{
  "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": 596.383843612671,
      "epoch": 0.14925373134328357,
      "grad_norm": 1.5561689138412476,
      "kl": 0.00016396641731262208,
      "learning_rate": 4.969220851487844e-07,
      "loss": 0.0,
      "reward": 0.6462053874507546,
      "reward_std": 0.3416209638118744,
      "rewards/accuracy_reward": 0.6462053874507546,
      "rewards/format_reward": 0.0,
      "step": 10
    },
    {
      "completion_length": 613.4104093551636,
      "epoch": 0.29850746268656714,
      "grad_norm": 0.9943106174468994,
      "kl": 0.0006253421306610107,
      "learning_rate": 4.442864903642427e-07,
      "loss": 0.0,
      "reward": 0.6948661018162966,
      "reward_std": 0.29683467308059336,
      "rewards/accuracy_reward": 0.6948661018162966,
      "rewards/format_reward": 0.0,
      "step": 20
    },
    {
      "completion_length": 636.3029315948486,
      "epoch": 0.44776119402985076,
      "grad_norm": 0.27561211585998535,
      "kl": 0.0012180805206298828,
      "learning_rate": 3.39591987386325e-07,
      "loss": 0.0,
      "reward": 0.7084821751341224,
      "reward_std": 0.27429150431416927,
      "rewards/accuracy_reward": 0.7084821751341224,
      "rewards/format_reward": 0.0,
      "step": 30
    },
    {
      "completion_length": 651.3704532623291,
      "epoch": 0.5970149253731343,
      "grad_norm": 0.3878922164440155,
      "kl": 0.001651430130004883,
      "learning_rate": 2.1089138373994222e-07,
      "loss": 0.0001,
      "reward": 0.7032366400584579,
      "reward_std": 0.26457019480876626,
      "rewards/accuracy_reward": 0.7032366400584579,
      "rewards/format_reward": 0.0,
      "step": 40
    },
    {
      "completion_length": 644.3892013549805,
      "epoch": 0.746268656716418,
      "grad_norm": 0.3261668384075165,
      "kl": 0.0016104459762573242,
      "learning_rate": 9.266990223754067e-08,
      "loss": 0.0001,
      "reward": 0.7097098544239998,
      "reward_std": 0.26254362566396594,
      "rewards/accuracy_reward": 0.7097098544239998,
      "rewards/format_reward": 0.0,
      "step": 50
    },
    {
      "completion_length": 641.7110774993896,
      "epoch": 0.8955223880597015,
      "grad_norm": 2.3543267250061035,
      "kl": 0.0013487815856933593,
      "learning_rate": 1.6604893375699592e-08,
      "loss": 0.0001,
      "reward": 0.7136161051690578,
      "reward_std": 0.2510954296216369,
      "rewards/accuracy_reward": 0.7136161051690578,
      "rewards/format_reward": 0.0,
      "step": 60
    },
    {
      "completion_length": 646.1266215188163,
      "epoch": 1.0,
      "kl": 0.001485262598310198,
      "reward": 0.7284226518656526,
      "reward_std": 0.23733017427314604,
      "rewards/accuracy_reward": 0.7284226518656526,
      "rewards/format_reward": 0.0,
      "step": 67,
      "total_flos": 0.0,
      "train_loss": 4.564031362168686e-05,
      "train_runtime": 12285.3838,
      "train_samples_per_second": 0.61,
      "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
}