{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9620253164556962,
  "eval_steps": 500,
  "global_step": 19,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05063291139240506,
      "grad_norm": 0.45614859461784363,
      "learning_rate": 9.931806517013612e-06,
      "loss": 0.2942,
      "step": 1
    },
    {
      "epoch": 0.10126582278481013,
      "grad_norm": 4.234086513519287,
      "learning_rate": 9.729086208503174e-06,
      "loss": 0.2962,
      "step": 2
    },
    {
      "epoch": 0.1518987341772152,
      "grad_norm": 2.4086997509002686,
      "learning_rate": 9.397368756032445e-06,
      "loss": 0.3051,
      "step": 3
    },
    {
      "epoch": 0.20253164556962025,
      "grad_norm": 0.43997353315353394,
      "learning_rate": 8.94570254698197e-06,
      "loss": 0.3265,
      "step": 4
    },
    {
      "epoch": 0.25316455696202533,
      "grad_norm": 0.47186556458473206,
      "learning_rate": 8.386407858128707e-06,
      "loss": 0.2857,
      "step": 5
    },
    {
      "epoch": 0.3037974683544304,
      "grad_norm": 0.3021100163459778,
      "learning_rate": 7.734740790612137e-06,
      "loss": 0.3048,
      "step": 6
    },
    {
      "epoch": 0.35443037974683544,
      "grad_norm": 0.24642139673233032,
      "learning_rate": 7.008477123264849e-06,
      "loss": 0.2819,
      "step": 7
    },
    {
      "epoch": 0.4050632911392405,
      "grad_norm": 0.23320744931697845,
      "learning_rate": 6.227427435703997e-06,
      "loss": 0.3121,
      "step": 8
    },
    {
      "epoch": 0.45569620253164556,
      "grad_norm": 0.3668489456176758,
      "learning_rate": 5.412896727361663e-06,
      "loss": 0.2888,
      "step": 9
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 0.24893039464950562,
      "learning_rate": 4.587103272638339e-06,
      "loss": 0.3415,
      "step": 10
    },
    {
      "epoch": 0.5569620253164557,
      "grad_norm": 0.2509308457374573,
      "learning_rate": 3.7725725642960047e-06,
      "loss": 0.3041,
      "step": 11
    },
    {
      "epoch": 0.6075949367088608,
      "grad_norm": 0.24936634302139282,
      "learning_rate": 2.991522876735154e-06,
      "loss": 0.3142,
      "step": 12
    },
    {
      "epoch": 0.6582278481012658,
      "grad_norm": 0.2625156044960022,
      "learning_rate": 2.265259209387867e-06,
      "loss": 0.2946,
      "step": 13
    },
    {
      "epoch": 0.7088607594936709,
      "grad_norm": 0.19627711176872253,
      "learning_rate": 1.6135921418712959e-06,
      "loss": 0.264,
      "step": 14
    },
    {
      "epoch": 0.759493670886076,
      "grad_norm": 0.22815899550914764,
      "learning_rate": 1.0542974530180327e-06,
      "loss": 0.3133,
      "step": 15
    },
    {
      "epoch": 0.810126582278481,
      "grad_norm": 0.21842673420906067,
      "learning_rate": 6.026312439675553e-07,
      "loss": 0.2863,
      "step": 16
    },
    {
      "epoch": 0.8607594936708861,
      "grad_norm": 0.2017790824174881,
      "learning_rate": 2.7091379149682683e-07,
      "loss": 0.3684,
      "step": 17
    },
    {
      "epoch": 0.9113924050632911,
      "grad_norm": 0.18349921703338623,
      "learning_rate": 6.819348298638839e-08,
      "loss": 0.3007,
      "step": 18
    },
    {
      "epoch": 0.9620253164556962,
      "grad_norm": 0.2032947838306427,
      "learning_rate": 0.0,
      "loss": 0.3063,
      "step": 19
    }
  ],
  "logging_steps": 1,
  "max_steps": 19,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.8521915203190784e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}