
      "rewards/accuracy_reward": 0.334375,
      "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": 14.2,
      "completions/max_terminated_length": 14.2,
      "completions/mean_length": 14.003125,
      "completions/mean_terminated_length": 14.003125,
      "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": 4682701.0,
      "reward": 0.6625,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.325,
      "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": 14.007246376811594,
      "eval_completions/max_terminated_length": 14.007246376811594,
      "eval_completions/mean_length": 14.00090579710145,
      "eval_completions/mean_terminated_length": 14.00090579710145,
      "eval_completions/min_length": 14.0,
      "eval_completions/min_terminated_length": 14.0,
      "eval_loss": 0.0,
      "eval_num_tokens": 4682701.0,
      "eval_reward": 0.6231884057971014,
      "eval_reward_std": 0.0,
      "eval_rewards/accuracy_reward": 0.2463768115942029,
      "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": 28.2299,
      "eval_samples_per_second": 9.777,
      "eval_steps_per_second": 1.24,
      "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": 4940497.0,
      "reward": 0.6375,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.275,
      "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": 14.2,
      "completions/max_terminated_length": 14.2,
      "completions/mean_length": 14.003125,
      "completions/mean_terminated_length": 14.003125,
      "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": 5203158.0,
      "reward": 0.65625,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.3125,
      "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": 5453890.0,
      "reward": 0.66875,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.3375,
      "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": 5715250.0,
      "reward": 0.6125,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.225,
      "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": 5972666.0,
      "reward": 0.63125,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.2625,
      "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": 6227802.0,
      "reward": 0.69375,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.3875,
      "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": 6483522.0,
      "reward": 0.6,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.2,
      "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": 6745466.0,
      "reward": 0.6625,
      "reward_std": 0.025966877490282057,
      "rewards/accuracy_reward": 0.325,
      "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": 6745466.0,
      "eval_reward": 0.6231884057971014,
      "eval_reward_std": 0.0,
      "eval_rewards/accuracy_reward": 0.2463768115942029,
      "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": 28.085,
      "eval_samples_per_second": 9.827,
      "eval_steps_per_second": 1.246,
      "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": 6996586.0,
      "reward": 0.65,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.3,
      "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": 7255634.0,
      "reward": 0.6375,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.275,
      "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": 7505602.0,
      "reward": 0.625,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.25,
      "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": 7651169.0,
      "reward": 0.6458333333333334,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.2916666666666667,
      "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": 0.00339745721725774,
      "train_runtime": 1777.8343,
      "train_samples_per_second": 1.242,
      "train_steps_per_second": 0.078
    }
  ],
  "logging_steps": 5,
  "max_steps": 138,
  "num_input_tokens_seen": 7651169,
  "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": 4,
  "trial_name": null,
  "trial_params": null
}