{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 370,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06756756756756757,
      "grad_norm": 4.227170409911558,
      "learning_rate": 1.3157894736842106e-05,
      "loss": 0.575,
      "step": 5
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 2.2776126764932063,
      "learning_rate": 2.6315789473684212e-05,
      "loss": 0.378,
      "step": 10
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 1.8654646175129226,
      "learning_rate": 3.9473684210526316e-05,
      "loss": 0.2857,
      "step": 15
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 1.380928609001772,
      "learning_rate": 4.9999098771046674e-05,
      "loss": 0.2447,
      "step": 20
    },
    {
      "epoch": 0.33783783783783783,
      "grad_norm": 3.241471282418704,
      "learning_rate": 4.996756333769319e-05,
      "loss": 0.2235,
      "step": 25
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 1.2985992616488145,
      "learning_rate": 4.989103862744732e-05,
      "loss": 0.2145,
      "step": 30
    },
    {
      "epoch": 0.47297297297297297,
      "grad_norm": 1.1067383831026958,
      "learning_rate": 4.976967787416565e-05,
      "loss": 0.1899,
      "step": 35
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 1.049570235777466,
      "learning_rate": 4.9603724091852456e-05,
      "loss": 0.1987,
      "step": 40
    },
    {
      "epoch": 0.6081081081081081,
      "grad_norm": 1.0331209710899183,
      "learning_rate": 4.9393509588046036e-05,
      "loss": 0.1912,
      "step": 45
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 0.925233682955553,
      "learning_rate": 4.9139455298402656e-05,
      "loss": 0.1746,
      "step": 50
    },
    {
      "epoch": 0.7432432432432432,
      "grad_norm": 0.7958783153604793,
      "learning_rate": 4.884206994381078e-05,
      "loss": 0.1822,
      "step": 55
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 0.9751386844667708,
      "learning_rate": 4.8501949011723144e-05,
      "loss": 0.1876,
      "step": 60
    },
    {
      "epoch": 0.8783783783783784,
      "grad_norm": 0.8402293921317799,
      "learning_rate": 4.811977356374667e-05,
      "loss": 0.1872,
      "step": 65
    },
    {
      "epoch": 0.9459459459459459,
      "grad_norm": 0.718701514552068,
      "learning_rate": 4.769630887187782e-05,
      "loss": 0.1676,
      "step": 70
    },
    {
      "epoch": 1.0135135135135136,
      "grad_norm": 0.5398531301606878,
      "learning_rate": 4.72324028861141e-05,
      "loss": 0.158,
      "step": 75
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 0.6189607559877081,
      "learning_rate": 4.6728984536510454e-05,
      "loss": 0.103,
      "step": 80
    },
    {
      "epoch": 1.1486486486486487,
      "grad_norm": 0.6977698037888556,
      "learning_rate": 4.6187061873080264e-05,
      "loss": 0.11,
      "step": 85
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 0.6702191594025242,
      "learning_rate": 4.560772004726575e-05,
      "loss": 0.0974,
      "step": 90
    },
    {
      "epoch": 1.2837837837837838,
      "grad_norm": 0.8375137882275626,
      "learning_rate": 4.499211913901974e-05,
      "loss": 0.0962,
      "step": 95
    },
    {
      "epoch": 1.3513513513513513,
      "grad_norm": 0.5623841444139801,
      "learning_rate": 4.434149183384977e-05,
      "loss": 0.0963,
      "step": 100
    },
    {
      "epoch": 1.4189189189189189,
      "grad_norm": 0.746823712074494,
      "learning_rate": 4.3657140954476165e-05,
      "loss": 0.0978,
      "step": 105
    },
    {
      "epoch": 1.4864864864864864,
      "grad_norm": 0.7241042591726438,
      "learning_rate": 4.294043685204651e-05,
      "loss": 0.0943,
      "step": 110
    },
    {
      "epoch": 1.554054054054054,
      "grad_norm": 0.8309567209936259,
      "learning_rate": 4.219281466213066e-05,
      "loss": 0.0997,
      "step": 115
    },
    {
      "epoch": 1.6216216216216215,
      "grad_norm": 0.7135108874545476,
      "learning_rate": 4.141577143099074e-05,
      "loss": 0.0954,
      "step": 120
    },
    {
      "epoch": 1.689189189189189,
      "grad_norm": 0.4901288548943104,
      "learning_rate": 4.06108631178804e-05,
      "loss": 0.0911,
      "step": 125
    },
    {
      "epoch": 1.7567567567567568,
      "grad_norm": 0.5126638837154042,
      "learning_rate": 3.977970147937635e-05,
      "loss": 0.0981,
      "step": 130
    },
    {
      "epoch": 1.8243243243243243,
      "grad_norm": 0.4361129957181847,
      "learning_rate": 3.892395084198053e-05,
      "loss": 0.0866,
      "step": 135
    },
    {
      "epoch": 1.8918918918918919,
      "grad_norm": 0.45933479640398944,
      "learning_rate": 3.8045324769455834e-05,
      "loss": 0.0815,
      "step": 140
    },
    {
      "epoch": 1.9594594594594594,
      "grad_norm": 0.6180056798090116,
      "learning_rate": 3.714558263156872e-05,
      "loss": 0.0853,
      "step": 145
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 0.8867749784287353,
      "learning_rate": 3.622652608110924e-05,
      "loss": 0.0714,
      "step": 150
    },
    {
      "epoch": 2.0945945945945947,
      "grad_norm": 0.41595529690592503,
      "learning_rate": 3.528999544624324e-05,
      "loss": 0.0582,
      "step": 155
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 0.46173444521128193,
      "learning_rate": 3.433786604542056e-05,
      "loss": 0.0546,
      "step": 160
    },
    {
      "epoch": 2.22972972972973,
      "grad_norm": 0.8285015328803698,
      "learning_rate": 3.337204443221834e-05,
      "loss": 0.0459,
      "step": 165
    },
    {
      "epoch": 2.2972972972972974,
      "grad_norm": 0.40330243772956614,
      "learning_rate": 3.2394464577638765e-05,
      "loss": 0.058,
      "step": 170
    },
    {
      "epoch": 2.364864864864865,
      "grad_norm": 0.38712423069839835,
      "learning_rate": 3.140708399750594e-05,
      "loss": 0.0524,
      "step": 175
    },
    {
      "epoch": 2.4324324324324325,
      "grad_norm": 0.4789835728870257,
      "learning_rate": 3.0411879832716246e-05,
      "loss": 0.0526,
      "step": 180
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.37205307961706024,
      "learning_rate": 2.9410844890191458e-05,
      "loss": 0.0507,
      "step": 185
    },
    {
      "epoch": 2.5675675675675675,
      "grad_norm": 0.6004132935282005,
      "learning_rate": 2.840598365246184e-05,
      "loss": 0.0527,
      "step": 190
    },
    {
      "epoch": 2.635135135135135,
      "grad_norm": 0.4560434366486544,
      "learning_rate": 2.7399308263870027e-05,
      "loss": 0.052,
      "step": 195
    },
    {
      "epoch": 2.7027027027027026,
      "grad_norm": 0.4624335921203337,
      "learning_rate": 2.6392834501432746e-05,
      "loss": 0.0462,
      "step": 200
    },
    {
      "epoch": 2.77027027027027,
      "grad_norm": 0.5498423698020634,
      "learning_rate": 2.538857773842847e-05,
      "loss": 0.0532,
      "step": 205
    },
    {
      "epoch": 2.8378378378378377,
      "grad_norm": 0.3705618200299343,
      "learning_rate": 2.438854890879351e-05,
      "loss": 0.0486,
      "step": 210
    },
    {
      "epoch": 2.9054054054054053,
      "grad_norm": 0.43411865881569756,
      "learning_rate": 2.3394750480407467e-05,
      "loss": 0.0522,
      "step": 215
    },
    {
      "epoch": 2.972972972972973,
      "grad_norm": 0.34856818385336974,
      "learning_rate": 2.2409172445331257e-05,
      "loss": 0.0433,
      "step": 220
    },
    {
      "epoch": 3.0405405405405403,
      "grad_norm": 0.3056885229191675,
      "learning_rate": 2.143378833502677e-05,
      "loss": 0.0367,
      "step": 225
    },
    {
      "epoch": 3.108108108108108,
      "grad_norm": 0.3437713870681847,
      "learning_rate": 2.0470551268537457e-05,
      "loss": 0.0264,
      "step": 230
    },
    {
      "epoch": 3.175675675675676,
      "grad_norm": 0.336480003243831,
      "learning_rate": 1.9521390041542946e-05,
      "loss": 0.0311,
      "step": 235
    },
    {
      "epoch": 3.2432432432432434,
      "grad_norm": 0.3411706759863995,
      "learning_rate": 1.8588205264118974e-05,
      "loss": 0.0269,
      "step": 240
    },
    {
      "epoch": 3.310810810810811,
      "grad_norm": 0.34062033026640975,
      "learning_rate": 1.7672865554936467e-05,
      "loss": 0.0281,
      "step": 245
    },
    {
      "epoch": 3.3783783783783785,
      "grad_norm": 0.3695748741767915,
      "learning_rate": 1.6777203799520573e-05,
      "loss": 0.027,
      "step": 250
    },
    {
      "epoch": 3.445945945945946,
      "grad_norm": 0.3601998041543281,
      "learning_rate": 1.5903013480062085e-05,
      "loss": 0.0282,
      "step": 255
    },
    {
      "epoch": 3.5135135135135136,
      "grad_norm": 0.45887851685959974,
      "learning_rate": 1.5052045084130445e-05,
      "loss": 0.0273,
      "step": 260
    },
    {
      "epoch": 3.581081081081081,
      "grad_norm": 0.35229536201704065,
      "learning_rate": 1.4226002599479743e-05,
      "loss": 0.0295,
      "step": 265
    },
    {
      "epoch": 3.6486486486486487,
      "grad_norm": 0.3353310971308658,
      "learning_rate": 1.3426540101966257e-05,
      "loss": 0.0322,
      "step": 270
    },
    {
      "epoch": 3.7162162162162162,
      "grad_norm": 0.41483094692292416,
      "learning_rate": 1.2655258443410268e-05,
      "loss": 0.0311,
      "step": 275
    },
    {
      "epoch": 3.7837837837837838,
      "grad_norm": 0.36712000215058754,
      "learning_rate": 1.1913702046034016e-05,
      "loss": 0.0289,
      "step": 280
    },
    {
      "epoch": 3.8513513513513513,
      "grad_norm": 0.5646368352969865,
      "learning_rate": 1.1203355809895042e-05,
      "loss": 0.0274,
      "step": 285
    },
    {
      "epoch": 3.918918918918919,
      "grad_norm": 0.4158288527920725,
      "learning_rate": 1.0525642139507222e-05,
      "loss": 0.028,
      "step": 290
    },
    {
      "epoch": 3.9864864864864864,
      "grad_norm": 0.3573187154947232,
      "learning_rate": 9.881918095603501e-06,
      "loss": 0.0276,
      "step": 295
    },
    {
      "epoch": 4.054054054054054,
      "grad_norm": 0.2472522738677183,
      "learning_rate": 9.273472677743755e-06,
      "loss": 0.0179,
      "step": 300
    },
    {
      "epoch": 4.121621621621622,
      "grad_norm": 0.20424848415230237,
      "learning_rate": 8.701524243208935e-06,
      "loss": 0.0142,
      "step": 305
    },
    {
      "epoch": 4.1891891891891895,
      "grad_norm": 0.2706498097595218,
      "learning_rate": 8.167218067350122e-06,
      "loss": 0.0174,
      "step": 310
    },
    {
      "epoch": 4.256756756756757,
      "grad_norm": 0.228170366357337,
      "learning_rate": 7.67162405027753e-06,
      "loss": 0.0149,
      "step": 315
    },
    {
      "epoch": 4.324324324324325,
      "grad_norm": 0.2817486193345113,
      "learning_rate": 7.21573457448164e-06,
      "loss": 0.0148,
      "step": 320
    },
    {
      "epoch": 4.391891891891892,
      "grad_norm": 0.22979041725844782,
      "learning_rate": 6.800462517676456e-06,
      "loss": 0.0133,
      "step": 325
    },
    {
      "epoch": 4.45945945945946,
      "grad_norm": 0.25690480860866444,
      "learning_rate": 6.426639424843892e-06,
      "loss": 0.0155,
      "step": 330
    },
    {
      "epoch": 4.527027027027027,
      "grad_norm": 0.30615645251349044,
      "learning_rate": 6.095013843139662e-06,
      "loss": 0.0142,
      "step": 335
    },
    {
      "epoch": 4.594594594594595,
      "grad_norm": 0.24160715474139485,
      "learning_rate": 5.806249822994849e-06,
      "loss": 0.0134,
      "step": 340
    },
    {
      "epoch": 4.662162162162162,
      "grad_norm": 0.24906080295211588,
      "learning_rate": 5.560925588414595e-06,
      "loss": 0.0133,
      "step": 345
    },
    {
      "epoch": 4.72972972972973,
      "grad_norm": 0.4021706429563905,
      "learning_rate": 5.359532379136472e-06,
      "loss": 0.0137,
      "step": 350
    },
    {
      "epoch": 4.797297297297297,
      "grad_norm": 0.29394464912604296,
      "learning_rate": 5.20247346696706e-06,
      "loss": 0.0139,
      "step": 355
    },
    {
      "epoch": 4.864864864864865,
      "grad_norm": 0.31733228546671827,
      "learning_rate": 5.090063348266363e-06,
      "loss": 0.0158,
      "step": 360
    },
    {
      "epoch": 4.9324324324324325,
      "grad_norm": 0.33778908257293244,
      "learning_rate": 5.022527114197126e-06,
      "loss": 0.0143,
      "step": 365
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.28233495289671173,
      "learning_rate": 5e-06,
      "loss": 0.0131,
      "step": 370
    },
    {
      "epoch": 5.0,
      "step": 370,
      "total_flos": 626617246416896.0,
      "train_loss": 0.08566334958414773,
      "train_runtime": 7937.4817,
      "train_samples_per_second": 5.959,
      "train_steps_per_second": 0.047
    }
  ],
  "logging_steps": 5,
  "max_steps": 370,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 626617246416896.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}