{
  "best_global_step": 1400,
  "best_metric": 82.55212784144531,
  "best_model_checkpoint": null,
  "epoch": 0.3973509933774834,
  "eval_steps": 100,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013245033112582781,
      "grad_norm": 7.202547550201416,
      "learning_rate": 9.998701986754968e-06,
      "loss": 0.7094,
      "step": 50
    },
    {
      "epoch": 0.026490066225165563,
      "grad_norm": 9.662558555603027,
      "learning_rate": 9.99737748344371e-06,
      "loss": 0.68,
      "step": 100
    },
    {
      "epoch": 0.026490066225165563,
      "eval_HasAns_exact": 75.14792899408285,
      "eval_HasAns_f1": 81.01957227969451,
      "eval_HasAns_total": 15041,
      "eval_best_exact": 75.14792899408285,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 81.01957227969451,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 75.14792899408285,
      "eval_f1": 81.01957227969451,
      "eval_loss": 0.5824803113937378,
      "eval_runtime": 120.1578,
      "eval_samples_per_second": 125.177,
      "eval_steps_per_second": 7.831,
      "eval_total": 15041,
      "step": 100
    },
    {
      "epoch": 0.039735099337748346,
      "grad_norm": 7.527211666107178,
      "learning_rate": 9.996052980132451e-06,
      "loss": 0.586,
      "step": 150
    },
    {
      "epoch": 0.052980132450331126,
      "grad_norm": 5.419323921203613,
      "learning_rate": 9.994728476821193e-06,
      "loss": 0.6035,
      "step": 200
    },
    {
      "epoch": 0.052980132450331126,
      "eval_HasAns_exact": 75.56013562927997,
      "eval_HasAns_f1": 81.46153699536843,
      "eval_HasAns_total": 15041,
      "eval_best_exact": 75.56013562927997,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 81.46153699536843,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 75.56013562927997,
      "eval_f1": 81.46153699536843,
      "eval_loss": 0.5453085899353027,
      "eval_runtime": 118.3719,
      "eval_samples_per_second": 127.066,
      "eval_steps_per_second": 7.95,
      "eval_total": 15041,
      "step": 200
    },
    {
      "epoch": 0.06622516556291391,
      "grad_norm": 9.9099760055542,
      "learning_rate": 9.993403973509935e-06,
      "loss": 0.5616,
      "step": 250
    },
    {
      "epoch": 0.07947019867549669,
      "grad_norm": 3.5184719562530518,
      "learning_rate": 9.992079470198677e-06,
      "loss": 0.5286,
      "step": 300
    },
    {
      "epoch": 0.07947019867549669,
      "eval_HasAns_exact": 75.8526693703876,
      "eval_HasAns_f1": 81.45745729278944,
      "eval_HasAns_total": 15041,
      "eval_best_exact": 75.8526693703876,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 81.45745729278944,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 75.8526693703876,
      "eval_f1": 81.45745729278944,
      "eval_loss": 0.5200360417366028,
      "eval_runtime": 118.7441,
      "eval_samples_per_second": 126.667,
      "eval_steps_per_second": 7.925,
      "eval_total": 15041,
      "step": 300
    },
    {
      "epoch": 0.09271523178807947,
      "grad_norm": 4.889588832855225,
      "learning_rate": 9.990754966887418e-06,
      "loss": 0.4943,
      "step": 350
    },
    {
      "epoch": 0.10596026490066225,
      "grad_norm": 6.106881141662598,
      "learning_rate": 9.98943046357616e-06,
      "loss": 0.5957,
      "step": 400
    },
    {
      "epoch": 0.10596026490066225,
      "eval_HasAns_exact": 76.39784588790639,
      "eval_HasAns_f1": 81.91199737367272,
      "eval_HasAns_total": 15041,
      "eval_best_exact": 76.39784588790639,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 81.91199737367272,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 76.39784588790639,
      "eval_f1": 81.91199737367272,
      "eval_loss": 0.49782633781433105,
      "eval_runtime": 118.2655,
      "eval_samples_per_second": 127.18,
      "eval_steps_per_second": 7.957,
      "eval_total": 15041,
      "step": 400
    },
    {
      "epoch": 0.11920529801324503,
      "grad_norm": 6.963775634765625,
      "learning_rate": 9.988105960264902e-06,
      "loss": 0.5675,
      "step": 450
    },
    {
      "epoch": 0.13245033112582782,
      "grad_norm": 7.559121608734131,
      "learning_rate": 9.986781456953643e-06,
      "loss": 0.5173,
      "step": 500
    },
    {
      "epoch": 0.13245033112582782,
      "eval_HasAns_exact": 75.94574828801277,
      "eval_HasAns_f1": 81.43615773338746,
      "eval_HasAns_total": 15041,
      "eval_best_exact": 75.94574828801277,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 81.43615773338746,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 75.94574828801277,
      "eval_f1": 81.43615773338746,
      "eval_loss": 0.4918788969516754,
      "eval_runtime": 118.4997,
      "eval_samples_per_second": 126.929,
      "eval_steps_per_second": 7.941,
      "eval_total": 15041,
      "step": 500
    },
    {
      "epoch": 0.1456953642384106,
      "grad_norm": 5.2273268699646,
      "learning_rate": 9.985456953642385e-06,
      "loss": 0.5059,
      "step": 550
    },
    {
      "epoch": 0.15894039735099338,
      "grad_norm": 13.281010627746582,
      "learning_rate": 9.984132450331127e-06,
      "loss": 0.4847,
      "step": 600
    },
    {
      "epoch": 0.15894039735099338,
      "eval_HasAns_exact": 76.42443986437073,
      "eval_HasAns_f1": 81.98556495448281,
      "eval_HasAns_total": 15041,
      "eval_best_exact": 76.42443986437073,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 81.98556495448281,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 76.42443986437073,
      "eval_f1": 81.98556495448281,
      "eval_loss": 0.48446840047836304,
      "eval_runtime": 118.3928,
      "eval_samples_per_second": 127.043,
      "eval_steps_per_second": 7.948,
      "eval_total": 15041,
      "step": 600
    },
    {
      "epoch": 0.17218543046357615,
      "grad_norm": 18.346189498901367,
      "learning_rate": 9.982807947019869e-06,
      "loss": 0.4857,
      "step": 650
    },
    {
      "epoch": 0.18543046357615894,
      "grad_norm": 11.825461387634277,
      "learning_rate": 9.98148344370861e-06,
      "loss": 0.4764,
      "step": 700
    },
    {
      "epoch": 0.18543046357615894,
      "eval_HasAns_exact": 76.54411275846022,
      "eval_HasAns_f1": 82.14175205695277,
      "eval_HasAns_total": 15041,
      "eval_best_exact": 76.54411275846022,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 82.14175205695277,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 76.54411275846022,
      "eval_f1": 82.14175205695277,
      "eval_loss": 0.4717336595058441,
      "eval_runtime": 118.5022,
      "eval_samples_per_second": 126.926,
      "eval_steps_per_second": 7.941,
      "eval_total": 15041,
      "step": 700
    },
    {
      "epoch": 0.1986754966887417,
      "grad_norm": 7.6593475341796875,
      "learning_rate": 9.980158940397352e-06,
      "loss": 0.486,
      "step": 750
    },
    {
      "epoch": 0.2119205298013245,
      "grad_norm": 6.091643333435059,
      "learning_rate": 9.978834437086094e-06,
      "loss": 0.4707,
      "step": 800
    },
    {
      "epoch": 0.2119205298013245,
      "eval_HasAns_exact": 76.86324047603217,
      "eval_HasAns_f1": 82.2239211673303,
      "eval_HasAns_total": 15041,
      "eval_best_exact": 76.86324047603217,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 82.2239211673303,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 76.86324047603217,
      "eval_f1": 82.2239211673303,
      "eval_loss": 0.4601329565048218,
      "eval_runtime": 119.1574,
      "eval_samples_per_second": 126.228,
      "eval_steps_per_second": 7.897,
      "eval_total": 15041,
      "step": 800
    },
    {
      "epoch": 0.2251655629139073,
      "grad_norm": 4.863158702850342,
      "learning_rate": 9.977509933774835e-06,
      "loss": 0.5042,
      "step": 850
    },
    {
      "epoch": 0.23841059602649006,
      "grad_norm": 5.747822284698486,
      "learning_rate": 9.976185430463577e-06,
      "loss": 0.4725,
      "step": 900
    },
    {
      "epoch": 0.23841059602649006,
      "eval_HasAns_exact": 76.98291337012166,
      "eval_HasAns_f1": 82.39127215176644,
      "eval_HasAns_total": 15041,
      "eval_best_exact": 76.98291337012166,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 82.39127215176644,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 76.98291337012166,
      "eval_f1": 82.39127215176644,
      "eval_loss": 0.45768168568611145,
      "eval_runtime": 118.7264,
      "eval_samples_per_second": 126.686,
      "eval_steps_per_second": 7.926,
      "eval_total": 15041,
      "step": 900
    },
    {
      "epoch": 0.25165562913907286,
      "grad_norm": 14.890397071838379,
      "learning_rate": 9.974860927152319e-06,
      "loss": 0.4476,
      "step": 950
    },
    {
      "epoch": 0.26490066225165565,
      "grad_norm": 8.837732315063477,
      "learning_rate": 9.97353642384106e-06,
      "loss": 0.4905,
      "step": 1000
    },
    {
      "epoch": 0.26490066225165565,
      "eval_HasAns_exact": 77.10923475832723,
      "eval_HasAns_f1": 82.37799175072134,
      "eval_HasAns_total": 15041,
      "eval_best_exact": 77.10923475832723,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 82.37799175072134,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 77.10923475832723,
      "eval_f1": 82.37799175072134,
      "eval_loss": 0.44477367401123047,
      "eval_runtime": 118.302,
      "eval_samples_per_second": 127.141,
      "eval_steps_per_second": 7.954,
      "eval_total": 15041,
      "step": 1000
    },
    {
      "epoch": 0.2781456953642384,
      "grad_norm": 5.750672817230225,
      "learning_rate": 9.972211920529802e-06,
      "loss": 0.5041,
      "step": 1050
    },
    {
      "epoch": 0.2913907284768212,
      "grad_norm": 5.720890998840332,
      "learning_rate": 9.970887417218544e-06,
      "loss": 0.5156,
      "step": 1100
    },
    {
      "epoch": 0.2913907284768212,
      "eval_HasAns_exact": 77.0826407818629,
      "eval_HasAns_f1": 82.36916366838726,
      "eval_HasAns_total": 15041,
      "eval_best_exact": 77.0826407818629,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 82.36916366838726,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 77.0826407818629,
      "eval_f1": 82.36916366838726,
      "eval_loss": 0.43873801827430725,
      "eval_runtime": 118.2856,
      "eval_samples_per_second": 127.158,
      "eval_steps_per_second": 7.955,
      "eval_total": 15041,
      "step": 1100
    },
    {
      "epoch": 0.304635761589404,
      "grad_norm": 6.990389823913574,
      "learning_rate": 9.969562913907286e-06,
      "loss": 0.4507,
      "step": 1150
    },
    {
      "epoch": 0.31788079470198677,
      "grad_norm": 11.490405082702637,
      "learning_rate": 9.968238410596027e-06,
      "loss": 0.4482,
      "step": 1200
    },
    {
      "epoch": 0.31788079470198677,
      "eval_HasAns_exact": 77.01615584070208,
      "eval_HasAns_f1": 82.29906445927755,
      "eval_HasAns_total": 15041,
      "eval_best_exact": 77.01615584070208,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 82.29906445927755,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 77.01615584070208,
      "eval_f1": 82.29906445927755,
      "eval_loss": 0.42996492981910706,
      "eval_runtime": 118.4966,
      "eval_samples_per_second": 126.932,
      "eval_steps_per_second": 7.941,
      "eval_total": 15041,
      "step": 1200
    },
    {
      "epoch": 0.33112582781456956,
      "grad_norm": 2.8688676357269287,
      "learning_rate": 9.966913907284769e-06,
      "loss": 0.4593,
      "step": 1250
    },
    {
      "epoch": 0.3443708609271523,
      "grad_norm": 7.523802280426025,
      "learning_rate": 9.96558940397351e-06,
      "loss": 0.4548,
      "step": 1300
    },
    {
      "epoch": 0.3443708609271523,
      "eval_HasAns_exact": 76.94967089954126,
      "eval_HasAns_f1": 82.17470826997452,
      "eval_HasAns_total": 15041,
      "eval_best_exact": 76.94967089954126,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 82.17470826997452,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 76.94967089954126,
      "eval_f1": 82.17470826997452,
      "eval_loss": 0.4349832832813263,
      "eval_runtime": 118.6592,
      "eval_samples_per_second": 126.758,
      "eval_steps_per_second": 7.93,
      "eval_total": 15041,
      "step": 1300
    },
    {
      "epoch": 0.3576158940397351,
      "grad_norm": 10.102520942687988,
      "learning_rate": 9.964264900662252e-06,
      "loss": 0.4935,
      "step": 1350
    },
    {
      "epoch": 0.3708609271523179,
      "grad_norm": 8.859588623046875,
      "learning_rate": 9.962940397350994e-06,
      "loss": 0.4344,
      "step": 1400
    },
    {
      "epoch": 0.3708609271523179,
      "eval_HasAns_exact": 77.19566518183632,
      "eval_HasAns_f1": 82.55212784144531,
      "eval_HasAns_total": 15041,
      "eval_best_exact": 77.19566518183632,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 82.55212784144531,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 77.19566518183632,
      "eval_f1": 82.55212784144531,
      "eval_loss": 0.42366155982017517,
      "eval_runtime": 119.1071,
      "eval_samples_per_second": 126.281,
      "eval_steps_per_second": 7.9,
      "eval_total": 15041,
      "step": 1400
    },
    {
      "epoch": 0.3841059602649007,
      "grad_norm": 5.980023384094238,
      "learning_rate": 9.961615894039736e-06,
      "loss": 0.4936,
      "step": 1450
    },
    {
      "epoch": 0.3973509933774834,
      "grad_norm": 5.025954246520996,
      "learning_rate": 9.960291390728478e-06,
      "loss": 0.4431,
      "step": 1500
    },
    {
      "epoch": 0.3973509933774834,
      "eval_HasAns_exact": 77.10923475832723,
      "eval_HasAns_f1": 82.41666220398032,
      "eval_HasAns_total": 15041,
      "eval_best_exact": 77.10923475832723,
      "eval_best_exact_thresh": 0.0,
      "eval_best_f1": 82.41666220398032,
      "eval_best_f1_thresh": 0.0,
      "eval_exact": 77.10923475832723,
      "eval_f1": 82.41666220398032,
      "eval_loss": 0.4237441122531891,
      "eval_runtime": 118.7094,
      "eval_samples_per_second": 126.704,
      "eval_steps_per_second": 7.927,
      "eval_total": 15041,
      "step": 1500
    }
  ],
  "logging_steps": 50,
  "max_steps": 377500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 10,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2542244323328e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}