{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.023075615147319584,
  "eval_steps": 500,
  "global_step": 1900,
  "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": 0.75,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 215.0,
      "completions/mean_length": 226.375,
      "completions/mean_terminated_length": 137.5,
      "completions/min_length": 60.0,
      "completions/min_terminated_length": 60.0,
      "entropy": 1.7876319885253906,
      "epoch": 1.2145060603852413e-05,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 0.45122280716896057,
      "kl": 0.0,
      "learning_rate": 0.0,
      "loss": -0.0,
      "num_tokens": 3903.0,
      "reward": 7250.048828125,
      "reward_std": 2273.237548828125,
      "rewards/reward_long_completions/mean": 806.75,
      "rewards/reward_long_completions/std": 293.8428955078125,
      "rewards/reward_long_words/mean": 6.343996047973633,
      "rewards/reward_long_words/std": 2.0528388023376465,
      "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,
      "completions/clipped_ratio": 0.9934869739478958,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 3.8597194388777556,
      "completions/mean_length": 255.0433366733467,
      "completions/mean_terminated_length": 2.520774917755433,
      "completions/min_length": 251.1442885771543,
      "completions/min_terminated_length": 1.3006012024048097,
      "entropy": 0.46742610163357157,
      "epoch": 0.006072530301926207,
      "frac_reward_zero_std": 0.8136272545090181,
      "grad_norm": 1.1401318111836645e-08,
      "kl": 0.27695997151695956,
      "learning_rate": 0.00019183846457059546,
      "loss": 0.0111,
      "num_tokens": 1761588.0,
      "reward": 26948.982748700528,
      "reward_std": 173.13352758659866,
      "rewards/reward_long_completions/mean": 3006.4551603206414,
      "rewards/reward_long_completions/std": 26.415839506175093,
      "rewards/reward_long_words/mean": 11.271554429927665,
      "rewards/reward_long_words/std": 0.46356010581049434,
      "step": 500
    },
    {
      "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": 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,
      "entropy": 8.449839063473518e-08,
      "epoch": 0.012145060603852413,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 1.2536369276006099e-08,
      "kl": 0.30570593059062956,
      "learning_rate": 0.00014850305016500775,
      "loss": 0.0122,
      "num_tokens": 3432260.0,
      "reward": 29819.603515625,
      "reward_std": 0.0,
      "rewards/reward_long_completions/mean": 3327.0,
      "rewards/reward_long_completions/std": 0.0,
      "rewards/reward_long_words/mean": 12.0,
      "rewards/reward_long_words/std": 0.0,
      "step": 1000
    },
    {
      "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": 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,
      "entropy": 8.525463378106223e-08,
      "epoch": 0.01821759090577862,
      "frac_reward_zero_std": 1.0,
      "grad_norm": 8.738510359762586e-09,
      "kl": 0.2979220716804266,
      "learning_rate": 9.352737661482471e-05,
      "loss": 0.0119,
      "num_tokens": 5134968.0,
      "reward": 29819.603515625,
      "reward_std": 0.0,
      "rewards/reward_long_completions/mean": 3327.0,
      "rewards/reward_long_completions/std": 0.0,
      "rewards/reward_long_words/mean": 12.0,
      "rewards/reward_long_words/std": 0.0,
      "step": 1500
    }
  ],
  "logging_steps": 500,
  "max_steps": 2126,
  "num_input_tokens_seen": 6451696,
  "num_train_epochs": 1,
  "save_steps": 100,
  "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
}