{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.625,
  "eval_steps": 500,
  "global_step": 100,
  "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,
      "completion_length": 256.0,
      "completions/clipped_ratio": 1.0,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 0.0,
      "completions/mean_length": 256.0,
      "completions/mean_terminated_length": 0.0,
      "completions/min_length": 256.0,
      "completions/min_terminated_length": 0.0,
      "epoch": 0.0625,
      "frac_reward_zero_std": 0.075,
      "grad_norm": 0.12458323687314987,
      "kl": 1.9381546007934957e-05,
      "learning_rate": 9.375000000000001e-06,
      "loss": 3.427267074584961e-08,
      "num_tokens": 57908.0,
      "reward": -1.4099999368190765,
      "reward_std": 0.7305359303951263,
      "rewards/reward_fn/mean": -1.409999930858612,
      "rewards/reward_fn/std": 0.8336655974388123,
      "step": 10
    },
    {
      "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,
      "completion_length": 256.0,
      "completions/clipped_ratio": 1.0,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 0.0,
      "completions/mean_length": 256.0,
      "completions/mean_terminated_length": 0.0,
      "completions/min_length": 256.0,
      "completions/min_terminated_length": 0.0,
      "epoch": 0.125,
      "frac_reward_zero_std": 0.05,
      "grad_norm": 0.13424909114837646,
      "kl": 3.758955572266132e-05,
      "learning_rate": 1.9791666666666665e-05,
      "loss": 2.0861625671386717e-08,
      "num_tokens": 115744.0,
      "reward": -1.5606249690055847,
      "reward_std": 0.6338691949844361,
      "rewards/reward_fn/mean": -1.5606249451637269,
      "rewards/reward_fn/std": 0.6913031578063965,
      "step": 20
    },
    {
      "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,
      "completion_length": 256.0,
      "completions/clipped_ratio": 1.0,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 0.0,
      "completions/mean_length": 256.0,
      "completions/mean_terminated_length": 0.0,
      "completions/min_length": 256.0,
      "completions/min_terminated_length": 0.0,
      "epoch": 0.1875,
      "frac_reward_zero_std": 0.025,
      "grad_norm": 0.12381561845541,
      "kl": 0.000246869730472099,
      "learning_rate": 3.0208333333333334e-05,
      "loss": 2.4400651454925537e-07,
      "num_tokens": 173524.0,
      "reward": -1.4581249356269836,
      "reward_std": 0.7430005550384522,
      "rewards/reward_fn/mean": -1.4581249117851258,
      "rewards/reward_fn/std": 0.7565619319677352,
      "step": 30
    },
    {
      "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,
      "completion_length": 256.0,
      "completions/clipped_ratio": 1.0,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 0.0,
      "completions/mean_length": 256.0,
      "completions/mean_terminated_length": 0.0,
      "completions/min_length": 256.0,
      "completions/min_terminated_length": 0.0,
      "epoch": 0.25,
      "frac_reward_zero_std": 0.025,
      "grad_norm": 0.14411121606826782,
      "kl": 0.0016107790230307727,
      "learning_rate": 4.0625000000000005e-05,
      "loss": 1.6100704669952392e-06,
      "num_tokens": 231416.0,
      "reward": -1.3331249535083771,
      "reward_std": 0.6972330152988434,
      "rewards/reward_fn/mean": -1.3331249415874482,
      "rewards/reward_fn/std": 0.766948527097702,
      "step": 40
    },
    {
      "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,
      "completion_length": 256.0,
      "completions/clipped_ratio": 1.0,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 0.0,
      "completions/mean_length": 256.0,
      "completions/mean_terminated_length": 0.0,
      "completions/min_length": 256.0,
      "completions/min_terminated_length": 0.0,
      "epoch": 0.3125,
      "frac_reward_zero_std": 0.175,
      "grad_norm": 0.14639103412628174,
      "kl": 0.007588638024753891,
      "learning_rate": 4.988425925925926e-05,
      "loss": 7.59512186050415e-06,
      "num_tokens": 289368.0,
      "reward": -1.0006249606609345,
      "reward_std": 0.6684236854314805,
      "rewards/reward_fn/mean": -1.0006249785423278,
      "rewards/reward_fn/std": 0.7909055948257446,
      "step": 50
    },
    {
      "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,
      "completion_length": 256.0,
      "completions/clipped_ratio": 1.0,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 0.0,
      "completions/mean_length": 256.0,
      "completions/mean_terminated_length": 0.0,
      "completions/min_length": 256.0,
      "completions/min_terminated_length": 0.0,
      "epoch": 0.375,
      "frac_reward_zero_std": 0.3,
      "grad_norm": 0.1545860469341278,
      "kl": 0.024985690240282566,
      "learning_rate": 4.8726851851851855e-05,
      "loss": 2.498328685760498e-05,
      "num_tokens": 346964.0,
      "reward": -0.6074999988079071,
      "reward_std": 0.5110155880451203,
      "rewards/reward_fn/mean": -0.6075000107288361,
      "rewards/reward_fn/std": 0.6012047231197357,
      "step": 60
    },
    {
      "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,
      "completion_length": 256.0,
      "completions/clipped_ratio": 1.0,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 0.0,
      "completions/mean_length": 256.0,
      "completions/mean_terminated_length": 0.0,
      "completions/min_length": 256.0,
      "completions/min_terminated_length": 0.0,
      "epoch": 0.4375,
      "frac_reward_zero_std": 0.725,
      "grad_norm": 0.12491069734096527,
      "kl": 0.042862199200317266,
      "learning_rate": 4.756944444444444e-05,
      "loss": 4.285752947907895e-05,
      "num_tokens": 404676.0,
      "reward": -0.41250000298023226,
      "reward_std": 0.19732050001621246,
      "rewards/reward_fn/mean": -0.41250000298023226,
      "rewards/reward_fn/std": 0.3099328398704529,
      "step": 70
    },
    {
      "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,
      "completion_length": 256.0,
      "completions/clipped_ratio": 1.0,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 0.0,
      "completions/mean_length": 256.0,
      "completions/mean_terminated_length": 0.0,
      "completions/min_length": 256.0,
      "completions/min_terminated_length": 0.0,
      "epoch": 0.5,
      "frac_reward_zero_std": 0.825,
      "grad_norm": 0.139762744307518,
      "kl": 0.05795831000432372,
      "learning_rate": 4.6412037037037034e-05,
      "loss": 5.795210599899292e-05,
      "num_tokens": 462404.0,
      "reward": -0.3443750023841858,
      "reward_std": 0.11552571803331375,
      "rewards/reward_fn/mean": -0.344375005364418,
      "rewards/reward_fn/std": 0.1971571922302246,
      "step": 80
    },
    {
      "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,
      "completion_length": 256.0,
      "completions/clipped_ratio": 1.0,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 0.0,
      "completions/mean_length": 256.0,
      "completions/mean_terminated_length": 0.0,
      "completions/min_length": 256.0,
      "completions/min_terminated_length": 0.0,
      "epoch": 0.5625,
      "frac_reward_zero_std": 0.9,
      "grad_norm": 0.0012635246384888887,
      "kl": 0.0758059567771852,
      "learning_rate": 4.525462962962963e-05,
      "loss": 7.580451783724129e-05,
      "num_tokens": 520292.0,
      "reward": -0.341250005364418,
      "reward_std": 0.06749999970197677,
      "rewards/reward_fn/mean": -0.34125000834465025,
      "rewards/reward_fn/std": 0.14239275455474854,
      "step": 90
    },
    {
      "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,
      "completion_length": 256.0,
      "completions/clipped_ratio": 1.0,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 0.0,
      "completions/mean_length": 256.0,
      "completions/mean_terminated_length": 0.0,
      "completions/min_length": 256.0,
      "completions/min_terminated_length": 0.0,
      "epoch": 0.625,
      "frac_reward_zero_std": 0.925,
      "grad_norm": 0.28265202045440674,
      "kl": 0.10205610543489456,
      "learning_rate": 4.4097222222222226e-05,
      "loss": 0.00010205432772636414,
      "num_tokens": 578164.0,
      "reward": -0.31062501221895217,
      "reward_std": 0.05374999940395355,
      "rewards/reward_fn/mean": -0.31062501221895217,
      "rewards/reward_fn/std": 0.0848927527666092,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 480,
  "num_input_tokens_seen": 578164,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}