{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7407407407407407,
  "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": 50.0,
      "completions/max_terminated_length": 50.0,
      "completions/mean_length": 21.125,
      "completions/mean_terminated_length": 21.125,
      "completions/min_length": 4.0,
      "completions/min_terminated_length": 4.0,
      "epoch": 0.14814814814814814,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 12.743616104125977,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0992,
      "num_tokens": 1193.0,
      "reward": 0.09130313247442245,
      "reward_std": 0.01168987131677568,
      "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": 0.09130313247442245,
      "rewards/question_recreation_reward_func/std": 0.013678928487934172,
      "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": 22.0,
      "completions/max_terminated_length": 22.0,
      "completions/mean_length": 12.375,
      "completions/mean_terminated_length": 12.375,
      "completions/min_length": 7.0,
      "completions/min_terminated_length": 7.0,
      "epoch": 0.2962962962962963,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 43.35768508911133,
      "kl": 0.017325570806860924,
      "learning_rate": 4.415111107797445e-07,
      "loss": -0.1484,
      "num_tokens": 2316.0,
      "reward": 0.1280631353147328,
      "reward_std": 0.018915515393018723,
      "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": 0.1280631353147328,
      "rewards/question_recreation_reward_func/std": 0.018273787572979927,
      "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": 0.0,
      "completions/max_length": 19.5,
      "completions/max_terminated_length": 19.5,
      "completions/mean_length": 13.375,
      "completions/mean_terminated_length": 13.375,
      "completions/min_length": 6.5,
      "completions/min_terminated_length": 6.5,
      "epoch": 0.4444444444444444,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 0.018915563821792603,
      "kl": 0.03074789233505726,
      "learning_rate": 2.934120444167326e-07,
      "loss": 0.0001,
      "num_tokens": 3447.0,
      "reward": 0.09580376278609037,
      "reward_std": 0.002759912982583046,
      "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": 0.09580376371741295,
      "rewards/question_recreation_reward_func/std": 0.002817572792991996,
      "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": 61.5,
      "completions/max_terminated_length": 61.5,
      "completions/mean_length": 29.375,
      "completions/mean_terminated_length": 29.375,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.5925925925925926,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 36.02655792236328,
      "kl": 0.03904347028583288,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.0023,
      "num_tokens": 4706.0,
      "reward": 0.01581350341439247,
      "reward_std": 0.008347119903191924,
      "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": 0.01581350341439247,
      "rewards/question_recreation_reward_func/std": 0.012281739618629217,
      "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": 18.0,
      "completions/max_terminated_length": 18.0,
      "completions/mean_length": 11.75,
      "completions/mean_terminated_length": 11.75,
      "completions/min_length": 4.5,
      "completions/min_terminated_length": 4.5,
      "epoch": 0.7407407407407407,
      "frac_reward_zero_std": 0.25,
      "grad_norm": 89.89861297607422,
      "kl": 0.04395892460888717,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0962,
      "num_tokens": 5824.0,
      "reward": 0.5346636138856411,
      "reward_std": 0.6897922963835299,
      "rewards/concensus_correctness_reward_func/mean": 0.2395000010728836,
      "rewards/concensus_correctness_reward_func/std": 0.4790000319480896,
      "rewards/consensus_reward_func/mean": 0.25,
      "rewards/consensus_reward_func/std": 0.5,
      "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": 0.045163657516241074,
      "rewards/question_recreation_reward_func/std": 0.028757712803781033,
      "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": 0.7407407407407407,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 0.009888447250705212,
      "train_runtime": 625.0756,
      "train_samples_per_second": 0.064,
      "train_steps_per_second": 0.016
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 5824,
  "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
}