{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.7804878048780486,
  "eval_steps": 100,
  "global_step": 36,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 99.209375,
      "epoch": 0.7804878048780488,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.0,
      "rewards/format_reward": 0.0,
      "step": 10
    },
    {
      "completion_length": 99.01910828025478,
      "epoch": 1.5463414634146342,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 0.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.0,
      "rewards/format_reward": 0.0,
      "step": 20
    },
    {
      "completion_length": 98.6592356687898,
      "epoch": 2.3121951219512193,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 8.04909677983872e-06,
      "loss": 0.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.0,
      "rewards/format_reward": 0.0,
      "step": 30
    },
    {
      "completion_length": 98.4375,
      "epoch": 2.7804878048780486,
      "kl": 0.0,
      "reward": 0.0,
      "reward_std": 0.0,
      "rewards/accuracy_reward": 0.0,
      "rewards/format_reward": 0.0,
      "step": 36,
      "total_flos": 0.0,
      "train_loss": 0.0,
      "train_runtime": 171.9512,
      "train_samples_per_second": 3.577,
      "train_steps_per_second": 0.209
    }
  ],
  "logging_steps": 10,
  "max_steps": 36,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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
}