{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9998824773768951,
  "eval_steps": 500,
  "global_step": 2127,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004700904924197908,
      "grad_norm": 4.338921070098877,
      "learning_rate": 9.984328475160634e-05,
      "loss": 10.2575,
      "step": 10
    },
    {
      "epoch": 0.009401809848395816,
      "grad_norm": 7.385047435760498,
      "learning_rate": 9.968656950321266e-05,
      "loss": 8.7185,
      "step": 20
    },
    {
      "epoch": 0.014102714772593724,
      "grad_norm": 8.822163581848145,
      "learning_rate": 9.9529854254819e-05,
      "loss": 6.0204,
      "step": 30
    },
    {
      "epoch": 0.018803619696791632,
      "grad_norm": 5.8417487144470215,
      "learning_rate": 9.937313900642533e-05,
      "loss": 3.0597,
      "step": 40
    },
    {
      "epoch": 0.02350452462098954,
      "grad_norm": 1.655334711074829,
      "learning_rate": 9.921642375803167e-05,
      "loss": 1.1494,
      "step": 50
    },
    {
      "epoch": 0.028205429545187448,
      "grad_norm": 1.3080294132232666,
      "learning_rate": 9.905970850963799e-05,
      "loss": 0.6757,
      "step": 60
    },
    {
      "epoch": 0.03290633446938536,
      "grad_norm": 3.848752975463867,
      "learning_rate": 9.890299326124433e-05,
      "loss": 0.6138,
      "step": 70
    },
    {
      "epoch": 0.037607239393583264,
      "grad_norm": 1.6154791116714478,
      "learning_rate": 9.874627801285066e-05,
      "loss": 0.5528,
      "step": 80
    },
    {
      "epoch": 0.042308144317781175,
      "grad_norm": 2.7457191944122314,
      "learning_rate": 9.858956276445698e-05,
      "loss": 0.5178,
      "step": 90
    },
    {
      "epoch": 0.04700904924197908,
      "grad_norm": 1.5741740465164185,
      "learning_rate": 9.843284751606332e-05,
      "loss": 0.4926,
      "step": 100
    },
    {
      "epoch": 0.05170995416617699,
      "grad_norm": 1.9329739809036255,
      "learning_rate": 9.827613226766966e-05,
      "loss": 0.5021,
      "step": 110
    },
    {
      "epoch": 0.056410859090374896,
      "grad_norm": 2.349841594696045,
      "learning_rate": 9.811941701927598e-05,
      "loss": 0.4663,
      "step": 120
    },
    {
      "epoch": 0.06111176401457281,
      "grad_norm": 1.533464789390564,
      "learning_rate": 9.796270177088231e-05,
      "loss": 0.4732,
      "step": 130
    },
    {
      "epoch": 0.06581266893877072,
      "grad_norm": 3.456256866455078,
      "learning_rate": 9.780598652248865e-05,
      "loss": 0.4624,
      "step": 140
    },
    {
      "epoch": 0.07051357386296862,
      "grad_norm": 2.1807849407196045,
      "learning_rate": 9.764927127409498e-05,
      "loss": 0.4604,
      "step": 150
    },
    {
      "epoch": 0.07521447878716653,
      "grad_norm": 2.223006010055542,
      "learning_rate": 9.74925560257013e-05,
      "loss": 0.4526,
      "step": 160
    },
    {
      "epoch": 0.07991538371136443,
      "grad_norm": 1.5491483211517334,
      "learning_rate": 9.733584077730764e-05,
      "loss": 0.4454,
      "step": 170
    },
    {
      "epoch": 0.08461628863556235,
      "grad_norm": 0.9801793694496155,
      "learning_rate": 9.717912552891398e-05,
      "loss": 0.4565,
      "step": 180
    },
    {
      "epoch": 0.08931719355976026,
      "grad_norm": 1.4270861148834229,
      "learning_rate": 9.70224102805203e-05,
      "loss": 0.4499,
      "step": 190
    },
    {
      "epoch": 0.09401809848395816,
      "grad_norm": 1.1395397186279297,
      "learning_rate": 9.686569503212663e-05,
      "loss": 0.4452,
      "step": 200
    },
    {
      "epoch": 0.09871900340815606,
      "grad_norm": 4.200931072235107,
      "learning_rate": 9.670897978373297e-05,
      "loss": 0.4351,
      "step": 210
    },
    {
      "epoch": 0.10341990833235398,
      "grad_norm": 0.9431071281433105,
      "learning_rate": 9.655226453533929e-05,
      "loss": 0.4445,
      "step": 220
    },
    {
      "epoch": 0.10812081325655189,
      "grad_norm": 1.4455124139785767,
      "learning_rate": 9.639554928694561e-05,
      "loss": 0.4287,
      "step": 230
    },
    {
      "epoch": 0.11282171818074979,
      "grad_norm": 0.823145866394043,
      "learning_rate": 9.623883403855195e-05,
      "loss": 0.4267,
      "step": 240
    },
    {
      "epoch": 0.1175226231049477,
      "grad_norm": 1.3632913827896118,
      "learning_rate": 9.608211879015829e-05,
      "loss": 0.4237,
      "step": 250
    },
    {
      "epoch": 0.12222352802914561,
      "grad_norm": 2.7535300254821777,
      "learning_rate": 9.592540354176461e-05,
      "loss": 0.4515,
      "step": 260
    },
    {
      "epoch": 0.12692443295334352,
      "grad_norm": 2.66774320602417,
      "learning_rate": 9.576868829337094e-05,
      "loss": 0.433,
      "step": 270
    },
    {
      "epoch": 0.13162533787754144,
      "grad_norm": 1.775460958480835,
      "learning_rate": 9.561197304497728e-05,
      "loss": 0.4218,
      "step": 280
    },
    {
      "epoch": 0.13632624280173933,
      "grad_norm": 0.793785810470581,
      "learning_rate": 9.545525779658361e-05,
      "loss": 0.4276,
      "step": 290
    },
    {
      "epoch": 0.14102714772593725,
      "grad_norm": 3.0376343727111816,
      "learning_rate": 9.529854254818994e-05,
      "loss": 0.4304,
      "step": 300
    },
    {
      "epoch": 0.14572805265013516,
      "grad_norm": 1.9679210186004639,
      "learning_rate": 9.514182729979627e-05,
      "loss": 0.4298,
      "step": 310
    },
    {
      "epoch": 0.15042895757433306,
      "grad_norm": 1.2378153800964355,
      "learning_rate": 9.498511205140261e-05,
      "loss": 0.4092,
      "step": 320
    },
    {
      "epoch": 0.15512986249853097,
      "grad_norm": 1.2181652784347534,
      "learning_rate": 9.482839680300893e-05,
      "loss": 0.4088,
      "step": 330
    },
    {
      "epoch": 0.15983076742272886,
      "grad_norm": 1.3195668458938599,
      "learning_rate": 9.467168155461526e-05,
      "loss": 0.4027,
      "step": 340
    },
    {
      "epoch": 0.16453167234692678,
      "grad_norm": 1.101954460144043,
      "learning_rate": 9.45149663062216e-05,
      "loss": 0.4299,
      "step": 350
    },
    {
      "epoch": 0.1692325772711247,
      "grad_norm": 3.099776029586792,
      "learning_rate": 9.435825105782794e-05,
      "loss": 0.4082,
      "step": 360
    },
    {
      "epoch": 0.1739334821953226,
      "grad_norm": 0.898208737373352,
      "learning_rate": 9.420153580943426e-05,
      "loss": 0.4148,
      "step": 370
    },
    {
      "epoch": 0.1786343871195205,
      "grad_norm": 1.2357901334762573,
      "learning_rate": 9.404482056104059e-05,
      "loss": 0.4085,
      "step": 380
    },
    {
      "epoch": 0.18333529204371843,
      "grad_norm": 1.5340213775634766,
      "learning_rate": 9.388810531264693e-05,
      "loss": 0.4186,
      "step": 390
    },
    {
      "epoch": 0.18803619696791632,
      "grad_norm": 0.8089154958724976,
      "learning_rate": 9.373139006425325e-05,
      "loss": 0.4114,
      "step": 400
    },
    {
      "epoch": 0.19273710189211424,
      "grad_norm": 1.6185780763626099,
      "learning_rate": 9.357467481585959e-05,
      "loss": 0.411,
      "step": 410
    },
    {
      "epoch": 0.19743800681631213,
      "grad_norm": 0.8345431089401245,
      "learning_rate": 9.341795956746592e-05,
      "loss": 0.41,
      "step": 420
    },
    {
      "epoch": 0.20213891174051005,
      "grad_norm": 2.1437103748321533,
      "learning_rate": 9.326124431907224e-05,
      "loss": 0.4085,
      "step": 430
    },
    {
      "epoch": 0.20683981666470797,
      "grad_norm": 6.498870372772217,
      "learning_rate": 9.310452907067858e-05,
      "loss": 0.4038,
      "step": 440
    },
    {
      "epoch": 0.21154072158890586,
      "grad_norm": 1.2205309867858887,
      "learning_rate": 9.294781382228491e-05,
      "loss": 0.4008,
      "step": 450
    },
    {
      "epoch": 0.21624162651310377,
      "grad_norm": 1.253982424736023,
      "learning_rate": 9.279109857389125e-05,
      "loss": 0.3977,
      "step": 460
    },
    {
      "epoch": 0.2209425314373017,
      "grad_norm": 3.27243971824646,
      "learning_rate": 9.263438332549757e-05,
      "loss": 0.4178,
      "step": 470
    },
    {
      "epoch": 0.22564343636149958,
      "grad_norm": 2.4955010414123535,
      "learning_rate": 9.247766807710391e-05,
      "loss": 0.3986,
      "step": 480
    },
    {
      "epoch": 0.2303443412856975,
      "grad_norm": 1.344426155090332,
      "learning_rate": 9.232095282871024e-05,
      "loss": 0.3956,
      "step": 490
    },
    {
      "epoch": 0.2350452462098954,
      "grad_norm": 1.3640114068984985,
      "learning_rate": 9.216423758031657e-05,
      "loss": 0.3976,
      "step": 500
    },
    {
      "epoch": 0.2397461511340933,
      "grad_norm": 0.8424949645996094,
      "learning_rate": 9.20075223319229e-05,
      "loss": 0.3913,
      "step": 510
    },
    {
      "epoch": 0.24444705605829123,
      "grad_norm": 1.0781666040420532,
      "learning_rate": 9.185080708352924e-05,
      "loss": 0.4075,
      "step": 520
    },
    {
      "epoch": 0.24914796098248912,
      "grad_norm": 0.9005725979804993,
      "learning_rate": 9.169409183513556e-05,
      "loss": 0.4197,
      "step": 530
    },
    {
      "epoch": 0.25384886590668704,
      "grad_norm": 1.195514440536499,
      "learning_rate": 9.15373765867419e-05,
      "loss": 0.4066,
      "step": 540
    },
    {
      "epoch": 0.25854977083088493,
      "grad_norm": 1.9088181257247925,
      "learning_rate": 9.138066133834823e-05,
      "loss": 0.4091,
      "step": 550
    },
    {
      "epoch": 0.2632506757550829,
      "grad_norm": 0.9328345060348511,
      "learning_rate": 9.122394608995457e-05,
      "loss": 0.3988,
      "step": 560
    },
    {
      "epoch": 0.26795158067928077,
      "grad_norm": 2.4227659702301025,
      "learning_rate": 9.106723084156089e-05,
      "loss": 0.391,
      "step": 570
    },
    {
      "epoch": 0.27265248560347866,
      "grad_norm": 1.7708094120025635,
      "learning_rate": 9.091051559316722e-05,
      "loss": 0.3982,
      "step": 580
    },
    {
      "epoch": 0.2773533905276766,
      "grad_norm": 1.006110668182373,
      "learning_rate": 9.075380034477356e-05,
      "loss": 0.394,
      "step": 590
    },
    {
      "epoch": 0.2820542954518745,
      "grad_norm": 0.9397707581520081,
      "learning_rate": 9.059708509637988e-05,
      "loss": 0.3898,
      "step": 600
    },
    {
      "epoch": 0.2867552003760724,
      "grad_norm": 1.3863813877105713,
      "learning_rate": 9.044036984798622e-05,
      "loss": 0.3898,
      "step": 610
    },
    {
      "epoch": 0.29145610530027033,
      "grad_norm": 1.7617021799087524,
      "learning_rate": 9.028365459959255e-05,
      "loss": 0.3957,
      "step": 620
    },
    {
      "epoch": 0.2961570102244682,
      "grad_norm": 1.261723518371582,
      "learning_rate": 9.012693935119887e-05,
      "loss": 0.3964,
      "step": 630
    },
    {
      "epoch": 0.3008579151486661,
      "grad_norm": 0.7548590302467346,
      "learning_rate": 8.997022410280521e-05,
      "loss": 0.3995,
      "step": 640
    },
    {
      "epoch": 0.305558820072864,
      "grad_norm": 1.4837889671325684,
      "learning_rate": 8.981350885441154e-05,
      "loss": 0.3729,
      "step": 650
    },
    {
      "epoch": 0.31025972499706195,
      "grad_norm": 1.868475317955017,
      "learning_rate": 8.965679360601788e-05,
      "loss": 0.3701,
      "step": 660
    },
    {
      "epoch": 0.31496062992125984,
      "grad_norm": 0.9629729390144348,
      "learning_rate": 8.95000783576242e-05,
      "loss": 0.399,
      "step": 670
    },
    {
      "epoch": 0.31966153484545773,
      "grad_norm": 1.5730236768722534,
      "learning_rate": 8.934336310923054e-05,
      "loss": 0.3854,
      "step": 680
    },
    {
      "epoch": 0.3243624397696557,
      "grad_norm": 1.4589276313781738,
      "learning_rate": 8.918664786083686e-05,
      "loss": 0.3879,
      "step": 690
    },
    {
      "epoch": 0.32906334469385357,
      "grad_norm": 4.129764080047607,
      "learning_rate": 8.90299326124432e-05,
      "loss": 0.3868,
      "step": 700
    },
    {
      "epoch": 0.33376424961805146,
      "grad_norm": 1.2538539171218872,
      "learning_rate": 8.887321736404952e-05,
      "loss": 0.4014,
      "step": 710
    },
    {
      "epoch": 0.3384651545422494,
      "grad_norm": 2.5101168155670166,
      "learning_rate": 8.871650211565585e-05,
      "loss": 0.3855,
      "step": 720
    },
    {
      "epoch": 0.3431660594664473,
      "grad_norm": 2.11893630027771,
      "learning_rate": 8.855978686726219e-05,
      "loss": 0.3847,
      "step": 730
    },
    {
      "epoch": 0.3478669643906452,
      "grad_norm": 2.154590129852295,
      "learning_rate": 8.840307161886851e-05,
      "loss": 0.3726,
      "step": 740
    },
    {
      "epoch": 0.35256786931484313,
      "grad_norm": 0.9320923686027527,
      "learning_rate": 8.824635637047485e-05,
      "loss": 0.3876,
      "step": 750
    },
    {
      "epoch": 0.357268774239041,
      "grad_norm": 1.1086455583572388,
      "learning_rate": 8.808964112208118e-05,
      "loss": 0.3813,
      "step": 760
    },
    {
      "epoch": 0.3619696791632389,
      "grad_norm": 1.0036139488220215,
      "learning_rate": 8.793292587368752e-05,
      "loss": 0.3802,
      "step": 770
    },
    {
      "epoch": 0.36667058408743686,
      "grad_norm": 1.2812787294387817,
      "learning_rate": 8.777621062529384e-05,
      "loss": 0.383,
      "step": 780
    },
    {
      "epoch": 0.37137148901163475,
      "grad_norm": 1.9546316862106323,
      "learning_rate": 8.761949537690017e-05,
      "loss": 0.3775,
      "step": 790
    },
    {
      "epoch": 0.37607239393583264,
      "grad_norm": 0.9139639139175415,
      "learning_rate": 8.746278012850651e-05,
      "loss": 0.3725,
      "step": 800
    },
    {
      "epoch": 0.38077329886003053,
      "grad_norm": 1.282999038696289,
      "learning_rate": 8.730606488011283e-05,
      "loss": 0.382,
      "step": 810
    },
    {
      "epoch": 0.3854742037842285,
      "grad_norm": 1.0331751108169556,
      "learning_rate": 8.714934963171917e-05,
      "loss": 0.3765,
      "step": 820
    },
    {
      "epoch": 0.39017510870842637,
      "grad_norm": 3.0494372844696045,
      "learning_rate": 8.69926343833255e-05,
      "loss": 0.3773,
      "step": 830
    },
    {
      "epoch": 0.39487601363262426,
      "grad_norm": 1.0024981498718262,
      "learning_rate": 8.683591913493183e-05,
      "loss": 0.3889,
      "step": 840
    },
    {
      "epoch": 0.3995769185568222,
      "grad_norm": 1.606170892715454,
      "learning_rate": 8.667920388653816e-05,
      "loss": 0.3585,
      "step": 850
    },
    {
      "epoch": 0.4042778234810201,
      "grad_norm": 1.0149178504943848,
      "learning_rate": 8.65224886381445e-05,
      "loss": 0.3893,
      "step": 860
    },
    {
      "epoch": 0.408978728405218,
      "grad_norm": 1.744429588317871,
      "learning_rate": 8.636577338975083e-05,
      "loss": 0.3788,
      "step": 870
    },
    {
      "epoch": 0.41367963332941593,
      "grad_norm": 2.3995683193206787,
      "learning_rate": 8.620905814135715e-05,
      "loss": 0.3594,
      "step": 880
    },
    {
      "epoch": 0.4183805382536138,
      "grad_norm": 2.227412700653076,
      "learning_rate": 8.605234289296349e-05,
      "loss": 0.3853,
      "step": 890
    },
    {
      "epoch": 0.4230814431778117,
      "grad_norm": 1.6415226459503174,
      "learning_rate": 8.589562764456982e-05,
      "loss": 0.3835,
      "step": 900
    },
    {
      "epoch": 0.42778234810200966,
      "grad_norm": 1.140038251876831,
      "learning_rate": 8.573891239617615e-05,
      "loss": 0.3742,
      "step": 910
    },
    {
      "epoch": 0.43248325302620755,
      "grad_norm": 2.5346789360046387,
      "learning_rate": 8.558219714778248e-05,
      "loss": 0.3886,
      "step": 920
    },
    {
      "epoch": 0.43718415795040544,
      "grad_norm": 1.060520887374878,
      "learning_rate": 8.542548189938882e-05,
      "loss": 0.3852,
      "step": 930
    },
    {
      "epoch": 0.4418850628746034,
      "grad_norm": 2.0687763690948486,
      "learning_rate": 8.526876665099514e-05,
      "loss": 0.3782,
      "step": 940
    },
    {
      "epoch": 0.4465859677988013,
      "grad_norm": 3.9409232139587402,
      "learning_rate": 8.511205140260148e-05,
      "loss": 0.3907,
      "step": 950
    },
    {
      "epoch": 0.45128687272299917,
      "grad_norm": 2.1936776638031006,
      "learning_rate": 8.495533615420781e-05,
      "loss": 0.3758,
      "step": 960
    },
    {
      "epoch": 0.4559877776471971,
      "grad_norm": 0.9638668298721313,
      "learning_rate": 8.479862090581415e-05,
      "loss": 0.3812,
      "step": 970
    },
    {
      "epoch": 0.460688682571395,
      "grad_norm": 1.0724684000015259,
      "learning_rate": 8.464190565742047e-05,
      "loss": 0.3649,
      "step": 980
    },
    {
      "epoch": 0.4653895874955929,
      "grad_norm": 1.2330756187438965,
      "learning_rate": 8.44851904090268e-05,
      "loss": 0.3878,
      "step": 990
    },
    {
      "epoch": 0.4700904924197908,
      "grad_norm": 1.3528395891189575,
      "learning_rate": 8.432847516063314e-05,
      "loss": 0.3795,
      "step": 1000
    },
    {
      "epoch": 0.47479139734398873,
      "grad_norm": 1.3239601850509644,
      "learning_rate": 8.417175991223946e-05,
      "loss": 0.3881,
      "step": 1010
    },
    {
      "epoch": 0.4794923022681866,
      "grad_norm": 0.8255568146705627,
      "learning_rate": 8.40150446638458e-05,
      "loss": 0.3712,
      "step": 1020
    },
    {
      "epoch": 0.4841932071923845,
      "grad_norm": 1.9237899780273438,
      "learning_rate": 8.385832941545213e-05,
      "loss": 0.3652,
      "step": 1030
    },
    {
      "epoch": 0.48889411211658246,
      "grad_norm": 1.6184757947921753,
      "learning_rate": 8.370161416705847e-05,
      "loss": 0.3646,
      "step": 1040
    },
    {
      "epoch": 0.49359501704078035,
      "grad_norm": 1.17612886428833,
      "learning_rate": 8.354489891866479e-05,
      "loss": 0.3751,
      "step": 1050
    },
    {
      "epoch": 0.49829592196497824,
      "grad_norm": 1.3280194997787476,
      "learning_rate": 8.338818367027113e-05,
      "loss": 0.3873,
      "step": 1060
    },
    {
      "epoch": 0.5029968268891761,
      "grad_norm": 1.4673656225204468,
      "learning_rate": 8.323146842187746e-05,
      "loss": 0.3651,
      "step": 1070
    },
    {
      "epoch": 0.5076977318133741,
      "grad_norm": 1.5769989490509033,
      "learning_rate": 8.307475317348378e-05,
      "loss": 0.3751,
      "step": 1080
    },
    {
      "epoch": 0.512398636737572,
      "grad_norm": 3.041260242462158,
      "learning_rate": 8.291803792509012e-05,
      "loss": 0.3754,
      "step": 1090
    },
    {
      "epoch": 0.5170995416617699,
      "grad_norm": 0.922623336315155,
      "learning_rate": 8.276132267669645e-05,
      "loss": 0.3722,
      "step": 1100
    },
    {
      "epoch": 0.5218004465859678,
      "grad_norm": 0.8527415990829468,
      "learning_rate": 8.260460742830278e-05,
      "loss": 0.3816,
      "step": 1110
    },
    {
      "epoch": 0.5265013515101657,
      "grad_norm": 1.1660065650939941,
      "learning_rate": 8.244789217990911e-05,
      "loss": 0.3844,
      "step": 1120
    },
    {
      "epoch": 0.5312022564343636,
      "grad_norm": 2.7265124320983887,
      "learning_rate": 8.229117693151545e-05,
      "loss": 0.3579,
      "step": 1130
    },
    {
      "epoch": 0.5359031613585615,
      "grad_norm": 0.9204573035240173,
      "learning_rate": 8.213446168312177e-05,
      "loss": 0.3848,
      "step": 1140
    },
    {
      "epoch": 0.5406040662827595,
      "grad_norm": 1.0934752225875854,
      "learning_rate": 8.197774643472809e-05,
      "loss": 0.3652,
      "step": 1150
    },
    {
      "epoch": 0.5453049712069573,
      "grad_norm": 0.9822810888290405,
      "learning_rate": 8.182103118633443e-05,
      "loss": 0.3784,
      "step": 1160
    },
    {
      "epoch": 0.5500058761311553,
      "grad_norm": 1.0165129899978638,
      "learning_rate": 8.166431593794076e-05,
      "loss": 0.3728,
      "step": 1170
    },
    {
      "epoch": 0.5547067810553532,
      "grad_norm": 1.2013338804244995,
      "learning_rate": 8.15076006895471e-05,
      "loss": 0.3552,
      "step": 1180
    },
    {
      "epoch": 0.559407685979551,
      "grad_norm": 1.170253872871399,
      "learning_rate": 8.135088544115342e-05,
      "loss": 0.3725,
      "step": 1190
    },
    {
      "epoch": 0.564108590903749,
      "grad_norm": 0.8883313536643982,
      "learning_rate": 8.119417019275976e-05,
      "loss": 0.3504,
      "step": 1200
    },
    {
      "epoch": 0.5688094958279469,
      "grad_norm": 2.107287883758545,
      "learning_rate": 8.103745494436609e-05,
      "loss": 0.3586,
      "step": 1210
    },
    {
      "epoch": 0.5735104007521448,
      "grad_norm": 1.9556785821914673,
      "learning_rate": 8.088073969597241e-05,
      "loss": 0.3596,
      "step": 1220
    },
    {
      "epoch": 0.5782113056763427,
      "grad_norm": 1.024415373802185,
      "learning_rate": 8.072402444757875e-05,
      "loss": 0.3642,
      "step": 1230
    },
    {
      "epoch": 0.5829122106005407,
      "grad_norm": 3.524789333343506,
      "learning_rate": 8.056730919918508e-05,
      "loss": 0.3695,
      "step": 1240
    },
    {
      "epoch": 0.5876131155247385,
      "grad_norm": 1.3371467590332031,
      "learning_rate": 8.04105939507914e-05,
      "loss": 0.3736,
      "step": 1250
    },
    {
      "epoch": 0.5923140204489364,
      "grad_norm": 1.91169011592865,
      "learning_rate": 8.025387870239774e-05,
      "loss": 0.3653,
      "step": 1260
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 0.9362313747406006,
      "learning_rate": 8.009716345400408e-05,
      "loss": 0.3813,
      "step": 1270
    },
    {
      "epoch": 0.6017158302973322,
      "grad_norm": 2.3379788398742676,
      "learning_rate": 7.994044820561041e-05,
      "loss": 0.3606,
      "step": 1280
    },
    {
      "epoch": 0.6064167352215302,
      "grad_norm": 1.9221323728561401,
      "learning_rate": 7.978373295721674e-05,
      "loss": 0.3706,
      "step": 1290
    },
    {
      "epoch": 0.611117640145728,
      "grad_norm": 2.1025121212005615,
      "learning_rate": 7.962701770882307e-05,
      "loss": 0.3585,
      "step": 1300
    },
    {
      "epoch": 0.615818545069926,
      "grad_norm": 1.7160892486572266,
      "learning_rate": 7.94703024604294e-05,
      "loss": 0.3849,
      "step": 1310
    },
    {
      "epoch": 0.6205194499941239,
      "grad_norm": 1.290818691253662,
      "learning_rate": 7.931358721203573e-05,
      "loss": 0.377,
      "step": 1320
    },
    {
      "epoch": 0.6252203549183217,
      "grad_norm": 0.9813281297683716,
      "learning_rate": 7.915687196364206e-05,
      "loss": 0.365,
      "step": 1330
    },
    {
      "epoch": 0.6299212598425197,
      "grad_norm": 0.9623616933822632,
      "learning_rate": 7.90001567152484e-05,
      "loss": 0.3496,
      "step": 1340
    },
    {
      "epoch": 0.6346221647667176,
      "grad_norm": 1.3078798055648804,
      "learning_rate": 7.884344146685473e-05,
      "loss": 0.3643,
      "step": 1350
    },
    {
      "epoch": 0.6393230696909155,
      "grad_norm": 0.9925209879875183,
      "learning_rate": 7.868672621846106e-05,
      "loss": 0.3608,
      "step": 1360
    },
    {
      "epoch": 0.6440239746151134,
      "grad_norm": 1.515331745147705,
      "learning_rate": 7.853001097006739e-05,
      "loss": 0.388,
      "step": 1370
    },
    {
      "epoch": 0.6487248795393113,
      "grad_norm": 2.109877586364746,
      "learning_rate": 7.837329572167373e-05,
      "loss": 0.3605,
      "step": 1380
    },
    {
      "epoch": 0.6534257844635092,
      "grad_norm": 1.320446491241455,
      "learning_rate": 7.821658047328005e-05,
      "loss": 0.3729,
      "step": 1390
    },
    {
      "epoch": 0.6581266893877071,
      "grad_norm": 1.2624431848526,
      "learning_rate": 7.805986522488639e-05,
      "loss": 0.3637,
      "step": 1400
    },
    {
      "epoch": 0.6628275943119051,
      "grad_norm": 1.3101025819778442,
      "learning_rate": 7.790314997649272e-05,
      "loss": 0.3738,
      "step": 1410
    },
    {
      "epoch": 0.6675284992361029,
      "grad_norm": 1.3762035369873047,
      "learning_rate": 7.774643472809904e-05,
      "loss": 0.364,
      "step": 1420
    },
    {
      "epoch": 0.6722294041603009,
      "grad_norm": 1.7407734394073486,
      "learning_rate": 7.758971947970538e-05,
      "loss": 0.3405,
      "step": 1430
    },
    {
      "epoch": 0.6769303090844988,
      "grad_norm": 1.209085464477539,
      "learning_rate": 7.743300423131171e-05,
      "loss": 0.3621,
      "step": 1440
    },
    {
      "epoch": 0.6816312140086966,
      "grad_norm": 2.3257131576538086,
      "learning_rate": 7.727628898291805e-05,
      "loss": 0.3524,
      "step": 1450
    },
    {
      "epoch": 0.6863321189328946,
      "grad_norm": 1.5234692096710205,
      "learning_rate": 7.711957373452437e-05,
      "loss": 0.3556,
      "step": 1460
    },
    {
      "epoch": 0.6910330238570925,
      "grad_norm": 2.3267507553100586,
      "learning_rate": 7.696285848613071e-05,
      "loss": 0.3589,
      "step": 1470
    },
    {
      "epoch": 0.6957339287812904,
      "grad_norm": 1.8741614818572998,
      "learning_rate": 7.680614323773704e-05,
      "loss": 0.3651,
      "step": 1480
    },
    {
      "epoch": 0.7004348337054883,
      "grad_norm": 2.3814918994903564,
      "learning_rate": 7.664942798934336e-05,
      "loss": 0.3568,
      "step": 1490
    },
    {
      "epoch": 0.7051357386296863,
      "grad_norm": 3.497832775115967,
      "learning_rate": 7.64927127409497e-05,
      "loss": 0.3723,
      "step": 1500
    },
    {
      "epoch": 0.7098366435538841,
      "grad_norm": 2.1036434173583984,
      "learning_rate": 7.633599749255604e-05,
      "loss": 0.3708,
      "step": 1510
    },
    {
      "epoch": 0.714537548478082,
      "grad_norm": 2.3688840866088867,
      "learning_rate": 7.617928224416236e-05,
      "loss": 0.3673,
      "step": 1520
    },
    {
      "epoch": 0.71923845340228,
      "grad_norm": 1.6410322189331055,
      "learning_rate": 7.60225669957687e-05,
      "loss": 0.3727,
      "step": 1530
    },
    {
      "epoch": 0.7239393583264778,
      "grad_norm": 1.0293692350387573,
      "learning_rate": 7.586585174737503e-05,
      "loss": 0.3751,
      "step": 1540
    },
    {
      "epoch": 0.7286402632506758,
      "grad_norm": 1.794756293296814,
      "learning_rate": 7.570913649898136e-05,
      "loss": 0.3612,
      "step": 1550
    },
    {
      "epoch": 0.7333411681748737,
      "grad_norm": 2.0058727264404297,
      "learning_rate": 7.555242125058769e-05,
      "loss": 0.3734,
      "step": 1560
    },
    {
      "epoch": 0.7380420730990715,
      "grad_norm": 1.8430676460266113,
      "learning_rate": 7.539570600219402e-05,
      "loss": 0.3533,
      "step": 1570
    },
    {
      "epoch": 0.7427429780232695,
      "grad_norm": 1.2136273384094238,
      "learning_rate": 7.523899075380036e-05,
      "loss": 0.3398,
      "step": 1580
    },
    {
      "epoch": 0.7474438829474674,
      "grad_norm": 0.9999972581863403,
      "learning_rate": 7.508227550540668e-05,
      "loss": 0.3322,
      "step": 1590
    },
    {
      "epoch": 0.7521447878716653,
      "grad_norm": 1.4663593769073486,
      "learning_rate": 7.4925560257013e-05,
      "loss": 0.3588,
      "step": 1600
    },
    {
      "epoch": 0.7568456927958632,
      "grad_norm": 0.8715286254882812,
      "learning_rate": 7.476884500861934e-05,
      "loss": 0.3566,
      "step": 1610
    },
    {
      "epoch": 0.7615465977200611,
      "grad_norm": 1.7180976867675781,
      "learning_rate": 7.461212976022567e-05,
      "loss": 0.3544,
      "step": 1620
    },
    {
      "epoch": 0.766247502644259,
      "grad_norm": 2.3892838954925537,
      "learning_rate": 7.4455414511832e-05,
      "loss": 0.3537,
      "step": 1630
    },
    {
      "epoch": 0.770948407568457,
      "grad_norm": 1.2725646495819092,
      "learning_rate": 7.429869926343833e-05,
      "loss": 0.3575,
      "step": 1640
    },
    {
      "epoch": 0.7756493124926548,
      "grad_norm": 1.1861917972564697,
      "learning_rate": 7.414198401504467e-05,
      "loss": 0.3588,
      "step": 1650
    },
    {
      "epoch": 0.7803502174168527,
      "grad_norm": 1.6121189594268799,
      "learning_rate": 7.398526876665099e-05,
      "loss": 0.3554,
      "step": 1660
    },
    {
      "epoch": 0.7850511223410507,
      "grad_norm": 1.183447003364563,
      "learning_rate": 7.382855351825732e-05,
      "loss": 0.3399,
      "step": 1670
    },
    {
      "epoch": 0.7897520272652485,
      "grad_norm": 0.9614543318748474,
      "learning_rate": 7.367183826986366e-05,
      "loss": 0.3505,
      "step": 1680
    },
    {
      "epoch": 0.7944529321894465,
      "grad_norm": 2.463824510574341,
      "learning_rate": 7.351512302147e-05,
      "loss": 0.3535,
      "step": 1690
    },
    {
      "epoch": 0.7991538371136444,
      "grad_norm": 1.1036416292190552,
      "learning_rate": 7.335840777307632e-05,
      "loss": 0.3492,
      "step": 1700
    },
    {
      "epoch": 0.8038547420378422,
      "grad_norm": 1.4613536596298218,
      "learning_rate": 7.320169252468265e-05,
      "loss": 0.351,
      "step": 1710
    },
    {
      "epoch": 0.8085556469620402,
      "grad_norm": 1.2614613771438599,
      "learning_rate": 7.304497727628899e-05,
      "loss": 0.3505,
      "step": 1720
    },
    {
      "epoch": 0.8132565518862381,
      "grad_norm": 1.1639400720596313,
      "learning_rate": 7.288826202789531e-05,
      "loss": 0.3657,
      "step": 1730
    },
    {
      "epoch": 0.817957456810436,
      "grad_norm": 1.6838788986206055,
      "learning_rate": 7.273154677950165e-05,
      "loss": 0.3503,
      "step": 1740
    },
    {
      "epoch": 0.8226583617346339,
      "grad_norm": 1.0945839881896973,
      "learning_rate": 7.257483153110798e-05,
      "loss": 0.3551,
      "step": 1750
    },
    {
      "epoch": 0.8273592666588319,
      "grad_norm": 1.1545921564102173,
      "learning_rate": 7.241811628271432e-05,
      "loss": 0.3488,
      "step": 1760
    },
    {
      "epoch": 0.8320601715830297,
      "grad_norm": 0.9361588954925537,
      "learning_rate": 7.226140103432064e-05,
      "loss": 0.3454,
      "step": 1770
    },
    {
      "epoch": 0.8367610765072276,
      "grad_norm": 0.959794819355011,
      "learning_rate": 7.210468578592697e-05,
      "loss": 0.3571,
      "step": 1780
    },
    {
      "epoch": 0.8414619814314256,
      "grad_norm": 1.1152044534683228,
      "learning_rate": 7.194797053753331e-05,
      "loss": 0.3713,
      "step": 1790
    },
    {
      "epoch": 0.8461628863556234,
      "grad_norm": 1.7348166704177856,
      "learning_rate": 7.179125528913963e-05,
      "loss": 0.3407,
      "step": 1800
    },
    {
      "epoch": 0.8508637912798214,
      "grad_norm": 2.3188705444335938,
      "learning_rate": 7.163454004074597e-05,
      "loss": 0.3489,
      "step": 1810
    },
    {
      "epoch": 0.8555646962040193,
      "grad_norm": 1.529905915260315,
      "learning_rate": 7.14778247923523e-05,
      "loss": 0.3385,
      "step": 1820
    },
    {
      "epoch": 0.8602656011282171,
      "grad_norm": 1.2101613283157349,
      "learning_rate": 7.132110954395862e-05,
      "loss": 0.355,
      "step": 1830
    },
    {
      "epoch": 0.8649665060524151,
      "grad_norm": 1.4338616132736206,
      "learning_rate": 7.116439429556496e-05,
      "loss": 0.3534,
      "step": 1840
    },
    {
      "epoch": 0.869667410976613,
      "grad_norm": 1.2460179328918457,
      "learning_rate": 7.10076790471713e-05,
      "loss": 0.3537,
      "step": 1850
    },
    {
      "epoch": 0.8743683159008109,
      "grad_norm": 1.6369551420211792,
      "learning_rate": 7.085096379877763e-05,
      "loss": 0.3514,
      "step": 1860
    },
    {
      "epoch": 0.8790692208250088,
      "grad_norm": 2.6983251571655273,
      "learning_rate": 7.069424855038395e-05,
      "loss": 0.348,
      "step": 1870
    },
    {
      "epoch": 0.8837701257492068,
      "grad_norm": 1.2817703485488892,
      "learning_rate": 7.053753330199029e-05,
      "loss": 0.3505,
      "step": 1880
    },
    {
      "epoch": 0.8884710306734046,
      "grad_norm": 1.0121359825134277,
      "learning_rate": 7.038081805359662e-05,
      "loss": 0.344,
      "step": 1890
    },
    {
      "epoch": 0.8931719355976026,
      "grad_norm": 0.9417720437049866,
      "learning_rate": 7.022410280520295e-05,
      "loss": 0.3462,
      "step": 1900
    },
    {
      "epoch": 0.8978728405218005,
      "grad_norm": 1.0144025087356567,
      "learning_rate": 7.006738755680928e-05,
      "loss": 0.3416,
      "step": 1910
    },
    {
      "epoch": 0.9025737454459983,
      "grad_norm": 2.533620834350586,
      "learning_rate": 6.991067230841562e-05,
      "loss": 0.3543,
      "step": 1920
    },
    {
      "epoch": 0.9072746503701963,
      "grad_norm": 1.5756601095199585,
      "learning_rate": 6.975395706002194e-05,
      "loss": 0.368,
      "step": 1930
    },
    {
      "epoch": 0.9119755552943942,
      "grad_norm": 1.2900676727294922,
      "learning_rate": 6.959724181162828e-05,
      "loss": 0.3368,
      "step": 1940
    },
    {
      "epoch": 0.9166764602185921,
      "grad_norm": 1.2235045433044434,
      "learning_rate": 6.944052656323461e-05,
      "loss": 0.3428,
      "step": 1950
    },
    {
      "epoch": 0.92137736514279,
      "grad_norm": 1.0844625234603882,
      "learning_rate": 6.928381131484095e-05,
      "loss": 0.365,
      "step": 1960
    },
    {
      "epoch": 0.9260782700669878,
      "grad_norm": 2.585019588470459,
      "learning_rate": 6.912709606644727e-05,
      "loss": 0.3394,
      "step": 1970
    },
    {
      "epoch": 0.9307791749911858,
      "grad_norm": 1.402716040611267,
      "learning_rate": 6.89703808180536e-05,
      "loss": 0.3513,
      "step": 1980
    },
    {
      "epoch": 0.9354800799153837,
      "grad_norm": 1.6604111194610596,
      "learning_rate": 6.881366556965994e-05,
      "loss": 0.3514,
      "step": 1990
    },
    {
      "epoch": 0.9401809848395816,
      "grad_norm": 1.0885512828826904,
      "learning_rate": 6.865695032126626e-05,
      "loss": 0.3504,
      "step": 2000
    },
    {
      "epoch": 0.9448818897637795,
      "grad_norm": 3.016390562057495,
      "learning_rate": 6.85002350728726e-05,
      "loss": 0.3607,
      "step": 2010
    },
    {
      "epoch": 0.9495827946879775,
      "grad_norm": 1.5509752035140991,
      "learning_rate": 6.834351982447893e-05,
      "loss": 0.3373,
      "step": 2020
    },
    {
      "epoch": 0.9542836996121753,
      "grad_norm": 1.8190217018127441,
      "learning_rate": 6.818680457608527e-05,
      "loss": 0.3412,
      "step": 2030
    },
    {
      "epoch": 0.9589846045363732,
      "grad_norm": 2.373183250427246,
      "learning_rate": 6.803008932769159e-05,
      "loss": 0.3455,
      "step": 2040
    },
    {
      "epoch": 0.9636855094605712,
      "grad_norm": 1.4944651126861572,
      "learning_rate": 6.787337407929793e-05,
      "loss": 0.3467,
      "step": 2050
    },
    {
      "epoch": 0.968386414384769,
      "grad_norm": 2.2049689292907715,
      "learning_rate": 6.771665883090425e-05,
      "loss": 0.3552,
      "step": 2060
    },
    {
      "epoch": 0.973087319308967,
      "grad_norm": 1.044244647026062,
      "learning_rate": 6.755994358251058e-05,
      "loss": 0.3475,
      "step": 2070
    },
    {
      "epoch": 0.9777882242331649,
      "grad_norm": 1.0703078508377075,
      "learning_rate": 6.74032283341169e-05,
      "loss": 0.3424,
      "step": 2080
    },
    {
      "epoch": 0.9824891291573628,
      "grad_norm": 1.2599198818206787,
      "learning_rate": 6.724651308572324e-05,
      "loss": 0.3513,
      "step": 2090
    },
    {
      "epoch": 0.9871900340815607,
      "grad_norm": 0.9976306557655334,
      "learning_rate": 6.708979783732958e-05,
      "loss": 0.3499,
      "step": 2100
    },
    {
      "epoch": 0.9918909390057586,
      "grad_norm": 1.1676925420761108,
      "learning_rate": 6.69330825889359e-05,
      "loss": 0.3362,
      "step": 2110
    },
    {
      "epoch": 0.9965918439299565,
      "grad_norm": 1.5144907236099243,
      "learning_rate": 6.677636734054223e-05,
      "loss": 0.3323,
      "step": 2120
    }
  ],
  "logging_steps": 10,
  "max_steps": 6381,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.7331697868700385e+19,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}