{
  "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": 708.9171075820923,
      "epoch": 0.14925373134328357,
      "grad_norm": 0.06562932580709457,
      "kl": 0.005872213840484619,
      "learning_rate": 1.9876883405951378e-05,
      "loss": 0.0002,
      "reward": 0.603348241513595,
      "reward_std": 0.16946082445792854,
      "rewards/accuracy_reward": 0.603348241513595,
      "rewards/format_reward": 0.0,
      "step": 10
    },
    {
      "completion_length": 682.0505897521973,
      "epoch": 0.29850746268656714,
      "grad_norm": 0.05642814189195633,
      "kl": 0.024619293212890626,
      "learning_rate": 1.777145961456971e-05,
      "loss": 0.001,
      "reward": 0.7039062824100256,
      "reward_std": 0.162486822437495,
      "rewards/accuracy_reward": 0.7039062824100256,
      "rewards/format_reward": 0.0,
      "step": 20
    },
    {
      "completion_length": 680.5775978088379,
      "epoch": 0.44776119402985076,
      "grad_norm": 0.07271964848041534,
      "kl": 0.029143524169921876,
      "learning_rate": 1.3583679495453e-05,
      "loss": 0.0012,
      "reward": 0.6966518176719546,
      "reward_std": 0.15723272264003754,
      "rewards/accuracy_reward": 0.6966518176719546,
      "rewards/format_reward": 0.0,
      "step": 30
    },
    {
      "completion_length": 678.4286026000976,
      "epoch": 0.5970149253731343,
      "grad_norm": 0.06629566103219986,
      "kl": 0.029315948486328125,
      "learning_rate": 8.43565534959769e-06,
      "loss": 0.0012,
      "reward": 0.6925223540514708,
      "reward_std": 0.1698813715018332,
      "rewards/accuracy_reward": 0.6925223540514708,
      "rewards/format_reward": 0.0,
      "step": 40
    },
    {
      "completion_length": 678.2587354660034,
      "epoch": 0.746268656716418,
      "grad_norm": 0.07359491288661957,
      "kl": 0.03377456665039062,
      "learning_rate": 3.7067960895016277e-06,
      "loss": 0.0014,
      "reward": 0.6977678883820773,
      "reward_std": 0.1756029822397977,
      "rewards/accuracy_reward": 0.6977678883820773,
      "rewards/format_reward": 0.0,
      "step": 50
    },
    {
      "completion_length": 676.1143146514893,
      "epoch": 0.8955223880597015,
      "grad_norm": 0.07282646745443344,
      "kl": 0.03675537109375,
      "learning_rate": 6.641957350279838e-07,
      "loss": 0.0015,
      "reward": 0.6957589590921998,
      "reward_std": 0.167550537455827,
      "rewards/accuracy_reward": 0.6957589590921998,
      "rewards/format_reward": 0.0,
      "step": 60
    },
    {
      "completion_length": 673.9289711543491,
      "epoch": 1.0,
      "kl": 0.03508213588169643,
      "reward": 0.7025404186653239,
      "reward_std": 0.1512090131374342,
      "rewards/accuracy_reward": 0.7025404186653239,
      "rewards/format_reward": 0.0,
      "step": 67,
      "total_flos": 0.0,
      "train_loss": 0.001102253468012187,
      "train_runtime": 12358.4402,
      "train_samples_per_second": 0.607,
      "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
}