{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 363,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013793103448275862,
      "grad_norm": 1.2861284017562866,
      "learning_rate": 1.3186813186813187e-06,
      "loss": 1.2808,
      "step": 5
    },
    {
      "epoch": 0.027586206896551724,
      "grad_norm": 1.0939148664474487,
      "learning_rate": 2.967032967032967e-06,
      "loss": 1.3562,
      "step": 10
    },
    {
      "epoch": 0.041379310344827586,
      "grad_norm": 0.7352843284606934,
      "learning_rate": 4.615384615384616e-06,
      "loss": 1.2664,
      "step": 15
    },
    {
      "epoch": 0.05517241379310345,
      "grad_norm": 0.644305944442749,
      "learning_rate": 6.2637362637362645e-06,
      "loss": 1.2978,
      "step": 20
    },
    {
      "epoch": 0.06896551724137931,
      "grad_norm": 0.5266907215118408,
      "learning_rate": 7.912087912087913e-06,
      "loss": 1.3218,
      "step": 25
    },
    {
      "epoch": 0.08275862068965517,
      "grad_norm": 0.5709158778190613,
      "learning_rate": 9.56043956043956e-06,
      "loss": 1.2448,
      "step": 30
    },
    {
      "epoch": 0.09655172413793103,
      "grad_norm": 0.5846296548843384,
      "learning_rate": 1.120879120879121e-05,
      "loss": 1.2439,
      "step": 35
    },
    {
      "epoch": 0.1103448275862069,
      "grad_norm": 0.4904540479183197,
      "learning_rate": 1.2857142857142857e-05,
      "loss": 1.2162,
      "step": 40
    },
    {
      "epoch": 0.12413793103448276,
      "grad_norm": 0.5115934014320374,
      "learning_rate": 1.4505494505494506e-05,
      "loss": 1.2357,
      "step": 45
    },
    {
      "epoch": 0.13793103448275862,
      "grad_norm": 0.4867129325866699,
      "learning_rate": 1.6153846153846154e-05,
      "loss": 1.1822,
      "step": 50
    },
    {
      "epoch": 0.15172413793103448,
      "grad_norm": 0.6010071039199829,
      "learning_rate": 1.78021978021978e-05,
      "loss": 1.1464,
      "step": 55
    },
    {
      "epoch": 0.16551724137931034,
      "grad_norm": 0.43062254786491394,
      "learning_rate": 1.9450549450549452e-05,
      "loss": 1.1763,
      "step": 60
    },
    {
      "epoch": 0.1793103448275862,
      "grad_norm": 0.5273615717887878,
      "learning_rate": 2.10989010989011e-05,
      "loss": 1.1936,
      "step": 65
    },
    {
      "epoch": 0.19310344827586207,
      "grad_norm": 0.46626806259155273,
      "learning_rate": 2.2747252747252748e-05,
      "loss": 1.1823,
      "step": 70
    },
    {
      "epoch": 0.20689655172413793,
      "grad_norm": 0.5032982230186462,
      "learning_rate": 2.4395604395604395e-05,
      "loss": 1.1455,
      "step": 75
    },
    {
      "epoch": 0.2206896551724138,
      "grad_norm": 0.4601927101612091,
      "learning_rate": 2.6043956043956046e-05,
      "loss": 1.126,
      "step": 80
    },
    {
      "epoch": 0.23448275862068965,
      "grad_norm": 0.5814331769943237,
      "learning_rate": 2.7692307692307694e-05,
      "loss": 1.1835,
      "step": 85
    },
    {
      "epoch": 0.2482758620689655,
      "grad_norm": 0.5030220150947571,
      "learning_rate": 2.934065934065934e-05,
      "loss": 1.1253,
      "step": 90
    },
    {
      "epoch": 0.2620689655172414,
      "grad_norm": 0.5223703980445862,
      "learning_rate": 2.9999775855589334e-05,
      "loss": 1.1587,
      "step": 95
    },
    {
      "epoch": 0.27586206896551724,
      "grad_norm": 0.5958484411239624,
      "learning_rate": 2.9998406108449657e-05,
      "loss": 1.0926,
      "step": 100
    },
    {
      "epoch": 0.2896551724137931,
      "grad_norm": 0.500812292098999,
      "learning_rate": 2.9995791252416083e-05,
      "loss": 1.0628,
      "step": 105
    },
    {
      "epoch": 0.30344827586206896,
      "grad_norm": 0.5202997326850891,
      "learning_rate": 2.9991931504563725e-05,
      "loss": 1.1535,
      "step": 110
    },
    {
      "epoch": 0.31724137931034485,
      "grad_norm": 0.47132763266563416,
      "learning_rate": 2.9986827185313715e-05,
      "loss": 1.0873,
      "step": 115
    },
    {
      "epoch": 0.3310344827586207,
      "grad_norm": 0.5247320532798767,
      "learning_rate": 2.998047871840664e-05,
      "loss": 1.0437,
      "step": 120
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 0.6326524019241333,
      "learning_rate": 2.9972886630867334e-05,
      "loss": 1.0278,
      "step": 125
    },
    {
      "epoch": 0.3586206896551724,
      "grad_norm": 0.6137468814849854,
      "learning_rate": 2.996405155296116e-05,
      "loss": 0.9953,
      "step": 130
    },
    {
      "epoch": 0.3724137931034483,
      "grad_norm": 0.6893109679222107,
      "learning_rate": 2.995397421814165e-05,
      "loss": 1.0209,
      "step": 135
    },
    {
      "epoch": 0.38620689655172413,
      "grad_norm": 0.6077777743339539,
      "learning_rate": 2.994265546298965e-05,
      "loss": 0.9781,
      "step": 140
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.6185184717178345,
      "learning_rate": 2.993009622714385e-05,
      "loss": 1.0459,
      "step": 145
    },
    {
      "epoch": 0.41379310344827586,
      "grad_norm": 0.6799812912940979,
      "learning_rate": 2.991629755322279e-05,
      "loss": 1.0188,
      "step": 150
    },
    {
      "epoch": 0.42758620689655175,
      "grad_norm": 0.6423669457435608,
      "learning_rate": 2.9901260586738305e-05,
      "loss": 1.036,
      "step": 155
    },
    {
      "epoch": 0.4413793103448276,
      "grad_norm": 0.7912122011184692,
      "learning_rate": 2.9884986576000416e-05,
      "loss": 0.9727,
      "step": 160
    },
    {
      "epoch": 0.45517241379310347,
      "grad_norm": 0.6771214604377747,
      "learning_rate": 2.9867476872013707e-05,
      "loss": 0.9286,
      "step": 165
    },
    {
      "epoch": 0.4689655172413793,
      "grad_norm": 0.6864525079727173,
      "learning_rate": 2.9848732928365188e-05,
      "loss": 0.9362,
      "step": 170
    },
    {
      "epoch": 0.4827586206896552,
      "grad_norm": 0.7123166918754578,
      "learning_rate": 2.98287563011036e-05,
      "loss": 0.9029,
      "step": 175
    },
    {
      "epoch": 0.496551724137931,
      "grad_norm": 0.6900257468223572,
      "learning_rate": 2.9807548648610238e-05,
      "loss": 0.9367,
      "step": 180
    },
    {
      "epoch": 0.5103448275862069,
      "grad_norm": 0.7352802157402039,
      "learning_rate": 2.9785111731461306e-05,
      "loss": 0.9544,
      "step": 185
    },
    {
      "epoch": 0.5241379310344828,
      "grad_norm": 0.7163735628128052,
      "learning_rate": 2.976144741228173e-05,
      "loss": 0.8899,
      "step": 190
    },
    {
      "epoch": 0.5379310344827586,
      "grad_norm": 0.7872961759567261,
      "learning_rate": 2.9736557655590536e-05,
      "loss": 0.939,
      "step": 195
    },
    {
      "epoch": 0.5517241379310345,
      "grad_norm": 0.7545033097267151,
      "learning_rate": 2.9710444527637785e-05,
      "loss": 0.8738,
      "step": 200
    },
    {
      "epoch": 0.5655172413793104,
      "grad_norm": 0.8260722756385803,
      "learning_rate": 2.9683110196233022e-05,
      "loss": 0.9045,
      "step": 205
    },
    {
      "epoch": 0.5793103448275863,
      "grad_norm": 0.7296833395957947,
      "learning_rate": 2.96545569305653e-05,
      "loss": 0.904,
      "step": 210
    },
    {
      "epoch": 0.593103448275862,
      "grad_norm": 0.8601064085960388,
      "learning_rate": 2.9624787101014838e-05,
      "loss": 0.8197,
      "step": 215
    },
    {
      "epoch": 0.6068965517241379,
      "grad_norm": 0.8468939065933228,
      "learning_rate": 2.9593803178956208e-05,
      "loss": 0.836,
      "step": 220
    },
    {
      "epoch": 0.6206896551724138,
      "grad_norm": 0.7784414887428284,
      "learning_rate": 2.9561607736553194e-05,
      "loss": 0.8486,
      "step": 225
    },
    {
      "epoch": 0.6344827586206897,
      "grad_norm": 0.9513041973114014,
      "learning_rate": 2.952820344654524e-05,
      "loss": 0.8396,
      "step": 230
    },
    {
      "epoch": 0.6482758620689655,
      "grad_norm": 0.8774826526641846,
      "learning_rate": 2.9493593082025586e-05,
      "loss": 0.8223,
      "step": 235
    },
    {
      "epoch": 0.6620689655172414,
      "grad_norm": 0.8445528149604797,
      "learning_rate": 2.9457779516211057e-05,
      "loss": 0.8663,
      "step": 240
    },
    {
      "epoch": 0.6758620689655173,
      "grad_norm": 1.1822575330734253,
      "learning_rate": 2.9420765722203522e-05,
      "loss": 0.8806,
      "step": 245
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 0.8731847405433655,
      "learning_rate": 2.9382554772743092e-05,
      "loss": 0.8232,
      "step": 250
    },
    {
      "epoch": 0.7034482758620689,
      "grad_norm": 0.9695132970809937,
      "learning_rate": 2.9343149839953044e-05,
      "loss": 0.7962,
      "step": 255
    },
    {
      "epoch": 0.7172413793103448,
      "grad_norm": 0.9002068638801575,
      "learning_rate": 2.9302554195076462e-05,
      "loss": 0.812,
      "step": 260
    },
    {
      "epoch": 0.7310344827586207,
      "grad_norm": 0.9631876349449158,
      "learning_rate": 2.926077120820468e-05,
      "loss": 0.7827,
      "step": 265
    },
    {
      "epoch": 0.7448275862068966,
      "grad_norm": 0.8464678525924683,
      "learning_rate": 2.9217804347997514e-05,
      "loss": 0.7673,
      "step": 270
    },
    {
      "epoch": 0.7586206896551724,
      "grad_norm": 0.8802338242530823,
      "learning_rate": 2.9173657181395308e-05,
      "loss": 0.7825,
      "step": 275
    },
    {
      "epoch": 0.7724137931034483,
      "grad_norm": 0.972342312335968,
      "learning_rate": 2.912833337332281e-05,
      "loss": 0.7638,
      "step": 280
    },
    {
      "epoch": 0.7862068965517242,
      "grad_norm": 0.9336219429969788,
      "learning_rate": 2.9081836686384934e-05,
      "loss": 0.7503,
      "step": 285
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.9606114625930786,
      "learning_rate": 2.90341709805544e-05,
      "loss": 0.7615,
      "step": 290
    },
    {
      "epoch": 0.8137931034482758,
      "grad_norm": 0.9412868618965149,
      "learning_rate": 2.8985340212851304e-05,
      "loss": 0.7718,
      "step": 295
    },
    {
      "epoch": 0.8275862068965517,
      "grad_norm": 1.0660676956176758,
      "learning_rate": 2.89353484370146e-05,
      "loss": 0.7839,
      "step": 300
    },
    {
      "epoch": 0.8413793103448276,
      "grad_norm": 0.9120925068855286,
      "learning_rate": 2.888419980316559e-05,
      "loss": 0.7595,
      "step": 305
    },
    {
      "epoch": 0.8551724137931035,
      "grad_norm": 0.8678473234176636,
      "learning_rate": 2.88318985574634e-05,
      "loss": 0.7418,
      "step": 310
    },
    {
      "epoch": 0.8689655172413793,
      "grad_norm": 1.0073208808898926,
      "learning_rate": 2.8778449041752463e-05,
      "loss": 0.7102,
      "step": 315
    },
    {
      "epoch": 0.8827586206896552,
      "grad_norm": 0.9804509282112122,
      "learning_rate": 2.8723855693202103e-05,
      "loss": 0.7199,
      "step": 320
    },
    {
      "epoch": 0.896551724137931,
      "grad_norm": 1.1153241395950317,
      "learning_rate": 2.866812304393816e-05,
      "loss": 0.7347,
      "step": 325
    },
    {
      "epoch": 0.9103448275862069,
      "grad_norm": 0.9621334671974182,
      "learning_rate": 2.8611255720666743e-05,
      "loss": 0.7268,
      "step": 330
    },
    {
      "epoch": 0.9241379310344827,
      "grad_norm": 1.0361660718917847,
      "learning_rate": 2.8553258444290155e-05,
      "loss": 0.6755,
      "step": 335
    },
    {
      "epoch": 0.9379310344827586,
      "grad_norm": 1.0129109621047974,
      "learning_rate": 2.8494136029514992e-05,
      "loss": 0.6995,
      "step": 340
    },
    {
      "epoch": 0.9517241379310345,
      "grad_norm": 1.198005199432373,
      "learning_rate": 2.84338933844524e-05,
      "loss": 0.6903,
      "step": 345
    },
    {
      "epoch": 0.9655172413793104,
      "grad_norm": 1.121144413948059,
      "learning_rate": 2.8372535510210694e-05,
      "loss": 0.6686,
      "step": 350
    },
    {
      "epoch": 0.9793103448275862,
      "grad_norm": 1.0109779834747314,
      "learning_rate": 2.8310067500480105e-05,
      "loss": 0.6309,
      "step": 355
    },
    {
      "epoch": 0.993103448275862,
      "grad_norm": 1.0399612188339233,
      "learning_rate": 2.8246494541109985e-05,
      "loss": 0.7209,
      "step": 360
    }
  ],
  "logging_steps": 5,
  "max_steps": 1815,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.1438772296246886e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}