{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.4,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 83.0,
      "epoch": 0.8,
      "grad_norm": 7.9807281494140625,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": -0.0,
      "reward": 1.7760924957692623,
      "reward_std": 0.022786720073781908,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.5,
      "rewards/question_recreation_reward_func": 0.1510925330221653,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.125,
      "step": 2
    },
    {
      "completion_length": 56.833333333333336,
      "epoch": 1.4,
      "grad_norm": 10.24837589263916,
      "kl": 0.0015244192351625923,
      "learning_rate": 4.415111107797445e-07,
      "loss": 0.0,
      "reward": 2.550933281580607,
      "reward_std": 0.07004699483513832,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 2.0,
      "rewards/question_recreation_reward_func": 0.42593332131703693,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.125,
      "step": 4
    },
    {
      "completion_length": 77.66666666666667,
      "epoch": 2.0,
      "grad_norm": 6.0542120933532715,
      "kl": 0.0016350069102675964,
      "learning_rate": 2.934120444167326e-07,
      "loss": 0.0,
      "reward": 1.5878510723511379,
      "reward_std": 0.0029388506275912127,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.3333333333333333,
      "rewards/question_recreation_reward_func": 0.1295176992813746,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.125,
      "step": 6
    },
    {
      "completion_length": 72.25,
      "epoch": 2.8,
      "grad_norm": 2.34584641456604,
      "kl": 0.0029444374376907945,
      "learning_rate": 1.2500000000000005e-07,
      "loss": -0.0,
      "reward": 1.8496044538915157,
      "reward_std": 0.0011594545212574303,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.5,
      "rewards/question_recreation_reward_func": 0.22460449486970901,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.125,
      "step": 8
    },
    {
      "completion_length": 75.83333333333333,
      "epoch": 3.4,
      "grad_norm": 5.32132625579834,
      "kl": 0.007413267778853576,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0,
      "reward": 1.6325677633285522,
      "reward_std": 0.042186157782756105,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.3333333333333333,
      "rewards/question_recreation_reward_func": 0.17423443992932638,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.125,
      "step": 10
    },
    {
      "epoch": 3.4,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 6.0011893765477e-06,
      "train_runtime": 503.4756,
      "train_samples_per_second": 0.079,
      "train_steps_per_second": 0.02
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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
}