{
  "best_global_step": 1,
  "best_metric": 0.42203541100025177,
  "best_model_checkpoint": "/root/workspace/Shaer/grpo/outputs/sanity_check/sanity_20260411_123535/checkpoint-1",
  "epoch": 0.5,
  "eval_steps": 1,
  "global_step": 1,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "clip_ratio/high_max": 0.10928299836814404,
      "clip_ratio/high_mean": 0.10928299836814404,
      "clip_ratio/low_mean": 0.09094957076013088,
      "clip_ratio/low_min": 0.09094957076013088,
      "clip_ratio/region_mean": 0.20023256912827492,
      "completions/clipped_ratio": 0.25,
      "completions/max_length": 640.0,
      "completions/max_terminated_length": 237.0,
      "completions/mean_length": 282.125,
      "completions/mean_terminated_length": 162.83334350585938,
      "completions/min_length": 86.0,
      "completions/min_terminated_length": 86.0,
      "entropy": 3.2345626056194305,
      "epoch": 0.5,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 4.5472893714904785,
      "kl": 0.9608133509755135,
      "learning_rate": 1e-05,
      "loss": 0.0268,
      "num_tokens": 3887.0,
      "reward": 0.2736811637878418,
      "reward_exact_count_bonus_mean": 0.25,
      "reward_exact_count_bonus_std": 0.4629100561141968,
      "reward_meter_mean": 0.22368116676807404,
      "reward_meter_std": 0.30434706807136536,
      "reward_std": 0.25279727578163147,
      "reward_total_mean": 0.2736811637878418,
      "rewards/exact_count_bonus/mean": 0.25,
      "rewards/exact_count_bonus/std": 0.4629100561141968,
      "rewards/meter/mean": 0.22368116676807404,
      "rewards/meter/std": 0.30434706807136536,
      "sampling/importance_sampling_ratio/max": 2.0,
      "sampling/importance_sampling_ratio/mean": 0.9976902008056641,
      "sampling/importance_sampling_ratio/min": 0.24163144826889038,
      "sampling/sampling_logp_difference/max": 1.4203417301177979,
      "sampling/sampling_logp_difference/mean": 0.15930314362049103,
      "step": 1
    },
    {
      "epoch": 0.5,
      "eval_clip_ratio/high_max": 0.0,
      "eval_clip_ratio/high_mean": 0.0,
      "eval_clip_ratio/low_mean": 0.0,
      "eval_clip_ratio/low_min": 0.0,
      "eval_clip_ratio/region_mean": 0.0,
      "eval_completions/clipped_ratio": 0.0,
      "eval_completions/max_length": 156.0,
      "eval_completions/max_terminated_length": 156.0,
      "eval_completions/mean_length": 106.125,
      "eval_completions/mean_terminated_length": 106.125,
      "eval_completions/min_length": 69.25,
      "eval_completions/min_terminated_length": 69.25,
      "eval_entropy": 2.1008258759975433,
      "eval_frac_reward_zero_std": 0.0,
      "eval_kl": 1.3679395914077759,
      "eval_loss": 0.0866735428571701,
      "eval_num_tokens": 3887.0,
      "eval_reward": 0.42203541100025177,
      "eval_reward_exact_count_bonus_mean": 0.9375,
      "eval_reward_exact_count_bonus_std": 0.125,
      "eval_reward_meter_mean": 0.23453541472554207,
      "eval_reward_meter_std": 0.22889509424567223,
      "eval_reward_std": 0.2391926608979702,
      "eval_reward_total_mean": 0.42203541100025177,
      "eval_rewards/exact_count_bonus/mean": 0.9375,
      "eval_rewards/exact_count_bonus/std": 0.125,
      "eval_rewards/meter/mean": 0.23453541472554207,
      "eval_rewards/meter/std": 0.22889509424567223,
      "eval_runtime": 15.7215,
      "eval_samples_per_second": 0.509,
      "eval_sampling/importance_sampling_ratio/max": 1.2397247850894928,
      "eval_sampling/importance_sampling_ratio/mean": 0.9995981901884079,
      "eval_sampling/importance_sampling_ratio/min": 0.7994033098220825,
      "eval_sampling/sampling_logp_difference/max": 0.24606388807296753,
      "eval_sampling/sampling_logp_difference/mean": 0.034631784074008465,
      "eval_steps_per_second": 0.127,
      "step": 1
    }
  ],
  "logging_steps": 1,
  "max_steps": 2,
  "num_input_tokens_seen": 3887,
  "num_train_epochs": 1,
  "save_steps": 1,
  "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": 1,
  "trial_name": null,
  "trial_params": null
}