{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.992,
  "eval_steps": 500,
  "global_step": 31,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "clip_ratio": 0.0,
      "completion_length": 503.94140625,
      "epoch": 0.32,
      "grad_norm": 0.055206917226314545,
      "kl": 0.0007647275924682617,
      "learning_rate": 1.5289640103269626e-05,
      "loss": -0.0178,
      "num_tokens": 837177.0,
      "reward": 0.14900912609314218,
      "reward_std": 0.23200407949070723,
      "rewards/_accuracy_reward": 0.14900912609314218,
      "rewards/_format_reward": 0.0,
      "step": 10
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 513.55390625,
      "epoch": 0.64,
      "grad_norm": 0.048017717897892,
      "kl": 0.0019702911376953125,
      "learning_rate": 5.5960584844236565e-06,
      "loss": 0.0085,
      "num_tokens": 1686614.0,
      "reward": 0.20446404698841433,
      "reward_std": 0.26745549326642504,
      "rewards/_accuracy_reward": 0.20446404698841433,
      "rewards/_format_reward": 0.0,
      "step": 20
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 525.440625,
      "epoch": 0.96,
      "grad_norm": 0.049744077026844025,
      "kl": 0.002144050598144531,
      "learning_rate": 5.1306766081048456e-08,
      "loss": 0.0187,
      "num_tokens": 2550850.0,
      "reward": 0.23339965324412332,
      "reward_std": 0.3011114658700535,
      "rewards/_accuracy_reward": 0.23339965324412332,
      "rewards/_format_reward": 0.0,
      "step": 30
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 546.765625,
      "epoch": 0.992,
      "kl": 0.0019164085388183594,
      "num_tokens": 2640088.0,
      "reward": 0.1563290636986494,
      "reward_std": 0.2728244187310338,
      "rewards/_accuracy_reward": 0.1563290636986494,
      "rewards/_format_reward": 0.0,
      "step": 31,
      "total_flos": 0.0,
      "train_loss": 0.0035367666953994383,
      "train_runtime": 25807.2718,
      "train_samples_per_second": 0.039,
      "train_steps_per_second": 0.001
    }
  ],
  "logging_steps": 10,
  "max_steps": 31,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "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": 8,
  "trial_name": null,
  "trial_params": null
}