{
  "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": 321.7783631563187,
      "epoch": 0.14925373134328357,
      "grad_norm": 844.2005004882812,
      "kl": 0.26083906888961794,
      "learning_rate": 1.9876883405951378e-05,
      "loss": 0.0104,
      "reward": 0.8205357508268207,
      "reward_std": 0.3335492295213044,
      "rewards/accuracy_reward": 0.28281251178123057,
      "rewards/format_reward": 0.5377232346101664,
      "step": 10
    },
    {
      "completion_length": 957.0839672088623,
      "epoch": 0.29850746268656714,
      "grad_norm": 12.81620979309082,
      "kl": 1.9741607666015626,
      "learning_rate": 1.777145961456971e-05,
      "loss": 0.0792,
      "reward": 0.2691964411525987,
      "reward_std": 0.21028053476475178,
      "rewards/accuracy_reward": 0.23214286774164067,
      "rewards/format_reward": 0.03705357332946733,
      "step": 20
    },
    {
      "completion_length": 422.6559352874756,
      "epoch": 0.44776119402985076,
      "grad_norm": 5.399049758911133,
      "kl": 0.2251617431640625,
      "learning_rate": 1.3583679495453e-05,
      "loss": 0.009,
      "reward": 1.2597098806872964,
      "reward_std": 0.36119014574214814,
      "rewards/accuracy_reward": 0.47042412888258694,
      "rewards/format_reward": 0.7892857480794191,
      "step": 30
    },
    {
      "completion_length": 268.14699935913086,
      "epoch": 0.5970149253731343,
      "grad_norm": 0.5281020402908325,
      "kl": 0.1599884033203125,
      "learning_rate": 8.43565534959769e-06,
      "loss": 0.0064,
      "reward": 1.3410714894533158,
      "reward_std": 0.3691547209396958,
      "rewards/accuracy_reward": 0.41651787590235473,
      "rewards/format_reward": 0.9245536047965288,
      "step": 40
    },
    {
      "completion_length": 327.67679929733276,
      "epoch": 0.746268656716418,
      "grad_norm": 6.650570869445801,
      "kl": 0.163006591796875,
      "learning_rate": 3.7067960895016277e-06,
      "loss": 0.0065,
      "reward": 1.4162947066128253,
      "reward_std": 0.4063243476208299,
      "rewards/accuracy_reward": 0.5241071661934257,
      "rewards/format_reward": 0.8921875409781933,
      "step": 50
    },
    {
      "completion_length": 262.67713165283203,
      "epoch": 0.8955223880597015,
      "grad_norm": 0.2625133991241455,
      "kl": 0.1500396728515625,
      "learning_rate": 6.641957350279838e-07,
      "loss": 0.006,
      "reward": 1.5008929297327995,
      "reward_std": 0.31554799154400826,
      "rewards/accuracy_reward": 0.5521205643191933,
      "rewards/format_reward": 0.9487723533064127,
      "step": 60
    },
    {
      "completion_length": 279.1561552456447,
      "epoch": 1.0,
      "kl": 0.14893450055803573,
      "reward": 1.5041454716452531,
      "reward_std": 0.3543888473484133,
      "rewards/accuracy_reward": 0.5596301265593085,
      "rewards/format_reward": 0.9445153373692717,
      "step": 67,
      "total_flos": 0.0,
      "train_loss": 0.018138731037502857,
      "train_runtime": 11014.2043,
      "train_samples_per_second": 0.681,
      "train_steps_per_second": 0.006
    }
  ],
  "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
}