{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.46511627906976744,
  "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": 102.5,
      "completions/max_terminated_length": 102.5,
      "completions/mean_length": 46.5,
      "completions/mean_terminated_length": 46.5,
      "completions/min_length": 17.0,
      "completions/min_terminated_length": 17.0,
      "epoch": 0.09302325581395349,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 26.819913864135742,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.1038,
      "num_tokens": 1396.0,
      "reward": 0.03198886290192604,
      "reward_std": 0.010370630770921707,
      "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": 0.03198886290192604,
      "rewards/question_recreation_reward_func/std": 0.011841414961963892,
      "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": 0.0,
      "rewards/xmlcount_reward_func/std": 0.0,
      "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": 31.5,
      "completions/max_terminated_length": 31.5,
      "completions/mean_length": 22.375,
      "completions/mean_terminated_length": 22.375,
      "completions/min_length": 16.0,
      "completions/min_terminated_length": 16.0,
      "epoch": 0.18604651162790697,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 47.122337341308594,
      "kl": 0.009030564804561436,
      "learning_rate": 4.415111107797445e-07,
      "loss": 0.0182,
      "num_tokens": 2599.0,
      "reward": 0.04082147125154734,
      "reward_std": 0.016715965699404478,
      "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": 0.04082146845757961,
      "rewards/question_recreation_reward_func/std": 0.026838398072868586,
      "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": 0.0,
      "rewards/xmlcount_reward_func/std": 0.0,
      "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": 0.125,
      "completions/max_length": 183.0,
      "completions/max_terminated_length": 148.5,
      "completions/mean_length": 90.25,
      "completions/mean_terminated_length": 70.16666793823242,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 0.27906976744186046,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 70.61158752441406,
      "kl": 0.014445176813751459,
      "learning_rate": 2.934120444167326e-07,
      "loss": -0.0519,
      "num_tokens": 4345.0,
      "reward": 0.02797679416835308,
      "reward_std": 0.005366061115637422,
      "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": 0.02797679416835308,
      "rewards/question_recreation_reward_func/std": 0.016844000667333603,
      "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": 0.0,
      "rewards/xmlcount_reward_func/std": 0.0,
      "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": 0.0,
      "completions/max_length": 35.0,
      "completions/max_terminated_length": 35.0,
      "completions/mean_length": 14.125,
      "completions/mean_terminated_length": 14.125,
      "completions/min_length": 4.0,
      "completions/min_terminated_length": 4.0,
      "epoch": 0.37209302325581395,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 84.35356140136719,
      "kl": 0.05594382411800325,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.0779,
      "num_tokens": 5482.0,
      "reward": 1.4956446290016174,
      "reward_std": 0.6916476492770016,
      "rewards/concensus_correctness_reward_func/mean": 0.7199999988079071,
      "rewards/concensus_correctness_reward_func/std": 1.0334109663963318,
      "rewards/consensus_reward_func/mean": 0.75,
      "rewards/consensus_reward_func/std": 1.0773502588272095,
      "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": 0.025644690729677677,
      "rewards/question_recreation_reward_func/std": 0.016321994364261627,
      "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": 0.0,
      "rewards/xmlcount_reward_func/std": 0.0,
      "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": 47.0,
      "completions/max_terminated_length": 47.0,
      "completions/mean_length": 22.375,
      "completions/mean_terminated_length": 22.375,
      "completions/min_length": 4.5,
      "completions/min_terminated_length": 4.5,
      "epoch": 0.46511627906976744,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 39.63914489746094,
      "kl": 0.015579930739477277,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0031,
      "num_tokens": 6685.0,
      "reward": 0.7941031903028488,
      "reward_std": 0.02715550092398189,
      "rewards/concensus_correctness_reward_func/mean": 0.7120000123977661,
      "rewards/concensus_correctness_reward_func/std": 0.8221468329429626,
      "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": 0.08210319094359875,
      "rewards/question_recreation_reward_func/std": 0.056017409078776836,
      "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": 0.0,
      "rewards/xmlcount_reward_func/std": 0.0,
      "step": 10
    },
    {
      "epoch": 0.46511627906976744,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 0.030200545489788056,
      "train_runtime": 708.4645,
      "train_samples_per_second": 0.056,
      "train_steps_per_second": 0.014
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 6685,
  "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
}