{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9790209790209791,
  "eval_steps": 500,
  "global_step": 35,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "clip_ratio": 0.0,
      "completion_length": 1954.0179138183594,
      "epoch": 0.027972027972027972,
      "grad_norm": 0.06958208978176117,
      "kl": 0.0,
      "learning_rate": 5e-06,
      "loss": 0.0105,
      "reward": 0.1316964365541935,
      "reward_std": 0.09034644812345505,
      "rewards/code_reward": 0.1316964365541935,
      "step": 1
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1942.4365810818142,
      "epoch": 0.27972027972027974,
      "grad_norm": 0.09030569344758987,
      "kl": 0.010952697859870063,
      "learning_rate": 1.8386870970865488e-05,
      "loss": 0.0078,
      "reward": 0.14115640407221186,
      "reward_std": 0.07494163533879651,
      "rewards/code_reward": 0.14115640407221186,
      "step": 10
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1886.2473937988282,
      "epoch": 0.5594405594405595,
      "grad_norm": 0.09897836297750473,
      "kl": 0.0487396240234375,
      "learning_rate": 1.0544157480451586e-05,
      "loss": 0.0126,
      "reward": 0.16140213604085146,
      "reward_std": 0.07699124878272415,
      "rewards/code_reward": 0.16140213604085146,
      "step": 20
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1932.8143585205078,
      "epoch": 0.8391608391608392,
      "grad_norm": 0.08572351187467575,
      "kl": 0.09188232421875,
      "learning_rate": 3.1308804546987615e-06,
      "loss": 0.0135,
      "reward": 0.13120310104131933,
      "reward_std": 0.07072200049005914,
      "rewards/code_reward": 0.13120310104131933,
      "step": 30
    },
    {
      "clip_ratio": 0.0,
      "completion_length": 1913.047674560547,
      "epoch": 0.9790209790209791,
      "kl": 0.1061767578125,
      "reward": 0.1406746106222272,
      "reward_std": 0.06878119893372059,
      "rewards/code_reward": 0.1406746106222272,
      "step": 35,
      "total_flos": 0.0,
      "train_loss": 0.011042823908584458,
      "train_runtime": 4637.2308,
      "train_samples_per_second": 0.216,
      "train_steps_per_second": 0.008
    }
  ],
  "logging_steps": 10,
  "max_steps": 35,
  "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": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}