{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 100,
  "global_step": 1626,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018450184501845018,
      "grad_norm": 9.194052941983164,
      "learning_rate": 1.226993865030675e-07,
      "loss": 1.1392,
      "step": 1
    },
    {
      "epoch": 0.00922509225092251,
      "grad_norm": 8.728469464225432,
      "learning_rate": 6.134969325153375e-07,
      "loss": 1.1321,
      "step": 5
    },
    {
      "epoch": 0.01845018450184502,
      "grad_norm": 5.066035045474869,
      "learning_rate": 1.226993865030675e-06,
      "loss": 1.0802,
      "step": 10
    },
    {
      "epoch": 0.027675276752767528,
      "grad_norm": 6.151048691792626,
      "learning_rate": 1.8404907975460124e-06,
      "loss": 1.0186,
      "step": 15
    },
    {
      "epoch": 0.03690036900369004,
      "grad_norm": 2.030218046940431,
      "learning_rate": 2.45398773006135e-06,
      "loss": 1.0181,
      "step": 20
    },
    {
      "epoch": 0.046125461254612546,
      "grad_norm": 1.7169054577646434,
      "learning_rate": 3.0674846625766875e-06,
      "loss": 0.9867,
      "step": 25
    },
    {
      "epoch": 0.055350553505535055,
      "grad_norm": 1.414702551784086,
      "learning_rate": 3.680981595092025e-06,
      "loss": 0.9848,
      "step": 30
    },
    {
      "epoch": 0.06457564575645756,
      "grad_norm": 1.471062511929668,
      "learning_rate": 4.294478527607362e-06,
      "loss": 0.975,
      "step": 35
    },
    {
      "epoch": 0.07380073800738007,
      "grad_norm": 1.9876641303020315,
      "learning_rate": 4.9079754601227e-06,
      "loss": 0.9616,
      "step": 40
    },
    {
      "epoch": 0.08302583025830258,
      "grad_norm": 1.7086605102377759,
      "learning_rate": 5.521472392638038e-06,
      "loss": 0.9716,
      "step": 45
    },
    {
      "epoch": 0.09225092250922509,
      "grad_norm": 2.202769359683669,
      "learning_rate": 6.134969325153375e-06,
      "loss": 0.9766,
      "step": 50
    },
    {
      "epoch": 0.1014760147601476,
      "grad_norm": 1.6222357117334487,
      "learning_rate": 6.748466257668712e-06,
      "loss": 0.9929,
      "step": 55
    },
    {
      "epoch": 0.11070110701107011,
      "grad_norm": 2.161648398755977,
      "learning_rate": 7.36196319018405e-06,
      "loss": 0.9774,
      "step": 60
    },
    {
      "epoch": 0.11992619926199262,
      "grad_norm": 1.7198404521131392,
      "learning_rate": 7.975460122699386e-06,
      "loss": 0.9743,
      "step": 65
    },
    {
      "epoch": 0.12915129151291513,
      "grad_norm": 2.5936580446065594,
      "learning_rate": 8.588957055214725e-06,
      "loss": 0.9878,
      "step": 70
    },
    {
      "epoch": 0.13837638376383765,
      "grad_norm": 2.188257188915145,
      "learning_rate": 9.202453987730062e-06,
      "loss": 0.9568,
      "step": 75
    },
    {
      "epoch": 0.14760147601476015,
      "grad_norm": 1.7531151641523148,
      "learning_rate": 9.8159509202454e-06,
      "loss": 0.9789,
      "step": 80
    },
    {
      "epoch": 0.15682656826568267,
      "grad_norm": 1.8091240872427208,
      "learning_rate": 1.0429447852760737e-05,
      "loss": 0.9678,
      "step": 85
    },
    {
      "epoch": 0.16605166051660517,
      "grad_norm": 2.098514635540621,
      "learning_rate": 1.1042944785276076e-05,
      "loss": 0.9617,
      "step": 90
    },
    {
      "epoch": 0.1752767527675277,
      "grad_norm": 2.4275494428488607,
      "learning_rate": 1.1656441717791411e-05,
      "loss": 0.9676,
      "step": 95
    },
    {
      "epoch": 0.18450184501845018,
      "grad_norm": 2.0637923302738095,
      "learning_rate": 1.226993865030675e-05,
      "loss": 0.9681,
      "step": 100
    },
    {
      "epoch": 0.18450184501845018,
      "eval_loss": 0.9788174629211426,
      "eval_runtime": 515.1712,
      "eval_samples_per_second": 29.796,
      "eval_steps_per_second": 0.116,
      "step": 100
    },
    {
      "epoch": 0.1937269372693727,
      "grad_norm": 2.069416549180579,
      "learning_rate": 1.2883435582822085e-05,
      "loss": 0.9528,
      "step": 105
    },
    {
      "epoch": 0.2029520295202952,
      "grad_norm": 2.2916715973700024,
      "learning_rate": 1.3496932515337424e-05,
      "loss": 0.9696,
      "step": 110
    },
    {
      "epoch": 0.21217712177121772,
      "grad_norm": 2.062468142825091,
      "learning_rate": 1.4110429447852763e-05,
      "loss": 0.9747,
      "step": 115
    },
    {
      "epoch": 0.22140221402214022,
      "grad_norm": 1.7271367882138293,
      "learning_rate": 1.47239263803681e-05,
      "loss": 0.9786,
      "step": 120
    },
    {
      "epoch": 0.23062730627306274,
      "grad_norm": 1.9545058702706481,
      "learning_rate": 1.5337423312883436e-05,
      "loss": 0.9758,
      "step": 125
    },
    {
      "epoch": 0.23985239852398524,
      "grad_norm": 1.9400595646067775,
      "learning_rate": 1.5950920245398772e-05,
      "loss": 0.9829,
      "step": 130
    },
    {
      "epoch": 0.24907749077490776,
      "grad_norm": 1.865861850010034,
      "learning_rate": 1.656441717791411e-05,
      "loss": 0.9915,
      "step": 135
    },
    {
      "epoch": 0.25830258302583026,
      "grad_norm": 1.9529698824708406,
      "learning_rate": 1.717791411042945e-05,
      "loss": 0.9831,
      "step": 140
    },
    {
      "epoch": 0.26752767527675275,
      "grad_norm": 1.8749039852563243,
      "learning_rate": 1.7791411042944788e-05,
      "loss": 0.9842,
      "step": 145
    },
    {
      "epoch": 0.2767527675276753,
      "grad_norm": 1.4867806820095497,
      "learning_rate": 1.8404907975460123e-05,
      "loss": 0.9859,
      "step": 150
    },
    {
      "epoch": 0.2859778597785978,
      "grad_norm": 2.1169911338934644,
      "learning_rate": 1.9018404907975462e-05,
      "loss": 0.9771,
      "step": 155
    },
    {
      "epoch": 0.2952029520295203,
      "grad_norm": 1.5398155481235816,
      "learning_rate": 1.96319018404908e-05,
      "loss": 0.9817,
      "step": 160
    },
    {
      "epoch": 0.3044280442804428,
      "grad_norm": 1.7130250807487832,
      "learning_rate": 1.9999907776750355e-05,
      "loss": 0.9997,
      "step": 165
    },
    {
      "epoch": 0.31365313653136534,
      "grad_norm": 2.1366171045520383,
      "learning_rate": 1.9998870284726968e-05,
      "loss": 1.0004,
      "step": 170
    },
    {
      "epoch": 0.32287822878228783,
      "grad_norm": 2.01400597362679,
      "learning_rate": 1.9996680141616956e-05,
      "loss": 0.9937,
      "step": 175
    },
    {
      "epoch": 0.33210332103321033,
      "grad_norm": 1.925569839756876,
      "learning_rate": 1.9993337599895925e-05,
      "loss": 0.9939,
      "step": 180
    },
    {
      "epoch": 0.3413284132841328,
      "grad_norm": 1.4590251035585917,
      "learning_rate": 1.998884304488584e-05,
      "loss": 0.9982,
      "step": 185
    },
    {
      "epoch": 0.3505535055350554,
      "grad_norm": 1.531094729781709,
      "learning_rate": 1.998319699471061e-05,
      "loss": 0.9925,
      "step": 190
    },
    {
      "epoch": 0.35977859778597787,
      "grad_norm": 1.9624667257758441,
      "learning_rate": 1.997640010023634e-05,
      "loss": 0.9765,
      "step": 195
    },
    {
      "epoch": 0.36900369003690037,
      "grad_norm": 1.6943282928766075,
      "learning_rate": 1.9968453144996345e-05,
      "loss": 0.9962,
      "step": 200
    },
    {
      "epoch": 0.36900369003690037,
      "eval_loss": 1.0030262470245361,
      "eval_runtime": 518.1283,
      "eval_samples_per_second": 29.626,
      "eval_steps_per_second": 0.116,
      "step": 200
    },
    {
      "epoch": 0.37822878228782286,
      "grad_norm": 3.0469311990676857,
      "learning_rate": 1.9959357045100764e-05,
      "loss": 0.9947,
      "step": 205
    },
    {
      "epoch": 0.3874538745387454,
      "grad_norm": 2.2551326104892864,
      "learning_rate": 1.9949112849131005e-05,
      "loss": 1.0023,
      "step": 210
    },
    {
      "epoch": 0.3966789667896679,
      "grad_norm": 1.8771683509279502,
      "learning_rate": 1.993772173801884e-05,
      "loss": 0.9934,
      "step": 215
    },
    {
      "epoch": 0.4059040590405904,
      "grad_norm": 1.8016877222967922,
      "learning_rate": 1.992518502491028e-05,
      "loss": 0.9807,
      "step": 220
    },
    {
      "epoch": 0.4151291512915129,
      "grad_norm": 1.4456497466009737,
      "learning_rate": 1.9911504155014187e-05,
      "loss": 0.9926,
      "step": 225
    },
    {
      "epoch": 0.42435424354243545,
      "grad_norm": 1.5156073716841811,
      "learning_rate": 1.989668070543569e-05,
      "loss": 0.9766,
      "step": 230
    },
    {
      "epoch": 0.43357933579335795,
      "grad_norm": 1.3959824735787207,
      "learning_rate": 1.9880716384994355e-05,
      "loss": 0.9964,
      "step": 235
    },
    {
      "epoch": 0.44280442804428044,
      "grad_norm": 1.4724192694561282,
      "learning_rate": 1.9863613034027224e-05,
      "loss": 0.9942,
      "step": 240
    },
    {
      "epoch": 0.45202952029520294,
      "grad_norm": 2.064409139190994,
      "learning_rate": 1.9845372624176646e-05,
      "loss": 1.0103,
      "step": 245
    },
    {
      "epoch": 0.4612546125461255,
      "grad_norm": 2.190902421105104,
      "learning_rate": 1.982599725816299e-05,
      "loss": 1.0075,
      "step": 250
    },
    {
      "epoch": 0.470479704797048,
      "grad_norm": 1.9443583169417478,
      "learning_rate": 1.9805489169542245e-05,
      "loss": 0.9971,
      "step": 255
    },
    {
      "epoch": 0.4797047970479705,
      "grad_norm": 1.553791831408308,
      "learning_rate": 1.978385072244857e-05,
      "loss": 0.9992,
      "step": 260
    },
    {
      "epoch": 0.488929889298893,
      "grad_norm": 1.4174068635451451,
      "learning_rate": 1.9761084411321706e-05,
      "loss": 0.9793,
      "step": 265
    },
    {
      "epoch": 0.4981549815498155,
      "grad_norm": 1.4969414214930414,
      "learning_rate": 1.9737192860619477e-05,
      "loss": 0.9791,
      "step": 270
    },
    {
      "epoch": 0.507380073800738,
      "grad_norm": 1.4025421975340602,
      "learning_rate": 1.971217882451521e-05,
      "loss": 0.9796,
      "step": 275
    },
    {
      "epoch": 0.5166051660516605,
      "grad_norm": 1.4448369862138994,
      "learning_rate": 1.9686045186580258e-05,
      "loss": 0.9884,
      "step": 280
    },
    {
      "epoch": 0.525830258302583,
      "grad_norm": 2.0639483249182464,
      "learning_rate": 1.9658794959451583e-05,
      "loss": 0.9831,
      "step": 285
    },
    {
      "epoch": 0.5350553505535055,
      "grad_norm": 1.6048970102781592,
      "learning_rate": 1.9630431284484447e-05,
      "loss": 0.9849,
      "step": 290
    },
    {
      "epoch": 0.544280442804428,
      "grad_norm": 1.4540480684938577,
      "learning_rate": 1.960095743139033e-05,
      "loss": 0.9796,
      "step": 295
    },
    {
      "epoch": 0.5535055350553506,
      "grad_norm": 1.424947900669971,
      "learning_rate": 1.957037679785994e-05,
      "loss": 0.9917,
      "step": 300
    },
    {
      "epoch": 0.5535055350553506,
      "eval_loss": 1.0008341073989868,
      "eval_runtime": 513.1068,
      "eval_samples_per_second": 29.916,
      "eval_steps_per_second": 0.117,
      "step": 300
    },
    {
      "epoch": 0.5627306273062731,
      "grad_norm": 1.2480517696242786,
      "learning_rate": 1.953869290917158e-05,
      "loss": 0.9943,
      "step": 305
    },
    {
      "epoch": 0.5719557195571956,
      "grad_norm": 1.191133450390735,
      "learning_rate": 1.9505909417784758e-05,
      "loss": 0.9899,
      "step": 310
    },
    {
      "epoch": 0.5811808118081181,
      "grad_norm": 1.1766418475997753,
      "learning_rate": 1.9472030102919102e-05,
      "loss": 0.9883,
      "step": 315
    },
    {
      "epoch": 0.5904059040590406,
      "grad_norm": 1.2121897211885717,
      "learning_rate": 1.9437058870118745e-05,
      "loss": 1.0037,
      "step": 320
    },
    {
      "epoch": 0.5996309963099631,
      "grad_norm": 1.2903187102851559,
      "learning_rate": 1.940099975080207e-05,
      "loss": 0.9892,
      "step": 325
    },
    {
      "epoch": 0.6088560885608856,
      "grad_norm": 1.4260318993897811,
      "learning_rate": 1.9363856901796984e-05,
      "loss": 0.9896,
      "step": 330
    },
    {
      "epoch": 0.6180811808118081,
      "grad_norm": 1.324489901337969,
      "learning_rate": 1.9325634604861728e-05,
      "loss": 0.9978,
      "step": 335
    },
    {
      "epoch": 0.6273062730627307,
      "grad_norm": 1.275426852454915,
      "learning_rate": 1.9286337266191295e-05,
      "loss": 0.993,
      "step": 340
    },
    {
      "epoch": 0.6365313653136532,
      "grad_norm": 1.329213272796139,
      "learning_rate": 1.9245969415909464e-05,
      "loss": 0.9879,
      "step": 345
    },
    {
      "epoch": 0.6457564575645757,
      "grad_norm": 1.4085398606096227,
      "learning_rate": 1.9204535707546602e-05,
      "loss": 0.9869,
      "step": 350
    },
    {
      "epoch": 0.6549815498154982,
      "grad_norm": 1.1848936755869721,
      "learning_rate": 1.916204091750321e-05,
      "loss": 0.9726,
      "step": 355
    },
    {
      "epoch": 0.6642066420664207,
      "grad_norm": 1.2968309154541056,
      "learning_rate": 1.9118489944499287e-05,
      "loss": 0.9902,
      "step": 360
    },
    {
      "epoch": 0.6734317343173432,
      "grad_norm": 1.2286246913756114,
      "learning_rate": 1.907388780900964e-05,
      "loss": 0.9811,
      "step": 365
    },
    {
      "epoch": 0.6826568265682657,
      "grad_norm": 1.2591567733071325,
      "learning_rate": 1.902823965268513e-05,
      "loss": 0.9858,
      "step": 370
    },
    {
      "epoch": 0.6918819188191881,
      "grad_norm": 1.4378514619406175,
      "learning_rate": 1.8981550737759932e-05,
      "loss": 0.9828,
      "step": 375
    },
    {
      "epoch": 0.7011070110701108,
      "grad_norm": 1.497308547977116,
      "learning_rate": 1.8933826446444933e-05,
      "loss": 0.9892,
      "step": 380
    },
    {
      "epoch": 0.7103321033210332,
      "grad_norm": 1.1745393096620436,
      "learning_rate": 1.888507228030729e-05,
      "loss": 0.9859,
      "step": 385
    },
    {
      "epoch": 0.7195571955719557,
      "grad_norm": 1.2233160586824499,
      "learning_rate": 1.8835293859636177e-05,
      "loss": 0.9763,
      "step": 390
    },
    {
      "epoch": 0.7287822878228782,
      "grad_norm": 1.3127902536541989,
      "learning_rate": 1.8784496922794947e-05,
      "loss": 0.981,
      "step": 395
    },
    {
      "epoch": 0.7380073800738007,
      "grad_norm": 1.3089866347753676,
      "learning_rate": 1.873268732555957e-05,
      "loss": 0.9652,
      "step": 400
    },
    {
      "epoch": 0.7380073800738007,
      "eval_loss": 0.993894636631012,
      "eval_runtime": 513.7147,
      "eval_samples_per_second": 29.88,
      "eval_steps_per_second": 0.117,
      "step": 400
    },
    {
      "epoch": 0.7472324723247232,
      "grad_norm": 1.3088189271034285,
      "learning_rate": 1.8679871040443632e-05,
      "loss": 1.0048,
      "step": 405
    },
    {
      "epoch": 0.7564575645756457,
      "grad_norm": 1.2954577066196238,
      "learning_rate": 1.8626054156009807e-05,
      "loss": 0.9927,
      "step": 410
    },
    {
      "epoch": 0.7656826568265682,
      "grad_norm": 1.317981053662398,
      "learning_rate": 1.8571242876167995e-05,
      "loss": 0.9752,
      "step": 415
    },
    {
      "epoch": 0.7749077490774908,
      "grad_norm": 1.4156756831610378,
      "learning_rate": 1.851544351946014e-05,
      "loss": 0.9945,
      "step": 420
    },
    {
      "epoch": 0.7841328413284133,
      "grad_norm": 1.1285773664771428,
      "learning_rate": 1.845866251833183e-05,
      "loss": 0.9708,
      "step": 425
    },
    {
      "epoch": 0.7933579335793358,
      "grad_norm": 1.2640468813011223,
      "learning_rate": 1.8400906418390808e-05,
      "loss": 0.9757,
      "step": 430
    },
    {
      "epoch": 0.8025830258302583,
      "grad_norm": 1.288546177133416,
      "learning_rate": 1.834218187765237e-05,
      "loss": 0.976,
      "step": 435
    },
    {
      "epoch": 0.8118081180811808,
      "grad_norm": 1.3086160465192265,
      "learning_rate": 1.8282495665771864e-05,
      "loss": 0.9761,
      "step": 440
    },
    {
      "epoch": 0.8210332103321033,
      "grad_norm": 1.1919282548241303,
      "learning_rate": 1.8221854663264294e-05,
      "loss": 0.9718,
      "step": 445
    },
    {
      "epoch": 0.8302583025830258,
      "grad_norm": 1.2454331164701038,
      "learning_rate": 1.8160265860711134e-05,
      "loss": 0.9842,
      "step": 450
    },
    {
      "epoch": 0.8394833948339483,
      "grad_norm": 1.183454477783249,
      "learning_rate": 1.8097736357954487e-05,
      "loss": 0.9705,
      "step": 455
    },
    {
      "epoch": 0.8487084870848709,
      "grad_norm": 1.1394535207411802,
      "learning_rate": 1.8034273363278615e-05,
      "loss": 0.9751,
      "step": 460
    },
    {
      "epoch": 0.8579335793357934,
      "grad_norm": 1.1866949984179949,
      "learning_rate": 1.7969884192578977e-05,
      "loss": 0.9749,
      "step": 465
    },
    {
      "epoch": 0.8671586715867159,
      "grad_norm": 1.299660479182102,
      "learning_rate": 1.7904576268518886e-05,
      "loss": 0.9598,
      "step": 470
    },
    {
      "epoch": 0.8763837638376384,
      "grad_norm": 1.2221383874437446,
      "learning_rate": 1.783835711967382e-05,
      "loss": 0.9842,
      "step": 475
    },
    {
      "epoch": 0.8856088560885609,
      "grad_norm": 1.2535423952991984,
      "learning_rate": 1.7771234379663545e-05,
      "loss": 0.9641,
      "step": 480
    },
    {
      "epoch": 0.8948339483394834,
      "grad_norm": 1.4654400132426395,
      "learning_rate": 1.770321578627213e-05,
      "loss": 0.9784,
      "step": 485
    },
    {
      "epoch": 0.9040590405904059,
      "grad_norm": 1.3747052246285973,
      "learning_rate": 1.763430918055595e-05,
      "loss": 0.9694,
      "step": 490
    },
    {
      "epoch": 0.9132841328413284,
      "grad_norm": 1.1551950486505687,
      "learning_rate": 1.756452250593979e-05,
      "loss": 0.9727,
      "step": 495
    },
    {
      "epoch": 0.922509225092251,
      "grad_norm": 1.128236535385729,
      "learning_rate": 1.7493863807301116e-05,
      "loss": 0.9666,
      "step": 500
    },
    {
      "epoch": 0.922509225092251,
      "eval_loss": 0.9816026091575623,
      "eval_runtime": 517.2137,
      "eval_samples_per_second": 29.678,
      "eval_steps_per_second": 0.116,
      "step": 500
    },
    {
      "epoch": 0.9317343173431735,
      "grad_norm": 1.230218009681161,
      "learning_rate": 1.74223412300427e-05,
      "loss": 0.9769,
      "step": 505
    },
    {
      "epoch": 0.940959409594096,
      "grad_norm": 1.1847589898088133,
      "learning_rate": 1.7349963019153638e-05,
      "loss": 0.9628,
      "step": 510
    },
    {
      "epoch": 0.9501845018450185,
      "grad_norm": 1.2246308831747907,
      "learning_rate": 1.7276737518258865e-05,
      "loss": 0.9602,
      "step": 515
    },
    {
      "epoch": 0.959409594095941,
      "grad_norm": 1.1390750572317663,
      "learning_rate": 1.7202673168657318e-05,
      "loss": 0.9627,
      "step": 520
    },
    {
      "epoch": 0.9686346863468634,
      "grad_norm": 1.1728205351456946,
      "learning_rate": 1.7127778508348858e-05,
      "loss": 0.9714,
      "step": 525
    },
    {
      "epoch": 0.977859778597786,
      "grad_norm": 1.2796699310011739,
      "learning_rate": 1.7052062171050008e-05,
      "loss": 0.967,
      "step": 530
    },
    {
      "epoch": 0.9870848708487084,
      "grad_norm": 1.1205342517216532,
      "learning_rate": 1.6975532885198678e-05,
      "loss": 0.9663,
      "step": 535
    },
    {
      "epoch": 0.996309963099631,
      "grad_norm": 1.185279277131673,
      "learning_rate": 1.6898199472947972e-05,
      "loss": 0.9581,
      "step": 540
    },
    {
      "epoch": 1.0055350553505535,
      "grad_norm": 3.007398366081561,
      "learning_rate": 1.6820070849149174e-05,
      "loss": 0.8519,
      "step": 545
    },
    {
      "epoch": 1.014760147601476,
      "grad_norm": 2.1038299784593337,
      "learning_rate": 1.6741156020324086e-05,
      "loss": 0.7509,
      "step": 550
    },
    {
      "epoch": 1.0239852398523985,
      "grad_norm": 1.5701183943228265,
      "learning_rate": 1.6661464083626734e-05,
      "loss": 0.7453,
      "step": 555
    },
    {
      "epoch": 1.033210332103321,
      "grad_norm": 1.2911074026361753,
      "learning_rate": 1.6581004225794715e-05,
      "loss": 0.7391,
      "step": 560
    },
    {
      "epoch": 1.0424354243542435,
      "grad_norm": 1.5938907876285198,
      "learning_rate": 1.649978572209012e-05,
      "loss": 0.7347,
      "step": 565
    },
    {
      "epoch": 1.051660516605166,
      "grad_norm": 1.3495506131008623,
      "learning_rate": 1.6417817935230318e-05,
      "loss": 0.7396,
      "step": 570
    },
    {
      "epoch": 1.0608856088560885,
      "grad_norm": 1.2781771587882627,
      "learning_rate": 1.6335110314308654e-05,
      "loss": 0.7305,
      "step": 575
    },
    {
      "epoch": 1.070110701107011,
      "grad_norm": 1.5798733908227265,
      "learning_rate": 1.6251672393705155e-05,
      "loss": 0.7365,
      "step": 580
    },
    {
      "epoch": 1.0793357933579335,
      "grad_norm": 1.416304183876239,
      "learning_rate": 1.6167513791987423e-05,
      "loss": 0.7373,
      "step": 585
    },
    {
      "epoch": 1.088560885608856,
      "grad_norm": 1.3677150489575043,
      "learning_rate": 1.6082644210801846e-05,
      "loss": 0.7299,
      "step": 590
    },
    {
      "epoch": 1.0977859778597785,
      "grad_norm": 1.3506677105351055,
      "learning_rate": 1.5997073433755187e-05,
      "loss": 0.7426,
      "step": 595
    },
    {
      "epoch": 1.1070110701107012,
      "grad_norm": 1.461155474048458,
      "learning_rate": 1.5910811325286768e-05,
      "loss": 0.7366,
      "step": 600
    },
    {
      "epoch": 1.1070110701107012,
      "eval_loss": 0.9852360486984253,
      "eval_runtime": 516.2338,
      "eval_samples_per_second": 29.735,
      "eval_steps_per_second": 0.116,
      "step": 600
    },
    {
      "epoch": 1.1162361623616237,
      "grad_norm": 1.2999195127889172,
      "learning_rate": 1.582386782953129e-05,
      "loss": 0.7351,
      "step": 605
    },
    {
      "epoch": 1.1254612546125462,
      "grad_norm": 1.5599221554130673,
      "learning_rate": 1.5736252969172522e-05,
      "loss": 0.7335,
      "step": 610
    },
    {
      "epoch": 1.1346863468634687,
      "grad_norm": 1.30824219510555,
      "learning_rate": 1.5647976844287884e-05,
      "loss": 0.7321,
      "step": 615
    },
    {
      "epoch": 1.1439114391143912,
      "grad_norm": 1.3590431139669035,
      "learning_rate": 1.5559049631184136e-05,
      "loss": 0.7294,
      "step": 620
    },
    {
      "epoch": 1.1531365313653137,
      "grad_norm": 1.5685872513743657,
      "learning_rate": 1.5469481581224274e-05,
      "loss": 0.7372,
      "step": 625
    },
    {
      "epoch": 1.1623616236162362,
      "grad_norm": 1.4194329169102744,
      "learning_rate": 1.5379283019645757e-05,
      "loss": 0.7423,
      "step": 630
    },
    {
      "epoch": 1.1715867158671587,
      "grad_norm": 1.8516238628155155,
      "learning_rate": 1.5288464344370267e-05,
      "loss": 0.7389,
      "step": 635
    },
    {
      "epoch": 1.1808118081180812,
      "grad_norm": 1.3787465939384576,
      "learning_rate": 1.5197036024805018e-05,
      "loss": 0.7277,
      "step": 640
    },
    {
      "epoch": 1.1900369003690037,
      "grad_norm": 1.2679935699299498,
      "learning_rate": 1.5105008600635888e-05,
      "loss": 0.7251,
      "step": 645
    },
    {
      "epoch": 1.1992619926199262,
      "grad_norm": 1.3661565990701046,
      "learning_rate": 1.5012392680612408e-05,
      "loss": 0.7348,
      "step": 650
    },
    {
      "epoch": 1.2084870848708487,
      "grad_norm": 1.380476117633752,
      "learning_rate": 1.4919198941324813e-05,
      "loss": 0.733,
      "step": 655
    },
    {
      "epoch": 1.2177121771217712,
      "grad_norm": 1.301175007422796,
      "learning_rate": 1.4825438125973263e-05,
      "loss": 0.7331,
      "step": 660
    },
    {
      "epoch": 1.2269372693726937,
      "grad_norm": 1.3531205842843421,
      "learning_rate": 1.4731121043129392e-05,
      "loss": 0.7379,
      "step": 665
    },
    {
      "epoch": 1.2361623616236161,
      "grad_norm": 1.444864127952419,
      "learning_rate": 1.4636258565490304e-05,
      "loss": 0.739,
      "step": 670
    },
    {
      "epoch": 1.2453874538745389,
      "grad_norm": 1.2863648775710423,
      "learning_rate": 1.4540861628625207e-05,
      "loss": 0.7368,
      "step": 675
    },
    {
      "epoch": 1.2546125461254611,
      "grad_norm": 1.2200332099647682,
      "learning_rate": 1.444494122971476e-05,
      "loss": 0.7343,
      "step": 680
    },
    {
      "epoch": 1.2638376383763839,
      "grad_norm": 1.3714375121406106,
      "learning_rate": 1.4348508426283342e-05,
      "loss": 0.7391,
      "step": 685
    },
    {
      "epoch": 1.2730627306273063,
      "grad_norm": 1.2638691361743832,
      "learning_rate": 1.4251574334924395e-05,
      "loss": 0.7397,
      "step": 690
    },
    {
      "epoch": 1.2822878228782288,
      "grad_norm": 1.4011111864399106,
      "learning_rate": 1.4154150130018867e-05,
      "loss": 0.7374,
      "step": 695
    },
    {
      "epoch": 1.2915129151291513,
      "grad_norm": 1.2912923761278596,
      "learning_rate": 1.4056247042447096e-05,
      "loss": 0.7228,
      "step": 700
    },
    {
      "epoch": 1.2915129151291513,
      "eval_loss": 0.9835454225540161,
      "eval_runtime": 517.9285,
      "eval_samples_per_second": 29.637,
      "eval_steps_per_second": 0.116,
      "step": 700
    },
    {
      "epoch": 1.3007380073800738,
      "grad_norm": 1.5854901671726367,
      "learning_rate": 1.3957876358294115e-05,
      "loss": 0.7296,
      "step": 705
    },
    {
      "epoch": 1.3099630996309963,
      "grad_norm": 1.38846996136312,
      "learning_rate": 1.385904941754862e-05,
      "loss": 0.7257,
      "step": 710
    },
    {
      "epoch": 1.3191881918819188,
      "grad_norm": 1.5297133474564781,
      "learning_rate": 1.375977761279571e-05,
      "loss": 0.7352,
      "step": 715
    },
    {
      "epoch": 1.3284132841328413,
      "grad_norm": 1.287259224142701,
      "learning_rate": 1.366007238790358e-05,
      "loss": 0.7301,
      "step": 720
    },
    {
      "epoch": 1.3376383763837638,
      "grad_norm": 1.2884194224179173,
      "learning_rate": 1.3559945236704286e-05,
      "loss": 0.7383,
      "step": 725
    },
    {
      "epoch": 1.3468634686346863,
      "grad_norm": 1.3779553004575515,
      "learning_rate": 1.3459407701668762e-05,
      "loss": 0.7313,
      "step": 730
    },
    {
      "epoch": 1.3560885608856088,
      "grad_norm": 1.5349656095564503,
      "learning_rate": 1.3358471372576229e-05,
      "loss": 0.7334,
      "step": 735
    },
    {
      "epoch": 1.3653136531365313,
      "grad_norm": 1.3570612666553503,
      "learning_rate": 1.3257147885178125e-05,
      "loss": 0.7253,
      "step": 740
    },
    {
      "epoch": 1.3745387453874538,
      "grad_norm": 1.3514442377769267,
      "learning_rate": 1.3155448919856792e-05,
      "loss": 0.7375,
      "step": 745
    },
    {
      "epoch": 1.3837638376383765,
      "grad_norm": 1.338752928401098,
      "learning_rate": 1.3053386200278963e-05,
      "loss": 0.7349,
      "step": 750
    },
    {
      "epoch": 1.3929889298892988,
      "grad_norm": 1.3943704063449442,
      "learning_rate": 1.2950971492044272e-05,
      "loss": 0.7338,
      "step": 755
    },
    {
      "epoch": 1.4022140221402215,
      "grad_norm": 1.3567491078204894,
      "learning_rate": 1.2848216601328958e-05,
      "loss": 0.7385,
      "step": 760
    },
    {
      "epoch": 1.4114391143911438,
      "grad_norm": 1.2556919848553412,
      "learning_rate": 1.2745133373524855e-05,
      "loss": 0.7457,
      "step": 765
    },
    {
      "epoch": 1.4206642066420665,
      "grad_norm": 1.3027608934231716,
      "learning_rate": 1.2641733691873884e-05,
      "loss": 0.7342,
      "step": 770
    },
    {
      "epoch": 1.429889298892989,
      "grad_norm": 1.2668132369825373,
      "learning_rate": 1.2538029476098175e-05,
      "loss": 0.7317,
      "step": 775
    },
    {
      "epoch": 1.4391143911439115,
      "grad_norm": 1.2498842281077402,
      "learning_rate": 1.2434032681025986e-05,
      "loss": 0.732,
      "step": 780
    },
    {
      "epoch": 1.448339483394834,
      "grad_norm": 1.221148464370588,
      "learning_rate": 1.2329755295213568e-05,
      "loss": 0.7168,
      "step": 785
    },
    {
      "epoch": 1.4575645756457565,
      "grad_norm": 1.2029873246463332,
      "learning_rate": 1.2225209339563144e-05,
      "loss": 0.7299,
      "step": 790
    },
    {
      "epoch": 1.466789667896679,
      "grad_norm": 1.2769506053242343,
      "learning_rate": 1.2120406865937174e-05,
      "loss": 0.7385,
      "step": 795
    },
    {
      "epoch": 1.4760147601476015,
      "grad_norm": 1.5254063393209267,
      "learning_rate": 1.2015359955769021e-05,
      "loss": 0.7319,
      "step": 800
    },
    {
      "epoch": 1.4760147601476015,
      "eval_loss": 0.9644125699996948,
      "eval_runtime": 512.8317,
      "eval_samples_per_second": 29.932,
      "eval_steps_per_second": 0.117,
      "step": 800
    },
    {
      "epoch": 1.485239852398524,
      "grad_norm": 1.4657220418578245,
      "learning_rate": 1.1910080718670246e-05,
      "loss": 0.7234,
      "step": 805
    },
    {
      "epoch": 1.4944649446494465,
      "grad_norm": 1.3333083489866098,
      "learning_rate": 1.1804581291034615e-05,
      "loss": 0.7314,
      "step": 810
    },
    {
      "epoch": 1.503690036900369,
      "grad_norm": 1.3111534531304956,
      "learning_rate": 1.169887383463906e-05,
      "loss": 0.7212,
      "step": 815
    },
    {
      "epoch": 1.5129151291512914,
      "grad_norm": 1.2536260067392955,
      "learning_rate": 1.1592970535241668e-05,
      "loss": 0.723,
      "step": 820
    },
    {
      "epoch": 1.5221402214022142,
      "grad_norm": 1.239943596383526,
      "learning_rate": 1.1486883601176944e-05,
      "loss": 0.7315,
      "step": 825
    },
    {
      "epoch": 1.5313653136531364,
      "grad_norm": 1.188861248391431,
      "learning_rate": 1.1380625261948458e-05,
      "loss": 0.7301,
      "step": 830
    },
    {
      "epoch": 1.5405904059040592,
      "grad_norm": 1.247650108627454,
      "learning_rate": 1.127420776681905e-05,
      "loss": 0.7202,
      "step": 835
    },
    {
      "epoch": 1.5498154981549814,
      "grad_norm": 1.4048683840262912,
      "learning_rate": 1.1167643383398746e-05,
      "loss": 0.7247,
      "step": 840
    },
    {
      "epoch": 1.5590405904059041,
      "grad_norm": 1.2897015340446114,
      "learning_rate": 1.1060944396230583e-05,
      "loss": 0.7311,
      "step": 845
    },
    {
      "epoch": 1.5682656826568264,
      "grad_norm": 1.21939417183643,
      "learning_rate": 1.0954123105374468e-05,
      "loss": 0.7249,
      "step": 850
    },
    {
      "epoch": 1.5774907749077491,
      "grad_norm": 1.2309319468475195,
      "learning_rate": 1.0847191824989252e-05,
      "loss": 0.7298,
      "step": 855
    },
    {
      "epoch": 1.5867158671586716,
      "grad_norm": 1.2218109998078897,
      "learning_rate": 1.0740162881913165e-05,
      "loss": 0.7223,
      "step": 860
    },
    {
      "epoch": 1.5959409594095941,
      "grad_norm": 1.4183791452745522,
      "learning_rate": 1.0633048614242817e-05,
      "loss": 0.7359,
      "step": 865
    },
    {
      "epoch": 1.6051660516605166,
      "grad_norm": 1.2210289040303786,
      "learning_rate": 1.0525861369910877e-05,
      "loss": 0.7302,
      "step": 870
    },
    {
      "epoch": 1.6143911439114391,
      "grad_norm": 1.3175608261808258,
      "learning_rate": 1.0418613505262623e-05,
      "loss": 0.7226,
      "step": 875
    },
    {
      "epoch": 1.6236162361623616,
      "grad_norm": 1.3018239201611663,
      "learning_rate": 1.0311317383631532e-05,
      "loss": 0.7227,
      "step": 880
    },
    {
      "epoch": 1.632841328413284,
      "grad_norm": 1.1647552351758403,
      "learning_rate": 1.0203985373914056e-05,
      "loss": 0.7204,
      "step": 885
    },
    {
      "epoch": 1.6420664206642066,
      "grad_norm": 1.210717925144679,
      "learning_rate": 1.0096629849143757e-05,
      "loss": 0.7115,
      "step": 890
    },
    {
      "epoch": 1.651291512915129,
      "grad_norm": 1.1959081633999162,
      "learning_rate": 9.989263185064974e-06,
      "loss": 0.7164,
      "step": 895
    },
    {
      "epoch": 1.6605166051660518,
      "grad_norm": 1.1679984043624778,
      "learning_rate": 9.881897758706155e-06,
      "loss": 0.7177,
      "step": 900
    },
    {
      "epoch": 1.6605166051660518,
      "eval_loss": 0.9529369473457336,
      "eval_runtime": 516.4151,
      "eval_samples_per_second": 29.724,
      "eval_steps_per_second": 0.116,
      "step": 900
    },
    {
      "epoch": 1.669741697416974,
      "grad_norm": 1.1784785526719634,
      "learning_rate": 9.77454594695308e-06,
      "loss": 0.7274,
      "step": 905
    },
    {
      "epoch": 1.6789667896678968,
      "grad_norm": 1.1964871209199903,
      "learning_rate": 9.667220125122044e-06,
      "loss": 0.7119,
      "step": 910
    },
    {
      "epoch": 1.688191881918819,
      "grad_norm": 1.173031357661576,
      "learning_rate": 9.559932665533291e-06,
      "loss": 0.7134,
      "step": 915
    },
    {
      "epoch": 1.6974169741697418,
      "grad_norm": 1.2312863536042935,
      "learning_rate": 9.452695936084728e-06,
      "loss": 0.7144,
      "step": 920
    },
    {
      "epoch": 1.706642066420664,
      "grad_norm": 1.2013984113686338,
      "learning_rate": 9.345522298826177e-06,
      "loss": 0.7146,
      "step": 925
    },
    {
      "epoch": 1.7158671586715868,
      "grad_norm": 1.1285995450468198,
      "learning_rate": 9.238424108534333e-06,
      "loss": 0.7126,
      "step": 930
    },
    {
      "epoch": 1.725092250922509,
      "grad_norm": 1.1727971825533714,
      "learning_rate": 9.131413711288485e-06,
      "loss": 0.7173,
      "step": 935
    },
    {
      "epoch": 1.7343173431734318,
      "grad_norm": 1.198238879588798,
      "learning_rate": 9.024503443047318e-06,
      "loss": 0.7186,
      "step": 940
    },
    {
      "epoch": 1.7435424354243543,
      "grad_norm": 1.2092538734459182,
      "learning_rate": 8.917705628226823e-06,
      "loss": 0.7064,
      "step": 945
    },
    {
      "epoch": 1.7527675276752768,
      "grad_norm": 1.1850959753551464,
      "learning_rate": 8.81103257827957e-06,
      "loss": 0.7196,
      "step": 950
    },
    {
      "epoch": 1.7619926199261993,
      "grad_norm": 1.1849846233150378,
      "learning_rate": 8.704496590275479e-06,
      "loss": 0.7181,
      "step": 955
    },
    {
      "epoch": 1.7712177121771218,
      "grad_norm": 1.1192440025321218,
      "learning_rate": 8.598109945484208e-06,
      "loss": 0.7127,
      "step": 960
    },
    {
      "epoch": 1.7804428044280443,
      "grad_norm": 1.185810311236685,
      "learning_rate": 8.491884907959426e-06,
      "loss": 0.7092,
      "step": 965
    },
    {
      "epoch": 1.7896678966789668,
      "grad_norm": 1.1653670987242044,
      "learning_rate": 8.385833723125006e-06,
      "loss": 0.7115,
      "step": 970
    },
    {
      "epoch": 1.7988929889298892,
      "grad_norm": 1.2928934171032893,
      "learning_rate": 8.279968616363417e-06,
      "loss": 0.7116,
      "step": 975
    },
    {
      "epoch": 1.8081180811808117,
      "grad_norm": 1.1749460908752425,
      "learning_rate": 8.174301791606384e-06,
      "loss": 0.7159,
      "step": 980
    },
    {
      "epoch": 1.8173431734317345,
      "grad_norm": 1.2968530721458553,
      "learning_rate": 8.06884542992806e-06,
      "loss": 0.7022,
      "step": 985
    },
    {
      "epoch": 1.8265682656826567,
      "grad_norm": 1.214409149915767,
      "learning_rate": 7.963611688140814e-06,
      "loss": 0.705,
      "step": 990
    },
    {
      "epoch": 1.8357933579335795,
      "grad_norm": 1.1751136227927774,
      "learning_rate": 7.858612697393792e-06,
      "loss": 0.7166,
      "step": 995
    },
    {
      "epoch": 1.8450184501845017,
      "grad_norm": 1.2707314516132002,
      "learning_rate": 7.753860561774495e-06,
      "loss": 0.7095,
      "step": 1000
    },
    {
      "epoch": 1.8450184501845017,
      "eval_loss": 0.9393758773803711,
      "eval_runtime": 524.5955,
      "eval_samples_per_second": 29.261,
      "eval_steps_per_second": 0.114,
      "step": 1000
    },
    {
      "epoch": 1.8542435424354244,
      "grad_norm": 1.2737022554438457,
      "learning_rate": 7.649367356913422e-06,
      "loss": 0.7133,
      "step": 1005
    },
    {
      "epoch": 1.8634686346863467,
      "grad_norm": 1.2146494230865963,
      "learning_rate": 7.545145128592009e-06,
      "loss": 0.7162,
      "step": 1010
    },
    {
      "epoch": 1.8726937269372694,
      "grad_norm": 1.2563305762066708,
      "learning_rate": 7.441205891354037e-06,
      "loss": 0.7128,
      "step": 1015
    },
    {
      "epoch": 1.881918819188192,
      "grad_norm": 1.2400110075293442,
      "learning_rate": 7.337561627120591e-06,
      "loss": 0.7059,
      "step": 1020
    },
    {
      "epoch": 1.8911439114391144,
      "grad_norm": 1.2653437150866325,
      "learning_rate": 7.234224283808832e-06,
      "loss": 0.7058,
      "step": 1025
    },
    {
      "epoch": 1.900369003690037,
      "grad_norm": 1.1646651085367645,
      "learning_rate": 7.131205773954636e-06,
      "loss": 0.706,
      "step": 1030
    },
    {
      "epoch": 1.9095940959409594,
      "grad_norm": 1.1518551233990397,
      "learning_rate": 7.028517973339361e-06,
      "loss": 0.7138,
      "step": 1035
    },
    {
      "epoch": 1.918819188191882,
      "grad_norm": 1.223360815231687,
      "learning_rate": 6.926172719620827e-06,
      "loss": 0.697,
      "step": 1040
    },
    {
      "epoch": 1.9280442804428044,
      "grad_norm": 1.2198079984824493,
      "learning_rate": 6.824181810968675e-06,
      "loss": 0.7004,
      "step": 1045
    },
    {
      "epoch": 1.937269372693727,
      "grad_norm": 1.176959664107674,
      "learning_rate": 6.722557004704322e-06,
      "loss": 0.7082,
      "step": 1050
    },
    {
      "epoch": 1.9464944649446494,
      "grad_norm": 1.1844320699248965,
      "learning_rate": 6.62131001594558e-06,
      "loss": 0.7043,
      "step": 1055
    },
    {
      "epoch": 1.9557195571955721,
      "grad_norm": 1.148753422424237,
      "learning_rate": 6.520452516256157e-06,
      "loss": 0.6949,
      "step": 1060
    },
    {
      "epoch": 1.9649446494464944,
      "grad_norm": 1.1572577267352544,
      "learning_rate": 6.419996132300203e-06,
      "loss": 0.7071,
      "step": 1065
    },
    {
      "epoch": 1.974169741697417,
      "grad_norm": 1.2001014830908205,
      "learning_rate": 6.319952444501984e-06,
      "loss": 0.7103,
      "step": 1070
    },
    {
      "epoch": 1.9833948339483394,
      "grad_norm": 1.4841715888010063,
      "learning_rate": 6.220332985710936e-06,
      "loss": 0.694,
      "step": 1075
    },
    {
      "epoch": 1.992619926199262,
      "grad_norm": 1.4256755997357629,
      "learning_rate": 6.121149239872151e-06,
      "loss": 0.6964,
      "step": 1080
    },
    {
      "epoch": 2.0018450184501844,
      "grad_norm": 4.270149025567802,
      "learning_rate": 6.0224126407025616e-06,
      "loss": 0.6543,
      "step": 1085
    },
    {
      "epoch": 2.011070110701107,
      "grad_norm": 2.6490744221351044,
      "learning_rate": 5.924134570372863e-06,
      "loss": 0.4529,
      "step": 1090
    },
    {
      "epoch": 2.0202952029520294,
      "grad_norm": 2.2645999605838227,
      "learning_rate": 5.826326358195391e-06,
      "loss": 0.4559,
      "step": 1095
    },
    {
      "epoch": 2.029520295202952,
      "grad_norm": 1.5705400512864462,
      "learning_rate": 5.728999279318131e-06,
      "loss": 0.4465,
      "step": 1100
    },
    {
      "epoch": 2.029520295202952,
      "eval_loss": 0.9917108416557312,
      "eval_runtime": 517.7798,
      "eval_samples_per_second": 29.646,
      "eval_steps_per_second": 0.116,
      "step": 1100
    },
    {
      "epoch": 2.0387453874538743,
      "grad_norm": 1.6254518927847355,
      "learning_rate": 5.632164553424904e-06,
      "loss": 0.4353,
      "step": 1105
    },
    {
      "epoch": 2.047970479704797,
      "grad_norm": 14.583137561537578,
      "learning_rate": 5.5358333434420054e-06,
      "loss": 0.4424,
      "step": 1110
    },
    {
      "epoch": 2.0571955719557193,
      "grad_norm": 1.447005279720627,
      "learning_rate": 5.440016754251364e-06,
      "loss": 0.4423,
      "step": 1115
    },
    {
      "epoch": 2.066420664206642,
      "grad_norm": 1.4595204240426687,
      "learning_rate": 5.344725831410369e-06,
      "loss": 0.4384,
      "step": 1120
    },
    {
      "epoch": 2.0756457564575648,
      "grad_norm": 1.3190598016289843,
      "learning_rate": 5.24997155987859e-06,
      "loss": 0.4368,
      "step": 1125
    },
    {
      "epoch": 2.084870848708487,
      "grad_norm": 1.322338946677976,
      "learning_rate": 5.155764862751427e-06,
      "loss": 0.4392,
      "step": 1130
    },
    {
      "epoch": 2.0940959409594098,
      "grad_norm": 1.3472757392525208,
      "learning_rate": 5.062116600000933e-06,
      "loss": 0.4297,
      "step": 1135
    },
    {
      "epoch": 2.103321033210332,
      "grad_norm": 1.2895577097092337,
      "learning_rate": 4.969037567223881e-06,
      "loss": 0.4413,
      "step": 1140
    },
    {
      "epoch": 2.1125461254612548,
      "grad_norm": 1.3471090116973288,
      "learning_rate": 4.876538494397274e-06,
      "loss": 0.4317,
      "step": 1145
    },
    {
      "epoch": 2.121771217712177,
      "grad_norm": 1.3092628602239211,
      "learning_rate": 4.784630044641435e-06,
      "loss": 0.4509,
      "step": 1150
    },
    {
      "epoch": 2.1309963099630997,
      "grad_norm": 1.344809966917295,
      "learning_rate": 4.6933228129907395e-06,
      "loss": 0.4375,
      "step": 1155
    },
    {
      "epoch": 2.140221402214022,
      "grad_norm": 1.3014430618254322,
      "learning_rate": 4.602627325172279e-06,
      "loss": 0.4424,
      "step": 1160
    },
    {
      "epoch": 2.1494464944649447,
      "grad_norm": 1.3672933559982345,
      "learning_rate": 4.512554036392448e-06,
      "loss": 0.4419,
      "step": 1165
    },
    {
      "epoch": 2.158671586715867,
      "grad_norm": 1.3446667993737584,
      "learning_rate": 4.423113330131708e-06,
      "loss": 0.4303,
      "step": 1170
    },
    {
      "epoch": 2.1678966789667897,
      "grad_norm": 1.3257443131859206,
      "learning_rate": 4.33431551694758e-06,
      "loss": 0.4369,
      "step": 1175
    },
    {
      "epoch": 2.177121771217712,
      "grad_norm": 1.3655737456565726,
      "learning_rate": 4.246170833286075e-06,
      "loss": 0.4293,
      "step": 1180
    },
    {
      "epoch": 2.1863468634686347,
      "grad_norm": 1.3298593125645854,
      "learning_rate": 4.1586894403016576e-06,
      "loss": 0.439,
      "step": 1185
    },
    {
      "epoch": 2.195571955719557,
      "grad_norm": 1.32505780264794,
      "learning_rate": 4.071881422685877e-06,
      "loss": 0.4285,
      "step": 1190
    },
    {
      "epoch": 2.2047970479704797,
      "grad_norm": 1.3004312804341762,
      "learning_rate": 3.985756787504837e-06,
      "loss": 0.4353,
      "step": 1195
    },
    {
      "epoch": 2.2140221402214024,
      "grad_norm": 1.3177561620055287,
      "learning_rate": 3.9003254630455775e-06,
      "loss": 0.4341,
      "step": 1200
    },
    {
      "epoch": 2.2140221402214024,
      "eval_loss": 0.9978848695755005,
      "eval_runtime": 514.7843,
      "eval_samples_per_second": 29.818,
      "eval_steps_per_second": 0.117,
      "step": 1200
    },
    {
      "epoch": 2.2232472324723247,
      "grad_norm": 1.3438896554856818,
      "learning_rate": 3.815597297671578e-06,
      "loss": 0.4336,
      "step": 1205
    },
    {
      "epoch": 2.2324723247232474,
      "grad_norm": 1.2896295540334282,
      "learning_rate": 3.731582058687462e-06,
      "loss": 0.435,
      "step": 1210
    },
    {
      "epoch": 2.2416974169741697,
      "grad_norm": 1.358035688644123,
      "learning_rate": 3.6482894312130146e-06,
      "loss": 0.4324,
      "step": 1215
    },
    {
      "epoch": 2.2509225092250924,
      "grad_norm": 1.312197292051631,
      "learning_rate": 3.565729017066729e-06,
      "loss": 0.4315,
      "step": 1220
    },
    {
      "epoch": 2.2601476014760147,
      "grad_norm": 1.3227121347141655,
      "learning_rate": 3.483910333658913e-06,
      "loss": 0.4364,
      "step": 1225
    },
    {
      "epoch": 2.2693726937269374,
      "grad_norm": 1.3256090212374516,
      "learning_rate": 3.402842812894529e-06,
      "loss": 0.4356,
      "step": 1230
    },
    {
      "epoch": 2.2785977859778597,
      "grad_norm": 1.317549750635349,
      "learning_rate": 3.3225358000859287e-06,
      "loss": 0.4349,
      "step": 1235
    },
    {
      "epoch": 2.2878228782287824,
      "grad_norm": 1.2612830347481554,
      "learning_rate": 3.2429985528755127e-06,
      "loss": 0.4306,
      "step": 1240
    },
    {
      "epoch": 2.2970479704797047,
      "grad_norm": 1.3450073317730427,
      "learning_rate": 3.1642402401685557e-06,
      "loss": 0.4361,
      "step": 1245
    },
    {
      "epoch": 2.3062730627306274,
      "grad_norm": 1.3431835139445107,
      "learning_rate": 3.0862699410762043e-06,
      "loss": 0.4393,
      "step": 1250
    },
    {
      "epoch": 2.3154981549815496,
      "grad_norm": 1.3379126436430948,
      "learning_rate": 3.0090966438688774e-06,
      "loss": 0.4306,
      "step": 1255
    },
    {
      "epoch": 2.3247232472324724,
      "grad_norm": 1.2809064467748859,
      "learning_rate": 2.9327292449401067e-06,
      "loss": 0.4416,
      "step": 1260
    },
    {
      "epoch": 2.3339483394833946,
      "grad_norm": 1.3548015164880183,
      "learning_rate": 2.8571765477809645e-06,
      "loss": 0.4338,
      "step": 1265
    },
    {
      "epoch": 2.3431734317343174,
      "grad_norm": 1.320665427008479,
      "learning_rate": 2.7824472619652386e-06,
      "loss": 0.4361,
      "step": 1270
    },
    {
      "epoch": 2.35239852398524,
      "grad_norm": 1.3096646770487193,
      "learning_rate": 2.7085500021453838e-06,
      "loss": 0.4294,
      "step": 1275
    },
    {
      "epoch": 2.3616236162361623,
      "grad_norm": 1.2800372167523524,
      "learning_rate": 2.635493287059464e-06,
      "loss": 0.4299,
      "step": 1280
    },
    {
      "epoch": 2.3708487084870846,
      "grad_norm": 1.303993086907089,
      "learning_rate": 2.563285538549104e-06,
      "loss": 0.4361,
      "step": 1285
    },
    {
      "epoch": 2.3800738007380073,
      "grad_norm": 1.2720280407092956,
      "learning_rate": 2.491935080588658e-06,
      "loss": 0.4384,
      "step": 1290
    },
    {
      "epoch": 2.38929889298893,
      "grad_norm": 1.2941980810201439,
      "learning_rate": 2.421450138325625e-06,
      "loss": 0.4306,
      "step": 1295
    },
    {
      "epoch": 2.3985239852398523,
      "grad_norm": 1.2949495993502738,
      "learning_rate": 2.351838837132464e-06,
      "loss": 0.432,
      "step": 1300
    },
    {
      "epoch": 2.3985239852398523,
      "eval_loss": 0.9954376816749573,
      "eval_runtime": 519.9495,
      "eval_samples_per_second": 29.522,
      "eval_steps_per_second": 0.115,
      "step": 1300
    },
    {
      "epoch": 2.407749077490775,
      "grad_norm": 1.3018815365771563,
      "learning_rate": 2.283109201669936e-06,
      "loss": 0.4357,
      "step": 1305
    },
    {
      "epoch": 2.4169741697416973,
      "grad_norm": 1.2956106687686837,
      "learning_rate": 2.2152691549620155e-06,
      "loss": 0.4283,
      "step": 1310
    },
    {
      "epoch": 2.42619926199262,
      "grad_norm": 1.287230882437174,
      "learning_rate": 2.148326517482543e-06,
      "loss": 0.4303,
      "step": 1315
    },
    {
      "epoch": 2.4354243542435423,
      "grad_norm": 1.2592322120333668,
      "learning_rate": 2.0822890062537106e-06,
      "loss": 0.4366,
      "step": 1320
    },
    {
      "epoch": 2.444649446494465,
      "grad_norm": 1.3039469988205457,
      "learning_rate": 2.01716423395644e-06,
      "loss": 0.4317,
      "step": 1325
    },
    {
      "epoch": 2.4538745387453873,
      "grad_norm": 1.282772824972497,
      "learning_rate": 1.9529597080528207e-06,
      "loss": 0.4272,
      "step": 1330
    },
    {
      "epoch": 2.46309963099631,
      "grad_norm": 1.3227463435260074,
      "learning_rate": 1.8896828299206494e-06,
      "loss": 0.4256,
      "step": 1335
    },
    {
      "epoch": 2.4723247232472323,
      "grad_norm": 1.3607936617452498,
      "learning_rate": 1.8273408940002202e-06,
      "loss": 0.4389,
      "step": 1340
    },
    {
      "epoch": 2.481549815498155,
      "grad_norm": 1.2740801988744865,
      "learning_rate": 1.7659410869534466e-06,
      "loss": 0.4247,
      "step": 1345
    },
    {
      "epoch": 2.4907749077490777,
      "grad_norm": 1.2544315701192987,
      "learning_rate": 1.7054904868353717e-06,
      "loss": 0.4256,
      "step": 1350
    },
    {
      "epoch": 2.5,
      "grad_norm": 1.31550558585801,
      "learning_rate": 1.6459960622782466e-06,
      "loss": 0.428,
      "step": 1355
    },
    {
      "epoch": 2.5092250922509223,
      "grad_norm": 1.3030144767834306,
      "learning_rate": 1.587464671688187e-06,
      "loss": 0.4217,
      "step": 1360
    },
    {
      "epoch": 2.518450184501845,
      "grad_norm": 1.261812680015863,
      "learning_rate": 1.5299030624545563e-06,
      "loss": 0.4381,
      "step": 1365
    },
    {
      "epoch": 2.5276752767527677,
      "grad_norm": 1.3015065571944802,
      "learning_rate": 1.4733178701721262e-06,
      "loss": 0.4337,
      "step": 1370
    },
    {
      "epoch": 2.53690036900369,
      "grad_norm": 1.2805139778312684,
      "learning_rate": 1.4177156178761508e-06,
      "loss": 0.4313,
      "step": 1375
    },
    {
      "epoch": 2.5461254612546127,
      "grad_norm": 1.3271791125805354,
      "learning_rate": 1.363102715290402e-06,
      "loss": 0.4314,
      "step": 1380
    },
    {
      "epoch": 2.555350553505535,
      "grad_norm": 1.3155240192251205,
      "learning_rate": 1.3094854580882599e-06,
      "loss": 0.4298,
      "step": 1385
    },
    {
      "epoch": 2.5645756457564577,
      "grad_norm": 1.2884517504542843,
      "learning_rate": 1.2568700271669676e-06,
      "loss": 0.4315,
      "step": 1390
    },
    {
      "epoch": 2.57380073800738,
      "grad_norm": 1.2601572769871257,
      "learning_rate": 1.2052624879351105e-06,
      "loss": 0.4341,
      "step": 1395
    },
    {
      "epoch": 2.5830258302583027,
      "grad_norm": 1.283042988722646,
      "learning_rate": 1.1546687896133924e-06,
      "loss": 0.4301,
      "step": 1400
    },
    {
      "epoch": 2.5830258302583027,
      "eval_loss": 0.9943162798881531,
      "eval_runtime": 513.9906,
      "eval_samples_per_second": 29.864,
      "eval_steps_per_second": 0.117,
      "step": 1400
    },
    {
      "epoch": 2.592250922509225,
      "grad_norm": 1.269448040169663,
      "learning_rate": 1.1050947645488419e-06,
      "loss": 0.424,
      "step": 1405
    },
    {
      "epoch": 2.6014760147601477,
      "grad_norm": 1.291108826010762,
      "learning_rate": 1.0565461275424504e-06,
      "loss": 0.4288,
      "step": 1410
    },
    {
      "epoch": 2.61070110701107,
      "grad_norm": 1.246075371329031,
      "learning_rate": 1.0090284751903989e-06,
      "loss": 0.4308,
      "step": 1415
    },
    {
      "epoch": 2.6199261992619927,
      "grad_norm": 1.268331381912208,
      "learning_rate": 9.625472852388739e-07,
      "loss": 0.4274,
      "step": 1420
    },
    {
      "epoch": 2.6291512915129154,
      "grad_norm": 1.2558980878489436,
      "learning_rate": 9.171079159526186e-07,
      "loss": 0.4263,
      "step": 1425
    },
    {
      "epoch": 2.6383763837638377,
      "grad_norm": 1.2507458001549574,
      "learning_rate": 8.727156054972374e-07,
      "loss": 0.4364,
      "step": 1430
    },
    {
      "epoch": 2.64760147601476,
      "grad_norm": 1.2344093421817917,
      "learning_rate": 8.29375471335343e-07,
      "loss": 0.43,
      "step": 1435
    },
    {
      "epoch": 2.6568265682656826,
      "grad_norm": 1.2520176453134155,
      "learning_rate": 7.870925096366366e-07,
      "loss": 0.4298,
      "step": 1440
    },
    {
      "epoch": 2.6660516605166054,
      "grad_norm": 1.2874930933327957,
      "learning_rate": 7.458715947019468e-07,
      "loss": 0.4262,
      "step": 1445
    },
    {
      "epoch": 2.6752767527675276,
      "grad_norm": 1.2682188739552445,
      "learning_rate": 7.057174784013432e-07,
      "loss": 0.4339,
      "step": 1450
    },
    {
      "epoch": 2.6845018450184504,
      "grad_norm": 1.2828645340804818,
      "learning_rate": 6.666347896263326e-07,
      "loss": 0.4274,
      "step": 1455
    },
    {
      "epoch": 2.6937269372693726,
      "grad_norm": 1.2595258026091076,
      "learning_rate": 6.286280337562656e-07,
      "loss": 0.4303,
      "step": 1460
    },
    {
      "epoch": 2.7029520295202953,
      "grad_norm": 1.24521822647123,
      "learning_rate": 5.917015921389569e-07,
      "loss": 0.4288,
      "step": 1465
    },
    {
      "epoch": 2.7121771217712176,
      "grad_norm": 1.232445478302712,
      "learning_rate": 5.558597215856065e-07,
      "loss": 0.4285,
      "step": 1470
    },
    {
      "epoch": 2.7214022140221403,
      "grad_norm": 1.216057817991593,
      "learning_rate": 5.211065538800952e-07,
      "loss": 0.4208,
      "step": 1475
    },
    {
      "epoch": 2.7306273062730626,
      "grad_norm": 1.288524367589534,
      "learning_rate": 4.874460953026705e-07,
      "loss": 0.4255,
      "step": 1480
    },
    {
      "epoch": 2.7398523985239853,
      "grad_norm": 1.2332155213343263,
      "learning_rate": 4.548822261681107e-07,
      "loss": 0.423,
      "step": 1485
    },
    {
      "epoch": 2.7490774907749076,
      "grad_norm": 1.2278878382563285,
      "learning_rate": 4.2341870037841516e-07,
      "loss": 0.4291,
      "step": 1490
    },
    {
      "epoch": 2.7583025830258303,
      "grad_norm": 1.262898121860552,
      "learning_rate": 3.930591449900578e-07,
      "loss": 0.4247,
      "step": 1495
    },
    {
      "epoch": 2.767527675276753,
      "grad_norm": 1.2437619506416164,
      "learning_rate": 3.638070597958665e-07,
      "loss": 0.4361,
      "step": 1500
    },
    {
      "epoch": 2.767527675276753,
      "eval_loss": 0.9930853247642517,
      "eval_runtime": 516.1928,
      "eval_samples_per_second": 29.737,
      "eval_steps_per_second": 0.116,
      "step": 1500
    },
    {
      "epoch": 2.7767527675276753,
      "grad_norm": 1.2468366513522777,
      "learning_rate": 3.356658169215743e-07,
      "loss": 0.4282,
      "step": 1505
    },
    {
      "epoch": 2.7859778597785976,
      "grad_norm": 1.2336029324910027,
      "learning_rate": 3.0863866043708393e-07,
      "loss": 0.4267,
      "step": 1510
    },
    {
      "epoch": 2.7952029520295203,
      "grad_norm": 1.3330748292636831,
      "learning_rate": 2.8272870598250677e-07,
      "loss": 0.4281,
      "step": 1515
    },
    {
      "epoch": 2.804428044280443,
      "grad_norm": 1.2486193575900169,
      "learning_rate": 2.5793894040898384e-07,
      "loss": 0.4224,
      "step": 1520
    },
    {
      "epoch": 2.8136531365313653,
      "grad_norm": 1.235394179484528,
      "learning_rate": 2.3427222143438065e-07,
      "loss": 0.4184,
      "step": 1525
    },
    {
      "epoch": 2.8228782287822876,
      "grad_norm": 1.2913244981868073,
      "learning_rate": 2.117312773138458e-07,
      "loss": 0.4238,
      "step": 1530
    },
    {
      "epoch": 2.8321033210332103,
      "grad_norm": 1.2580451640594703,
      "learning_rate": 1.903187065253076e-07,
      "loss": 0.4274,
      "step": 1535
    },
    {
      "epoch": 2.841328413284133,
      "grad_norm": 1.262849856657073,
      "learning_rate": 1.7003697746992398e-07,
      "loss": 0.4242,
      "step": 1540
    },
    {
      "epoch": 2.8505535055350553,
      "grad_norm": 1.2336423601103856,
      "learning_rate": 1.5088842818752892e-07,
      "loss": 0.4338,
      "step": 1545
    },
    {
      "epoch": 2.859778597785978,
      "grad_norm": 1.279029201429549,
      "learning_rate": 1.3287526608711132e-07,
      "loss": 0.4247,
      "step": 1550
    },
    {
      "epoch": 2.8690036900369003,
      "grad_norm": 1.2569044993333771,
      "learning_rate": 1.1599956769234533e-07,
      "loss": 0.4167,
      "step": 1555
    },
    {
      "epoch": 2.878228782287823,
      "grad_norm": 1.229520630461672,
      "learning_rate": 1.0026327840221728e-07,
      "loss": 0.4182,
      "step": 1560
    },
    {
      "epoch": 2.8874538745387452,
      "grad_norm": 1.255986608003343,
      "learning_rate": 8.566821226675514e-08,
      "loss": 0.4294,
      "step": 1565
    },
    {
      "epoch": 2.896678966789668,
      "grad_norm": 1.2895814979486142,
      "learning_rate": 7.22160517779169e-08,
      "loss": 0.429,
      "step": 1570
    },
    {
      "epoch": 2.9059040590405907,
      "grad_norm": 1.2790109206046127,
      "learning_rate": 5.99083476756357e-08,
      "loss": 0.4261,
      "step": 1575
    },
    {
      "epoch": 2.915129151291513,
      "grad_norm": 1.2194809596900478,
      "learning_rate": 4.87465187690439e-08,
      "loss": 0.4211,
      "step": 1580
    },
    {
      "epoch": 2.9243542435424352,
      "grad_norm": 1.2665552740156838,
      "learning_rate": 3.873185177292737e-08,
      "loss": 0.4251,
      "step": 1585
    },
    {
      "epoch": 2.933579335793358,
      "grad_norm": 1.2812371627035533,
      "learning_rate": 2.9865501159387355e-08,
      "loss": 0.4282,
      "step": 1590
    },
    {
      "epoch": 2.9428044280442807,
      "grad_norm": 1.2399165066075877,
      "learning_rate": 2.214848902475808e-08,
      "loss": 0.4341,
      "step": 1595
    },
    {
      "epoch": 2.952029520295203,
      "grad_norm": 1.2154194504631015,
      "learning_rate": 1.558170497178213e-08,
      "loss": 0.4256,
      "step": 1600
    },
    {
      "epoch": 2.952029520295203,
      "eval_loss": 0.9934021830558777,
      "eval_runtime": 525.4852,
      "eval_samples_per_second": 29.211,
      "eval_steps_per_second": 0.114,
      "step": 1600
    },
    {
      "epoch": 2.961254612546125,
      "grad_norm": 1.2717521820081574,
      "learning_rate": 1.0165906007056914e-08,
      "loss": 0.4323,
      "step": 1605
    },
    {
      "epoch": 2.970479704797048,
      "grad_norm": 1.2491830905746684,
      "learning_rate": 5.901716453770023e-09,
      "loss": 0.4271,
      "step": 1610
    },
    {
      "epoch": 2.9797047970479706,
      "grad_norm": 1.2521953436091506,
      "learning_rate": 2.7896278797256983e-09,
      "loss": 0.4256,
      "step": 1615
    },
    {
      "epoch": 2.988929889298893,
      "grad_norm": 1.2335508198968657,
      "learning_rate": 8.299990406823721e-10,
      "loss": 0.4342,
      "step": 1620
    },
    {
      "epoch": 2.9981549815498156,
      "grad_norm": 1.2480273735451688,
      "learning_rate": 2.3055838990204693e-11,
      "loss": 0.4266,
      "step": 1625
    },
    {
      "epoch": 3.0,
      "step": 1626,
      "total_flos": 1361805280542720.0,
      "train_loss": 0.713569560815634,
      "train_runtime": 59769.2599,
      "train_samples_per_second": 6.961,
      "train_steps_per_second": 0.027
    }
  ],
  "logging_steps": 5,
  "max_steps": 1626,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1361805280542720.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}