{
  "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": 789.554499053955,
      "epoch": 0.14925373134328357,
      "grad_norm": 0.043297264724969864,
      "kl": 0.004566696286201477,
      "learning_rate": 1.9876883405951378e-05,
      "loss": 0.0002,
      "reward": 0.4319196644704789,
      "reward_std": 0.20852676765061914,
      "rewards/accuracy_reward": 0.4319196644704789,
      "rewards/format_reward": 0.0,
      "step": 10
    },
    {
      "completion_length": 734.4851900100708,
      "epoch": 0.29850746268656714,
      "grad_norm": 0.16099897027015686,
      "kl": 0.03243827819824219,
      "learning_rate": 1.777145961456971e-05,
      "loss": 0.0013,
      "reward": 0.5745535990223288,
      "reward_std": 0.20332427299581468,
      "rewards/accuracy_reward": 0.5745535990223288,
      "rewards/format_reward": 0.0,
      "step": 20
    },
    {
      "completion_length": 721.6080696105957,
      "epoch": 0.44776119402985076,
      "grad_norm": 0.06975095719099045,
      "kl": 0.05985336303710938,
      "learning_rate": 1.3583679495453e-05,
      "loss": 0.0024,
      "reward": 0.5524553818628192,
      "reward_std": 0.20610087024979293,
      "rewards/accuracy_reward": 0.5524553818628192,
      "rewards/format_reward": 0.0,
      "step": 30
    },
    {
      "completion_length": 745.682396697998,
      "epoch": 0.5970149253731343,
      "grad_norm": 0.2870137095451355,
      "kl": 0.1195068359375,
      "learning_rate": 8.43565534959769e-06,
      "loss": 0.0048,
      "reward": 0.531361632142216,
      "reward_std": 0.23335362751968206,
      "rewards/accuracy_reward": 0.531361632142216,
      "rewards/format_reward": 0.0,
      "step": 40
    },
    {
      "completion_length": 746.5999227523804,
      "epoch": 0.746268656716418,
      "grad_norm": 0.15197083353996277,
      "kl": 0.18003997802734376,
      "learning_rate": 3.7067960895016277e-06,
      "loss": 0.0072,
      "reward": 0.5380580605007708,
      "reward_std": 0.22012359318323432,
      "rewards/accuracy_reward": 0.5380580605007708,
      "rewards/format_reward": 0.0,
      "step": 50
    },
    {
      "completion_length": 730.7483596801758,
      "epoch": 0.8955223880597015,
      "grad_norm": 0.07760823518037796,
      "kl": 0.1339630126953125,
      "learning_rate": 6.641957350279838e-07,
      "loss": 0.0054,
      "reward": 0.5560268121771514,
      "reward_std": 0.21179640120826662,
      "rewards/accuracy_reward": 0.5560268121771514,
      "rewards/format_reward": 0.0,
      "step": 60
    },
    {
      "completion_length": 728.2434926714216,
      "epoch": 1.0,
      "kl": 0.10872977120535714,
      "reward": 0.5656356508178371,
      "reward_std": 0.20917304552027158,
      "rewards/accuracy_reward": 0.5656356508178371,
      "rewards/format_reward": 0.0,
      "step": 67,
      "total_flos": 0.0,
      "train_loss": 0.0036342136384641278,
      "train_runtime": 9992.8459,
      "train_samples_per_second": 0.751,
      "train_steps_per_second": 0.007
    }
  ],
  "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
}