{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.5,
  "eval_steps": 500,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 124.84375,
      "epoch": 1.0,
      "grad_norm": 11.724444389343262,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0,
      "reward": 0.10400887671858072,
      "reward_std": 0.059505054785404354,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.10400887671858072,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 2
    },
    {
      "completion_length": 67.09375,
      "epoch": 2.0,
      "grad_norm": 9.153244018554688,
      "kl": 0.0016897159675863804,
      "learning_rate": 2.5e-07,
      "loss": 0.0,
      "reward": 0.1202575417701155,
      "reward_std": 0.03390007340203738,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.11635129200294614,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.00390625,
      "step": 4
    },
    {
      "completion_length": 157.0625,
      "epoch": 2.5,
      "kl": 0.003887881402988569,
      "reward": 0.07775045488961041,
      "reward_std": 0.010330976816476323,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.07775045488961041,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 5,
      "total_flos": 0.0,
      "train_loss": 1.4945864677429199e-06,
      "train_runtime": 10897.8725,
      "train_samples_per_second": 0.007,
      "train_steps_per_second": 0.0
    }
  ],
  "logging_steps": 2,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 25,
  "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
}