{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.24096385542168675,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 63.5,
      "completions/max_terminated_length": 63.5,
      "completions/mean_length": 35.0,
      "completions/mean_terminated_length": 35.0,
      "completions/min_length": 14.0,
      "completions/min_terminated_length": 14.0,
      "epoch": 0.04819277108433735,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 17.314556121826172,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": 0.0107,
      "num_tokens": 1304.0,
      "reward": 0.12473818846046925,
      "reward_std": 0.026818931568413973,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.0,
      "rewards/consensus_reward_func/std": 0.0,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 0.0,
      "rewards/final_correctness_reward_func/std": 0.0,
      "rewards/question_recreation_reward_func/mean": 0.12473818846046925,
      "rewards/question_recreation_reward_func/std": 0.0307374969124794,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.0,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 0.0,
      "rewards/xmlcount_reward_func/std": 0.0,
      "step": 2
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 72.5,
      "completions/max_terminated_length": 72.5,
      "completions/mean_length": 43.625,
      "completions/mean_terminated_length": 43.625,
      "completions/min_length": 24.0,
      "completions/min_terminated_length": 24.0,
      "epoch": 0.0963855421686747,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 43.791683197021484,
      "kl": 0.0040386376567767,
      "learning_rate": 4.415111107797445e-07,
      "loss": -0.0489,
      "num_tokens": 2677.0,
      "reward": 0.0236467644572258,
      "reward_std": 0.00882497476413846,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.0,
      "rewards/consensus_reward_func/std": 0.0,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 0.0,
      "rewards/final_correctness_reward_func/std": 0.0,
      "rewards/question_recreation_reward_func/mean": 0.023646765388548374,
      "rewards/question_recreation_reward_func/std": 0.007400925969704986,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.0,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 0.0,
      "rewards/xmlcount_reward_func/std": 0.0,
      "step": 4
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 77.0,
      "completions/max_terminated_length": 77.0,
      "completions/mean_length": 39.75,
      "completions/mean_terminated_length": 39.75,
      "completions/min_length": 16.5,
      "completions/min_terminated_length": 16.5,
      "epoch": 0.14457831325301204,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 39.4578857421875,
      "kl": 0.0063580243731848896,
      "learning_rate": 2.934120444167326e-07,
      "loss": 0.0318,
      "num_tokens": 4019.0,
      "reward": 0.12428901437669992,
      "reward_std": 0.030817807652056217,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.0,
      "rewards/consensus_reward_func/std": 0.0,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 0.0,
      "rewards/final_correctness_reward_func/std": 0.0,
      "rewards/question_recreation_reward_func/mean": 0.12428901344537735,
      "rewards/question_recreation_reward_func/std": 0.030232174787670374,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.0,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 0.0,
      "rewards/xmlcount_reward_func/std": 0.0,
      "step": 6
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 91.0,
      "completions/max_terminated_length": 91.0,
      "completions/mean_length": 51.875,
      "completions/mean_terminated_length": 51.875,
      "completions/min_length": 22.5,
      "completions/min_terminated_length": 22.5,
      "epoch": 0.1927710843373494,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 43.962554931640625,
      "kl": 0.010772253677714616,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.0536,
      "num_tokens": 5458.0,
      "reward": 0.10668943636119366,
      "reward_std": 0.03776418976485729,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.0,
      "rewards/consensus_reward_func/std": 0.0,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 0.0,
      "rewards/final_correctness_reward_func/std": 0.0,
      "rewards/question_recreation_reward_func/mean": 0.10668943636119366,
      "rewards/question_recreation_reward_func/std": 0.03313516452908516,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.0,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 0.0,
      "rewards/xmlcount_reward_func/std": 0.0,
      "step": 8
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.125,
      "completions/max_length": 154.0,
      "completions/max_terminated_length": 94.0,
      "completions/mean_length": 69.375,
      "completions/mean_terminated_length": 44.54166603088379,
      "completions/min_length": 14.5,
      "completions/min_terminated_length": 14.5,
      "epoch": 0.24096385542168675,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 17.73666763305664,
      "kl": 0.008697476470842957,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0032,
      "num_tokens": 7037.0,
      "reward": 0.10204933770000935,
      "reward_std": 0.03418661467730999,
      "rewards/concensus_correctness_reward_func/mean": 0.0,
      "rewards/concensus_correctness_reward_func/std": 0.0,
      "rewards/consensus_reward_func/mean": 0.0,
      "rewards/consensus_reward_func/std": 0.0,
      "rewards/cumulative_reward_2/mean": 0.0,
      "rewards/cumulative_reward_2/std": 0.0,
      "rewards/final_correctness_reward_func/mean": 0.0,
      "rewards/final_correctness_reward_func/std": 0.0,
      "rewards/question_recreation_reward_func/mean": 0.10204933770000935,
      "rewards/question_recreation_reward_func/std": 0.04046265175566077,
      "rewards/soft_format_reward_func/mean": 0.0,
      "rewards/soft_format_reward_func/std": 0.0,
      "rewards/strict_format_reward_func/mean": 0.0,
      "rewards/strict_format_reward_func/std": 0.0,
      "rewards/xmlcount_reward_func/mean": 0.0,
      "rewards/xmlcount_reward_func/std": 0.0,
      "step": 10
    },
    {
      "epoch": 0.24096385542168675,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 0.010071155428886414,
      "train_runtime": 2283.2649,
      "train_samples_per_second": 0.018,
      "train_steps_per_second": 0.004
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 7037,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": 2,
  "trial_name": null,
  "trial_params": null
}