{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.625,
  "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,
      "completion_length": 2.375,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 3.0,
      "completions/max_terminated_length": 3.0,
      "completions/mean_length": 2.375,
      "completions/mean_terminated_length": 2.375,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.0625,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 5.300995349884033,
      "kl": 0.0,
      "learning_rate": 0.0,
      "loss": 0.01562187448143959,
      "num_tokens": 8343.0,
      "reward": 0.125,
      "reward_std": 0.25,
      "rewards/reward_from_oracle/mean": 0.125,
      "rewards/reward_from_oracle/std": 0.3535533845424652,
      "step": 1
    },
    {
      "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": 2.375,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 3.0,
      "completions/max_terminated_length": 3.0,
      "completions/mean_length": 2.375,
      "completions/mean_terminated_length": 2.375,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.125,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 9.095938682556152,
      "kl": 0.0,
      "learning_rate": 5e-06,
      "loss": 0.029151180759072304,
      "num_tokens": 16682.0,
      "reward": 0.375,
      "reward_std": 0.5386751294136047,
      "rewards/reward_from_oracle/mean": 0.375,
      "rewards/reward_from_oracle/std": 0.5175492167472839,
      "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,
      "completion_length": 2.375,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 3.0,
      "completions/max_terminated_length": 3.0,
      "completions/mean_length": 2.375,
      "completions/mean_terminated_length": 2.375,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.1875,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 8.75147533416748,
      "kl": 0.0,
      "learning_rate": 4.849231551964771e-06,
      "loss": 0.023432811722159386,
      "num_tokens": 25025.0,
      "reward": 0.25,
      "reward_std": 0.5,
      "rewards/reward_from_oracle/mean": 0.25,
      "rewards/reward_from_oracle/std": 0.4629100561141968,
      "step": 3
    },
    {
      "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": 2.125,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 3.0,
      "completions/max_terminated_length": 3.0,
      "completions/mean_length": 2.125,
      "completions/mean_terminated_length": 2.125,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.25,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 10.478106498718262,
      "kl": 0.0,
      "learning_rate": 4.415111107797445e-06,
      "loss": 0.013529304414987564,
      "num_tokens": 33362.0,
      "reward": 0.5,
      "reward_std": 0.5773502588272095,
      "rewards/reward_from_oracle/mean": 0.5,
      "rewards/reward_from_oracle/std": 0.5345224738121033,
      "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,
      "completion_length": 2.125,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 3.0,
      "completions/max_terminated_length": 3.0,
      "completions/mean_length": 2.125,
      "completions/mean_terminated_length": 2.125,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.3125,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 8.125267028808594,
      "kl": 0.0,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.013529304414987564,
      "num_tokens": 41707.0,
      "reward": 0.625,
      "reward_std": 0.5386751294136047,
      "rewards/reward_from_oracle/mean": 0.625,
      "rewards/reward_from_oracle/std": 0.5175492167472839,
      "step": 5
    },
    {
      "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": 2.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 2.0,
      "completions/max_terminated_length": 2.0,
      "completions/mean_length": 2.0,
      "completions/mean_terminated_length": 2.0,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.375,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 3.183867931365967,
      "kl": 0.0,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 0.0,
      "num_tokens": 50047.0,
      "reward": 0.875,
      "reward_std": 0.25,
      "rewards/reward_from_oracle/mean": 0.875,
      "rewards/reward_from_oracle/std": 0.3535533845424652,
      "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,
      "completion_length": 2.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 2.0,
      "completions/max_terminated_length": 2.0,
      "completions/mean_length": 2.0,
      "completions/mean_terminated_length": 2.0,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.4375,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 7.007436275482178,
      "kl": 0.0,
      "learning_rate": 2.0658795558326745e-06,
      "loss": 0.0,
      "num_tokens": 58391.0,
      "reward": 0.75,
      "reward_std": 0.5,
      "rewards/reward_from_oracle/mean": 0.75,
      "rewards/reward_from_oracle/std": 0.4629100561141968,
      "step": 7
    },
    {
      "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": 2.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 2.0,
      "completions/max_terminated_length": 2.0,
      "completions/mean_length": 2.0,
      "completions/mean_terminated_length": 2.0,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.5,
      "frac_reward_zero_std": 0.5,
      "grad_norm": 3.759775161743164,
      "kl": 0.0,
      "learning_rate": 1.2500000000000007e-06,
      "loss": 1.862645149230957e-09,
      "num_tokens": 66727.0,
      "reward": 0.875,
      "reward_std": 0.25,
      "rewards/reward_from_oracle/mean": 0.875,
      "rewards/reward_from_oracle/std": 0.3535533845424652,
      "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,
      "completion_length": 2.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 2.0,
      "completions/max_terminated_length": 2.0,
      "completions/mean_length": 2.0,
      "completions/mean_terminated_length": 2.0,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.5625,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 7.748785495758057,
      "kl": 0.0,
      "learning_rate": 5.848888922025553e-07,
      "loss": 1.862645149230957e-09,
      "num_tokens": 75063.0,
      "reward": 0.75,
      "reward_std": 0.5,
      "rewards/reward_from_oracle/mean": 0.75,
      "rewards/reward_from_oracle/std": 0.4629100561141968,
      "step": 9
    },
    {
      "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": 2.0,
      "completions/clipped_ratio": 0.0,
      "completions/max_length": 2.0,
      "completions/max_terminated_length": 2.0,
      "completions/mean_length": 2.0,
      "completions/mean_terminated_length": 2.0,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.625,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 0.0,
      "kl": 0.0,
      "learning_rate": 1.507684480352292e-07,
      "loss": 0.0,
      "num_tokens": 83403.0,
      "reward": 1.0,
      "reward_std": 0.0,
      "rewards/reward_from_oracle/mean": 1.0,
      "rewards/reward_from_oracle/std": 0.0,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 83403,
  "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": 8,
  "trial_name": null,
  "trial_params": null
}