{
  "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": 469.26162589788436,
      "epoch": 0.14925373134328357,
      "grad_norm": 158.0776824951172,
      "kl": 0.522365927696228,
      "learning_rate": 1.9876883405951378e-05,
      "loss": 0.0209,
      "reward": 0.36372769413283096,
      "reward_std": 0.23131797942332924,
      "rewards/accuracy_reward": 0.11350446951109916,
      "rewards/format_reward": 0.25022322274744513,
      "step": 10
    },
    {
      "completion_length": 55.07768114209175,
      "epoch": 0.29850746268656714,
      "grad_norm": 930.0825805664062,
      "kl": 109.860009765625,
      "learning_rate": 1.777145961456971e-05,
      "loss": 4.4045,
      "reward": 1.2064732640981675,
      "reward_std": 0.2529828853905201,
      "rewards/accuracy_reward": 0.2789062637137249,
      "rewards/format_reward": 0.9275669876486063,
      "step": 20
    },
    {
      "completion_length": 30.540961265563965,
      "epoch": 0.44776119402985076,
      "grad_norm": 1.2762861251831055,
      "kl": 0.80147705078125,
      "learning_rate": 1.3583679495453e-05,
      "loss": 0.0321,
      "reward": 1.2282366633415223,
      "reward_std": 0.16877365885302426,
      "rewards/accuracy_reward": 0.23794644025620074,
      "rewards/format_reward": 0.9902901940047741,
      "step": 30
    },
    {
      "completion_length": 41.73939917087555,
      "epoch": 0.5970149253731343,
      "grad_norm": 0.4882577359676361,
      "kl": 0.73848876953125,
      "learning_rate": 8.43565534959769e-06,
      "loss": 0.0295,
      "reward": 1.2350447032600642,
      "reward_std": 0.20153872366063297,
      "rewards/accuracy_reward": 0.24877233271254226,
      "rewards/format_reward": 0.9862723421305418,
      "step": 40
    },
    {
      "completion_length": 191.30971891880034,
      "epoch": 0.746268656716418,
      "grad_norm": 0.4109732210636139,
      "kl": 0.367132568359375,
      "learning_rate": 3.7067960895016277e-06,
      "loss": 0.0147,
      "reward": 1.1986607703613117,
      "reward_std": 0.3550489211920649,
      "rewards/accuracy_reward": 0.38348216039594263,
      "rewards/format_reward": 0.8151786073227413,
      "step": 50
    },
    {
      "completion_length": 255.62713146209717,
      "epoch": 0.8955223880597015,
      "grad_norm": 0.2800893783569336,
      "kl": 0.1984527587890625,
      "learning_rate": 6.641957350279838e-07,
      "loss": 0.0079,
      "reward": 1.4333706043660641,
      "reward_std": 0.32061776854097845,
      "rewards/accuracy_reward": 0.48337055975571275,
      "rewards/format_reward": 0.9500000335276126,
      "step": 60
    },
    {
      "completion_length": 287.7824833733695,
      "epoch": 1.0,
      "kl": 0.157440185546875,
      "reward": 1.47985762996333,
      "reward_std": 0.3193885385990143,
      "rewards/accuracy_reward": 0.5188669421310935,
      "rewards/format_reward": 0.9609906737293515,
      "step": 67,
      "total_flos": 0.0,
      "train_loss": 0.6738471064660976,
      "train_runtime": 7514.6892,
      "train_samples_per_second": 0.998,
      "train_steps_per_second": 0.009
    }
  ],
  "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
}