{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.1757789535567313,
  "eval_steps": 42,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0023515579071134627,
      "eval_loss": 11.93134593963623,
      "eval_runtime": 10.5205,
      "eval_samples_per_second": 272.23,
      "eval_steps_per_second": 8.555,
      "step": 1
    },
    {
      "epoch": 0.007054673721340388,
      "grad_norm": 0.012463300488889217,
      "learning_rate": 3e-05,
      "loss": 11.9313,
      "step": 3
    },
    {
      "epoch": 0.014109347442680775,
      "grad_norm": 0.015666738152503967,
      "learning_rate": 6e-05,
      "loss": 11.9317,
      "step": 6
    },
    {
      "epoch": 0.021164021164021163,
      "grad_norm": 0.021637123078107834,
      "learning_rate": 9e-05,
      "loss": 11.9311,
      "step": 9
    },
    {
      "epoch": 0.02821869488536155,
      "grad_norm": 0.01769455522298813,
      "learning_rate": 9.999588943391597e-05,
      "loss": 11.9313,
      "step": 12
    },
    {
      "epoch": 0.03527336860670194,
      "grad_norm": 0.018525123596191406,
      "learning_rate": 9.99743108100344e-05,
      "loss": 11.9307,
      "step": 15
    },
    {
      "epoch": 0.042328042328042326,
      "grad_norm": 0.022749891504645348,
      "learning_rate": 9.993424445916923e-05,
      "loss": 11.9299,
      "step": 18
    },
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 0.033247560262680054,
      "learning_rate": 9.987570520365104e-05,
      "loss": 11.9297,
      "step": 21
    },
    {
      "epoch": 0.0564373897707231,
      "grad_norm": 0.03264958783984184,
      "learning_rate": 9.979871469976196e-05,
      "loss": 11.9297,
      "step": 24
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 0.03716759756207466,
      "learning_rate": 9.970330142972401e-05,
      "loss": 11.9294,
      "step": 27
    },
    {
      "epoch": 0.07054673721340388,
      "grad_norm": 0.06127162277698517,
      "learning_rate": 9.95895006911623e-05,
      "loss": 11.9286,
      "step": 30
    },
    {
      "epoch": 0.07760141093474426,
      "grad_norm": 0.04590151831507683,
      "learning_rate": 9.945735458404681e-05,
      "loss": 11.9284,
      "step": 33
    },
    {
      "epoch": 0.08465608465608465,
      "grad_norm": 0.056038279086351395,
      "learning_rate": 9.930691199511775e-05,
      "loss": 11.9269,
      "step": 36
    },
    {
      "epoch": 0.09171075837742504,
      "grad_norm": 0.05783422291278839,
      "learning_rate": 9.91382285798002e-05,
      "loss": 11.927,
      "step": 39
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 0.053165242075920105,
      "learning_rate": 9.895136674161465e-05,
      "loss": 11.9254,
      "step": 42
    },
    {
      "epoch": 0.09876543209876543,
      "eval_loss": 11.925036430358887,
      "eval_runtime": 10.6532,
      "eval_samples_per_second": 268.841,
      "eval_steps_per_second": 8.448,
      "step": 42
    },
    {
      "epoch": 0.10582010582010581,
      "grad_norm": 0.038137730211019516,
      "learning_rate": 9.874639560909117e-05,
      "loss": 11.9253,
      "step": 45
    },
    {
      "epoch": 0.1128747795414462,
      "grad_norm": 0.047474514693021774,
      "learning_rate": 9.852339101019574e-05,
      "loss": 11.9246,
      "step": 48
    },
    {
      "epoch": 0.11992945326278659,
      "grad_norm": 0.040923334658145905,
      "learning_rate": 9.828243544427796e-05,
      "loss": 11.924,
      "step": 51
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 0.04106362909078598,
      "learning_rate": 9.802361805155097e-05,
      "loss": 11.923,
      "step": 54
    },
    {
      "epoch": 0.13403880070546736,
      "grad_norm": 0.032283883541822433,
      "learning_rate": 9.774703458011453e-05,
      "loss": 11.9225,
      "step": 57
    },
    {
      "epoch": 0.14109347442680775,
      "grad_norm": 0.06524904817342758,
      "learning_rate": 9.745278735053343e-05,
      "loss": 11.9216,
      "step": 60
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.030542707070708275,
      "learning_rate": 9.714098521798465e-05,
      "loss": 11.9207,
      "step": 63
    },
    {
      "epoch": 0.15520282186948853,
      "grad_norm": 0.02981523610651493,
      "learning_rate": 9.681174353198687e-05,
      "loss": 11.9213,
      "step": 66
    },
    {
      "epoch": 0.16225749559082892,
      "grad_norm": 0.03491352126002312,
      "learning_rate": 9.64651840937276e-05,
      "loss": 11.921,
      "step": 69
    },
    {
      "epoch": 0.1693121693121693,
      "grad_norm": 0.029117964208126068,
      "learning_rate": 9.610143511100354e-05,
      "loss": 11.9203,
      "step": 72
    },
    {
      "epoch": 0.1763668430335097,
      "grad_norm": 0.03240862861275673,
      "learning_rate": 9.572063115079063e-05,
      "loss": 11.9196,
      "step": 75
    },
    {
      "epoch": 0.18342151675485008,
      "grad_norm": 0.022400949150323868,
      "learning_rate": 9.53229130894619e-05,
      "loss": 11.9196,
      "step": 78
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.022678203880786896,
      "learning_rate": 9.490842806067095e-05,
      "loss": 11.9205,
      "step": 81
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.03054334782063961,
      "learning_rate": 9.44773294009206e-05,
      "loss": 11.9196,
      "step": 84
    },
    {
      "epoch": 0.19753086419753085,
      "eval_loss": 11.919329643249512,
      "eval_runtime": 10.8695,
      "eval_samples_per_second": 263.49,
      "eval_steps_per_second": 8.28,
      "step": 84
    },
    {
      "epoch": 0.20458553791887124,
      "grad_norm": 0.02172757126390934,
      "learning_rate": 9.40297765928369e-05,
      "loss": 11.9193,
      "step": 87
    },
    {
      "epoch": 0.21164021164021163,
      "grad_norm": 0.023694947361946106,
      "learning_rate": 9.356593520616948e-05,
      "loss": 11.919,
      "step": 90
    },
    {
      "epoch": 0.21869488536155202,
      "grad_norm": 0.03806081414222717,
      "learning_rate": 9.308597683653975e-05,
      "loss": 11.9175,
      "step": 93
    },
    {
      "epoch": 0.2257495590828924,
      "grad_norm": 0.02170073799788952,
      "learning_rate": 9.259007904196023e-05,
      "loss": 11.9193,
      "step": 96
    },
    {
      "epoch": 0.2328042328042328,
      "grad_norm": 0.02128906175494194,
      "learning_rate": 9.207842527714767e-05,
      "loss": 11.9188,
      "step": 99
    },
    {
      "epoch": 0.23985890652557318,
      "grad_norm": 0.02206624485552311,
      "learning_rate": 9.155120482565521e-05,
      "loss": 11.9186,
      "step": 102
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 0.021899454295635223,
      "learning_rate": 9.10086127298478e-05,
      "loss": 11.918,
      "step": 105
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 0.030206996947526932,
      "learning_rate": 9.045084971874738e-05,
      "loss": 11.9182,
      "step": 108
    },
    {
      "epoch": 0.26102292768959434,
      "grad_norm": 0.02562589943408966,
      "learning_rate": 8.987812213377424e-05,
      "loss": 11.9188,
      "step": 111
    },
    {
      "epoch": 0.26807760141093473,
      "grad_norm": 0.021965835243463516,
      "learning_rate": 8.929064185241213e-05,
      "loss": 11.9183,
      "step": 114
    },
    {
      "epoch": 0.2751322751322751,
      "grad_norm": 0.02135823480784893,
      "learning_rate": 8.868862620982534e-05,
      "loss": 11.9182,
      "step": 117
    },
    {
      "epoch": 0.2821869488536155,
      "grad_norm": 0.029081886634230614,
      "learning_rate": 8.807229791845673e-05,
      "loss": 11.9185,
      "step": 120
    },
    {
      "epoch": 0.2892416225749559,
      "grad_norm": 0.01876562461256981,
      "learning_rate": 8.744188498563641e-05,
      "loss": 11.9178,
      "step": 123
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.026901056990027428,
      "learning_rate": 8.679762062923175e-05,
      "loss": 11.9171,
      "step": 126
    },
    {
      "epoch": 0.2962962962962963,
      "eval_loss": 11.917308807373047,
      "eval_runtime": 10.6998,
      "eval_samples_per_second": 267.668,
      "eval_steps_per_second": 8.411,
      "step": 126
    },
    {
      "epoch": 0.30335097001763667,
      "grad_norm": 0.02258964441716671,
      "learning_rate": 8.613974319136958e-05,
      "loss": 11.9175,
      "step": 129
    },
    {
      "epoch": 0.31040564373897706,
      "grad_norm": 0.019902532920241356,
      "learning_rate": 8.54684960502629e-05,
      "loss": 11.9189,
      "step": 132
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 0.020657015964388847,
      "learning_rate": 8.478412753017433e-05,
      "loss": 11.9177,
      "step": 135
    },
    {
      "epoch": 0.32451499118165783,
      "grad_norm": 0.02019345760345459,
      "learning_rate": 8.408689080954998e-05,
      "loss": 11.9179,
      "step": 138
    },
    {
      "epoch": 0.3315696649029982,
      "grad_norm": 0.020498735830187798,
      "learning_rate": 8.33770438273574e-05,
      "loss": 11.9175,
      "step": 141
    },
    {
      "epoch": 0.3386243386243386,
      "grad_norm": 0.02337423898279667,
      "learning_rate": 8.265484918766243e-05,
      "loss": 11.9178,
      "step": 144
    },
    {
      "epoch": 0.345679012345679,
      "grad_norm": 0.02081083133816719,
      "learning_rate": 8.192057406248028e-05,
      "loss": 11.9165,
      "step": 147
    },
    {
      "epoch": 0.3527336860670194,
      "grad_norm": 0.01860121265053749,
      "learning_rate": 8.117449009293668e-05,
      "loss": 11.9177,
      "step": 150
    },
    {
      "epoch": 0.35978835978835977,
      "grad_norm": 0.02201470360159874,
      "learning_rate": 8.041687328877567e-05,
      "loss": 11.9165,
      "step": 153
    },
    {
      "epoch": 0.36684303350970016,
      "grad_norm": 0.024001609534025192,
      "learning_rate": 7.964800392625129e-05,
      "loss": 11.9168,
      "step": 156
    },
    {
      "epoch": 0.37389770723104054,
      "grad_norm": 0.02816389873623848,
      "learning_rate": 7.886816644444098e-05,
      "loss": 11.9174,
      "step": 159
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.01967223547399044,
      "learning_rate": 7.807764934001874e-05,
      "loss": 11.9147,
      "step": 162
    },
    {
      "epoch": 0.3880070546737213,
      "grad_norm": 0.033686283975839615,
      "learning_rate": 7.727674506052743e-05,
      "loss": 11.9176,
      "step": 165
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.029333915561437607,
      "learning_rate": 7.646574989618938e-05,
      "loss": 11.9173,
      "step": 168
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 11.916316032409668,
      "eval_runtime": 10.8242,
      "eval_samples_per_second": 264.592,
      "eval_steps_per_second": 8.315,
      "step": 168
    },
    {
      "epoch": 0.4021164021164021,
      "grad_norm": 0.020618749782443047,
      "learning_rate": 7.564496387029532e-05,
      "loss": 11.9169,
      "step": 171
    },
    {
      "epoch": 0.4091710758377425,
      "grad_norm": 0.02999415621161461,
      "learning_rate": 7.481469062821252e-05,
      "loss": 11.9169,
      "step": 174
    },
    {
      "epoch": 0.41622574955908287,
      "grad_norm": 0.01824590004980564,
      "learning_rate": 7.39752373250527e-05,
      "loss": 11.9167,
      "step": 177
    },
    {
      "epoch": 0.42328042328042326,
      "grad_norm": 0.05701108276844025,
      "learning_rate": 7.312691451204178e-05,
      "loss": 11.9158,
      "step": 180
    },
    {
      "epoch": 0.43033509700176364,
      "grad_norm": 0.022198380902409554,
      "learning_rate": 7.227003602163295e-05,
      "loss": 11.9165,
      "step": 183
    },
    {
      "epoch": 0.43738977072310403,
      "grad_norm": 0.022028392180800438,
      "learning_rate": 7.14049188514063e-05,
      "loss": 11.9166,
      "step": 186
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.03448006883263588,
      "learning_rate": 7.05318830467969e-05,
      "loss": 11.9165,
      "step": 189
    },
    {
      "epoch": 0.4514991181657848,
      "grad_norm": 0.023939242586493492,
      "learning_rate": 6.965125158269619e-05,
      "loss": 11.9164,
      "step": 192
    },
    {
      "epoch": 0.4585537918871252,
      "grad_norm": 0.01913815177977085,
      "learning_rate": 6.876335024396872e-05,
      "loss": 11.9166,
      "step": 195
    },
    {
      "epoch": 0.4656084656084656,
      "grad_norm": 0.02663358673453331,
      "learning_rate": 6.786850750493006e-05,
      "loss": 11.917,
      "step": 198
    },
    {
      "epoch": 0.47266313932980597,
      "grad_norm": 0.020899388939142227,
      "learning_rate": 6.696705440782938e-05,
      "loss": 11.9154,
      "step": 201
    },
    {
      "epoch": 0.47971781305114636,
      "grad_norm": 0.023673586547374725,
      "learning_rate": 6.605932444038229e-05,
      "loss": 11.9157,
      "step": 204
    },
    {
      "epoch": 0.48677248677248675,
      "grad_norm": 0.025094488635659218,
      "learning_rate": 6.514565341239861e-05,
      "loss": 11.9159,
      "step": 207
    },
    {
      "epoch": 0.49382716049382713,
      "grad_norm": 0.02767755836248398,
      "learning_rate": 6.422637933155162e-05,
      "loss": 11.9158,
      "step": 210
    },
    {
      "epoch": 0.49382716049382713,
      "eval_loss": 11.915718078613281,
      "eval_runtime": 10.5682,
      "eval_samples_per_second": 271.003,
      "eval_steps_per_second": 8.516,
      "step": 210
    },
    {
      "epoch": 0.5008818342151675,
      "grad_norm": 0.02221379242837429,
      "learning_rate": 6.330184227833376e-05,
      "loss": 11.9166,
      "step": 213
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 0.021963153034448624,
      "learning_rate": 6.237238428024572e-05,
      "loss": 11.9161,
      "step": 216
    },
    {
      "epoch": 0.5149911816578483,
      "grad_norm": 0.026923993602395058,
      "learning_rate": 6.143834918526527e-05,
      "loss": 11.9146,
      "step": 219
    },
    {
      "epoch": 0.5220458553791887,
      "grad_norm": 0.035227347165346146,
      "learning_rate": 6.0500082534642464e-05,
      "loss": 11.9154,
      "step": 222
    },
    {
      "epoch": 0.5291005291005291,
      "grad_norm": 0.021038008853793144,
      "learning_rate": 5.955793143506863e-05,
      "loss": 11.9158,
      "step": 225
    },
    {
      "epoch": 0.5361552028218695,
      "grad_norm": 0.01937274821102619,
      "learning_rate": 5.861224443026595e-05,
      "loss": 11.9162,
      "step": 228
    },
    {
      "epoch": 0.5432098765432098,
      "grad_norm": 0.019016142934560776,
      "learning_rate": 5.766337137204579e-05,
      "loss": 11.9163,
      "step": 231
    },
    {
      "epoch": 0.5502645502645502,
      "grad_norm": 0.027969468384981155,
      "learning_rate": 5.6711663290882776e-05,
      "loss": 11.9162,
      "step": 234
    },
    {
      "epoch": 0.5573192239858906,
      "grad_norm": 0.017542190849781036,
      "learning_rate": 5.575747226605298e-05,
      "loss": 11.917,
      "step": 237
    },
    {
      "epoch": 0.564373897707231,
      "grad_norm": 0.023203639313578606,
      "learning_rate": 5.480115129538409e-05,
      "loss": 11.9157,
      "step": 240
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.014958036132156849,
      "learning_rate": 5.384305416466584e-05,
      "loss": 11.9154,
      "step": 243
    },
    {
      "epoch": 0.5784832451499118,
      "grad_norm": 0.027328725904226303,
      "learning_rate": 5.288353531676873e-05,
      "loss": 11.9163,
      "step": 246
    },
    {
      "epoch": 0.5855379188712522,
      "grad_norm": 0.03369058296084404,
      "learning_rate": 5.192294972051992e-05,
      "loss": 11.9157,
      "step": 249
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.019253922626376152,
      "learning_rate": 5.0961652739384356e-05,
      "loss": 11.9147,
      "step": 252
    },
    {
      "epoch": 0.5925925925925926,
      "eval_loss": 11.915318489074707,
      "eval_runtime": 10.3985,
      "eval_samples_per_second": 275.425,
      "eval_steps_per_second": 8.655,
      "step": 252
    },
    {
      "epoch": 0.599647266313933,
      "grad_norm": 0.024502824991941452,
      "learning_rate": 5e-05,
      "loss": 11.9151,
      "step": 255
    },
    {
      "epoch": 0.6067019400352733,
      "grad_norm": 0.03233085200190544,
      "learning_rate": 4.903834726061565e-05,
      "loss": 11.9151,
      "step": 258
    },
    {
      "epoch": 0.6137566137566137,
      "grad_norm": 0.02394239790737629,
      "learning_rate": 4.807705027948008e-05,
      "loss": 11.915,
      "step": 261
    },
    {
      "epoch": 0.6208112874779541,
      "grad_norm": 0.01676931232213974,
      "learning_rate": 4.711646468323129e-05,
      "loss": 11.9164,
      "step": 264
    },
    {
      "epoch": 0.6278659611992945,
      "grad_norm": 0.02555139549076557,
      "learning_rate": 4.6156945835334184e-05,
      "loss": 11.9157,
      "step": 267
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 0.02273687720298767,
      "learning_rate": 4.5198848704615914e-05,
      "loss": 11.9159,
      "step": 270
    },
    {
      "epoch": 0.6419753086419753,
      "grad_norm": 0.0266796313226223,
      "learning_rate": 4.424252773394704e-05,
      "loss": 11.9163,
      "step": 273
    },
    {
      "epoch": 0.6490299823633157,
      "grad_norm": 0.025090264156460762,
      "learning_rate": 4.328833670911724e-05,
      "loss": 11.9164,
      "step": 276
    },
    {
      "epoch": 0.656084656084656,
      "grad_norm": 0.02523481287062168,
      "learning_rate": 4.23366286279542e-05,
      "loss": 11.9157,
      "step": 279
    },
    {
      "epoch": 0.6631393298059964,
      "grad_norm": 0.021461475640535355,
      "learning_rate": 4.138775556973406e-05,
      "loss": 11.9147,
      "step": 282
    },
    {
      "epoch": 0.6701940035273368,
      "grad_norm": 0.023472610861063004,
      "learning_rate": 4.04420685649314e-05,
      "loss": 11.9161,
      "step": 285
    },
    {
      "epoch": 0.6772486772486772,
      "grad_norm": 0.024858828634023666,
      "learning_rate": 3.9499917465357534e-05,
      "loss": 11.9152,
      "step": 288
    },
    {
      "epoch": 0.6843033509700176,
      "grad_norm": 0.020553085952997208,
      "learning_rate": 3.856165081473474e-05,
      "loss": 11.9139,
      "step": 291
    },
    {
      "epoch": 0.691358024691358,
      "grad_norm": 0.02018040418624878,
      "learning_rate": 3.762761571975429e-05,
      "loss": 11.9156,
      "step": 294
    },
    {
      "epoch": 0.691358024691358,
      "eval_loss": 11.915068626403809,
      "eval_runtime": 10.6749,
      "eval_samples_per_second": 268.292,
      "eval_steps_per_second": 8.431,
      "step": 294
    },
    {
      "epoch": 0.6984126984126984,
      "grad_norm": 0.01783376932144165,
      "learning_rate": 3.6698157721666246e-05,
      "loss": 11.9134,
      "step": 297
    },
    {
      "epoch": 0.7054673721340388,
      "grad_norm": 0.028524892404675484,
      "learning_rate": 3.5773620668448384e-05,
      "loss": 11.9158,
      "step": 300
    },
    {
      "epoch": 0.7125220458553791,
      "grad_norm": 0.02065563015639782,
      "learning_rate": 3.48543465876014e-05,
      "loss": 11.9146,
      "step": 303
    },
    {
      "epoch": 0.7195767195767195,
      "grad_norm": 0.045134805142879486,
      "learning_rate": 3.3940675559617724e-05,
      "loss": 11.9159,
      "step": 306
    },
    {
      "epoch": 0.7266313932980599,
      "grad_norm": 0.023695290088653564,
      "learning_rate": 3.303294559217063e-05,
      "loss": 11.9153,
      "step": 309
    },
    {
      "epoch": 0.7336860670194003,
      "grad_norm": 0.01704533025622368,
      "learning_rate": 3.213149249506997e-05,
      "loss": 11.915,
      "step": 312
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.02306770719587803,
      "learning_rate": 3.12366497560313e-05,
      "loss": 11.9155,
      "step": 315
    },
    {
      "epoch": 0.7477954144620811,
      "grad_norm": 0.023183325305581093,
      "learning_rate": 3.0348748417303823e-05,
      "loss": 11.9152,
      "step": 318
    },
    {
      "epoch": 0.7548500881834215,
      "grad_norm": 0.01855415478348732,
      "learning_rate": 2.9468116953203107e-05,
      "loss": 11.9163,
      "step": 321
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.02062196470797062,
      "learning_rate": 2.8595081148593738e-05,
      "loss": 11.9154,
      "step": 324
    },
    {
      "epoch": 0.7689594356261023,
      "grad_norm": 0.025098076090216637,
      "learning_rate": 2.772996397836704e-05,
      "loss": 11.9162,
      "step": 327
    },
    {
      "epoch": 0.7760141093474426,
      "grad_norm": 0.018340418115258217,
      "learning_rate": 2.687308548795825e-05,
      "loss": 11.9156,
      "step": 330
    },
    {
      "epoch": 0.783068783068783,
      "grad_norm": 0.02159620076417923,
      "learning_rate": 2.6024762674947313e-05,
      "loss": 11.9144,
      "step": 333
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.02330397628247738,
      "learning_rate": 2.5185309371787513e-05,
      "loss": 11.9156,
      "step": 336
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 11.914894104003906,
      "eval_runtime": 10.4255,
      "eval_samples_per_second": 274.71,
      "eval_steps_per_second": 8.633,
      "step": 336
    },
    {
      "epoch": 0.7971781305114638,
      "grad_norm": 0.023469174280762672,
      "learning_rate": 2.43550361297047e-05,
      "loss": 11.9143,
      "step": 339
    },
    {
      "epoch": 0.8042328042328042,
      "grad_norm": 0.01915036514401436,
      "learning_rate": 2.353425010381063e-05,
      "loss": 11.917,
      "step": 342
    },
    {
      "epoch": 0.8112874779541446,
      "grad_norm": 0.021919777616858482,
      "learning_rate": 2.272325493947257e-05,
      "loss": 11.9137,
      "step": 345
    },
    {
      "epoch": 0.818342151675485,
      "grad_norm": 0.03252611309289932,
      "learning_rate": 2.192235065998126e-05,
      "loss": 11.9149,
      "step": 348
    },
    {
      "epoch": 0.8253968253968254,
      "grad_norm": 0.021312009543180466,
      "learning_rate": 2.1131833555559037e-05,
      "loss": 11.9156,
      "step": 351
    },
    {
      "epoch": 0.8324514991181657,
      "grad_norm": 0.02721288986504078,
      "learning_rate": 2.0351996073748713e-05,
      "loss": 11.9151,
      "step": 354
    },
    {
      "epoch": 0.8395061728395061,
      "grad_norm": 0.019871938973665237,
      "learning_rate": 1.9583126711224343e-05,
      "loss": 11.9153,
      "step": 357
    },
    {
      "epoch": 0.8465608465608465,
      "grad_norm": 0.02446158602833748,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 11.9161,
      "step": 360
    },
    {
      "epoch": 0.8536155202821869,
      "grad_norm": 0.028117047622799873,
      "learning_rate": 1.807942593751973e-05,
      "loss": 11.9168,
      "step": 363
    },
    {
      "epoch": 0.8606701940035273,
      "grad_norm": 0.02583438903093338,
      "learning_rate": 1.7345150812337564e-05,
      "loss": 11.9152,
      "step": 366
    },
    {
      "epoch": 0.8677248677248677,
      "grad_norm": 0.026459960266947746,
      "learning_rate": 1.66229561726426e-05,
      "loss": 11.9158,
      "step": 369
    },
    {
      "epoch": 0.8747795414462081,
      "grad_norm": 0.01762359030544758,
      "learning_rate": 1.5913109190450032e-05,
      "loss": 11.9162,
      "step": 372
    },
    {
      "epoch": 0.8818342151675485,
      "grad_norm": 0.02677866630256176,
      "learning_rate": 1.5215872469825682e-05,
      "loss": 11.9157,
      "step": 375
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.03301187977194786,
      "learning_rate": 1.4531503949737108e-05,
      "loss": 11.9147,
      "step": 378
    },
    {
      "epoch": 0.8888888888888888,
      "eval_loss": 11.914801597595215,
      "eval_runtime": 10.6272,
      "eval_samples_per_second": 269.497,
      "eval_steps_per_second": 8.469,
      "step": 378
    },
    {
      "epoch": 0.8959435626102292,
      "grad_norm": 0.019808808341622353,
      "learning_rate": 1.3860256808630428e-05,
      "loss": 11.916,
      "step": 381
    },
    {
      "epoch": 0.9029982363315696,
      "grad_norm": 0.023428916931152344,
      "learning_rate": 1.3202379370768252e-05,
      "loss": 11.916,
      "step": 384
    },
    {
      "epoch": 0.91005291005291,
      "grad_norm": 0.018417634069919586,
      "learning_rate": 1.2558115014363592e-05,
      "loss": 11.9163,
      "step": 387
    },
    {
      "epoch": 0.9171075837742504,
      "grad_norm": 0.020826270803809166,
      "learning_rate": 1.1927702081543279e-05,
      "loss": 11.9157,
      "step": 390
    },
    {
      "epoch": 0.9241622574955908,
      "grad_norm": 0.02966841123998165,
      "learning_rate": 1.1311373790174657e-05,
      "loss": 11.9141,
      "step": 393
    },
    {
      "epoch": 0.9312169312169312,
      "grad_norm": 0.018212970346212387,
      "learning_rate": 1.0709358147587884e-05,
      "loss": 11.9149,
      "step": 396
    },
    {
      "epoch": 0.9382716049382716,
      "grad_norm": 0.022182345390319824,
      "learning_rate": 1.0121877866225781e-05,
      "loss": 11.9147,
      "step": 399
    },
    {
      "epoch": 0.9453262786596119,
      "grad_norm": 0.0208954568952322,
      "learning_rate": 9.549150281252633e-06,
      "loss": 11.9151,
      "step": 402
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.022049158811569214,
      "learning_rate": 8.991387270152201e-06,
      "loss": 11.9143,
      "step": 405
    },
    {
      "epoch": 0.9594356261022927,
      "grad_norm": 0.024066656827926636,
      "learning_rate": 8.448795174344804e-06,
      "loss": 11.9147,
      "step": 408
    },
    {
      "epoch": 0.9664902998236331,
      "grad_norm": 0.0210318211466074,
      "learning_rate": 7.921574722852343e-06,
      "loss": 11.9155,
      "step": 411
    },
    {
      "epoch": 0.9735449735449735,
      "grad_norm": 0.028868673369288445,
      "learning_rate": 7.409920958039795e-06,
      "loss": 11.9127,
      "step": 414
    },
    {
      "epoch": 0.9805996472663139,
      "grad_norm": 0.023974774405360222,
      "learning_rate": 6.9140231634602485e-06,
      "loss": 11.9156,
      "step": 417
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.028788629919290543,
      "learning_rate": 6.43406479383053e-06,
      "loss": 11.9142,
      "step": 420
    },
    {
      "epoch": 0.9876543209876543,
      "eval_loss": 11.914738655090332,
      "eval_runtime": 10.0919,
      "eval_samples_per_second": 283.793,
      "eval_steps_per_second": 8.918,
      "step": 420
    },
    {
      "epoch": 0.9947089947089947,
      "grad_norm": 0.023696357384324074,
      "learning_rate": 5.9702234071631e-06,
      "loss": 11.9155,
      "step": 423
    },
    {
      "epoch": 1.001763668430335,
      "grad_norm": 0.03524714708328247,
      "learning_rate": 5.5226705990794155e-06,
      "loss": 14.6697,
      "step": 426
    },
    {
      "epoch": 1.0088183421516754,
      "grad_norm": 0.019016897305846214,
      "learning_rate": 5.091571939329048e-06,
      "loss": 12.1316,
      "step": 429
    },
    {
      "epoch": 1.0158730158730158,
      "grad_norm": 0.021377887576818466,
      "learning_rate": 4.677086910538092e-06,
      "loss": 12.2558,
      "step": 432
    },
    {
      "epoch": 1.0229276895943562,
      "grad_norm": 0.02245590090751648,
      "learning_rate": 4.279368849209381e-06,
      "loss": 11.7679,
      "step": 435
    },
    {
      "epoch": 1.0299823633156966,
      "grad_norm": 0.016183845698833466,
      "learning_rate": 3.898564888996476e-06,
      "loss": 11.9971,
      "step": 438
    },
    {
      "epoch": 1.037037037037037,
      "grad_norm": 0.017965037375688553,
      "learning_rate": 3.534815906272404e-06,
      "loss": 11.6156,
      "step": 441
    },
    {
      "epoch": 1.0440917107583774,
      "grad_norm": 0.020000630989670753,
      "learning_rate": 3.18825646801314e-06,
      "loss": 12.1001,
      "step": 444
    },
    {
      "epoch": 1.0511463844797178,
      "grad_norm": 0.021238798275589943,
      "learning_rate": 2.8590147820153513e-06,
      "loss": 11.8095,
      "step": 447
    },
    {
      "epoch": 1.0582010582010581,
      "grad_norm": 0.025096235796809196,
      "learning_rate": 2.547212649466568e-06,
      "loss": 11.8153,
      "step": 450
    },
    {
      "epoch": 1.0652557319223985,
      "grad_norm": 0.02049741894006729,
      "learning_rate": 2.2529654198854835e-06,
      "loss": 11.9978,
      "step": 453
    },
    {
      "epoch": 1.072310405643739,
      "grad_norm": 0.025018183514475822,
      "learning_rate": 1.9763819484490355e-06,
      "loss": 11.9496,
      "step": 456
    },
    {
      "epoch": 1.0793650793650793,
      "grad_norm": 0.021498849615454674,
      "learning_rate": 1.7175645557220566e-06,
      "loss": 11.7952,
      "step": 459
    },
    {
      "epoch": 1.0864197530864197,
      "grad_norm": 0.02332150749862194,
      "learning_rate": 1.4766089898042678e-06,
      "loss": 11.7297,
      "step": 462
    },
    {
      "epoch": 1.0864197530864197,
      "eval_loss": 11.914722442626953,
      "eval_runtime": 10.3803,
      "eval_samples_per_second": 275.908,
      "eval_steps_per_second": 8.67,
      "step": 462
    },
    {
      "epoch": 1.09347442680776,
      "grad_norm": 0.028014004230499268,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 12.2078,
      "step": 465
    },
    {
      "epoch": 1.1005291005291005,
      "grad_norm": 0.019710175693035126,
      "learning_rate": 1.0486332583853563e-06,
      "loss": 11.932,
      "step": 468
    },
    {
      "epoch": 1.1075837742504409,
      "grad_norm": 0.0251897145062685,
      "learning_rate": 8.617714201998084e-07,
      "loss": 11.9246,
      "step": 471
    },
    {
      "epoch": 1.1146384479717812,
      "grad_norm": 0.020719952881336212,
      "learning_rate": 6.93088004882253e-07,
      "loss": 11.9967,
      "step": 474
    },
    {
      "epoch": 1.1216931216931216,
      "grad_norm": 0.01866576448082924,
      "learning_rate": 5.426454159531913e-07,
      "loss": 11.7563,
      "step": 477
    },
    {
      "epoch": 1.128747795414462,
      "grad_norm": 0.029010610654950142,
      "learning_rate": 4.104993088376974e-07,
      "loss": 11.9562,
      "step": 480
    },
    {
      "epoch": 1.1358024691358024,
      "grad_norm": 0.020120302215218544,
      "learning_rate": 2.966985702759828e-07,
      "loss": 12.0342,
      "step": 483
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.02001938596367836,
      "learning_rate": 2.012853002380466e-07,
      "loss": 11.7064,
      "step": 486
    },
    {
      "epoch": 1.1499118165784832,
      "grad_norm": 0.021438777446746826,
      "learning_rate": 1.2429479634897267e-07,
      "loss": 11.9928,
      "step": 489
    },
    {
      "epoch": 1.1569664902998236,
      "grad_norm": 0.016329078003764153,
      "learning_rate": 6.575554083078084e-08,
      "loss": 11.9815,
      "step": 492
    },
    {
      "epoch": 1.164021164021164,
      "grad_norm": 0.05567369982600212,
      "learning_rate": 2.568918996560532e-08,
      "loss": 11.9687,
      "step": 495
    },
    {
      "epoch": 1.1710758377425043,
      "grad_norm": 0.026132524013519287,
      "learning_rate": 4.110566084036816e-09,
      "loss": 11.8083,
      "step": 498
    }
  ],
  "logging_steps": 3,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 42,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 13720076943360.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}