{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 10,
  "global_step": 188,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 559.6541828155517,
      "epoch": 0.05333333333333334,
      "grad_norm": 0.13850688934326172,
      "kl": 0.000306999683380127,
      "learning_rate": 1.60427807486631e-05,
      "loss": 0.016,
      "reward": 0.02916666753590107,
      "reward_std": 0.07144345119595527,
      "rewards/accuracy_reward": 0.02916666753590107,
      "rewards/format_reward": 0.0,
      "step": 10
    },
    {
      "completion_length": 563.3125160217285,
      "epoch": 0.10666666666666667,
      "grad_norm": 0.0018512221286073327,
      "kl": 0.00039801597595214846,
      "learning_rate": 3.20855614973262e-05,
      "loss": -0.0104,
      "reward": 0.01666666716337204,
      "reward_std": 0.03332236036658287,
      "rewards/accuracy_reward": 0.01666666716337204,
      "rewards/format_reward": 0.0,
      "step": 20
    },
    {
      "completion_length": 568.7541816711425,
      "epoch": 0.16,
      "grad_norm": 0.08763159811496735,
      "kl": 0.0006775140762329101,
      "learning_rate": 4.8128342245989304e-05,
      "loss": 0.0221,
      "reward": 0.02500000074505806,
      "reward_std": 0.05373477563261986,
      "rewards/accuracy_reward": 0.02500000074505806,
      "rewards/format_reward": 0.0,
      "step": 30
    },
    {
      "completion_length": 544.433352279663,
      "epoch": 0.21333333333333335,
      "grad_norm": 0.07478004693984985,
      "kl": 0.0009945392608642577,
      "learning_rate": 6.41711229946524e-05,
      "loss": -0.007,
      "reward": 0.03750000074505806,
      "reward_std": 0.07493030950427056,
      "rewards/accuracy_reward": 0.03750000074505806,
      "rewards/format_reward": 0.0,
      "step": 40
    },
    {
      "completion_length": 558.0416824340821,
      "epoch": 0.26666666666666666,
      "grad_norm": 0.0056296749971807,
      "kl": 0.0018447399139404296,
      "learning_rate": 8.021390374331551e-05,
      "loss": -0.0183,
      "reward": 0.03333333432674408,
      "reward_std": 0.07414718866348266,
      "rewards/accuracy_reward": 0.03333333432674408,
      "rewards/format_reward": 0.0,
      "step": 50
    },
    {
      "completion_length": 514.7416809082031,
      "epoch": 0.32,
      "grad_norm": 0.04819507524371147,
      "kl": 0.004059267044067383,
      "learning_rate": 9.625668449197861e-05,
      "loss": 0.0222,
      "reward": 0.03750000074505806,
      "reward_std": 0.06742783784866332,
      "rewards/accuracy_reward": 0.03750000074505806,
      "rewards/format_reward": 0.0,
      "step": 60
    },
    {
      "completion_length": 492.67084846496584,
      "epoch": 0.37333333333333335,
      "grad_norm": 0.017955631017684937,
      "kl": 0.00576171875,
      "learning_rate": 0.0001122994652406417,
      "loss": -0.0364,
      "reward": 0.06250000149011611,
      "reward_std": 0.12116261124610901,
      "rewards/accuracy_reward": 0.06250000149011611,
      "rewards/format_reward": 0.0,
      "step": 70
    },
    {
      "completion_length": 547.7750144958496,
      "epoch": 0.4266666666666667,
      "grad_norm": 0.1688847839832306,
      "kl": 0.008740234375,
      "learning_rate": 0.0001283422459893048,
      "loss": 0.0085,
      "reward": 0.06666666865348816,
      "reward_std": 0.12578697204589845,
      "rewards/accuracy_reward": 0.06666666865348816,
      "rewards/format_reward": 0.0,
      "step": 80
    },
    {
      "completion_length": 456.55834770202637,
      "epoch": 0.48,
      "grad_norm": 0.05612310767173767,
      "kl": 0.0114776611328125,
      "learning_rate": 0.0001443850267379679,
      "loss": -0.006,
      "reward": 0.12500000186264515,
      "reward_std": 0.18614107817411424,
      "rewards/accuracy_reward": 0.12500000186264515,
      "rewards/format_reward": 0.0,
      "step": 90
    },
    {
      "completion_length": 521.2875152587891,
      "epoch": 0.5333333333333333,
      "grad_norm": 0.06599655747413635,
      "kl": 0.018022537231445312,
      "learning_rate": 0.00016042780748663101,
      "loss": 0.0321,
      "reward": 0.1625000037252903,
      "reward_std": 0.2668332472443581,
      "rewards/accuracy_reward": 0.1625000037252903,
      "rewards/format_reward": 0.0,
      "step": 100
    },
    {
      "completion_length": 578.708349609375,
      "epoch": 0.5866666666666667,
      "grad_norm": 0.10739815980195999,
      "kl": 0.02028350830078125,
      "learning_rate": 0.0001764705882352941,
      "loss": 0.0315,
      "reward": 0.1541666690260172,
      "reward_std": 0.22565403282642366,
      "rewards/accuracy_reward": 0.1541666690260172,
      "rewards/format_reward": 0.0,
      "step": 110
    },
    {
      "completion_length": 578.1541816711426,
      "epoch": 0.64,
      "grad_norm": 0.059991322457790375,
      "kl": 0.0370635986328125,
      "learning_rate": 0.00019251336898395722,
      "loss": 0.0516,
      "reward": 0.13333333656191826,
      "reward_std": 0.1974847875535488,
      "rewards/accuracy_reward": 0.13333333656191826,
      "rewards/format_reward": 0.0,
      "step": 120
    },
    {
      "completion_length": 530.4750141143799,
      "epoch": 0.6933333333333334,
      "grad_norm": 0.30204519629478455,
      "kl": 0.07847900390625,
      "learning_rate": 0.0002085561497326203,
      "loss": -0.0095,
      "reward": 0.09166666865348816,
      "reward_std": 0.1606755696237087,
      "rewards/accuracy_reward": 0.09166666865348816,
      "rewards/format_reward": 0.0,
      "step": 130
    },
    {
      "completion_length": 473.15001449584963,
      "epoch": 0.7466666666666667,
      "grad_norm": 0.04992169886827469,
      "kl": 0.194708251953125,
      "learning_rate": 0.0002245989304812834,
      "loss": 0.0413,
      "reward": 0.10833333544433117,
      "reward_std": 0.17916736453771592,
      "rewards/accuracy_reward": 0.10833333544433117,
      "rewards/format_reward": 0.0,
      "step": 140
    },
    {
      "completion_length": 538.2416828155517,
      "epoch": 0.8,
      "grad_norm": 0.08135983347892761,
      "kl": 0.5037109375,
      "learning_rate": 0.0002406417112299465,
      "loss": 0.0135,
      "reward": 0.03750000111758709,
      "reward_std": 0.08435339704155922,
      "rewards/accuracy_reward": 0.03750000111758709,
      "rewards/format_reward": 0.0,
      "step": 150
    },
    {
      "completion_length": 475.47501335144045,
      "epoch": 0.8533333333333334,
      "grad_norm": 0.2563917338848114,
      "kl": 0.57646484375,
      "learning_rate": 0.0002566844919786096,
      "loss": -0.0059,
      "reward": 0.07916666865348816,
      "reward_std": 0.16198744028806686,
      "rewards/accuracy_reward": 0.07916666865348816,
      "rewards/format_reward": 0.0,
      "step": 160
    },
    {
      "completion_length": 380.40834312438966,
      "epoch": 0.9066666666666666,
      "grad_norm": 0.1821465641260147,
      "kl": 0.9548828125,
      "learning_rate": 0.0002727272727272727,
      "loss": -0.0106,
      "reward": 0.07083333469927311,
      "reward_std": 0.13215193897485733,
      "rewards/accuracy_reward": 0.07083333469927311,
      "rewards/format_reward": 0.0,
      "step": 170
    },
    {
      "completion_length": 308.63750953674315,
      "epoch": 0.96,
      "grad_norm": 0.09076907485723495,
      "kl": 0.826904296875,
      "learning_rate": 0.0002887700534759358,
      "loss": 0.0082,
      "reward": 0.05833333469927311,
      "reward_std": 0.09595146998763085,
      "rewards/accuracy_reward": 0.05833333469927311,
      "rewards/format_reward": 0.0,
      "step": 180
    }
  ],
  "logging_steps": 10,
  "max_steps": 1870,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}