{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5128205128205128,
  "eval_steps": 500,
  "global_step": 20,
  "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": 0.80078125,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 253.0,
      "completions/mean_length": 237.14453125,
      "completions/mean_terminated_length": 161.3529510498047,
      "completions/min_length": 10.0,
      "completions/min_terminated_length": 10.0,
      "entropy": 1.3392305374145508,
      "epoch": 0.02564102564102564,
      "frac_reward_zero_std": 0.2890625,
      "grad_norm": 0.07342787832021713,
      "learning_rate": 0.0,
      "loss": 0.0068,
      "num_tokens": 153643.0,
      "reward": 0.859375,
      "reward_std": 1.100690484046936,
      "rewards/mathematical_correctness_reward_function/mean": 0.859375,
      "rewards/mathematical_correctness_reward_function/std": 1.1006906032562256,
      "step": 1,
      "step_time": 86.24474567199923
    },
    {
      "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": 0.83984375,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 253.0,
      "completions/mean_length": 239.8671875,
      "completions/mean_terminated_length": 155.26828002929688,
      "completions/min_length": 37.0,
      "completions/min_terminated_length": 37.0,
      "entropy": 1.1771463677287102,
      "epoch": 0.05128205128205128,
      "frac_reward_zero_std": 0.3515625,
      "grad_norm": 0.06119547039270401,
      "learning_rate": 2.5e-06,
      "loss": 0.0204,
      "num_tokens": 308163.0,
      "reward": 0.88671875,
      "reward_std": 1.3041635751724243,
      "rewards/mathematical_correctness_reward_function/mean": 0.88671875,
      "rewards/mathematical_correctness_reward_function/std": 1.3041635751724243,
      "step": 2,
      "step_time": 86.508452252001
    },
    {
      "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": 0.85546875,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 253.0,
      "completions/mean_length": 244.81640625,
      "completions/mean_terminated_length": 178.6216278076172,
      "completions/min_length": 48.0,
      "completions/min_terminated_length": 48.0,
      "entropy": 1.1922413893043995,
      "epoch": 0.07692307692307693,
      "frac_reward_zero_std": 0.375,
      "grad_norm": 0.056310124695301056,
      "learning_rate": 5e-06,
      "loss": 0.0119,
      "num_tokens": 463868.0,
      "reward": 0.90234375,
      "reward_std": 1.124693512916565,
      "rewards/mathematical_correctness_reward_function/mean": 0.90234375,
      "rewards/mathematical_correctness_reward_function/std": 1.1246936321258545,
      "step": 3,
      "step_time": 85.8330284170006
    },
    {
      "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": 0.84765625,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 255.0,
      "completions/mean_length": 243.02734375,
      "completions/mean_terminated_length": 170.84616088867188,
      "completions/min_length": 82.0,
      "completions/min_terminated_length": 82.0,
      "entropy": 1.2269665226340294,
      "epoch": 0.10256410256410256,
      "frac_reward_zero_std": 0.3984375,
      "grad_norm": 0.05933857336640358,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.0091,
      "num_tokens": 619011.0,
      "reward": 0.91796875,
      "reward_std": 1.1119270324707031,
      "rewards/mathematical_correctness_reward_function/mean": 0.91796875,
      "rewards/mathematical_correctness_reward_function/std": 1.1119270324707031,
      "step": 4,
      "step_time": 85.85383133499909
    },
    {
      "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": 0.80859375,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 256.0,
      "completions/mean_length": 235.5390625,
      "completions/mean_terminated_length": 149.10203552246094,
      "completions/min_length": 11.0,
      "completions/min_terminated_length": 11.0,
      "entropy": 1.1289030984044075,
      "epoch": 0.1282051282051282,
      "frac_reward_zero_std": 0.3203125,
      "grad_norm": 0.06574889272451401,
      "learning_rate": 1e-05,
      "loss": 0.0168,
      "num_tokens": 772231.0,
      "reward": 1.10546875,
      "reward_std": 1.3549507856369019,
      "rewards/mathematical_correctness_reward_function/mean": 1.10546875,
      "rewards/mathematical_correctness_reward_function/std": 1.3549507856369019,
      "step": 5,
      "step_time": 85.96325700299985
    },
    {
      "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": 0.73828125,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 256.0,
      "completions/mean_length": 233.44140625,
      "completions/mean_terminated_length": 169.80596923828125,
      "completions/min_length": 46.0,
      "completions/min_terminated_length": 46.0,
      "entropy": 1.2140139639377594,
      "epoch": 0.15384615384615385,
      "frac_reward_zero_std": 0.2734375,
      "grad_norm": 0.06448275595903397,
      "learning_rate": 9.979871469976197e-06,
      "loss": 0.0187,
      "num_tokens": 924882.0,
      "reward": 1.21875,
      "reward_std": 1.1127601861953735,
      "rewards/mathematical_correctness_reward_function/mean": 1.21875,
      "rewards/mathematical_correctness_reward_function/std": 1.1127601861953735,
      "step": 6,
      "step_time": 86.28028441999868
    },
    {
      "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": 0.828125,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 254.0,
      "completions/mean_length": 241.78515625,
      "completions/mean_terminated_length": 173.2954559326172,
      "completions/min_length": 36.0,
      "completions/min_terminated_length": 36.0,
      "entropy": 1.241826605051756,
      "epoch": 0.1794871794871795,
      "frac_reward_zero_std": 0.2421875,
      "grad_norm": 0.06542028486728668,
      "learning_rate": 9.91964794299315e-06,
      "loss": 0.0025,
      "num_tokens": 1079615.0,
      "reward": 1.29296875,
      "reward_std": 1.1359151601791382,
      "rewards/mathematical_correctness_reward_function/mean": 1.29296875,
      "rewards/mathematical_correctness_reward_function/std": 1.1359151601791382,
      "step": 7,
      "step_time": 85.96726177399978
    },
    {
      "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": 0.7578125,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 256.0,
      "completions/mean_length": 231.3046875,
      "completions/mean_terminated_length": 154.03225708007812,
      "completions/min_length": 44.0,
      "completions/min_terminated_length": 44.0,
      "entropy": 1.2537630051374435,
      "epoch": 0.20512820512820512,
      "frac_reward_zero_std": 0.3046875,
      "grad_norm": 0.06004541367292404,
      "learning_rate": 9.819814303479268e-06,
      "loss": 0.0227,
      "num_tokens": 1231799.0,
      "reward": 1.33984375,
      "reward_std": 1.1537383794784546,
      "rewards/mathematical_correctness_reward_function/mean": 1.33984375,
      "rewards/mathematical_correctness_reward_function/std": 1.1537383794784546,
      "step": 8,
      "step_time": 85.93508993700198
    },
    {
      "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": 0.7265625,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 250.0,
      "completions/mean_length": 229.26953125,
      "completions/mean_terminated_length": 158.24285888671875,
      "completions/min_length": 51.0,
      "completions/min_terminated_length": 51.0,
      "entropy": 1.1602798961102962,
      "epoch": 0.23076923076923078,
      "frac_reward_zero_std": 0.2421875,
      "grad_norm": 0.07147325575351715,
      "learning_rate": 9.681174353198687e-06,
      "loss": 0.0138,
      "num_tokens": 1383510.0,
      "reward": 1.62890625,
      "reward_std": 1.3191591501235962,
      "rewards/mathematical_correctness_reward_function/mean": 1.62890625,
      "rewards/mathematical_correctness_reward_function/std": 1.3191591501235962,
      "step": 9,
      "step_time": 86.19385715199951
    },
    {
      "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": 0.671875,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 255.0,
      "completions/mean_length": 222.59375,
      "completions/mean_terminated_length": 154.1904754638672,
      "completions/min_length": 49.0,
      "completions/min_terminated_length": 49.0,
      "entropy": 1.2778590954840183,
      "epoch": 0.2564102564102564,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 0.06555230915546417,
      "learning_rate": 9.504844339512096e-06,
      "loss": -0.0007,
      "num_tokens": 1533384.0,
      "reward": 1.66015625,
      "reward_std": 1.3186944723129272,
      "rewards/mathematical_correctness_reward_function/mean": 1.66015625,
      "rewards/mathematical_correctness_reward_function/std": 1.3186945915222168,
      "step": 10,
      "step_time": 85.93042380499901
    },
    {
      "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": 0.66796875,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 254.0,
      "completions/mean_length": 219.453125,
      "completions/mean_terminated_length": 145.92941284179688,
      "completions/min_length": 38.0,
      "completions/min_terminated_length": 38.0,
      "entropy": 1.2968238294124603,
      "epoch": 0.28205128205128205,
      "frac_reward_zero_std": 0.3046875,
      "grad_norm": 0.0640135407447815,
      "learning_rate": 9.292243968009332e-06,
      "loss": 0.0186,
      "num_tokens": 1682622.0,
      "reward": 1.64453125,
      "reward_std": 1.355674147605896,
      "rewards/mathematical_correctness_reward_function/mean": 1.64453125,
      "rewards/mathematical_correctness_reward_function/std": 1.355674147605896,
      "step": 11,
      "step_time": 86.73103137099861
    },
    {
      "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": 0.70703125,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 256.0,
      "completions/mean_length": 227.4921875,
      "completions/mean_terminated_length": 158.69334411621094,
      "completions/min_length": 53.0,
      "completions/min_terminated_length": 53.0,
      "entropy": 1.1798847801983356,
      "epoch": 0.3076923076923077,
      "frac_reward_zero_std": 0.234375,
      "grad_norm": 0.06765235960483551,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.0153,
      "num_tokens": 1833938.0,
      "reward": 1.74609375,
      "reward_std": 1.2469509840011597,
      "rewards/mathematical_correctness_reward_function/mean": 1.74609375,
      "rewards/mathematical_correctness_reward_function/std": 1.2469509840011597,
      "step": 12,
      "step_time": 85.93055903300046
    },
    {
      "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": 0.72265625,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 255.0,
      "completions/mean_length": 227.6640625,
      "completions/mean_terminated_length": 153.8309783935547,
      "completions/min_length": 42.0,
      "completions/min_terminated_length": 42.0,
      "entropy": 1.0747726932168007,
      "epoch": 0.3333333333333333,
      "frac_reward_zero_std": 0.265625,
      "grad_norm": 0.06723812222480774,
      "learning_rate": 8.765357330018056e-06,
      "loss": 0.0142,
      "num_tokens": 1985174.0,
      "reward": 1.92578125,
      "reward_std": 1.4164161682128906,
      "rewards/mathematical_correctness_reward_function/mean": 1.92578125,
      "rewards/mathematical_correctness_reward_function/std": 1.4164161682128906,
      "step": 13,
      "step_time": 86.18083131499952
    },
    {
      "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": 0.671875,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 256.0,
      "completions/mean_length": 216.9453125,
      "completions/mean_terminated_length": 136.9761962890625,
      "completions/min_length": 19.0,
      "completions/min_terminated_length": 19.0,
      "entropy": 1.048094429075718,
      "epoch": 0.358974358974359,
      "frac_reward_zero_std": 0.2890625,
      "grad_norm": 0.06610685586929321,
      "learning_rate": 8.455313244934324e-06,
      "loss": 0.015,
      "num_tokens": 2133660.0,
      "reward": 1.8671875,
      "reward_std": 1.1740400791168213,
      "rewards/mathematical_correctness_reward_function/mean": 1.8671875,
      "rewards/mathematical_correctness_reward_function/std": 1.1740400791168213,
      "step": 14,
      "step_time": 86.0845494640007
    },
    {
      "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": 0.6171875,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 250.0,
      "completions/mean_length": 207.58984375,
      "completions/mean_terminated_length": 129.5408172607422,
      "completions/min_length": 39.0,
      "completions/min_terminated_length": 39.0,
      "entropy": 1.1446622498333454,
      "epoch": 0.38461538461538464,
      "frac_reward_zero_std": 0.2734375,
      "grad_norm": 0.07915058732032776,
      "learning_rate": 8.117449009293668e-06,
      "loss": 0.0438,
      "num_tokens": 2279705.0,
      "reward": 2.02734375,
      "reward_std": 1.1960861682891846,
      "rewards/mathematical_correctness_reward_function/mean": 2.02734375,
      "rewards/mathematical_correctness_reward_function/std": 1.1960861682891846,
      "step": 15,
      "step_time": 86.29595133900057
    },
    {
      "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": 0.6328125,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 252.0,
      "completions/mean_length": 209.8671875,
      "completions/mean_terminated_length": 130.3616943359375,
      "completions/min_length": 49.0,
      "completions/min_terminated_length": 49.0,
      "entropy": 1.0856149233877659,
      "epoch": 0.41025641025641024,
      "frac_reward_zero_std": 0.2421875,
      "grad_norm": 0.07183024287223816,
      "learning_rate": 7.754484907260513e-06,
      "loss": 0.0186,
      "num_tokens": 2426473.0,
      "reward": 2.00390625,
      "reward_std": 1.272632122039795,
      "rewards/mathematical_correctness_reward_function/mean": 2.00390625,
      "rewards/mathematical_correctness_reward_function/std": 1.272632122039795,
      "step": 16,
      "step_time": 86.06944787800421
    },
    {
      "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": 0.59375,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 249.0,
      "completions/mean_length": 203.3203125,
      "completions/mean_terminated_length": 126.3269271850586,
      "completions/min_length": 42.0,
      "completions/min_terminated_length": 42.0,
      "entropy": 1.1112723909318447,
      "epoch": 0.4358974358974359,
      "frac_reward_zero_std": 0.3203125,
      "grad_norm": 0.07727660983800888,
      "learning_rate": 7.369343312364994e-06,
      "loss": 0.0017,
      "num_tokens": 2571503.0,
      "reward": 2.3515625,
      "reward_std": 1.4637573957443237,
      "rewards/mathematical_correctness_reward_function/mean": 2.3515625,
      "rewards/mathematical_correctness_reward_function/std": 1.4637575149536133,
      "step": 17,
      "step_time": 86.03456121599811
    },
    {
      "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": 0.57421875,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 251.0,
      "completions/mean_length": 200.82421875,
      "completions/mean_terminated_length": 126.412841796875,
      "completions/min_length": 44.0,
      "completions/min_terminated_length": 44.0,
      "entropy": 1.0709168612957,
      "epoch": 0.46153846153846156,
      "frac_reward_zero_std": 0.3671875,
      "grad_norm": 0.07580733299255371,
      "learning_rate": 6.965125158269619e-06,
      "loss": 0.023,
      "num_tokens": 2716018.0,
      "reward": 2.24609375,
      "reward_std": 1.2295321226119995,
      "rewards/mathematical_correctness_reward_function/mean": 2.24609375,
      "rewards/mathematical_correctness_reward_function/std": 1.229532241821289,
      "step": 18,
      "step_time": 86.06337975900169
    },
    {
      "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": 0.5859375,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 256.0,
      "completions/mean_length": 203.3125,
      "completions/mean_terminated_length": 128.7547149658203,
      "completions/min_length": 46.0,
      "completions/min_terminated_length": 46.0,
      "entropy": 1.0283005349338055,
      "epoch": 0.48717948717948717,
      "frac_reward_zero_std": 0.421875,
      "grad_norm": 0.06546252965927124,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.0157,
      "num_tokens": 2861190.0,
      "reward": 2.3203125,
      "reward_std": 1.2008728981018066,
      "rewards/mathematical_correctness_reward_function/mean": 2.3203125,
      "rewards/mathematical_correctness_reward_function/std": 1.2008728981018066,
      "step": 19,
      "step_time": 86.31491269100479
    },
    {
      "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": 0.5234375,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 256.0,
      "completions/mean_length": 190.8125,
      "completions/mean_terminated_length": 119.2131118774414,
      "completions/min_length": 43.0,
      "completions/min_terminated_length": 43.0,
      "entropy": 1.0640101097524166,
      "epoch": 0.5128205128205128,
      "frac_reward_zero_std": 0.3359375,
      "grad_norm": 0.07372903823852539,
      "learning_rate": 6.112604669781572e-06,
      "loss": 0.0409,
      "num_tokens": 3002934.0,
      "reward": 2.54296875,
      "reward_std": 1.3038816452026367,
      "rewards/mathematical_correctness_reward_function/mean": 2.54296875,
      "rewards/mathematical_correctness_reward_function/std": 1.3038816452026367,
      "step": 20,
      "step_time": 85.70871102700039
    }
  ],
  "logging_steps": 1,
  "max_steps": 39,
  "num_input_tokens_seen": 3002934,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": 16,
  "trial_name": null,
  "trial_params": null
}