{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8695652173913043,
  "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": 0.0,
      "completions/max_length": 84.5,
      "completions/max_terminated_length": 84.5,
      "completions/mean_length": 46.125,
      "completions/mean_terminated_length": 46.125,
      "completions/min_length": 20.5,
      "completions/min_terminated_length": 20.5,
      "epoch": 0.17391304347826086,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 50.021663665771484,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": -0.0009,
      "num_tokens": 1393.0,
      "reward": 0.3569868355989456,
      "reward_std": 0.10140731558203697,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.0,
      "rewards/consensus_reward_func/std": 0.0,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 0.0,
      "rewards/final_correctness_reward_func/std": 0.0,
      "rewards/question_recreation_reward_func/mean": 0.032236830331385136,
      "rewards/question_recreation_reward_func/std": 0.017948506865650415,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.0,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 0.32474999129772186,
      "rewards/xmlcount_reward_func/std": 0.19420991092920303,
      "step": 2
    },
    {
      "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": 109.0,
      "completions/max_terminated_length": 109.0,
      "completions/mean_length": 70.75,
      "completions/mean_terminated_length": 70.75,
      "completions/min_length": 41.5,
      "completions/min_terminated_length": 41.5,
      "epoch": 0.34782608695652173,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 19.0537109375,
      "kl": 0.002165338257327676,
      "learning_rate": 4.415111107797445e-07,
      "loss": 0.0282,
      "num_tokens": 2983.0,
      "reward": 0.4277445673942566,
      "reward_std": 0.14516344666481018,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.0,
      "rewards/consensus_reward_func/std": 0.0,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 0.0,
      "rewards/final_correctness_reward_func/std": 0.0,
      "rewards/question_recreation_reward_func/mean": 0.16299461387097836,
      "rewards/question_recreation_reward_func/std": 0.06881882064044476,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.0,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 0.26474998891353607,
      "rewards/xmlcount_reward_func/std": 0.28970315866172314,
      "step": 4
    },
    {
      "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": 177.0,
      "completions/max_terminated_length": 177.0,
      "completions/mean_length": 91.625,
      "completions/mean_terminated_length": 91.625,
      "completions/min_length": 33.5,
      "completions/min_terminated_length": 33.5,
      "epoch": 0.5217391304347826,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 13.790047645568848,
      "kl": 0.0031155047909123823,
      "learning_rate": 2.934120444167326e-07,
      "loss": 0.1559,
      "num_tokens": 4740.0,
      "reward": 0.25488629564642906,
      "reward_std": 0.1210553664714098,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.0,
      "rewards/consensus_reward_func/std": 0.0,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 0.0,
      "rewards/final_correctness_reward_func/std": 0.0,
      "rewards/question_recreation_reward_func/mean": 0.04713628068566322,
      "rewards/question_recreation_reward_func/std": 0.032215227372944355,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.0,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 0.20775000005960464,
      "rewards/xmlcount_reward_func/std": 0.2513107433915138,
      "step": 6
    },
    {
      "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": 0.125,
      "completions/max_length": 198.0,
      "completions/max_terminated_length": 98.5,
      "completions/mean_length": 95.5,
      "completions/mean_terminated_length": 69.5,
      "completions/min_length": 44.5,
      "completions/min_terminated_length": 44.5,
      "epoch": 0.6956521739130435,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 19.808725357055664,
      "kl": 0.015141080017201602,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.0002,
      "num_tokens": 6528.0,
      "reward": 0.2949913889169693,
      "reward_std": 0.13783530704677105,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.0,
      "rewards/consensus_reward_func/std": 0.0,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 0.0,
      "rewards/final_correctness_reward_func/std": 0.0,
      "rewards/question_recreation_reward_func/mean": 0.04011638090014458,
      "rewards/question_recreation_reward_func/std": 0.03736674599349499,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.0,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 0.2548750042915344,
      "rewards/xmlcount_reward_func/std": 0.30075830966234207,
      "step": 8
    },
    {
      "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": 63.5,
      "completions/max_terminated_length": 63.5,
      "completions/mean_length": 49.5,
      "completions/mean_terminated_length": 49.5,
      "completions/min_length": 24.5,
      "completions/min_terminated_length": 24.5,
      "epoch": 0.8695652173913043,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 43.93717956542969,
      "kl": 0.027774153277277946,
      "learning_rate": 1.507684480352292e-08,
      "loss": -0.0862,
      "num_tokens": 7948.0,
      "reward": 0.4353444501757622,
      "reward_std": 0.1529897004365921,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.0,
      "rewards/consensus_reward_func/std": 0.0,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 0.0,
      "rewards/final_correctness_reward_func/std": 0.0,
      "rewards/question_recreation_reward_func/mean": 0.132094481959939,
      "rewards/question_recreation_reward_func/std": 0.03221887769177556,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.0,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 0.3032499924302101,
      "rewards/xmlcount_reward_func/std": 0.16571738570928574,
      "step": 10
    },
    {
      "epoch": 0.8695652173913043,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 0.019416041672229767,
      "train_runtime": 1276.5475,
      "train_samples_per_second": 0.031,
      "train_steps_per_second": 0.008
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 7948,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}