{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 8,
  "global_step": 8,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "clip_ratio": 0.0,
      "completion_length": 866.75,
      "epoch": 0.125,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 3e-06,
      "loss": 0.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.0,
      "rewards/format_reward": 0.0,
      "step": 1
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 449.25,
      "epoch": 0.625,
      "grad_norm": 0.043186482042074203,
      "kl": 0.0009279251098632812,
      "learning_rate": 1.1662185990655286e-06,
      "loss": 0.0,
      "reward": 0.8125,
      "reward_std": 0.26933756470680237,
      "rewards/accuracy_reward": 0.8125,
      "rewards/format_reward": 0.0,
      "step": 5
    },
    {
      "epoch": 1.0,
      "eval_clip_ratio": 0.0,
      "eval_completion_length": 570.34375,
      "eval_kl": 0.0012311935424804688,
      "eval_loss": 4.939456994179636e-05,
      "eval_reward": 0.78125,
      "eval_reward_std": 0.27900634706020355,
      "eval_rewards/accuracy_reward": 0.78125,
      "eval_rewards/format_reward": 0.0,
      "eval_runtime": 78.5017,
      "eval_samples_per_second": 0.102,
      "eval_steps_per_second": 0.025,
      "step": 8
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 647.6666666666666,
      "epoch": 1.0,
      "kl": 0.0002209345499674479,
      "reward": 0.9166666666666666,
      "reward_std": 0.16666666666666666,
      "rewards/accuracy_reward": 0.9166666666666666,
      "rewards/format_reward": 0.0,
      "step": 8,
      "total_flos": 0.0,
      "train_loss": -0.062465423718094826,
      "train_runtime": 165.9317,
      "train_samples_per_second": 0.048,
      "train_steps_per_second": 0.048
    }
  ],
  "logging_steps": 5,
  "max_steps": 8,
  "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
}