{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 300,
  "global_step": 819,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003663003663003663,
      "grad_norm": 165.0,
      "learning_rate": 2e-06,
      "loss": 9.1083,
      "step": 1
    },
    {
      "epoch": 0.018315018315018316,
      "grad_norm": 64.0,
      "learning_rate": 1.9998820020169668e-06,
      "loss": 8.3175,
      "step": 5
    },
    {
      "epoch": 0.03663003663003663,
      "grad_norm": 26.875,
      "learning_rate": 1.999402682936637e-06,
      "loss": 7.3293,
      "step": 10
    },
    {
      "epoch": 0.054945054945054944,
      "grad_norm": 16.75,
      "learning_rate": 1.998554844493029e-06,
      "loss": 6.8602,
      "step": 15
    },
    {
      "epoch": 0.07326007326007326,
      "grad_norm": 11.0,
      "learning_rate": 1.997338799317767e-06,
      "loss": 6.6054,
      "step": 20
    },
    {
      "epoch": 0.09157509157509157,
      "grad_norm": 8.4375,
      "learning_rate": 1.995754995814884e-06,
      "loss": 6.3957,
      "step": 25
    },
    {
      "epoch": 0.10989010989010989,
      "grad_norm": 6.9375,
      "learning_rate": 1.9938040179954784e-06,
      "loss": 6.256,
      "step": 30
    },
    {
      "epoch": 0.1282051282051282,
      "grad_norm": 6.15625,
      "learning_rate": 1.991486585262365e-06,
      "loss": 6.1321,
      "step": 35
    },
    {
      "epoch": 0.14652014652014653,
      "grad_norm": 5.1875,
      "learning_rate": 1.988803552144804e-06,
      "loss": 6.018,
      "step": 40
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 5.59375,
      "learning_rate": 1.9857559079834022e-06,
      "loss": 5.9438,
      "step": 45
    },
    {
      "epoch": 0.18315018315018314,
      "grad_norm": 6.5,
      "learning_rate": 1.982344776565302e-06,
      "loss": 5.8733,
      "step": 50
    },
    {
      "epoch": 0.20146520146520147,
      "grad_norm": 4.84375,
      "learning_rate": 1.978571415709799e-06,
      "loss": 5.8341,
      "step": 55
    },
    {
      "epoch": 0.21978021978021978,
      "grad_norm": 4.125,
      "learning_rate": 1.9744372168045322e-06,
      "loss": 5.793,
      "step": 60
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 3.8125,
      "learning_rate": 1.9699437042924264e-06,
      "loss": 5.7305,
      "step": 65
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 4.0,
      "learning_rate": 1.965092535109567e-06,
      "loss": 5.671,
      "step": 70
    },
    {
      "epoch": 0.27472527472527475,
      "grad_norm": 4.125,
      "learning_rate": 1.959885498074224e-06,
      "loss": 5.6563,
      "step": 75
    },
    {
      "epoch": 0.29304029304029305,
      "grad_norm": 3.765625,
      "learning_rate": 1.954324513227244e-06,
      "loss": 5.5778,
      "step": 80
    },
    {
      "epoch": 0.31135531135531136,
      "grad_norm": 3.75,
      "learning_rate": 1.948411631124053e-06,
      "loss": 5.5838,
      "step": 85
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 6.71875,
      "learning_rate": 1.942149032078538e-06,
      "loss": 5.5305,
      "step": 90
    },
    {
      "epoch": 0.34798534798534797,
      "grad_norm": 4.6875,
      "learning_rate": 1.935539025359077e-06,
      "loss": 5.5108,
      "step": 95
    },
    {
      "epoch": 0.3663003663003663,
      "grad_norm": 3.546875,
      "learning_rate": 1.928584048337022e-06,
      "loss": 5.494,
      "step": 100
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 3.75,
      "learning_rate": 1.9212866655879395e-06,
      "loss": 5.4749,
      "step": 105
    },
    {
      "epoch": 0.40293040293040294,
      "grad_norm": 4.5,
      "learning_rate": 1.9136495679459563e-06,
      "loss": 5.4473,
      "step": 110
    },
    {
      "epoch": 0.42124542124542125,
      "grad_norm": 4.34375,
      "learning_rate": 1.9056755715115372e-06,
      "loss": 5.4071,
      "step": 115
    },
    {
      "epoch": 0.43956043956043955,
      "grad_norm": 3.609375,
      "learning_rate": 1.8973676166130791e-06,
      "loss": 5.3994,
      "step": 120
    },
    {
      "epoch": 0.45787545787545786,
      "grad_norm": 3.859375,
      "learning_rate": 1.8887287667226963e-06,
      "loss": 5.3773,
      "step": 125
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 3.4375,
      "learning_rate": 1.8797622073265943e-06,
      "loss": 5.3734,
      "step": 130
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 3.8125,
      "learning_rate": 1.8704712447504579e-06,
      "loss": 5.323,
      "step": 135
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 3.4375,
      "learning_rate": 1.8608593049402752e-06,
      "loss": 5.2964,
      "step": 140
    },
    {
      "epoch": 0.5311355311355311,
      "grad_norm": 3.484375,
      "learning_rate": 1.850929932199058e-06,
      "loss": 5.2951,
      "step": 145
    },
    {
      "epoch": 0.5494505494505495,
      "grad_norm": 3.375,
      "learning_rate": 1.8406867878799152e-06,
      "loss": 5.2498,
      "step": 150
    },
    {
      "epoch": 0.5677655677655677,
      "grad_norm": 3.859375,
      "learning_rate": 1.8301336490359678e-06,
      "loss": 5.2432,
      "step": 155
    },
    {
      "epoch": 0.5860805860805861,
      "grad_norm": 3.90625,
      "learning_rate": 1.819274407027599e-06,
      "loss": 5.2436,
      "step": 160
    },
    {
      "epoch": 0.6043956043956044,
      "grad_norm": 4.6875,
      "learning_rate": 1.8081130660875555e-06,
      "loss": 5.2218,
      "step": 165
    },
    {
      "epoch": 0.6227106227106227,
      "grad_norm": 3.5625,
      "learning_rate": 1.79665374184443e-06,
      "loss": 5.2194,
      "step": 170
    },
    {
      "epoch": 0.6410256410256411,
      "grad_norm": 3.546875,
      "learning_rate": 1.7849006598050625e-06,
      "loss": 5.1988,
      "step": 175
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 3.9375,
      "learning_rate": 1.7728581537964318e-06,
      "loss": 5.1814,
      "step": 180
    },
    {
      "epoch": 0.6776556776556777,
      "grad_norm": 4.40625,
      "learning_rate": 1.7605306643676006e-06,
      "loss": 5.1318,
      "step": 185
    },
    {
      "epoch": 0.6959706959706959,
      "grad_norm": 3.4375,
      "learning_rate": 1.747922737152308e-06,
      "loss": 5.1609,
      "step": 190
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 4.125,
      "learning_rate": 1.7350390211928166e-06,
      "loss": 5.1395,
      "step": 195
    },
    {
      "epoch": 0.7326007326007326,
      "grad_norm": 3.375,
      "learning_rate": 1.721884267225624e-06,
      "loss": 5.0794,
      "step": 200
    },
    {
      "epoch": 0.7509157509157509,
      "grad_norm": 3.421875,
      "learning_rate": 1.7084633259296795e-06,
      "loss": 5.0974,
      "step": 205
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 3.46875,
      "learning_rate": 1.6947811461377467e-06,
      "loss": 5.1007,
      "step": 210
    },
    {
      "epoch": 0.7875457875457875,
      "grad_norm": 3.984375,
      "learning_rate": 1.6808427730115712e-06,
      "loss": 5.0777,
      "step": 215
    },
    {
      "epoch": 0.8058608058608059,
      "grad_norm": 3.828125,
      "learning_rate": 1.6666533461815323e-06,
      "loss": 5.0517,
      "step": 220
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 3.546875,
      "learning_rate": 1.6522180978514552e-06,
      "loss": 5.0462,
      "step": 225
    },
    {
      "epoch": 0.8424908424908425,
      "grad_norm": 3.78125,
      "learning_rate": 1.6375423508692912e-06,
      "loss": 5.0538,
      "step": 230
    },
    {
      "epoch": 0.8608058608058609,
      "grad_norm": 3.515625,
      "learning_rate": 1.622631516764372e-06,
      "loss": 5.0335,
      "step": 235
    },
    {
      "epoch": 0.8791208791208791,
      "grad_norm": 3.359375,
      "learning_rate": 1.607491093751966e-06,
      "loss": 5.0177,
      "step": 240
    },
    {
      "epoch": 0.8974358974358975,
      "grad_norm": 4.8125,
      "learning_rate": 1.592126664705868e-06,
      "loss": 4.998,
      "step": 245
    },
    {
      "epoch": 0.9157509157509157,
      "grad_norm": 3.671875,
      "learning_rate": 1.5765438950997703e-06,
      "loss": 4.992,
      "step": 250
    },
    {
      "epoch": 0.9340659340659341,
      "grad_norm": 3.828125,
      "learning_rate": 1.5607485309181812e-06,
      "loss": 4.9831,
      "step": 255
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 3.90625,
      "learning_rate": 1.544746396537651e-06,
      "loss": 4.9835,
      "step": 260
    },
    {
      "epoch": 0.9706959706959707,
      "grad_norm": 3.484375,
      "learning_rate": 1.5285433925790945e-06,
      "loss": 4.962,
      "step": 265
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 3.421875,
      "learning_rate": 1.5121454937319975e-06,
      "loss": 4.9708,
      "step": 270
    },
    {
      "epoch": 1.0073260073260073,
      "grad_norm": 3.9375,
      "learning_rate": 1.4955587465513128e-06,
      "loss": 4.9494,
      "step": 275
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 3.703125,
      "learning_rate": 1.4787892672278555e-06,
      "loss": 4.9172,
      "step": 280
    },
    {
      "epoch": 1.043956043956044,
      "grad_norm": 3.515625,
      "learning_rate": 1.461843239333021e-06,
      "loss": 4.9262,
      "step": 285
    },
    {
      "epoch": 1.0622710622710623,
      "grad_norm": 3.75,
      "learning_rate": 1.444726911538657e-06,
      "loss": 4.9115,
      "step": 290
    },
    {
      "epoch": 1.0805860805860805,
      "grad_norm": 3.671875,
      "learning_rate": 1.4274465953129325e-06,
      "loss": 4.8926,
      "step": 295
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 3.625,
      "learning_rate": 1.4100086625930462e-06,
      "loss": 4.8845,
      "step": 300
    },
    {
      "epoch": 1.098901098901099,
      "eval_loss": 4.895308017730713,
      "eval_runtime": 14.5245,
      "eval_samples_per_second": 36.421,
      "eval_steps_per_second": 1.17,
      "step": 300
    },
    {
      "epoch": 1.1172161172161172,
      "grad_norm": 3.5,
      "learning_rate": 1.3924195434356441e-06,
      "loss": 4.8754,
      "step": 305
    },
    {
      "epoch": 1.1355311355311355,
      "grad_norm": 3.484375,
      "learning_rate": 1.3746857236458005e-06,
      "loss": 4.8566,
      "step": 310
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 3.875,
      "learning_rate": 1.3568137423854457e-06,
      "loss": 4.873,
      "step": 315
    },
    {
      "epoch": 1.1721611721611722,
      "grad_norm": 3.515625,
      "learning_rate": 1.3388101897621183e-06,
      "loss": 4.8476,
      "step": 320
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 4.0,
      "learning_rate": 1.32068170439893e-06,
      "loss": 4.8846,
      "step": 325
    },
    {
      "epoch": 1.2087912087912087,
      "grad_norm": 3.453125,
      "learning_rate": 1.3024349709866448e-06,
      "loss": 4.864,
      "step": 330
    },
    {
      "epoch": 1.2271062271062272,
      "grad_norm": 5.125,
      "learning_rate": 1.2840767178187654e-06,
      "loss": 4.8457,
      "step": 335
    },
    {
      "epoch": 1.2454212454212454,
      "grad_norm": 3.828125,
      "learning_rate": 1.265613714310548e-06,
      "loss": 4.8469,
      "step": 340
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 3.59375,
      "learning_rate": 1.2470527685028482e-06,
      "loss": 4.8406,
      "step": 345
    },
    {
      "epoch": 1.282051282051282,
      "grad_norm": 3.609375,
      "learning_rate": 1.228400724551728e-06,
      "loss": 4.8545,
      "step": 350
    },
    {
      "epoch": 1.3003663003663004,
      "grad_norm": 3.578125,
      "learning_rate": 1.2096644602047445e-06,
      "loss": 4.8236,
      "step": 355
    },
    {
      "epoch": 1.3186813186813187,
      "grad_norm": 3.515625,
      "learning_rate": 1.1908508842648505e-06,
      "loss": 4.8126,
      "step": 360
    },
    {
      "epoch": 1.3369963369963371,
      "grad_norm": 3.453125,
      "learning_rate": 1.171966934042847e-06,
      "loss": 4.8038,
      "step": 365
    },
    {
      "epoch": 1.3553113553113554,
      "grad_norm": 3.484375,
      "learning_rate": 1.1530195727993199e-06,
      "loss": 4.8278,
      "step": 370
    },
    {
      "epoch": 1.3736263736263736,
      "grad_norm": 3.53125,
      "learning_rate": 1.1340157871770115e-06,
      "loss": 4.8217,
      "step": 375
    },
    {
      "epoch": 1.3919413919413919,
      "grad_norm": 3.6875,
      "learning_rate": 1.1149625846245681e-06,
      "loss": 4.7912,
      "step": 380
    },
    {
      "epoch": 1.4102564102564101,
      "grad_norm": 3.515625,
      "learning_rate": 1.095866990812615e-06,
      "loss": 4.8004,
      "step": 385
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 3.5625,
      "learning_rate": 1.0767360470431157e-06,
      "loss": 4.7896,
      "step": 390
    },
    {
      "epoch": 1.4468864468864469,
      "grad_norm": 3.625,
      "learning_rate": 1.0575768076529625e-06,
      "loss": 4.7788,
      "step": 395
    },
    {
      "epoch": 1.4652014652014653,
      "grad_norm": 3.640625,
      "learning_rate": 1.0383963374127645e-06,
      "loss": 4.8106,
      "step": 400
    },
    {
      "epoch": 1.4835164835164836,
      "grad_norm": 3.71875,
      "learning_rate": 1.0192017089217861e-06,
      "loss": 4.7749,
      "step": 405
    },
    {
      "epoch": 1.5018315018315018,
      "grad_norm": 3.484375,
      "learning_rate": 1e-06,
      "loss": 4.7864,
      "step": 410
    },
    {
      "epoch": 1.52014652014652,
      "grad_norm": 3.59375,
      "learning_rate": 9.80798291078214e-07,
      "loss": 4.7869,
      "step": 415
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 3.625,
      "learning_rate": 9.616036625872356e-07,
      "loss": 4.8314,
      "step": 420
    },
    {
      "epoch": 1.5567765567765568,
      "grad_norm": 3.734375,
      "learning_rate": 9.424231923470376e-07,
      "loss": 4.7831,
      "step": 425
    },
    {
      "epoch": 1.575091575091575,
      "grad_norm": 3.578125,
      "learning_rate": 9.232639529568842e-07,
      "loss": 4.7636,
      "step": 430
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 3.71875,
      "learning_rate": 9.041330091873851e-07,
      "loss": 4.7465,
      "step": 435
    },
    {
      "epoch": 1.6117216117216118,
      "grad_norm": 3.546875,
      "learning_rate": 8.850374153754321e-07,
      "loss": 4.7616,
      "step": 440
    },
    {
      "epoch": 1.63003663003663,
      "grad_norm": 3.46875,
      "learning_rate": 8.659842128229886e-07,
      "loss": 4.7542,
      "step": 445
    },
    {
      "epoch": 1.6483516483516483,
      "grad_norm": 3.5,
      "learning_rate": 8.4698042720068e-07,
      "loss": 4.745,
      "step": 450
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 3.921875,
      "learning_rate": 8.280330659571531e-07,
      "loss": 4.738,
      "step": 455
    },
    {
      "epoch": 1.684981684981685,
      "grad_norm": 3.75,
      "learning_rate": 8.091491157351493e-07,
      "loss": 4.7335,
      "step": 460
    },
    {
      "epoch": 1.7032967032967035,
      "grad_norm": 3.546875,
      "learning_rate": 7.903355397952556e-07,
      "loss": 4.7792,
      "step": 465
    },
    {
      "epoch": 1.7216117216117217,
      "grad_norm": 3.546875,
      "learning_rate": 7.715992754482718e-07,
      "loss": 4.7288,
      "step": 470
    },
    {
      "epoch": 1.73992673992674,
      "grad_norm": 3.515625,
      "learning_rate": 7.529472314971522e-07,
      "loss": 4.7489,
      "step": 475
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 3.484375,
      "learning_rate": 7.34386285689452e-07,
      "loss": 4.7163,
      "step": 480
    },
    {
      "epoch": 1.7765567765567765,
      "grad_norm": 3.828125,
      "learning_rate": 7.159232821812347e-07,
      "loss": 4.7201,
      "step": 485
    },
    {
      "epoch": 1.7948717948717947,
      "grad_norm": 3.5625,
      "learning_rate": 6.975650290133554e-07,
      "loss": 4.7334,
      "step": 490
    },
    {
      "epoch": 1.8131868131868132,
      "grad_norm": 3.609375,
      "learning_rate": 6.793182956010699e-07,
      "loss": 4.7339,
      "step": 495
    },
    {
      "epoch": 1.8315018315018317,
      "grad_norm": 3.484375,
      "learning_rate": 6.611898102378818e-07,
      "loss": 4.7384,
      "step": 500
    },
    {
      "epoch": 1.84981684981685,
      "grad_norm": 3.546875,
      "learning_rate": 6.431862576145544e-07,
      "loss": 4.7402,
      "step": 505
    },
    {
      "epoch": 1.8681318681318682,
      "grad_norm": 3.703125,
      "learning_rate": 6.253142763541995e-07,
      "loss": 4.723,
      "step": 510
    },
    {
      "epoch": 1.8864468864468864,
      "grad_norm": 3.5,
      "learning_rate": 6.075804565643561e-07,
      "loss": 4.7457,
      "step": 515
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 3.5625,
      "learning_rate": 5.899913374069538e-07,
      "loss": 4.712,
      "step": 520
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 3.703125,
      "learning_rate": 5.725534046870677e-07,
      "loss": 4.7273,
      "step": 525
    },
    {
      "epoch": 1.9413919413919414,
      "grad_norm": 3.5625,
      "learning_rate": 5.552730884613428e-07,
      "loss": 4.6981,
      "step": 530
    },
    {
      "epoch": 1.9597069597069599,
      "grad_norm": 3.609375,
      "learning_rate": 5.381567606669793e-07,
      "loss": 4.7482,
      "step": 535
    },
    {
      "epoch": 1.978021978021978,
      "grad_norm": 3.765625,
      "learning_rate": 5.212107327721445e-07,
      "loss": 4.718,
      "step": 540
    },
    {
      "epoch": 1.9963369963369964,
      "grad_norm": 3.6875,
      "learning_rate": 5.044412534486873e-07,
      "loss": 4.7148,
      "step": 545
    },
    {
      "epoch": 2.0146520146520146,
      "grad_norm": 3.71875,
      "learning_rate": 4.878545062680026e-07,
      "loss": 4.6767,
      "step": 550
    },
    {
      "epoch": 2.032967032967033,
      "grad_norm": 3.453125,
      "learning_rate": 4.7145660742090575e-07,
      "loss": 4.706,
      "step": 555
    },
    {
      "epoch": 2.051282051282051,
      "grad_norm": 4.0,
      "learning_rate": 4.5525360346234907e-07,
      "loss": 4.7142,
      "step": 560
    },
    {
      "epoch": 2.06959706959707,
      "grad_norm": 3.546875,
      "learning_rate": 4.392514690818193e-07,
      "loss": 4.7053,
      "step": 565
    },
    {
      "epoch": 2.087912087912088,
      "grad_norm": 3.765625,
      "learning_rate": 4.2345610490022996e-07,
      "loss": 4.6978,
      "step": 570
    },
    {
      "epoch": 2.1062271062271063,
      "grad_norm": 3.53125,
      "learning_rate": 4.078733352941321e-07,
      "loss": 4.7147,
      "step": 575
    },
    {
      "epoch": 2.1245421245421245,
      "grad_norm": 3.546875,
      "learning_rate": 3.925089062480339e-07,
      "loss": 4.6861,
      "step": 580
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 3.703125,
      "learning_rate": 3.77368483235628e-07,
      "loss": 4.725,
      "step": 585
    },
    {
      "epoch": 2.161172161172161,
      "grad_norm": 3.453125,
      "learning_rate": 3.6245764913070875e-07,
      "loss": 4.7223,
      "step": 590
    },
    {
      "epoch": 2.1794871794871793,
      "grad_norm": 3.578125,
      "learning_rate": 3.477819021485447e-07,
      "loss": 4.7254,
      "step": 595
    },
    {
      "epoch": 2.197802197802198,
      "grad_norm": 3.578125,
      "learning_rate": 3.333466538184674e-07,
      "loss": 4.7074,
      "step": 600
    },
    {
      "epoch": 2.197802197802198,
      "eval_loss": 4.718916893005371,
      "eval_runtime": 14.5284,
      "eval_samples_per_second": 36.412,
      "eval_steps_per_second": 1.17,
      "step": 600
    },
    {
      "epoch": 2.2161172161172162,
      "grad_norm": 3.546875,
      "learning_rate": 3.1915722698842874e-07,
      "loss": 4.705,
      "step": 605
    },
    {
      "epoch": 2.2344322344322345,
      "grad_norm": 3.734375,
      "learning_rate": 3.0521885386225344e-07,
      "loss": 4.7118,
      "step": 610
    },
    {
      "epoch": 2.2527472527472527,
      "grad_norm": 3.703125,
      "learning_rate": 2.9153667407032066e-07,
      "loss": 4.7285,
      "step": 615
    },
    {
      "epoch": 2.271062271062271,
      "grad_norm": 3.59375,
      "learning_rate": 2.7811573277437603e-07,
      "loss": 4.681,
      "step": 620
    },
    {
      "epoch": 2.2893772893772892,
      "grad_norm": 3.546875,
      "learning_rate": 2.649609788071836e-07,
      "loss": 4.707,
      "step": 625
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 3.46875,
      "learning_rate": 2.520772628476919e-07,
      "loss": 4.7278,
      "step": 630
    },
    {
      "epoch": 2.326007326007326,
      "grad_norm": 3.59375,
      "learning_rate": 2.394693356323997e-07,
      "loss": 4.7202,
      "step": 635
    },
    {
      "epoch": 2.3443223443223444,
      "grad_norm": 3.609375,
      "learning_rate": 2.2714184620356826e-07,
      "loss": 4.706,
      "step": 640
    },
    {
      "epoch": 2.3626373626373627,
      "grad_norm": 3.5,
      "learning_rate": 2.150993401949376e-07,
      "loss": 4.732,
      "step": 645
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 4.46875,
      "learning_rate": 2.0334625815557026e-07,
      "loss": 4.6981,
      "step": 650
    },
    {
      "epoch": 2.399267399267399,
      "grad_norm": 3.5625,
      "learning_rate": 1.9188693391244438e-07,
      "loss": 4.7334,
      "step": 655
    },
    {
      "epoch": 2.4175824175824174,
      "grad_norm": 3.609375,
      "learning_rate": 1.8072559297240097e-07,
      "loss": 4.7284,
      "step": 660
    },
    {
      "epoch": 2.435897435897436,
      "grad_norm": 3.515625,
      "learning_rate": 1.6986635096403212e-07,
      "loss": 4.7189,
      "step": 665
    },
    {
      "epoch": 2.4542124542124544,
      "grad_norm": 3.484375,
      "learning_rate": 1.5931321212008465e-07,
      "loss": 4.7007,
      "step": 670
    },
    {
      "epoch": 2.4725274725274726,
      "grad_norm": 3.53125,
      "learning_rate": 1.490700678009421e-07,
      "loss": 4.6923,
      "step": 675
    },
    {
      "epoch": 2.490842490842491,
      "grad_norm": 3.546875,
      "learning_rate": 1.3914069505972482e-07,
      "loss": 4.7265,
      "step": 680
    },
    {
      "epoch": 2.509157509157509,
      "grad_norm": 3.6875,
      "learning_rate": 1.2952875524954232e-07,
      "loss": 4.7318,
      "step": 685
    },
    {
      "epoch": 2.5274725274725274,
      "grad_norm": 3.546875,
      "learning_rate": 1.2023779267340563e-07,
      "loss": 4.7144,
      "step": 690
    },
    {
      "epoch": 2.5457875457875456,
      "grad_norm": 3.609375,
      "learning_rate": 1.112712332773038e-07,
      "loss": 4.6979,
      "step": 695
    },
    {
      "epoch": 2.564102564102564,
      "grad_norm": 3.5625,
      "learning_rate": 1.026323833869206e-07,
      "loss": 4.6933,
      "step": 700
    },
    {
      "epoch": 2.5824175824175826,
      "grad_norm": 3.59375,
      "learning_rate": 9.432442848846289e-08,
      "loss": 4.731,
      "step": 705
    },
    {
      "epoch": 2.600732600732601,
      "grad_norm": 3.53125,
      "learning_rate": 8.63504320540438e-08,
      "loss": 4.7246,
      "step": 710
    },
    {
      "epoch": 2.619047619047619,
      "grad_norm": 3.53125,
      "learning_rate": 7.871333441206052e-08,
      "loss": 4.7311,
      "step": 715
    },
    {
      "epoch": 2.6373626373626373,
      "grad_norm": 3.53125,
      "learning_rate": 7.141595166297832e-08,
      "loss": 4.7213,
      "step": 720
    },
    {
      "epoch": 2.6556776556776556,
      "grad_norm": 3.484375,
      "learning_rate": 6.446097464092248e-08,
      "loss": 4.6983,
      "step": 725
    },
    {
      "epoch": 2.6739926739926743,
      "grad_norm": 3.546875,
      "learning_rate": 5.78509679214616e-08,
      "loss": 4.6839,
      "step": 730
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 3.5625,
      "learning_rate": 5.1588368875946864e-08,
      "loss": 4.7098,
      "step": 735
    },
    {
      "epoch": 2.7106227106227108,
      "grad_norm": 3.65625,
      "learning_rate": 4.567548677275601e-08,
      "loss": 4.6954,
      "step": 740
    },
    {
      "epoch": 2.728937728937729,
      "grad_norm": 3.578125,
      "learning_rate": 4.0114501925775925e-08,
      "loss": 4.7284,
      "step": 745
    },
    {
      "epoch": 2.7472527472527473,
      "grad_norm": 3.765625,
      "learning_rate": 3.490746489043317e-08,
      "loss": 4.7099,
      "step": 750
    },
    {
      "epoch": 2.7655677655677655,
      "grad_norm": 3.5625,
      "learning_rate": 3.005629570757373e-08,
      "loss": 4.7144,
      "step": 755
    },
    {
      "epoch": 2.7838827838827838,
      "grad_norm": 3.625,
      "learning_rate": 2.5562783195467675e-08,
      "loss": 4.6949,
      "step": 760
    },
    {
      "epoch": 2.802197802197802,
      "grad_norm": 3.515625,
      "learning_rate": 2.1428584290201114e-08,
      "loss": 4.7045,
      "step": 765
    },
    {
      "epoch": 2.8205128205128203,
      "grad_norm": 3.703125,
      "learning_rate": 1.7655223434698053e-08,
      "loss": 4.688,
      "step": 770
    },
    {
      "epoch": 2.838827838827839,
      "grad_norm": 3.578125,
      "learning_rate": 1.4244092016597931e-08,
      "loss": 4.7177,
      "step": 775
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 3.59375,
      "learning_rate": 1.11964478551958e-08,
      "loss": 4.7073,
      "step": 780
    },
    {
      "epoch": 2.8754578754578755,
      "grad_norm": 3.453125,
      "learning_rate": 8.513414737635005e-09,
      "loss": 4.7176,
      "step": 785
    },
    {
      "epoch": 2.8937728937728937,
      "grad_norm": 3.515625,
      "learning_rate": 6.1959820045215385e-09,
      "loss": 4.6779,
      "step": 790
    },
    {
      "epoch": 2.912087912087912,
      "grad_norm": 3.484375,
      "learning_rate": 4.245004185115752e-09,
      "loss": 4.7052,
      "step": 795
    },
    {
      "epoch": 2.9304029304029307,
      "grad_norm": 3.484375,
      "learning_rate": 2.661200682232745e-09,
      "loss": 4.7179,
      "step": 800
    },
    {
      "epoch": 2.948717948717949,
      "grad_norm": 3.640625,
      "learning_rate": 1.4451555069708853e-09,
      "loss": 4.6552,
      "step": 805
    },
    {
      "epoch": 2.967032967032967,
      "grad_norm": 4.21875,
      "learning_rate": 5.973170633631897e-10,
      "loss": 4.6979,
      "step": 810
    },
    {
      "epoch": 2.9853479853479854,
      "grad_norm": 3.578125,
      "learning_rate": 1.1799798303335772e-10,
      "loss": 4.7113,
      "step": 815
    },
    {
      "epoch": 3.0,
      "step": 819,
      "total_flos": 5.361516984661967e+18,
      "train_loss": 5.0057218712328115,
      "train_runtime": 5088.8536,
      "train_samples_per_second": 10.267,
      "train_steps_per_second": 0.161
    }
  ],
  "logging_steps": 5,
  "max_steps": 819,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.361516984661967e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}