{
  "best_global_step": 15,
  "best_metric": 0.04914529249072075,
  "best_model_checkpoint": "outputs/microsoft/Phi-3.5-mini-instruct/countdown_n25_mcl_1024/checkpoint-15",
  "epoch": 2.96,
  "eval_steps": 5,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8,
      "grad_norm": 0.019620755687355995,
      "learning_rate": 7.777777777777778e-07,
      "loss": 0.056,
      "step": 5
    },
    {
      "epoch": 0.8,
      "eval_clip_ratio": 0.0,
      "eval_completion_length": 782.45,
      "eval_kl": 3.187358379364014e-05,
      "eval_loss": 0.0509527251124382,
      "eval_num_tokens": 79701.0,
      "eval_reward": 0.1875,
      "eval_reward_std": 0.20239237546920777,
      "eval_rewards/equation_reward_func": 0.125,
      "eval_rewards/format_reward_func": 0.0625,
      "eval_runtime": 1285.4303,
      "eval_samples_per_second": 0.016,
      "eval_steps_per_second": 0.004,
      "step": 5
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.009305542334914207,
      "learning_rate": 5e-07,
      "loss": 0.0492,
      "step": 10
    },
    {
      "epoch": 1.6400000000000001,
      "eval_clip_ratio": 0.0,
      "eval_completion_length": 723.9125,
      "eval_kl": 2.8911232948303223e-05,
      "eval_loss": 0.07218091189861298,
      "eval_num_tokens": 153374.0,
      "eval_reward": 0.125,
      "eval_reward_std": 0.15,
      "eval_rewards/equation_reward_func": 0.1,
      "eval_rewards/format_reward_func": 0.025,
      "eval_runtime": 1245.9899,
      "eval_samples_per_second": 0.016,
      "eval_steps_per_second": 0.004,
      "step": 10
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.01135913748294115,
      "learning_rate": 2.222222222222222e-07,
      "loss": 0.0296,
      "step": 15
    },
    {
      "epoch": 2.48,
      "eval_clip_ratio": 0.0,
      "eval_completion_length": 771.5625,
      "eval_kl": 3.11434268951416e-05,
      "eval_loss": 0.04914529249072075,
      "eval_num_tokens": 232914.0,
      "eval_reward": 0.0875,
      "eval_reward_std": 0.13273502588272096,
      "eval_rewards/equation_reward_func": 0.0625,
      "eval_rewards/format_reward_func": 0.025,
      "eval_runtime": 1305.0413,
      "eval_samples_per_second": 0.015,
      "eval_steps_per_second": 0.004,
      "step": 15
    }
  ],
  "logging_steps": 5,
  "max_steps": 18,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "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": 4,
  "trial_name": null,
  "trial_params": null
}