trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 247.78125,
      "epoch": 0.2,
      "grad_norm": 4.862517833709717,
      "kl": 0.0,
      "learning_rate": 5e-07,
      "loss": -0.0,
      "reward": 0.07542214676504955,
      "reward_std": 0.11460273773991503,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.12257839407538995,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": -0.04715624824166298,
      "step": 2
    },
    {
      "completion_length": 233.84375,
      "epoch": 0.4,
      "grad_norm": 6.7133402824401855,
      "kl": 0.0004883616990127848,
      "learning_rate": 4.415111107797445e-07,
      "loss": 0.0,
      "reward": 0.09165580023545772,
      "reward_std": 0.04656617870205082,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.0877182997064665,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.003937500063329935,
      "step": 4
    },
    {
      "completion_length": 211.40625,
      "epoch": 0.6,
      "grad_norm": 5.468976020812988,
      "kl": 0.0019214348831155803,
      "learning_rate": 2.934120444167326e-07,
      "loss": 0.0,
      "reward": 0.09261799091473222,
      "reward_std": 0.04726607238990255,
      "rewards/concensus_correctness_reward_func": 0.0,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.0919929908704944,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0006249999860301614,
      "step": 6
    },
    {
      "completion_length": 185.875,
      "epoch": 0.8,
      "grad_norm": 15.175353050231934,
      "kl": 0.010549276465098956,
      "learning_rate": 1.2500000000000005e-07,
      "loss": 0.0,
      "reward": 0.17108983627986163,
      "reward_std": 0.09242143104529532,
      "rewards/concensus_correctness_reward_func": 0.02043749950826168,
      "rewards/consensus_reward_func": 0.0,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.14290233771316707,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.00774999987334013,
      "step": 8
    },
    {
      "completion_length": 183.09375,
      "epoch": 1.0,
      "grad_norm": 17.882421493530273,
      "kl": 0.011150044223541045,
      "learning_rate": 1.507684480352292e-08,
      "loss": 0.0,
      "reward": 0.23528616363182664,
      "reward_std": 0.16651459495187737,
      "rewards/concensus_correctness_reward_func": 0.019625000655651093,
      "rewards/consensus_reward_func": 0.0625,
      "rewards/cumulative_reward_2": 0.0,
      "rewards/final_correctness_reward_func": 0.0,
      "rewards/question_recreation_reward_func": 0.15316116577014327,
      "rewards/soft_format_reward_func": 0.0,
      "rewards/strict_format_reward_func": 0.0,
      "rewards/xmlcount_reward_func": 0.0,
      "step": 10
    },
    {
      "epoch": 1.0,
      "step": 10,
      "total_flos": 0.0,
      "train_loss": 4.746392369270324e-06,
      "train_runtime": 11958.0868,
      "train_samples_per_second": 0.013,
      "train_steps_per_second": 0.001
    }
  ],
  "logging_steps": 2,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "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": 2,
  "trial_name": null,
  "trial_params": null
}