{
  "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": 78.375,
      "epoch": 0.8,
      "grad_norm": 5.627739906311035,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.7521542385220528,
      "reward_std": 0.044539074537169654,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.5,
      "rewards/question_recreation_reward_func": 0.15840421058237553,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.09375,
      "step": 2
    },
    {
      "completion_length": 49.666666666666664,
      "epoch": 1.4,
      "grad_norm": 0.005242869723588228,
      "kl": 0.016141654608266737,
      "learning_rate": 4.415111107797445e-07,
      "loss": 0.0,
      "reward": 1.9181493918100994,
      "reward_std": 0.015638279418150585,
      "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": 0.4598161180814107,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.125,
      "step": 4
    },
    {
      "completion_length": 58.666666666666664,
      "epoch": 2.0,
      "grad_norm": 7.197663307189941,
      "kl": 0.010560240286091963,
      "learning_rate": 2.934120444167326e-07,
      "loss": 0.0,
      "reward": 0.9169059892495474,
      "reward_std": 0.0018884773987034957,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.6666666666666666,
      "rewards/question_recreation_reward_func": 0.16690599421660104,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.08333333333333333,
      "step": 6
    },
    {
      "completion_length": 61.375,
      "epoch": 2.8,
      "grad_norm": 2.7515034675598145,
      "kl": 0.004465199788683094,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.0,
      "reward": 1.361022423952818,
      "reward_std": 0.00136809196555987,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 1.0,
      "rewards/question_recreation_reward_func": 0.26727242209017277,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.09375,
      "step": 8
    },
    {
      "completion_length": 70.0,
      "epoch": 3.4,
      "grad_norm": 6.803511619567871,
      "kl": 0.01901205163449049,
      "learning_rate": 1.507684480352292e-08,
      "loss": -0.0,
      "reward": 0.9308561086654663,
      "reward_std": 0.005250229577844341,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.6666666666666666,
      "rewards/question_recreation_reward_func": 0.1391894891858101,
      "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": -3.1709017093817236e-06,
      "train_runtime": 939.9173,
      "train_samples_per_second": 0.043,
      "train_steps_per_second": 0.011
    }
  ],
  "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
}