{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2564102564102564,
  "eval_steps": 500,
  "global_step": 10,
  "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
    }
  ],
  "logging_steps": 1,
  "max_steps": 39,
  "num_input_tokens_seen": 1533384,
  "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
}