{
  "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": 593.7482410430908,
      "epoch": 0.14925373134328357,
      "grad_norm": 3.3375449180603027,
      "kl": 0.00016417205333709716,
      "learning_rate": 4.969220851487844e-07,
      "loss": 0.0,
      "reward": 0.6577009251341224,
      "reward_std": 0.33679639026522634,
      "rewards/accuracy_reward": 0.6577009251341224,
      "rewards/format_reward": 0.0,
      "step": 10
    },
    {
      "completion_length": 615.897794342041,
      "epoch": 0.29850746268656714,
      "grad_norm": 6.283264636993408,
      "kl": 0.0006311476230621338,
      "learning_rate": 4.442864903642427e-07,
      "loss": 0.0,
      "reward": 0.7003348525613546,
      "reward_std": 0.28909211745485663,
      "rewards/accuracy_reward": 0.7003348525613546,
      "rewards/format_reward": 0.0,
      "step": 20
    },
    {
      "completion_length": 627.0369699478149,
      "epoch": 0.44776119402985076,
      "grad_norm": 1.084415316581726,
      "kl": 0.0013591766357421875,
      "learning_rate": 3.39591987386325e-07,
      "loss": 0.0001,
      "reward": 0.7119419971480966,
      "reward_std": 0.26750571075826884,
      "rewards/accuracy_reward": 0.7119419971480966,
      "rewards/format_reward": 0.0,
      "step": 30
    },
    {
      "completion_length": 646.3926631927491,
      "epoch": 0.5970149253731343,
      "grad_norm": 0.20786528289318085,
      "kl": 0.0015711426734924317,
      "learning_rate": 2.1089138373994222e-07,
      "loss": 0.0001,
      "reward": 0.7162946753203869,
      "reward_std": 0.2570623795501888,
      "rewards/accuracy_reward": 0.7162946753203869,
      "rewards/format_reward": 0.0,
      "step": 40
    },
    {
      "completion_length": 644.9664350509644,
      "epoch": 0.746268656716418,
      "grad_norm": 0.18577325344085693,
      "kl": 0.0016170144081115723,
      "learning_rate": 9.266990223754067e-08,
      "loss": 0.0001,
      "reward": 0.717187531106174,
      "reward_std": 0.2541773657780141,
      "rewards/accuracy_reward": 0.717187531106174,
      "rewards/format_reward": 0.0,
      "step": 50
    },
    {
      "completion_length": 645.4328433990479,
      "epoch": 0.8955223880597015,
      "grad_norm": 0.10769952088594437,
      "kl": 0.001490175724029541,
      "learning_rate": 1.6604893375699592e-08,
      "loss": 0.0001,
      "reward": 0.710714316368103,
      "reward_std": 0.24781657787971198,
      "rewards/accuracy_reward": 0.710714316368103,
      "rewards/format_reward": 0.0,
      "step": 60
    },
    {
      "completion_length": 640.3468578883579,
      "epoch": 1.0,
      "kl": 0.0016015597752162389,
      "reward": 0.7274128685572318,
      "reward_std": 0.23784327866243465,
      "rewards/accuracy_reward": 0.7274128685572318,
      "rewards/format_reward": 0.0,
      "step": 67,
      "total_flos": 0.0,
      "train_loss": 4.8947690507404006e-05,
      "train_runtime": 12203.8092,
      "train_samples_per_second": 0.615,
      "train_steps_per_second": 0.005
    }
  ],
  "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
}