{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9893390191897654,
  "eval_steps": 500,
  "global_step": 58,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 787.0493625640869,
      "epoch": 0.08528784648187633,
      "grad_norm": 0.5925782918930054,
      "kl": 0.00022783279418945313,
      "learning_rate": 2.5e-06,
      "loss": 0.1861,
      "reward": 0.6294643152505159,
      "reward_std": 0.37560802698135376,
      "rewards/accuracy_reward": 0.6283482428640127,
      "rewards/format_reward": 0.0011160714784637094,
      "step": 5
    },
    {
      "completion_length": 761.9397659301758,
      "epoch": 0.17057569296375266,
      "grad_norm": 0.26905158162117004,
      "kl": 0.11848912239074708,
      "learning_rate": 2.956412726139078e-06,
      "loss": 0.2277,
      "reward": 0.6962053876370191,
      "reward_std": 0.3356273040175438,
      "rewards/accuracy_reward": 0.6957589592784643,
      "rewards/format_reward": 0.00044642859138548373,
      "step": 10
    },
    {
      "completion_length": 690.9866397857666,
      "epoch": 0.255863539445629,
      "grad_norm": 0.41785764694213867,
      "kl": 0.004120731353759765,
      "learning_rate": 2.7836719084521715e-06,
      "loss": 0.1767,
      "reward": 0.7720982506871223,
      "reward_std": 0.23429525471292437,
      "rewards/accuracy_reward": 0.7720982506871223,
      "rewards/format_reward": 0.0,
      "step": 15
    },
    {
      "completion_length": 639.1794933319092,
      "epoch": 0.3411513859275053,
      "grad_norm": 0.18890324234962463,
      "kl": 0.004371070861816406,
      "learning_rate": 2.4946839873611927e-06,
      "loss": 0.0811,
      "reward": 0.8058036096394062,
      "reward_std": 0.19427869664505124,
      "rewards/accuracy_reward": 0.8058036096394062,
      "rewards/format_reward": 0.0,
      "step": 20
    },
    {
      "completion_length": 661.3855205535889,
      "epoch": 0.42643923240938164,
      "grad_norm": 0.10522360354661942,
      "kl": 0.04144001007080078,
      "learning_rate": 2.1156192081791355e-06,
      "loss": 0.0571,
      "reward": 0.8104911096394062,
      "reward_std": 0.1754706274252385,
      "rewards/accuracy_reward": 0.8104911096394062,
      "rewards/format_reward": 0.0,
      "step": 25
    },
    {
      "completion_length": 660.1663227081299,
      "epoch": 0.511727078891258,
      "grad_norm": 0.10592413693666458,
      "kl": 0.005521965026855469,
      "learning_rate": 1.6808050203829845e-06,
      "loss": 0.0425,
      "reward": 0.8000000387430191,
      "reward_std": 0.15711483028717338,
      "rewards/accuracy_reward": 0.8000000387430191,
      "rewards/format_reward": 0.0,
      "step": 30
    },
    {
      "completion_length": 656.0531524658203,
      "epoch": 0.5970149253731343,
      "grad_norm": 0.08047433197498322,
      "kl": 0.006989288330078125,
      "learning_rate": 1.2296174432791415e-06,
      "loss": 0.0544,
      "reward": 0.7861607529222965,
      "reward_std": 0.17227764171548188,
      "rewards/accuracy_reward": 0.7861607529222965,
      "rewards/format_reward": 0.0,
      "step": 35
    },
    {
      "completion_length": 637.837085723877,
      "epoch": 0.6823027718550106,
      "grad_norm": 0.0917467549443245,
      "kl": 0.00831298828125,
      "learning_rate": 8.029152419343472e-07,
      "loss": 0.0435,
      "reward": 0.8058036088943481,
      "reward_std": 0.1664866884239018,
      "rewards/accuracy_reward": 0.8058036088943481,
      "rewards/format_reward": 0.0,
      "step": 40
    },
    {
      "completion_length": 665.8060611724853,
      "epoch": 0.767590618336887,
      "grad_norm": 0.09342845529317856,
      "kl": 0.00903778076171875,
      "learning_rate": 4.3933982822017883e-07,
      "loss": 0.04,
      "reward": 0.7988839663565159,
      "reward_std": 0.17079528416506945,
      "rewards/accuracy_reward": 0.7988839663565159,
      "rewards/format_reward": 0.0,
      "step": 45
    },
    {
      "completion_length": 672.3283798217774,
      "epoch": 0.8528784648187633,
      "grad_norm": 0.10385381430387497,
      "kl": 0.009936904907226563,
      "learning_rate": 1.718159615201853e-07,
      "loss": 0.0402,
      "reward": 0.7877232532948255,
      "reward_std": 0.17090726913884283,
      "rewards/accuracy_reward": 0.7877232532948255,
      "rewards/format_reward": 0.0,
      "step": 50
    },
    {
      "completion_length": 653.8888690948486,
      "epoch": 0.9381663113006397,
      "grad_norm": 0.09379885345697403,
      "kl": 0.01168975830078125,
      "learning_rate": 2.4570139579284723e-08,
      "loss": 0.036,
      "reward": 0.8174107491970062,
      "reward_std": 0.17556129512377083,
      "rewards/accuracy_reward": 0.8174107491970062,
      "rewards/format_reward": 0.0,
      "step": 55
    },
    {
      "completion_length": 643.0528577168783,
      "epoch": 0.9893390191897654,
      "kl": 0.009972254435221354,
      "reward": 0.7979911093910536,
      "reward_std": 0.163272281565393,
      "rewards/accuracy_reward": 0.7979911093910536,
      "rewards/format_reward": 0.0,
      "step": 58,
      "total_flos": 0.0,
      "train_loss": 0.0899812507218328,
      "train_runtime": 42154.8272,
      "train_samples_per_second": 0.178,
      "train_steps_per_second": 0.001
    }
  ],
  "logging_steps": 5,
  "max_steps": 58,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}