{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 67,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 707.4456775665283,
      "epoch": 0.14925373134328357,
      "grad_norm": 0.06321819126605988,
      "kl": 0.006711304187774658,
      "learning_rate": 1.9876883405951378e-05,
      "loss": 0.0003,
      "reward": 0.5986607405939139,
      "reward_std": 0.16735767447389663,
      "rewards/accuracy_reward": 0.5986607405939139,
      "rewards/format_reward": 0.0,
      "step": 10
    },
    {
      "completion_length": 675.7138690948486,
      "epoch": 0.29850746268656714,
      "grad_norm": 0.07178156822919846,
      "kl": 0.025733184814453126,
      "learning_rate": 1.777145961456971e-05,
      "loss": 0.001,
      "reward": 0.6954241393133997,
      "reward_std": 0.16923737577162684,
      "rewards/accuracy_reward": 0.6954241393133997,
      "rewards/format_reward": 0.0,
      "step": 20
    },
    {
      "completion_length": 685.2908779144287,
      "epoch": 0.44776119402985076,
      "grad_norm": 0.07352711260318756,
      "kl": 0.02706298828125,
      "learning_rate": 1.3583679495453e-05,
      "loss": 0.0011,
      "reward": 0.6889509245753288,
      "reward_std": 0.15610567890107632,
      "rewards/accuracy_reward": 0.6889509245753288,
      "rewards/format_reward": 0.0,
      "step": 30
    },
    {
      "completion_length": 691.1547193527222,
      "epoch": 0.5970149253731343,
      "grad_norm": 0.059463296085596085,
      "kl": 0.03000030517578125,
      "learning_rate": 8.43565534959769e-06,
      "loss": 0.0012,
      "reward": 0.6849330635741353,
      "reward_std": 0.16573377684690058,
      "rewards/accuracy_reward": 0.6849330635741353,
      "rewards/format_reward": 0.0,
      "step": 40
    },
    {
      "completion_length": 690.842552947998,
      "epoch": 0.746268656716418,
      "grad_norm": 0.06777255237102509,
      "kl": 0.03056793212890625,
      "learning_rate": 3.7067960895016277e-06,
      "loss": 0.0012,
      "reward": 0.7001116393133998,
      "reward_std": 0.16762742078863085,
      "rewards/accuracy_reward": 0.7001116393133998,
      "rewards/format_reward": 0.0,
      "step": 50
    },
    {
      "completion_length": 668.4015930175781,
      "epoch": 0.8955223880597015,
      "grad_norm": 0.07001896947622299,
      "kl": 0.031087493896484374,
      "learning_rate": 6.641957350279838e-07,
      "loss": 0.0012,
      "reward": 0.7029018193483353,
      "reward_std": 0.16094307857565582,
      "rewards/accuracy_reward": 0.7029018193483353,
      "rewards/format_reward": 0.0,
      "step": 60
    },
    {
      "completion_length": 663.3861323765346,
      "epoch": 1.0,
      "kl": 0.03179168701171875,
      "reward": 0.7240115058209214,
      "reward_std": 0.1582813827054841,
      "rewards/accuracy_reward": 0.7240115058209214,
      "rewards/format_reward": 0.0,
      "step": 67,
      "total_flos": 0.0,
      "train_loss": 0.0010332457457126966,
      "train_runtime": 12336.334,
      "train_samples_per_second": 0.608,
      "train_steps_per_second": 0.005
    }
  ],
  "logging_steps": 10,
  "max_steps": 67,
  "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": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}