{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5128205128205128,
  "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": 48.0,
      "completions/max_terminated_length": 48.0,
      "completions/mean_length": 29.0,
      "completions/mean_terminated_length": 29.0,
      "completions/min_length": 16.0,
      "completions/min_terminated_length": 16.0,
      "epoch": 0.10256410256410256,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 66.07881164550781,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0702,
      "num_tokens": 1256.0,
      "reward": 0.026949090883135796,
      "reward_std": 0.00813433644361794,
      "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": 0.026949090883135796,
      "rewards/question_recreation_reward_func/std": 0.008170501794666052,
      "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": 95.0,
      "completions/max_terminated_length": 95.0,
      "completions/mean_length": 45.625,
      "completions/mean_terminated_length": 45.625,
      "completions/min_length": 21.0,
      "completions/min_terminated_length": 21.0,
      "epoch": 0.20512820512820512,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 37.884674072265625,
      "kl": 0.0024425766605418175,
      "learning_rate": 4.415111107797445e-07,
      "loss": -0.0942,
      "num_tokens": 2645.0,
      "reward": 0.10819943062961102,
      "reward_std": 0.03681066678836942,
      "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": 0.10819943062961102,
      "rewards/question_recreation_reward_func/std": 0.05056785373017192,
      "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": 55.0,
      "completions/max_terminated_length": 55.0,
      "completions/mean_length": 38.125,
      "completions/mean_terminated_length": 38.125,
      "completions/min_length": 24.0,
      "completions/min_terminated_length": 24.0,
      "epoch": 0.3076923076923077,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 39.26205825805664,
      "kl": 0.009228412294760346,
      "learning_rate": 2.934120444167326e-07,
      "loss": -0.0,
      "num_tokens": 3974.0,
      "reward": 0.13380783051252365,
      "reward_std": 0.016271354164928198,
      "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": 0.13380782958120108,
      "rewards/question_recreation_reward_func/std": 0.04104881267994642,
      "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": 66.5,
      "completions/max_terminated_length": 66.5,
      "completions/mean_length": 35.125,
      "completions/mean_terminated_length": 35.125,
      "completions/min_length": 18.0,
      "completions/min_terminated_length": 18.0,
      "epoch": 0.41025641025641024,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 34.62491226196289,
      "kl": 0.005057038099039346,
      "learning_rate": 1.2500000000000005e-07,
      "loss": -0.0789,
      "num_tokens": 5279.0,
      "reward": 0.10237674228847027,
      "reward_std": 0.016381334979087114,
      "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": 0.10237674042582512,
      "rewards/question_recreation_reward_func/std": 0.026739858090877533,
      "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": 71.5,
      "completions/max_terminated_length": 71.5,
      "completions/mean_length": 34.125,
      "completions/mean_terminated_length": 34.125,
      "completions/min_length": 19.5,
      "completions/min_terminated_length": 19.5,
      "epoch": 0.5128205128205128,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 29.29859161376953,
      "kl": 0.014766428037546575,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0321,
      "num_tokens": 6576.0,
      "reward": 0.026895208284258842,
      "reward_std": 0.006386967375874519,
      "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": 0.02689521014690399,
      "rewards/question_recreation_reward_func/std": 0.00949656730517745,
      "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": 0.5128205128205128,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": -0.014154134690761567,
      "train_runtime": 1421.1194,
      "train_samples_per_second": 0.028,
      "train_steps_per_second": 0.007
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 6576,
  "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
}