{
  "best_global_step": 4700,
  "best_metric": 0.7582268714904785,
  "best_model_checkpoint": "task2file/sft_qwen_14B_v2/checkpoints/checkpoint-4500",
  "epoch": 2.109704641350211,
  "eval_steps": 100,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008438818565400844,
      "grad_norm": 0.5386583805084229,
      "learning_rate": 1.7574692442882248e-07,
      "loss": 1.6941628456115723,
      "step": 2
    },
    {
      "epoch": 0.0016877637130801688,
      "grad_norm": 0.5477277636528015,
      "learning_rate": 5.272407732864675e-07,
      "loss": 1.7132279872894287,
      "step": 4
    },
    {
      "epoch": 0.002531645569620253,
      "grad_norm": 0.5390765070915222,
      "learning_rate": 8.787346221441126e-07,
      "loss": 1.641180396080017,
      "step": 6
    },
    {
      "epoch": 0.0033755274261603376,
      "grad_norm": 0.5023683905601501,
      "learning_rate": 1.2302284710017575e-06,
      "loss": 1.5616240501403809,
      "step": 8
    },
    {
      "epoch": 0.004219409282700422,
      "grad_norm": 0.4899154603481293,
      "learning_rate": 1.5817223198594026e-06,
      "loss": 1.572033405303955,
      "step": 10
    },
    {
      "epoch": 0.005063291139240506,
      "grad_norm": 0.5239788293838501,
      "learning_rate": 1.9332161687170474e-06,
      "loss": 1.6242921352386475,
      "step": 12
    },
    {
      "epoch": 0.00590717299578059,
      "grad_norm": 0.5172926783561707,
      "learning_rate": 2.2847100175746925e-06,
      "loss": 1.6800041198730469,
      "step": 14
    },
    {
      "epoch": 0.006751054852320675,
      "grad_norm": 0.5539224743843079,
      "learning_rate": 2.6362038664323376e-06,
      "loss": 1.6450834274291992,
      "step": 16
    },
    {
      "epoch": 0.007594936708860759,
      "grad_norm": 0.5255337953567505,
      "learning_rate": 2.9876977152899827e-06,
      "loss": 1.6673263311386108,
      "step": 18
    },
    {
      "epoch": 0.008438818565400843,
      "grad_norm": 0.5074548721313477,
      "learning_rate": 3.3391915641476277e-06,
      "loss": 1.531802773475647,
      "step": 20
    },
    {
      "epoch": 0.009282700421940928,
      "grad_norm": 0.4160279333591461,
      "learning_rate": 3.6906854130052724e-06,
      "loss": 1.599354863166809,
      "step": 22
    },
    {
      "epoch": 0.010126582278481013,
      "grad_norm": 0.5716474652290344,
      "learning_rate": 4.0421792618629174e-06,
      "loss": 1.6700962781906128,
      "step": 24
    },
    {
      "epoch": 0.010970464135021098,
      "grad_norm": 0.5148899555206299,
      "learning_rate": 4.3936731107205625e-06,
      "loss": 1.66217839717865,
      "step": 26
    },
    {
      "epoch": 0.01181434599156118,
      "grad_norm": 0.575722336769104,
      "learning_rate": 4.7451669595782076e-06,
      "loss": 1.6692266464233398,
      "step": 28
    },
    {
      "epoch": 0.012658227848101266,
      "grad_norm": 0.5345953106880188,
      "learning_rate": 5.096660808435853e-06,
      "loss": 1.5518689155578613,
      "step": 30
    },
    {
      "epoch": 0.01350210970464135,
      "grad_norm": 0.4462043344974518,
      "learning_rate": 5.448154657293498e-06,
      "loss": 1.5930007696151733,
      "step": 32
    },
    {
      "epoch": 0.014345991561181435,
      "grad_norm": 0.5119605660438538,
      "learning_rate": 5.799648506151143e-06,
      "loss": 1.6069684028625488,
      "step": 34
    },
    {
      "epoch": 0.015189873417721518,
      "grad_norm": 0.5328608751296997,
      "learning_rate": 6.151142355008788e-06,
      "loss": 1.5838109254837036,
      "step": 36
    },
    {
      "epoch": 0.016033755274261603,
      "grad_norm": 0.5065920352935791,
      "learning_rate": 6.502636203866433e-06,
      "loss": 1.608130931854248,
      "step": 38
    },
    {
      "epoch": 0.016877637130801686,
      "grad_norm": 0.4479359984397888,
      "learning_rate": 6.854130052724078e-06,
      "loss": 1.5942182540893555,
      "step": 40
    },
    {
      "epoch": 0.017721518987341773,
      "grad_norm": 0.42844903469085693,
      "learning_rate": 7.205623901581722e-06,
      "loss": 1.6441553831100464,
      "step": 42
    },
    {
      "epoch": 0.018565400843881856,
      "grad_norm": 0.476630836725235,
      "learning_rate": 7.557117750439367e-06,
      "loss": 1.6068111658096313,
      "step": 44
    },
    {
      "epoch": 0.019409282700421943,
      "grad_norm": 0.4532654881477356,
      "learning_rate": 7.908611599297012e-06,
      "loss": 1.6618021726608276,
      "step": 46
    },
    {
      "epoch": 0.020253164556962026,
      "grad_norm": 0.3701118230819702,
      "learning_rate": 8.260105448154657e-06,
      "loss": 1.4730033874511719,
      "step": 48
    },
    {
      "epoch": 0.02109704641350211,
      "grad_norm": 0.38471561670303345,
      "learning_rate": 8.611599297012302e-06,
      "loss": 1.4828267097473145,
      "step": 50
    },
    {
      "epoch": 0.021940928270042195,
      "grad_norm": 0.3602336347103119,
      "learning_rate": 8.963093145869948e-06,
      "loss": 1.3877452611923218,
      "step": 52
    },
    {
      "epoch": 0.02278481012658228,
      "grad_norm": 0.40318572521209717,
      "learning_rate": 9.314586994727593e-06,
      "loss": 1.49052894115448,
      "step": 54
    },
    {
      "epoch": 0.02362869198312236,
      "grad_norm": 0.3223826587200165,
      "learning_rate": 9.666080843585238e-06,
      "loss": 1.4912524223327637,
      "step": 56
    },
    {
      "epoch": 0.024472573839662448,
      "grad_norm": 0.3873065114021301,
      "learning_rate": 1.0017574692442883e-05,
      "loss": 1.526674509048462,
      "step": 58
    },
    {
      "epoch": 0.02531645569620253,
      "grad_norm": 0.410159707069397,
      "learning_rate": 1.0369068541300528e-05,
      "loss": 1.4480271339416504,
      "step": 60
    },
    {
      "epoch": 0.026160337552742614,
      "grad_norm": 0.3632003962993622,
      "learning_rate": 1.0720562390158173e-05,
      "loss": 1.4222990274429321,
      "step": 62
    },
    {
      "epoch": 0.0270042194092827,
      "grad_norm": 0.33118435740470886,
      "learning_rate": 1.1072056239015818e-05,
      "loss": 1.387171745300293,
      "step": 64
    },
    {
      "epoch": 0.027848101265822784,
      "grad_norm": 0.3301764726638794,
      "learning_rate": 1.1423550087873463e-05,
      "loss": 1.3523777723312378,
      "step": 66
    },
    {
      "epoch": 0.02869198312236287,
      "grad_norm": 0.34342435002326965,
      "learning_rate": 1.1775043936731108e-05,
      "loss": 1.4515162706375122,
      "step": 68
    },
    {
      "epoch": 0.029535864978902954,
      "grad_norm": 0.3243122100830078,
      "learning_rate": 1.2126537785588753e-05,
      "loss": 1.3509243726730347,
      "step": 70
    },
    {
      "epoch": 0.030379746835443037,
      "grad_norm": 0.3450150787830353,
      "learning_rate": 1.2478031634446398e-05,
      "loss": 1.4936245679855347,
      "step": 72
    },
    {
      "epoch": 0.031223628691983123,
      "grad_norm": 0.38912028074264526,
      "learning_rate": 1.2829525483304042e-05,
      "loss": 1.3419109582901,
      "step": 74
    },
    {
      "epoch": 0.032067510548523206,
      "grad_norm": 0.3019310235977173,
      "learning_rate": 1.3181019332161687e-05,
      "loss": 1.4284154176712036,
      "step": 76
    },
    {
      "epoch": 0.03291139240506329,
      "grad_norm": 0.37803682684898376,
      "learning_rate": 1.3532513181019332e-05,
      "loss": 1.4256561994552612,
      "step": 78
    },
    {
      "epoch": 0.03375527426160337,
      "grad_norm": 0.34191736578941345,
      "learning_rate": 1.3884007029876977e-05,
      "loss": 1.3256909847259521,
      "step": 80
    },
    {
      "epoch": 0.03459915611814346,
      "grad_norm": 0.35242700576782227,
      "learning_rate": 1.4235500878734624e-05,
      "loss": 1.2710685729980469,
      "step": 82
    },
    {
      "epoch": 0.035443037974683546,
      "grad_norm": 0.38094228506088257,
      "learning_rate": 1.4586994727592269e-05,
      "loss": 1.253411889076233,
      "step": 84
    },
    {
      "epoch": 0.036286919831223625,
      "grad_norm": 0.36837366223335266,
      "learning_rate": 1.4938488576449914e-05,
      "loss": 1.3064342737197876,
      "step": 86
    },
    {
      "epoch": 0.03713080168776371,
      "grad_norm": 0.3443569242954254,
      "learning_rate": 1.5289982425307557e-05,
      "loss": 1.293562412261963,
      "step": 88
    },
    {
      "epoch": 0.0379746835443038,
      "grad_norm": 0.3799338936805725,
      "learning_rate": 1.5641476274165202e-05,
      "loss": 1.3382648229599,
      "step": 90
    },
    {
      "epoch": 0.038818565400843885,
      "grad_norm": 0.40501922369003296,
      "learning_rate": 1.599297012302285e-05,
      "loss": 1.3925724029541016,
      "step": 92
    },
    {
      "epoch": 0.039662447257383965,
      "grad_norm": 0.4419630467891693,
      "learning_rate": 1.6344463971880492e-05,
      "loss": 1.357171893119812,
      "step": 94
    },
    {
      "epoch": 0.04050632911392405,
      "grad_norm": 0.3619817793369293,
      "learning_rate": 1.6695957820738137e-05,
      "loss": 1.3029985427856445,
      "step": 96
    },
    {
      "epoch": 0.04135021097046414,
      "grad_norm": 0.4851357340812683,
      "learning_rate": 1.7047451669595782e-05,
      "loss": 1.3498191833496094,
      "step": 98
    },
    {
      "epoch": 0.04219409282700422,
      "grad_norm": 0.418658584356308,
      "learning_rate": 1.7398945518453427e-05,
      "loss": 1.185287356376648,
      "step": 100
    },
    {
      "epoch": 0.04219409282700422,
      "eval_loss": 1.2979938983917236,
      "eval_runtime": 682.1979,
      "eval_samples_per_second": 3.089,
      "eval_steps_per_second": 3.089,
      "step": 100
    },
    {
      "epoch": 0.043037974683544304,
      "grad_norm": 0.4464418888092041,
      "learning_rate": 1.7750439367311073e-05,
      "loss": 1.2217272520065308,
      "step": 102
    },
    {
      "epoch": 0.04388185654008439,
      "grad_norm": 0.4706237316131592,
      "learning_rate": 1.8101933216168718e-05,
      "loss": 1.2052050828933716,
      "step": 104
    },
    {
      "epoch": 0.04472573839662447,
      "grad_norm": 0.46394404768943787,
      "learning_rate": 1.8453427065026363e-05,
      "loss": 1.221343994140625,
      "step": 106
    },
    {
      "epoch": 0.04556962025316456,
      "grad_norm": 0.4726889431476593,
      "learning_rate": 1.8804920913884008e-05,
      "loss": 1.2387475967407227,
      "step": 108
    },
    {
      "epoch": 0.046413502109704644,
      "grad_norm": 0.42130985856056213,
      "learning_rate": 1.9156414762741653e-05,
      "loss": 1.2851309776306152,
      "step": 110
    },
    {
      "epoch": 0.04725738396624472,
      "grad_norm": 0.4504576623439789,
      "learning_rate": 1.9507908611599298e-05,
      "loss": 1.2753145694732666,
      "step": 112
    },
    {
      "epoch": 0.04810126582278481,
      "grad_norm": 0.396085262298584,
      "learning_rate": 1.9859402460456943e-05,
      "loss": 1.2427717447280884,
      "step": 114
    },
    {
      "epoch": 0.048945147679324896,
      "grad_norm": 0.5106491446495056,
      "learning_rate": 2.0210896309314588e-05,
      "loss": 1.2943825721740723,
      "step": 116
    },
    {
      "epoch": 0.049789029535864976,
      "grad_norm": 0.42351317405700684,
      "learning_rate": 2.0562390158172233e-05,
      "loss": 1.263301134109497,
      "step": 118
    },
    {
      "epoch": 0.05063291139240506,
      "grad_norm": 0.4403539299964905,
      "learning_rate": 2.0913884007029878e-05,
      "loss": 1.2647849321365356,
      "step": 120
    },
    {
      "epoch": 0.05147679324894515,
      "grad_norm": 0.5260752439498901,
      "learning_rate": 2.1265377855887523e-05,
      "loss": 1.2351393699645996,
      "step": 122
    },
    {
      "epoch": 0.05232067510548523,
      "grad_norm": 0.44978851079940796,
      "learning_rate": 2.1616871704745168e-05,
      "loss": 1.0384471416473389,
      "step": 124
    },
    {
      "epoch": 0.053164556962025315,
      "grad_norm": 0.47732362151145935,
      "learning_rate": 2.1968365553602813e-05,
      "loss": 1.1518068313598633,
      "step": 126
    },
    {
      "epoch": 0.0540084388185654,
      "grad_norm": 0.5473551750183105,
      "learning_rate": 2.231985940246046e-05,
      "loss": 1.2264912128448486,
      "step": 128
    },
    {
      "epoch": 0.05485232067510549,
      "grad_norm": 0.4473855197429657,
      "learning_rate": 2.2671353251318103e-05,
      "loss": 1.1615246534347534,
      "step": 130
    },
    {
      "epoch": 0.05569620253164557,
      "grad_norm": 0.5980377197265625,
      "learning_rate": 2.302284710017575e-05,
      "loss": 1.1334880590438843,
      "step": 132
    },
    {
      "epoch": 0.056540084388185655,
      "grad_norm": 0.5987792015075684,
      "learning_rate": 2.3374340949033394e-05,
      "loss": 1.1546804904937744,
      "step": 134
    },
    {
      "epoch": 0.05738396624472574,
      "grad_norm": 0.45355498790740967,
      "learning_rate": 2.372583479789104e-05,
      "loss": 1.194953441619873,
      "step": 136
    },
    {
      "epoch": 0.05822784810126582,
      "grad_norm": 0.5373698472976685,
      "learning_rate": 2.4077328646748684e-05,
      "loss": 1.1067466735839844,
      "step": 138
    },
    {
      "epoch": 0.05907172995780591,
      "grad_norm": 0.48734328150749207,
      "learning_rate": 2.442882249560633e-05,
      "loss": 1.188468098640442,
      "step": 140
    },
    {
      "epoch": 0.059915611814345994,
      "grad_norm": 0.4692173898220062,
      "learning_rate": 2.478031634446397e-05,
      "loss": 1.1624362468719482,
      "step": 142
    },
    {
      "epoch": 0.060759493670886074,
      "grad_norm": 0.532554030418396,
      "learning_rate": 2.513181019332162e-05,
      "loss": 1.0978907346725464,
      "step": 144
    },
    {
      "epoch": 0.06160337552742616,
      "grad_norm": 0.5853802561759949,
      "learning_rate": 2.5483304042179264e-05,
      "loss": 1.2030781507492065,
      "step": 146
    },
    {
      "epoch": 0.06244725738396625,
      "grad_norm": 0.5061611533164978,
      "learning_rate": 2.583479789103691e-05,
      "loss": 1.082366943359375,
      "step": 148
    },
    {
      "epoch": 0.06329113924050633,
      "grad_norm": 0.49426141381263733,
      "learning_rate": 2.6186291739894554e-05,
      "loss": 1.10564386844635,
      "step": 150
    },
    {
      "epoch": 0.06413502109704641,
      "grad_norm": 0.5846618413925171,
      "learning_rate": 2.6537785588752196e-05,
      "loss": 1.1992807388305664,
      "step": 152
    },
    {
      "epoch": 0.06497890295358649,
      "grad_norm": 0.5517552495002747,
      "learning_rate": 2.6889279437609844e-05,
      "loss": 1.1757566928863525,
      "step": 154
    },
    {
      "epoch": 0.06582278481012659,
      "grad_norm": 0.5667305588722229,
      "learning_rate": 2.7240773286467486e-05,
      "loss": 1.0548783540725708,
      "step": 156
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 0.6760414242744446,
      "learning_rate": 2.7592267135325134e-05,
      "loss": 1.184364914894104,
      "step": 158
    },
    {
      "epoch": 0.06751054852320675,
      "grad_norm": 0.5261430740356445,
      "learning_rate": 2.7943760984182776e-05,
      "loss": 1.1945042610168457,
      "step": 160
    },
    {
      "epoch": 0.06835443037974684,
      "grad_norm": 0.6155015230178833,
      "learning_rate": 2.8295254833040425e-05,
      "loss": 1.2021973133087158,
      "step": 162
    },
    {
      "epoch": 0.06919831223628692,
      "grad_norm": 0.6131619215011597,
      "learning_rate": 2.8646748681898066e-05,
      "loss": 1.144123911857605,
      "step": 164
    },
    {
      "epoch": 0.070042194092827,
      "grad_norm": 0.5749185681343079,
      "learning_rate": 2.8998242530755715e-05,
      "loss": 1.1329256296157837,
      "step": 166
    },
    {
      "epoch": 0.07088607594936709,
      "grad_norm": 0.5243118405342102,
      "learning_rate": 2.9349736379613356e-05,
      "loss": 1.0892387628555298,
      "step": 168
    },
    {
      "epoch": 0.07172995780590717,
      "grad_norm": 0.7190104722976685,
      "learning_rate": 2.9701230228471005e-05,
      "loss": 1.163260817527771,
      "step": 170
    },
    {
      "epoch": 0.07257383966244725,
      "grad_norm": 0.5486982464790344,
      "learning_rate": 3.0052724077328647e-05,
      "loss": 1.0880777835845947,
      "step": 172
    },
    {
      "epoch": 0.07341772151898734,
      "grad_norm": 0.5020889043807983,
      "learning_rate": 3.0404217926186295e-05,
      "loss": 1.0433368682861328,
      "step": 174
    },
    {
      "epoch": 0.07426160337552742,
      "grad_norm": 0.47329774498939514,
      "learning_rate": 3.075571177504394e-05,
      "loss": 1.0528991222381592,
      "step": 176
    },
    {
      "epoch": 0.0751054852320675,
      "grad_norm": 0.6635547876358032,
      "learning_rate": 3.110720562390158e-05,
      "loss": 1.1627811193466187,
      "step": 178
    },
    {
      "epoch": 0.0759493670886076,
      "grad_norm": 0.5624618530273438,
      "learning_rate": 3.145869947275923e-05,
      "loss": 1.084869384765625,
      "step": 180
    },
    {
      "epoch": 0.07679324894514768,
      "grad_norm": 0.6029536724090576,
      "learning_rate": 3.181019332161687e-05,
      "loss": 1.2227671146392822,
      "step": 182
    },
    {
      "epoch": 0.07763713080168777,
      "grad_norm": 0.930959939956665,
      "learning_rate": 3.216168717047452e-05,
      "loss": 1.0955452919006348,
      "step": 184
    },
    {
      "epoch": 0.07848101265822785,
      "grad_norm": 0.5326952338218689,
      "learning_rate": 3.251318101933216e-05,
      "loss": 1.0640798807144165,
      "step": 186
    },
    {
      "epoch": 0.07932489451476793,
      "grad_norm": 0.5484727621078491,
      "learning_rate": 3.286467486818981e-05,
      "loss": 1.0700589418411255,
      "step": 188
    },
    {
      "epoch": 0.08016877637130802,
      "grad_norm": 0.605273425579071,
      "learning_rate": 3.3216168717047456e-05,
      "loss": 1.1593081951141357,
      "step": 190
    },
    {
      "epoch": 0.0810126582278481,
      "grad_norm": 0.5704394578933716,
      "learning_rate": 3.35676625659051e-05,
      "loss": 1.1617076396942139,
      "step": 192
    },
    {
      "epoch": 0.08185654008438818,
      "grad_norm": 0.5929452180862427,
      "learning_rate": 3.3919156414762746e-05,
      "loss": 1.1346839666366577,
      "step": 194
    },
    {
      "epoch": 0.08270042194092828,
      "grad_norm": 0.5624077916145325,
      "learning_rate": 3.427065026362039e-05,
      "loss": 1.0934710502624512,
      "step": 196
    },
    {
      "epoch": 0.08354430379746836,
      "grad_norm": 0.6717425584793091,
      "learning_rate": 3.4622144112478036e-05,
      "loss": 1.1810534000396729,
      "step": 198
    },
    {
      "epoch": 0.08438818565400844,
      "grad_norm": 0.5120199918746948,
      "learning_rate": 3.4973637961335674e-05,
      "loss": 1.1525514125823975,
      "step": 200
    },
    {
      "epoch": 0.08438818565400844,
      "eval_loss": 1.142486810684204,
      "eval_runtime": 668.2356,
      "eval_samples_per_second": 3.153,
      "eval_steps_per_second": 3.153,
      "step": 200
    },
    {
      "epoch": 0.08523206751054853,
      "grad_norm": 0.5144487023353577,
      "learning_rate": 3.5325131810193326e-05,
      "loss": 1.0243735313415527,
      "step": 202
    },
    {
      "epoch": 0.08607594936708861,
      "grad_norm": 0.6325069069862366,
      "learning_rate": 3.5676625659050964e-05,
      "loss": 1.118743896484375,
      "step": 204
    },
    {
      "epoch": 0.08691983122362869,
      "grad_norm": 0.5501633882522583,
      "learning_rate": 3.6028119507908616e-05,
      "loss": 1.0380504131317139,
      "step": 206
    },
    {
      "epoch": 0.08776371308016878,
      "grad_norm": 0.6133899688720703,
      "learning_rate": 3.6379613356766254e-05,
      "loss": 0.9837555885314941,
      "step": 208
    },
    {
      "epoch": 0.08860759493670886,
      "grad_norm": 0.5799810886383057,
      "learning_rate": 3.6731107205623906e-05,
      "loss": 1.090720295906067,
      "step": 210
    },
    {
      "epoch": 0.08945147679324894,
      "grad_norm": 0.6039511561393738,
      "learning_rate": 3.7082601054481544e-05,
      "loss": 1.120232343673706,
      "step": 212
    },
    {
      "epoch": 0.09029535864978903,
      "grad_norm": 0.5983024835586548,
      "learning_rate": 3.7434094903339196e-05,
      "loss": 1.096949815750122,
      "step": 214
    },
    {
      "epoch": 0.09113924050632911,
      "grad_norm": 0.5641079545021057,
      "learning_rate": 3.7785588752196835e-05,
      "loss": 1.1226298809051514,
      "step": 216
    },
    {
      "epoch": 0.0919831223628692,
      "grad_norm": 0.655717134475708,
      "learning_rate": 3.8137082601054486e-05,
      "loss": 1.1260643005371094,
      "step": 218
    },
    {
      "epoch": 0.09282700421940929,
      "grad_norm": 0.6111898422241211,
      "learning_rate": 3.848857644991213e-05,
      "loss": 1.0777709484100342,
      "step": 220
    },
    {
      "epoch": 0.09367088607594937,
      "grad_norm": 0.6821302771568298,
      "learning_rate": 3.884007029876977e-05,
      "loss": 1.10588800907135,
      "step": 222
    },
    {
      "epoch": 0.09451476793248945,
      "grad_norm": 0.693175733089447,
      "learning_rate": 3.919156414762742e-05,
      "loss": 1.1498671770095825,
      "step": 224
    },
    {
      "epoch": 0.09535864978902954,
      "grad_norm": 0.5288166403770447,
      "learning_rate": 3.954305799648506e-05,
      "loss": 1.0587562322616577,
      "step": 226
    },
    {
      "epoch": 0.09620253164556962,
      "grad_norm": 0.6882867813110352,
      "learning_rate": 3.989455184534271e-05,
      "loss": 1.1107512712478638,
      "step": 228
    },
    {
      "epoch": 0.0970464135021097,
      "grad_norm": 0.5834154486656189,
      "learning_rate": 4.024604569420035e-05,
      "loss": 1.020510196685791,
      "step": 230
    },
    {
      "epoch": 0.09789029535864979,
      "grad_norm": 0.7157064080238342,
      "learning_rate": 4.0597539543058e-05,
      "loss": 1.0642449855804443,
      "step": 232
    },
    {
      "epoch": 0.09873417721518987,
      "grad_norm": 0.6530708074569702,
      "learning_rate": 4.094903339191564e-05,
      "loss": 1.0359872579574585,
      "step": 234
    },
    {
      "epoch": 0.09957805907172995,
      "grad_norm": 0.6329686045646667,
      "learning_rate": 4.130052724077329e-05,
      "loss": 1.050504446029663,
      "step": 236
    },
    {
      "epoch": 0.10042194092827005,
      "grad_norm": 0.6597026586532593,
      "learning_rate": 4.165202108963093e-05,
      "loss": 1.2621175050735474,
      "step": 238
    },
    {
      "epoch": 0.10126582278481013,
      "grad_norm": 0.6195225119590759,
      "learning_rate": 4.200351493848858e-05,
      "loss": 1.1218310594558716,
      "step": 240
    },
    {
      "epoch": 0.1021097046413502,
      "grad_norm": 0.6764137744903564,
      "learning_rate": 4.235500878734622e-05,
      "loss": 1.1250728368759155,
      "step": 242
    },
    {
      "epoch": 0.1029535864978903,
      "grad_norm": 0.552363395690918,
      "learning_rate": 4.270650263620387e-05,
      "loss": 1.028212308883667,
      "step": 244
    },
    {
      "epoch": 0.10379746835443038,
      "grad_norm": 0.5620495676994324,
      "learning_rate": 4.305799648506151e-05,
      "loss": 1.0425450801849365,
      "step": 246
    },
    {
      "epoch": 0.10464135021097046,
      "grad_norm": 0.6860032081604004,
      "learning_rate": 4.3409490333919156e-05,
      "loss": 1.144278883934021,
      "step": 248
    },
    {
      "epoch": 0.10548523206751055,
      "grad_norm": 0.6033259034156799,
      "learning_rate": 4.37609841827768e-05,
      "loss": 1.1223982572555542,
      "step": 250
    },
    {
      "epoch": 0.10632911392405063,
      "grad_norm": 0.6292146444320679,
      "learning_rate": 4.4112478031634446e-05,
      "loss": 1.1609960794448853,
      "step": 252
    },
    {
      "epoch": 0.10717299578059072,
      "grad_norm": 0.7982883453369141,
      "learning_rate": 4.44639718804921e-05,
      "loss": 1.063547968864441,
      "step": 254
    },
    {
      "epoch": 0.1080168776371308,
      "grad_norm": 0.7719110250473022,
      "learning_rate": 4.4815465729349736e-05,
      "loss": 1.0719804763793945,
      "step": 256
    },
    {
      "epoch": 0.10886075949367088,
      "grad_norm": 0.6101011633872986,
      "learning_rate": 4.516695957820739e-05,
      "loss": 1.0778400897979736,
      "step": 258
    },
    {
      "epoch": 0.10970464135021098,
      "grad_norm": 0.7300994396209717,
      "learning_rate": 4.5518453427065026e-05,
      "loss": 1.2129558324813843,
      "step": 260
    },
    {
      "epoch": 0.11054852320675106,
      "grad_norm": 0.8348747491836548,
      "learning_rate": 4.586994727592268e-05,
      "loss": 1.221714735031128,
      "step": 262
    },
    {
      "epoch": 0.11139240506329114,
      "grad_norm": 0.5445612072944641,
      "learning_rate": 4.6221441124780316e-05,
      "loss": 1.0187978744506836,
      "step": 264
    },
    {
      "epoch": 0.11223628691983123,
      "grad_norm": 0.6230319738388062,
      "learning_rate": 4.657293497363797e-05,
      "loss": 1.096561312675476,
      "step": 266
    },
    {
      "epoch": 0.11308016877637131,
      "grad_norm": 0.6231237649917603,
      "learning_rate": 4.6924428822495606e-05,
      "loss": 1.089842438697815,
      "step": 268
    },
    {
      "epoch": 0.11392405063291139,
      "grad_norm": 0.7178627252578735,
      "learning_rate": 4.727592267135325e-05,
      "loss": 1.0696645975112915,
      "step": 270
    },
    {
      "epoch": 0.11476793248945148,
      "grad_norm": 0.6895854473114014,
      "learning_rate": 4.7627416520210896e-05,
      "loss": 1.0511361360549927,
      "step": 272
    },
    {
      "epoch": 0.11561181434599156,
      "grad_norm": 0.6046878695487976,
      "learning_rate": 4.797891036906854e-05,
      "loss": 1.1373958587646484,
      "step": 274
    },
    {
      "epoch": 0.11645569620253164,
      "grad_norm": 0.6524552702903748,
      "learning_rate": 4.833040421792619e-05,
      "loss": 1.0734186172485352,
      "step": 276
    },
    {
      "epoch": 0.11729957805907174,
      "grad_norm": 0.6331019997596741,
      "learning_rate": 4.868189806678383e-05,
      "loss": 1.123913049697876,
      "step": 278
    },
    {
      "epoch": 0.11814345991561181,
      "grad_norm": 0.5919018983840942,
      "learning_rate": 4.903339191564148e-05,
      "loss": 1.0635710954666138,
      "step": 280
    },
    {
      "epoch": 0.1189873417721519,
      "grad_norm": 0.6067633032798767,
      "learning_rate": 4.938488576449912e-05,
      "loss": 1.0429247617721558,
      "step": 282
    },
    {
      "epoch": 0.11983122362869199,
      "grad_norm": 0.6583750247955322,
      "learning_rate": 4.9736379613356774e-05,
      "loss": 1.1397464275360107,
      "step": 284
    },
    {
      "epoch": 0.12067510548523207,
      "grad_norm": 0.6200069785118103,
      "learning_rate": 5.008787346221442e-05,
      "loss": 1.0590803623199463,
      "step": 286
    },
    {
      "epoch": 0.12151898734177215,
      "grad_norm": 0.6798665523529053,
      "learning_rate": 5.0439367311072064e-05,
      "loss": 1.1318789720535278,
      "step": 288
    },
    {
      "epoch": 0.12236286919831224,
      "grad_norm": 0.7508794069290161,
      "learning_rate": 5.07908611599297e-05,
      "loss": 1.0934956073760986,
      "step": 290
    },
    {
      "epoch": 0.12320675105485232,
      "grad_norm": 0.6901452541351318,
      "learning_rate": 5.114235500878735e-05,
      "loss": 1.163407802581787,
      "step": 292
    },
    {
      "epoch": 0.1240506329113924,
      "grad_norm": 0.6423285603523254,
      "learning_rate": 5.1493848857644985e-05,
      "loss": 1.09059476852417,
      "step": 294
    },
    {
      "epoch": 0.1248945147679325,
      "grad_norm": 0.6839275360107422,
      "learning_rate": 5.1845342706502644e-05,
      "loss": 1.0690211057662964,
      "step": 296
    },
    {
      "epoch": 0.1257383966244726,
      "grad_norm": 0.6350128054618835,
      "learning_rate": 5.219683655536028e-05,
      "loss": 0.982322096824646,
      "step": 298
    },
    {
      "epoch": 0.12658227848101267,
      "grad_norm": 0.7136530876159668,
      "learning_rate": 5.254833040421793e-05,
      "loss": 1.1132930517196655,
      "step": 300
    },
    {
      "epoch": 0.12658227848101267,
      "eval_loss": 1.0952109098434448,
      "eval_runtime": 677.0652,
      "eval_samples_per_second": 3.112,
      "eval_steps_per_second": 3.112,
      "step": 300
    },
    {
      "epoch": 0.12742616033755275,
      "grad_norm": 0.7339721322059631,
      "learning_rate": 5.289982425307557e-05,
      "loss": 0.973595917224884,
      "step": 302
    },
    {
      "epoch": 0.12827004219409283,
      "grad_norm": 0.5941481590270996,
      "learning_rate": 5.3251318101933224e-05,
      "loss": 0.9819849729537964,
      "step": 304
    },
    {
      "epoch": 0.1291139240506329,
      "grad_norm": 0.7153938412666321,
      "learning_rate": 5.360281195079086e-05,
      "loss": 1.0315470695495605,
      "step": 306
    },
    {
      "epoch": 0.12995780590717299,
      "grad_norm": 0.5167180299758911,
      "learning_rate": 5.395430579964851e-05,
      "loss": 0.9492001533508301,
      "step": 308
    },
    {
      "epoch": 0.1308016877637131,
      "grad_norm": 0.6055944561958313,
      "learning_rate": 5.430579964850615e-05,
      "loss": 1.0156209468841553,
      "step": 310
    },
    {
      "epoch": 0.13164556962025317,
      "grad_norm": 0.7662386298179626,
      "learning_rate": 5.4657293497363805e-05,
      "loss": 1.1791651248931885,
      "step": 312
    },
    {
      "epoch": 0.13248945147679325,
      "grad_norm": 0.6065546274185181,
      "learning_rate": 5.500878734622145e-05,
      "loss": 1.0009297132492065,
      "step": 314
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.604225754737854,
      "learning_rate": 5.536028119507909e-05,
      "loss": 1.0208244323730469,
      "step": 316
    },
    {
      "epoch": 0.1341772151898734,
      "grad_norm": 0.6186763048171997,
      "learning_rate": 5.571177504393673e-05,
      "loss": 0.9968416690826416,
      "step": 318
    },
    {
      "epoch": 0.1350210970464135,
      "grad_norm": 0.7100363969802856,
      "learning_rate": 5.606326889279437e-05,
      "loss": 0.9540256857872009,
      "step": 320
    },
    {
      "epoch": 0.1358649789029536,
      "grad_norm": 0.6979711055755615,
      "learning_rate": 5.641476274165203e-05,
      "loss": 1.0631953477859497,
      "step": 322
    },
    {
      "epoch": 0.13670886075949368,
      "grad_norm": 0.6237109303474426,
      "learning_rate": 5.676625659050967e-05,
      "loss": 1.0170501470565796,
      "step": 324
    },
    {
      "epoch": 0.13755274261603376,
      "grad_norm": 0.6525548696517944,
      "learning_rate": 5.711775043936731e-05,
      "loss": 1.0715603828430176,
      "step": 326
    },
    {
      "epoch": 0.13839662447257384,
      "grad_norm": 0.6869221329689026,
      "learning_rate": 5.746924428822495e-05,
      "loss": 1.0111541748046875,
      "step": 328
    },
    {
      "epoch": 0.13924050632911392,
      "grad_norm": 0.553188145160675,
      "learning_rate": 5.782073813708261e-05,
      "loss": 1.0311682224273682,
      "step": 330
    },
    {
      "epoch": 0.140084388185654,
      "grad_norm": 0.6760852932929993,
      "learning_rate": 5.817223198594025e-05,
      "loss": 1.0213634967803955,
      "step": 332
    },
    {
      "epoch": 0.1409282700421941,
      "grad_norm": 0.5907419919967651,
      "learning_rate": 5.8523725834797894e-05,
      "loss": 0.9748594164848328,
      "step": 334
    },
    {
      "epoch": 0.14177215189873418,
      "grad_norm": 0.7044920921325684,
      "learning_rate": 5.887521968365554e-05,
      "loss": 1.05863356590271,
      "step": 336
    },
    {
      "epoch": 0.14261603375527426,
      "grad_norm": 0.679073691368103,
      "learning_rate": 5.922671353251318e-05,
      "loss": 1.1341127157211304,
      "step": 338
    },
    {
      "epoch": 0.14345991561181434,
      "grad_norm": 0.7676237225532532,
      "learning_rate": 5.957820738137083e-05,
      "loss": 0.9540836215019226,
      "step": 340
    },
    {
      "epoch": 0.14430379746835442,
      "grad_norm": 0.6313899755477905,
      "learning_rate": 5.9929701230228474e-05,
      "loss": 1.0585911273956299,
      "step": 342
    },
    {
      "epoch": 0.1451476793248945,
      "grad_norm": 0.7123099565505981,
      "learning_rate": 6.028119507908612e-05,
      "loss": 1.0760118961334229,
      "step": 344
    },
    {
      "epoch": 0.1459915611814346,
      "grad_norm": 0.585935652256012,
      "learning_rate": 6.063268892794376e-05,
      "loss": 1.036866307258606,
      "step": 346
    },
    {
      "epoch": 0.1468354430379747,
      "grad_norm": 0.5643263459205627,
      "learning_rate": 6.0984182776801416e-05,
      "loss": 1.0242938995361328,
      "step": 348
    },
    {
      "epoch": 0.14767932489451477,
      "grad_norm": 0.626761794090271,
      "learning_rate": 6.133567662565906e-05,
      "loss": 1.0497376918792725,
      "step": 350
    },
    {
      "epoch": 0.14852320675105485,
      "grad_norm": 0.5106956958770752,
      "learning_rate": 6.16871704745167e-05,
      "loss": 0.9811885356903076,
      "step": 352
    },
    {
      "epoch": 0.14936708860759493,
      "grad_norm": 0.6948089003562927,
      "learning_rate": 6.203866432337434e-05,
      "loss": 1.0715330839157104,
      "step": 354
    },
    {
      "epoch": 0.150210970464135,
      "grad_norm": 0.699713945388794,
      "learning_rate": 6.239015817223199e-05,
      "loss": 1.0405226945877075,
      "step": 356
    },
    {
      "epoch": 0.15105485232067511,
      "grad_norm": 0.6437667012214661,
      "learning_rate": 6.274165202108964e-05,
      "loss": 1.0490930080413818,
      "step": 358
    },
    {
      "epoch": 0.1518987341772152,
      "grad_norm": 0.6952699422836304,
      "learning_rate": 6.309314586994728e-05,
      "loss": 0.9267548322677612,
      "step": 360
    },
    {
      "epoch": 0.15274261603375527,
      "grad_norm": 0.6713186502456665,
      "learning_rate": 6.344463971880492e-05,
      "loss": 1.0427420139312744,
      "step": 362
    },
    {
      "epoch": 0.15358649789029535,
      "grad_norm": 0.6750379800796509,
      "learning_rate": 6.379613356766257e-05,
      "loss": 1.048950433731079,
      "step": 364
    },
    {
      "epoch": 0.15443037974683543,
      "grad_norm": 0.6053379774093628,
      "learning_rate": 6.414762741652022e-05,
      "loss": 1.0156004428863525,
      "step": 366
    },
    {
      "epoch": 0.15527426160337554,
      "grad_norm": 0.8063633441925049,
      "learning_rate": 6.449912126537786e-05,
      "loss": 1.0020819902420044,
      "step": 368
    },
    {
      "epoch": 0.15611814345991562,
      "grad_norm": 0.8027494549751282,
      "learning_rate": 6.48506151142355e-05,
      "loss": 1.055633783340454,
      "step": 370
    },
    {
      "epoch": 0.1569620253164557,
      "grad_norm": 0.6580121517181396,
      "learning_rate": 6.520210896309315e-05,
      "loss": 1.0149940252304077,
      "step": 372
    },
    {
      "epoch": 0.15780590717299578,
      "grad_norm": 0.6561233997344971,
      "learning_rate": 6.55536028119508e-05,
      "loss": 0.9769611954689026,
      "step": 374
    },
    {
      "epoch": 0.15864978902953586,
      "grad_norm": 0.6444346308708191,
      "learning_rate": 6.590509666080844e-05,
      "loss": 0.9099349975585938,
      "step": 376
    },
    {
      "epoch": 0.15949367088607594,
      "grad_norm": 0.5879359245300293,
      "learning_rate": 6.625659050966608e-05,
      "loss": 1.0797548294067383,
      "step": 378
    },
    {
      "epoch": 0.16033755274261605,
      "grad_norm": 0.6994144916534424,
      "learning_rate": 6.660808435852373e-05,
      "loss": 1.0336791276931763,
      "step": 380
    },
    {
      "epoch": 0.16118143459915613,
      "grad_norm": 0.6128669381141663,
      "learning_rate": 6.695957820738138e-05,
      "loss": 1.018118143081665,
      "step": 382
    },
    {
      "epoch": 0.1620253164556962,
      "grad_norm": 1.0237540006637573,
      "learning_rate": 6.731107205623902e-05,
      "loss": 1.1405497789382935,
      "step": 384
    },
    {
      "epoch": 0.16286919831223629,
      "grad_norm": 0.6091578006744385,
      "learning_rate": 6.766256590509666e-05,
      "loss": 1.0314189195632935,
      "step": 386
    },
    {
      "epoch": 0.16371308016877636,
      "grad_norm": 0.5916037559509277,
      "learning_rate": 6.801405975395431e-05,
      "loss": 0.9564052820205688,
      "step": 388
    },
    {
      "epoch": 0.16455696202531644,
      "grad_norm": 0.771653950214386,
      "learning_rate": 6.836555360281195e-05,
      "loss": 1.0023859739303589,
      "step": 390
    },
    {
      "epoch": 0.16540084388185655,
      "grad_norm": 0.654658317565918,
      "learning_rate": 6.87170474516696e-05,
      "loss": 1.07024085521698,
      "step": 392
    },
    {
      "epoch": 0.16624472573839663,
      "grad_norm": 0.6611968874931335,
      "learning_rate": 6.906854130052724e-05,
      "loss": 1.0552500486373901,
      "step": 394
    },
    {
      "epoch": 0.1670886075949367,
      "grad_norm": 0.6955893039703369,
      "learning_rate": 6.942003514938489e-05,
      "loss": 1.0562875270843506,
      "step": 396
    },
    {
      "epoch": 0.1679324894514768,
      "grad_norm": 0.6666058301925659,
      "learning_rate": 6.977152899824253e-05,
      "loss": 0.9850592017173767,
      "step": 398
    },
    {
      "epoch": 0.16877637130801687,
      "grad_norm": 0.6131711006164551,
      "learning_rate": 7.012302284710018e-05,
      "loss": 1.0077755451202393,
      "step": 400
    },
    {
      "epoch": 0.16877637130801687,
      "eval_loss": 1.0625108480453491,
      "eval_runtime": 691.0068,
      "eval_samples_per_second": 3.049,
      "eval_steps_per_second": 3.049,
      "step": 400
    },
    {
      "epoch": 0.16962025316455695,
      "grad_norm": 0.6286499500274658,
      "learning_rate": 7.047451669595783e-05,
      "loss": 1.1012427806854248,
      "step": 402
    },
    {
      "epoch": 0.17046413502109706,
      "grad_norm": 0.6639351844787598,
      "learning_rate": 7.082601054481547e-05,
      "loss": 1.0379719734191895,
      "step": 404
    },
    {
      "epoch": 0.17130801687763714,
      "grad_norm": 0.750401496887207,
      "learning_rate": 7.117750439367311e-05,
      "loss": 1.031856656074524,
      "step": 406
    },
    {
      "epoch": 0.17215189873417722,
      "grad_norm": 0.8084847331047058,
      "learning_rate": 7.152899824253075e-05,
      "loss": 1.0493193864822388,
      "step": 408
    },
    {
      "epoch": 0.1729957805907173,
      "grad_norm": 0.7448462247848511,
      "learning_rate": 7.188049209138841e-05,
      "loss": 1.1012418270111084,
      "step": 410
    },
    {
      "epoch": 0.17383966244725738,
      "grad_norm": 0.5841867923736572,
      "learning_rate": 7.223198594024605e-05,
      "loss": 0.9926692247390747,
      "step": 412
    },
    {
      "epoch": 0.17468354430379746,
      "grad_norm": 0.7125606536865234,
      "learning_rate": 7.258347978910369e-05,
      "loss": 1.0588877201080322,
      "step": 414
    },
    {
      "epoch": 0.17552742616033756,
      "grad_norm": 0.5750942230224609,
      "learning_rate": 7.293497363796134e-05,
      "loss": 1.038270354270935,
      "step": 416
    },
    {
      "epoch": 0.17637130801687764,
      "grad_norm": 0.565444827079773,
      "learning_rate": 7.328646748681899e-05,
      "loss": 0.9843021035194397,
      "step": 418
    },
    {
      "epoch": 0.17721518987341772,
      "grad_norm": 0.5825693011283875,
      "learning_rate": 7.363796133567663e-05,
      "loss": 1.0731632709503174,
      "step": 420
    },
    {
      "epoch": 0.1780590717299578,
      "grad_norm": 0.6267391443252563,
      "learning_rate": 7.398945518453427e-05,
      "loss": 1.0061273574829102,
      "step": 422
    },
    {
      "epoch": 0.17890295358649788,
      "grad_norm": 0.6621372103691101,
      "learning_rate": 7.434094903339192e-05,
      "loss": 1.0461612939834595,
      "step": 424
    },
    {
      "epoch": 0.17974683544303796,
      "grad_norm": 0.6635435223579407,
      "learning_rate": 7.469244288224957e-05,
      "loss": 0.9789207577705383,
      "step": 426
    },
    {
      "epoch": 0.18059071729957807,
      "grad_norm": 0.6342346668243408,
      "learning_rate": 7.504393673110721e-05,
      "loss": 1.0527069568634033,
      "step": 428
    },
    {
      "epoch": 0.18143459915611815,
      "grad_norm": 0.6762149930000305,
      "learning_rate": 7.539543057996485e-05,
      "loss": 0.9708702564239502,
      "step": 430
    },
    {
      "epoch": 0.18227848101265823,
      "grad_norm": 0.7073282599449158,
      "learning_rate": 7.57469244288225e-05,
      "loss": 1.0509834289550781,
      "step": 432
    },
    {
      "epoch": 0.1831223628691983,
      "grad_norm": 0.6917856931686401,
      "learning_rate": 7.609841827768014e-05,
      "loss": 1.0128819942474365,
      "step": 434
    },
    {
      "epoch": 0.1839662447257384,
      "grad_norm": 0.5574942231178284,
      "learning_rate": 7.644991212653779e-05,
      "loss": 0.989395797252655,
      "step": 436
    },
    {
      "epoch": 0.1848101265822785,
      "grad_norm": 0.640765905380249,
      "learning_rate": 7.680140597539543e-05,
      "loss": 0.9846042990684509,
      "step": 438
    },
    {
      "epoch": 0.18565400843881857,
      "grad_norm": 0.6699127554893494,
      "learning_rate": 7.715289982425308e-05,
      "loss": 1.0344442129135132,
      "step": 440
    },
    {
      "epoch": 0.18649789029535865,
      "grad_norm": 0.6164930462837219,
      "learning_rate": 7.750439367311072e-05,
      "loss": 1.0179373025894165,
      "step": 442
    },
    {
      "epoch": 0.18734177215189873,
      "grad_norm": 0.6880720853805542,
      "learning_rate": 7.785588752196837e-05,
      "loss": 1.0518895387649536,
      "step": 444
    },
    {
      "epoch": 0.1881856540084388,
      "grad_norm": 0.6501413583755493,
      "learning_rate": 7.820738137082601e-05,
      "loss": 1.0442606210708618,
      "step": 446
    },
    {
      "epoch": 0.1890295358649789,
      "grad_norm": 0.6076085567474365,
      "learning_rate": 7.855887521968366e-05,
      "loss": 0.9828442335128784,
      "step": 448
    },
    {
      "epoch": 0.189873417721519,
      "grad_norm": 0.6418202519416809,
      "learning_rate": 7.89103690685413e-05,
      "loss": 1.0573710203170776,
      "step": 450
    },
    {
      "epoch": 0.19071729957805908,
      "grad_norm": 0.7055076360702515,
      "learning_rate": 7.926186291739895e-05,
      "loss": 1.0216103792190552,
      "step": 452
    },
    {
      "epoch": 0.19156118143459916,
      "grad_norm": 0.5668330192565918,
      "learning_rate": 7.961335676625659e-05,
      "loss": 0.9837722778320312,
      "step": 454
    },
    {
      "epoch": 0.19240506329113924,
      "grad_norm": 0.6419380307197571,
      "learning_rate": 7.996485061511424e-05,
      "loss": 1.0003894567489624,
      "step": 456
    },
    {
      "epoch": 0.19324894514767932,
      "grad_norm": 0.5949198007583618,
      "learning_rate": 8.031634446397188e-05,
      "loss": 1.0609031915664673,
      "step": 458
    },
    {
      "epoch": 0.1940928270042194,
      "grad_norm": 0.7032039761543274,
      "learning_rate": 8.066783831282952e-05,
      "loss": 1.0543403625488281,
      "step": 460
    },
    {
      "epoch": 0.1949367088607595,
      "grad_norm": 0.5775868892669678,
      "learning_rate": 8.101933216168718e-05,
      "loss": 0.9819303154945374,
      "step": 462
    },
    {
      "epoch": 0.19578059071729959,
      "grad_norm": 0.9301062226295471,
      "learning_rate": 8.137082601054482e-05,
      "loss": 1.0542067289352417,
      "step": 464
    },
    {
      "epoch": 0.19662447257383966,
      "grad_norm": 0.6193217039108276,
      "learning_rate": 8.172231985940246e-05,
      "loss": 0.9966341257095337,
      "step": 466
    },
    {
      "epoch": 0.19746835443037974,
      "grad_norm": 0.6286146640777588,
      "learning_rate": 8.20738137082601e-05,
      "loss": 1.0474121570587158,
      "step": 468
    },
    {
      "epoch": 0.19831223628691982,
      "grad_norm": 0.7418972253799438,
      "learning_rate": 8.242530755711776e-05,
      "loss": 0.9549239277839661,
      "step": 470
    },
    {
      "epoch": 0.1991561181434599,
      "grad_norm": 0.6122808456420898,
      "learning_rate": 8.27768014059754e-05,
      "loss": 1.0191338062286377,
      "step": 472
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.6375362277030945,
      "learning_rate": 8.312829525483304e-05,
      "loss": 1.0987539291381836,
      "step": 474
    },
    {
      "epoch": 0.2008438818565401,
      "grad_norm": 0.6459513306617737,
      "learning_rate": 8.347978910369068e-05,
      "loss": 1.0369136333465576,
      "step": 476
    },
    {
      "epoch": 0.20168776371308017,
      "grad_norm": 0.7029640674591064,
      "learning_rate": 8.383128295254833e-05,
      "loss": 1.0582096576690674,
      "step": 478
    },
    {
      "epoch": 0.20253164556962025,
      "grad_norm": 0.6345387697219849,
      "learning_rate": 8.418277680140598e-05,
      "loss": 1.022916316986084,
      "step": 480
    },
    {
      "epoch": 0.20337552742616033,
      "grad_norm": 0.5764590501785278,
      "learning_rate": 8.453427065026362e-05,
      "loss": 0.973024308681488,
      "step": 482
    },
    {
      "epoch": 0.2042194092827004,
      "grad_norm": 0.5884482860565186,
      "learning_rate": 8.488576449912127e-05,
      "loss": 1.0292812585830688,
      "step": 484
    },
    {
      "epoch": 0.20506329113924052,
      "grad_norm": 0.616357147693634,
      "learning_rate": 8.523725834797891e-05,
      "loss": 1.0083447694778442,
      "step": 486
    },
    {
      "epoch": 0.2059071729957806,
      "grad_norm": 0.7671196460723877,
      "learning_rate": 8.558875219683656e-05,
      "loss": 0.9936985373497009,
      "step": 488
    },
    {
      "epoch": 0.20675105485232068,
      "grad_norm": 0.6197299957275391,
      "learning_rate": 8.59402460456942e-05,
      "loss": 1.051513910293579,
      "step": 490
    },
    {
      "epoch": 0.20759493670886076,
      "grad_norm": 0.6912890672683716,
      "learning_rate": 8.629173989455185e-05,
      "loss": 0.9474978446960449,
      "step": 492
    },
    {
      "epoch": 0.20843881856540084,
      "grad_norm": 0.6941592693328857,
      "learning_rate": 8.664323374340949e-05,
      "loss": 1.0671660900115967,
      "step": 494
    },
    {
      "epoch": 0.20928270042194091,
      "grad_norm": 0.5889528393745422,
      "learning_rate": 8.699472759226714e-05,
      "loss": 1.0020159482955933,
      "step": 496
    },
    {
      "epoch": 0.21012658227848102,
      "grad_norm": 0.6478549838066101,
      "learning_rate": 8.734622144112478e-05,
      "loss": 1.0165860652923584,
      "step": 498
    },
    {
      "epoch": 0.2109704641350211,
      "grad_norm": 0.6018255949020386,
      "learning_rate": 8.769771528998243e-05,
      "loss": 0.8798263072967529,
      "step": 500
    },
    {
      "epoch": 0.2109704641350211,
      "eval_loss": 1.042096495628357,
      "eval_runtime": 692.4361,
      "eval_samples_per_second": 3.043,
      "eval_steps_per_second": 3.043,
      "step": 500
    },
    {
      "epoch": 0.21181434599156118,
      "grad_norm": 0.578990638256073,
      "learning_rate": 8.804920913884007e-05,
      "loss": 1.092096209526062,
      "step": 502
    },
    {
      "epoch": 0.21265822784810126,
      "grad_norm": 0.6597883701324463,
      "learning_rate": 8.840070298769771e-05,
      "loss": 1.0413451194763184,
      "step": 504
    },
    {
      "epoch": 0.21350210970464134,
      "grad_norm": 0.6660305261611938,
      "learning_rate": 8.875219683655536e-05,
      "loss": 1.0073142051696777,
      "step": 506
    },
    {
      "epoch": 0.21434599156118145,
      "grad_norm": 0.6283115148544312,
      "learning_rate": 8.910369068541301e-05,
      "loss": 1.0319768190383911,
      "step": 508
    },
    {
      "epoch": 0.21518987341772153,
      "grad_norm": 0.6257343292236328,
      "learning_rate": 8.945518453427065e-05,
      "loss": 1.0046353340148926,
      "step": 510
    },
    {
      "epoch": 0.2160337552742616,
      "grad_norm": 0.5530875325202942,
      "learning_rate": 8.980667838312829e-05,
      "loss": 0.9169099926948547,
      "step": 512
    },
    {
      "epoch": 0.2168776371308017,
      "grad_norm": 0.5369633436203003,
      "learning_rate": 9.015817223198594e-05,
      "loss": 0.9081505537033081,
      "step": 514
    },
    {
      "epoch": 0.21772151898734177,
      "grad_norm": 0.6618232131004333,
      "learning_rate": 9.05096660808436e-05,
      "loss": 0.9165045022964478,
      "step": 516
    },
    {
      "epoch": 0.21856540084388185,
      "grad_norm": 0.600666344165802,
      "learning_rate": 9.086115992970123e-05,
      "loss": 0.91348797082901,
      "step": 518
    },
    {
      "epoch": 0.21940928270042195,
      "grad_norm": 0.5919831991195679,
      "learning_rate": 9.121265377855887e-05,
      "loss": 1.006508469581604,
      "step": 520
    },
    {
      "epoch": 0.22025316455696203,
      "grad_norm": 0.688058614730835,
      "learning_rate": 9.156414762741654e-05,
      "loss": 1.0013236999511719,
      "step": 522
    },
    {
      "epoch": 0.2210970464135021,
      "grad_norm": 0.6721227765083313,
      "learning_rate": 9.191564147627418e-05,
      "loss": 1.0909923315048218,
      "step": 524
    },
    {
      "epoch": 0.2219409282700422,
      "grad_norm": 0.5987313389778137,
      "learning_rate": 9.226713532513181e-05,
      "loss": 1.0117096900939941,
      "step": 526
    },
    {
      "epoch": 0.22278481012658227,
      "grad_norm": 0.6191489696502686,
      "learning_rate": 9.261862917398945e-05,
      "loss": 1.0153647661209106,
      "step": 528
    },
    {
      "epoch": 0.22362869198312235,
      "grad_norm": 0.6821563243865967,
      "learning_rate": 9.29701230228471e-05,
      "loss": 0.9649755954742432,
      "step": 530
    },
    {
      "epoch": 0.22447257383966246,
      "grad_norm": 1.760398268699646,
      "learning_rate": 9.332161687170476e-05,
      "loss": 0.8673232197761536,
      "step": 532
    },
    {
      "epoch": 0.22531645569620254,
      "grad_norm": 0.6670058369636536,
      "learning_rate": 9.36731107205624e-05,
      "loss": 0.9942440986633301,
      "step": 534
    },
    {
      "epoch": 0.22616033755274262,
      "grad_norm": 0.7345916032791138,
      "learning_rate": 9.402460456942003e-05,
      "loss": 1.0364389419555664,
      "step": 536
    },
    {
      "epoch": 0.2270042194092827,
      "grad_norm": 0.5946128964424133,
      "learning_rate": 9.437609841827768e-05,
      "loss": 0.9314924478530884,
      "step": 538
    },
    {
      "epoch": 0.22784810126582278,
      "grad_norm": 0.5800848603248596,
      "learning_rate": 9.472759226713534e-05,
      "loss": 1.0694862604141235,
      "step": 540
    },
    {
      "epoch": 0.22869198312236286,
      "grad_norm": 0.6712192893028259,
      "learning_rate": 9.507908611599297e-05,
      "loss": 1.03531014919281,
      "step": 542
    },
    {
      "epoch": 0.22953586497890296,
      "grad_norm": 0.5641416311264038,
      "learning_rate": 9.543057996485063e-05,
      "loss": 0.9795235991477966,
      "step": 544
    },
    {
      "epoch": 0.23037974683544304,
      "grad_norm": 0.50412517786026,
      "learning_rate": 9.578207381370826e-05,
      "loss": 0.9641494750976562,
      "step": 546
    },
    {
      "epoch": 0.23122362869198312,
      "grad_norm": 0.579118549823761,
      "learning_rate": 9.61335676625659e-05,
      "loss": 0.9375281929969788,
      "step": 548
    },
    {
      "epoch": 0.2320675105485232,
      "grad_norm": 0.5888341665267944,
      "learning_rate": 9.648506151142355e-05,
      "loss": 0.9414046406745911,
      "step": 550
    },
    {
      "epoch": 0.23291139240506328,
      "grad_norm": 0.5595056414604187,
      "learning_rate": 9.68365553602812e-05,
      "loss": 0.9005617499351501,
      "step": 552
    },
    {
      "epoch": 0.23375527426160336,
      "grad_norm": 0.6605326533317566,
      "learning_rate": 9.718804920913884e-05,
      "loss": 1.0283968448638916,
      "step": 554
    },
    {
      "epoch": 0.23459915611814347,
      "grad_norm": 0.5657313466072083,
      "learning_rate": 9.753954305799648e-05,
      "loss": 1.0058249235153198,
      "step": 556
    },
    {
      "epoch": 0.23544303797468355,
      "grad_norm": 0.5433364510536194,
      "learning_rate": 9.789103690685413e-05,
      "loss": 0.9835494756698608,
      "step": 558
    },
    {
      "epoch": 0.23628691983122363,
      "grad_norm": 0.6129802465438843,
      "learning_rate": 9.824253075571179e-05,
      "loss": 1.054532527923584,
      "step": 560
    },
    {
      "epoch": 0.2371308016877637,
      "grad_norm": 0.6496239304542542,
      "learning_rate": 9.859402460456942e-05,
      "loss": 1.0240973234176636,
      "step": 562
    },
    {
      "epoch": 0.2379746835443038,
      "grad_norm": 0.6380873918533325,
      "learning_rate": 9.894551845342706e-05,
      "loss": 1.0229179859161377,
      "step": 564
    },
    {
      "epoch": 0.23881856540084387,
      "grad_norm": 0.6151993870735168,
      "learning_rate": 9.929701230228471e-05,
      "loss": 1.0111570358276367,
      "step": 566
    },
    {
      "epoch": 0.23966244725738398,
      "grad_norm": 0.5727584958076477,
      "learning_rate": 9.964850615114237e-05,
      "loss": 0.9450829029083252,
      "step": 568
    },
    {
      "epoch": 0.24050632911392406,
      "grad_norm": 0.6620725989341736,
      "learning_rate": 0.0001,
      "loss": 0.9800319075584412,
      "step": 570
    },
    {
      "epoch": 0.24135021097046414,
      "grad_norm": 0.6151163578033447,
      "learning_rate": 0.00010035149384885764,
      "loss": 0.9757438898086548,
      "step": 572
    },
    {
      "epoch": 0.24219409282700421,
      "grad_norm": 0.5672140717506409,
      "learning_rate": 0.0001007029876977153,
      "loss": 0.9104921817779541,
      "step": 574
    },
    {
      "epoch": 0.2430379746835443,
      "grad_norm": 0.5697256326675415,
      "learning_rate": 0.00010105448154657293,
      "loss": 1.1027376651763916,
      "step": 576
    },
    {
      "epoch": 0.2438818565400844,
      "grad_norm": 0.5590381622314453,
      "learning_rate": 0.00010140597539543057,
      "loss": 1.0055404901504517,
      "step": 578
    },
    {
      "epoch": 0.24472573839662448,
      "grad_norm": 0.5518567562103271,
      "learning_rate": 0.00010175746924428824,
      "loss": 1.020835518836975,
      "step": 580
    },
    {
      "epoch": 0.24556962025316456,
      "grad_norm": 0.6338496208190918,
      "learning_rate": 0.00010210896309314588,
      "loss": 0.9528344869613647,
      "step": 582
    },
    {
      "epoch": 0.24641350210970464,
      "grad_norm": 0.6497329473495483,
      "learning_rate": 0.00010246045694200353,
      "loss": 1.0088670253753662,
      "step": 584
    },
    {
      "epoch": 0.24725738396624472,
      "grad_norm": 0.49888095259666443,
      "learning_rate": 0.00010281195079086117,
      "loss": 0.9961200952529907,
      "step": 586
    },
    {
      "epoch": 0.2481012658227848,
      "grad_norm": 0.5680158734321594,
      "learning_rate": 0.0001031634446397188,
      "loss": 0.9635610580444336,
      "step": 588
    },
    {
      "epoch": 0.2489451476793249,
      "grad_norm": 0.658168375492096,
      "learning_rate": 0.00010351493848857646,
      "loss": 0.9392287135124207,
      "step": 590
    },
    {
      "epoch": 0.249789029535865,
      "grad_norm": 0.618262767791748,
      "learning_rate": 0.0001038664323374341,
      "loss": 0.9600516557693481,
      "step": 592
    },
    {
      "epoch": 0.25063291139240507,
      "grad_norm": 0.6003909111022949,
      "learning_rate": 0.00010421792618629173,
      "loss": 1.005476713180542,
      "step": 594
    },
    {
      "epoch": 0.2514767932489452,
      "grad_norm": 0.5437078475952148,
      "learning_rate": 0.00010456942003514938,
      "loss": 0.9523017406463623,
      "step": 596
    },
    {
      "epoch": 0.2523206751054852,
      "grad_norm": 0.5524541735649109,
      "learning_rate": 0.00010492091388400705,
      "loss": 0.9526668787002563,
      "step": 598
    },
    {
      "epoch": 0.25316455696202533,
      "grad_norm": 0.679504930973053,
      "learning_rate": 0.00010527240773286469,
      "loss": 1.019660472869873,
      "step": 600
    },
    {
      "epoch": 0.25316455696202533,
      "eval_loss": 1.0193854570388794,
      "eval_runtime": 677.9523,
      "eval_samples_per_second": 3.108,
      "eval_steps_per_second": 3.108,
      "step": 600
    },
    {
      "epoch": 0.2540084388185654,
      "grad_norm": 0.5646136999130249,
      "learning_rate": 0.00010562390158172233,
      "loss": 0.9910882711410522,
      "step": 602
    },
    {
      "epoch": 0.2548523206751055,
      "grad_norm": 0.5238093137741089,
      "learning_rate": 0.00010597539543057998,
      "loss": 0.9616432785987854,
      "step": 604
    },
    {
      "epoch": 0.25569620253164554,
      "grad_norm": 0.7483857274055481,
      "learning_rate": 0.00010632688927943762,
      "loss": 1.0078275203704834,
      "step": 606
    },
    {
      "epoch": 0.25654008438818565,
      "grad_norm": 0.578948974609375,
      "learning_rate": 0.00010667838312829525,
      "loss": 0.9827103018760681,
      "step": 608
    },
    {
      "epoch": 0.25738396624472576,
      "grad_norm": 0.5525906085968018,
      "learning_rate": 0.00010702987697715289,
      "loss": 1.0423277616500854,
      "step": 610
    },
    {
      "epoch": 0.2582278481012658,
      "grad_norm": 0.6721326112747192,
      "learning_rate": 0.00010738137082601054,
      "loss": 0.9561693072319031,
      "step": 612
    },
    {
      "epoch": 0.2590717299578059,
      "grad_norm": 0.5701051354408264,
      "learning_rate": 0.00010773286467486821,
      "loss": 0.9602992534637451,
      "step": 614
    },
    {
      "epoch": 0.25991561181434597,
      "grad_norm": 0.6349860429763794,
      "learning_rate": 0.00010808435852372585,
      "loss": 1.1422650814056396,
      "step": 616
    },
    {
      "epoch": 0.2607594936708861,
      "grad_norm": 0.5496085286140442,
      "learning_rate": 0.00010843585237258349,
      "loss": 0.9762773513793945,
      "step": 618
    },
    {
      "epoch": 0.2616033755274262,
      "grad_norm": 0.6080722808837891,
      "learning_rate": 0.00010878734622144114,
      "loss": 1.0133616924285889,
      "step": 620
    },
    {
      "epoch": 0.26244725738396624,
      "grad_norm": 0.5450218915939331,
      "learning_rate": 0.00010913884007029878,
      "loss": 0.9385587573051453,
      "step": 622
    },
    {
      "epoch": 0.26329113924050634,
      "grad_norm": 0.592106819152832,
      "learning_rate": 0.00010949033391915641,
      "loss": 0.9359989762306213,
      "step": 624
    },
    {
      "epoch": 0.2641350210970464,
      "grad_norm": 0.6449427604675293,
      "learning_rate": 0.00010984182776801407,
      "loss": 1.0266027450561523,
      "step": 626
    },
    {
      "epoch": 0.2649789029535865,
      "grad_norm": 0.538299560546875,
      "learning_rate": 0.0001101933216168717,
      "loss": 0.9303187131881714,
      "step": 628
    },
    {
      "epoch": 0.26582278481012656,
      "grad_norm": 0.546316921710968,
      "learning_rate": 0.00011054481546572934,
      "loss": 0.9368857145309448,
      "step": 630
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.5818730592727661,
      "learning_rate": 0.00011089630931458701,
      "loss": 0.9573145508766174,
      "step": 632
    },
    {
      "epoch": 0.26751054852320677,
      "grad_norm": 0.5958262085914612,
      "learning_rate": 0.00011124780316344465,
      "loss": 0.9345449805259705,
      "step": 634
    },
    {
      "epoch": 0.2683544303797468,
      "grad_norm": 0.6259077787399292,
      "learning_rate": 0.0001115992970123023,
      "loss": 1.0906590223312378,
      "step": 636
    },
    {
      "epoch": 0.26919831223628693,
      "grad_norm": 0.589672863483429,
      "learning_rate": 0.00011195079086115994,
      "loss": 1.0757447481155396,
      "step": 638
    },
    {
      "epoch": 0.270042194092827,
      "grad_norm": 0.5714080333709717,
      "learning_rate": 0.00011230228471001758,
      "loss": 0.9310855269432068,
      "step": 640
    },
    {
      "epoch": 0.2708860759493671,
      "grad_norm": 0.45342639088630676,
      "learning_rate": 0.00011265377855887523,
      "loss": 0.9276360273361206,
      "step": 642
    },
    {
      "epoch": 0.2717299578059072,
      "grad_norm": 0.6386750340461731,
      "learning_rate": 0.00011300527240773287,
      "loss": 1.084719181060791,
      "step": 644
    },
    {
      "epoch": 0.27257383966244725,
      "grad_norm": 0.6446163654327393,
      "learning_rate": 0.0001133567662565905,
      "loss": 0.9763918519020081,
      "step": 646
    },
    {
      "epoch": 0.27341772151898736,
      "grad_norm": 0.5925686359405518,
      "learning_rate": 0.00011370826010544816,
      "loss": 0.9517921805381775,
      "step": 648
    },
    {
      "epoch": 0.2742616033755274,
      "grad_norm": 0.5399773716926575,
      "learning_rate": 0.00011405975395430582,
      "loss": 1.0587927103042603,
      "step": 650
    },
    {
      "epoch": 0.2751054852320675,
      "grad_norm": 0.5872456431388855,
      "learning_rate": 0.00011441124780316346,
      "loss": 0.883341908454895,
      "step": 652
    },
    {
      "epoch": 0.2759493670886076,
      "grad_norm": 0.5574564337730408,
      "learning_rate": 0.0001147627416520211,
      "loss": 1.0306891202926636,
      "step": 654
    },
    {
      "epoch": 0.2767932489451477,
      "grad_norm": 0.47789013385772705,
      "learning_rate": 0.00011511423550087874,
      "loss": 0.8814032077789307,
      "step": 656
    },
    {
      "epoch": 0.2776371308016878,
      "grad_norm": 0.5565530061721802,
      "learning_rate": 0.00011546572934973639,
      "loss": 0.9460552334785461,
      "step": 658
    },
    {
      "epoch": 0.27848101265822783,
      "grad_norm": 0.5299761295318604,
      "learning_rate": 0.00011581722319859403,
      "loss": 0.9475110769271851,
      "step": 660
    },
    {
      "epoch": 0.27932489451476794,
      "grad_norm": 0.6503344178199768,
      "learning_rate": 0.00011616871704745166,
      "loss": 1.0630913972854614,
      "step": 662
    },
    {
      "epoch": 0.280168776371308,
      "grad_norm": 0.5794585943222046,
      "learning_rate": 0.00011652021089630932,
      "loss": 0.9389138221740723,
      "step": 664
    },
    {
      "epoch": 0.2810126582278481,
      "grad_norm": 0.5762867331504822,
      "learning_rate": 0.00011687170474516695,
      "loss": 0.8934136033058167,
      "step": 666
    },
    {
      "epoch": 0.2818565400843882,
      "grad_norm": 0.6565435528755188,
      "learning_rate": 0.00011722319859402462,
      "loss": 1.1072614192962646,
      "step": 668
    },
    {
      "epoch": 0.28270042194092826,
      "grad_norm": 0.5819830298423767,
      "learning_rate": 0.00011757469244288226,
      "loss": 1.0501434803009033,
      "step": 670
    },
    {
      "epoch": 0.28354430379746837,
      "grad_norm": 0.6071487069129944,
      "learning_rate": 0.00011792618629173991,
      "loss": 0.9880793690681458,
      "step": 672
    },
    {
      "epoch": 0.2843881856540084,
      "grad_norm": 0.5765058398246765,
      "learning_rate": 0.00011827768014059755,
      "loss": 0.9670693874359131,
      "step": 674
    },
    {
      "epoch": 0.2852320675105485,
      "grad_norm": 0.5245351791381836,
      "learning_rate": 0.00011862917398945519,
      "loss": 0.9602360725402832,
      "step": 676
    },
    {
      "epoch": 0.28607594936708863,
      "grad_norm": 0.6189922094345093,
      "learning_rate": 0.00011898066783831282,
      "loss": 0.9684560894966125,
      "step": 678
    },
    {
      "epoch": 0.2869198312236287,
      "grad_norm": 0.6138690710067749,
      "learning_rate": 0.00011933216168717048,
      "loss": 0.9465792775154114,
      "step": 680
    },
    {
      "epoch": 0.2877637130801688,
      "grad_norm": 0.5371595621109009,
      "learning_rate": 0.00011968365553602812,
      "loss": 0.8495944738388062,
      "step": 682
    },
    {
      "epoch": 0.28860759493670884,
      "grad_norm": 0.5549944639205933,
      "learning_rate": 0.00012003514938488578,
      "loss": 0.9663267135620117,
      "step": 684
    },
    {
      "epoch": 0.28945147679324895,
      "grad_norm": 0.6484189033508301,
      "learning_rate": 0.00012038664323374342,
      "loss": 0.9736058712005615,
      "step": 686
    },
    {
      "epoch": 0.290295358649789,
      "grad_norm": 0.540351390838623,
      "learning_rate": 0.00012073813708260107,
      "loss": 1.0591845512390137,
      "step": 688
    },
    {
      "epoch": 0.2911392405063291,
      "grad_norm": 0.5657922029495239,
      "learning_rate": 0.00012108963093145871,
      "loss": 0.944908618927002,
      "step": 690
    },
    {
      "epoch": 0.2919831223628692,
      "grad_norm": 0.6040505170822144,
      "learning_rate": 0.00012144112478031635,
      "loss": 1.0018219947814941,
      "step": 692
    },
    {
      "epoch": 0.29282700421940927,
      "grad_norm": 0.5435477495193481,
      "learning_rate": 0.000121792618629174,
      "loss": 1.0351502895355225,
      "step": 694
    },
    {
      "epoch": 0.2936708860759494,
      "grad_norm": 0.5712518692016602,
      "learning_rate": 0.00012214411247803164,
      "loss": 0.9935672283172607,
      "step": 696
    },
    {
      "epoch": 0.29451476793248943,
      "grad_norm": 0.6138222813606262,
      "learning_rate": 0.00012249560632688928,
      "loss": 1.0165108442306519,
      "step": 698
    },
    {
      "epoch": 0.29535864978902954,
      "grad_norm": 0.4495212435722351,
      "learning_rate": 0.00012284710017574691,
      "loss": 0.9334425926208496,
      "step": 700
    },
    {
      "epoch": 0.29535864978902954,
      "eval_loss": 0.996929407119751,
      "eval_runtime": 668.6398,
      "eval_samples_per_second": 3.151,
      "eval_steps_per_second": 3.151,
      "step": 700
    },
    {
      "epoch": 0.29620253164556964,
      "grad_norm": 0.5321539044380188,
      "learning_rate": 0.00012319859402460458,
      "loss": 1.0516537427902222,
      "step": 702
    },
    {
      "epoch": 0.2970464135021097,
      "grad_norm": 0.5716516971588135,
      "learning_rate": 0.00012355008787346222,
      "loss": 0.9387198686599731,
      "step": 704
    },
    {
      "epoch": 0.2978902953586498,
      "grad_norm": 0.5617920160293579,
      "learning_rate": 0.00012390158172231988,
      "loss": 0.99737948179245,
      "step": 706
    },
    {
      "epoch": 0.29873417721518986,
      "grad_norm": 0.4922899007797241,
      "learning_rate": 0.00012425307557117752,
      "loss": 0.9955025911331177,
      "step": 708
    },
    {
      "epoch": 0.29957805907172996,
      "grad_norm": 0.543501615524292,
      "learning_rate": 0.00012460456942003516,
      "loss": 0.9124280214309692,
      "step": 710
    },
    {
      "epoch": 0.30042194092827,
      "grad_norm": 0.49590054154396057,
      "learning_rate": 0.0001249560632688928,
      "loss": 0.9820216298103333,
      "step": 712
    },
    {
      "epoch": 0.3012658227848101,
      "grad_norm": 0.5984305739402771,
      "learning_rate": 0.00012530755711775044,
      "loss": 1.0152074098587036,
      "step": 714
    },
    {
      "epoch": 0.30210970464135023,
      "grad_norm": 0.9343504905700684,
      "learning_rate": 0.00012565905096660807,
      "loss": 1.0577725172042847,
      "step": 716
    },
    {
      "epoch": 0.3029535864978903,
      "grad_norm": 0.5118702054023743,
      "learning_rate": 0.0001260105448154657,
      "loss": 0.9830358028411865,
      "step": 718
    },
    {
      "epoch": 0.3037974683544304,
      "grad_norm": 0.4940392076969147,
      "learning_rate": 0.00012636203866432338,
      "loss": 0.9466043710708618,
      "step": 720
    },
    {
      "epoch": 0.30464135021097044,
      "grad_norm": 0.5965693593025208,
      "learning_rate": 0.00012671353251318104,
      "loss": 1.015270709991455,
      "step": 722
    },
    {
      "epoch": 0.30548523206751055,
      "grad_norm": 0.5020529627799988,
      "learning_rate": 0.00012706502636203868,
      "loss": 0.9703927636146545,
      "step": 724
    },
    {
      "epoch": 0.30632911392405066,
      "grad_norm": 0.6067010164260864,
      "learning_rate": 0.00012741652021089632,
      "loss": 1.0255526304244995,
      "step": 726
    },
    {
      "epoch": 0.3071729957805907,
      "grad_norm": 0.5931884050369263,
      "learning_rate": 0.00012776801405975396,
      "loss": 0.9335633516311646,
      "step": 728
    },
    {
      "epoch": 0.3080168776371308,
      "grad_norm": 0.5938752293586731,
      "learning_rate": 0.0001281195079086116,
      "loss": 1.0921578407287598,
      "step": 730
    },
    {
      "epoch": 0.30886075949367087,
      "grad_norm": 0.49728086590766907,
      "learning_rate": 0.00012847100175746923,
      "loss": 0.963066041469574,
      "step": 732
    },
    {
      "epoch": 0.309704641350211,
      "grad_norm": 0.5452080965042114,
      "learning_rate": 0.0001288224956063269,
      "loss": 0.9513075351715088,
      "step": 734
    },
    {
      "epoch": 0.3105485232067511,
      "grad_norm": 0.5497731566429138,
      "learning_rate": 0.00012917398945518454,
      "loss": 0.8576077222824097,
      "step": 736
    },
    {
      "epoch": 0.31139240506329113,
      "grad_norm": 0.5580397248268127,
      "learning_rate": 0.0001295254833040422,
      "loss": 0.9542577862739563,
      "step": 738
    },
    {
      "epoch": 0.31223628691983124,
      "grad_norm": 0.5890427827835083,
      "learning_rate": 0.00012987697715289984,
      "loss": 0.8992732167243958,
      "step": 740
    },
    {
      "epoch": 0.3130801687763713,
      "grad_norm": 0.5942965745925903,
      "learning_rate": 0.00013022847100175748,
      "loss": 1.0322896242141724,
      "step": 742
    },
    {
      "epoch": 0.3139240506329114,
      "grad_norm": 0.6341713070869446,
      "learning_rate": 0.00013057996485061512,
      "loss": 0.9217103719711304,
      "step": 744
    },
    {
      "epoch": 0.31476793248945145,
      "grad_norm": 0.5294105410575867,
      "learning_rate": 0.00013093145869947276,
      "loss": 0.951789915561676,
      "step": 746
    },
    {
      "epoch": 0.31561181434599156,
      "grad_norm": 0.6372058391571045,
      "learning_rate": 0.0001312829525483304,
      "loss": 0.9459875226020813,
      "step": 748
    },
    {
      "epoch": 0.31645569620253167,
      "grad_norm": 0.5979796648025513,
      "learning_rate": 0.00013163444639718806,
      "loss": 0.9626097679138184,
      "step": 750
    },
    {
      "epoch": 0.3172995780590717,
      "grad_norm": 0.5682399868965149,
      "learning_rate": 0.0001319859402460457,
      "loss": 1.0261781215667725,
      "step": 752
    },
    {
      "epoch": 0.3181434599156118,
      "grad_norm": 0.5349125266075134,
      "learning_rate": 0.00013233743409490336,
      "loss": 0.9319828152656555,
      "step": 754
    },
    {
      "epoch": 0.3189873417721519,
      "grad_norm": 0.6093934178352356,
      "learning_rate": 0.000132688927943761,
      "loss": 0.9216550588607788,
      "step": 756
    },
    {
      "epoch": 0.319831223628692,
      "grad_norm": 0.5188612341880798,
      "learning_rate": 0.00013304042179261864,
      "loss": 0.901739776134491,
      "step": 758
    },
    {
      "epoch": 0.3206751054852321,
      "grad_norm": 0.5877130627632141,
      "learning_rate": 0.00013339191564147628,
      "loss": 1.0362589359283447,
      "step": 760
    },
    {
      "epoch": 0.32151898734177214,
      "grad_norm": 0.5542771816253662,
      "learning_rate": 0.00013374340949033392,
      "loss": 0.8787116408348083,
      "step": 762
    },
    {
      "epoch": 0.32236286919831225,
      "grad_norm": 0.5084902048110962,
      "learning_rate": 0.00013409490333919156,
      "loss": 0.9237037301063538,
      "step": 764
    },
    {
      "epoch": 0.3232067510548523,
      "grad_norm": 0.5461528301239014,
      "learning_rate": 0.00013444639718804922,
      "loss": 1.0150731801986694,
      "step": 766
    },
    {
      "epoch": 0.3240506329113924,
      "grad_norm": 0.53483647108078,
      "learning_rate": 0.00013479789103690686,
      "loss": 0.8985214829444885,
      "step": 768
    },
    {
      "epoch": 0.32489451476793246,
      "grad_norm": 0.5580531358718872,
      "learning_rate": 0.0001351493848857645,
      "loss": 1.0225775241851807,
      "step": 770
    },
    {
      "epoch": 0.32573839662447257,
      "grad_norm": 0.5203377604484558,
      "learning_rate": 0.00013550087873462216,
      "loss": 0.9571293592453003,
      "step": 772
    },
    {
      "epoch": 0.3265822784810127,
      "grad_norm": 0.5049671530723572,
      "learning_rate": 0.0001358523725834798,
      "loss": 1.0468909740447998,
      "step": 774
    },
    {
      "epoch": 0.32742616033755273,
      "grad_norm": 0.4723063111305237,
      "learning_rate": 0.00013620386643233744,
      "loss": 0.7743215560913086,
      "step": 776
    },
    {
      "epoch": 0.32827004219409284,
      "grad_norm": 0.6310980916023254,
      "learning_rate": 0.00013655536028119508,
      "loss": 1.021510362625122,
      "step": 778
    },
    {
      "epoch": 0.3291139240506329,
      "grad_norm": 0.47066664695739746,
      "learning_rate": 0.00013690685413005274,
      "loss": 0.9134382605552673,
      "step": 780
    },
    {
      "epoch": 0.329957805907173,
      "grad_norm": 0.5725092887878418,
      "learning_rate": 0.00013725834797891038,
      "loss": 0.9797834753990173,
      "step": 782
    },
    {
      "epoch": 0.3308016877637131,
      "grad_norm": 0.5139563083648682,
      "learning_rate": 0.00013760984182776802,
      "loss": 0.9372621178627014,
      "step": 784
    },
    {
      "epoch": 0.33164556962025316,
      "grad_norm": 0.5275821685791016,
      "learning_rate": 0.00013796133567662566,
      "loss": 0.9528245329856873,
      "step": 786
    },
    {
      "epoch": 0.33248945147679326,
      "grad_norm": 0.5702582001686096,
      "learning_rate": 0.0001383128295254833,
      "loss": 0.9750176072120667,
      "step": 788
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.5281293392181396,
      "learning_rate": 0.00013866432337434096,
      "loss": 0.9412306547164917,
      "step": 790
    },
    {
      "epoch": 0.3341772151898734,
      "grad_norm": 0.5578986406326294,
      "learning_rate": 0.0001390158172231986,
      "loss": 0.997580885887146,
      "step": 792
    },
    {
      "epoch": 0.33502109704641353,
      "grad_norm": 0.50461345911026,
      "learning_rate": 0.00013936731107205624,
      "loss": 0.9082320928573608,
      "step": 794
    },
    {
      "epoch": 0.3358649789029536,
      "grad_norm": 0.5258530378341675,
      "learning_rate": 0.0001397188049209139,
      "loss": 1.0082844495773315,
      "step": 796
    },
    {
      "epoch": 0.3367088607594937,
      "grad_norm": 0.5548169016838074,
      "learning_rate": 0.00014007029876977154,
      "loss": 0.9729003310203552,
      "step": 798
    },
    {
      "epoch": 0.33755274261603374,
      "grad_norm": 0.48601076006889343,
      "learning_rate": 0.00014042179261862918,
      "loss": 0.9099526405334473,
      "step": 800
    },
    {
      "epoch": 0.33755274261603374,
      "eval_loss": 0.9800403714179993,
      "eval_runtime": 678.8306,
      "eval_samples_per_second": 3.104,
      "eval_steps_per_second": 3.104,
      "step": 800
    },
    {
      "epoch": 0.33839662447257385,
      "grad_norm": 0.5413158535957336,
      "learning_rate": 0.00014077328646748682,
      "loss": 0.8610644936561584,
      "step": 802
    },
    {
      "epoch": 0.3392405063291139,
      "grad_norm": 0.5147035717964172,
      "learning_rate": 0.00014112478031634446,
      "loss": 0.9584825038909912,
      "step": 804
    },
    {
      "epoch": 0.340084388185654,
      "grad_norm": 0.5931771397590637,
      "learning_rate": 0.0001414762741652021,
      "loss": 1.0142558813095093,
      "step": 806
    },
    {
      "epoch": 0.3409282700421941,
      "grad_norm": 0.5178377032279968,
      "learning_rate": 0.00014182776801405976,
      "loss": 1.0078763961791992,
      "step": 808
    },
    {
      "epoch": 0.34177215189873417,
      "grad_norm": 0.5453237295150757,
      "learning_rate": 0.0001421792618629174,
      "loss": 0.9107215404510498,
      "step": 810
    },
    {
      "epoch": 0.3426160337552743,
      "grad_norm": 0.5886152982711792,
      "learning_rate": 0.00014253075571177506,
      "loss": 0.9981362819671631,
      "step": 812
    },
    {
      "epoch": 0.3434599156118143,
      "grad_norm": 0.48040178418159485,
      "learning_rate": 0.0001428822495606327,
      "loss": 0.9636131525039673,
      "step": 814
    },
    {
      "epoch": 0.34430379746835443,
      "grad_norm": 0.5011753439903259,
      "learning_rate": 0.00014323374340949034,
      "loss": 0.9590586423873901,
      "step": 816
    },
    {
      "epoch": 0.34514767932489454,
      "grad_norm": 0.57858806848526,
      "learning_rate": 0.00014358523725834798,
      "loss": 0.978246808052063,
      "step": 818
    },
    {
      "epoch": 0.3459915611814346,
      "grad_norm": 0.46092939376831055,
      "learning_rate": 0.00014393673110720562,
      "loss": 0.8549934029579163,
      "step": 820
    },
    {
      "epoch": 0.3468354430379747,
      "grad_norm": 0.5756489038467407,
      "learning_rate": 0.00014428822495606326,
      "loss": 0.9771265387535095,
      "step": 822
    },
    {
      "epoch": 0.34767932489451475,
      "grad_norm": 0.5501731634140015,
      "learning_rate": 0.00014463971880492092,
      "loss": 0.8739748001098633,
      "step": 824
    },
    {
      "epoch": 0.34852320675105486,
      "grad_norm": 0.5451868176460266,
      "learning_rate": 0.0001449912126537786,
      "loss": 0.9129468202590942,
      "step": 826
    },
    {
      "epoch": 0.3493670886075949,
      "grad_norm": 0.4624619781970978,
      "learning_rate": 0.00014534270650263623,
      "loss": 0.9196704030036926,
      "step": 828
    },
    {
      "epoch": 0.350210970464135,
      "grad_norm": 0.520878791809082,
      "learning_rate": 0.00014569420035149386,
      "loss": 0.9976527690887451,
      "step": 830
    },
    {
      "epoch": 0.3510548523206751,
      "grad_norm": 0.4469171464443207,
      "learning_rate": 0.0001460456942003515,
      "loss": 0.7753443717956543,
      "step": 832
    },
    {
      "epoch": 0.3518987341772152,
      "grad_norm": 0.5105249881744385,
      "learning_rate": 0.00014639718804920914,
      "loss": 0.9584846496582031,
      "step": 834
    },
    {
      "epoch": 0.3527426160337553,
      "grad_norm": 0.5043913125991821,
      "learning_rate": 0.00014674868189806678,
      "loss": 0.9013500213623047,
      "step": 836
    },
    {
      "epoch": 0.35358649789029534,
      "grad_norm": 0.575850784778595,
      "learning_rate": 0.00014710017574692442,
      "loss": 0.9775562286376953,
      "step": 838
    },
    {
      "epoch": 0.35443037974683544,
      "grad_norm": 0.5128876566886902,
      "learning_rate": 0.00014745166959578208,
      "loss": 0.9278940558433533,
      "step": 840
    },
    {
      "epoch": 0.35527426160337555,
      "grad_norm": 0.5757885575294495,
      "learning_rate": 0.00014780316344463975,
      "loss": 1.0091488361358643,
      "step": 842
    },
    {
      "epoch": 0.3561181434599156,
      "grad_norm": 0.500934898853302,
      "learning_rate": 0.00014815465729349739,
      "loss": 0.9286836981773376,
      "step": 844
    },
    {
      "epoch": 0.3569620253164557,
      "grad_norm": 0.5220686197280884,
      "learning_rate": 0.00014850615114235502,
      "loss": 0.9484171867370605,
      "step": 846
    },
    {
      "epoch": 0.35780590717299576,
      "grad_norm": 0.5494697690010071,
      "learning_rate": 0.00014885764499121266,
      "loss": 1.0556397438049316,
      "step": 848
    },
    {
      "epoch": 0.35864978902953587,
      "grad_norm": 0.46633943915367126,
      "learning_rate": 0.0001492091388400703,
      "loss": 0.933089017868042,
      "step": 850
    },
    {
      "epoch": 0.3594936708860759,
      "grad_norm": 0.4864962697029114,
      "learning_rate": 0.00014956063268892794,
      "loss": 1.0016963481903076,
      "step": 852
    },
    {
      "epoch": 0.36033755274261603,
      "grad_norm": 0.5032764673233032,
      "learning_rate": 0.0001499121265377856,
      "loss": 0.9085348844528198,
      "step": 854
    },
    {
      "epoch": 0.36118143459915614,
      "grad_norm": 0.5424998998641968,
      "learning_rate": 0.00015026362038664324,
      "loss": 0.923502504825592,
      "step": 856
    },
    {
      "epoch": 0.3620253164556962,
      "grad_norm": 0.5181655287742615,
      "learning_rate": 0.00015061511423550088,
      "loss": 0.919174313545227,
      "step": 858
    },
    {
      "epoch": 0.3628691983122363,
      "grad_norm": 0.5129443407058716,
      "learning_rate": 0.00015096660808435855,
      "loss": 0.851981520652771,
      "step": 860
    },
    {
      "epoch": 0.36371308016877635,
      "grad_norm": 0.49540698528289795,
      "learning_rate": 0.00015131810193321618,
      "loss": 0.8633858561515808,
      "step": 862
    },
    {
      "epoch": 0.36455696202531646,
      "grad_norm": 0.4706701934337616,
      "learning_rate": 0.00015166959578207382,
      "loss": 0.9473677277565002,
      "step": 864
    },
    {
      "epoch": 0.36540084388185656,
      "grad_norm": 0.587704598903656,
      "learning_rate": 0.00015202108963093146,
      "loss": 0.942383885383606,
      "step": 866
    },
    {
      "epoch": 0.3662447257383966,
      "grad_norm": 0.5851273536682129,
      "learning_rate": 0.0001523725834797891,
      "loss": 0.9811251163482666,
      "step": 868
    },
    {
      "epoch": 0.3670886075949367,
      "grad_norm": 0.46357613801956177,
      "learning_rate": 0.00015272407732864676,
      "loss": 0.8151084184646606,
      "step": 870
    },
    {
      "epoch": 0.3679324894514768,
      "grad_norm": 0.47250670194625854,
      "learning_rate": 0.0001530755711775044,
      "loss": 0.9023333191871643,
      "step": 872
    },
    {
      "epoch": 0.3687763713080169,
      "grad_norm": 0.47510042786598206,
      "learning_rate": 0.00015342706502636204,
      "loss": 0.8758499622344971,
      "step": 874
    },
    {
      "epoch": 0.369620253164557,
      "grad_norm": 0.5687124729156494,
      "learning_rate": 0.00015377855887521968,
      "loss": 0.9837421774864197,
      "step": 876
    },
    {
      "epoch": 0.37046413502109704,
      "grad_norm": 0.49064236879348755,
      "learning_rate": 0.00015413005272407735,
      "loss": 0.9084216356277466,
      "step": 878
    },
    {
      "epoch": 0.37130801687763715,
      "grad_norm": 0.5288164615631104,
      "learning_rate": 0.00015448154657293498,
      "loss": 0.8425542712211609,
      "step": 880
    },
    {
      "epoch": 0.3721518987341772,
      "grad_norm": 0.5446951985359192,
      "learning_rate": 0.00015483304042179262,
      "loss": 1.006197452545166,
      "step": 882
    },
    {
      "epoch": 0.3729957805907173,
      "grad_norm": 0.46872642636299133,
      "learning_rate": 0.00015518453427065026,
      "loss": 0.9779444932937622,
      "step": 884
    },
    {
      "epoch": 0.37383966244725736,
      "grad_norm": 0.4852714240550995,
      "learning_rate": 0.00015553602811950793,
      "loss": 0.9099963307380676,
      "step": 886
    },
    {
      "epoch": 0.37468354430379747,
      "grad_norm": 0.5219841003417969,
      "learning_rate": 0.00015588752196836556,
      "loss": 0.9730570316314697,
      "step": 888
    },
    {
      "epoch": 0.3755274261603376,
      "grad_norm": 0.5258626341819763,
      "learning_rate": 0.0001562390158172232,
      "loss": 0.9304586052894592,
      "step": 890
    },
    {
      "epoch": 0.3763713080168776,
      "grad_norm": 0.4266716241836548,
      "learning_rate": 0.00015659050966608084,
      "loss": 0.8680716156959534,
      "step": 892
    },
    {
      "epoch": 0.37721518987341773,
      "grad_norm": 0.46361327171325684,
      "learning_rate": 0.0001569420035149385,
      "loss": 0.8428018093109131,
      "step": 894
    },
    {
      "epoch": 0.3780590717299578,
      "grad_norm": 0.5313687920570374,
      "learning_rate": 0.00015729349736379614,
      "loss": 0.8465750217437744,
      "step": 896
    },
    {
      "epoch": 0.3789029535864979,
      "grad_norm": 0.47166210412979126,
      "learning_rate": 0.00015764499121265378,
      "loss": 0.9120327234268188,
      "step": 898
    },
    {
      "epoch": 0.379746835443038,
      "grad_norm": 0.4647318720817566,
      "learning_rate": 0.00015799648506151145,
      "loss": 0.8950425982475281,
      "step": 900
    },
    {
      "epoch": 0.379746835443038,
      "eval_loss": 0.9643027186393738,
      "eval_runtime": 691.7929,
      "eval_samples_per_second": 3.046,
      "eval_steps_per_second": 3.046,
      "step": 900
    },
    {
      "epoch": 0.38059071729957805,
      "grad_norm": 0.5445119738578796,
      "learning_rate": 0.00015834797891036909,
      "loss": 0.908163845539093,
      "step": 902
    },
    {
      "epoch": 0.38143459915611816,
      "grad_norm": 0.4311858117580414,
      "learning_rate": 0.00015869947275922672,
      "loss": 0.8945821523666382,
      "step": 904
    },
    {
      "epoch": 0.3822784810126582,
      "grad_norm": 0.5590984225273132,
      "learning_rate": 0.00015905096660808436,
      "loss": 0.9478458762168884,
      "step": 906
    },
    {
      "epoch": 0.3831223628691983,
      "grad_norm": 0.5470241904258728,
      "learning_rate": 0.000159402460456942,
      "loss": 0.9259957671165466,
      "step": 908
    },
    {
      "epoch": 0.38396624472573837,
      "grad_norm": 0.5498791337013245,
      "learning_rate": 0.00015975395430579964,
      "loss": 0.8824930787086487,
      "step": 910
    },
    {
      "epoch": 0.3848101265822785,
      "grad_norm": 0.4779198467731476,
      "learning_rate": 0.0001601054481546573,
      "loss": 0.8842340707778931,
      "step": 912
    },
    {
      "epoch": 0.3856540084388186,
      "grad_norm": 0.5390620827674866,
      "learning_rate": 0.00016045694200351494,
      "loss": 0.92950040102005,
      "step": 914
    },
    {
      "epoch": 0.38649789029535864,
      "grad_norm": 0.505519688129425,
      "learning_rate": 0.0001608084358523726,
      "loss": 0.8420897126197815,
      "step": 916
    },
    {
      "epoch": 0.38734177215189874,
      "grad_norm": 0.4463907778263092,
      "learning_rate": 0.00016115992970123025,
      "loss": 0.8256624341011047,
      "step": 918
    },
    {
      "epoch": 0.3881856540084388,
      "grad_norm": 0.5321422219276428,
      "learning_rate": 0.00016151142355008788,
      "loss": 0.8701168298721313,
      "step": 920
    },
    {
      "epoch": 0.3890295358649789,
      "grad_norm": 0.4343073070049286,
      "learning_rate": 0.00016186291739894552,
      "loss": 0.9019309878349304,
      "step": 922
    },
    {
      "epoch": 0.389873417721519,
      "grad_norm": 0.5311984419822693,
      "learning_rate": 0.00016221441124780316,
      "loss": 0.8560551404953003,
      "step": 924
    },
    {
      "epoch": 0.39071729957805906,
      "grad_norm": 0.588691771030426,
      "learning_rate": 0.0001625659050966608,
      "loss": 0.9700050354003906,
      "step": 926
    },
    {
      "epoch": 0.39156118143459917,
      "grad_norm": 0.5425586104393005,
      "learning_rate": 0.00016291739894551844,
      "loss": 1.043768048286438,
      "step": 928
    },
    {
      "epoch": 0.3924050632911392,
      "grad_norm": 0.5228736996650696,
      "learning_rate": 0.0001632688927943761,
      "loss": 0.9501712918281555,
      "step": 930
    },
    {
      "epoch": 0.39324894514767933,
      "grad_norm": 0.48960360884666443,
      "learning_rate": 0.00016362038664323377,
      "loss": 0.9223058223724365,
      "step": 932
    },
    {
      "epoch": 0.39409282700421944,
      "grad_norm": 0.45204755663871765,
      "learning_rate": 0.0001639718804920914,
      "loss": 0.9692960977554321,
      "step": 934
    },
    {
      "epoch": 0.3949367088607595,
      "grad_norm": 0.5299274921417236,
      "learning_rate": 0.00016432337434094905,
      "loss": 0.9467466473579407,
      "step": 936
    },
    {
      "epoch": 0.3957805907172996,
      "grad_norm": 0.5607715249061584,
      "learning_rate": 0.00016467486818980668,
      "loss": 0.9118053317070007,
      "step": 938
    },
    {
      "epoch": 0.39662447257383965,
      "grad_norm": 0.5271831154823303,
      "learning_rate": 0.00016502636203866432,
      "loss": 0.9131460189819336,
      "step": 940
    },
    {
      "epoch": 0.39746835443037976,
      "grad_norm": 0.5075286030769348,
      "learning_rate": 0.00016537785588752196,
      "loss": 0.9358300566673279,
      "step": 942
    },
    {
      "epoch": 0.3983122362869198,
      "grad_norm": 0.515731155872345,
      "learning_rate": 0.00016572934973637963,
      "loss": 0.8908210396766663,
      "step": 944
    },
    {
      "epoch": 0.3991561181434599,
      "grad_norm": 0.4856977164745331,
      "learning_rate": 0.00016608084358523726,
      "loss": 0.9775290489196777,
      "step": 946
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.48846355080604553,
      "learning_rate": 0.00016643233743409493,
      "loss": 0.8957490921020508,
      "step": 948
    },
    {
      "epoch": 0.4008438818565401,
      "grad_norm": 0.42990800738334656,
      "learning_rate": 0.00016678383128295257,
      "loss": 0.9036174416542053,
      "step": 950
    },
    {
      "epoch": 0.4016877637130802,
      "grad_norm": 0.49552062153816223,
      "learning_rate": 0.0001671353251318102,
      "loss": 0.991032600402832,
      "step": 952
    },
    {
      "epoch": 0.40253164556962023,
      "grad_norm": 0.4565040171146393,
      "learning_rate": 0.00016748681898066784,
      "loss": 0.823063313961029,
      "step": 954
    },
    {
      "epoch": 0.40337552742616034,
      "grad_norm": 0.4290153682231903,
      "learning_rate": 0.00016783831282952548,
      "loss": 0.8785063624382019,
      "step": 956
    },
    {
      "epoch": 0.40421940928270045,
      "grad_norm": 0.5419702529907227,
      "learning_rate": 0.00016818980667838312,
      "loss": 0.8763971924781799,
      "step": 958
    },
    {
      "epoch": 0.4050632911392405,
      "grad_norm": 0.5177501440048218,
      "learning_rate": 0.00016854130052724079,
      "loss": 0.9470553398132324,
      "step": 960
    },
    {
      "epoch": 0.4059071729957806,
      "grad_norm": 0.539725661277771,
      "learning_rate": 0.00016889279437609842,
      "loss": 0.9235025644302368,
      "step": 962
    },
    {
      "epoch": 0.40675105485232066,
      "grad_norm": 0.5324983596801758,
      "learning_rate": 0.0001692442882249561,
      "loss": 1.0248996019363403,
      "step": 964
    },
    {
      "epoch": 0.40759493670886077,
      "grad_norm": 0.4936407506465912,
      "learning_rate": 0.00016959578207381373,
      "loss": 0.9076873660087585,
      "step": 966
    },
    {
      "epoch": 0.4084388185654008,
      "grad_norm": 0.4960501194000244,
      "learning_rate": 0.00016994727592267137,
      "loss": 0.9162673950195312,
      "step": 968
    },
    {
      "epoch": 0.4092827004219409,
      "grad_norm": 0.45093682408332825,
      "learning_rate": 0.000170298769771529,
      "loss": 0.904100775718689,
      "step": 970
    },
    {
      "epoch": 0.41012658227848103,
      "grad_norm": 0.4560275077819824,
      "learning_rate": 0.00017065026362038664,
      "loss": 0.8633337020874023,
      "step": 972
    },
    {
      "epoch": 0.4109704641350211,
      "grad_norm": 0.44885000586509705,
      "learning_rate": 0.00017100175746924428,
      "loss": 0.8454209566116333,
      "step": 974
    },
    {
      "epoch": 0.4118143459915612,
      "grad_norm": 0.47251659631729126,
      "learning_rate": 0.00017135325131810195,
      "loss": 0.824730396270752,
      "step": 976
    },
    {
      "epoch": 0.41265822784810124,
      "grad_norm": 0.6597666144371033,
      "learning_rate": 0.00017170474516695959,
      "loss": 0.9496501684188843,
      "step": 978
    },
    {
      "epoch": 0.41350210970464135,
      "grad_norm": 0.39806297421455383,
      "learning_rate": 0.00017205623901581722,
      "loss": 0.9419087171554565,
      "step": 980
    },
    {
      "epoch": 0.41434599156118146,
      "grad_norm": 0.48231109976768494,
      "learning_rate": 0.0001724077328646749,
      "loss": 0.9182976484298706,
      "step": 982
    },
    {
      "epoch": 0.4151898734177215,
      "grad_norm": 0.5438776612281799,
      "learning_rate": 0.00017275922671353253,
      "loss": 0.9386967420578003,
      "step": 984
    },
    {
      "epoch": 0.4160337552742616,
      "grad_norm": 0.4959667921066284,
      "learning_rate": 0.00017311072056239017,
      "loss": 0.897849440574646,
      "step": 986
    },
    {
      "epoch": 0.41687763713080167,
      "grad_norm": 0.43533357977867126,
      "learning_rate": 0.0001734622144112478,
      "loss": 0.8776953816413879,
      "step": 988
    },
    {
      "epoch": 0.4177215189873418,
      "grad_norm": 0.47513946890830994,
      "learning_rate": 0.00017381370826010547,
      "loss": 0.9162989854812622,
      "step": 990
    },
    {
      "epoch": 0.41856540084388183,
      "grad_norm": 0.4907188415527344,
      "learning_rate": 0.0001741652021089631,
      "loss": 0.9482660889625549,
      "step": 992
    },
    {
      "epoch": 0.41940928270042194,
      "grad_norm": 0.44499966502189636,
      "learning_rate": 0.00017451669595782075,
      "loss": 0.8812930583953857,
      "step": 994
    },
    {
      "epoch": 0.42025316455696204,
      "grad_norm": 0.4535730481147766,
      "learning_rate": 0.00017486818980667838,
      "loss": 0.9439874887466431,
      "step": 996
    },
    {
      "epoch": 0.4210970464135021,
      "grad_norm": 0.5240745544433594,
      "learning_rate": 0.00017521968365553602,
      "loss": 0.8818395137786865,
      "step": 998
    },
    {
      "epoch": 0.4219409282700422,
      "grad_norm": 0.5301211476325989,
      "learning_rate": 0.0001755711775043937,
      "loss": 0.886186957359314,
      "step": 1000
    },
    {
      "epoch": 0.4219409282700422,
      "eval_loss": 0.9487298727035522,
      "eval_runtime": 689.4288,
      "eval_samples_per_second": 3.056,
      "eval_steps_per_second": 3.056,
      "step": 1000
    },
    {
      "epoch": 0.42278481012658226,
      "grad_norm": 0.47876957058906555,
      "learning_rate": 0.00017592267135325133,
      "loss": 0.8814021348953247,
      "step": 1002
    },
    {
      "epoch": 0.42362869198312236,
      "grad_norm": 0.4929780960083008,
      "learning_rate": 0.00017627416520210896,
      "loss": 0.8295068740844727,
      "step": 1004
    },
    {
      "epoch": 0.42447257383966247,
      "grad_norm": 0.41888436675071716,
      "learning_rate": 0.00017662565905096663,
      "loss": 0.8364827036857605,
      "step": 1006
    },
    {
      "epoch": 0.4253164556962025,
      "grad_norm": 0.5175151824951172,
      "learning_rate": 0.00017697715289982427,
      "loss": 1.0167189836502075,
      "step": 1008
    },
    {
      "epoch": 0.42616033755274263,
      "grad_norm": 0.4815356135368347,
      "learning_rate": 0.0001773286467486819,
      "loss": 0.8460752964019775,
      "step": 1010
    },
    {
      "epoch": 0.4270042194092827,
      "grad_norm": 0.5210875272750854,
      "learning_rate": 0.00017768014059753954,
      "loss": 0.8595574498176575,
      "step": 1012
    },
    {
      "epoch": 0.4278481012658228,
      "grad_norm": 0.4400486946105957,
      "learning_rate": 0.00017803163444639718,
      "loss": 0.8764723539352417,
      "step": 1014
    },
    {
      "epoch": 0.4286919831223629,
      "grad_norm": 0.5282127857208252,
      "learning_rate": 0.00017838312829525482,
      "loss": 0.9706798791885376,
      "step": 1016
    },
    {
      "epoch": 0.42953586497890295,
      "grad_norm": 0.47523441910743713,
      "learning_rate": 0.00017873462214411249,
      "loss": 0.8912002444267273,
      "step": 1018
    },
    {
      "epoch": 0.43037974683544306,
      "grad_norm": 0.49640706181526184,
      "learning_rate": 0.00017908611599297012,
      "loss": 0.8835636973381042,
      "step": 1020
    },
    {
      "epoch": 0.4312236286919831,
      "grad_norm": 0.5253039002418518,
      "learning_rate": 0.0001794376098418278,
      "loss": 0.8711735606193542,
      "step": 1022
    },
    {
      "epoch": 0.4320675105485232,
      "grad_norm": 0.49285009503364563,
      "learning_rate": 0.00017978910369068543,
      "loss": 0.9064869284629822,
      "step": 1024
    },
    {
      "epoch": 0.43291139240506327,
      "grad_norm": 0.48758041858673096,
      "learning_rate": 0.00018014059753954307,
      "loss": 0.8993359208106995,
      "step": 1026
    },
    {
      "epoch": 0.4337552742616034,
      "grad_norm": 0.4815461039543152,
      "learning_rate": 0.0001804920913884007,
      "loss": 0.8747937679290771,
      "step": 1028
    },
    {
      "epoch": 0.4345991561181435,
      "grad_norm": 0.4930349886417389,
      "learning_rate": 0.00018084358523725834,
      "loss": 0.8879084587097168,
      "step": 1030
    },
    {
      "epoch": 0.43544303797468353,
      "grad_norm": 0.49303027987480164,
      "learning_rate": 0.00018119507908611598,
      "loss": 1.0023083686828613,
      "step": 1032
    },
    {
      "epoch": 0.43628691983122364,
      "grad_norm": 0.5312249064445496,
      "learning_rate": 0.00018154657293497365,
      "loss": 0.938680112361908,
      "step": 1034
    },
    {
      "epoch": 0.4371308016877637,
      "grad_norm": 0.5174582004547119,
      "learning_rate": 0.0001818980667838313,
      "loss": 0.854195773601532,
      "step": 1036
    },
    {
      "epoch": 0.4379746835443038,
      "grad_norm": 0.5452545881271362,
      "learning_rate": 0.00018224956063268895,
      "loss": 0.9059375524520874,
      "step": 1038
    },
    {
      "epoch": 0.4388185654008439,
      "grad_norm": 0.5480839014053345,
      "learning_rate": 0.0001826010544815466,
      "loss": 0.9708920121192932,
      "step": 1040
    },
    {
      "epoch": 0.43966244725738396,
      "grad_norm": 0.44693151116371155,
      "learning_rate": 0.00018295254833040423,
      "loss": 0.8561046123504639,
      "step": 1042
    },
    {
      "epoch": 0.44050632911392407,
      "grad_norm": 0.4024234116077423,
      "learning_rate": 0.00018330404217926187,
      "loss": 0.8811968564987183,
      "step": 1044
    },
    {
      "epoch": 0.4413502109704641,
      "grad_norm": 0.5586408376693726,
      "learning_rate": 0.0001836555360281195,
      "loss": 0.978068470954895,
      "step": 1046
    },
    {
      "epoch": 0.4421940928270042,
      "grad_norm": 0.4918624758720398,
      "learning_rate": 0.00018400702987697714,
      "loss": 0.8640981316566467,
      "step": 1048
    },
    {
      "epoch": 0.4430379746835443,
      "grad_norm": 0.4335230588912964,
      "learning_rate": 0.0001843585237258348,
      "loss": 0.9077964425086975,
      "step": 1050
    },
    {
      "epoch": 0.4438818565400844,
      "grad_norm": 0.5275123715400696,
      "learning_rate": 0.00018471001757469247,
      "loss": 0.960682213306427,
      "step": 1052
    },
    {
      "epoch": 0.4447257383966245,
      "grad_norm": 0.5144415497779846,
      "learning_rate": 0.0001850615114235501,
      "loss": 0.8549577593803406,
      "step": 1054
    },
    {
      "epoch": 0.44556962025316454,
      "grad_norm": 0.5166662931442261,
      "learning_rate": 0.00018541300527240775,
      "loss": 0.9320827126502991,
      "step": 1056
    },
    {
      "epoch": 0.44641350210970465,
      "grad_norm": 0.5011980533599854,
      "learning_rate": 0.0001857644991212654,
      "loss": 0.9632431864738464,
      "step": 1058
    },
    {
      "epoch": 0.4472573839662447,
      "grad_norm": 0.49312469363212585,
      "learning_rate": 0.00018611599297012303,
      "loss": 0.9442946910858154,
      "step": 1060
    },
    {
      "epoch": 0.4481012658227848,
      "grad_norm": 0.49958568811416626,
      "learning_rate": 0.00018646748681898066,
      "loss": 0.952802300453186,
      "step": 1062
    },
    {
      "epoch": 0.4489451476793249,
      "grad_norm": 0.49827462434768677,
      "learning_rate": 0.00018681898066783833,
      "loss": 0.9630650877952576,
      "step": 1064
    },
    {
      "epoch": 0.44978902953586497,
      "grad_norm": 0.523980438709259,
      "learning_rate": 0.00018717047451669597,
      "loss": 0.9081395268440247,
      "step": 1066
    },
    {
      "epoch": 0.4506329113924051,
      "grad_norm": 0.5108568668365479,
      "learning_rate": 0.0001875219683655536,
      "loss": 0.9398958683013916,
      "step": 1068
    },
    {
      "epoch": 0.45147679324894513,
      "grad_norm": 0.4453965127468109,
      "learning_rate": 0.00018787346221441127,
      "loss": 0.93592768907547,
      "step": 1070
    },
    {
      "epoch": 0.45232067510548524,
      "grad_norm": 0.4675683081150055,
      "learning_rate": 0.0001882249560632689,
      "loss": 0.8879633545875549,
      "step": 1072
    },
    {
      "epoch": 0.4531645569620253,
      "grad_norm": 0.47398847341537476,
      "learning_rate": 0.00018857644991212655,
      "loss": 0.9966004490852356,
      "step": 1074
    },
    {
      "epoch": 0.4540084388185654,
      "grad_norm": 0.46053192019462585,
      "learning_rate": 0.0001889279437609842,
      "loss": 0.9184179902076721,
      "step": 1076
    },
    {
      "epoch": 0.4548523206751055,
      "grad_norm": 0.5601398348808289,
      "learning_rate": 0.00018927943760984182,
      "loss": 0.9434974193572998,
      "step": 1078
    },
    {
      "epoch": 0.45569620253164556,
      "grad_norm": 0.48422637581825256,
      "learning_rate": 0.0001896309314586995,
      "loss": 0.9522465467453003,
      "step": 1080
    },
    {
      "epoch": 0.45654008438818566,
      "grad_norm": 0.46280911564826965,
      "learning_rate": 0.00018998242530755713,
      "loss": 0.9315434694290161,
      "step": 1082
    },
    {
      "epoch": 0.4573839662447257,
      "grad_norm": 0.4658683240413666,
      "learning_rate": 0.00019033391915641477,
      "loss": 0.8165783286094666,
      "step": 1084
    },
    {
      "epoch": 0.4582278481012658,
      "grad_norm": 0.4192182123661041,
      "learning_rate": 0.0001906854130052724,
      "loss": 0.8024274110794067,
      "step": 1086
    },
    {
      "epoch": 0.45907172995780593,
      "grad_norm": 0.4178735613822937,
      "learning_rate": 0.00019103690685413007,
      "loss": 0.8620653748512268,
      "step": 1088
    },
    {
      "epoch": 0.459915611814346,
      "grad_norm": 0.4488574266433716,
      "learning_rate": 0.0001913884007029877,
      "loss": 0.9121530055999756,
      "step": 1090
    },
    {
      "epoch": 0.4607594936708861,
      "grad_norm": 0.5164965987205505,
      "learning_rate": 0.00019173989455184535,
      "loss": 0.9496700763702393,
      "step": 1092
    },
    {
      "epoch": 0.46160337552742614,
      "grad_norm": 0.41563132405281067,
      "learning_rate": 0.00019209138840070299,
      "loss": 0.8757708668708801,
      "step": 1094
    },
    {
      "epoch": 0.46244725738396625,
      "grad_norm": 2.3222429752349854,
      "learning_rate": 0.00019244288224956065,
      "loss": 0.8406533002853394,
      "step": 1096
    },
    {
      "epoch": 0.46329113924050636,
      "grad_norm": 0.4813845157623291,
      "learning_rate": 0.0001927943760984183,
      "loss": 0.9459465742111206,
      "step": 1098
    },
    {
      "epoch": 0.4641350210970464,
      "grad_norm": 0.6233882308006287,
      "learning_rate": 0.00019314586994727593,
      "loss": 0.9376904368400574,
      "step": 1100
    },
    {
      "epoch": 0.4641350210970464,
      "eval_loss": 0.9357889294624329,
      "eval_runtime": 676.9573,
      "eval_samples_per_second": 3.112,
      "eval_steps_per_second": 3.112,
      "step": 1100
    },
    {
      "epoch": 0.4649789029535865,
      "grad_norm": 0.5125579237937927,
      "learning_rate": 0.00019349736379613357,
      "loss": 0.8998825550079346,
      "step": 1102
    },
    {
      "epoch": 0.46582278481012657,
      "grad_norm": 0.4534320831298828,
      "learning_rate": 0.00019384885764499123,
      "loss": 0.9213768839836121,
      "step": 1104
    },
    {
      "epoch": 0.4666666666666667,
      "grad_norm": 0.4715143144130707,
      "learning_rate": 0.00019420035149384887,
      "loss": 0.9739661812782288,
      "step": 1106
    },
    {
      "epoch": 0.4675105485232067,
      "grad_norm": 0.45529672503471375,
      "learning_rate": 0.0001945518453427065,
      "loss": 0.9113216400146484,
      "step": 1108
    },
    {
      "epoch": 0.46835443037974683,
      "grad_norm": 0.48199015855789185,
      "learning_rate": 0.00019490333919156417,
      "loss": 0.92528235912323,
      "step": 1110
    },
    {
      "epoch": 0.46919831223628694,
      "grad_norm": 0.4425188899040222,
      "learning_rate": 0.0001952548330404218,
      "loss": 0.8612716197967529,
      "step": 1112
    },
    {
      "epoch": 0.470042194092827,
      "grad_norm": 0.4311593770980835,
      "learning_rate": 0.00019560632688927945,
      "loss": 0.8901699185371399,
      "step": 1114
    },
    {
      "epoch": 0.4708860759493671,
      "grad_norm": 0.497806578874588,
      "learning_rate": 0.0001959578207381371,
      "loss": 0.9271994829177856,
      "step": 1116
    },
    {
      "epoch": 0.47172995780590715,
      "grad_norm": 0.47149473428726196,
      "learning_rate": 0.00019630931458699473,
      "loss": 0.8740925788879395,
      "step": 1118
    },
    {
      "epoch": 0.47257383966244726,
      "grad_norm": 0.5029966235160828,
      "learning_rate": 0.00019666080843585236,
      "loss": 0.9190115928649902,
      "step": 1120
    },
    {
      "epoch": 0.47341772151898737,
      "grad_norm": 0.47972601652145386,
      "learning_rate": 0.00019701230228471003,
      "loss": 1.0043057203292847,
      "step": 1122
    },
    {
      "epoch": 0.4742616033755274,
      "grad_norm": 0.45096471905708313,
      "learning_rate": 0.00019736379613356767,
      "loss": 0.9472925066947937,
      "step": 1124
    },
    {
      "epoch": 0.4751054852320675,
      "grad_norm": 0.459852933883667,
      "learning_rate": 0.00019771528998242533,
      "loss": 0.8043124079704285,
      "step": 1126
    },
    {
      "epoch": 0.4759493670886076,
      "grad_norm": 0.5313422679901123,
      "learning_rate": 0.00019806678383128297,
      "loss": 0.9662142395973206,
      "step": 1128
    },
    {
      "epoch": 0.4767932489451477,
      "grad_norm": 0.43474531173706055,
      "learning_rate": 0.0001984182776801406,
      "loss": 0.8691151738166809,
      "step": 1130
    },
    {
      "epoch": 0.47763713080168774,
      "grad_norm": 0.5232312083244324,
      "learning_rate": 0.00019876977152899825,
      "loss": 0.9024254083633423,
      "step": 1132
    },
    {
      "epoch": 0.47848101265822784,
      "grad_norm": 0.47671905159950256,
      "learning_rate": 0.0001991212653778559,
      "loss": 0.8996873497962952,
      "step": 1134
    },
    {
      "epoch": 0.47932489451476795,
      "grad_norm": 0.42289480566978455,
      "learning_rate": 0.00019947275922671353,
      "loss": 0.8336917757987976,
      "step": 1136
    },
    {
      "epoch": 0.480168776371308,
      "grad_norm": 0.4700844883918762,
      "learning_rate": 0.0001998242530755712,
      "loss": 0.8943206071853638,
      "step": 1138
    },
    {
      "epoch": 0.4810126582278481,
      "grad_norm": 0.5341399312019348,
      "learning_rate": 0.00019999999711649004,
      "loss": 0.9340365529060364,
      "step": 1140
    },
    {
      "epoch": 0.48185654008438816,
      "grad_norm": 0.46169522404670715,
      "learning_rate": 0.00019999997404841123,
      "loss": 0.8241778016090393,
      "step": 1142
    },
    {
      "epoch": 0.48270042194092827,
      "grad_norm": 0.5475223064422607,
      "learning_rate": 0.00019999992791225896,
      "loss": 1.0096158981323242,
      "step": 1144
    },
    {
      "epoch": 0.4835443037974684,
      "grad_norm": 0.524641215801239,
      "learning_rate": 0.00019999985870804385,
      "loss": 0.9650378227233887,
      "step": 1146
    },
    {
      "epoch": 0.48438818565400843,
      "grad_norm": 0.4326174855232239,
      "learning_rate": 0.00019999976643578186,
      "loss": 0.9003009796142578,
      "step": 1148
    },
    {
      "epoch": 0.48523206751054854,
      "grad_norm": 0.49034059047698975,
      "learning_rate": 0.0001999996510954943,
      "loss": 0.9793432950973511,
      "step": 1150
    },
    {
      "epoch": 0.4860759493670886,
      "grad_norm": 0.4760092496871948,
      "learning_rate": 0.00019999951268720776,
      "loss": 0.8793007731437683,
      "step": 1152
    },
    {
      "epoch": 0.4869198312236287,
      "grad_norm": 0.44606879353523254,
      "learning_rate": 0.00019999935121095417,
      "loss": 0.888630747795105,
      "step": 1154
    },
    {
      "epoch": 0.4877637130801688,
      "grad_norm": 0.5030332207679749,
      "learning_rate": 0.0001999991666667708,
      "loss": 0.9660000801086426,
      "step": 1156
    },
    {
      "epoch": 0.48860759493670886,
      "grad_norm": 0.4295555055141449,
      "learning_rate": 0.00019999895905470014,
      "loss": 0.824654757976532,
      "step": 1158
    },
    {
      "epoch": 0.48945147679324896,
      "grad_norm": 0.392167866230011,
      "learning_rate": 0.0001999987283747902,
      "loss": 0.8159562349319458,
      "step": 1160
    },
    {
      "epoch": 0.490295358649789,
      "grad_norm": 0.484611839056015,
      "learning_rate": 0.00019999847462709412,
      "loss": 0.9630686044692993,
      "step": 1162
    },
    {
      "epoch": 0.4911392405063291,
      "grad_norm": 0.45891445875167847,
      "learning_rate": 0.00019999819781167042,
      "loss": 0.8396129608154297,
      "step": 1164
    },
    {
      "epoch": 0.4919831223628692,
      "grad_norm": 0.5553452968597412,
      "learning_rate": 0.00019999789792858304,
      "loss": 0.8194513916969299,
      "step": 1166
    },
    {
      "epoch": 0.4928270042194093,
      "grad_norm": 0.38998672366142273,
      "learning_rate": 0.00019999757497790106,
      "loss": 0.9268721342086792,
      "step": 1168
    },
    {
      "epoch": 0.4936708860759494,
      "grad_norm": 0.45445355772972107,
      "learning_rate": 0.00019999722895969904,
      "loss": 0.9204684495925903,
      "step": 1170
    },
    {
      "epoch": 0.49451476793248944,
      "grad_norm": 0.484225332736969,
      "learning_rate": 0.00019999685987405678,
      "loss": 0.9270301461219788,
      "step": 1172
    },
    {
      "epoch": 0.49535864978902955,
      "grad_norm": 0.45215415954589844,
      "learning_rate": 0.00019999646772105942,
      "loss": 0.8782645463943481,
      "step": 1174
    },
    {
      "epoch": 0.4962025316455696,
      "grad_norm": 0.41578832268714905,
      "learning_rate": 0.00019999605250079744,
      "loss": 0.873112678527832,
      "step": 1176
    },
    {
      "epoch": 0.4970464135021097,
      "grad_norm": 0.4632788300514221,
      "learning_rate": 0.0001999956142133666,
      "loss": 0.9593189358711243,
      "step": 1178
    },
    {
      "epoch": 0.4978902953586498,
      "grad_norm": 0.5007622838020325,
      "learning_rate": 0.000199995152858868,
      "loss": 0.9215621948242188,
      "step": 1180
    },
    {
      "epoch": 0.49873417721518987,
      "grad_norm": 0.5201935768127441,
      "learning_rate": 0.0001999946684374081,
      "loss": 0.8964219689369202,
      "step": 1182
    },
    {
      "epoch": 0.49957805907173,
      "grad_norm": 0.5053967237472534,
      "learning_rate": 0.0001999941609490986,
      "loss": 0.8528663516044617,
      "step": 1184
    },
    {
      "epoch": 0.5004219409282701,
      "grad_norm": 0.44397974014282227,
      "learning_rate": 0.0001999936303940566,
      "loss": 0.8214734792709351,
      "step": 1186
    },
    {
      "epoch": 0.5012658227848101,
      "grad_norm": 0.4563101530075073,
      "learning_rate": 0.0001999930767724045,
      "loss": 0.8882166743278503,
      "step": 1188
    },
    {
      "epoch": 0.5021097046413502,
      "grad_norm": 0.4666728675365448,
      "learning_rate": 0.00019999250008426997,
      "loss": 0.8882588148117065,
      "step": 1190
    },
    {
      "epoch": 0.5029535864978903,
      "grad_norm": 0.4423629939556122,
      "learning_rate": 0.00019999190032978607,
      "loss": 0.8353691697120667,
      "step": 1192
    },
    {
      "epoch": 0.5037974683544304,
      "grad_norm": 0.4514595866203308,
      "learning_rate": 0.00019999127750909118,
      "loss": 0.8721219301223755,
      "step": 1194
    },
    {
      "epoch": 0.5046413502109705,
      "grad_norm": 0.48469996452331543,
      "learning_rate": 0.00019999063162232886,
      "loss": 0.902795135974884,
      "step": 1196
    },
    {
      "epoch": 0.5054852320675105,
      "grad_norm": 0.4931983947753906,
      "learning_rate": 0.00019998996266964823,
      "loss": 0.8843175768852234,
      "step": 1198
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 0.507408082485199,
      "learning_rate": 0.00019998927065120357,
      "loss": 0.9179208278656006,
      "step": 1200
    },
    {
      "epoch": 0.5063291139240507,
      "eval_loss": 0.9224098324775696,
      "eval_runtime": 669.7542,
      "eval_samples_per_second": 3.146,
      "eval_steps_per_second": 3.146,
      "step": 1200
    },
    {
      "epoch": 0.5071729957805907,
      "grad_norm": 0.4024188220500946,
      "learning_rate": 0.00019998855556715447,
      "loss": 0.9078981876373291,
      "step": 1202
    },
    {
      "epoch": 0.5080168776371308,
      "grad_norm": 0.6558667421340942,
      "learning_rate": 0.00019998781741766594,
      "loss": 0.8089252710342407,
      "step": 1204
    },
    {
      "epoch": 0.5088607594936709,
      "grad_norm": 0.45128145813941956,
      "learning_rate": 0.00019998705620290823,
      "loss": 0.9316248297691345,
      "step": 1206
    },
    {
      "epoch": 0.509704641350211,
      "grad_norm": 0.4733511507511139,
      "learning_rate": 0.00019998627192305694,
      "loss": 0.9047867655754089,
      "step": 1208
    },
    {
      "epoch": 0.510548523206751,
      "grad_norm": 0.4026021659374237,
      "learning_rate": 0.00019998546457829298,
      "loss": 0.8507166504859924,
      "step": 1210
    },
    {
      "epoch": 0.5113924050632911,
      "grad_norm": 0.43416184186935425,
      "learning_rate": 0.00019998463416880262,
      "loss": 0.8490090370178223,
      "step": 1212
    },
    {
      "epoch": 0.5122362869198313,
      "grad_norm": 0.3678364157676697,
      "learning_rate": 0.0001999837806947774,
      "loss": 0.7730492949485779,
      "step": 1214
    },
    {
      "epoch": 0.5130801687763713,
      "grad_norm": 0.49042677879333496,
      "learning_rate": 0.00019998290415641415,
      "loss": 0.9625269174575806,
      "step": 1216
    },
    {
      "epoch": 0.5139240506329114,
      "grad_norm": 0.4576701819896698,
      "learning_rate": 0.00019998200455391516,
      "loss": 0.8961732983589172,
      "step": 1218
    },
    {
      "epoch": 0.5147679324894515,
      "grad_norm": 0.4465518593788147,
      "learning_rate": 0.00019998108188748793,
      "loss": 0.8508996367454529,
      "step": 1220
    },
    {
      "epoch": 0.5156118143459916,
      "grad_norm": 0.4267960488796234,
      "learning_rate": 0.00019998013615734524,
      "loss": 0.8664930462837219,
      "step": 1222
    },
    {
      "epoch": 0.5164556962025316,
      "grad_norm": 0.39936602115631104,
      "learning_rate": 0.0001999791673637053,
      "loss": 0.8841317892074585,
      "step": 1224
    },
    {
      "epoch": 0.5172995780590718,
      "grad_norm": 0.4442414343357086,
      "learning_rate": 0.0001999781755067916,
      "loss": 0.8601276874542236,
      "step": 1226
    },
    {
      "epoch": 0.5181434599156118,
      "grad_norm": 0.4397028088569641,
      "learning_rate": 0.00019997716058683292,
      "loss": 0.8377046585083008,
      "step": 1228
    },
    {
      "epoch": 0.5189873417721519,
      "grad_norm": 0.5327648520469666,
      "learning_rate": 0.0001999761226040634,
      "loss": 0.9853615164756775,
      "step": 1230
    },
    {
      "epoch": 0.5198312236286919,
      "grad_norm": 0.40931421518325806,
      "learning_rate": 0.00019997506155872244,
      "loss": 0.9235715866088867,
      "step": 1232
    },
    {
      "epoch": 0.5206751054852321,
      "grad_norm": 0.4599161148071289,
      "learning_rate": 0.00019997397745105487,
      "loss": 0.868396520614624,
      "step": 1234
    },
    {
      "epoch": 0.5215189873417722,
      "grad_norm": 0.4813833236694336,
      "learning_rate": 0.0001999728702813107,
      "loss": 0.9946733117103577,
      "step": 1236
    },
    {
      "epoch": 0.5223628691983122,
      "grad_norm": 0.43518269062042236,
      "learning_rate": 0.00019997174004974543,
      "loss": 0.8608635067939758,
      "step": 1238
    },
    {
      "epoch": 0.5232067510548524,
      "grad_norm": 0.45646214485168457,
      "learning_rate": 0.0001999705867566197,
      "loss": 0.819354772567749,
      "step": 1240
    },
    {
      "epoch": 0.5240506329113924,
      "grad_norm": 0.46834197640419006,
      "learning_rate": 0.00019996941040219954,
      "loss": 0.8934658765792847,
      "step": 1242
    },
    {
      "epoch": 0.5248945147679325,
      "grad_norm": 0.46065032482147217,
      "learning_rate": 0.0001999682109867564,
      "loss": 0.8624778985977173,
      "step": 1244
    },
    {
      "epoch": 0.5257383966244725,
      "grad_norm": 0.4506741166114807,
      "learning_rate": 0.00019996698851056688,
      "loss": 0.8540882468223572,
      "step": 1246
    },
    {
      "epoch": 0.5265822784810127,
      "grad_norm": 0.4550519287586212,
      "learning_rate": 0.00019996574297391302,
      "loss": 0.9003006219863892,
      "step": 1248
    },
    {
      "epoch": 0.5274261603375527,
      "grad_norm": 0.4097813367843628,
      "learning_rate": 0.00019996447437708214,
      "loss": 0.8490248918533325,
      "step": 1250
    },
    {
      "epoch": 0.5282700421940928,
      "grad_norm": 0.4375711679458618,
      "learning_rate": 0.00019996318272036688,
      "loss": 0.9204569458961487,
      "step": 1252
    },
    {
      "epoch": 0.529113924050633,
      "grad_norm": 0.4335198998451233,
      "learning_rate": 0.00019996186800406518,
      "loss": 0.8831789493560791,
      "step": 1254
    },
    {
      "epoch": 0.529957805907173,
      "grad_norm": 0.4840933084487915,
      "learning_rate": 0.00019996053022848035,
      "loss": 0.8578064441680908,
      "step": 1256
    },
    {
      "epoch": 0.5308016877637131,
      "grad_norm": 0.48911216855049133,
      "learning_rate": 0.00019995916939392097,
      "loss": 0.9235416650772095,
      "step": 1258
    },
    {
      "epoch": 0.5316455696202531,
      "grad_norm": 0.41106730699539185,
      "learning_rate": 0.00019995778550070098,
      "loss": 0.7897764444351196,
      "step": 1260
    },
    {
      "epoch": 0.5324894514767933,
      "grad_norm": 0.42233356833457947,
      "learning_rate": 0.00019995637854913957,
      "loss": 0.9392989873886108,
      "step": 1262
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.39145180583000183,
      "learning_rate": 0.0001999549485395613,
      "loss": 0.9130091667175293,
      "step": 1264
    },
    {
      "epoch": 0.5341772151898734,
      "grad_norm": 0.42780739068984985,
      "learning_rate": 0.00019995349547229614,
      "loss": 0.9690561890602112,
      "step": 1266
    },
    {
      "epoch": 0.5350210970464135,
      "grad_norm": 0.4823327362537384,
      "learning_rate": 0.0001999520193476792,
      "loss": 0.9990131258964539,
      "step": 1268
    },
    {
      "epoch": 0.5358649789029536,
      "grad_norm": 0.4669715166091919,
      "learning_rate": 0.00019995052016605097,
      "loss": 0.8343052864074707,
      "step": 1270
    },
    {
      "epoch": 0.5367088607594936,
      "grad_norm": 0.4024743437767029,
      "learning_rate": 0.0001999489979277574,
      "loss": 0.9605970978736877,
      "step": 1272
    },
    {
      "epoch": 0.5375527426160338,
      "grad_norm": 0.42063432931900024,
      "learning_rate": 0.0001999474526331495,
      "loss": 0.8164438009262085,
      "step": 1274
    },
    {
      "epoch": 0.5383966244725739,
      "grad_norm": 0.47953495383262634,
      "learning_rate": 0.00019994588428258383,
      "loss": 0.879767656326294,
      "step": 1276
    },
    {
      "epoch": 0.5392405063291139,
      "grad_norm": 0.39668557047843933,
      "learning_rate": 0.00019994429287642214,
      "loss": 0.7658726572990417,
      "step": 1278
    },
    {
      "epoch": 0.540084388185654,
      "grad_norm": 0.5136121511459351,
      "learning_rate": 0.00019994267841503155,
      "loss": 0.9477384686470032,
      "step": 1280
    },
    {
      "epoch": 0.5409282700421941,
      "grad_norm": 0.4039286673069,
      "learning_rate": 0.00019994104089878452,
      "loss": 0.7883896827697754,
      "step": 1282
    },
    {
      "epoch": 0.5417721518987342,
      "grad_norm": 0.4425487816333771,
      "learning_rate": 0.0001999393803280587,
      "loss": 0.8526129126548767,
      "step": 1284
    },
    {
      "epoch": 0.5426160337552742,
      "grad_norm": 0.4544559121131897,
      "learning_rate": 0.00019993769670323725,
      "loss": 0.8694683909416199,
      "step": 1286
    },
    {
      "epoch": 0.5434599156118144,
      "grad_norm": 0.42872917652130127,
      "learning_rate": 0.0001999359900247085,
      "loss": 0.8211527466773987,
      "step": 1288
    },
    {
      "epoch": 0.5443037974683544,
      "grad_norm": 0.41549673676490784,
      "learning_rate": 0.00019993426029286617,
      "loss": 0.7967932224273682,
      "step": 1290
    },
    {
      "epoch": 0.5451476793248945,
      "grad_norm": 0.42888355255126953,
      "learning_rate": 0.00019993250750810926,
      "loss": 0.8291563987731934,
      "step": 1292
    },
    {
      "epoch": 0.5459915611814345,
      "grad_norm": 0.44985485076904297,
      "learning_rate": 0.0001999307316708421,
      "loss": 0.8787803649902344,
      "step": 1294
    },
    {
      "epoch": 0.5468354430379747,
      "grad_norm": 0.43326008319854736,
      "learning_rate": 0.00019992893278147436,
      "loss": 0.8375519514083862,
      "step": 1296
    },
    {
      "epoch": 0.5476793248945148,
      "grad_norm": 0.406556099653244,
      "learning_rate": 0.00019992711084042096,
      "loss": 0.8538051247596741,
      "step": 1298
    },
    {
      "epoch": 0.5485232067510548,
      "grad_norm": 0.46090877056121826,
      "learning_rate": 0.00019992526584810226,
      "loss": 0.9722132086753845,
      "step": 1300
    },
    {
      "epoch": 0.5485232067510548,
      "eval_loss": 0.9068717360496521,
      "eval_runtime": 680.7718,
      "eval_samples_per_second": 3.095,
      "eval_steps_per_second": 3.095,
      "step": 1300
    },
    {
      "epoch": 0.549367088607595,
      "grad_norm": 0.44932207465171814,
      "learning_rate": 0.00019992339780494382,
      "loss": 0.8474152684211731,
      "step": 1302
    },
    {
      "epoch": 0.550210970464135,
      "grad_norm": 0.5185276865959167,
      "learning_rate": 0.0001999215067113766,
      "loss": 0.8440775871276855,
      "step": 1304
    },
    {
      "epoch": 0.5510548523206751,
      "grad_norm": 0.43811365962028503,
      "learning_rate": 0.0001999195925678368,
      "loss": 0.8848010897636414,
      "step": 1306
    },
    {
      "epoch": 0.5518987341772152,
      "grad_norm": 0.4861660301685333,
      "learning_rate": 0.00019991765537476596,
      "loss": 0.8265100121498108,
      "step": 1308
    },
    {
      "epoch": 0.5527426160337553,
      "grad_norm": 0.5068721771240234,
      "learning_rate": 0.000199915695132611,
      "loss": 0.9327963590621948,
      "step": 1310
    },
    {
      "epoch": 0.5535864978902953,
      "grad_norm": 0.4902805685997009,
      "learning_rate": 0.0001999137118418241,
      "loss": 0.9315155744552612,
      "step": 1312
    },
    {
      "epoch": 0.5544303797468354,
      "grad_norm": 0.4530964493751526,
      "learning_rate": 0.00019991170550286272,
      "loss": 0.9344852566719055,
      "step": 1314
    },
    {
      "epoch": 0.5552742616033756,
      "grad_norm": 0.4106673300266266,
      "learning_rate": 0.00019990967611618974,
      "loss": 0.8326173424720764,
      "step": 1316
    },
    {
      "epoch": 0.5561181434599156,
      "grad_norm": 0.4439711570739746,
      "learning_rate": 0.0001999076236822733,
      "loss": 0.8934909105300903,
      "step": 1318
    },
    {
      "epoch": 0.5569620253164557,
      "grad_norm": 0.40245553851127625,
      "learning_rate": 0.0001999055482015868,
      "loss": 0.6691107153892517,
      "step": 1320
    },
    {
      "epoch": 0.5578059071729958,
      "grad_norm": 0.43904435634613037,
      "learning_rate": 0.0001999034496746091,
      "loss": 0.8560307621955872,
      "step": 1322
    },
    {
      "epoch": 0.5586497890295359,
      "grad_norm": 0.5131705403327942,
      "learning_rate": 0.00019990132810182422,
      "loss": 0.9024442434310913,
      "step": 1324
    },
    {
      "epoch": 0.5594936708860759,
      "grad_norm": 0.4539531171321869,
      "learning_rate": 0.00019989918348372156,
      "loss": 0.8675428628921509,
      "step": 1326
    },
    {
      "epoch": 0.560337552742616,
      "grad_norm": 0.44469985365867615,
      "learning_rate": 0.00019989701582079591,
      "loss": 0.8853429555892944,
      "step": 1328
    },
    {
      "epoch": 0.5611814345991561,
      "grad_norm": 0.4485546946525574,
      "learning_rate": 0.00019989482511354725,
      "loss": 0.9675378799438477,
      "step": 1330
    },
    {
      "epoch": 0.5620253164556962,
      "grad_norm": 0.43316468596458435,
      "learning_rate": 0.00019989261136248097,
      "loss": 0.8256655335426331,
      "step": 1332
    },
    {
      "epoch": 0.5628691983122363,
      "grad_norm": 0.4315780699253082,
      "learning_rate": 0.00019989037456810772,
      "loss": 0.7727690935134888,
      "step": 1334
    },
    {
      "epoch": 0.5637130801687764,
      "grad_norm": 0.45147502422332764,
      "learning_rate": 0.00019988811473094348,
      "loss": 0.9240618348121643,
      "step": 1336
    },
    {
      "epoch": 0.5645569620253165,
      "grad_norm": 0.4606908857822418,
      "learning_rate": 0.00019988583185150957,
      "loss": 0.8005949258804321,
      "step": 1338
    },
    {
      "epoch": 0.5654008438818565,
      "grad_norm": 0.48932451009750366,
      "learning_rate": 0.00019988352593033255,
      "loss": 0.9042718410491943,
      "step": 1340
    },
    {
      "epoch": 0.5662447257383966,
      "grad_norm": 0.46022218465805054,
      "learning_rate": 0.00019988119696794443,
      "loss": 0.8724613785743713,
      "step": 1342
    },
    {
      "epoch": 0.5670886075949367,
      "grad_norm": 0.4414621889591217,
      "learning_rate": 0.00019987884496488242,
      "loss": 0.8653066158294678,
      "step": 1344
    },
    {
      "epoch": 0.5679324894514768,
      "grad_norm": 0.4490342140197754,
      "learning_rate": 0.0001998764699216891,
      "loss": 0.8843849301338196,
      "step": 1346
    },
    {
      "epoch": 0.5687763713080168,
      "grad_norm": 0.47690069675445557,
      "learning_rate": 0.00019987407183891232,
      "loss": 0.8385393023490906,
      "step": 1348
    },
    {
      "epoch": 0.569620253164557,
      "grad_norm": 0.41409361362457275,
      "learning_rate": 0.00019987165071710527,
      "loss": 0.77492755651474,
      "step": 1350
    },
    {
      "epoch": 0.570464135021097,
      "grad_norm": 0.4151647984981537,
      "learning_rate": 0.0001998692065568265,
      "loss": 0.8368680477142334,
      "step": 1352
    },
    {
      "epoch": 0.5713080168776371,
      "grad_norm": 0.4105067849159241,
      "learning_rate": 0.0001998667393586398,
      "loss": 0.833220362663269,
      "step": 1354
    },
    {
      "epoch": 0.5721518987341773,
      "grad_norm": 0.44701820611953735,
      "learning_rate": 0.0001998642491231143,
      "loss": 0.8041552305221558,
      "step": 1356
    },
    {
      "epoch": 0.5729957805907173,
      "grad_norm": 0.4621582329273224,
      "learning_rate": 0.00019986173585082444,
      "loss": 0.9052709937095642,
      "step": 1358
    },
    {
      "epoch": 0.5738396624472574,
      "grad_norm": 0.4934713840484619,
      "learning_rate": 0.00019985919954235005,
      "loss": 0.8036054372787476,
      "step": 1360
    },
    {
      "epoch": 0.5746835443037974,
      "grad_norm": 0.4557384252548218,
      "learning_rate": 0.0001998566401982761,
      "loss": 0.8340095281600952,
      "step": 1362
    },
    {
      "epoch": 0.5755274261603376,
      "grad_norm": 0.5048403739929199,
      "learning_rate": 0.00019985405781919305,
      "loss": 0.8703633546829224,
      "step": 1364
    },
    {
      "epoch": 0.5763713080168776,
      "grad_norm": 0.4707714319229126,
      "learning_rate": 0.0001998514524056966,
      "loss": 0.9115830659866333,
      "step": 1366
    },
    {
      "epoch": 0.5772151898734177,
      "grad_norm": 0.4502186179161072,
      "learning_rate": 0.00019984882395838777,
      "loss": 0.8603149056434631,
      "step": 1368
    },
    {
      "epoch": 0.5780590717299579,
      "grad_norm": 0.4229136109352112,
      "learning_rate": 0.00019984617247787288,
      "loss": 0.7482197284698486,
      "step": 1370
    },
    {
      "epoch": 0.5789029535864979,
      "grad_norm": 0.49208030104637146,
      "learning_rate": 0.0001998434979647636,
      "loss": 0.9071239233016968,
      "step": 1372
    },
    {
      "epoch": 0.579746835443038,
      "grad_norm": 0.47393161058425903,
      "learning_rate": 0.00019984080041967687,
      "loss": 0.9370644092559814,
      "step": 1374
    },
    {
      "epoch": 0.580590717299578,
      "grad_norm": 0.4483324885368347,
      "learning_rate": 0.00019983807984323492,
      "loss": 0.8536180257797241,
      "step": 1376
    },
    {
      "epoch": 0.5814345991561182,
      "grad_norm": 0.4163796007633209,
      "learning_rate": 0.00019983533623606543,
      "loss": 0.7360405325889587,
      "step": 1378
    },
    {
      "epoch": 0.5822784810126582,
      "grad_norm": 0.44147446751594543,
      "learning_rate": 0.00019983256959880122,
      "loss": 0.8162824511528015,
      "step": 1380
    },
    {
      "epoch": 0.5831223628691983,
      "grad_norm": 0.44443491101264954,
      "learning_rate": 0.0001998297799320805,
      "loss": 0.9169327616691589,
      "step": 1382
    },
    {
      "epoch": 0.5839662447257384,
      "grad_norm": 0.4641949236392975,
      "learning_rate": 0.00019982696723654686,
      "loss": 0.8875693678855896,
      "step": 1384
    },
    {
      "epoch": 0.5848101265822785,
      "grad_norm": 0.4327974319458008,
      "learning_rate": 0.00019982413151284906,
      "loss": 0.7747344970703125,
      "step": 1386
    },
    {
      "epoch": 0.5856540084388185,
      "grad_norm": 0.44200772047042847,
      "learning_rate": 0.0001998212727616413,
      "loss": 0.8490481972694397,
      "step": 1388
    },
    {
      "epoch": 0.5864978902953587,
      "grad_norm": 0.39084959030151367,
      "learning_rate": 0.000199818390983583,
      "loss": 0.8014808297157288,
      "step": 1390
    },
    {
      "epoch": 0.5873417721518988,
      "grad_norm": 0.3691277801990509,
      "learning_rate": 0.00019981548617933897,
      "loss": 0.8650928139686584,
      "step": 1392
    },
    {
      "epoch": 0.5881856540084388,
      "grad_norm": 0.480002760887146,
      "learning_rate": 0.00019981255834957925,
      "loss": 0.7713267803192139,
      "step": 1394
    },
    {
      "epoch": 0.5890295358649789,
      "grad_norm": 0.4397226572036743,
      "learning_rate": 0.00019980960749497927,
      "loss": 0.9053656458854675,
      "step": 1396
    },
    {
      "epoch": 0.589873417721519,
      "grad_norm": 0.4263727366924286,
      "learning_rate": 0.00019980663361621973,
      "loss": 0.8737669587135315,
      "step": 1398
    },
    {
      "epoch": 0.5907172995780591,
      "grad_norm": 0.4468817710876465,
      "learning_rate": 0.0001998036367139866,
      "loss": 0.9396650791168213,
      "step": 1400
    },
    {
      "epoch": 0.5907172995780591,
      "eval_loss": 0.8971880674362183,
      "eval_runtime": 692.8046,
      "eval_samples_per_second": 3.041,
      "eval_steps_per_second": 3.041,
      "step": 1400
    },
    {
      "epoch": 0.5915611814345991,
      "grad_norm": 0.4128144383430481,
      "learning_rate": 0.00019980061678897127,
      "loss": 0.926134467124939,
      "step": 1402
    },
    {
      "epoch": 0.5924050632911393,
      "grad_norm": 0.45524629950523376,
      "learning_rate": 0.00019979757384187035,
      "loss": 0.826360285282135,
      "step": 1404
    },
    {
      "epoch": 0.5932489451476793,
      "grad_norm": 0.42521336674690247,
      "learning_rate": 0.0001997945078733858,
      "loss": 0.8147702813148499,
      "step": 1406
    },
    {
      "epoch": 0.5940928270042194,
      "grad_norm": 0.4172525107860565,
      "learning_rate": 0.00019979141888422489,
      "loss": 0.7711596488952637,
      "step": 1408
    },
    {
      "epoch": 0.5949367088607594,
      "grad_norm": 0.46193623542785645,
      "learning_rate": 0.00019978830687510013,
      "loss": 0.7875980138778687,
      "step": 1410
    },
    {
      "epoch": 0.5957805907172996,
      "grad_norm": 0.4455825686454773,
      "learning_rate": 0.00019978517184672946,
      "loss": 0.8590195178985596,
      "step": 1412
    },
    {
      "epoch": 0.5966244725738397,
      "grad_norm": 0.4266505539417267,
      "learning_rate": 0.00019978201379983608,
      "loss": 0.9318227767944336,
      "step": 1414
    },
    {
      "epoch": 0.5974683544303797,
      "grad_norm": 0.42627251148223877,
      "learning_rate": 0.00019977883273514843,
      "loss": 0.8644474744796753,
      "step": 1416
    },
    {
      "epoch": 0.5983122362869199,
      "grad_norm": 0.393873393535614,
      "learning_rate": 0.00019977562865340038,
      "loss": 0.7760446071624756,
      "step": 1418
    },
    {
      "epoch": 0.5991561181434599,
      "grad_norm": 0.44334208965301514,
      "learning_rate": 0.000199772401555331,
      "loss": 0.8071584701538086,
      "step": 1420
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.39390063285827637,
      "learning_rate": 0.0001997691514416848,
      "loss": 0.9076889753341675,
      "step": 1422
    },
    {
      "epoch": 0.60084388185654,
      "grad_norm": 0.46753421425819397,
      "learning_rate": 0.00019976587831321144,
      "loss": 0.8534318804740906,
      "step": 1424
    },
    {
      "epoch": 0.6016877637130802,
      "grad_norm": 0.4840681254863739,
      "learning_rate": 0.00019976258217066598,
      "loss": 0.9049596190452576,
      "step": 1426
    },
    {
      "epoch": 0.6025316455696202,
      "grad_norm": 0.4740557372570038,
      "learning_rate": 0.00019975926301480878,
      "loss": 0.8520918488502502,
      "step": 1428
    },
    {
      "epoch": 0.6033755274261603,
      "grad_norm": 0.46498584747314453,
      "learning_rate": 0.00019975592084640553,
      "loss": 0.8221305012702942,
      "step": 1430
    },
    {
      "epoch": 0.6042194092827005,
      "grad_norm": 0.40885692834854126,
      "learning_rate": 0.0001997525556662272,
      "loss": 0.8132198452949524,
      "step": 1432
    },
    {
      "epoch": 0.6050632911392405,
      "grad_norm": 0.4375821053981781,
      "learning_rate": 0.00019974916747505006,
      "loss": 0.870534360408783,
      "step": 1434
    },
    {
      "epoch": 0.6059071729957806,
      "grad_norm": 0.4780935049057007,
      "learning_rate": 0.00019974575627365569,
      "loss": 0.8825759291648865,
      "step": 1436
    },
    {
      "epoch": 0.6067510548523207,
      "grad_norm": 0.4623970687389374,
      "learning_rate": 0.00019974232206283098,
      "loss": 0.8187641501426697,
      "step": 1438
    },
    {
      "epoch": 0.6075949367088608,
      "grad_norm": 0.42172595858573914,
      "learning_rate": 0.0001997388648433682,
      "loss": 0.8569821119308472,
      "step": 1440
    },
    {
      "epoch": 0.6084388185654008,
      "grad_norm": 0.49386659264564514,
      "learning_rate": 0.0001997353846160648,
      "loss": 0.9173614382743835,
      "step": 1442
    },
    {
      "epoch": 0.6092827004219409,
      "grad_norm": 0.47122615575790405,
      "learning_rate": 0.00019973188138172363,
      "loss": 0.9444975256919861,
      "step": 1444
    },
    {
      "epoch": 0.610126582278481,
      "grad_norm": 0.4831530451774597,
      "learning_rate": 0.0001997283551411528,
      "loss": 0.9537245631217957,
      "step": 1446
    },
    {
      "epoch": 0.6109704641350211,
      "grad_norm": 0.44460317492485046,
      "learning_rate": 0.0001997248058951658,
      "loss": 0.8481367230415344,
      "step": 1448
    },
    {
      "epoch": 0.6118143459915611,
      "grad_norm": 0.4315263628959656,
      "learning_rate": 0.00019972123364458128,
      "loss": 0.8572371006011963,
      "step": 1450
    },
    {
      "epoch": 0.6126582278481013,
      "grad_norm": 0.38559582829475403,
      "learning_rate": 0.00019971763839022336,
      "loss": 0.762590765953064,
      "step": 1452
    },
    {
      "epoch": 0.6135021097046414,
      "grad_norm": 0.3820290267467499,
      "learning_rate": 0.00019971402013292138,
      "loss": 0.7879500389099121,
      "step": 1454
    },
    {
      "epoch": 0.6143459915611814,
      "grad_norm": 0.42509570717811584,
      "learning_rate": 0.00019971037887351,
      "loss": 0.8696863055229187,
      "step": 1456
    },
    {
      "epoch": 0.6151898734177215,
      "grad_norm": 0.46750548481941223,
      "learning_rate": 0.00019970671461282916,
      "loss": 0.8425862789154053,
      "step": 1458
    },
    {
      "epoch": 0.6160337552742616,
      "grad_norm": 0.3937121033668518,
      "learning_rate": 0.0001997030273517242,
      "loss": 0.8028931021690369,
      "step": 1460
    },
    {
      "epoch": 0.6168776371308017,
      "grad_norm": 0.4361220896244049,
      "learning_rate": 0.00019969931709104565,
      "loss": 0.8662509918212891,
      "step": 1462
    },
    {
      "epoch": 0.6177215189873417,
      "grad_norm": 0.4737963378429413,
      "learning_rate": 0.00019969558383164943,
      "loss": 0.8962596654891968,
      "step": 1464
    },
    {
      "epoch": 0.6185654008438819,
      "grad_norm": 0.3952867388725281,
      "learning_rate": 0.00019969182757439668,
      "loss": 0.8630867600440979,
      "step": 1466
    },
    {
      "epoch": 0.619409282700422,
      "grad_norm": 0.41688743233680725,
      "learning_rate": 0.00019968804832015393,
      "loss": 0.8759240508079529,
      "step": 1468
    },
    {
      "epoch": 0.620253164556962,
      "grad_norm": 0.4599224627017975,
      "learning_rate": 0.00019968424606979298,
      "loss": 0.8459385633468628,
      "step": 1470
    },
    {
      "epoch": 0.6210970464135022,
      "grad_norm": 0.5476765632629395,
      "learning_rate": 0.00019968042082419094,
      "loss": 0.8844659328460693,
      "step": 1472
    },
    {
      "epoch": 0.6219409282700422,
      "grad_norm": 0.46202269196510315,
      "learning_rate": 0.00019967657258423022,
      "loss": 0.860946536064148,
      "step": 1474
    },
    {
      "epoch": 0.6227848101265823,
      "grad_norm": 0.39446666836738586,
      "learning_rate": 0.00019967270135079853,
      "loss": 0.7587860822677612,
      "step": 1476
    },
    {
      "epoch": 0.6236286919831223,
      "grad_norm": 0.4500375986099243,
      "learning_rate": 0.0001996688071247889,
      "loss": 0.9143000245094299,
      "step": 1478
    },
    {
      "epoch": 0.6244725738396625,
      "grad_norm": 0.4203545153141022,
      "learning_rate": 0.0001996648899070996,
      "loss": 0.7865519523620605,
      "step": 1480
    },
    {
      "epoch": 0.6253164556962025,
      "grad_norm": 0.45623889565467834,
      "learning_rate": 0.00019966094969863432,
      "loss": 0.9192912578582764,
      "step": 1482
    },
    {
      "epoch": 0.6261603375527426,
      "grad_norm": 0.4139637053012848,
      "learning_rate": 0.00019965698650030195,
      "loss": 0.8459161520004272,
      "step": 1484
    },
    {
      "epoch": 0.6270042194092827,
      "grad_norm": 0.4410824179649353,
      "learning_rate": 0.00019965300031301678,
      "loss": 0.8159077763557434,
      "step": 1486
    },
    {
      "epoch": 0.6278481012658228,
      "grad_norm": 0.43821197748184204,
      "learning_rate": 0.00019964899113769828,
      "loss": 0.884467363357544,
      "step": 1488
    },
    {
      "epoch": 0.6286919831223629,
      "grad_norm": 0.4692091643810272,
      "learning_rate": 0.00019964495897527133,
      "loss": 0.8693601489067078,
      "step": 1490
    },
    {
      "epoch": 0.6295358649789029,
      "grad_norm": 0.40715447068214417,
      "learning_rate": 0.00019964090382666608,
      "loss": 0.8897743225097656,
      "step": 1492
    },
    {
      "epoch": 0.6303797468354431,
      "grad_norm": 0.4123334586620331,
      "learning_rate": 0.0001996368256928179,
      "loss": 0.8274733424186707,
      "step": 1494
    },
    {
      "epoch": 0.6312236286919831,
      "grad_norm": 0.44347211718559265,
      "learning_rate": 0.00019963272457466767,
      "loss": 0.8158749938011169,
      "step": 1496
    },
    {
      "epoch": 0.6320675105485232,
      "grad_norm": 0.4700329601764679,
      "learning_rate": 0.00019962860047316135,
      "loss": 0.8439569473266602,
      "step": 1498
    },
    {
      "epoch": 0.6329113924050633,
      "grad_norm": 0.46415844559669495,
      "learning_rate": 0.00019962445338925027,
      "loss": 0.8316822648048401,
      "step": 1500
    },
    {
      "epoch": 0.6329113924050633,
      "eval_loss": 0.887488842010498,
      "eval_runtime": 686.2804,
      "eval_samples_per_second": 3.07,
      "eval_steps_per_second": 3.07,
      "step": 1500
    },
    {
      "epoch": 0.6337552742616034,
      "grad_norm": 0.44183167815208435,
      "learning_rate": 0.0001996202833238911,
      "loss": 0.9121994972229004,
      "step": 1502
    },
    {
      "epoch": 0.6345991561181434,
      "grad_norm": 0.4279208779335022,
      "learning_rate": 0.00019961609027804587,
      "loss": 0.9160211086273193,
      "step": 1504
    },
    {
      "epoch": 0.6354430379746835,
      "grad_norm": 0.3967169523239136,
      "learning_rate": 0.00019961187425268176,
      "loss": 0.861677348613739,
      "step": 1506
    },
    {
      "epoch": 0.6362869198312237,
      "grad_norm": 0.4796451926231384,
      "learning_rate": 0.0001996076352487713,
      "loss": 0.8478423357009888,
      "step": 1508
    },
    {
      "epoch": 0.6371308016877637,
      "grad_norm": 0.3861426115036011,
      "learning_rate": 0.00019960337326729245,
      "loss": 0.8739159107208252,
      "step": 1510
    },
    {
      "epoch": 0.6379746835443038,
      "grad_norm": 0.4567820429801941,
      "learning_rate": 0.00019959908830922824,
      "loss": 0.7693920731544495,
      "step": 1512
    },
    {
      "epoch": 0.6388185654008439,
      "grad_norm": 0.4457108676433563,
      "learning_rate": 0.00019959478037556724,
      "loss": 0.8482301831245422,
      "step": 1514
    },
    {
      "epoch": 0.639662447257384,
      "grad_norm": 0.43918928503990173,
      "learning_rate": 0.00019959044946730314,
      "loss": 0.8626812696456909,
      "step": 1516
    },
    {
      "epoch": 0.640506329113924,
      "grad_norm": 0.4095900058746338,
      "learning_rate": 0.00019958609558543504,
      "loss": 0.8342230916023254,
      "step": 1518
    },
    {
      "epoch": 0.6413502109704642,
      "grad_norm": 0.4181270897388458,
      "learning_rate": 0.00019958171873096724,
      "loss": 0.8794118165969849,
      "step": 1520
    },
    {
      "epoch": 0.6421940928270042,
      "grad_norm": 0.4750959277153015,
      "learning_rate": 0.00019957731890490947,
      "loss": 0.7787677049636841,
      "step": 1522
    },
    {
      "epoch": 0.6430379746835443,
      "grad_norm": 0.5129296779632568,
      "learning_rate": 0.00019957289610827663,
      "loss": 0.9084368348121643,
      "step": 1524
    },
    {
      "epoch": 0.6438818565400843,
      "grad_norm": 0.4829029142856598,
      "learning_rate": 0.000199568450342089,
      "loss": 0.9066952466964722,
      "step": 1526
    },
    {
      "epoch": 0.6447257383966245,
      "grad_norm": 0.4225057363510132,
      "learning_rate": 0.00019956398160737214,
      "loss": 0.8127874732017517,
      "step": 1528
    },
    {
      "epoch": 0.6455696202531646,
      "grad_norm": 0.4231826364994049,
      "learning_rate": 0.00019955948990515684,
      "loss": 0.8781921863555908,
      "step": 1530
    },
    {
      "epoch": 0.6464135021097046,
      "grad_norm": 0.4436216950416565,
      "learning_rate": 0.00019955497523647933,
      "loss": 0.8136996626853943,
      "step": 1532
    },
    {
      "epoch": 0.6472573839662448,
      "grad_norm": 0.4018244743347168,
      "learning_rate": 0.00019955043760238098,
      "loss": 0.8003877401351929,
      "step": 1534
    },
    {
      "epoch": 0.6481012658227848,
      "grad_norm": 0.40024611353874207,
      "learning_rate": 0.0001995458770039086,
      "loss": 0.8996267914772034,
      "step": 1536
    },
    {
      "epoch": 0.6489451476793249,
      "grad_norm": 0.42845702171325684,
      "learning_rate": 0.00019954129344211424,
      "loss": 0.8610522150993347,
      "step": 1538
    },
    {
      "epoch": 0.6497890295358649,
      "grad_norm": 0.4258182644844055,
      "learning_rate": 0.00019953668691805517,
      "loss": 0.8991837501525879,
      "step": 1540
    },
    {
      "epoch": 0.6506329113924051,
      "grad_norm": 0.4483257830142975,
      "learning_rate": 0.0001995320574327941,
      "loss": 0.8150189518928528,
      "step": 1542
    },
    {
      "epoch": 0.6514767932489451,
      "grad_norm": 0.4320627748966217,
      "learning_rate": 0.0001995274049873989,
      "loss": 0.8572840690612793,
      "step": 1544
    },
    {
      "epoch": 0.6523206751054852,
      "grad_norm": 0.39950594305992126,
      "learning_rate": 0.00019952272958294288,
      "loss": 0.7766129374504089,
      "step": 1546
    },
    {
      "epoch": 0.6531645569620254,
      "grad_norm": 0.4130117893218994,
      "learning_rate": 0.00019951803122050446,
      "loss": 0.9032199382781982,
      "step": 1548
    },
    {
      "epoch": 0.6540084388185654,
      "grad_norm": 0.4436919391155243,
      "learning_rate": 0.00019951330990116754,
      "loss": 0.8361048102378845,
      "step": 1550
    },
    {
      "epoch": 0.6548523206751055,
      "grad_norm": 0.4229227900505066,
      "learning_rate": 0.00019950856562602121,
      "loss": 0.8661768436431885,
      "step": 1552
    },
    {
      "epoch": 0.6556962025316456,
      "grad_norm": 0.4839727580547333,
      "learning_rate": 0.00019950379839615988,
      "loss": 0.9737826585769653,
      "step": 1554
    },
    {
      "epoch": 0.6565400843881857,
      "grad_norm": 0.3859386742115021,
      "learning_rate": 0.00019949900821268328,
      "loss": 0.7542453408241272,
      "step": 1556
    },
    {
      "epoch": 0.6573839662447257,
      "grad_norm": 0.39643988013267517,
      "learning_rate": 0.0001994941950766964,
      "loss": 0.9226290583610535,
      "step": 1558
    },
    {
      "epoch": 0.6582278481012658,
      "grad_norm": 0.4261355400085449,
      "learning_rate": 0.00019948935898930954,
      "loss": 0.8375602960586548,
      "step": 1560
    },
    {
      "epoch": 0.6590717299578059,
      "grad_norm": 0.445931077003479,
      "learning_rate": 0.00019948449995163826,
      "loss": 0.7847310304641724,
      "step": 1562
    },
    {
      "epoch": 0.659915611814346,
      "grad_norm": 0.4680459797382355,
      "learning_rate": 0.00019947961796480353,
      "loss": 0.851150631904602,
      "step": 1564
    },
    {
      "epoch": 0.660759493670886,
      "grad_norm": 0.6826074719429016,
      "learning_rate": 0.00019947471302993143,
      "loss": 0.8259562253952026,
      "step": 1566
    },
    {
      "epoch": 0.6616033755274262,
      "grad_norm": 0.47369205951690674,
      "learning_rate": 0.00019946978514815352,
      "loss": 0.879021406173706,
      "step": 1568
    },
    {
      "epoch": 0.6624472573839663,
      "grad_norm": 0.41111937165260315,
      "learning_rate": 0.0001994648343206065,
      "loss": 0.9296056032180786,
      "step": 1570
    },
    {
      "epoch": 0.6632911392405063,
      "grad_norm": 0.4297783076763153,
      "learning_rate": 0.00019945986054843248,
      "loss": 0.873822808265686,
      "step": 1572
    },
    {
      "epoch": 0.6641350210970464,
      "grad_norm": 0.48124316334724426,
      "learning_rate": 0.00019945486383277878,
      "loss": 0.937151312828064,
      "step": 1574
    },
    {
      "epoch": 0.6649789029535865,
      "grad_norm": 0.4048190116882324,
      "learning_rate": 0.00019944984417479805,
      "loss": 0.8398929834365845,
      "step": 1576
    },
    {
      "epoch": 0.6658227848101266,
      "grad_norm": 0.4023774266242981,
      "learning_rate": 0.00019944480157564826,
      "loss": 0.8269520998001099,
      "step": 1578
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.3784184157848358,
      "learning_rate": 0.00019943973603649262,
      "loss": 0.8237608671188354,
      "step": 1580
    },
    {
      "epoch": 0.6675105485232068,
      "grad_norm": 0.4448573887348175,
      "learning_rate": 0.00019943464755849965,
      "loss": 0.8469099998474121,
      "step": 1582
    },
    {
      "epoch": 0.6683544303797468,
      "grad_norm": 0.4690774083137512,
      "learning_rate": 0.00019942953614284317,
      "loss": 0.8630822896957397,
      "step": 1584
    },
    {
      "epoch": 0.6691983122362869,
      "grad_norm": 0.43670853972435,
      "learning_rate": 0.00019942440179070227,
      "loss": 0.8904082179069519,
      "step": 1586
    },
    {
      "epoch": 0.6700421940928271,
      "grad_norm": 0.4236849844455719,
      "learning_rate": 0.00019941924450326138,
      "loss": 0.8355640172958374,
      "step": 1588
    },
    {
      "epoch": 0.6708860759493671,
      "grad_norm": 0.48624539375305176,
      "learning_rate": 0.00019941406428171013,
      "loss": 0.8898435831069946,
      "step": 1590
    },
    {
      "epoch": 0.6717299578059072,
      "grad_norm": 0.4453780949115753,
      "learning_rate": 0.00019940886112724355,
      "loss": 0.9000012278556824,
      "step": 1592
    },
    {
      "epoch": 0.6725738396624472,
      "grad_norm": 0.4417199194431305,
      "learning_rate": 0.00019940363504106193,
      "loss": 0.8171058893203735,
      "step": 1594
    },
    {
      "epoch": 0.6734177215189874,
      "grad_norm": 0.45055362582206726,
      "learning_rate": 0.00019939838602437074,
      "loss": 0.8703798055648804,
      "step": 1596
    },
    {
      "epoch": 0.6742616033755274,
      "grad_norm": 0.42316532135009766,
      "learning_rate": 0.00019939311407838088,
      "loss": 0.8677281737327576,
      "step": 1598
    },
    {
      "epoch": 0.6751054852320675,
      "grad_norm": 0.3935781717300415,
      "learning_rate": 0.0001993878192043085,
      "loss": 0.7314013242721558,
      "step": 1600
    },
    {
      "epoch": 0.6751054852320675,
      "eval_loss": 0.8769772052764893,
      "eval_runtime": 677.9338,
      "eval_samples_per_second": 3.108,
      "eval_steps_per_second": 3.108,
      "step": 1600
    },
    {
      "epoch": 0.6759493670886076,
      "grad_norm": 0.4197012186050415,
      "learning_rate": 0.000199382501403375,
      "loss": 0.8075380325317383,
      "step": 1602
    },
    {
      "epoch": 0.6767932489451477,
      "grad_norm": 0.45227327942848206,
      "learning_rate": 0.00019937716067680713,
      "loss": 0.7885794639587402,
      "step": 1604
    },
    {
      "epoch": 0.6776371308016877,
      "grad_norm": 0.45660385489463806,
      "learning_rate": 0.00019937179702583682,
      "loss": 0.868261992931366,
      "step": 1606
    },
    {
      "epoch": 0.6784810126582278,
      "grad_norm": 0.3955288231372833,
      "learning_rate": 0.00019936641045170144,
      "loss": 0.8306655287742615,
      "step": 1608
    },
    {
      "epoch": 0.679324894514768,
      "grad_norm": 0.3651324510574341,
      "learning_rate": 0.00019936100095564353,
      "loss": 0.7505315542221069,
      "step": 1610
    },
    {
      "epoch": 0.680168776371308,
      "grad_norm": 0.4240955412387848,
      "learning_rate": 0.00019935556853891096,
      "loss": 0.8792756795883179,
      "step": 1612
    },
    {
      "epoch": 0.6810126582278481,
      "grad_norm": 0.4142507314682007,
      "learning_rate": 0.00019935011320275687,
      "loss": 0.7328272461891174,
      "step": 1614
    },
    {
      "epoch": 0.6818565400843882,
      "grad_norm": 0.48339322209358215,
      "learning_rate": 0.00019934463494843975,
      "loss": 0.8414849042892456,
      "step": 1616
    },
    {
      "epoch": 0.6827004219409283,
      "grad_norm": 0.4312443435192108,
      "learning_rate": 0.00019933913377722328,
      "loss": 0.8588716983795166,
      "step": 1618
    },
    {
      "epoch": 0.6835443037974683,
      "grad_norm": 0.43849512934684753,
      "learning_rate": 0.0001993336096903765,
      "loss": 0.846511960029602,
      "step": 1620
    },
    {
      "epoch": 0.6843881856540084,
      "grad_norm": 0.45767566561698914,
      "learning_rate": 0.0001993280626891737,
      "loss": 0.9352323412895203,
      "step": 1622
    },
    {
      "epoch": 0.6852320675105485,
      "grad_norm": 0.438412606716156,
      "learning_rate": 0.00019932249277489444,
      "loss": 0.8884757161140442,
      "step": 1624
    },
    {
      "epoch": 0.6860759493670886,
      "grad_norm": 0.45893922448158264,
      "learning_rate": 0.0001993168999488237,
      "loss": 0.7739649415016174,
      "step": 1626
    },
    {
      "epoch": 0.6869198312236287,
      "grad_norm": 0.38631772994995117,
      "learning_rate": 0.0001993112842122515,
      "loss": 0.7948258519172668,
      "step": 1628
    },
    {
      "epoch": 0.6877637130801688,
      "grad_norm": 0.3824027180671692,
      "learning_rate": 0.00019930564556647334,
      "loss": 0.750511884689331,
      "step": 1630
    },
    {
      "epoch": 0.6886075949367089,
      "grad_norm": 0.3980776071548462,
      "learning_rate": 0.00019929998401278996,
      "loss": 0.9006738662719727,
      "step": 1632
    },
    {
      "epoch": 0.6894514767932489,
      "grad_norm": 0.41419896483421326,
      "learning_rate": 0.00019929429955250734,
      "loss": 0.6996869444847107,
      "step": 1634
    },
    {
      "epoch": 0.6902953586497891,
      "grad_norm": 0.43783676624298096,
      "learning_rate": 0.00019928859218693682,
      "loss": 0.8523393273353577,
      "step": 1636
    },
    {
      "epoch": 0.6911392405063291,
      "grad_norm": 0.4378126561641693,
      "learning_rate": 0.00019928286191739497,
      "loss": 0.8885987401008606,
      "step": 1638
    },
    {
      "epoch": 0.6919831223628692,
      "grad_norm": 0.4276133179664612,
      "learning_rate": 0.00019927710874520363,
      "loss": 0.8563809990882874,
      "step": 1640
    },
    {
      "epoch": 0.6928270042194092,
      "grad_norm": 0.4600282311439514,
      "learning_rate": 0.00019927133267168992,
      "loss": 0.854114294052124,
      "step": 1642
    },
    {
      "epoch": 0.6936708860759494,
      "grad_norm": 0.5058461427688599,
      "learning_rate": 0.00019926553369818635,
      "loss": 0.8557889461517334,
      "step": 1644
    },
    {
      "epoch": 0.6945147679324895,
      "grad_norm": 0.4947412312030792,
      "learning_rate": 0.00019925971182603057,
      "loss": 0.8622767925262451,
      "step": 1646
    },
    {
      "epoch": 0.6953586497890295,
      "grad_norm": 0.42555496096611023,
      "learning_rate": 0.00019925386705656558,
      "loss": 0.7836558818817139,
      "step": 1648
    },
    {
      "epoch": 0.6962025316455697,
      "grad_norm": 0.47560831904411316,
      "learning_rate": 0.00019924799939113967,
      "loss": 0.7877846956253052,
      "step": 1650
    },
    {
      "epoch": 0.6970464135021097,
      "grad_norm": 0.391702264547348,
      "learning_rate": 0.0001992421088311064,
      "loss": 0.775681734085083,
      "step": 1652
    },
    {
      "epoch": 0.6978902953586498,
      "grad_norm": 0.463679701089859,
      "learning_rate": 0.0001992361953778246,
      "loss": 0.8809882402420044,
      "step": 1654
    },
    {
      "epoch": 0.6987341772151898,
      "grad_norm": 0.44096484780311584,
      "learning_rate": 0.00019923025903265836,
      "loss": 0.8513299226760864,
      "step": 1656
    },
    {
      "epoch": 0.69957805907173,
      "grad_norm": 0.47818854451179504,
      "learning_rate": 0.0001992242997969772,
      "loss": 0.8309667706489563,
      "step": 1658
    },
    {
      "epoch": 0.70042194092827,
      "grad_norm": 0.4192790985107422,
      "learning_rate": 0.00019921831767215565,
      "loss": 0.8817558884620667,
      "step": 1660
    },
    {
      "epoch": 0.7012658227848101,
      "grad_norm": 0.45285239815711975,
      "learning_rate": 0.00019921231265957373,
      "loss": 0.8315755724906921,
      "step": 1662
    },
    {
      "epoch": 0.7021097046413503,
      "grad_norm": 0.47118625044822693,
      "learning_rate": 0.00019920628476061673,
      "loss": 0.8698058724403381,
      "step": 1664
    },
    {
      "epoch": 0.7029535864978903,
      "grad_norm": 0.4769238829612732,
      "learning_rate": 0.0001992002339766751,
      "loss": 0.953620970249176,
      "step": 1666
    },
    {
      "epoch": 0.7037974683544304,
      "grad_norm": 0.39397355914115906,
      "learning_rate": 0.00019919416030914468,
      "loss": 0.8536615371704102,
      "step": 1668
    },
    {
      "epoch": 0.7046413502109705,
      "grad_norm": 0.3659648299217224,
      "learning_rate": 0.00019918806375942655,
      "loss": 0.8159828782081604,
      "step": 1670
    },
    {
      "epoch": 0.7054852320675106,
      "grad_norm": 0.4381789565086365,
      "learning_rate": 0.00019918194432892703,
      "loss": 0.782463550567627,
      "step": 1672
    },
    {
      "epoch": 0.7063291139240506,
      "grad_norm": 0.44745752215385437,
      "learning_rate": 0.00019917580201905778,
      "loss": 0.9314272999763489,
      "step": 1674
    },
    {
      "epoch": 0.7071729957805907,
      "grad_norm": 0.4515164792537689,
      "learning_rate": 0.00019916963683123574,
      "loss": 0.860816240310669,
      "step": 1676
    },
    {
      "epoch": 0.7080168776371308,
      "grad_norm": 0.42735886573791504,
      "learning_rate": 0.00019916344876688303,
      "loss": 0.8008456826210022,
      "step": 1678
    },
    {
      "epoch": 0.7088607594936709,
      "grad_norm": 0.418275386095047,
      "learning_rate": 0.00019915723782742718,
      "loss": 0.7796595096588135,
      "step": 1680
    },
    {
      "epoch": 0.7097046413502109,
      "grad_norm": 0.44347989559173584,
      "learning_rate": 0.00019915100401430089,
      "loss": 0.9006506204605103,
      "step": 1682
    },
    {
      "epoch": 0.7105485232067511,
      "grad_norm": 0.3932702839374542,
      "learning_rate": 0.00019914474732894225,
      "loss": 0.7750146985054016,
      "step": 1684
    },
    {
      "epoch": 0.7113924050632912,
      "grad_norm": 0.4810502231121063,
      "learning_rate": 0.00019913846777279447,
      "loss": 0.7508097290992737,
      "step": 1686
    },
    {
      "epoch": 0.7122362869198312,
      "grad_norm": 0.4166778028011322,
      "learning_rate": 0.00019913216534730622,
      "loss": 0.7926796078681946,
      "step": 1688
    },
    {
      "epoch": 0.7130801687763713,
      "grad_norm": 0.47900474071502686,
      "learning_rate": 0.00019912584005393123,
      "loss": 0.8363928198814392,
      "step": 1690
    },
    {
      "epoch": 0.7139240506329114,
      "grad_norm": 0.435143381357193,
      "learning_rate": 0.00019911949189412872,
      "loss": 0.8649623990058899,
      "step": 1692
    },
    {
      "epoch": 0.7147679324894515,
      "grad_norm": 0.4070208966732025,
      "learning_rate": 0.00019911312086936305,
      "loss": 0.8196499943733215,
      "step": 1694
    },
    {
      "epoch": 0.7156118143459915,
      "grad_norm": 0.4717724621295929,
      "learning_rate": 0.0001991067269811039,
      "loss": 0.9157413840293884,
      "step": 1696
    },
    {
      "epoch": 0.7164556962025317,
      "grad_norm": 0.3942880928516388,
      "learning_rate": 0.0001991003102308262,
      "loss": 0.7880456447601318,
      "step": 1698
    },
    {
      "epoch": 0.7172995780590717,
      "grad_norm": 0.4037776589393616,
      "learning_rate": 0.0001990938706200102,
      "loss": 0.8088646531105042,
      "step": 1700
    },
    {
      "epoch": 0.7172995780590717,
      "eval_loss": 0.8708170056343079,
      "eval_runtime": 670.3019,
      "eval_samples_per_second": 3.143,
      "eval_steps_per_second": 3.143,
      "step": 1700
    },
    {
      "epoch": 0.7181434599156118,
      "grad_norm": 0.4443536400794983,
      "learning_rate": 0.0001990874081501414,
      "loss": 0.8740324378013611,
      "step": 1702
    },
    {
      "epoch": 0.7189873417721518,
      "grad_norm": 0.45089733600616455,
      "learning_rate": 0.00019908092282271053,
      "loss": 0.8305023908615112,
      "step": 1704
    },
    {
      "epoch": 0.719831223628692,
      "grad_norm": 0.3903036415576935,
      "learning_rate": 0.00019907441463921366,
      "loss": 0.7718394994735718,
      "step": 1706
    },
    {
      "epoch": 0.7206751054852321,
      "grad_norm": 0.42990729212760925,
      "learning_rate": 0.00019906788360115208,
      "loss": 0.843289315700531,
      "step": 1708
    },
    {
      "epoch": 0.7215189873417721,
      "grad_norm": 0.4287833571434021,
      "learning_rate": 0.0001990613297100324,
      "loss": 0.8332282900810242,
      "step": 1710
    },
    {
      "epoch": 0.7223628691983123,
      "grad_norm": 0.4557269513607025,
      "learning_rate": 0.00019905475296736646,
      "loss": 0.784180223941803,
      "step": 1712
    },
    {
      "epoch": 0.7232067510548523,
      "grad_norm": 0.4001525640487671,
      "learning_rate": 0.0001990481533746714,
      "loss": 0.7807716131210327,
      "step": 1714
    },
    {
      "epoch": 0.7240506329113924,
      "grad_norm": 0.5208709836006165,
      "learning_rate": 0.0001990415309334696,
      "loss": 0.7936414480209351,
      "step": 1716
    },
    {
      "epoch": 0.7248945147679325,
      "grad_norm": 0.46469953656196594,
      "learning_rate": 0.00019903488564528875,
      "loss": 0.7964845895767212,
      "step": 1718
    },
    {
      "epoch": 0.7257383966244726,
      "grad_norm": 0.405773401260376,
      "learning_rate": 0.00019902821751166178,
      "loss": 0.8302215337753296,
      "step": 1720
    },
    {
      "epoch": 0.7265822784810126,
      "grad_norm": 0.3874973654747009,
      "learning_rate": 0.00019902152653412692,
      "loss": 0.8486512899398804,
      "step": 1722
    },
    {
      "epoch": 0.7274261603375527,
      "grad_norm": 0.46865755319595337,
      "learning_rate": 0.00019901481271422758,
      "loss": 0.837841272354126,
      "step": 1724
    },
    {
      "epoch": 0.7282700421940929,
      "grad_norm": 0.4139123558998108,
      "learning_rate": 0.0001990080760535126,
      "loss": 0.7640942335128784,
      "step": 1726
    },
    {
      "epoch": 0.7291139240506329,
      "grad_norm": 0.5003024935722351,
      "learning_rate": 0.000199001316553536,
      "loss": 0.8236244320869446,
      "step": 1728
    },
    {
      "epoch": 0.729957805907173,
      "grad_norm": 0.38495776057243347,
      "learning_rate": 0.00019899453421585696,
      "loss": 0.7792612314224243,
      "step": 1730
    },
    {
      "epoch": 0.7308016877637131,
      "grad_norm": 0.4462733268737793,
      "learning_rate": 0.00019898772904204014,
      "loss": 0.7733872532844543,
      "step": 1732
    },
    {
      "epoch": 0.7316455696202532,
      "grad_norm": 0.398248553276062,
      "learning_rate": 0.00019898090103365532,
      "loss": 0.8933147192001343,
      "step": 1734
    },
    {
      "epoch": 0.7324894514767932,
      "grad_norm": 0.4231175482273102,
      "learning_rate": 0.00019897405019227756,
      "loss": 0.8198356628417969,
      "step": 1736
    },
    {
      "epoch": 0.7333333333333333,
      "grad_norm": 0.43639084696769714,
      "learning_rate": 0.0001989671765194873,
      "loss": 0.8266391158103943,
      "step": 1738
    },
    {
      "epoch": 0.7341772151898734,
      "grad_norm": 0.4235835671424866,
      "learning_rate": 0.00019896028001687008,
      "loss": 0.7839997410774231,
      "step": 1740
    },
    {
      "epoch": 0.7350210970464135,
      "grad_norm": 0.4033111035823822,
      "learning_rate": 0.00019895336068601687,
      "loss": 0.7153518199920654,
      "step": 1742
    },
    {
      "epoch": 0.7358649789029535,
      "grad_norm": 0.44281265139579773,
      "learning_rate": 0.00019894641852852377,
      "loss": 0.9079289436340332,
      "step": 1744
    },
    {
      "epoch": 0.7367088607594937,
      "grad_norm": 0.4882747232913971,
      "learning_rate": 0.0001989394535459922,
      "loss": 0.8645254373550415,
      "step": 1746
    },
    {
      "epoch": 0.7375527426160338,
      "grad_norm": 0.34858641028404236,
      "learning_rate": 0.00019893246574002887,
      "loss": 0.8134214878082275,
      "step": 1748
    },
    {
      "epoch": 0.7383966244725738,
      "grad_norm": 0.4273303747177124,
      "learning_rate": 0.00019892545511224574,
      "loss": 0.8142663240432739,
      "step": 1750
    },
    {
      "epoch": 0.739240506329114,
      "grad_norm": 0.4289957284927368,
      "learning_rate": 0.00019891842166426004,
      "loss": 0.7957643866539001,
      "step": 1752
    },
    {
      "epoch": 0.740084388185654,
      "grad_norm": 0.4812224805355072,
      "learning_rate": 0.00019891136539769416,
      "loss": 0.9000363945960999,
      "step": 1754
    },
    {
      "epoch": 0.7409282700421941,
      "grad_norm": 0.4078022837638855,
      "learning_rate": 0.00019890428631417595,
      "loss": 0.7719792723655701,
      "step": 1756
    },
    {
      "epoch": 0.7417721518987341,
      "grad_norm": 0.40169858932495117,
      "learning_rate": 0.00019889718441533838,
      "loss": 0.7681847214698792,
      "step": 1758
    },
    {
      "epoch": 0.7426160337552743,
      "grad_norm": 0.3713594377040863,
      "learning_rate": 0.00019889005970281972,
      "loss": 0.7536827325820923,
      "step": 1760
    },
    {
      "epoch": 0.7434599156118143,
      "grad_norm": 0.4183627665042877,
      "learning_rate": 0.0001988829121782635,
      "loss": 0.9000160694122314,
      "step": 1762
    },
    {
      "epoch": 0.7443037974683544,
      "grad_norm": 0.4241594672203064,
      "learning_rate": 0.00019887574184331851,
      "loss": 0.8047307133674622,
      "step": 1764
    },
    {
      "epoch": 0.7451476793248946,
      "grad_norm": 0.4249233603477478,
      "learning_rate": 0.00019886854869963883,
      "loss": 0.8932583928108215,
      "step": 1766
    },
    {
      "epoch": 0.7459915611814346,
      "grad_norm": 0.35815340280532837,
      "learning_rate": 0.00019886133274888378,
      "loss": 0.7684977054595947,
      "step": 1768
    },
    {
      "epoch": 0.7468354430379747,
      "grad_norm": 0.41035401821136475,
      "learning_rate": 0.00019885409399271795,
      "loss": 0.8644338250160217,
      "step": 1770
    },
    {
      "epoch": 0.7476793248945147,
      "grad_norm": 0.5450286269187927,
      "learning_rate": 0.00019884683243281116,
      "loss": 0.8035860657691956,
      "step": 1772
    },
    {
      "epoch": 0.7485232067510549,
      "grad_norm": 0.5280999541282654,
      "learning_rate": 0.0001988395480708385,
      "loss": 0.8861207962036133,
      "step": 1774
    },
    {
      "epoch": 0.7493670886075949,
      "grad_norm": 0.42665231227874756,
      "learning_rate": 0.00019883224090848036,
      "loss": 0.7506847977638245,
      "step": 1776
    },
    {
      "epoch": 0.750210970464135,
      "grad_norm": 0.39029282331466675,
      "learning_rate": 0.00019882491094742232,
      "loss": 0.7662046551704407,
      "step": 1778
    },
    {
      "epoch": 0.7510548523206751,
      "grad_norm": 0.43870019912719727,
      "learning_rate": 0.00019881755818935534,
      "loss": 0.7590143084526062,
      "step": 1780
    },
    {
      "epoch": 0.7518987341772152,
      "grad_norm": 0.4195050001144409,
      "learning_rate": 0.0001988101826359755,
      "loss": 0.9340365529060364,
      "step": 1782
    },
    {
      "epoch": 0.7527426160337553,
      "grad_norm": 0.4236123263835907,
      "learning_rate": 0.0001988027842889842,
      "loss": 0.7969209551811218,
      "step": 1784
    },
    {
      "epoch": 0.7535864978902953,
      "grad_norm": 0.4274357259273529,
      "learning_rate": 0.00019879536315008808,
      "loss": 0.7892382144927979,
      "step": 1786
    },
    {
      "epoch": 0.7544303797468355,
      "grad_norm": 0.4622916579246521,
      "learning_rate": 0.00019878791922099912,
      "loss": 0.8752562403678894,
      "step": 1788
    },
    {
      "epoch": 0.7552742616033755,
      "grad_norm": 0.3648734986782074,
      "learning_rate": 0.00019878045250343445,
      "loss": 0.813011884689331,
      "step": 1790
    },
    {
      "epoch": 0.7561181434599156,
      "grad_norm": 0.41361239552497864,
      "learning_rate": 0.00019877296299911648,
      "loss": 0.7310198545455933,
      "step": 1792
    },
    {
      "epoch": 0.7569620253164557,
      "grad_norm": 0.4113222062587738,
      "learning_rate": 0.00019876545070977294,
      "loss": 0.858386754989624,
      "step": 1794
    },
    {
      "epoch": 0.7578059071729958,
      "grad_norm": 0.4295370876789093,
      "learning_rate": 0.00019875791563713676,
      "loss": 0.8377325534820557,
      "step": 1796
    },
    {
      "epoch": 0.7586497890295358,
      "grad_norm": 0.4227522015571594,
      "learning_rate": 0.0001987503577829461,
      "loss": 0.9139418005943298,
      "step": 1798
    },
    {
      "epoch": 0.759493670886076,
      "grad_norm": 0.3638151288032532,
      "learning_rate": 0.00019874277714894442,
      "loss": 0.6994872689247131,
      "step": 1800
    },
    {
      "epoch": 0.759493670886076,
      "eval_loss": 0.8625519275665283,
      "eval_runtime": 686.4271,
      "eval_samples_per_second": 3.07,
      "eval_steps_per_second": 3.07,
      "step": 1800
    },
    {
      "epoch": 0.760337552742616,
      "grad_norm": 0.46954411268234253,
      "learning_rate": 0.00019873517373688047,
      "loss": 0.8681167960166931,
      "step": 1802
    },
    {
      "epoch": 0.7611814345991561,
      "grad_norm": 0.41958674788475037,
      "learning_rate": 0.00019872754754850819,
      "loss": 0.7420852184295654,
      "step": 1804
    },
    {
      "epoch": 0.7620253164556962,
      "grad_norm": 0.431226521730423,
      "learning_rate": 0.00019871989858558678,
      "loss": 0.8018608093261719,
      "step": 1806
    },
    {
      "epoch": 0.7628691983122363,
      "grad_norm": 0.45129454135894775,
      "learning_rate": 0.0001987122268498807,
      "loss": 0.8793904781341553,
      "step": 1808
    },
    {
      "epoch": 0.7637130801687764,
      "grad_norm": 0.44278961420059204,
      "learning_rate": 0.00019870453234315972,
      "loss": 0.8416730761528015,
      "step": 1810
    },
    {
      "epoch": 0.7645569620253164,
      "grad_norm": 0.4689098000526428,
      "learning_rate": 0.00019869681506719876,
      "loss": 0.8225743174552917,
      "step": 1812
    },
    {
      "epoch": 0.7654008438818566,
      "grad_norm": 0.4413386881351471,
      "learning_rate": 0.00019868907502377806,
      "loss": 0.7871913313865662,
      "step": 1814
    },
    {
      "epoch": 0.7662447257383966,
      "grad_norm": 0.48395273089408875,
      "learning_rate": 0.00019868131221468315,
      "loss": 0.8616237044334412,
      "step": 1816
    },
    {
      "epoch": 0.7670886075949367,
      "grad_norm": 0.370263934135437,
      "learning_rate": 0.0001986735266417047,
      "loss": 0.7243452668190002,
      "step": 1818
    },
    {
      "epoch": 0.7679324894514767,
      "grad_norm": 0.4522445797920227,
      "learning_rate": 0.00019866571830663875,
      "loss": 0.8623812198638916,
      "step": 1820
    },
    {
      "epoch": 0.7687763713080169,
      "grad_norm": 0.43821004033088684,
      "learning_rate": 0.00019865788721128643,
      "loss": 0.776618480682373,
      "step": 1822
    },
    {
      "epoch": 0.769620253164557,
      "grad_norm": 0.3825650215148926,
      "learning_rate": 0.00019865003335745436,
      "loss": 0.8722774982452393,
      "step": 1824
    },
    {
      "epoch": 0.770464135021097,
      "grad_norm": 0.43684205412864685,
      "learning_rate": 0.00019864215674695416,
      "loss": 0.907802939414978,
      "step": 1826
    },
    {
      "epoch": 0.7713080168776372,
      "grad_norm": 0.4128975570201874,
      "learning_rate": 0.00019863425738160287,
      "loss": 0.8505539298057556,
      "step": 1828
    },
    {
      "epoch": 0.7721518987341772,
      "grad_norm": 0.4254065454006195,
      "learning_rate": 0.0001986263352632227,
      "loss": 0.83274906873703,
      "step": 1830
    },
    {
      "epoch": 0.7729957805907173,
      "grad_norm": 0.4137375056743622,
      "learning_rate": 0.00019861839039364118,
      "loss": 0.8172078728675842,
      "step": 1832
    },
    {
      "epoch": 0.7738396624472574,
      "grad_norm": 0.4387703239917755,
      "learning_rate": 0.00019861042277469096,
      "loss": 0.8610842227935791,
      "step": 1834
    },
    {
      "epoch": 0.7746835443037975,
      "grad_norm": 0.398952454328537,
      "learning_rate": 0.00019860243240821005,
      "loss": 0.7961188554763794,
      "step": 1836
    },
    {
      "epoch": 0.7755274261603375,
      "grad_norm": 0.4079921543598175,
      "learning_rate": 0.0001985944192960417,
      "loss": 0.8078321218490601,
      "step": 1838
    },
    {
      "epoch": 0.7763713080168776,
      "grad_norm": 0.4701489508152008,
      "learning_rate": 0.00019858638344003433,
      "loss": 0.8743909001350403,
      "step": 1840
    },
    {
      "epoch": 0.7772151898734178,
      "grad_norm": 0.5391269326210022,
      "learning_rate": 0.00019857832484204173,
      "loss": 0.7681707143783569,
      "step": 1842
    },
    {
      "epoch": 0.7780590717299578,
      "grad_norm": 0.36250734329223633,
      "learning_rate": 0.00019857024350392277,
      "loss": 0.7817525863647461,
      "step": 1844
    },
    {
      "epoch": 0.7789029535864979,
      "grad_norm": 0.41237136721611023,
      "learning_rate": 0.00019856213942754175,
      "loss": 0.7614551782608032,
      "step": 1846
    },
    {
      "epoch": 0.779746835443038,
      "grad_norm": 0.3968869745731354,
      "learning_rate": 0.00019855401261476807,
      "loss": 0.7492313981056213,
      "step": 1848
    },
    {
      "epoch": 0.7805907172995781,
      "grad_norm": 0.441476434469223,
      "learning_rate": 0.00019854586306747646,
      "loss": 0.8615695238113403,
      "step": 1850
    },
    {
      "epoch": 0.7814345991561181,
      "grad_norm": 0.4486154317855835,
      "learning_rate": 0.00019853769078754686,
      "loss": 0.8416724801063538,
      "step": 1852
    },
    {
      "epoch": 0.7822784810126582,
      "grad_norm": 0.45148879289627075,
      "learning_rate": 0.0001985294957768644,
      "loss": 0.8987806439399719,
      "step": 1854
    },
    {
      "epoch": 0.7831223628691983,
      "grad_norm": 0.39330095052719116,
      "learning_rate": 0.0001985212780373196,
      "loss": 0.7597590088844299,
      "step": 1856
    },
    {
      "epoch": 0.7839662447257384,
      "grad_norm": 0.4260408580303192,
      "learning_rate": 0.00019851303757080808,
      "loss": 0.8429927229881287,
      "step": 1858
    },
    {
      "epoch": 0.7848101265822784,
      "grad_norm": 0.37519171833992004,
      "learning_rate": 0.00019850477437923075,
      "loss": 0.7443564534187317,
      "step": 1860
    },
    {
      "epoch": 0.7856540084388186,
      "grad_norm": 0.4991084337234497,
      "learning_rate": 0.00019849648846449383,
      "loss": 0.934238612651825,
      "step": 1862
    },
    {
      "epoch": 0.7864978902953587,
      "grad_norm": 0.4711335003376007,
      "learning_rate": 0.00019848817982850867,
      "loss": 0.8938905000686646,
      "step": 1864
    },
    {
      "epoch": 0.7873417721518987,
      "grad_norm": 0.4145370423793793,
      "learning_rate": 0.00019847984847319193,
      "loss": 0.8745643496513367,
      "step": 1866
    },
    {
      "epoch": 0.7881856540084389,
      "grad_norm": 0.3444044888019562,
      "learning_rate": 0.00019847149440046548,
      "loss": 0.7178786396980286,
      "step": 1868
    },
    {
      "epoch": 0.7890295358649789,
      "grad_norm": 0.34632962942123413,
      "learning_rate": 0.00019846311761225646,
      "loss": 0.9114303588867188,
      "step": 1870
    },
    {
      "epoch": 0.789873417721519,
      "grad_norm": 0.38630741834640503,
      "learning_rate": 0.0001984547181104972,
      "loss": 0.836281955242157,
      "step": 1872
    },
    {
      "epoch": 0.790717299578059,
      "grad_norm": 0.40947434306144714,
      "learning_rate": 0.00019844629589712534,
      "loss": 0.8247858881950378,
      "step": 1874
    },
    {
      "epoch": 0.7915611814345992,
      "grad_norm": 0.45878684520721436,
      "learning_rate": 0.00019843785097408372,
      "loss": 0.8446351289749146,
      "step": 1876
    },
    {
      "epoch": 0.7924050632911392,
      "grad_norm": 0.37202852964401245,
      "learning_rate": 0.0001984293833433204,
      "loss": 0.8567686676979065,
      "step": 1878
    },
    {
      "epoch": 0.7932489451476793,
      "grad_norm": 0.3839069902896881,
      "learning_rate": 0.00019842089300678876,
      "loss": 0.8134047985076904,
      "step": 1880
    },
    {
      "epoch": 0.7940928270042195,
      "grad_norm": 0.4018687605857849,
      "learning_rate": 0.00019841237996644727,
      "loss": 0.8670110106468201,
      "step": 1882
    },
    {
      "epoch": 0.7949367088607595,
      "grad_norm": 0.372089684009552,
      "learning_rate": 0.0001984038442242598,
      "loss": 0.7975355386734009,
      "step": 1884
    },
    {
      "epoch": 0.7957805907172996,
      "grad_norm": 0.4492705166339874,
      "learning_rate": 0.0001983952857821953,
      "loss": 0.8755611777305603,
      "step": 1886
    },
    {
      "epoch": 0.7966244725738396,
      "grad_norm": 0.451054185628891,
      "learning_rate": 0.00019838670464222813,
      "loss": 0.8680241107940674,
      "step": 1888
    },
    {
      "epoch": 0.7974683544303798,
      "grad_norm": 0.4036900997161865,
      "learning_rate": 0.00019837810080633773,
      "loss": 0.7990990877151489,
      "step": 1890
    },
    {
      "epoch": 0.7983122362869198,
      "grad_norm": 0.46125802397727966,
      "learning_rate": 0.0001983694742765089,
      "loss": 0.8598953485488892,
      "step": 1892
    },
    {
      "epoch": 0.7991561181434599,
      "grad_norm": 0.4458785951137543,
      "learning_rate": 0.00019836082505473153,
      "loss": 0.7707474827766418,
      "step": 1894
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.44501590728759766,
      "learning_rate": 0.0001983521531430009,
      "loss": 0.8069534301757812,
      "step": 1896
    },
    {
      "epoch": 0.8008438818565401,
      "grad_norm": 0.400771826505661,
      "learning_rate": 0.0001983434585433174,
      "loss": 0.862334668636322,
      "step": 1898
    },
    {
      "epoch": 0.8016877637130801,
      "grad_norm": 0.39193347096443176,
      "learning_rate": 0.00019833474125768676,
      "loss": 0.8125433325767517,
      "step": 1900
    },
    {
      "epoch": 0.8016877637130801,
      "eval_loss": 0.8546335697174072,
      "eval_runtime": 688.5301,
      "eval_samples_per_second": 3.06,
      "eval_steps_per_second": 3.06,
      "step": 1900
    },
    {
      "epoch": 0.8025316455696202,
      "grad_norm": 0.441129207611084,
      "learning_rate": 0.00019832600128811986,
      "loss": 0.8246012330055237,
      "step": 1902
    },
    {
      "epoch": 0.8033755274261604,
      "grad_norm": 0.4089467227458954,
      "learning_rate": 0.00019831723863663285,
      "loss": 0.8387641310691833,
      "step": 1904
    },
    {
      "epoch": 0.8042194092827004,
      "grad_norm": 0.4871654510498047,
      "learning_rate": 0.0001983084533052471,
      "loss": 0.7891429662704468,
      "step": 1906
    },
    {
      "epoch": 0.8050632911392405,
      "grad_norm": 0.40085604786872864,
      "learning_rate": 0.00019829964529598923,
      "loss": 0.8008774518966675,
      "step": 1908
    },
    {
      "epoch": 0.8059071729957806,
      "grad_norm": 0.38775014877319336,
      "learning_rate": 0.00019829081461089109,
      "loss": 0.7921834588050842,
      "step": 1910
    },
    {
      "epoch": 0.8067510548523207,
      "grad_norm": 0.37830594182014465,
      "learning_rate": 0.0001982819612519897,
      "loss": 0.7752519845962524,
      "step": 1912
    },
    {
      "epoch": 0.8075949367088607,
      "grad_norm": 0.41137194633483887,
      "learning_rate": 0.0001982730852213274,
      "loss": 0.7958255410194397,
      "step": 1914
    },
    {
      "epoch": 0.8084388185654009,
      "grad_norm": 0.4871830940246582,
      "learning_rate": 0.0001982641865209517,
      "loss": 0.8177281618118286,
      "step": 1916
    },
    {
      "epoch": 0.809282700421941,
      "grad_norm": 0.4157388210296631,
      "learning_rate": 0.0001982552651529154,
      "loss": 0.7726616859436035,
      "step": 1918
    },
    {
      "epoch": 0.810126582278481,
      "grad_norm": 0.32338014245033264,
      "learning_rate": 0.00019824632111927645,
      "loss": 0.6601400375366211,
      "step": 1920
    },
    {
      "epoch": 0.810970464135021,
      "grad_norm": 0.4642949104309082,
      "learning_rate": 0.00019823735442209804,
      "loss": 0.7866622805595398,
      "step": 1922
    },
    {
      "epoch": 0.8118143459915612,
      "grad_norm": 0.43558797240257263,
      "learning_rate": 0.00019822836506344865,
      "loss": 0.7857986092567444,
      "step": 1924
    },
    {
      "epoch": 0.8126582278481013,
      "grad_norm": 0.3996953070163727,
      "learning_rate": 0.000198219353045402,
      "loss": 0.8407763838768005,
      "step": 1926
    },
    {
      "epoch": 0.8135021097046413,
      "grad_norm": 0.4415414333343506,
      "learning_rate": 0.00019821031837003686,
      "loss": 0.8433752655982971,
      "step": 1928
    },
    {
      "epoch": 0.8143459915611815,
      "grad_norm": 0.37329310178756714,
      "learning_rate": 0.00019820126103943752,
      "loss": 0.6941158175468445,
      "step": 1930
    },
    {
      "epoch": 0.8151898734177215,
      "grad_norm": 0.4482601284980774,
      "learning_rate": 0.00019819218105569323,
      "loss": 0.775604248046875,
      "step": 1932
    },
    {
      "epoch": 0.8160337552742616,
      "grad_norm": 0.426194429397583,
      "learning_rate": 0.00019818307842089854,
      "loss": 0.8496418595314026,
      "step": 1934
    },
    {
      "epoch": 0.8168776371308016,
      "grad_norm": 0.42379093170166016,
      "learning_rate": 0.00019817395313715335,
      "loss": 0.7767958045005798,
      "step": 1936
    },
    {
      "epoch": 0.8177215189873418,
      "grad_norm": 0.4149782061576843,
      "learning_rate": 0.0001981648052065626,
      "loss": 0.7347666025161743,
      "step": 1938
    },
    {
      "epoch": 0.8185654008438819,
      "grad_norm": 0.3927431106567383,
      "learning_rate": 0.0001981556346312366,
      "loss": 0.7839647531509399,
      "step": 1940
    },
    {
      "epoch": 0.8194092827004219,
      "grad_norm": 0.4483136236667633,
      "learning_rate": 0.00019814644141329083,
      "loss": 0.8870531916618347,
      "step": 1942
    },
    {
      "epoch": 0.8202531645569621,
      "grad_norm": 0.4400147497653961,
      "learning_rate": 0.00019813722555484594,
      "loss": 0.8646620512008667,
      "step": 1944
    },
    {
      "epoch": 0.8210970464135021,
      "grad_norm": 0.469971626996994,
      "learning_rate": 0.00019812798705802785,
      "loss": 0.9576541781425476,
      "step": 1946
    },
    {
      "epoch": 0.8219409282700422,
      "grad_norm": 0.388113409280777,
      "learning_rate": 0.00019811872592496776,
      "loss": 0.7956477403640747,
      "step": 1948
    },
    {
      "epoch": 0.8227848101265823,
      "grad_norm": 0.4271424114704132,
      "learning_rate": 0.00019810944215780201,
      "loss": 0.8440352082252502,
      "step": 1950
    },
    {
      "epoch": 0.8236286919831224,
      "grad_norm": 0.4097966253757477,
      "learning_rate": 0.00019810013575867217,
      "loss": 0.8589065074920654,
      "step": 1952
    },
    {
      "epoch": 0.8244725738396624,
      "grad_norm": 0.41550710797309875,
      "learning_rate": 0.00019809080672972504,
      "loss": 0.8606626987457275,
      "step": 1954
    },
    {
      "epoch": 0.8253164556962025,
      "grad_norm": 0.3680916130542755,
      "learning_rate": 0.0001980814550731127,
      "loss": 0.7582436800003052,
      "step": 1956
    },
    {
      "epoch": 0.8261603375527427,
      "grad_norm": 0.573297917842865,
      "learning_rate": 0.00019807208079099234,
      "loss": 0.8345186710357666,
      "step": 1958
    },
    {
      "epoch": 0.8270042194092827,
      "grad_norm": 0.43631303310394287,
      "learning_rate": 0.00019806268388552646,
      "loss": 0.889683723449707,
      "step": 1960
    },
    {
      "epoch": 0.8278481012658228,
      "grad_norm": 0.442531019449234,
      "learning_rate": 0.00019805326435888275,
      "loss": 0.8092973232269287,
      "step": 1962
    },
    {
      "epoch": 0.8286919831223629,
      "grad_norm": 0.45020824670791626,
      "learning_rate": 0.0001980438222132341,
      "loss": 0.8919535279273987,
      "step": 1964
    },
    {
      "epoch": 0.829535864978903,
      "grad_norm": 0.43131786584854126,
      "learning_rate": 0.0001980343574507586,
      "loss": 0.7652381658554077,
      "step": 1966
    },
    {
      "epoch": 0.830379746835443,
      "grad_norm": 0.4461326599121094,
      "learning_rate": 0.00019802487007363967,
      "loss": 0.8512389659881592,
      "step": 1968
    },
    {
      "epoch": 0.8312236286919831,
      "grad_norm": 0.4676894247531891,
      "learning_rate": 0.0001980153600840658,
      "loss": 0.8681327700614929,
      "step": 1970
    },
    {
      "epoch": 0.8320675105485232,
      "grad_norm": 0.38376888632774353,
      "learning_rate": 0.00019800582748423075,
      "loss": 0.7476955652236938,
      "step": 1972
    },
    {
      "epoch": 0.8329113924050633,
      "grad_norm": 0.37173229455947876,
      "learning_rate": 0.00019799627227633354,
      "loss": 0.814192533493042,
      "step": 1974
    },
    {
      "epoch": 0.8337552742616033,
      "grad_norm": 0.4345237910747528,
      "learning_rate": 0.00019798669446257844,
      "loss": 0.7668994069099426,
      "step": 1976
    },
    {
      "epoch": 0.8345991561181435,
      "grad_norm": 0.45872583985328674,
      "learning_rate": 0.0001979770940451747,
      "loss": 0.8321775197982788,
      "step": 1978
    },
    {
      "epoch": 0.8354430379746836,
      "grad_norm": 0.40618205070495605,
      "learning_rate": 0.0001979674710263371,
      "loss": 0.7824342250823975,
      "step": 1980
    },
    {
      "epoch": 0.8362869198312236,
      "grad_norm": 0.38377392292022705,
      "learning_rate": 0.00019795782540828544,
      "loss": 0.8752480745315552,
      "step": 1982
    },
    {
      "epoch": 0.8371308016877637,
      "grad_norm": 0.36340072751045227,
      "learning_rate": 0.00019794815719324476,
      "loss": 0.66700679063797,
      "step": 1984
    },
    {
      "epoch": 0.8379746835443038,
      "grad_norm": 0.4638384282588959,
      "learning_rate": 0.00019793846638344536,
      "loss": 0.8582209944725037,
      "step": 1986
    },
    {
      "epoch": 0.8388185654008439,
      "grad_norm": 0.38364699482917786,
      "learning_rate": 0.00019792875298112268,
      "loss": 0.7724968791007996,
      "step": 1988
    },
    {
      "epoch": 0.8396624472573839,
      "grad_norm": 0.439730703830719,
      "learning_rate": 0.00019791901698851749,
      "loss": 0.8542404174804688,
      "step": 1990
    },
    {
      "epoch": 0.8405063291139241,
      "grad_norm": 0.4622722566127777,
      "learning_rate": 0.00019790925840787563,
      "loss": 0.8424296975135803,
      "step": 1992
    },
    {
      "epoch": 0.8413502109704641,
      "grad_norm": 0.4491989314556122,
      "learning_rate": 0.0001978994772414482,
      "loss": 0.8400710225105286,
      "step": 1994
    },
    {
      "epoch": 0.8421940928270042,
      "grad_norm": 0.372295081615448,
      "learning_rate": 0.0001978896734914916,
      "loss": 0.7265452146530151,
      "step": 1996
    },
    {
      "epoch": 0.8430379746835444,
      "grad_norm": 0.4328666925430298,
      "learning_rate": 0.00019787984716026732,
      "loss": 0.8458228707313538,
      "step": 1998
    },
    {
      "epoch": 0.8438818565400844,
      "grad_norm": 0.42246317863464355,
      "learning_rate": 0.00019786999825004216,
      "loss": 0.8517491817474365,
      "step": 2000
    },
    {
      "epoch": 0.8438818565400844,
      "eval_loss": 0.8460908532142639,
      "eval_runtime": 685.2518,
      "eval_samples_per_second": 3.075,
      "eval_steps_per_second": 3.075,
      "step": 2000
    },
    {
      "epoch": 0.8447257383966245,
      "grad_norm": 0.3927323818206787,
      "learning_rate": 0.00019786012676308802,
      "loss": 0.8045481443405151,
      "step": 2002
    },
    {
      "epoch": 0.8455696202531645,
      "grad_norm": 0.38189369440078735,
      "learning_rate": 0.00019785023270168202,
      "loss": 0.7509838938713074,
      "step": 2004
    },
    {
      "epoch": 0.8464135021097047,
      "grad_norm": 0.40383535623550415,
      "learning_rate": 0.00019784031606810663,
      "loss": 0.7730163335800171,
      "step": 2006
    },
    {
      "epoch": 0.8472573839662447,
      "grad_norm": 0.3665419816970825,
      "learning_rate": 0.00019783037686464935,
      "loss": 0.7096828818321228,
      "step": 2008
    },
    {
      "epoch": 0.8481012658227848,
      "grad_norm": 0.36623379588127136,
      "learning_rate": 0.00019782041509360302,
      "loss": 0.8186401128768921,
      "step": 2010
    },
    {
      "epoch": 0.8489451476793249,
      "grad_norm": 0.477255642414093,
      "learning_rate": 0.0001978104307572656,
      "loss": 0.8502879738807678,
      "step": 2012
    },
    {
      "epoch": 0.849789029535865,
      "grad_norm": 0.44456636905670166,
      "learning_rate": 0.00019780042385794032,
      "loss": 0.9010884761810303,
      "step": 2014
    },
    {
      "epoch": 0.850632911392405,
      "grad_norm": 0.42378175258636475,
      "learning_rate": 0.00019779039439793552,
      "loss": 0.774183452129364,
      "step": 2016
    },
    {
      "epoch": 0.8514767932489451,
      "grad_norm": 0.43021997809410095,
      "learning_rate": 0.00019778034237956482,
      "loss": 0.8487694263458252,
      "step": 2018
    },
    {
      "epoch": 0.8523206751054853,
      "grad_norm": 0.38188812136650085,
      "learning_rate": 0.00019777026780514704,
      "loss": 0.8004868030548096,
      "step": 2020
    },
    {
      "epoch": 0.8531645569620253,
      "grad_norm": 0.3684130609035492,
      "learning_rate": 0.0001977601706770062,
      "loss": 0.7680953145027161,
      "step": 2022
    },
    {
      "epoch": 0.8540084388185654,
      "grad_norm": 0.444844514131546,
      "learning_rate": 0.00019775005099747153,
      "loss": 0.8990264534950256,
      "step": 2024
    },
    {
      "epoch": 0.8548523206751055,
      "grad_norm": 0.3432365655899048,
      "learning_rate": 0.00019773990876887737,
      "loss": 0.7676048874855042,
      "step": 2026
    },
    {
      "epoch": 0.8556962025316456,
      "grad_norm": 0.3728618025779724,
      "learning_rate": 0.00019772974399356343,
      "loss": 0.8546769618988037,
      "step": 2028
    },
    {
      "epoch": 0.8565400843881856,
      "grad_norm": 0.42767980694770813,
      "learning_rate": 0.00019771955667387449,
      "loss": 0.8009977340698242,
      "step": 2030
    },
    {
      "epoch": 0.8573839662447258,
      "grad_norm": 0.4125710129737854,
      "learning_rate": 0.00019770934681216055,
      "loss": 0.8424299955368042,
      "step": 2032
    },
    {
      "epoch": 0.8582278481012658,
      "grad_norm": 0.4399266839027405,
      "learning_rate": 0.00019769911441077685,
      "loss": 0.7940502762794495,
      "step": 2034
    },
    {
      "epoch": 0.8590717299578059,
      "grad_norm": 0.41797709465026855,
      "learning_rate": 0.0001976888594720838,
      "loss": 0.9424314498901367,
      "step": 2036
    },
    {
      "epoch": 0.859915611814346,
      "grad_norm": 0.5245009660720825,
      "learning_rate": 0.00019767858199844698,
      "loss": 0.9102896451950073,
      "step": 2038
    },
    {
      "epoch": 0.8607594936708861,
      "grad_norm": 0.4092593193054199,
      "learning_rate": 0.00019766828199223728,
      "loss": 0.7434720396995544,
      "step": 2040
    },
    {
      "epoch": 0.8616033755274262,
      "grad_norm": 0.40787473320961,
      "learning_rate": 0.00019765795945583068,
      "loss": 0.7441987991333008,
      "step": 2042
    },
    {
      "epoch": 0.8624472573839662,
      "grad_norm": 0.42438021302223206,
      "learning_rate": 0.0001976476143916084,
      "loss": 0.8317872881889343,
      "step": 2044
    },
    {
      "epoch": 0.8632911392405064,
      "grad_norm": 0.38261914253234863,
      "learning_rate": 0.00019763724680195682,
      "loss": 0.764509379863739,
      "step": 2046
    },
    {
      "epoch": 0.8641350210970464,
      "grad_norm": 0.43295741081237793,
      "learning_rate": 0.00019762685668926758,
      "loss": 0.8666167855262756,
      "step": 2048
    },
    {
      "epoch": 0.8649789029535865,
      "grad_norm": 0.36384403705596924,
      "learning_rate": 0.00019761644405593743,
      "loss": 0.7606754302978516,
      "step": 2050
    },
    {
      "epoch": 0.8658227848101265,
      "grad_norm": 0.4296814501285553,
      "learning_rate": 0.0001976060089043684,
      "loss": 0.827495813369751,
      "step": 2052
    },
    {
      "epoch": 0.8666666666666667,
      "grad_norm": 0.3831455111503601,
      "learning_rate": 0.0001975955512369677,
      "loss": 0.7418577075004578,
      "step": 2054
    },
    {
      "epoch": 0.8675105485232067,
      "grad_norm": 0.44710344076156616,
      "learning_rate": 0.0001975850710561477,
      "loss": 0.8603045344352722,
      "step": 2056
    },
    {
      "epoch": 0.8683544303797468,
      "grad_norm": 0.44012558460235596,
      "learning_rate": 0.00019757456836432593,
      "loss": 0.900658905506134,
      "step": 2058
    },
    {
      "epoch": 0.869198312236287,
      "grad_norm": 0.42166298627853394,
      "learning_rate": 0.0001975640431639252,
      "loss": 0.8416497707366943,
      "step": 2060
    },
    {
      "epoch": 0.870042194092827,
      "grad_norm": 0.40824490785598755,
      "learning_rate": 0.00019755349545737345,
      "loss": 0.8281066417694092,
      "step": 2062
    },
    {
      "epoch": 0.8708860759493671,
      "grad_norm": 0.4272223711013794,
      "learning_rate": 0.00019754292524710388,
      "loss": 0.83869469165802,
      "step": 2064
    },
    {
      "epoch": 0.8717299578059071,
      "grad_norm": 0.3732798397541046,
      "learning_rate": 0.00019753233253555478,
      "loss": 0.8337644934654236,
      "step": 2066
    },
    {
      "epoch": 0.8725738396624473,
      "grad_norm": 0.4048069417476654,
      "learning_rate": 0.00019752171732516973,
      "loss": 0.7677452564239502,
      "step": 2068
    },
    {
      "epoch": 0.8734177215189873,
      "grad_norm": 0.43628430366516113,
      "learning_rate": 0.00019751107961839742,
      "loss": 0.8320774435997009,
      "step": 2070
    },
    {
      "epoch": 0.8742616033755274,
      "grad_norm": 0.43674105405807495,
      "learning_rate": 0.00019750041941769174,
      "loss": 0.8480262160301208,
      "step": 2072
    },
    {
      "epoch": 0.8751054852320675,
      "grad_norm": 0.3678584098815918,
      "learning_rate": 0.0001974897367255119,
      "loss": 0.7598503828048706,
      "step": 2074
    },
    {
      "epoch": 0.8759493670886076,
      "grad_norm": 0.4316411316394806,
      "learning_rate": 0.0001974790315443221,
      "loss": 0.7907084822654724,
      "step": 2076
    },
    {
      "epoch": 0.8767932489451477,
      "grad_norm": 0.426465779542923,
      "learning_rate": 0.00019746830387659182,
      "loss": 0.8287727236747742,
      "step": 2078
    },
    {
      "epoch": 0.8776371308016878,
      "grad_norm": 0.447337806224823,
      "learning_rate": 0.00019745755372479578,
      "loss": 0.8464577794075012,
      "step": 2080
    },
    {
      "epoch": 0.8784810126582279,
      "grad_norm": 0.37877580523490906,
      "learning_rate": 0.0001974467810914138,
      "loss": 0.7383086681365967,
      "step": 2082
    },
    {
      "epoch": 0.8793248945147679,
      "grad_norm": 0.3914664089679718,
      "learning_rate": 0.0001974359859789309,
      "loss": 0.729221522808075,
      "step": 2084
    },
    {
      "epoch": 0.880168776371308,
      "grad_norm": 0.39767366647720337,
      "learning_rate": 0.00019742516838983733,
      "loss": 0.692332923412323,
      "step": 2086
    },
    {
      "epoch": 0.8810126582278481,
      "grad_norm": 0.4396754205226898,
      "learning_rate": 0.0001974143283266285,
      "loss": 0.8540068864822388,
      "step": 2088
    },
    {
      "epoch": 0.8818565400843882,
      "grad_norm": 0.4968172609806061,
      "learning_rate": 0.00019740346579180502,
      "loss": 0.8570998907089233,
      "step": 2090
    },
    {
      "epoch": 0.8827004219409282,
      "grad_norm": 0.41686809062957764,
      "learning_rate": 0.00019739258078787264,
      "loss": 0.784139096736908,
      "step": 2092
    },
    {
      "epoch": 0.8835443037974684,
      "grad_norm": 0.38788047432899475,
      "learning_rate": 0.0001973816733173423,
      "loss": 0.8521397113800049,
      "step": 2094
    },
    {
      "epoch": 0.8843881856540085,
      "grad_norm": 0.38369178771972656,
      "learning_rate": 0.00019737074338273023,
      "loss": 0.8457935452461243,
      "step": 2096
    },
    {
      "epoch": 0.8852320675105485,
      "grad_norm": 0.38869398832321167,
      "learning_rate": 0.0001973597909865577,
      "loss": 0.7425959706306458,
      "step": 2098
    },
    {
      "epoch": 0.8860759493670886,
      "grad_norm": 0.4067917466163635,
      "learning_rate": 0.00019734881613135122,
      "loss": 0.7742393016815186,
      "step": 2100
    },
    {
      "epoch": 0.8860759493670886,
      "eval_loss": 0.8401098847389221,
      "eval_runtime": 669.1149,
      "eval_samples_per_second": 3.149,
      "eval_steps_per_second": 3.149,
      "step": 2100
    },
    {
      "epoch": 0.8869198312236287,
      "grad_norm": 0.4282098412513733,
      "learning_rate": 0.00019733781881964242,
      "loss": 0.9099814295768738,
      "step": 2102
    },
    {
      "epoch": 0.8877637130801688,
      "grad_norm": 0.33882173895835876,
      "learning_rate": 0.00019732679905396826,
      "loss": 0.7458856105804443,
      "step": 2104
    },
    {
      "epoch": 0.8886075949367088,
      "grad_norm": 0.43959516286849976,
      "learning_rate": 0.00019731575683687078,
      "loss": 0.7829693555831909,
      "step": 2106
    },
    {
      "epoch": 0.889451476793249,
      "grad_norm": 0.40046483278274536,
      "learning_rate": 0.00019730469217089716,
      "loss": 0.7898997068405151,
      "step": 2108
    },
    {
      "epoch": 0.890295358649789,
      "grad_norm": 0.40572553873062134,
      "learning_rate": 0.00019729360505859984,
      "loss": 0.7874186635017395,
      "step": 2110
    },
    {
      "epoch": 0.8911392405063291,
      "grad_norm": 0.42086347937583923,
      "learning_rate": 0.0001972824955025364,
      "loss": 0.8499898910522461,
      "step": 2112
    },
    {
      "epoch": 0.8919831223628693,
      "grad_norm": 0.38845229148864746,
      "learning_rate": 0.00019727136350526956,
      "loss": 0.7940409779548645,
      "step": 2114
    },
    {
      "epoch": 0.8928270042194093,
      "grad_norm": 0.41575267910957336,
      "learning_rate": 0.00019726020906936728,
      "loss": 0.8279082775115967,
      "step": 2116
    },
    {
      "epoch": 0.8936708860759494,
      "grad_norm": 0.37615057826042175,
      "learning_rate": 0.0001972490321974027,
      "loss": 0.8217757940292358,
      "step": 2118
    },
    {
      "epoch": 0.8945147679324894,
      "grad_norm": 0.9318385124206543,
      "learning_rate": 0.00019723783289195415,
      "loss": 0.7637750506401062,
      "step": 2120
    },
    {
      "epoch": 0.8953586497890296,
      "grad_norm": 0.41948962211608887,
      "learning_rate": 0.000197226611155605,
      "loss": 0.8702366948127747,
      "step": 2122
    },
    {
      "epoch": 0.8962025316455696,
      "grad_norm": 0.4718417525291443,
      "learning_rate": 0.00019721536699094392,
      "loss": 0.8146984577178955,
      "step": 2124
    },
    {
      "epoch": 0.8970464135021097,
      "grad_norm": 0.4470657408237457,
      "learning_rate": 0.00019720410040056474,
      "loss": 0.8646075129508972,
      "step": 2126
    },
    {
      "epoch": 0.8978902953586498,
      "grad_norm": 0.4176540970802307,
      "learning_rate": 0.00019719281138706643,
      "loss": 0.7925992012023926,
      "step": 2128
    },
    {
      "epoch": 0.8987341772151899,
      "grad_norm": 0.4854719042778015,
      "learning_rate": 0.00019718149995305315,
      "loss": 0.8142143487930298,
      "step": 2130
    },
    {
      "epoch": 0.8995780590717299,
      "grad_norm": 0.4270440340042114,
      "learning_rate": 0.00019717016610113427,
      "loss": 0.8050890564918518,
      "step": 2132
    },
    {
      "epoch": 0.90042194092827,
      "grad_norm": 0.37710970640182495,
      "learning_rate": 0.00019715880983392422,
      "loss": 0.7888354659080505,
      "step": 2134
    },
    {
      "epoch": 0.9012658227848102,
      "grad_norm": 0.4181252717971802,
      "learning_rate": 0.00019714743115404273,
      "loss": 0.7348225712776184,
      "step": 2136
    },
    {
      "epoch": 0.9021097046413502,
      "grad_norm": 0.4475359618663788,
      "learning_rate": 0.0001971360300641146,
      "loss": 0.7729623913764954,
      "step": 2138
    },
    {
      "epoch": 0.9029535864978903,
      "grad_norm": 0.4052332937717438,
      "learning_rate": 0.00019712460656676992,
      "loss": 0.8066384792327881,
      "step": 2140
    },
    {
      "epoch": 0.9037974683544304,
      "grad_norm": 0.4567393362522125,
      "learning_rate": 0.0001971131606646438,
      "loss": 0.8053154349327087,
      "step": 2142
    },
    {
      "epoch": 0.9046413502109705,
      "grad_norm": 0.4304409325122833,
      "learning_rate": 0.00019710169236037656,
      "loss": 0.7242560386657715,
      "step": 2144
    },
    {
      "epoch": 0.9054852320675105,
      "grad_norm": 0.4785008132457733,
      "learning_rate": 0.0001970902016566138,
      "loss": 0.8475301265716553,
      "step": 2146
    },
    {
      "epoch": 0.9063291139240506,
      "grad_norm": 0.45226508378982544,
      "learning_rate": 0.00019707868855600618,
      "loss": 0.928544282913208,
      "step": 2148
    },
    {
      "epoch": 0.9071729957805907,
      "grad_norm": 0.3794468641281128,
      "learning_rate": 0.00019706715306120956,
      "loss": 0.8135722875595093,
      "step": 2150
    },
    {
      "epoch": 0.9080168776371308,
      "grad_norm": 0.4005141258239746,
      "learning_rate": 0.0001970555951748849,
      "loss": 0.7808290719985962,
      "step": 2152
    },
    {
      "epoch": 0.9088607594936708,
      "grad_norm": 0.37929919362068176,
      "learning_rate": 0.00019704401489969842,
      "loss": 0.8292917013168335,
      "step": 2154
    },
    {
      "epoch": 0.909704641350211,
      "grad_norm": 0.4458678066730499,
      "learning_rate": 0.0001970324122383215,
      "loss": 0.772884726524353,
      "step": 2156
    },
    {
      "epoch": 0.9105485232067511,
      "grad_norm": 0.41907885670661926,
      "learning_rate": 0.0001970207871934306,
      "loss": 0.8204470872879028,
      "step": 2158
    },
    {
      "epoch": 0.9113924050632911,
      "grad_norm": 0.40610212087631226,
      "learning_rate": 0.00019700913976770741,
      "loss": 0.8361451625823975,
      "step": 2160
    },
    {
      "epoch": 0.9122362869198313,
      "grad_norm": 0.4213273227214813,
      "learning_rate": 0.00019699746996383878,
      "loss": 0.8456075191497803,
      "step": 2162
    },
    {
      "epoch": 0.9130801687763713,
      "grad_norm": 0.49264612793922424,
      "learning_rate": 0.0001969857777845167,
      "loss": 0.8731603622436523,
      "step": 2164
    },
    {
      "epoch": 0.9139240506329114,
      "grad_norm": 0.42002132534980774,
      "learning_rate": 0.00019697406323243834,
      "loss": 0.8149666786193848,
      "step": 2166
    },
    {
      "epoch": 0.9147679324894514,
      "grad_norm": 0.37501421570777893,
      "learning_rate": 0.000196962326310306,
      "loss": 0.7508546710014343,
      "step": 2168
    },
    {
      "epoch": 0.9156118143459916,
      "grad_norm": 0.3706159293651581,
      "learning_rate": 0.00019695056702082717,
      "loss": 0.830280601978302,
      "step": 2170
    },
    {
      "epoch": 0.9164556962025316,
      "grad_norm": 0.3873467445373535,
      "learning_rate": 0.00019693878536671452,
      "loss": 0.7297167778015137,
      "step": 2172
    },
    {
      "epoch": 0.9172995780590717,
      "grad_norm": 0.42876651883125305,
      "learning_rate": 0.00019692698135068582,
      "loss": 0.7924292087554932,
      "step": 2174
    },
    {
      "epoch": 0.9181434599156119,
      "grad_norm": 0.4259159564971924,
      "learning_rate": 0.00019691515497546406,
      "loss": 0.8098247051239014,
      "step": 2176
    },
    {
      "epoch": 0.9189873417721519,
      "grad_norm": 0.38152721524238586,
      "learning_rate": 0.00019690330624377728,
      "loss": 0.6789063215255737,
      "step": 2178
    },
    {
      "epoch": 0.919831223628692,
      "grad_norm": 0.4135437607765198,
      "learning_rate": 0.00019689143515835887,
      "loss": 0.8582620620727539,
      "step": 2180
    },
    {
      "epoch": 0.920675105485232,
      "grad_norm": 0.3818798065185547,
      "learning_rate": 0.0001968795417219472,
      "loss": 0.8059743642807007,
      "step": 2182
    },
    {
      "epoch": 0.9215189873417722,
      "grad_norm": 0.39021286368370056,
      "learning_rate": 0.00019686762593728582,
      "loss": 0.7432259917259216,
      "step": 2184
    },
    {
      "epoch": 0.9223628691983122,
      "grad_norm": 0.37864068150520325,
      "learning_rate": 0.00019685568780712355,
      "loss": 0.7561086416244507,
      "step": 2186
    },
    {
      "epoch": 0.9232067510548523,
      "grad_norm": 0.450847864151001,
      "learning_rate": 0.00019684372733421425,
      "loss": 0.7552722692489624,
      "step": 2188
    },
    {
      "epoch": 0.9240506329113924,
      "grad_norm": 0.37909507751464844,
      "learning_rate": 0.00019683174452131695,
      "loss": 0.6905336380004883,
      "step": 2190
    },
    {
      "epoch": 0.9248945147679325,
      "grad_norm": 0.4439173638820648,
      "learning_rate": 0.0001968197393711959,
      "loss": 0.7710593938827515,
      "step": 2192
    },
    {
      "epoch": 0.9257383966244725,
      "grad_norm": 0.3908376395702362,
      "learning_rate": 0.00019680771188662044,
      "loss": 0.8212814331054688,
      "step": 2194
    },
    {
      "epoch": 0.9265822784810127,
      "grad_norm": 0.3528299033641815,
      "learning_rate": 0.00019679566207036507,
      "loss": 0.751355767250061,
      "step": 2196
    },
    {
      "epoch": 0.9274261603375528,
      "grad_norm": 0.4351397156715393,
      "learning_rate": 0.00019678358992520945,
      "loss": 0.8204057812690735,
      "step": 2198
    },
    {
      "epoch": 0.9282700421940928,
      "grad_norm": 0.45566943287849426,
      "learning_rate": 0.0001967714954539384,
      "loss": 0.763841450214386,
      "step": 2200
    },
    {
      "epoch": 0.9282700421940928,
      "eval_loss": 0.8336610198020935,
      "eval_runtime": 674.5134,
      "eval_samples_per_second": 3.124,
      "eval_steps_per_second": 3.124,
      "step": 2200
    },
    {
      "epoch": 0.9291139240506329,
      "grad_norm": 0.4516221284866333,
      "learning_rate": 0.00019675937865934188,
      "loss": 0.861711323261261,
      "step": 2202
    },
    {
      "epoch": 0.929957805907173,
      "grad_norm": 0.43421855568885803,
      "learning_rate": 0.00019674723954421502,
      "loss": 0.8062718510627747,
      "step": 2204
    },
    {
      "epoch": 0.9308016877637131,
      "grad_norm": 0.42442476749420166,
      "learning_rate": 0.00019673507811135803,
      "loss": 0.8069695234298706,
      "step": 2206
    },
    {
      "epoch": 0.9316455696202531,
      "grad_norm": 0.3976045250892639,
      "learning_rate": 0.00019672289436357637,
      "loss": 0.7336108684539795,
      "step": 2208
    },
    {
      "epoch": 0.9324894514767933,
      "grad_norm": 0.4131270945072174,
      "learning_rate": 0.00019671068830368058,
      "loss": 0.7559890151023865,
      "step": 2210
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 0.4599294364452362,
      "learning_rate": 0.00019669845993448634,
      "loss": 0.8447075486183167,
      "step": 2212
    },
    {
      "epoch": 0.9341772151898734,
      "grad_norm": 0.4291204810142517,
      "learning_rate": 0.00019668620925881455,
      "loss": 0.8329233527183533,
      "step": 2214
    },
    {
      "epoch": 0.9350210970464135,
      "grad_norm": 0.4226539731025696,
      "learning_rate": 0.00019667393627949116,
      "loss": 0.749232292175293,
      "step": 2216
    },
    {
      "epoch": 0.9358649789029536,
      "grad_norm": 0.4159580171108246,
      "learning_rate": 0.00019666164099934732,
      "loss": 0.7470011115074158,
      "step": 2218
    },
    {
      "epoch": 0.9367088607594937,
      "grad_norm": 0.4160766303539276,
      "learning_rate": 0.00019664932342121935,
      "loss": 0.8094202280044556,
      "step": 2220
    },
    {
      "epoch": 0.9375527426160337,
      "grad_norm": 0.45284298062324524,
      "learning_rate": 0.00019663698354794863,
      "loss": 0.8398169875144958,
      "step": 2222
    },
    {
      "epoch": 0.9383966244725739,
      "grad_norm": 0.3960540294647217,
      "learning_rate": 0.00019662462138238178,
      "loss": 0.7652443051338196,
      "step": 2224
    },
    {
      "epoch": 0.9392405063291139,
      "grad_norm": 0.4269275367259979,
      "learning_rate": 0.00019661223692737047,
      "loss": 0.7909489870071411,
      "step": 2226
    },
    {
      "epoch": 0.940084388185654,
      "grad_norm": 0.38187873363494873,
      "learning_rate": 0.00019659983018577157,
      "loss": 0.7821935415267944,
      "step": 2228
    },
    {
      "epoch": 0.9409282700421941,
      "grad_norm": 0.45898866653442383,
      "learning_rate": 0.0001965874011604471,
      "loss": 0.7792721390724182,
      "step": 2230
    },
    {
      "epoch": 0.9417721518987342,
      "grad_norm": 0.4740699827671051,
      "learning_rate": 0.00019657494985426418,
      "loss": 0.885725200176239,
      "step": 2232
    },
    {
      "epoch": 0.9426160337552743,
      "grad_norm": 0.3912813365459442,
      "learning_rate": 0.00019656247627009506,
      "loss": 0.7898101806640625,
      "step": 2234
    },
    {
      "epoch": 0.9434599156118143,
      "grad_norm": 0.4552418291568756,
      "learning_rate": 0.0001965499804108172,
      "loss": 0.8646330833435059,
      "step": 2236
    },
    {
      "epoch": 0.9443037974683545,
      "grad_norm": 0.4178548753261566,
      "learning_rate": 0.0001965374622793131,
      "loss": 0.8068296313285828,
      "step": 2238
    },
    {
      "epoch": 0.9451476793248945,
      "grad_norm": 0.38649076223373413,
      "learning_rate": 0.00019652492187847057,
      "loss": 0.7953271865844727,
      "step": 2240
    },
    {
      "epoch": 0.9459915611814346,
      "grad_norm": 0.39785075187683105,
      "learning_rate": 0.0001965123592111823,
      "loss": 0.8423402309417725,
      "step": 2242
    },
    {
      "epoch": 0.9468354430379747,
      "grad_norm": 0.47455263137817383,
      "learning_rate": 0.00019649977428034632,
      "loss": 0.8883589506149292,
      "step": 2244
    },
    {
      "epoch": 0.9476793248945148,
      "grad_norm": 0.3866841197013855,
      "learning_rate": 0.0001964871670888657,
      "loss": 0.7232863903045654,
      "step": 2246
    },
    {
      "epoch": 0.9485232067510548,
      "grad_norm": 0.3950609564781189,
      "learning_rate": 0.00019647453763964876,
      "loss": 0.7265347838401794,
      "step": 2248
    },
    {
      "epoch": 0.9493670886075949,
      "grad_norm": 0.4315829575061798,
      "learning_rate": 0.0001964618859356088,
      "loss": 0.8000131249427795,
      "step": 2250
    },
    {
      "epoch": 0.950210970464135,
      "grad_norm": 0.403984934091568,
      "learning_rate": 0.00019644921197966433,
      "loss": 0.823086678981781,
      "step": 2252
    },
    {
      "epoch": 0.9510548523206751,
      "grad_norm": 0.4311080574989319,
      "learning_rate": 0.00019643651577473897,
      "loss": 0.8457553386688232,
      "step": 2254
    },
    {
      "epoch": 0.9518987341772152,
      "grad_norm": 0.3884856104850769,
      "learning_rate": 0.00019642379732376158,
      "loss": 0.7866189479827881,
      "step": 2256
    },
    {
      "epoch": 0.9527426160337553,
      "grad_norm": 0.3384067714214325,
      "learning_rate": 0.00019641105662966595,
      "loss": 0.7095813751220703,
      "step": 2258
    },
    {
      "epoch": 0.9535864978902954,
      "grad_norm": 0.40426746010780334,
      "learning_rate": 0.00019639829369539117,
      "loss": 0.8271632194519043,
      "step": 2260
    },
    {
      "epoch": 0.9544303797468354,
      "grad_norm": 0.45495131611824036,
      "learning_rate": 0.00019638550852388144,
      "loss": 0.8204861283302307,
      "step": 2262
    },
    {
      "epoch": 0.9552742616033755,
      "grad_norm": 0.47201067209243774,
      "learning_rate": 0.00019637270111808598,
      "loss": 0.884763777256012,
      "step": 2264
    },
    {
      "epoch": 0.9561181434599156,
      "grad_norm": 0.3959396779537201,
      "learning_rate": 0.0001963598714809592,
      "loss": 0.7630926370620728,
      "step": 2266
    },
    {
      "epoch": 0.9569620253164557,
      "grad_norm": 0.4197136461734772,
      "learning_rate": 0.00019634701961546077,
      "loss": 0.797870397567749,
      "step": 2268
    },
    {
      "epoch": 0.9578059071729957,
      "grad_norm": 0.381290078163147,
      "learning_rate": 0.00019633414552455526,
      "loss": 0.7755846977233887,
      "step": 2270
    },
    {
      "epoch": 0.9586497890295359,
      "grad_norm": 0.3868124783039093,
      "learning_rate": 0.00019632124921121255,
      "loss": 0.7553264498710632,
      "step": 2272
    },
    {
      "epoch": 0.959493670886076,
      "grad_norm": 0.4350631833076477,
      "learning_rate": 0.00019630833067840747,
      "loss": 0.7792160511016846,
      "step": 2274
    },
    {
      "epoch": 0.960337552742616,
      "grad_norm": 0.4717157781124115,
      "learning_rate": 0.00019629538992912016,
      "loss": 0.878220796585083,
      "step": 2276
    },
    {
      "epoch": 0.9611814345991562,
      "grad_norm": 0.45545122027397156,
      "learning_rate": 0.00019628242696633584,
      "loss": 0.8891014456748962,
      "step": 2278
    },
    {
      "epoch": 0.9620253164556962,
      "grad_norm": 0.4421025514602661,
      "learning_rate": 0.00019626944179304467,
      "loss": 0.8024723529815674,
      "step": 2280
    },
    {
      "epoch": 0.9628691983122363,
      "grad_norm": 0.40385812520980835,
      "learning_rate": 0.00019625643441224222,
      "loss": 0.8036280274391174,
      "step": 2282
    },
    {
      "epoch": 0.9637130801687763,
      "grad_norm": 0.3866552412509918,
      "learning_rate": 0.00019624340482692898,
      "loss": 0.8072395324707031,
      "step": 2284
    },
    {
      "epoch": 0.9645569620253165,
      "grad_norm": 0.4113233685493469,
      "learning_rate": 0.0001962303530401106,
      "loss": 0.8046114444732666,
      "step": 2286
    },
    {
      "epoch": 0.9654008438818565,
      "grad_norm": 0.40720227360725403,
      "learning_rate": 0.00019621727905479798,
      "loss": 0.8434037566184998,
      "step": 2288
    },
    {
      "epoch": 0.9662447257383966,
      "grad_norm": 0.35759273171424866,
      "learning_rate": 0.00019620418287400693,
      "loss": 0.7832419276237488,
      "step": 2290
    },
    {
      "epoch": 0.9670886075949368,
      "grad_norm": 0.4170442223548889,
      "learning_rate": 0.0001961910645007585,
      "loss": 0.7975693345069885,
      "step": 2292
    },
    {
      "epoch": 0.9679324894514768,
      "grad_norm": 0.4126700162887573,
      "learning_rate": 0.00019617792393807895,
      "loss": 0.8554494976997375,
      "step": 2294
    },
    {
      "epoch": 0.9687763713080169,
      "grad_norm": 0.4231695830821991,
      "learning_rate": 0.00019616476118899942,
      "loss": 0.824539065361023,
      "step": 2296
    },
    {
      "epoch": 0.9696202531645569,
      "grad_norm": 0.3556209206581116,
      "learning_rate": 0.0001961515762565564,
      "loss": 0.7008040547370911,
      "step": 2298
    },
    {
      "epoch": 0.9704641350210971,
      "grad_norm": 0.4370400309562683,
      "learning_rate": 0.00019613836914379132,
      "loss": 0.8192558288574219,
      "step": 2300
    },
    {
      "epoch": 0.9704641350210971,
      "eval_loss": 0.8281980156898499,
      "eval_runtime": 688.6136,
      "eval_samples_per_second": 3.06,
      "eval_steps_per_second": 3.06,
      "step": 2300
    },
    {
      "epoch": 0.9713080168776371,
      "grad_norm": 0.4207614064216614,
      "learning_rate": 0.00019612513985375088,
      "loss": 0.878928005695343,
      "step": 2302
    },
    {
      "epoch": 0.9721518987341772,
      "grad_norm": 0.37607815861701965,
      "learning_rate": 0.0001961118883894868,
      "loss": 0.736182689666748,
      "step": 2304
    },
    {
      "epoch": 0.9729957805907173,
      "grad_norm": 0.43311476707458496,
      "learning_rate": 0.00019609861475405592,
      "loss": 0.8403618335723877,
      "step": 2306
    },
    {
      "epoch": 0.9738396624472574,
      "grad_norm": 0.4533176124095917,
      "learning_rate": 0.00019608531895052021,
      "loss": 0.8414564728736877,
      "step": 2308
    },
    {
      "epoch": 0.9746835443037974,
      "grad_norm": 0.4025697410106659,
      "learning_rate": 0.00019607200098194677,
      "loss": 0.8105775117874146,
      "step": 2310
    },
    {
      "epoch": 0.9755274261603376,
      "grad_norm": 0.37894198298454285,
      "learning_rate": 0.00019605866085140784,
      "loss": 0.8053821325302124,
      "step": 2312
    },
    {
      "epoch": 0.9763713080168777,
      "grad_norm": 0.46265891194343567,
      "learning_rate": 0.0001960452985619807,
      "loss": 0.8092884421348572,
      "step": 2314
    },
    {
      "epoch": 0.9772151898734177,
      "grad_norm": 0.3770054280757904,
      "learning_rate": 0.0001960319141167477,
      "loss": 0.7456095218658447,
      "step": 2316
    },
    {
      "epoch": 0.9780590717299578,
      "grad_norm": 0.44084450602531433,
      "learning_rate": 0.0001960185075187965,
      "loss": 0.7739883661270142,
      "step": 2318
    },
    {
      "epoch": 0.9789029535864979,
      "grad_norm": 0.3880341351032257,
      "learning_rate": 0.00019600507877121965,
      "loss": 0.6961302757263184,
      "step": 2320
    },
    {
      "epoch": 0.979746835443038,
      "grad_norm": 0.468037486076355,
      "learning_rate": 0.00019599162787711495,
      "loss": 0.8447984457015991,
      "step": 2322
    },
    {
      "epoch": 0.980590717299578,
      "grad_norm": 0.4123631417751312,
      "learning_rate": 0.00019597815483958527,
      "loss": 0.8155615329742432,
      "step": 2324
    },
    {
      "epoch": 0.9814345991561182,
      "grad_norm": 0.3827875554561615,
      "learning_rate": 0.00019596465966173853,
      "loss": 0.7990952730178833,
      "step": 2326
    },
    {
      "epoch": 0.9822784810126582,
      "grad_norm": 0.4644222557544708,
      "learning_rate": 0.00019595114234668788,
      "loss": 0.8899750709533691,
      "step": 2328
    },
    {
      "epoch": 0.9831223628691983,
      "grad_norm": 0.43699249625205994,
      "learning_rate": 0.00019593760289755144,
      "loss": 0.7863160371780396,
      "step": 2330
    },
    {
      "epoch": 0.9839662447257383,
      "grad_norm": 0.40713244676589966,
      "learning_rate": 0.00019592404131745254,
      "loss": 0.7960637807846069,
      "step": 2332
    },
    {
      "epoch": 0.9848101265822785,
      "grad_norm": 0.37364068627357483,
      "learning_rate": 0.00019591045760951957,
      "loss": 0.714144229888916,
      "step": 2334
    },
    {
      "epoch": 0.9856540084388186,
      "grad_norm": 0.4094736576080322,
      "learning_rate": 0.00019589685177688599,
      "loss": 0.7311791777610779,
      "step": 2336
    },
    {
      "epoch": 0.9864978902953586,
      "grad_norm": 0.4275180697441101,
      "learning_rate": 0.0001958832238226905,
      "loss": 0.8191342353820801,
      "step": 2338
    },
    {
      "epoch": 0.9873417721518988,
      "grad_norm": 0.4627651274204254,
      "learning_rate": 0.00019586957375007668,
      "loss": 0.7476106286048889,
      "step": 2340
    },
    {
      "epoch": 0.9881856540084388,
      "grad_norm": 0.44676414132118225,
      "learning_rate": 0.00019585590156219346,
      "loss": 0.8257967233657837,
      "step": 2342
    },
    {
      "epoch": 0.9890295358649789,
      "grad_norm": 0.40667134523391724,
      "learning_rate": 0.00019584220726219466,
      "loss": 0.7922079563140869,
      "step": 2344
    },
    {
      "epoch": 0.9898734177215189,
      "grad_norm": 0.40865346789360046,
      "learning_rate": 0.00019582849085323934,
      "loss": 0.7892434597015381,
      "step": 2346
    },
    {
      "epoch": 0.9907172995780591,
      "grad_norm": 0.43309709429740906,
      "learning_rate": 0.00019581475233849163,
      "loss": 0.8766644597053528,
      "step": 2348
    },
    {
      "epoch": 0.9915611814345991,
      "grad_norm": 0.41558781266212463,
      "learning_rate": 0.00019580099172112069,
      "loss": 0.9183312058448792,
      "step": 2350
    },
    {
      "epoch": 0.9924050632911392,
      "grad_norm": 0.432748019695282,
      "learning_rate": 0.00019578720900430082,
      "loss": 0.7905668020248413,
      "step": 2352
    },
    {
      "epoch": 0.9932489451476794,
      "grad_norm": 0.4116985499858856,
      "learning_rate": 0.0001957734041912115,
      "loss": 0.8279712200164795,
      "step": 2354
    },
    {
      "epoch": 0.9940928270042194,
      "grad_norm": 0.3927275240421295,
      "learning_rate": 0.00019575957728503718,
      "loss": 0.7451362609863281,
      "step": 2356
    },
    {
      "epoch": 0.9949367088607595,
      "grad_norm": 0.3389509320259094,
      "learning_rate": 0.0001957457282889675,
      "loss": 0.6769390106201172,
      "step": 2358
    },
    {
      "epoch": 0.9957805907172996,
      "grad_norm": 0.4220774471759796,
      "learning_rate": 0.00019573185720619712,
      "loss": 0.7590897083282471,
      "step": 2360
    },
    {
      "epoch": 0.9966244725738397,
      "grad_norm": 0.4299897849559784,
      "learning_rate": 0.00019571796403992583,
      "loss": 0.8301284313201904,
      "step": 2362
    },
    {
      "epoch": 0.9974683544303797,
      "grad_norm": 0.4031789302825928,
      "learning_rate": 0.00019570404879335856,
      "loss": 0.8019471764564514,
      "step": 2364
    },
    {
      "epoch": 0.9983122362869198,
      "grad_norm": 0.3957567811012268,
      "learning_rate": 0.00019569011146970526,
      "loss": 0.7427027821540833,
      "step": 2366
    },
    {
      "epoch": 0.99915611814346,
      "grad_norm": 0.41741347312927246,
      "learning_rate": 0.000195676152072181,
      "loss": 0.8221617341041565,
      "step": 2368
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.47121551632881165,
      "learning_rate": 0.00019566217060400595,
      "loss": 0.8143455982208252,
      "step": 2370
    },
    {
      "epoch": 1.0008438818565402,
      "grad_norm": 0.3854716122150421,
      "learning_rate": 0.0001956481670684054,
      "loss": 0.6971694231033325,
      "step": 2372
    },
    {
      "epoch": 1.00168776371308,
      "grad_norm": 0.4029138386249542,
      "learning_rate": 0.00019563414146860964,
      "loss": 0.6719155311584473,
      "step": 2374
    },
    {
      "epoch": 1.0025316455696203,
      "grad_norm": 0.40136656165122986,
      "learning_rate": 0.00019562009380785412,
      "loss": 0.7161872386932373,
      "step": 2376
    },
    {
      "epoch": 1.0033755274261604,
      "grad_norm": 0.40685850381851196,
      "learning_rate": 0.0001956060240893794,
      "loss": 0.71699059009552,
      "step": 2378
    },
    {
      "epoch": 1.0042194092827004,
      "grad_norm": 0.46153366565704346,
      "learning_rate": 0.00019559193231643104,
      "loss": 0.8030059337615967,
      "step": 2380
    },
    {
      "epoch": 1.0050632911392405,
      "grad_norm": 0.45048823952674866,
      "learning_rate": 0.0001955778184922598,
      "loss": 0.7666479349136353,
      "step": 2382
    },
    {
      "epoch": 1.0059071729957807,
      "grad_norm": 0.4260413348674774,
      "learning_rate": 0.00019556368262012142,
      "loss": 0.7481234073638916,
      "step": 2384
    },
    {
      "epoch": 1.0067510548523206,
      "grad_norm": 0.4819575548171997,
      "learning_rate": 0.0001955495247032768,
      "loss": 0.7943820953369141,
      "step": 2386
    },
    {
      "epoch": 1.0075949367088608,
      "grad_norm": 0.45789605379104614,
      "learning_rate": 0.0001955353447449919,
      "loss": 0.6401634812355042,
      "step": 2388
    },
    {
      "epoch": 1.0084388185654007,
      "grad_norm": 0.37019097805023193,
      "learning_rate": 0.00019552114274853778,
      "loss": 0.7058886885643005,
      "step": 2390
    },
    {
      "epoch": 1.009282700421941,
      "grad_norm": 0.44416263699531555,
      "learning_rate": 0.0001955069187171905,
      "loss": 0.7631242871284485,
      "step": 2392
    },
    {
      "epoch": 1.010126582278481,
      "grad_norm": 0.4478379786014557,
      "learning_rate": 0.00019549267265423138,
      "loss": 0.7873892784118652,
      "step": 2394
    },
    {
      "epoch": 1.010970464135021,
      "grad_norm": 0.4596130847930908,
      "learning_rate": 0.00019547840456294658,
      "loss": 0.7882059216499329,
      "step": 2396
    },
    {
      "epoch": 1.0118143459915612,
      "grad_norm": 0.4062999188899994,
      "learning_rate": 0.0001954641144466276,
      "loss": 0.6358574628829956,
      "step": 2398
    },
    {
      "epoch": 1.0126582278481013,
      "grad_norm": 0.47627049684524536,
      "learning_rate": 0.0001954498023085708,
      "loss": 0.7803886532783508,
      "step": 2400
    },
    {
      "epoch": 1.0126582278481013,
      "eval_loss": 0.8250564932823181,
      "eval_runtime": 691.5833,
      "eval_samples_per_second": 3.047,
      "eval_steps_per_second": 3.047,
      "step": 2400
    },
    {
      "epoch": 1.0135021097046413,
      "grad_norm": 0.40690696239471436,
      "learning_rate": 0.00019543546815207777,
      "loss": 0.7394700050354004,
      "step": 2402
    },
    {
      "epoch": 1.0143459915611814,
      "grad_norm": 0.45543980598449707,
      "learning_rate": 0.0001954211119804551,
      "loss": 0.7096555829048157,
      "step": 2404
    },
    {
      "epoch": 1.0151898734177216,
      "grad_norm": 0.4367314279079437,
      "learning_rate": 0.00019540673379701454,
      "loss": 0.7961843013763428,
      "step": 2406
    },
    {
      "epoch": 1.0160337552742615,
      "grad_norm": 0.4458340108394623,
      "learning_rate": 0.00019539233360507278,
      "loss": 0.743843138217926,
      "step": 2408
    },
    {
      "epoch": 1.0168776371308017,
      "grad_norm": 0.3741893470287323,
      "learning_rate": 0.0001953779114079517,
      "loss": 0.7273756265640259,
      "step": 2410
    },
    {
      "epoch": 1.0177215189873419,
      "grad_norm": 0.4340079426765442,
      "learning_rate": 0.00019536346720897823,
      "loss": 0.7922506928443909,
      "step": 2412
    },
    {
      "epoch": 1.0185654008438818,
      "grad_norm": 0.4518018662929535,
      "learning_rate": 0.00019534900101148437,
      "loss": 0.6492037773132324,
      "step": 2414
    },
    {
      "epoch": 1.019409282700422,
      "grad_norm": 0.4160727560520172,
      "learning_rate": 0.00019533451281880716,
      "loss": 0.7422950863838196,
      "step": 2416
    },
    {
      "epoch": 1.0202531645569621,
      "grad_norm": 0.35953211784362793,
      "learning_rate": 0.00019532000263428883,
      "loss": 0.6489207148551941,
      "step": 2418
    },
    {
      "epoch": 1.021097046413502,
      "grad_norm": 0.38774433732032776,
      "learning_rate": 0.0001953054704612765,
      "loss": 0.7449417114257812,
      "step": 2420
    },
    {
      "epoch": 1.0219409282700422,
      "grad_norm": 0.48185858130455017,
      "learning_rate": 0.0001952909163031225,
      "loss": 0.8481494188308716,
      "step": 2422
    },
    {
      "epoch": 1.0227848101265822,
      "grad_norm": 0.4098491072654724,
      "learning_rate": 0.00019527634016318425,
      "loss": 0.7442291378974915,
      "step": 2424
    },
    {
      "epoch": 1.0236286919831223,
      "grad_norm": 0.41284480690956116,
      "learning_rate": 0.00019526174204482412,
      "loss": 0.7564480900764465,
      "step": 2426
    },
    {
      "epoch": 1.0244725738396625,
      "grad_norm": 0.44948479533195496,
      "learning_rate": 0.00019524712195140965,
      "loss": 0.7234854102134705,
      "step": 2428
    },
    {
      "epoch": 1.0253164556962024,
      "grad_norm": 0.39939233660697937,
      "learning_rate": 0.0001952324798863134,
      "loss": 0.7638729810714722,
      "step": 2430
    },
    {
      "epoch": 1.0261603375527426,
      "grad_norm": 0.40807482600212097,
      "learning_rate": 0.00019521781585291298,
      "loss": 0.6922630071640015,
      "step": 2432
    },
    {
      "epoch": 1.0270042194092828,
      "grad_norm": 0.45735791325569153,
      "learning_rate": 0.00019520312985459116,
      "loss": 0.762996256351471,
      "step": 2434
    },
    {
      "epoch": 1.0278481012658227,
      "grad_norm": 0.4280409812927246,
      "learning_rate": 0.0001951884218947357,
      "loss": 0.7811596989631653,
      "step": 2436
    },
    {
      "epoch": 1.0286919831223629,
      "grad_norm": 0.41957560181617737,
      "learning_rate": 0.00019517369197673943,
      "loss": 0.7278305292129517,
      "step": 2438
    },
    {
      "epoch": 1.029535864978903,
      "grad_norm": 0.4832586646080017,
      "learning_rate": 0.00019515894010400028,
      "loss": 0.807456910610199,
      "step": 2440
    },
    {
      "epoch": 1.030379746835443,
      "grad_norm": 0.46448788046836853,
      "learning_rate": 0.00019514416627992122,
      "loss": 0.7421302795410156,
      "step": 2442
    },
    {
      "epoch": 1.0312236286919831,
      "grad_norm": 0.41362619400024414,
      "learning_rate": 0.00019512937050791024,
      "loss": 0.6892213225364685,
      "step": 2444
    },
    {
      "epoch": 1.0320675105485233,
      "grad_norm": 0.4158109128475189,
      "learning_rate": 0.0001951145527913805,
      "loss": 0.7305331826210022,
      "step": 2446
    },
    {
      "epoch": 1.0329113924050632,
      "grad_norm": 0.4725087881088257,
      "learning_rate": 0.00019509971313375011,
      "loss": 0.7682753205299377,
      "step": 2448
    },
    {
      "epoch": 1.0337552742616034,
      "grad_norm": 0.4341438114643097,
      "learning_rate": 0.00019508485153844237,
      "loss": 0.747041642665863,
      "step": 2450
    },
    {
      "epoch": 1.0345991561181433,
      "grad_norm": 0.44515377283096313,
      "learning_rate": 0.00019506996800888548,
      "loss": 0.7312062382698059,
      "step": 2452
    },
    {
      "epoch": 1.0354430379746835,
      "grad_norm": 0.5313915014266968,
      "learning_rate": 0.00019505506254851283,
      "loss": 0.7861107587814331,
      "step": 2454
    },
    {
      "epoch": 1.0362869198312237,
      "grad_norm": 0.6094246506690979,
      "learning_rate": 0.00019504013516076285,
      "loss": 0.8458115458488464,
      "step": 2456
    },
    {
      "epoch": 1.0371308016877636,
      "grad_norm": 0.36419153213500977,
      "learning_rate": 0.00019502518584907895,
      "loss": 0.6091256141662598,
      "step": 2458
    },
    {
      "epoch": 1.0379746835443038,
      "grad_norm": 0.399271696805954,
      "learning_rate": 0.00019501021461690966,
      "loss": 0.6703370809555054,
      "step": 2460
    },
    {
      "epoch": 1.038818565400844,
      "grad_norm": 0.38560932874679565,
      "learning_rate": 0.00019499522146770856,
      "loss": 0.7220943570137024,
      "step": 2462
    },
    {
      "epoch": 1.0396624472573839,
      "grad_norm": 0.44199803471565247,
      "learning_rate": 0.00019498020640493428,
      "loss": 0.7501406073570251,
      "step": 2464
    },
    {
      "epoch": 1.040506329113924,
      "grad_norm": 0.47394421696662903,
      "learning_rate": 0.00019496516943205054,
      "loss": 0.7957925796508789,
      "step": 2466
    },
    {
      "epoch": 1.0413502109704642,
      "grad_norm": 0.5274425745010376,
      "learning_rate": 0.00019495011055252603,
      "loss": 0.7964824438095093,
      "step": 2468
    },
    {
      "epoch": 1.0421940928270041,
      "grad_norm": 0.44004881381988525,
      "learning_rate": 0.0001949350297698346,
      "loss": 0.7478582262992859,
      "step": 2470
    },
    {
      "epoch": 1.0430379746835443,
      "grad_norm": 0.40662670135498047,
      "learning_rate": 0.000194919927087455,
      "loss": 0.738339900970459,
      "step": 2472
    },
    {
      "epoch": 1.0438818565400845,
      "grad_norm": 0.43934181332588196,
      "learning_rate": 0.00019490480250887123,
      "loss": 0.817171037197113,
      "step": 2474
    },
    {
      "epoch": 1.0447257383966244,
      "grad_norm": 0.4111221432685852,
      "learning_rate": 0.00019488965603757223,
      "loss": 0.7413169145584106,
      "step": 2476
    },
    {
      "epoch": 1.0455696202531646,
      "grad_norm": 0.3770996630191803,
      "learning_rate": 0.00019487448767705194,
      "loss": 0.7893102169036865,
      "step": 2478
    },
    {
      "epoch": 1.0464135021097047,
      "grad_norm": 0.4524461627006531,
      "learning_rate": 0.00019485929743080945,
      "loss": 0.7037841081619263,
      "step": 2480
    },
    {
      "epoch": 1.0472573839662447,
      "grad_norm": 0.4232378900051117,
      "learning_rate": 0.00019484408530234885,
      "loss": 0.7456525564193726,
      "step": 2482
    },
    {
      "epoch": 1.0481012658227848,
      "grad_norm": 0.3842810392379761,
      "learning_rate": 0.00019482885129517929,
      "loss": 0.7263808250427246,
      "step": 2484
    },
    {
      "epoch": 1.048945147679325,
      "grad_norm": 0.43203726410865784,
      "learning_rate": 0.00019481359541281495,
      "loss": 0.7101474404335022,
      "step": 2486
    },
    {
      "epoch": 1.049789029535865,
      "grad_norm": 0.46944454312324524,
      "learning_rate": 0.00019479831765877509,
      "loss": 0.8561921715736389,
      "step": 2488
    },
    {
      "epoch": 1.0506329113924051,
      "grad_norm": 0.4455019533634186,
      "learning_rate": 0.00019478301803658397,
      "loss": 0.7206679582595825,
      "step": 2490
    },
    {
      "epoch": 1.051476793248945,
      "grad_norm": 0.4253813326358795,
      "learning_rate": 0.00019476769654977095,
      "loss": 0.7271745800971985,
      "step": 2492
    },
    {
      "epoch": 1.0523206751054852,
      "grad_norm": 0.42758429050445557,
      "learning_rate": 0.00019475235320187033,
      "loss": 0.7358576059341431,
      "step": 2494
    },
    {
      "epoch": 1.0531645569620254,
      "grad_norm": 0.400634765625,
      "learning_rate": 0.00019473698799642164,
      "loss": 0.6617647409439087,
      "step": 2496
    },
    {
      "epoch": 1.0540084388185653,
      "grad_norm": 0.4132104814052582,
      "learning_rate": 0.00019472160093696926,
      "loss": 0.6900970935821533,
      "step": 2498
    },
    {
      "epoch": 1.0548523206751055,
      "grad_norm": 0.5116495490074158,
      "learning_rate": 0.00019470619202706268,
      "loss": 0.7352861762046814,
      "step": 2500
    },
    {
      "epoch": 1.0548523206751055,
      "eval_loss": 0.8249453902244568,
      "eval_runtime": 679.4446,
      "eval_samples_per_second": 3.101,
      "eval_steps_per_second": 3.101,
      "step": 2500
    },
    {
      "epoch": 1.0556962025316456,
      "grad_norm": 0.42822444438934326,
      "learning_rate": 0.0001946907612702565,
      "loss": 0.7583479881286621,
      "step": 2502
    },
    {
      "epoch": 1.0565400843881856,
      "grad_norm": 0.4788980782032013,
      "learning_rate": 0.00019467530867011025,
      "loss": 0.777511477470398,
      "step": 2504
    },
    {
      "epoch": 1.0573839662447257,
      "grad_norm": 0.4210498034954071,
      "learning_rate": 0.00019465983423018856,
      "loss": 0.7452852129936218,
      "step": 2506
    },
    {
      "epoch": 1.058227848101266,
      "grad_norm": 0.43219906091690063,
      "learning_rate": 0.0001946443379540611,
      "loss": 0.7540958523750305,
      "step": 2508
    },
    {
      "epoch": 1.0590717299578059,
      "grad_norm": 0.4361002445220947,
      "learning_rate": 0.00019462881984530253,
      "loss": 0.7175624966621399,
      "step": 2510
    },
    {
      "epoch": 1.059915611814346,
      "grad_norm": 0.4575091600418091,
      "learning_rate": 0.00019461327990749264,
      "loss": 0.7342076301574707,
      "step": 2512
    },
    {
      "epoch": 1.0607594936708862,
      "grad_norm": 0.4823324978351593,
      "learning_rate": 0.00019459771814421615,
      "loss": 0.8255488872528076,
      "step": 2514
    },
    {
      "epoch": 1.0616033755274261,
      "grad_norm": 0.41693785786628723,
      "learning_rate": 0.00019458213455906284,
      "loss": 0.6624729633331299,
      "step": 2516
    },
    {
      "epoch": 1.0624472573839663,
      "grad_norm": 0.41319167613983154,
      "learning_rate": 0.00019456652915562762,
      "loss": 0.8224266767501831,
      "step": 2518
    },
    {
      "epoch": 1.0632911392405062,
      "grad_norm": 0.4405190050601959,
      "learning_rate": 0.00019455090193751023,
      "loss": 0.7582900524139404,
      "step": 2520
    },
    {
      "epoch": 1.0641350210970464,
      "grad_norm": 0.4564387798309326,
      "learning_rate": 0.0001945352529083157,
      "loss": 0.7948101162910461,
      "step": 2522
    },
    {
      "epoch": 1.0649789029535865,
      "grad_norm": 0.4247225224971771,
      "learning_rate": 0.00019451958207165394,
      "loss": 0.7670508027076721,
      "step": 2524
    },
    {
      "epoch": 1.0658227848101265,
      "grad_norm": 0.42070862650871277,
      "learning_rate": 0.00019450388943113983,
      "loss": 0.7753698229789734,
      "step": 2526
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.3729179799556732,
      "learning_rate": 0.00019448817499039342,
      "loss": 0.710904598236084,
      "step": 2528
    },
    {
      "epoch": 1.0675105485232068,
      "grad_norm": 0.40901753306388855,
      "learning_rate": 0.0001944724387530397,
      "loss": 0.7000213265419006,
      "step": 2530
    },
    {
      "epoch": 1.0683544303797468,
      "grad_norm": 0.4481421113014221,
      "learning_rate": 0.00019445668072270877,
      "loss": 0.7374410629272461,
      "step": 2532
    },
    {
      "epoch": 1.069198312236287,
      "grad_norm": 0.4839915335178375,
      "learning_rate": 0.00019444090090303567,
      "loss": 0.746309220790863,
      "step": 2534
    },
    {
      "epoch": 1.070042194092827,
      "grad_norm": 0.4982132613658905,
      "learning_rate": 0.00019442509929766048,
      "loss": 0.7448083162307739,
      "step": 2536
    },
    {
      "epoch": 1.070886075949367,
      "grad_norm": 0.3987475037574768,
      "learning_rate": 0.00019440927591022838,
      "loss": 0.7052555680274963,
      "step": 2538
    },
    {
      "epoch": 1.0717299578059072,
      "grad_norm": 0.4089896082878113,
      "learning_rate": 0.00019439343074438944,
      "loss": 0.7090281248092651,
      "step": 2540
    },
    {
      "epoch": 1.0725738396624473,
      "grad_norm": 0.3703136146068573,
      "learning_rate": 0.00019437756380379895,
      "loss": 0.7530601024627686,
      "step": 2542
    },
    {
      "epoch": 1.0734177215189873,
      "grad_norm": 0.4015701413154602,
      "learning_rate": 0.00019436167509211702,
      "loss": 0.7597941160202026,
      "step": 2544
    },
    {
      "epoch": 1.0742616033755275,
      "grad_norm": 0.3915148675441742,
      "learning_rate": 0.00019434576461300888,
      "loss": 0.7168124318122864,
      "step": 2546
    },
    {
      "epoch": 1.0751054852320676,
      "grad_norm": 0.44643113017082214,
      "learning_rate": 0.00019432983237014482,
      "loss": 0.7762725949287415,
      "step": 2548
    },
    {
      "epoch": 1.0759493670886076,
      "grad_norm": 0.46874719858169556,
      "learning_rate": 0.00019431387836720004,
      "loss": 0.7879725098609924,
      "step": 2550
    },
    {
      "epoch": 1.0767932489451477,
      "grad_norm": 0.4143001437187195,
      "learning_rate": 0.00019429790260785487,
      "loss": 0.7351391315460205,
      "step": 2552
    },
    {
      "epoch": 1.0776371308016879,
      "grad_norm": 0.4569888412952423,
      "learning_rate": 0.0001942819050957946,
      "loss": 0.86613929271698,
      "step": 2554
    },
    {
      "epoch": 1.0784810126582278,
      "grad_norm": 0.41729897260665894,
      "learning_rate": 0.00019426588583470954,
      "loss": 0.7122719287872314,
      "step": 2556
    },
    {
      "epoch": 1.079324894514768,
      "grad_norm": 0.42295604944229126,
      "learning_rate": 0.000194249844828295,
      "loss": 0.6605332493782043,
      "step": 2558
    },
    {
      "epoch": 1.080168776371308,
      "grad_norm": 0.45787641406059265,
      "learning_rate": 0.00019423378208025137,
      "loss": 0.7839207649230957,
      "step": 2560
    },
    {
      "epoch": 1.081012658227848,
      "grad_norm": 0.43370622396469116,
      "learning_rate": 0.00019421769759428404,
      "loss": 0.7557987570762634,
      "step": 2562
    },
    {
      "epoch": 1.0818565400843883,
      "grad_norm": 0.4371975362300873,
      "learning_rate": 0.00019420159137410335,
      "loss": 0.7349345088005066,
      "step": 2564
    },
    {
      "epoch": 1.0827004219409282,
      "grad_norm": 0.468730628490448,
      "learning_rate": 0.0001941854634234247,
      "loss": 0.7024962902069092,
      "step": 2566
    },
    {
      "epoch": 1.0835443037974684,
      "grad_norm": 0.4257284998893738,
      "learning_rate": 0.0001941693137459685,
      "loss": 0.6981064081192017,
      "step": 2568
    },
    {
      "epoch": 1.0843881856540085,
      "grad_norm": 0.4322902262210846,
      "learning_rate": 0.00019415314234546015,
      "loss": 0.7899637818336487,
      "step": 2570
    },
    {
      "epoch": 1.0852320675105485,
      "grad_norm": 0.44384217262268066,
      "learning_rate": 0.00019413694922563014,
      "loss": 0.7964152693748474,
      "step": 2572
    },
    {
      "epoch": 1.0860759493670886,
      "grad_norm": 0.47391360998153687,
      "learning_rate": 0.0001941207343902139,
      "loss": 0.7902941107749939,
      "step": 2574
    },
    {
      "epoch": 1.0869198312236288,
      "grad_norm": 0.4575883746147156,
      "learning_rate": 0.00019410449784295182,
      "loss": 0.7818595170974731,
      "step": 2576
    },
    {
      "epoch": 1.0877637130801687,
      "grad_norm": 0.41236087679862976,
      "learning_rate": 0.0001940882395875894,
      "loss": 0.7516021728515625,
      "step": 2578
    },
    {
      "epoch": 1.0886075949367089,
      "grad_norm": 0.3817494213581085,
      "learning_rate": 0.0001940719596278771,
      "loss": 0.6870401501655579,
      "step": 2580
    },
    {
      "epoch": 1.0894514767932488,
      "grad_norm": 0.4630168378353119,
      "learning_rate": 0.00019405565796757043,
      "loss": 0.7437341809272766,
      "step": 2582
    },
    {
      "epoch": 1.090295358649789,
      "grad_norm": 0.4063820540904999,
      "learning_rate": 0.00019403933461042982,
      "loss": 0.7101680040359497,
      "step": 2584
    },
    {
      "epoch": 1.0911392405063292,
      "grad_norm": 0.44423359632492065,
      "learning_rate": 0.0001940229895602208,
      "loss": 0.6894780397415161,
      "step": 2586
    },
    {
      "epoch": 1.091983122362869,
      "grad_norm": 0.4267353117465973,
      "learning_rate": 0.0001940066228207138,
      "loss": 0.7277120351791382,
      "step": 2588
    },
    {
      "epoch": 1.0928270042194093,
      "grad_norm": 0.44747647643089294,
      "learning_rate": 0.00019399023439568434,
      "loss": 0.6512353420257568,
      "step": 2590
    },
    {
      "epoch": 1.0936708860759494,
      "grad_norm": 0.4557100832462311,
      "learning_rate": 0.00019397382428891296,
      "loss": 0.7850068807601929,
      "step": 2592
    },
    {
      "epoch": 1.0945147679324894,
      "grad_norm": 0.44980114698410034,
      "learning_rate": 0.0001939573925041851,
      "loss": 0.786868691444397,
      "step": 2594
    },
    {
      "epoch": 1.0953586497890295,
      "grad_norm": 0.45374399423599243,
      "learning_rate": 0.00019394093904529126,
      "loss": 0.8260899186134338,
      "step": 2596
    },
    {
      "epoch": 1.0962025316455697,
      "grad_norm": 0.40681353211402893,
      "learning_rate": 0.00019392446391602695,
      "loss": 0.7056689262390137,
      "step": 2598
    },
    {
      "epoch": 1.0970464135021096,
      "grad_norm": 0.39278075098991394,
      "learning_rate": 0.0001939079671201927,
      "loss": 0.7557252645492554,
      "step": 2600
    },
    {
      "epoch": 1.0970464135021096,
      "eval_loss": 0.8211485743522644,
      "eval_runtime": 670.2276,
      "eval_samples_per_second": 3.144,
      "eval_steps_per_second": 3.144,
      "step": 2600
    },
    {
      "epoch": 1.0978902953586498,
      "grad_norm": 0.4261230230331421,
      "learning_rate": 0.00019389144866159398,
      "loss": 0.7139819264411926,
      "step": 2602
    },
    {
      "epoch": 1.09873417721519,
      "grad_norm": 0.4664439558982849,
      "learning_rate": 0.0001938749085440412,
      "loss": 0.7274705767631531,
      "step": 2604
    },
    {
      "epoch": 1.09957805907173,
      "grad_norm": 0.46306154131889343,
      "learning_rate": 0.00019385834677134998,
      "loss": 0.7547051906585693,
      "step": 2606
    },
    {
      "epoch": 1.10042194092827,
      "grad_norm": 0.39753687381744385,
      "learning_rate": 0.00019384176334734073,
      "loss": 0.6942694187164307,
      "step": 2608
    },
    {
      "epoch": 1.1012658227848102,
      "grad_norm": 0.4556522071361542,
      "learning_rate": 0.00019382515827583898,
      "loss": 0.7161701321601868,
      "step": 2610
    },
    {
      "epoch": 1.1021097046413502,
      "grad_norm": 0.3863290250301361,
      "learning_rate": 0.0001938085315606751,
      "loss": 0.7165710926055908,
      "step": 2612
    },
    {
      "epoch": 1.1029535864978903,
      "grad_norm": 0.49601292610168457,
      "learning_rate": 0.00019379188320568466,
      "loss": 0.8080679774284363,
      "step": 2614
    },
    {
      "epoch": 1.1037974683544305,
      "grad_norm": 0.4498465955257416,
      "learning_rate": 0.00019377521321470805,
      "loss": 0.7032502889633179,
      "step": 2616
    },
    {
      "epoch": 1.1046413502109704,
      "grad_norm": 0.4537963569164276,
      "learning_rate": 0.00019375852159159073,
      "loss": 0.7076731324195862,
      "step": 2618
    },
    {
      "epoch": 1.1054852320675106,
      "grad_norm": 0.4042968153953552,
      "learning_rate": 0.0001937418083401832,
      "loss": 0.7020825743675232,
      "step": 2620
    },
    {
      "epoch": 1.1063291139240505,
      "grad_norm": 0.44306516647338867,
      "learning_rate": 0.00019372507346434076,
      "loss": 0.7222874760627747,
      "step": 2622
    },
    {
      "epoch": 1.1071729957805907,
      "grad_norm": 0.3792516887187958,
      "learning_rate": 0.00019370831696792392,
      "loss": 0.6136211156845093,
      "step": 2624
    },
    {
      "epoch": 1.1080168776371309,
      "grad_norm": 0.46655353903770447,
      "learning_rate": 0.00019369153885479806,
      "loss": 0.7358977198600769,
      "step": 2626
    },
    {
      "epoch": 1.1088607594936708,
      "grad_norm": 0.4416999816894531,
      "learning_rate": 0.0001936747391288336,
      "loss": 0.7484551072120667,
      "step": 2628
    },
    {
      "epoch": 1.109704641350211,
      "grad_norm": 0.4620150327682495,
      "learning_rate": 0.00019365791779390584,
      "loss": 0.6874802708625793,
      "step": 2630
    },
    {
      "epoch": 1.1105485232067511,
      "grad_norm": 0.4357883334159851,
      "learning_rate": 0.00019364107485389518,
      "loss": 0.7168865203857422,
      "step": 2632
    },
    {
      "epoch": 1.111392405063291,
      "grad_norm": 0.4581143856048584,
      "learning_rate": 0.00019362421031268699,
      "loss": 0.7533737421035767,
      "step": 2634
    },
    {
      "epoch": 1.1122362869198312,
      "grad_norm": 0.46408653259277344,
      "learning_rate": 0.00019360732417417152,
      "loss": 0.8245398998260498,
      "step": 2636
    },
    {
      "epoch": 1.1130801687763714,
      "grad_norm": 0.4639282524585724,
      "learning_rate": 0.00019359041644224415,
      "loss": 0.7095663547515869,
      "step": 2638
    },
    {
      "epoch": 1.1139240506329113,
      "grad_norm": 0.4598273038864136,
      "learning_rate": 0.00019357348712080517,
      "loss": 0.7030285596847534,
      "step": 2640
    },
    {
      "epoch": 1.1147679324894515,
      "grad_norm": 0.42993804812431335,
      "learning_rate": 0.00019355653621375978,
      "loss": 0.7158969640731812,
      "step": 2642
    },
    {
      "epoch": 1.1156118143459917,
      "grad_norm": 0.36132168769836426,
      "learning_rate": 0.0001935395637250183,
      "loss": 0.6800820231437683,
      "step": 2644
    },
    {
      "epoch": 1.1164556962025316,
      "grad_norm": 0.5004428029060364,
      "learning_rate": 0.00019352256965849592,
      "loss": 0.694972813129425,
      "step": 2646
    },
    {
      "epoch": 1.1172995780590718,
      "grad_norm": 0.43715354800224304,
      "learning_rate": 0.00019350555401811286,
      "loss": 0.7164262533187866,
      "step": 2648
    },
    {
      "epoch": 1.1181434599156117,
      "grad_norm": 0.42316755652427673,
      "learning_rate": 0.00019348851680779433,
      "loss": 0.7026737928390503,
      "step": 2650
    },
    {
      "epoch": 1.1189873417721519,
      "grad_norm": 0.35848063230514526,
      "learning_rate": 0.0001934714580314704,
      "loss": 0.6774232387542725,
      "step": 2652
    },
    {
      "epoch": 1.119831223628692,
      "grad_norm": 0.46613892912864685,
      "learning_rate": 0.00019345437769307627,
      "loss": 0.7789244055747986,
      "step": 2654
    },
    {
      "epoch": 1.120675105485232,
      "grad_norm": 0.4298146367073059,
      "learning_rate": 0.00019343727579655204,
      "loss": 0.8647177815437317,
      "step": 2656
    },
    {
      "epoch": 1.1215189873417721,
      "grad_norm": 0.4638161361217499,
      "learning_rate": 0.00019342015234584276,
      "loss": 0.6949124336242676,
      "step": 2658
    },
    {
      "epoch": 1.1223628691983123,
      "grad_norm": 0.4079605042934418,
      "learning_rate": 0.00019340300734489854,
      "loss": 0.6677125096321106,
      "step": 2660
    },
    {
      "epoch": 1.1232067510548522,
      "grad_norm": 0.46079063415527344,
      "learning_rate": 0.00019338584079767434,
      "loss": 0.7521067261695862,
      "step": 2662
    },
    {
      "epoch": 1.1240506329113924,
      "grad_norm": 0.3935202956199646,
      "learning_rate": 0.0001933686527081302,
      "loss": 0.6829184889793396,
      "step": 2664
    },
    {
      "epoch": 1.1248945147679326,
      "grad_norm": 0.45696479082107544,
      "learning_rate": 0.000193351443080231,
      "loss": 0.7122842669487,
      "step": 2666
    },
    {
      "epoch": 1.1257383966244725,
      "grad_norm": 0.4078282415866852,
      "learning_rate": 0.0001933342119179468,
      "loss": 0.7316977977752686,
      "step": 2668
    },
    {
      "epoch": 1.1265822784810127,
      "grad_norm": 0.4282447099685669,
      "learning_rate": 0.0001933169592252524,
      "loss": 0.7323395013809204,
      "step": 2670
    },
    {
      "epoch": 1.1274261603375528,
      "grad_norm": 0.46398648619651794,
      "learning_rate": 0.00019329968500612766,
      "loss": 0.7177348732948303,
      "step": 2672
    },
    {
      "epoch": 1.1282700421940928,
      "grad_norm": 0.4560202658176422,
      "learning_rate": 0.0001932823892645575,
      "loss": 0.7957183122634888,
      "step": 2674
    },
    {
      "epoch": 1.129113924050633,
      "grad_norm": 0.4790743887424469,
      "learning_rate": 0.00019326507200453162,
      "loss": 0.762060284614563,
      "step": 2676
    },
    {
      "epoch": 1.129957805907173,
      "grad_norm": 0.46524202823638916,
      "learning_rate": 0.00019324773323004484,
      "loss": 0.7227895259857178,
      "step": 2678
    },
    {
      "epoch": 1.130801687763713,
      "grad_norm": 0.47912222146987915,
      "learning_rate": 0.00019323037294509683,
      "loss": 0.6968042254447937,
      "step": 2680
    },
    {
      "epoch": 1.1316455696202532,
      "grad_norm": 0.4412849247455597,
      "learning_rate": 0.00019321299115369233,
      "loss": 0.6682016253471375,
      "step": 2682
    },
    {
      "epoch": 1.1324894514767934,
      "grad_norm": 0.4138370752334595,
      "learning_rate": 0.00019319558785984095,
      "loss": 0.7287812829017639,
      "step": 2684
    },
    {
      "epoch": 1.1333333333333333,
      "grad_norm": 0.391170859336853,
      "learning_rate": 0.00019317816306755733,
      "loss": 0.6547526121139526,
      "step": 2686
    },
    {
      "epoch": 1.1341772151898735,
      "grad_norm": 0.45472806692123413,
      "learning_rate": 0.00019316071678086098,
      "loss": 0.6942042708396912,
      "step": 2688
    },
    {
      "epoch": 1.1350210970464134,
      "grad_norm": 0.40321481227874756,
      "learning_rate": 0.00019314324900377648,
      "loss": 0.7417841553688049,
      "step": 2690
    },
    {
      "epoch": 1.1358649789029536,
      "grad_norm": 0.3806784152984619,
      "learning_rate": 0.00019312575974033327,
      "loss": 0.7780525088310242,
      "step": 2692
    },
    {
      "epoch": 1.1367088607594937,
      "grad_norm": 0.43763765692710876,
      "learning_rate": 0.0001931082489945658,
      "loss": 0.661472499370575,
      "step": 2694
    },
    {
      "epoch": 1.1375527426160337,
      "grad_norm": 0.45410826802253723,
      "learning_rate": 0.00019309071677051348,
      "loss": 0.7443127632141113,
      "step": 2696
    },
    {
      "epoch": 1.1383966244725738,
      "grad_norm": 0.47907447814941406,
      "learning_rate": 0.00019307316307222062,
      "loss": 0.744393527507782,
      "step": 2698
    },
    {
      "epoch": 1.139240506329114,
      "grad_norm": 0.41723814606666565,
      "learning_rate": 0.00019305558790373654,
      "loss": 0.7042794227600098,
      "step": 2700
    },
    {
      "epoch": 1.139240506329114,
      "eval_loss": 0.8155058026313782,
      "eval_runtime": 678.284,
      "eval_samples_per_second": 3.106,
      "eval_steps_per_second": 3.106,
      "step": 2700
    },
    {
      "epoch": 1.140084388185654,
      "grad_norm": 0.3863268196582794,
      "learning_rate": 0.0001930379912691155,
      "loss": 0.6715745329856873,
      "step": 2702
    },
    {
      "epoch": 1.140928270042194,
      "grad_norm": 0.49994897842407227,
      "learning_rate": 0.00019302037317241673,
      "loss": 0.6959030628204346,
      "step": 2704
    },
    {
      "epoch": 1.1417721518987343,
      "grad_norm": 0.46377572417259216,
      "learning_rate": 0.00019300273361770432,
      "loss": 0.6534222364425659,
      "step": 2706
    },
    {
      "epoch": 1.1426160337552742,
      "grad_norm": 0.3841579556465149,
      "learning_rate": 0.00019298507260904745,
      "loss": 0.6750475764274597,
      "step": 2708
    },
    {
      "epoch": 1.1434599156118144,
      "grad_norm": 0.4171544313430786,
      "learning_rate": 0.00019296739015052015,
      "loss": 0.7714900374412537,
      "step": 2710
    },
    {
      "epoch": 1.1443037974683543,
      "grad_norm": 0.44384199380874634,
      "learning_rate": 0.00019294968624620137,
      "loss": 0.7281306982040405,
      "step": 2712
    },
    {
      "epoch": 1.1451476793248945,
      "grad_norm": 0.43345192074775696,
      "learning_rate": 0.00019293196090017513,
      "loss": 0.7407262325286865,
      "step": 2714
    },
    {
      "epoch": 1.1459915611814346,
      "grad_norm": 0.3897020220756531,
      "learning_rate": 0.00019291421411653034,
      "loss": 0.6794347167015076,
      "step": 2716
    },
    {
      "epoch": 1.1468354430379746,
      "grad_norm": 0.4289143681526184,
      "learning_rate": 0.00019289644589936075,
      "loss": 0.7026289105415344,
      "step": 2718
    },
    {
      "epoch": 1.1476793248945147,
      "grad_norm": 0.4783557057380676,
      "learning_rate": 0.0001928786562527652,
      "loss": 0.7613762617111206,
      "step": 2720
    },
    {
      "epoch": 1.148523206751055,
      "grad_norm": 0.4152112901210785,
      "learning_rate": 0.00019286084518084745,
      "loss": 0.7123059630393982,
      "step": 2722
    },
    {
      "epoch": 1.1493670886075948,
      "grad_norm": 0.4204908013343811,
      "learning_rate": 0.0001928430126877161,
      "loss": 0.7198041677474976,
      "step": 2724
    },
    {
      "epoch": 1.150210970464135,
      "grad_norm": 0.41333863139152527,
      "learning_rate": 0.00019282515877748485,
      "loss": 0.6859839558601379,
      "step": 2726
    },
    {
      "epoch": 1.1510548523206752,
      "grad_norm": 0.4041498005390167,
      "learning_rate": 0.00019280728345427218,
      "loss": 0.7185758948326111,
      "step": 2728
    },
    {
      "epoch": 1.1518987341772151,
      "grad_norm": 0.4487358629703522,
      "learning_rate": 0.00019278938672220167,
      "loss": 0.7899971008300781,
      "step": 2730
    },
    {
      "epoch": 1.1527426160337553,
      "grad_norm": 0.3510114252567291,
      "learning_rate": 0.00019277146858540166,
      "loss": 0.6266586780548096,
      "step": 2732
    },
    {
      "epoch": 1.1535864978902954,
      "grad_norm": 0.4295555055141449,
      "learning_rate": 0.00019275352904800553,
      "loss": 0.7450110912322998,
      "step": 2734
    },
    {
      "epoch": 1.1544303797468354,
      "grad_norm": 0.40629687905311584,
      "learning_rate": 0.00019273556811415165,
      "loss": 0.6875549554824829,
      "step": 2736
    },
    {
      "epoch": 1.1552742616033755,
      "grad_norm": 0.4243362247943878,
      "learning_rate": 0.00019271758578798322,
      "loss": 0.8141522407531738,
      "step": 2738
    },
    {
      "epoch": 1.1561181434599157,
      "grad_norm": 0.483306884765625,
      "learning_rate": 0.00019269958207364843,
      "loss": 0.6905186176300049,
      "step": 2740
    },
    {
      "epoch": 1.1569620253164556,
      "grad_norm": 0.4303925335407257,
      "learning_rate": 0.00019268155697530037,
      "loss": 0.6709047555923462,
      "step": 2742
    },
    {
      "epoch": 1.1578059071729958,
      "grad_norm": 0.4533381760120392,
      "learning_rate": 0.0001926635104970971,
      "loss": 0.7107465863227844,
      "step": 2744
    },
    {
      "epoch": 1.158649789029536,
      "grad_norm": 0.4823286533355713,
      "learning_rate": 0.0001926454426432016,
      "loss": 0.8043986558914185,
      "step": 2746
    },
    {
      "epoch": 1.159493670886076,
      "grad_norm": 0.3892867863178253,
      "learning_rate": 0.00019262735341778179,
      "loss": 0.7812165021896362,
      "step": 2748
    },
    {
      "epoch": 1.160337552742616,
      "grad_norm": 0.46737003326416016,
      "learning_rate": 0.00019260924282501045,
      "loss": 0.7141886353492737,
      "step": 2750
    },
    {
      "epoch": 1.1611814345991562,
      "grad_norm": 0.4335328936576843,
      "learning_rate": 0.0001925911108690654,
      "loss": 0.7528460621833801,
      "step": 2752
    },
    {
      "epoch": 1.1620253164556962,
      "grad_norm": 0.3792484700679779,
      "learning_rate": 0.00019257295755412932,
      "loss": 0.7817611694335938,
      "step": 2754
    },
    {
      "epoch": 1.1628691983122363,
      "grad_norm": 0.41246429085731506,
      "learning_rate": 0.00019255478288438983,
      "loss": 0.6904958486557007,
      "step": 2756
    },
    {
      "epoch": 1.1637130801687763,
      "grad_norm": 0.44368481636047363,
      "learning_rate": 0.00019253658686403948,
      "loss": 0.7571630477905273,
      "step": 2758
    },
    {
      "epoch": 1.1645569620253164,
      "grad_norm": 0.40121781826019287,
      "learning_rate": 0.00019251836949727574,
      "loss": 0.6747061014175415,
      "step": 2760
    },
    {
      "epoch": 1.1654008438818566,
      "grad_norm": 0.4660188853740692,
      "learning_rate": 0.000192500130788301,
      "loss": 0.7722339034080505,
      "step": 2762
    },
    {
      "epoch": 1.1662447257383965,
      "grad_norm": 0.41693782806396484,
      "learning_rate": 0.0001924818707413226,
      "loss": 0.8081457018852234,
      "step": 2764
    },
    {
      "epoch": 1.1670886075949367,
      "grad_norm": 0.4274570345878601,
      "learning_rate": 0.00019246358936055274,
      "loss": 0.7745853066444397,
      "step": 2766
    },
    {
      "epoch": 1.1679324894514769,
      "grad_norm": 0.4385969638824463,
      "learning_rate": 0.00019244528665020863,
      "loss": 0.7918146252632141,
      "step": 2768
    },
    {
      "epoch": 1.1687763713080168,
      "grad_norm": 0.42832866311073303,
      "learning_rate": 0.00019242696261451234,
      "loss": 0.7382830381393433,
      "step": 2770
    },
    {
      "epoch": 1.169620253164557,
      "grad_norm": 0.44177982211112976,
      "learning_rate": 0.00019240861725769085,
      "loss": 0.7501721978187561,
      "step": 2772
    },
    {
      "epoch": 1.1704641350210971,
      "grad_norm": 0.4193457365036011,
      "learning_rate": 0.00019239025058397611,
      "loss": 0.6495388150215149,
      "step": 2774
    },
    {
      "epoch": 1.171308016877637,
      "grad_norm": 0.5145925283432007,
      "learning_rate": 0.000192371862597605,
      "loss": 0.8291991353034973,
      "step": 2776
    },
    {
      "epoch": 1.1721518987341772,
      "grad_norm": 0.40911251306533813,
      "learning_rate": 0.00019235345330281914,
      "loss": 0.7491340637207031,
      "step": 2778
    },
    {
      "epoch": 1.1729957805907172,
      "grad_norm": 0.3920276165008545,
      "learning_rate": 0.0001923350227038653,
      "loss": 0.6315004825592041,
      "step": 2780
    },
    {
      "epoch": 1.1738396624472573,
      "grad_norm": 0.442303329706192,
      "learning_rate": 0.0001923165708049951,
      "loss": 0.7538990378379822,
      "step": 2782
    },
    {
      "epoch": 1.1746835443037975,
      "grad_norm": 0.4693523049354553,
      "learning_rate": 0.00019229809761046497,
      "loss": 0.7440794110298157,
      "step": 2784
    },
    {
      "epoch": 1.1755274261603375,
      "grad_norm": 0.4948059618473053,
      "learning_rate": 0.0001922796031245363,
      "loss": 0.7342568635940552,
      "step": 2786
    },
    {
      "epoch": 1.1763713080168776,
      "grad_norm": 0.3900465965270996,
      "learning_rate": 0.00019226108735147547,
      "loss": 0.6969661116600037,
      "step": 2788
    },
    {
      "epoch": 1.1772151898734178,
      "grad_norm": 0.36153602600097656,
      "learning_rate": 0.00019224255029555372,
      "loss": 0.7097541689872742,
      "step": 2790
    },
    {
      "epoch": 1.1780590717299577,
      "grad_norm": 0.41168832778930664,
      "learning_rate": 0.00019222399196104715,
      "loss": 0.8141831755638123,
      "step": 2792
    },
    {
      "epoch": 1.1789029535864979,
      "grad_norm": 0.4542821943759918,
      "learning_rate": 0.0001922054123522368,
      "loss": 0.7458863258361816,
      "step": 2794
    },
    {
      "epoch": 1.179746835443038,
      "grad_norm": 0.4026047885417938,
      "learning_rate": 0.0001921868114734087,
      "loss": 0.6535642147064209,
      "step": 2796
    },
    {
      "epoch": 1.180590717299578,
      "grad_norm": 0.4417034387588501,
      "learning_rate": 0.0001921681893288537,
      "loss": 0.6248135566711426,
      "step": 2798
    },
    {
      "epoch": 1.1814345991561181,
      "grad_norm": 0.45027074217796326,
      "learning_rate": 0.00019214954592286748,
      "loss": 0.6777785420417786,
      "step": 2800
    },
    {
      "epoch": 1.1814345991561181,
      "eval_loss": 0.8124309182167053,
      "eval_runtime": 688.4759,
      "eval_samples_per_second": 3.06,
      "eval_steps_per_second": 3.06,
      "step": 2800
    },
    {
      "epoch": 1.1822784810126583,
      "grad_norm": 0.406865656375885,
      "learning_rate": 0.00019213088125975082,
      "loss": 0.6460301876068115,
      "step": 2802
    },
    {
      "epoch": 1.1831223628691983,
      "grad_norm": 0.5052749514579773,
      "learning_rate": 0.00019211219534380928,
      "loss": 0.7292830944061279,
      "step": 2804
    },
    {
      "epoch": 1.1839662447257384,
      "grad_norm": 0.4028380513191223,
      "learning_rate": 0.00019209348817935328,
      "loss": 0.7399409413337708,
      "step": 2806
    },
    {
      "epoch": 1.1848101265822786,
      "grad_norm": 0.4522664248943329,
      "learning_rate": 0.00019207475977069826,
      "loss": 0.6885398030281067,
      "step": 2808
    },
    {
      "epoch": 1.1856540084388185,
      "grad_norm": 0.419546514749527,
      "learning_rate": 0.0001920560101221645,
      "loss": 0.6962382197380066,
      "step": 2810
    },
    {
      "epoch": 1.1864978902953587,
      "grad_norm": 0.48912352323532104,
      "learning_rate": 0.00019203723923807715,
      "loss": 0.7380965352058411,
      "step": 2812
    },
    {
      "epoch": 1.1873417721518988,
      "grad_norm": 0.40905487537384033,
      "learning_rate": 0.00019201844712276635,
      "loss": 0.755382776260376,
      "step": 2814
    },
    {
      "epoch": 1.1881856540084388,
      "grad_norm": 0.385623037815094,
      "learning_rate": 0.000191999633780567,
      "loss": 0.7066168189048767,
      "step": 2816
    },
    {
      "epoch": 1.189029535864979,
      "grad_norm": 0.4488723576068878,
      "learning_rate": 0.00019198079921581908,
      "loss": 0.7172947525978088,
      "step": 2818
    },
    {
      "epoch": 1.189873417721519,
      "grad_norm": 0.385277658700943,
      "learning_rate": 0.00019196194343286727,
      "loss": 0.6714195013046265,
      "step": 2820
    },
    {
      "epoch": 1.190717299578059,
      "grad_norm": 0.4280855655670166,
      "learning_rate": 0.00019194306643606127,
      "loss": 0.7076966166496277,
      "step": 2822
    },
    {
      "epoch": 1.1915611814345992,
      "grad_norm": 0.4626067578792572,
      "learning_rate": 0.00019192416822975567,
      "loss": 0.7926747798919678,
      "step": 2824
    },
    {
      "epoch": 1.1924050632911392,
      "grad_norm": 0.3994208574295044,
      "learning_rate": 0.00019190524881830987,
      "loss": 0.7654290199279785,
      "step": 2826
    },
    {
      "epoch": 1.1932489451476793,
      "grad_norm": 0.47346508502960205,
      "learning_rate": 0.00019188630820608825,
      "loss": 0.7857998609542847,
      "step": 2828
    },
    {
      "epoch": 1.1940928270042195,
      "grad_norm": 0.446077823638916,
      "learning_rate": 0.00019186734639746003,
      "loss": 0.7603738903999329,
      "step": 2830
    },
    {
      "epoch": 1.1949367088607594,
      "grad_norm": 0.41503727436065674,
      "learning_rate": 0.00019184836339679936,
      "loss": 0.790582537651062,
      "step": 2832
    },
    {
      "epoch": 1.1957805907172996,
      "grad_norm": 0.43651700019836426,
      "learning_rate": 0.00019182935920848522,
      "loss": 0.7229864597320557,
      "step": 2834
    },
    {
      "epoch": 1.1966244725738397,
      "grad_norm": 0.4409031867980957,
      "learning_rate": 0.00019181033383690153,
      "loss": 0.7817287445068359,
      "step": 2836
    },
    {
      "epoch": 1.1974683544303797,
      "grad_norm": 0.3562015891075134,
      "learning_rate": 0.0001917912872864371,
      "loss": 0.6342297792434692,
      "step": 2838
    },
    {
      "epoch": 1.1983122362869199,
      "grad_norm": 0.4767192602157593,
      "learning_rate": 0.00019177221956148555,
      "loss": 0.7065272927284241,
      "step": 2840
    },
    {
      "epoch": 1.1991561181434598,
      "grad_norm": 0.45131945610046387,
      "learning_rate": 0.00019175313066644546,
      "loss": 0.777110755443573,
      "step": 2842
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.47566652297973633,
      "learning_rate": 0.00019173402060572027,
      "loss": 0.7456457018852234,
      "step": 2844
    },
    {
      "epoch": 1.2008438818565401,
      "grad_norm": 0.48909857869148254,
      "learning_rate": 0.00019171488938371834,
      "loss": 0.8041547536849976,
      "step": 2846
    },
    {
      "epoch": 1.20168776371308,
      "grad_norm": 0.436591774225235,
      "learning_rate": 0.00019169573700485284,
      "loss": 0.6786676049232483,
      "step": 2848
    },
    {
      "epoch": 1.2025316455696202,
      "grad_norm": 0.44230160117149353,
      "learning_rate": 0.00019167656347354183,
      "loss": 0.7661880850791931,
      "step": 2850
    },
    {
      "epoch": 1.2033755274261604,
      "grad_norm": 0.4844048321247101,
      "learning_rate": 0.00019165736879420836,
      "loss": 0.7369645833969116,
      "step": 2852
    },
    {
      "epoch": 1.2042194092827003,
      "grad_norm": 0.4272955060005188,
      "learning_rate": 0.0001916381529712802,
      "loss": 0.7776681184768677,
      "step": 2854
    },
    {
      "epoch": 1.2050632911392405,
      "grad_norm": 0.42392730712890625,
      "learning_rate": 0.00019161891600919008,
      "loss": 0.8019667267799377,
      "step": 2856
    },
    {
      "epoch": 1.2059071729957807,
      "grad_norm": 0.4528326988220215,
      "learning_rate": 0.00019159965791237565,
      "loss": 0.7811952233314514,
      "step": 2858
    },
    {
      "epoch": 1.2067510548523206,
      "grad_norm": 0.42840948700904846,
      "learning_rate": 0.00019158037868527932,
      "loss": 0.7244279980659485,
      "step": 2860
    },
    {
      "epoch": 1.2075949367088608,
      "grad_norm": 0.4291226863861084,
      "learning_rate": 0.00019156107833234845,
      "loss": 0.7675760984420776,
      "step": 2862
    },
    {
      "epoch": 1.208438818565401,
      "grad_norm": 0.4455093443393707,
      "learning_rate": 0.00019154175685803527,
      "loss": 0.7071483135223389,
      "step": 2864
    },
    {
      "epoch": 1.2092827004219409,
      "grad_norm": 0.41356268525123596,
      "learning_rate": 0.00019152241426679688,
      "loss": 0.7554603815078735,
      "step": 2866
    },
    {
      "epoch": 1.210126582278481,
      "grad_norm": 0.43875646591186523,
      "learning_rate": 0.00019150305056309525,
      "loss": 0.7198356986045837,
      "step": 2868
    },
    {
      "epoch": 1.2109704641350212,
      "grad_norm": 0.454356849193573,
      "learning_rate": 0.0001914836657513972,
      "loss": 0.7393195629119873,
      "step": 2870
    },
    {
      "epoch": 1.2118143459915611,
      "grad_norm": 0.37668535113334656,
      "learning_rate": 0.00019146425983617444,
      "loss": 0.7277671694755554,
      "step": 2872
    },
    {
      "epoch": 1.2126582278481013,
      "grad_norm": 0.37869662046432495,
      "learning_rate": 0.00019144483282190354,
      "loss": 0.6783158183097839,
      "step": 2874
    },
    {
      "epoch": 1.2135021097046415,
      "grad_norm": 0.4333525002002716,
      "learning_rate": 0.00019142538471306596,
      "loss": 0.7024772763252258,
      "step": 2876
    },
    {
      "epoch": 1.2143459915611814,
      "grad_norm": 0.4693842828273773,
      "learning_rate": 0.00019140591551414796,
      "loss": 0.7387984395027161,
      "step": 2878
    },
    {
      "epoch": 1.2151898734177216,
      "grad_norm": 0.432640939950943,
      "learning_rate": 0.00019138642522964074,
      "loss": 0.7597174644470215,
      "step": 2880
    },
    {
      "epoch": 1.2160337552742617,
      "grad_norm": 0.432477205991745,
      "learning_rate": 0.00019136691386404032,
      "loss": 0.7884587049484253,
      "step": 2882
    },
    {
      "epoch": 1.2168776371308017,
      "grad_norm": 0.39305904507637024,
      "learning_rate": 0.00019134738142184763,
      "loss": 0.6873269081115723,
      "step": 2884
    },
    {
      "epoch": 1.2177215189873418,
      "grad_norm": 0.4485352635383606,
      "learning_rate": 0.00019132782790756838,
      "loss": 0.6523491144180298,
      "step": 2886
    },
    {
      "epoch": 1.2185654008438818,
      "grad_norm": 0.4480868875980377,
      "learning_rate": 0.00019130825332571322,
      "loss": 0.7383941411972046,
      "step": 2888
    },
    {
      "epoch": 1.219409282700422,
      "grad_norm": 0.44085049629211426,
      "learning_rate": 0.00019128865768079764,
      "loss": 0.7391335964202881,
      "step": 2890
    },
    {
      "epoch": 1.220253164556962,
      "grad_norm": 0.4621105492115021,
      "learning_rate": 0.00019126904097734198,
      "loss": 0.7282017469406128,
      "step": 2892
    },
    {
      "epoch": 1.221097046413502,
      "grad_norm": 0.41478198766708374,
      "learning_rate": 0.00019124940321987136,
      "loss": 0.7554038763046265,
      "step": 2894
    },
    {
      "epoch": 1.2219409282700422,
      "grad_norm": 0.4143751263618469,
      "learning_rate": 0.00019122974441291595,
      "loss": 0.6826799511909485,
      "step": 2896
    },
    {
      "epoch": 1.2227848101265824,
      "grad_norm": 0.45392894744873047,
      "learning_rate": 0.00019121006456101057,
      "loss": 0.751000702381134,
      "step": 2898
    },
    {
      "epoch": 1.2236286919831223,
      "grad_norm": 0.46946296095848083,
      "learning_rate": 0.00019119036366869506,
      "loss": 0.7598516941070557,
      "step": 2900
    },
    {
      "epoch": 1.2236286919831223,
      "eval_loss": 0.8077136278152466,
      "eval_runtime": 685.6042,
      "eval_samples_per_second": 3.073,
      "eval_steps_per_second": 3.073,
      "step": 2900
    },
    {
      "epoch": 1.2244725738396625,
      "grad_norm": 0.4316656291484833,
      "learning_rate": 0.00019117064174051395,
      "loss": 0.7518358826637268,
      "step": 2902
    },
    {
      "epoch": 1.2253164556962026,
      "grad_norm": 0.47737377882003784,
      "learning_rate": 0.0001911508987810168,
      "loss": 0.7308215498924255,
      "step": 2904
    },
    {
      "epoch": 1.2261603375527426,
      "grad_norm": 0.40906062722206116,
      "learning_rate": 0.00019113113479475783,
      "loss": 0.6996226906776428,
      "step": 2906
    },
    {
      "epoch": 1.2270042194092827,
      "grad_norm": 0.517085075378418,
      "learning_rate": 0.00019111134978629633,
      "loss": 0.8364415168762207,
      "step": 2908
    },
    {
      "epoch": 1.2278481012658227,
      "grad_norm": 0.425581693649292,
      "learning_rate": 0.00019109154376019624,
      "loss": 0.722011923789978,
      "step": 2910
    },
    {
      "epoch": 1.2286919831223628,
      "grad_norm": 0.4651593565940857,
      "learning_rate": 0.00019107171672102643,
      "loss": 0.7586172223091125,
      "step": 2912
    },
    {
      "epoch": 1.229535864978903,
      "grad_norm": 0.4578891396522522,
      "learning_rate": 0.00019105186867336067,
      "loss": 0.7387955188751221,
      "step": 2914
    },
    {
      "epoch": 1.230379746835443,
      "grad_norm": 0.4312961995601654,
      "learning_rate": 0.00019103199962177748,
      "loss": 0.8036285638809204,
      "step": 2916
    },
    {
      "epoch": 1.231223628691983,
      "grad_norm": 0.4355425536632538,
      "learning_rate": 0.00019101210957086026,
      "loss": 0.7356550097465515,
      "step": 2918
    },
    {
      "epoch": 1.2320675105485233,
      "grad_norm": 0.424675852060318,
      "learning_rate": 0.00019099219852519733,
      "loss": 0.6730139255523682,
      "step": 2920
    },
    {
      "epoch": 1.2329113924050632,
      "grad_norm": 0.41102367639541626,
      "learning_rate": 0.0001909722664893817,
      "loss": 0.6983892321586609,
      "step": 2922
    },
    {
      "epoch": 1.2337552742616034,
      "grad_norm": 0.4088250398635864,
      "learning_rate": 0.00019095231346801132,
      "loss": 0.6297144889831543,
      "step": 2924
    },
    {
      "epoch": 1.2345991561181435,
      "grad_norm": 0.3685890734195709,
      "learning_rate": 0.00019093233946568906,
      "loss": 0.7035690546035767,
      "step": 2926
    },
    {
      "epoch": 1.2354430379746835,
      "grad_norm": 0.39438629150390625,
      "learning_rate": 0.0001909123444870224,
      "loss": 0.820853054523468,
      "step": 2928
    },
    {
      "epoch": 1.2362869198312236,
      "grad_norm": 0.5041676163673401,
      "learning_rate": 0.00019089232853662392,
      "loss": 0.7884082794189453,
      "step": 2930
    },
    {
      "epoch": 1.2371308016877638,
      "grad_norm": 0.40592801570892334,
      "learning_rate": 0.00019087229161911086,
      "loss": 0.773978590965271,
      "step": 2932
    },
    {
      "epoch": 1.2379746835443037,
      "grad_norm": 0.41828030347824097,
      "learning_rate": 0.00019085223373910536,
      "loss": 0.6742141842842102,
      "step": 2934
    },
    {
      "epoch": 1.238818565400844,
      "grad_norm": 0.39984026551246643,
      "learning_rate": 0.0001908321549012344,
      "loss": 0.7106125950813293,
      "step": 2936
    },
    {
      "epoch": 1.239662447257384,
      "grad_norm": 0.4841296970844269,
      "learning_rate": 0.00019081205511012973,
      "loss": 0.7390915751457214,
      "step": 2938
    },
    {
      "epoch": 1.240506329113924,
      "grad_norm": 0.39837637543678284,
      "learning_rate": 0.00019079193437042806,
      "loss": 0.6527198553085327,
      "step": 2940
    },
    {
      "epoch": 1.2413502109704642,
      "grad_norm": 0.40916863083839417,
      "learning_rate": 0.0001907717926867708,
      "loss": 0.6939712762832642,
      "step": 2942
    },
    {
      "epoch": 1.2421940928270043,
      "grad_norm": 0.4329306483268738,
      "learning_rate": 0.0001907516300638043,
      "loss": 0.7566131353378296,
      "step": 2944
    },
    {
      "epoch": 1.2430379746835443,
      "grad_norm": 0.47983601689338684,
      "learning_rate": 0.00019073144650617963,
      "loss": 0.7893748879432678,
      "step": 2946
    },
    {
      "epoch": 1.2438818565400844,
      "grad_norm": 0.4368246793746948,
      "learning_rate": 0.0001907112420185528,
      "loss": 0.8259525299072266,
      "step": 2948
    },
    {
      "epoch": 1.2447257383966246,
      "grad_norm": 0.41272372007369995,
      "learning_rate": 0.0001906910166055846,
      "loss": 0.734692394733429,
      "step": 2950
    },
    {
      "epoch": 1.2455696202531645,
      "grad_norm": 0.36929839849472046,
      "learning_rate": 0.00019067077027194057,
      "loss": 0.7091750502586365,
      "step": 2952
    },
    {
      "epoch": 1.2464135021097047,
      "grad_norm": 0.4395252466201782,
      "learning_rate": 0.00019065050302229125,
      "loss": 0.6960210204124451,
      "step": 2954
    },
    {
      "epoch": 1.2472573839662446,
      "grad_norm": 0.46784868836402893,
      "learning_rate": 0.00019063021486131186,
      "loss": 0.7817115187644958,
      "step": 2956
    },
    {
      "epoch": 1.2481012658227848,
      "grad_norm": 0.4191588759422302,
      "learning_rate": 0.00019060990579368244,
      "loss": 0.7933676242828369,
      "step": 2958
    },
    {
      "epoch": 1.248945147679325,
      "grad_norm": 0.3967524468898773,
      "learning_rate": 0.000190589575824088,
      "loss": 0.6856688857078552,
      "step": 2960
    },
    {
      "epoch": 1.249789029535865,
      "grad_norm": 0.40346091985702515,
      "learning_rate": 0.0001905692249572182,
      "loss": 0.6783818602561951,
      "step": 2962
    },
    {
      "epoch": 1.250632911392405,
      "grad_norm": 0.38349980115890503,
      "learning_rate": 0.0001905488531977676,
      "loss": 0.6997019052505493,
      "step": 2964
    },
    {
      "epoch": 1.2514767932489452,
      "grad_norm": 0.44021397829055786,
      "learning_rate": 0.0001905284605504356,
      "loss": 0.6978800892829895,
      "step": 2966
    },
    {
      "epoch": 1.2523206751054852,
      "grad_norm": 0.47491583228111267,
      "learning_rate": 0.0001905080470199264,
      "loss": 0.7007693648338318,
      "step": 2968
    },
    {
      "epoch": 1.2531645569620253,
      "grad_norm": 0.4011451005935669,
      "learning_rate": 0.00019048761261094898,
      "loss": 0.7258896231651306,
      "step": 2970
    },
    {
      "epoch": 1.2540084388185653,
      "grad_norm": 0.44206640124320984,
      "learning_rate": 0.0001904671573282172,
      "loss": 0.6746299266815186,
      "step": 2972
    },
    {
      "epoch": 1.2548523206751054,
      "grad_norm": 0.4532456696033478,
      "learning_rate": 0.00019044668117644965,
      "loss": 0.7638527154922485,
      "step": 2974
    },
    {
      "epoch": 1.2556962025316456,
      "grad_norm": 0.44301095604896545,
      "learning_rate": 0.00019042618416036984,
      "loss": 0.659598171710968,
      "step": 2976
    },
    {
      "epoch": 1.2565400843881855,
      "grad_norm": 0.37427952885627747,
      "learning_rate": 0.00019040566628470597,
      "loss": 0.7132709622383118,
      "step": 2978
    },
    {
      "epoch": 1.2573839662447257,
      "grad_norm": 0.4195408821105957,
      "learning_rate": 0.0001903851275541912,
      "loss": 0.8163022398948669,
      "step": 2980
    },
    {
      "epoch": 1.2582278481012659,
      "grad_norm": 0.3951880633831024,
      "learning_rate": 0.00019036456797356336,
      "loss": 0.7481505870819092,
      "step": 2982
    },
    {
      "epoch": 1.2590717299578058,
      "grad_norm": 0.4239100217819214,
      "learning_rate": 0.00019034398754756522,
      "loss": 0.750126838684082,
      "step": 2984
    },
    {
      "epoch": 1.259915611814346,
      "grad_norm": 0.4209354817867279,
      "learning_rate": 0.0001903233862809442,
      "loss": 0.746433436870575,
      "step": 2986
    },
    {
      "epoch": 1.2607594936708861,
      "grad_norm": 0.4188138544559479,
      "learning_rate": 0.00019030276417845266,
      "loss": 0.7104454040527344,
      "step": 2988
    },
    {
      "epoch": 1.261603375527426,
      "grad_norm": 0.4531371593475342,
      "learning_rate": 0.00019028212124484772,
      "loss": 0.650738000869751,
      "step": 2990
    },
    {
      "epoch": 1.2624472573839662,
      "grad_norm": 0.4672204256057739,
      "learning_rate": 0.00019026145748489133,
      "loss": 0.6870551109313965,
      "step": 2992
    },
    {
      "epoch": 1.2632911392405064,
      "grad_norm": 0.40681278705596924,
      "learning_rate": 0.00019024077290335018,
      "loss": 0.6879403591156006,
      "step": 2994
    },
    {
      "epoch": 1.2641350210970463,
      "grad_norm": 0.4491691291332245,
      "learning_rate": 0.00019022006750499585,
      "loss": 0.6886372566223145,
      "step": 2996
    },
    {
      "epoch": 1.2649789029535865,
      "grad_norm": 0.4144807457923889,
      "learning_rate": 0.0001901993412946046,
      "loss": 0.7199324369430542,
      "step": 2998
    },
    {
      "epoch": 1.2658227848101267,
      "grad_norm": 0.40370482206344604,
      "learning_rate": 0.0001901785942769577,
      "loss": 0.7105490565299988,
      "step": 3000
    },
    {
      "epoch": 1.2658227848101267,
      "eval_loss": 0.8033165335655212,
      "eval_runtime": 678.7554,
      "eval_samples_per_second": 3.104,
      "eval_steps_per_second": 3.104,
      "step": 3000
    },
    {
      "epoch": 1.2666666666666666,
      "grad_norm": 0.42637890577316284,
      "learning_rate": 0.00019015782645684097,
      "loss": 0.7385403513908386,
      "step": 3002
    },
    {
      "epoch": 1.2675105485232068,
      "grad_norm": 0.3709809482097626,
      "learning_rate": 0.00019013703783904518,
      "loss": 0.6395129561424255,
      "step": 3004
    },
    {
      "epoch": 1.268354430379747,
      "grad_norm": 0.4642501175403595,
      "learning_rate": 0.00019011622842836592,
      "loss": 0.7123657464981079,
      "step": 3006
    },
    {
      "epoch": 1.2691983122362869,
      "grad_norm": 0.4553911089897156,
      "learning_rate": 0.00019009539822960342,
      "loss": 0.744048535823822,
      "step": 3008
    },
    {
      "epoch": 1.270042194092827,
      "grad_norm": 0.39334386587142944,
      "learning_rate": 0.0001900745472475629,
      "loss": 0.7181914448738098,
      "step": 3010
    },
    {
      "epoch": 1.2708860759493672,
      "grad_norm": 0.40902766585350037,
      "learning_rate": 0.00019005367548705426,
      "loss": 0.7238107919692993,
      "step": 3012
    },
    {
      "epoch": 1.2717299578059071,
      "grad_norm": 0.48296019434928894,
      "learning_rate": 0.00019003278295289216,
      "loss": 0.7479744553565979,
      "step": 3014
    },
    {
      "epoch": 1.2725738396624473,
      "grad_norm": 0.4807029962539673,
      "learning_rate": 0.00019001186964989617,
      "loss": 0.829924464225769,
      "step": 3016
    },
    {
      "epoch": 1.2734177215189875,
      "grad_norm": 0.4239083528518677,
      "learning_rate": 0.00018999093558289055,
      "loss": 0.7204707264900208,
      "step": 3018
    },
    {
      "epoch": 1.2742616033755274,
      "grad_norm": 0.4687928259372711,
      "learning_rate": 0.0001899699807567044,
      "loss": 0.7668164968490601,
      "step": 3020
    },
    {
      "epoch": 1.2751054852320676,
      "grad_norm": 0.41724732518196106,
      "learning_rate": 0.0001899490051761716,
      "loss": 0.766342043876648,
      "step": 3022
    },
    {
      "epoch": 1.2759493670886077,
      "grad_norm": 0.4131613075733185,
      "learning_rate": 0.00018992800884613082,
      "loss": 0.6595507860183716,
      "step": 3024
    },
    {
      "epoch": 1.2767932489451477,
      "grad_norm": 0.4156053364276886,
      "learning_rate": 0.00018990699177142548,
      "loss": 0.7419850826263428,
      "step": 3026
    },
    {
      "epoch": 1.2776371308016878,
      "grad_norm": 0.41845977306365967,
      "learning_rate": 0.00018988595395690388,
      "loss": 0.67264324426651,
      "step": 3028
    },
    {
      "epoch": 1.2784810126582278,
      "grad_norm": 0.3826757073402405,
      "learning_rate": 0.00018986489540741893,
      "loss": 0.6269281506538391,
      "step": 3030
    },
    {
      "epoch": 1.279324894514768,
      "grad_norm": 0.4531428813934326,
      "learning_rate": 0.00018984381612782854,
      "loss": 0.71211177110672,
      "step": 3032
    },
    {
      "epoch": 1.2801687763713079,
      "grad_norm": 0.3747255802154541,
      "learning_rate": 0.00018982271612299524,
      "loss": 0.635804295539856,
      "step": 3034
    },
    {
      "epoch": 1.281012658227848,
      "grad_norm": 0.4079552888870239,
      "learning_rate": 0.00018980159539778638,
      "loss": 0.7269464731216431,
      "step": 3036
    },
    {
      "epoch": 1.2818565400843882,
      "grad_norm": 0.4193854033946991,
      "learning_rate": 0.00018978045395707418,
      "loss": 0.7737077474594116,
      "step": 3038
    },
    {
      "epoch": 1.2827004219409281,
      "grad_norm": 0.4182516038417816,
      "learning_rate": 0.0001897592918057355,
      "loss": 0.7458174824714661,
      "step": 3040
    },
    {
      "epoch": 1.2835443037974683,
      "grad_norm": 0.43343567848205566,
      "learning_rate": 0.00018973810894865205,
      "loss": 0.6565808057785034,
      "step": 3042
    },
    {
      "epoch": 1.2843881856540085,
      "grad_norm": 0.4294503331184387,
      "learning_rate": 0.00018971690539071033,
      "loss": 0.736944317817688,
      "step": 3044
    },
    {
      "epoch": 1.2852320675105484,
      "grad_norm": 0.41330763697624207,
      "learning_rate": 0.0001896956811368016,
      "loss": 0.6921742558479309,
      "step": 3046
    },
    {
      "epoch": 1.2860759493670886,
      "grad_norm": 0.44992703199386597,
      "learning_rate": 0.0001896744361918218,
      "loss": 0.7004357576370239,
      "step": 3048
    },
    {
      "epoch": 1.2869198312236287,
      "grad_norm": 0.43748870491981506,
      "learning_rate": 0.0001896531705606719,
      "loss": 0.6767720580101013,
      "step": 3050
    },
    {
      "epoch": 1.2877637130801687,
      "grad_norm": 0.47581973671913147,
      "learning_rate": 0.0001896318842482573,
      "loss": 0.7596892714500427,
      "step": 3052
    },
    {
      "epoch": 1.2886075949367088,
      "grad_norm": 0.45806005597114563,
      "learning_rate": 0.00018961057725948844,
      "loss": 0.7650044560432434,
      "step": 3054
    },
    {
      "epoch": 1.289451476793249,
      "grad_norm": 0.4291481375694275,
      "learning_rate": 0.00018958924959928042,
      "loss": 0.6654610633850098,
      "step": 3056
    },
    {
      "epoch": 1.290295358649789,
      "grad_norm": 0.42454418540000916,
      "learning_rate": 0.00018956790127255309,
      "loss": 0.7079797387123108,
      "step": 3058
    },
    {
      "epoch": 1.2911392405063291,
      "grad_norm": 0.46820637583732605,
      "learning_rate": 0.00018954653228423114,
      "loss": 0.7724313735961914,
      "step": 3060
    },
    {
      "epoch": 1.2919831223628693,
      "grad_norm": 0.4440016746520996,
      "learning_rate": 0.00018952514263924396,
      "loss": 0.7746338248252869,
      "step": 3062
    },
    {
      "epoch": 1.2928270042194092,
      "grad_norm": 0.4296419620513916,
      "learning_rate": 0.00018950373234252572,
      "loss": 0.7570929527282715,
      "step": 3064
    },
    {
      "epoch": 1.2936708860759494,
      "grad_norm": 0.428780734539032,
      "learning_rate": 0.0001894823013990154,
      "loss": 0.7274802923202515,
      "step": 3066
    },
    {
      "epoch": 1.2945147679324895,
      "grad_norm": 0.4111585021018982,
      "learning_rate": 0.0001894608498136567,
      "loss": 0.6595024466514587,
      "step": 3068
    },
    {
      "epoch": 1.2953586497890295,
      "grad_norm": 0.4373013973236084,
      "learning_rate": 0.00018943937759139802,
      "loss": 0.7316440939903259,
      "step": 3070
    },
    {
      "epoch": 1.2962025316455696,
      "grad_norm": 0.37705400586128235,
      "learning_rate": 0.0001894178847371927,
      "loss": 0.7072293162345886,
      "step": 3072
    },
    {
      "epoch": 1.2970464135021098,
      "grad_norm": 0.4171125888824463,
      "learning_rate": 0.00018939637125599864,
      "loss": 0.7218101024627686,
      "step": 3074
    },
    {
      "epoch": 1.2978902953586497,
      "grad_norm": 0.4264235198497772,
      "learning_rate": 0.00018937483715277865,
      "loss": 0.725140392780304,
      "step": 3076
    },
    {
      "epoch": 1.29873417721519,
      "grad_norm": 0.4251643121242523,
      "learning_rate": 0.0001893532824325002,
      "loss": 0.7423256635665894,
      "step": 3078
    },
    {
      "epoch": 1.29957805907173,
      "grad_norm": 0.43096452951431274,
      "learning_rate": 0.00018933170710013554,
      "loss": 0.7058811187744141,
      "step": 3080
    },
    {
      "epoch": 1.30042194092827,
      "grad_norm": 0.466804176568985,
      "learning_rate": 0.00018931011116066172,
      "loss": 0.7334373593330383,
      "step": 3082
    },
    {
      "epoch": 1.3012658227848102,
      "grad_norm": 0.36896654963493347,
      "learning_rate": 0.00018928849461906047,
      "loss": 0.6033462285995483,
      "step": 3084
    },
    {
      "epoch": 1.3021097046413503,
      "grad_norm": 0.42875027656555176,
      "learning_rate": 0.00018926685748031833,
      "loss": 0.690375566482544,
      "step": 3086
    },
    {
      "epoch": 1.3029535864978903,
      "grad_norm": 0.4041171967983246,
      "learning_rate": 0.00018924519974942658,
      "loss": 0.7468435168266296,
      "step": 3088
    },
    {
      "epoch": 1.3037974683544304,
      "grad_norm": 0.4704097807407379,
      "learning_rate": 0.00018922352143138126,
      "loss": 0.7574344873428345,
      "step": 3090
    },
    {
      "epoch": 1.3046413502109704,
      "grad_norm": 0.4391418397426605,
      "learning_rate": 0.0001892018225311831,
      "loss": 0.756452739238739,
      "step": 3092
    },
    {
      "epoch": 1.3054852320675105,
      "grad_norm": 0.42684388160705566,
      "learning_rate": 0.0001891801030538376,
      "loss": 0.6620991230010986,
      "step": 3094
    },
    {
      "epoch": 1.3063291139240507,
      "grad_norm": 0.4972277283668518,
      "learning_rate": 0.00018915836300435507,
      "loss": 0.7764125466346741,
      "step": 3096
    },
    {
      "epoch": 1.3071729957805907,
      "grad_norm": 0.3905445337295532,
      "learning_rate": 0.00018913660238775053,
      "loss": 0.6557663083076477,
      "step": 3098
    },
    {
      "epoch": 1.3080168776371308,
      "grad_norm": 0.4553062319755554,
      "learning_rate": 0.0001891148212090437,
      "loss": 0.6746718883514404,
      "step": 3100
    },
    {
      "epoch": 1.3080168776371308,
      "eval_loss": 0.8010181784629822,
      "eval_runtime": 668.1688,
      "eval_samples_per_second": 3.153,
      "eval_steps_per_second": 3.153,
      "step": 3100
    },
    {
      "epoch": 1.3088607594936708,
      "grad_norm": 0.4254429340362549,
      "learning_rate": 0.00018909301947325915,
      "loss": 0.7916419506072998,
      "step": 3102
    },
    {
      "epoch": 1.309704641350211,
      "grad_norm": 0.6118508577346802,
      "learning_rate": 0.00018907119718542602,
      "loss": 0.883936882019043,
      "step": 3104
    },
    {
      "epoch": 1.310548523206751,
      "grad_norm": 0.43206971883773804,
      "learning_rate": 0.00018904935435057837,
      "loss": 0.7145928740501404,
      "step": 3106
    },
    {
      "epoch": 1.311392405063291,
      "grad_norm": 0.39657703042030334,
      "learning_rate": 0.0001890274909737549,
      "loss": 0.7442842125892639,
      "step": 3108
    },
    {
      "epoch": 1.3122362869198312,
      "grad_norm": 0.4087927043437958,
      "learning_rate": 0.00018900560705999904,
      "loss": 0.6815276145935059,
      "step": 3110
    },
    {
      "epoch": 1.3130801687763713,
      "grad_norm": 0.430259108543396,
      "learning_rate": 0.00018898370261435904,
      "loss": 0.8153640627861023,
      "step": 3112
    },
    {
      "epoch": 1.3139240506329113,
      "grad_norm": 0.47486868500709534,
      "learning_rate": 0.0001889617776418878,
      "loss": 0.7828266024589539,
      "step": 3114
    },
    {
      "epoch": 1.3147679324894515,
      "grad_norm": 0.4929087162017822,
      "learning_rate": 0.000188939832147643,
      "loss": 0.7849065661430359,
      "step": 3116
    },
    {
      "epoch": 1.3156118143459916,
      "grad_norm": 0.39038679003715515,
      "learning_rate": 0.00018891786613668704,
      "loss": 0.7262985706329346,
      "step": 3118
    },
    {
      "epoch": 1.3164556962025316,
      "grad_norm": 0.4827214479446411,
      "learning_rate": 0.0001888958796140871,
      "loss": 0.8121856451034546,
      "step": 3120
    },
    {
      "epoch": 1.3172995780590717,
      "grad_norm": 0.47739601135253906,
      "learning_rate": 0.000188873872584915,
      "loss": 0.7165566086769104,
      "step": 3122
    },
    {
      "epoch": 1.3181434599156119,
      "grad_norm": 0.4274037778377533,
      "learning_rate": 0.0001888518450542473,
      "loss": 0.6698412299156189,
      "step": 3124
    },
    {
      "epoch": 1.3189873417721518,
      "grad_norm": 0.44825276732444763,
      "learning_rate": 0.00018882979702716544,
      "loss": 0.7271128296852112,
      "step": 3126
    },
    {
      "epoch": 1.319831223628692,
      "grad_norm": 0.42956918478012085,
      "learning_rate": 0.00018880772850875537,
      "loss": 0.7924301624298096,
      "step": 3128
    },
    {
      "epoch": 1.3206751054852321,
      "grad_norm": 0.4848136305809021,
      "learning_rate": 0.00018878563950410792,
      "loss": 0.7846497893333435,
      "step": 3130
    },
    {
      "epoch": 1.321518987341772,
      "grad_norm": 0.46651726961135864,
      "learning_rate": 0.00018876353001831864,
      "loss": 0.7262214422225952,
      "step": 3132
    },
    {
      "epoch": 1.3223628691983123,
      "grad_norm": 0.44598284363746643,
      "learning_rate": 0.0001887414000564877,
      "loss": 0.7640091180801392,
      "step": 3134
    },
    {
      "epoch": 1.3232067510548524,
      "grad_norm": 0.43744903802871704,
      "learning_rate": 0.00018871924962372006,
      "loss": 0.6960080862045288,
      "step": 3136
    },
    {
      "epoch": 1.3240506329113924,
      "grad_norm": 0.4737822413444519,
      "learning_rate": 0.00018869707872512544,
      "loss": 0.7121244072914124,
      "step": 3138
    },
    {
      "epoch": 1.3248945147679325,
      "grad_norm": 0.44452038407325745,
      "learning_rate": 0.00018867488736581817,
      "loss": 0.713148295879364,
      "step": 3140
    },
    {
      "epoch": 1.3257383966244727,
      "grad_norm": 0.47142693400382996,
      "learning_rate": 0.0001886526755509175,
      "loss": 0.6904974579811096,
      "step": 3142
    },
    {
      "epoch": 1.3265822784810126,
      "grad_norm": 0.40572887659072876,
      "learning_rate": 0.00018863044328554712,
      "loss": 0.7319386005401611,
      "step": 3144
    },
    {
      "epoch": 1.3274261603375528,
      "grad_norm": 0.44173532724380493,
      "learning_rate": 0.00018860819057483566,
      "loss": 0.7268120646476746,
      "step": 3146
    },
    {
      "epoch": 1.328270042194093,
      "grad_norm": 0.43025046586990356,
      "learning_rate": 0.00018858591742391642,
      "loss": 0.7129524946212769,
      "step": 3148
    },
    {
      "epoch": 1.3291139240506329,
      "grad_norm": 0.41418036818504333,
      "learning_rate": 0.00018856362383792732,
      "loss": 0.6917402148246765,
      "step": 3150
    },
    {
      "epoch": 1.329957805907173,
      "grad_norm": 0.46275854110717773,
      "learning_rate": 0.00018854130982201111,
      "loss": 0.7653918862342834,
      "step": 3152
    },
    {
      "epoch": 1.3308016877637132,
      "grad_norm": 0.38927653431892395,
      "learning_rate": 0.0001885189753813152,
      "loss": 0.7311477065086365,
      "step": 3154
    },
    {
      "epoch": 1.3316455696202532,
      "grad_norm": 0.44294974207878113,
      "learning_rate": 0.0001884966205209917,
      "loss": 0.7978816628456116,
      "step": 3156
    },
    {
      "epoch": 1.3324894514767933,
      "grad_norm": 0.3772844970226288,
      "learning_rate": 0.00018847424524619745,
      "loss": 0.7497738599777222,
      "step": 3158
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.4538787603378296,
      "learning_rate": 0.000188451849562094,
      "loss": 0.712806761264801,
      "step": 3160
    },
    {
      "epoch": 1.3341772151898734,
      "grad_norm": 0.4194336533546448,
      "learning_rate": 0.00018842943347384763,
      "loss": 0.7282580137252808,
      "step": 3162
    },
    {
      "epoch": 1.3350210970464136,
      "grad_norm": 0.4186438024044037,
      "learning_rate": 0.00018840699698662925,
      "loss": 0.797752320766449,
      "step": 3164
    },
    {
      "epoch": 1.3358649789029535,
      "grad_norm": 0.47711506485939026,
      "learning_rate": 0.00018838454010561457,
      "loss": 0.8175379633903503,
      "step": 3166
    },
    {
      "epoch": 1.3367088607594937,
      "grad_norm": 0.4380176067352295,
      "learning_rate": 0.00018836206283598394,
      "loss": 0.659176766872406,
      "step": 3168
    },
    {
      "epoch": 1.3375527426160336,
      "grad_norm": 0.4505249559879303,
      "learning_rate": 0.00018833956518292245,
      "loss": 0.732314944267273,
      "step": 3170
    },
    {
      "epoch": 1.3383966244725738,
      "grad_norm": 0.3832913935184479,
      "learning_rate": 0.00018831704715161984,
      "loss": 0.6791377067565918,
      "step": 3172
    },
    {
      "epoch": 1.339240506329114,
      "grad_norm": 0.42996498942375183,
      "learning_rate": 0.00018829450874727064,
      "loss": 0.7395796775817871,
      "step": 3174
    },
    {
      "epoch": 1.340084388185654,
      "grad_norm": 0.3926190435886383,
      "learning_rate": 0.000188271949975074,
      "loss": 0.6893631219863892,
      "step": 3176
    },
    {
      "epoch": 1.340928270042194,
      "grad_norm": 0.4353938102722168,
      "learning_rate": 0.0001882493708402338,
      "loss": 0.6708382964134216,
      "step": 3178
    },
    {
      "epoch": 1.3417721518987342,
      "grad_norm": 0.43043214082717896,
      "learning_rate": 0.0001882267713479586,
      "loss": 0.8447695374488831,
      "step": 3180
    },
    {
      "epoch": 1.3426160337552742,
      "grad_norm": 0.40693536400794983,
      "learning_rate": 0.00018820415150346163,
      "loss": 0.7081091403961182,
      "step": 3182
    },
    {
      "epoch": 1.3434599156118143,
      "grad_norm": 0.45037057995796204,
      "learning_rate": 0.00018818151131196097,
      "loss": 0.6822336316108704,
      "step": 3184
    },
    {
      "epoch": 1.3443037974683545,
      "grad_norm": 0.3731948137283325,
      "learning_rate": 0.00018815885077867915,
      "loss": 0.6316909790039062,
      "step": 3186
    },
    {
      "epoch": 1.3451476793248944,
      "grad_norm": 0.4248095750808716,
      "learning_rate": 0.00018813616990884363,
      "loss": 0.7452375292778015,
      "step": 3188
    },
    {
      "epoch": 1.3459915611814346,
      "grad_norm": 0.39229142665863037,
      "learning_rate": 0.00018811346870768638,
      "loss": 0.6493782997131348,
      "step": 3190
    },
    {
      "epoch": 1.3468354430379748,
      "grad_norm": 0.45015549659729004,
      "learning_rate": 0.00018809074718044414,
      "loss": 0.735163688659668,
      "step": 3192
    },
    {
      "epoch": 1.3476793248945147,
      "grad_norm": 0.39756354689598083,
      "learning_rate": 0.00018806800533235836,
      "loss": 0.6656006574630737,
      "step": 3194
    },
    {
      "epoch": 1.3485232067510549,
      "grad_norm": 0.4410010576248169,
      "learning_rate": 0.0001880452431686751,
      "loss": 0.7040987014770508,
      "step": 3196
    },
    {
      "epoch": 1.349367088607595,
      "grad_norm": 0.48144352436065674,
      "learning_rate": 0.0001880224606946452,
      "loss": 0.7722331285476685,
      "step": 3198
    },
    {
      "epoch": 1.350210970464135,
      "grad_norm": 0.38644957542419434,
      "learning_rate": 0.00018799965791552414,
      "loss": 0.6681689023971558,
      "step": 3200
    },
    {
      "epoch": 1.350210970464135,
      "eval_loss": 0.797160804271698,
      "eval_runtime": 680.976,
      "eval_samples_per_second": 3.094,
      "eval_steps_per_second": 3.094,
      "step": 3200
    },
    {
      "epoch": 1.3510548523206751,
      "grad_norm": 0.4471014440059662,
      "learning_rate": 0.00018797683483657201,
      "loss": 0.6995527744293213,
      "step": 3202
    },
    {
      "epoch": 1.3518987341772153,
      "grad_norm": 0.4065002202987671,
      "learning_rate": 0.00018795399146305378,
      "loss": 0.659622848033905,
      "step": 3204
    },
    {
      "epoch": 1.3527426160337552,
      "grad_norm": 0.4787910580635071,
      "learning_rate": 0.00018793112780023888,
      "loss": 0.7927116751670837,
      "step": 3206
    },
    {
      "epoch": 1.3535864978902954,
      "grad_norm": 0.43351876735687256,
      "learning_rate": 0.0001879082438534015,
      "loss": 0.6738835573196411,
      "step": 3208
    },
    {
      "epoch": 1.3544303797468356,
      "grad_norm": 0.4275745749473572,
      "learning_rate": 0.00018788533962782063,
      "loss": 0.7785354852676392,
      "step": 3210
    },
    {
      "epoch": 1.3552742616033755,
      "grad_norm": 0.4506145119667053,
      "learning_rate": 0.00018786241512877975,
      "loss": 0.7325424551963806,
      "step": 3212
    },
    {
      "epoch": 1.3561181434599157,
      "grad_norm": 0.42040735483169556,
      "learning_rate": 0.00018783947036156713,
      "loss": 0.6898744702339172,
      "step": 3214
    },
    {
      "epoch": 1.3569620253164558,
      "grad_norm": 0.4650438129901886,
      "learning_rate": 0.0001878165053314757,
      "loss": 0.7498815655708313,
      "step": 3216
    },
    {
      "epoch": 1.3578059071729958,
      "grad_norm": 0.4194130599498749,
      "learning_rate": 0.000187793520043803,
      "loss": 0.6891883611679077,
      "step": 3218
    },
    {
      "epoch": 1.358649789029536,
      "grad_norm": 0.4447539746761322,
      "learning_rate": 0.0001877705145038514,
      "loss": 0.753805935382843,
      "step": 3220
    },
    {
      "epoch": 1.3594936708860759,
      "grad_norm": 0.4047110974788666,
      "learning_rate": 0.00018774748871692773,
      "loss": 0.6476293802261353,
      "step": 3222
    },
    {
      "epoch": 1.360337552742616,
      "grad_norm": 0.39818957448005676,
      "learning_rate": 0.00018772444268834364,
      "loss": 0.6765931844711304,
      "step": 3224
    },
    {
      "epoch": 1.3611814345991562,
      "grad_norm": 0.41843733191490173,
      "learning_rate": 0.0001877013764234154,
      "loss": 0.7360382676124573,
      "step": 3226
    },
    {
      "epoch": 1.3620253164556961,
      "grad_norm": 0.41397789120674133,
      "learning_rate": 0.00018767828992746394,
      "loss": 0.7149524688720703,
      "step": 3228
    },
    {
      "epoch": 1.3628691983122363,
      "grad_norm": 0.43585047125816345,
      "learning_rate": 0.00018765518320581492,
      "loss": 0.6932925581932068,
      "step": 3230
    },
    {
      "epoch": 1.3637130801687762,
      "grad_norm": 0.3651057481765747,
      "learning_rate": 0.00018763205626379857,
      "loss": 0.6561182141304016,
      "step": 3232
    },
    {
      "epoch": 1.3645569620253164,
      "grad_norm": 0.44937077164649963,
      "learning_rate": 0.00018760890910674984,
      "loss": 0.7436831593513489,
      "step": 3234
    },
    {
      "epoch": 1.3654008438818566,
      "grad_norm": 0.5045920014381409,
      "learning_rate": 0.00018758574174000832,
      "loss": 0.7849522233009338,
      "step": 3236
    },
    {
      "epoch": 1.3662447257383965,
      "grad_norm": 0.4625580906867981,
      "learning_rate": 0.00018756255416891833,
      "loss": 0.7501618266105652,
      "step": 3238
    },
    {
      "epoch": 1.3670886075949367,
      "grad_norm": 0.3721269369125366,
      "learning_rate": 0.00018753934639882875,
      "loss": 0.7656083106994629,
      "step": 3240
    },
    {
      "epoch": 1.3679324894514768,
      "grad_norm": 0.41721680760383606,
      "learning_rate": 0.00018751611843509318,
      "loss": 0.7816168069839478,
      "step": 3242
    },
    {
      "epoch": 1.3687763713080168,
      "grad_norm": 0.8452199101448059,
      "learning_rate": 0.00018749287028306988,
      "loss": 0.7002755403518677,
      "step": 3244
    },
    {
      "epoch": 1.369620253164557,
      "grad_norm": 0.4320507347583771,
      "learning_rate": 0.00018746960194812172,
      "loss": 0.7358270883560181,
      "step": 3246
    },
    {
      "epoch": 1.370464135021097,
      "grad_norm": 0.43323323130607605,
      "learning_rate": 0.00018744631343561627,
      "loss": 0.6528644561767578,
      "step": 3248
    },
    {
      "epoch": 1.371308016877637,
      "grad_norm": 0.41487041115760803,
      "learning_rate": 0.0001874230047509258,
      "loss": 0.7317517995834351,
      "step": 3250
    },
    {
      "epoch": 1.3721518987341772,
      "grad_norm": 0.5085384249687195,
      "learning_rate": 0.00018739967589942707,
      "loss": 0.8236643671989441,
      "step": 3252
    },
    {
      "epoch": 1.3729957805907174,
      "grad_norm": 0.4126952290534973,
      "learning_rate": 0.00018737632688650168,
      "loss": 0.730254054069519,
      "step": 3254
    },
    {
      "epoch": 1.3738396624472573,
      "grad_norm": 0.5272142291069031,
      "learning_rate": 0.00018735295771753573,
      "loss": 0.7637890577316284,
      "step": 3256
    },
    {
      "epoch": 1.3746835443037975,
      "grad_norm": 0.4319530725479126,
      "learning_rate": 0.00018732956839792012,
      "loss": 0.7906988263130188,
      "step": 3258
    },
    {
      "epoch": 1.3755274261603376,
      "grad_norm": 0.4393143355846405,
      "learning_rate": 0.00018730615893305025,
      "loss": 0.7261547446250916,
      "step": 3260
    },
    {
      "epoch": 1.3763713080168776,
      "grad_norm": 0.4161636233329773,
      "learning_rate": 0.00018728272932832632,
      "loss": 0.6857497692108154,
      "step": 3262
    },
    {
      "epoch": 1.3772151898734177,
      "grad_norm": 0.48862120509147644,
      "learning_rate": 0.00018725927958915297,
      "loss": 0.7488857507705688,
      "step": 3264
    },
    {
      "epoch": 1.378059071729958,
      "grad_norm": 0.4422304928302765,
      "learning_rate": 0.0001872358097209397,
      "loss": 0.7257721424102783,
      "step": 3266
    },
    {
      "epoch": 1.3789029535864978,
      "grad_norm": 0.4577067494392395,
      "learning_rate": 0.00018721231972910048,
      "loss": 0.746697187423706,
      "step": 3268
    },
    {
      "epoch": 1.379746835443038,
      "grad_norm": 0.42382001876831055,
      "learning_rate": 0.00018718880961905406,
      "loss": 0.768519401550293,
      "step": 3270
    },
    {
      "epoch": 1.3805907172995782,
      "grad_norm": 0.43368014693260193,
      "learning_rate": 0.00018716527939622378,
      "loss": 0.7426102757453918,
      "step": 3272
    },
    {
      "epoch": 1.381434599156118,
      "grad_norm": 0.3777220547199249,
      "learning_rate": 0.00018714172906603757,
      "loss": 0.7104197144508362,
      "step": 3274
    },
    {
      "epoch": 1.3822784810126583,
      "grad_norm": 0.46071696281433105,
      "learning_rate": 0.00018711815863392802,
      "loss": 0.7502968907356262,
      "step": 3276
    },
    {
      "epoch": 1.3831223628691984,
      "grad_norm": 0.42510855197906494,
      "learning_rate": 0.00018709456810533245,
      "loss": 0.6400540471076965,
      "step": 3278
    },
    {
      "epoch": 1.3839662447257384,
      "grad_norm": 0.4217228293418884,
      "learning_rate": 0.00018707095748569268,
      "loss": 0.6648687720298767,
      "step": 3280
    },
    {
      "epoch": 1.3848101265822785,
      "grad_norm": 0.48267799615859985,
      "learning_rate": 0.00018704732678045526,
      "loss": 0.7176171541213989,
      "step": 3282
    },
    {
      "epoch": 1.3856540084388187,
      "grad_norm": 0.47114965319633484,
      "learning_rate": 0.00018702367599507134,
      "loss": 0.8402457237243652,
      "step": 3284
    },
    {
      "epoch": 1.3864978902953586,
      "grad_norm": 0.5054492354393005,
      "learning_rate": 0.00018700000513499667,
      "loss": 0.8130836486816406,
      "step": 3286
    },
    {
      "epoch": 1.3873417721518988,
      "grad_norm": 0.39435645937919617,
      "learning_rate": 0.00018697631420569168,
      "loss": 0.6432579755783081,
      "step": 3288
    },
    {
      "epoch": 1.3881856540084387,
      "grad_norm": 0.3997228443622589,
      "learning_rate": 0.00018695260321262142,
      "loss": 0.6921643614768982,
      "step": 3290
    },
    {
      "epoch": 1.389029535864979,
      "grad_norm": 0.37304237484931946,
      "learning_rate": 0.00018692887216125557,
      "loss": 0.7162153124809265,
      "step": 3292
    },
    {
      "epoch": 1.389873417721519,
      "grad_norm": 0.7997981309890747,
      "learning_rate": 0.00018690512105706838,
      "loss": 0.7194803953170776,
      "step": 3294
    },
    {
      "epoch": 1.390717299578059,
      "grad_norm": 0.41268959641456604,
      "learning_rate": 0.00018688134990553883,
      "loss": 0.6888322830200195,
      "step": 3296
    },
    {
      "epoch": 1.3915611814345992,
      "grad_norm": 0.4485826790332794,
      "learning_rate": 0.00018685755871215043,
      "loss": 0.7387221455574036,
      "step": 3298
    },
    {
      "epoch": 1.3924050632911391,
      "grad_norm": 0.47835296392440796,
      "learning_rate": 0.0001868337474823914,
      "loss": 0.8061952590942383,
      "step": 3300
    },
    {
      "epoch": 1.3924050632911391,
      "eval_loss": 0.795619547367096,
      "eval_runtime": 692.7157,
      "eval_samples_per_second": 3.042,
      "eval_steps_per_second": 3.042,
      "step": 3300
    },
    {
      "epoch": 1.3932489451476793,
      "grad_norm": 0.4024396240711212,
      "learning_rate": 0.00018680991622175446,
      "loss": 0.7317537069320679,
      "step": 3302
    },
    {
      "epoch": 1.3940928270042194,
      "grad_norm": 0.4526490271091461,
      "learning_rate": 0.00018678606493573708,
      "loss": 0.7470992207527161,
      "step": 3304
    },
    {
      "epoch": 1.3949367088607594,
      "grad_norm": 0.5055129528045654,
      "learning_rate": 0.00018676219362984126,
      "loss": 0.7627943754196167,
      "step": 3306
    },
    {
      "epoch": 1.3957805907172995,
      "grad_norm": 0.4030216634273529,
      "learning_rate": 0.0001867383023095737,
      "loss": 0.684033989906311,
      "step": 3308
    },
    {
      "epoch": 1.3966244725738397,
      "grad_norm": 0.4353308379650116,
      "learning_rate": 0.0001867143909804456,
      "loss": 0.7366722822189331,
      "step": 3310
    },
    {
      "epoch": 1.3974683544303796,
      "grad_norm": 0.5360553860664368,
      "learning_rate": 0.0001866904596479729,
      "loss": 0.8050951957702637,
      "step": 3312
    },
    {
      "epoch": 1.3983122362869198,
      "grad_norm": 0.46081677079200745,
      "learning_rate": 0.00018666650831767608,
      "loss": 0.7227963805198669,
      "step": 3314
    },
    {
      "epoch": 1.39915611814346,
      "grad_norm": 0.4325845539569855,
      "learning_rate": 0.00018664253699508029,
      "loss": 0.714216411113739,
      "step": 3316
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.4373100996017456,
      "learning_rate": 0.0001866185456857152,
      "loss": 0.7378593683242798,
      "step": 3318
    },
    {
      "epoch": 1.40084388185654,
      "grad_norm": 0.43221279978752136,
      "learning_rate": 0.00018659453439511512,
      "loss": 0.7565981149673462,
      "step": 3320
    },
    {
      "epoch": 1.4016877637130802,
      "grad_norm": 0.3938370943069458,
      "learning_rate": 0.00018657050312881904,
      "loss": 0.6409488916397095,
      "step": 3322
    },
    {
      "epoch": 1.4025316455696202,
      "grad_norm": 0.43609440326690674,
      "learning_rate": 0.00018654645189237055,
      "loss": 0.6911652088165283,
      "step": 3324
    },
    {
      "epoch": 1.4033755274261603,
      "grad_norm": 0.4526350200176239,
      "learning_rate": 0.00018652238069131774,
      "loss": 0.7275710701942444,
      "step": 3326
    },
    {
      "epoch": 1.4042194092827005,
      "grad_norm": 0.3990516662597656,
      "learning_rate": 0.0001864982895312134,
      "loss": 0.6466895341873169,
      "step": 3328
    },
    {
      "epoch": 1.4050632911392404,
      "grad_norm": 0.44321122765541077,
      "learning_rate": 0.0001864741784176149,
      "loss": 0.6520540714263916,
      "step": 3330
    },
    {
      "epoch": 1.4059071729957806,
      "grad_norm": 0.44733941555023193,
      "learning_rate": 0.0001864500473560842,
      "loss": 0.7289671301841736,
      "step": 3332
    },
    {
      "epoch": 1.4067510548523208,
      "grad_norm": 0.4569414556026459,
      "learning_rate": 0.00018642589635218789,
      "loss": 0.7664391398429871,
      "step": 3334
    },
    {
      "epoch": 1.4075949367088607,
      "grad_norm": 0.4172186851501465,
      "learning_rate": 0.00018640172541149709,
      "loss": 0.7747462391853333,
      "step": 3336
    },
    {
      "epoch": 1.4084388185654009,
      "grad_norm": 0.4540993869304657,
      "learning_rate": 0.0001863775345395877,
      "loss": 0.8337607383728027,
      "step": 3338
    },
    {
      "epoch": 1.409282700421941,
      "grad_norm": 0.4306154251098633,
      "learning_rate": 0.00018635332374203993,
      "loss": 0.6851577758789062,
      "step": 3340
    },
    {
      "epoch": 1.410126582278481,
      "grad_norm": 0.45615455508232117,
      "learning_rate": 0.00018632909302443884,
      "loss": 0.6841398477554321,
      "step": 3342
    },
    {
      "epoch": 1.4109704641350211,
      "grad_norm": 0.35296666622161865,
      "learning_rate": 0.00018630484239237397,
      "loss": 0.6672312021255493,
      "step": 3344
    },
    {
      "epoch": 1.4118143459915613,
      "grad_norm": 0.4424770176410675,
      "learning_rate": 0.00018628057185143945,
      "loss": 0.7027004361152649,
      "step": 3346
    },
    {
      "epoch": 1.4126582278481012,
      "grad_norm": 0.429817259311676,
      "learning_rate": 0.0001862562814072341,
      "loss": 0.7397928237915039,
      "step": 3348
    },
    {
      "epoch": 1.4135021097046414,
      "grad_norm": 0.4720051884651184,
      "learning_rate": 0.00018623197106536118,
      "loss": 0.8009215593338013,
      "step": 3350
    },
    {
      "epoch": 1.4143459915611816,
      "grad_norm": 0.42197802662849426,
      "learning_rate": 0.0001862076408314287,
      "loss": 0.6875046491622925,
      "step": 3352
    },
    {
      "epoch": 1.4151898734177215,
      "grad_norm": 0.3674047589302063,
      "learning_rate": 0.00018618329071104907,
      "loss": 0.7202261090278625,
      "step": 3354
    },
    {
      "epoch": 1.4160337552742617,
      "grad_norm": 0.42327889800071716,
      "learning_rate": 0.0001861589207098395,
      "loss": 0.6981248259544373,
      "step": 3356
    },
    {
      "epoch": 1.4168776371308016,
      "grad_norm": 0.40644150972366333,
      "learning_rate": 0.00018613453083342162,
      "loss": 0.7081356048583984,
      "step": 3358
    },
    {
      "epoch": 1.4177215189873418,
      "grad_norm": 0.3948482275009155,
      "learning_rate": 0.00018611012108742168,
      "loss": 0.6420091986656189,
      "step": 3360
    },
    {
      "epoch": 1.4185654008438817,
      "grad_norm": 0.44622674584388733,
      "learning_rate": 0.00018608569147747064,
      "loss": 0.7662023305892944,
      "step": 3362
    },
    {
      "epoch": 1.4194092827004219,
      "grad_norm": 0.39772045612335205,
      "learning_rate": 0.00018606124200920386,
      "loss": 0.7243877649307251,
      "step": 3364
    },
    {
      "epoch": 1.420253164556962,
      "grad_norm": 0.4284326136112213,
      "learning_rate": 0.00018603677268826138,
      "loss": 0.7399296164512634,
      "step": 3366
    },
    {
      "epoch": 1.421097046413502,
      "grad_norm": 0.3749450445175171,
      "learning_rate": 0.0001860122835202878,
      "loss": 0.6978716850280762,
      "step": 3368
    },
    {
      "epoch": 1.4219409282700421,
      "grad_norm": 0.46721795201301575,
      "learning_rate": 0.00018598777451093234,
      "loss": 0.7733059525489807,
      "step": 3370
    },
    {
      "epoch": 1.4227848101265823,
      "grad_norm": 0.39606085419654846,
      "learning_rate": 0.0001859632456658487,
      "loss": 0.6721867918968201,
      "step": 3372
    },
    {
      "epoch": 1.4236286919831223,
      "grad_norm": 0.3879879117012024,
      "learning_rate": 0.00018593869699069527,
      "loss": 0.715825080871582,
      "step": 3374
    },
    {
      "epoch": 1.4244725738396624,
      "grad_norm": 0.3641676902770996,
      "learning_rate": 0.0001859141284911349,
      "loss": 0.6226941347122192,
      "step": 3376
    },
    {
      "epoch": 1.4253164556962026,
      "grad_norm": 0.4612879753112793,
      "learning_rate": 0.0001858895401728351,
      "loss": 0.7972121238708496,
      "step": 3378
    },
    {
      "epoch": 1.4261603375527425,
      "grad_norm": 0.4406103193759918,
      "learning_rate": 0.00018586493204146795,
      "loss": 0.6663658022880554,
      "step": 3380
    },
    {
      "epoch": 1.4270042194092827,
      "grad_norm": 0.420205295085907,
      "learning_rate": 0.00018584030410271,
      "loss": 0.6867321133613586,
      "step": 3382
    },
    {
      "epoch": 1.4278481012658228,
      "grad_norm": 0.4499560594558716,
      "learning_rate": 0.00018581565636224253,
      "loss": 0.66688072681427,
      "step": 3384
    },
    {
      "epoch": 1.4286919831223628,
      "grad_norm": 0.42507919669151306,
      "learning_rate": 0.00018579098882575123,
      "loss": 0.6714702844619751,
      "step": 3386
    },
    {
      "epoch": 1.429535864978903,
      "grad_norm": 0.43856513500213623,
      "learning_rate": 0.0001857663014989265,
      "loss": 0.7219351530075073,
      "step": 3388
    },
    {
      "epoch": 1.4303797468354431,
      "grad_norm": 0.5167419910430908,
      "learning_rate": 0.00018574159438746314,
      "loss": 0.7157991528511047,
      "step": 3390
    },
    {
      "epoch": 1.431223628691983,
      "grad_norm": 0.4443167746067047,
      "learning_rate": 0.00018571686749706067,
      "loss": 0.7509840726852417,
      "step": 3392
    },
    {
      "epoch": 1.4320675105485232,
      "grad_norm": 0.41321757435798645,
      "learning_rate": 0.0001856921208334231,
      "loss": 0.756000816822052,
      "step": 3394
    },
    {
      "epoch": 1.4329113924050634,
      "grad_norm": 0.4094153046607971,
      "learning_rate": 0.000185667354402259,
      "loss": 0.7047854065895081,
      "step": 3396
    },
    {
      "epoch": 1.4337552742616033,
      "grad_norm": 0.4248482286930084,
      "learning_rate": 0.0001856425682092815,
      "loss": 0.7620865106582642,
      "step": 3398
    },
    {
      "epoch": 1.4345991561181435,
      "grad_norm": 0.4190550148487091,
      "learning_rate": 0.0001856177622602083,
      "loss": 0.7441845536231995,
      "step": 3400
    },
    {
      "epoch": 1.4345991561181435,
      "eval_loss": 0.7917885780334473,
      "eval_runtime": 686.1689,
      "eval_samples_per_second": 3.071,
      "eval_steps_per_second": 3.071,
      "step": 3400
    },
    {
      "epoch": 1.4354430379746836,
      "grad_norm": 0.45602327585220337,
      "learning_rate": 0.00018559293656076166,
      "loss": 0.7123498916625977,
      "step": 3402
    },
    {
      "epoch": 1.4362869198312236,
      "grad_norm": 0.5209269523620605,
      "learning_rate": 0.00018556809111666843,
      "loss": 0.7096527814865112,
      "step": 3404
    },
    {
      "epoch": 1.4371308016877637,
      "grad_norm": 0.44521182775497437,
      "learning_rate": 0.00018554322593365995,
      "loss": 0.7116838693618774,
      "step": 3406
    },
    {
      "epoch": 1.437974683544304,
      "grad_norm": 0.44571003317832947,
      "learning_rate": 0.00018551834101747212,
      "loss": 0.7756352424621582,
      "step": 3408
    },
    {
      "epoch": 1.4388185654008439,
      "grad_norm": 0.4030776023864746,
      "learning_rate": 0.00018549343637384543,
      "loss": 0.689633309841156,
      "step": 3410
    },
    {
      "epoch": 1.439662447257384,
      "grad_norm": 0.4025530517101288,
      "learning_rate": 0.0001854685120085249,
      "loss": 0.7173827290534973,
      "step": 3412
    },
    {
      "epoch": 1.4405063291139242,
      "grad_norm": 0.4376870095729828,
      "learning_rate": 0.0001854435679272601,
      "loss": 0.7212072610855103,
      "step": 3414
    },
    {
      "epoch": 1.4413502109704641,
      "grad_norm": 0.4469084143638611,
      "learning_rate": 0.00018541860413580515,
      "loss": 0.8260660171508789,
      "step": 3416
    },
    {
      "epoch": 1.4421940928270043,
      "grad_norm": 0.48033684492111206,
      "learning_rate": 0.00018539362063991872,
      "loss": 0.764930248260498,
      "step": 3418
    },
    {
      "epoch": 1.4430379746835442,
      "grad_norm": 0.4428006708621979,
      "learning_rate": 0.00018536861744536403,
      "loss": 0.7436494827270508,
      "step": 3420
    },
    {
      "epoch": 1.4438818565400844,
      "grad_norm": 0.41812989115715027,
      "learning_rate": 0.00018534359455790885,
      "loss": 0.7695552706718445,
      "step": 3422
    },
    {
      "epoch": 1.4447257383966245,
      "grad_norm": 0.4243115186691284,
      "learning_rate": 0.00018531855198332544,
      "loss": 0.7430856823921204,
      "step": 3424
    },
    {
      "epoch": 1.4455696202531645,
      "grad_norm": 0.44387027621269226,
      "learning_rate": 0.00018529348972739067,
      "loss": 0.7015851140022278,
      "step": 3426
    },
    {
      "epoch": 1.4464135021097047,
      "grad_norm": 0.5105122923851013,
      "learning_rate": 0.0001852684077958859,
      "loss": 0.7073075771331787,
      "step": 3428
    },
    {
      "epoch": 1.4472573839662446,
      "grad_norm": 0.40193185210227966,
      "learning_rate": 0.00018524330619459708,
      "loss": 0.7478930950164795,
      "step": 3430
    },
    {
      "epoch": 1.4481012658227848,
      "grad_norm": 0.47935256361961365,
      "learning_rate": 0.00018521818492931463,
      "loss": 0.6987152099609375,
      "step": 3432
    },
    {
      "epoch": 1.448945147679325,
      "grad_norm": 0.42298686504364014,
      "learning_rate": 0.00018519304400583356,
      "loss": 0.6677015423774719,
      "step": 3434
    },
    {
      "epoch": 1.4497890295358649,
      "grad_norm": 0.37220221757888794,
      "learning_rate": 0.0001851678834299534,
      "loss": 0.5727065205574036,
      "step": 3436
    },
    {
      "epoch": 1.450632911392405,
      "grad_norm": 0.4990854561328888,
      "learning_rate": 0.00018514270320747823,
      "loss": 0.7245276570320129,
      "step": 3438
    },
    {
      "epoch": 1.4514767932489452,
      "grad_norm": 0.4366965889930725,
      "learning_rate": 0.00018511750334421665,
      "loss": 0.5907649993896484,
      "step": 3440
    },
    {
      "epoch": 1.4523206751054851,
      "grad_norm": 0.4355267286300659,
      "learning_rate": 0.00018509228384598172,
      "loss": 0.6898093223571777,
      "step": 3442
    },
    {
      "epoch": 1.4531645569620253,
      "grad_norm": 0.4055832028388977,
      "learning_rate": 0.00018506704471859116,
      "loss": 0.6242932081222534,
      "step": 3444
    },
    {
      "epoch": 1.4540084388185655,
      "grad_norm": 0.42599600553512573,
      "learning_rate": 0.00018504178596786712,
      "loss": 0.7214970588684082,
      "step": 3446
    },
    {
      "epoch": 1.4548523206751054,
      "grad_norm": 0.41228237748146057,
      "learning_rate": 0.0001850165075996363,
      "loss": 0.7120789885520935,
      "step": 3448
    },
    {
      "epoch": 1.4556962025316456,
      "grad_norm": 0.4529595375061035,
      "learning_rate": 0.00018499120961972996,
      "loss": 0.7376183867454529,
      "step": 3450
    },
    {
      "epoch": 1.4565400843881857,
      "grad_norm": 0.4260895550251007,
      "learning_rate": 0.00018496589203398386,
      "loss": 0.7321018576622009,
      "step": 3452
    },
    {
      "epoch": 1.4573839662447257,
      "grad_norm": 0.46325981616973877,
      "learning_rate": 0.00018494055484823824,
      "loss": 0.7099342346191406,
      "step": 3454
    },
    {
      "epoch": 1.4582278481012658,
      "grad_norm": 0.43322354555130005,
      "learning_rate": 0.00018491519806833795,
      "loss": 0.6663834452629089,
      "step": 3456
    },
    {
      "epoch": 1.459071729957806,
      "grad_norm": 0.421683132648468,
      "learning_rate": 0.0001848898217001323,
      "loss": 0.6634764671325684,
      "step": 3458
    },
    {
      "epoch": 1.459915611814346,
      "grad_norm": 0.44365957379341125,
      "learning_rate": 0.00018486442574947511,
      "loss": 0.697095513343811,
      "step": 3460
    },
    {
      "epoch": 1.460759493670886,
      "grad_norm": 0.4892813265323639,
      "learning_rate": 0.00018483901022222474,
      "loss": 0.8009715676307678,
      "step": 3462
    },
    {
      "epoch": 1.4616033755274263,
      "grad_norm": 0.4230288863182068,
      "learning_rate": 0.00018481357512424408,
      "loss": 0.631499707698822,
      "step": 3464
    },
    {
      "epoch": 1.4624472573839662,
      "grad_norm": 0.49490758776664734,
      "learning_rate": 0.00018478812046140056,
      "loss": 0.8045525550842285,
      "step": 3466
    },
    {
      "epoch": 1.4632911392405064,
      "grad_norm": 0.5035375952720642,
      "learning_rate": 0.00018476264623956597,
      "loss": 0.7299133539199829,
      "step": 3468
    },
    {
      "epoch": 1.4641350210970465,
      "grad_norm": 0.45048409700393677,
      "learning_rate": 0.00018473715246461684,
      "loss": 0.7313228845596313,
      "step": 3470
    },
    {
      "epoch": 1.4649789029535865,
      "grad_norm": 0.41414541006088257,
      "learning_rate": 0.00018471163914243405,
      "loss": 0.7515901923179626,
      "step": 3472
    },
    {
      "epoch": 1.4658227848101266,
      "grad_norm": 0.4440646767616272,
      "learning_rate": 0.00018468610627890298,
      "loss": 0.7425532341003418,
      "step": 3474
    },
    {
      "epoch": 1.4666666666666668,
      "grad_norm": 0.4749740660190582,
      "learning_rate": 0.00018466055387991362,
      "loss": 0.7509122490882874,
      "step": 3476
    },
    {
      "epoch": 1.4675105485232067,
      "grad_norm": 0.498951256275177,
      "learning_rate": 0.00018463498195136046,
      "loss": 0.7395774126052856,
      "step": 3478
    },
    {
      "epoch": 1.4683544303797469,
      "grad_norm": 0.45996859669685364,
      "learning_rate": 0.00018460939049914237,
      "loss": 0.7860153317451477,
      "step": 3480
    },
    {
      "epoch": 1.469198312236287,
      "grad_norm": 0.5989604592323303,
      "learning_rate": 0.0001845837795291629,
      "loss": 0.8193565607070923,
      "step": 3482
    },
    {
      "epoch": 1.470042194092827,
      "grad_norm": 0.3903721272945404,
      "learning_rate": 0.0001845581490473299,
      "loss": 0.6569210290908813,
      "step": 3484
    },
    {
      "epoch": 1.4708860759493672,
      "grad_norm": 0.4316142201423645,
      "learning_rate": 0.00018453249905955592,
      "loss": 0.7226642370223999,
      "step": 3486
    },
    {
      "epoch": 1.471729957805907,
      "grad_norm": 0.4447585344314575,
      "learning_rate": 0.00018450682957175786,
      "loss": 0.8134398460388184,
      "step": 3488
    },
    {
      "epoch": 1.4725738396624473,
      "grad_norm": 0.42515450716018677,
      "learning_rate": 0.0001844811405898572,
      "loss": 0.7668985724449158,
      "step": 3490
    },
    {
      "epoch": 1.4734177215189874,
      "grad_norm": 0.39883363246917725,
      "learning_rate": 0.0001844554321197799,
      "loss": 0.7289790511131287,
      "step": 3492
    },
    {
      "epoch": 1.4742616033755274,
      "grad_norm": 0.4419080317020416,
      "learning_rate": 0.00018442970416745645,
      "loss": 0.7611824870109558,
      "step": 3494
    },
    {
      "epoch": 1.4751054852320675,
      "grad_norm": 0.37460315227508545,
      "learning_rate": 0.0001844039567388217,
      "loss": 0.6926230788230896,
      "step": 3496
    },
    {
      "epoch": 1.4759493670886075,
      "grad_norm": 0.47706854343414307,
      "learning_rate": 0.00018437818983981513,
      "loss": 0.7889325618743896,
      "step": 3498
    },
    {
      "epoch": 1.4767932489451476,
      "grad_norm": 0.449028879404068,
      "learning_rate": 0.00018435240347638074,
      "loss": 0.7231656312942505,
      "step": 3500
    },
    {
      "epoch": 1.4767932489451476,
      "eval_loss": 0.7902651429176331,
      "eval_runtime": 672.312,
      "eval_samples_per_second": 3.134,
      "eval_steps_per_second": 3.134,
      "step": 3500
    },
    {
      "epoch": 1.4776371308016878,
      "grad_norm": 0.44085755944252014,
      "learning_rate": 0.00018432659765446686,
      "loss": 0.7464927434921265,
      "step": 3502
    },
    {
      "epoch": 1.4784810126582277,
      "grad_norm": 0.4243546724319458,
      "learning_rate": 0.0001843007723800264,
      "loss": 0.7312393188476562,
      "step": 3504
    },
    {
      "epoch": 1.479324894514768,
      "grad_norm": 0.4437529444694519,
      "learning_rate": 0.00018427492765901677,
      "loss": 0.7169944643974304,
      "step": 3506
    },
    {
      "epoch": 1.480168776371308,
      "grad_norm": 0.3639313280582428,
      "learning_rate": 0.0001842490634973999,
      "loss": 0.6169725060462952,
      "step": 3508
    },
    {
      "epoch": 1.481012658227848,
      "grad_norm": 0.4452592730522156,
      "learning_rate": 0.0001842231799011421,
      "loss": 0.7034649848937988,
      "step": 3510
    },
    {
      "epoch": 1.4818565400843882,
      "grad_norm": 0.5229591131210327,
      "learning_rate": 0.00018419727687621421,
      "loss": 0.7535615563392639,
      "step": 3512
    },
    {
      "epoch": 1.4827004219409283,
      "grad_norm": 0.40748512744903564,
      "learning_rate": 0.00018417135442859163,
      "loss": 0.6858918070793152,
      "step": 3514
    },
    {
      "epoch": 1.4835443037974683,
      "grad_norm": 0.4532773792743683,
      "learning_rate": 0.0001841454125642541,
      "loss": 0.7120109796524048,
      "step": 3516
    },
    {
      "epoch": 1.4843881856540084,
      "grad_norm": 0.4281020760536194,
      "learning_rate": 0.00018411945128918593,
      "loss": 0.6837015748023987,
      "step": 3518
    },
    {
      "epoch": 1.4852320675105486,
      "grad_norm": 0.4891088306903839,
      "learning_rate": 0.0001840934706093759,
      "loss": 0.6639618873596191,
      "step": 3520
    },
    {
      "epoch": 1.4860759493670885,
      "grad_norm": 0.44358906149864197,
      "learning_rate": 0.00018406747053081724,
      "loss": 0.693483829498291,
      "step": 3522
    },
    {
      "epoch": 1.4869198312236287,
      "grad_norm": 0.40134626626968384,
      "learning_rate": 0.00018404145105950767,
      "loss": 0.7046290636062622,
      "step": 3524
    },
    {
      "epoch": 1.4877637130801689,
      "grad_norm": 0.4601934552192688,
      "learning_rate": 0.0001840154122014494,
      "loss": 0.6991957426071167,
      "step": 3526
    },
    {
      "epoch": 1.4886075949367088,
      "grad_norm": 0.39107242226600647,
      "learning_rate": 0.00018398935396264906,
      "loss": 0.667023241519928,
      "step": 3528
    },
    {
      "epoch": 1.489451476793249,
      "grad_norm": 0.4498196542263031,
      "learning_rate": 0.00018396327634911784,
      "loss": 0.7187332510948181,
      "step": 3530
    },
    {
      "epoch": 1.4902953586497891,
      "grad_norm": 0.41769179701805115,
      "learning_rate": 0.0001839371793668713,
      "loss": 0.6854014992713928,
      "step": 3532
    },
    {
      "epoch": 1.491139240506329,
      "grad_norm": 0.40170612931251526,
      "learning_rate": 0.0001839110630219295,
      "loss": 0.6643120050430298,
      "step": 3534
    },
    {
      "epoch": 1.4919831223628692,
      "grad_norm": 0.43697425723075867,
      "learning_rate": 0.00018388492732031701,
      "loss": 0.6822295188903809,
      "step": 3536
    },
    {
      "epoch": 1.4928270042194094,
      "grad_norm": 0.4400080442428589,
      "learning_rate": 0.00018385877226806288,
      "loss": 0.7500558495521545,
      "step": 3538
    },
    {
      "epoch": 1.4936708860759493,
      "grad_norm": 0.5162575244903564,
      "learning_rate": 0.00018383259787120048,
      "loss": 0.7742161750793457,
      "step": 3540
    },
    {
      "epoch": 1.4945147679324895,
      "grad_norm": 0.4234789311885834,
      "learning_rate": 0.0001838064041357678,
      "loss": 0.7334147095680237,
      "step": 3542
    },
    {
      "epoch": 1.4953586497890297,
      "grad_norm": 0.40562525391578674,
      "learning_rate": 0.0001837801910678072,
      "loss": 0.691303014755249,
      "step": 3544
    },
    {
      "epoch": 1.4962025316455696,
      "grad_norm": 0.3651523292064667,
      "learning_rate": 0.00018375395867336556,
      "loss": 0.6478174328804016,
      "step": 3546
    },
    {
      "epoch": 1.4970464135021098,
      "grad_norm": 0.45428016781806946,
      "learning_rate": 0.00018372770695849417,
      "loss": 0.6800187826156616,
      "step": 3548
    },
    {
      "epoch": 1.49789029535865,
      "grad_norm": 0.4258574843406677,
      "learning_rate": 0.00018370143592924882,
      "loss": 0.7386951446533203,
      "step": 3550
    },
    {
      "epoch": 1.4987341772151899,
      "grad_norm": 0.4260908365249634,
      "learning_rate": 0.00018367514559168972,
      "loss": 0.757290780544281,
      "step": 3552
    },
    {
      "epoch": 1.49957805907173,
      "grad_norm": 0.4037017226219177,
      "learning_rate": 0.00018364883595188152,
      "loss": 0.7254101037979126,
      "step": 3554
    },
    {
      "epoch": 1.5004219409282702,
      "grad_norm": 0.4212391674518585,
      "learning_rate": 0.0001836225070158934,
      "loss": 0.7342239618301392,
      "step": 3556
    },
    {
      "epoch": 1.5012658227848101,
      "grad_norm": 0.4902292490005493,
      "learning_rate": 0.0001835961587897989,
      "loss": 0.7147436738014221,
      "step": 3558
    },
    {
      "epoch": 1.50210970464135,
      "grad_norm": 0.39230459928512573,
      "learning_rate": 0.00018356979127967605,
      "loss": 0.7473883628845215,
      "step": 3560
    },
    {
      "epoch": 1.5029535864978905,
      "grad_norm": 0.4203200340270996,
      "learning_rate": 0.00018354340449160735,
      "loss": 0.7026845812797546,
      "step": 3562
    },
    {
      "epoch": 1.5037974683544304,
      "grad_norm": 0.44363775849342346,
      "learning_rate": 0.00018351699843167972,
      "loss": 0.7426526546478271,
      "step": 3564
    },
    {
      "epoch": 1.5046413502109703,
      "grad_norm": 0.4479754865169525,
      "learning_rate": 0.0001834905731059845,
      "loss": 0.6800932884216309,
      "step": 3566
    },
    {
      "epoch": 1.5054852320675105,
      "grad_norm": 0.43898341059684753,
      "learning_rate": 0.0001834641285206176,
      "loss": 0.6681315898895264,
      "step": 3568
    },
    {
      "epoch": 1.5063291139240507,
      "grad_norm": 0.44789746403694153,
      "learning_rate": 0.00018343766468167916,
      "loss": 0.7319603562355042,
      "step": 3570
    },
    {
      "epoch": 1.5071729957805906,
      "grad_norm": 0.44450023770332336,
      "learning_rate": 0.00018341118159527392,
      "loss": 0.7205765843391418,
      "step": 3572
    },
    {
      "epoch": 1.5080168776371308,
      "grad_norm": 0.4461601674556732,
      "learning_rate": 0.00018338467926751103,
      "loss": 0.8053180575370789,
      "step": 3574
    },
    {
      "epoch": 1.508860759493671,
      "grad_norm": 0.415216863155365,
      "learning_rate": 0.00018335815770450408,
      "loss": 0.6944835186004639,
      "step": 3576
    },
    {
      "epoch": 1.5097046413502109,
      "grad_norm": 0.48354068398475647,
      "learning_rate": 0.00018333161691237105,
      "loss": 0.7333522439002991,
      "step": 3578
    },
    {
      "epoch": 1.510548523206751,
      "grad_norm": 0.44450995326042175,
      "learning_rate": 0.00018330505689723446,
      "loss": 0.7036639451980591,
      "step": 3580
    },
    {
      "epoch": 1.5113924050632912,
      "grad_norm": 0.355945348739624,
      "learning_rate": 0.00018327847766522111,
      "loss": 0.6589286923408508,
      "step": 3582
    },
    {
      "epoch": 1.5122362869198311,
      "grad_norm": 0.4532116651535034,
      "learning_rate": 0.00018325187922246236,
      "loss": 0.7284913063049316,
      "step": 3584
    },
    {
      "epoch": 1.5130801687763713,
      "grad_norm": 0.45910802483558655,
      "learning_rate": 0.00018322526157509396,
      "loss": 0.7253853678703308,
      "step": 3586
    },
    {
      "epoch": 1.5139240506329115,
      "grad_norm": 0.4729263186454773,
      "learning_rate": 0.0001831986247292561,
      "loss": 0.7626010179519653,
      "step": 3588
    },
    {
      "epoch": 1.5147679324894514,
      "grad_norm": 0.42071840167045593,
      "learning_rate": 0.00018317196869109336,
      "loss": 0.705466091632843,
      "step": 3590
    },
    {
      "epoch": 1.5156118143459916,
      "grad_norm": 0.40275856852531433,
      "learning_rate": 0.00018314529346675479,
      "loss": 0.6900550723075867,
      "step": 3592
    },
    {
      "epoch": 1.5164556962025317,
      "grad_norm": 0.43557414412498474,
      "learning_rate": 0.00018311859906239387,
      "loss": 0.6951512694358826,
      "step": 3594
    },
    {
      "epoch": 1.5172995780590717,
      "grad_norm": 0.4007355570793152,
      "learning_rate": 0.00018309188548416844,
      "loss": 0.7453750967979431,
      "step": 3596
    },
    {
      "epoch": 1.5181434599156118,
      "grad_norm": 0.4686451256275177,
      "learning_rate": 0.00018306515273824086,
      "loss": 0.7549434900283813,
      "step": 3598
    },
    {
      "epoch": 1.518987341772152,
      "grad_norm": 0.47308704257011414,
      "learning_rate": 0.0001830384008307778,
      "loss": 0.7708864212036133,
      "step": 3600
    },
    {
      "epoch": 1.518987341772152,
      "eval_loss": 0.785450279712677,
      "eval_runtime": 675.2312,
      "eval_samples_per_second": 3.12,
      "eval_steps_per_second": 3.12,
      "step": 3600
    },
    {
      "epoch": 1.519831223628692,
      "grad_norm": 0.4343389570713043,
      "learning_rate": 0.0001830116297679505,
      "loss": 0.7501338124275208,
      "step": 3602
    },
    {
      "epoch": 1.520675105485232,
      "grad_norm": 0.4971345067024231,
      "learning_rate": 0.00018298483955593445,
      "loss": 0.7358015179634094,
      "step": 3604
    },
    {
      "epoch": 1.5215189873417723,
      "grad_norm": 0.42013493180274963,
      "learning_rate": 0.0001829580302009097,
      "loss": 0.7972728610038757,
      "step": 3606
    },
    {
      "epoch": 1.5223628691983122,
      "grad_norm": 0.44829806685447693,
      "learning_rate": 0.00018293120170906062,
      "loss": 0.5908644199371338,
      "step": 3608
    },
    {
      "epoch": 1.5232067510548524,
      "grad_norm": 0.47412917017936707,
      "learning_rate": 0.000182904354086576,
      "loss": 0.7872797846794128,
      "step": 3610
    },
    {
      "epoch": 1.5240506329113925,
      "grad_norm": 0.4224211275577545,
      "learning_rate": 0.0001828774873396491,
      "loss": 0.7327616214752197,
      "step": 3612
    },
    {
      "epoch": 1.5248945147679325,
      "grad_norm": 0.4055147171020508,
      "learning_rate": 0.00018285060147447756,
      "loss": 0.6649892330169678,
      "step": 3614
    },
    {
      "epoch": 1.5257383966244724,
      "grad_norm": 0.4058035910129547,
      "learning_rate": 0.00018282369649726346,
      "loss": 0.6939427852630615,
      "step": 3616
    },
    {
      "epoch": 1.5265822784810128,
      "grad_norm": 0.4192068874835968,
      "learning_rate": 0.00018279677241421325,
      "loss": 0.6351069211959839,
      "step": 3618
    },
    {
      "epoch": 1.5274261603375527,
      "grad_norm": 0.4659916162490845,
      "learning_rate": 0.00018276982923153776,
      "loss": 0.6963213682174683,
      "step": 3620
    },
    {
      "epoch": 1.5282700421940927,
      "grad_norm": 0.4993051290512085,
      "learning_rate": 0.00018274286695545229,
      "loss": 0.7463255524635315,
      "step": 3622
    },
    {
      "epoch": 1.529113924050633,
      "grad_norm": 0.39232251048088074,
      "learning_rate": 0.00018271588559217654,
      "loss": 0.6566499471664429,
      "step": 3624
    },
    {
      "epoch": 1.529957805907173,
      "grad_norm": 0.4482063353061676,
      "learning_rate": 0.00018268888514793457,
      "loss": 0.7695494890213013,
      "step": 3626
    },
    {
      "epoch": 1.530801687763713,
      "grad_norm": 0.4000336825847626,
      "learning_rate": 0.00018266186562895483,
      "loss": 0.7357239723205566,
      "step": 3628
    },
    {
      "epoch": 1.5316455696202531,
      "grad_norm": 0.4220462441444397,
      "learning_rate": 0.0001826348270414703,
      "loss": 0.7234170436859131,
      "step": 3630
    },
    {
      "epoch": 1.5324894514767933,
      "grad_norm": 0.4787490665912628,
      "learning_rate": 0.00018260776939171814,
      "loss": 0.7864061594009399,
      "step": 3632
    },
    {
      "epoch": 1.5333333333333332,
      "grad_norm": 0.3670683205127716,
      "learning_rate": 0.00018258069268594013,
      "loss": 0.670537531375885,
      "step": 3634
    },
    {
      "epoch": 1.5341772151898734,
      "grad_norm": 0.41599538922309875,
      "learning_rate": 0.0001825535969303823,
      "loss": 0.7535691261291504,
      "step": 3636
    },
    {
      "epoch": 1.5350210970464135,
      "grad_norm": 0.5033245086669922,
      "learning_rate": 0.00018252648213129514,
      "loss": 0.7553712725639343,
      "step": 3638
    },
    {
      "epoch": 1.5358649789029535,
      "grad_norm": 0.4235823452472687,
      "learning_rate": 0.0001824993482949335,
      "loss": 0.7149441242218018,
      "step": 3640
    },
    {
      "epoch": 1.5367088607594936,
      "grad_norm": 0.37993329763412476,
      "learning_rate": 0.00018247219542755664,
      "loss": 0.735568642616272,
      "step": 3642
    },
    {
      "epoch": 1.5375527426160338,
      "grad_norm": 0.39534425735473633,
      "learning_rate": 0.00018244502353542818,
      "loss": 0.693510115146637,
      "step": 3644
    },
    {
      "epoch": 1.5383966244725737,
      "grad_norm": 0.45447441935539246,
      "learning_rate": 0.00018241783262481622,
      "loss": 0.7261984348297119,
      "step": 3646
    },
    {
      "epoch": 1.539240506329114,
      "grad_norm": 0.4131409823894501,
      "learning_rate": 0.0001823906227019931,
      "loss": 0.7518824338912964,
      "step": 3648
    },
    {
      "epoch": 1.540084388185654,
      "grad_norm": 0.46603885293006897,
      "learning_rate": 0.00018236339377323567,
      "loss": 0.7650659680366516,
      "step": 3650
    },
    {
      "epoch": 1.540928270042194,
      "grad_norm": 0.3998747766017914,
      "learning_rate": 0.00018233614584482513,
      "loss": 0.6436064839363098,
      "step": 3652
    },
    {
      "epoch": 1.5417721518987342,
      "grad_norm": 0.4314839839935303,
      "learning_rate": 0.00018230887892304703,
      "loss": 0.7068451642990112,
      "step": 3654
    },
    {
      "epoch": 1.5426160337552743,
      "grad_norm": 0.4324610233306885,
      "learning_rate": 0.0001822815930141913,
      "loss": 0.7342977523803711,
      "step": 3656
    },
    {
      "epoch": 1.5434599156118143,
      "grad_norm": 0.4385458827018738,
      "learning_rate": 0.0001822542881245524,
      "loss": 0.6482785940170288,
      "step": 3658
    },
    {
      "epoch": 1.5443037974683544,
      "grad_norm": 0.3736587166786194,
      "learning_rate": 0.0001822269642604289,
      "loss": 0.6319621205329895,
      "step": 3660
    },
    {
      "epoch": 1.5451476793248946,
      "grad_norm": 0.42113035917282104,
      "learning_rate": 0.00018219962142812393,
      "loss": 0.6603307723999023,
      "step": 3662
    },
    {
      "epoch": 1.5459915611814345,
      "grad_norm": 0.422158420085907,
      "learning_rate": 0.00018217225963394496,
      "loss": 0.6874772906303406,
      "step": 3664
    },
    {
      "epoch": 1.5468354430379747,
      "grad_norm": 0.42724940180778503,
      "learning_rate": 0.00018214487888420388,
      "loss": 0.7231854796409607,
      "step": 3666
    },
    {
      "epoch": 1.5476793248945149,
      "grad_norm": 0.3747844398021698,
      "learning_rate": 0.00018211747918521685,
      "loss": 0.6418231129646301,
      "step": 3668
    },
    {
      "epoch": 1.5485232067510548,
      "grad_norm": 0.37007269263267517,
      "learning_rate": 0.00018209006054330446,
      "loss": 0.7019823789596558,
      "step": 3670
    },
    {
      "epoch": 1.549367088607595,
      "grad_norm": 0.409701943397522,
      "learning_rate": 0.00018206262296479168,
      "loss": 0.6632764339447021,
      "step": 3672
    },
    {
      "epoch": 1.5502109704641351,
      "grad_norm": 0.49566221237182617,
      "learning_rate": 0.00018203516645600782,
      "loss": 0.7327075600624084,
      "step": 3674
    },
    {
      "epoch": 1.551054852320675,
      "grad_norm": 0.4549940526485443,
      "learning_rate": 0.0001820076910232866,
      "loss": 0.6535149812698364,
      "step": 3676
    },
    {
      "epoch": 1.5518987341772152,
      "grad_norm": 0.42619478702545166,
      "learning_rate": 0.000181980196672966,
      "loss": 0.7761320471763611,
      "step": 3678
    },
    {
      "epoch": 1.5527426160337554,
      "grad_norm": 0.4332887828350067,
      "learning_rate": 0.00018195268341138852,
      "loss": 0.6728626489639282,
      "step": 3680
    },
    {
      "epoch": 1.5535864978902953,
      "grad_norm": 0.4972975552082062,
      "learning_rate": 0.0001819251512449009,
      "loss": 0.7369232177734375,
      "step": 3682
    },
    {
      "epoch": 1.5544303797468353,
      "grad_norm": 0.3619556725025177,
      "learning_rate": 0.00018189760017985428,
      "loss": 0.6703663468360901,
      "step": 3684
    },
    {
      "epoch": 1.5552742616033757,
      "grad_norm": 0.46435829997062683,
      "learning_rate": 0.00018187003022260417,
      "loss": 0.7183756828308105,
      "step": 3686
    },
    {
      "epoch": 1.5561181434599156,
      "grad_norm": 0.4605063498020172,
      "learning_rate": 0.00018184244137951045,
      "loss": 0.680042564868927,
      "step": 3688
    },
    {
      "epoch": 1.5569620253164556,
      "grad_norm": 0.4023124873638153,
      "learning_rate": 0.00018181483365693732,
      "loss": 0.679821789264679,
      "step": 3690
    },
    {
      "epoch": 1.557805907172996,
      "grad_norm": 0.459499716758728,
      "learning_rate": 0.00018178720706125333,
      "loss": 0.7408921718597412,
      "step": 3692
    },
    {
      "epoch": 1.5586497890295359,
      "grad_norm": 0.4397135078907013,
      "learning_rate": 0.00018175956159883146,
      "loss": 0.6926741003990173,
      "step": 3694
    },
    {
      "epoch": 1.5594936708860758,
      "grad_norm": 0.4476170837879181,
      "learning_rate": 0.0001817318972760489,
      "loss": 0.752724826335907,
      "step": 3696
    },
    {
      "epoch": 1.560337552742616,
      "grad_norm": 0.43684154748916626,
      "learning_rate": 0.00018170421409928735,
      "loss": 0.7217722535133362,
      "step": 3698
    },
    {
      "epoch": 1.5611814345991561,
      "grad_norm": 0.4118131995201111,
      "learning_rate": 0.00018167651207493278,
      "loss": 0.7264936566352844,
      "step": 3700
    },
    {
      "epoch": 1.5611814345991561,
      "eval_loss": 0.7854447960853577,
      "eval_runtime": 687.7907,
      "eval_samples_per_second": 3.063,
      "eval_steps_per_second": 3.063,
      "step": 3700
    },
    {
      "epoch": 1.562025316455696,
      "grad_norm": 0.40639030933380127,
      "learning_rate": 0.0001816487912093755,
      "loss": 0.701478123664856,
      "step": 3702
    },
    {
      "epoch": 1.5628691983122363,
      "grad_norm": 0.4205699563026428,
      "learning_rate": 0.00018162105150901017,
      "loss": 0.696711003780365,
      "step": 3704
    },
    {
      "epoch": 1.5637130801687764,
      "grad_norm": 0.46437183022499084,
      "learning_rate": 0.0001815932929802358,
      "loss": 0.7130293250083923,
      "step": 3706
    },
    {
      "epoch": 1.5645569620253164,
      "grad_norm": 0.4413023591041565,
      "learning_rate": 0.0001815655156294558,
      "loss": 0.7180310487747192,
      "step": 3708
    },
    {
      "epoch": 1.5654008438818565,
      "grad_norm": 0.3964478075504303,
      "learning_rate": 0.00018153771946307783,
      "loss": 0.6883325576782227,
      "step": 3710
    },
    {
      "epoch": 1.5662447257383967,
      "grad_norm": 0.34486109018325806,
      "learning_rate": 0.00018150990448751394,
      "loss": 0.6683162450790405,
      "step": 3712
    },
    {
      "epoch": 1.5670886075949366,
      "grad_norm": 0.4209035336971283,
      "learning_rate": 0.00018148207070918052,
      "loss": 0.6969789862632751,
      "step": 3714
    },
    {
      "epoch": 1.5679324894514768,
      "grad_norm": 0.41674816608428955,
      "learning_rate": 0.00018145421813449829,
      "loss": 0.714320182800293,
      "step": 3716
    },
    {
      "epoch": 1.568776371308017,
      "grad_norm": 0.4365934729576111,
      "learning_rate": 0.00018142634676989228,
      "loss": 0.7125279307365417,
      "step": 3718
    },
    {
      "epoch": 1.5696202531645569,
      "grad_norm": 0.43599721789360046,
      "learning_rate": 0.00018139845662179188,
      "loss": 0.6787398457527161,
      "step": 3720
    },
    {
      "epoch": 1.570464135021097,
      "grad_norm": 0.36320003867149353,
      "learning_rate": 0.0001813705476966308,
      "loss": 0.6401328444480896,
      "step": 3722
    },
    {
      "epoch": 1.5713080168776372,
      "grad_norm": 0.43504419922828674,
      "learning_rate": 0.00018134262000084718,
      "loss": 0.6875129342079163,
      "step": 3724
    },
    {
      "epoch": 1.5721518987341772,
      "grad_norm": 0.476723313331604,
      "learning_rate": 0.00018131467354088332,
      "loss": 0.6903918385505676,
      "step": 3726
    },
    {
      "epoch": 1.5729957805907173,
      "grad_norm": 0.4465550184249878,
      "learning_rate": 0.00018128670832318592,
      "loss": 0.690018892288208,
      "step": 3728
    },
    {
      "epoch": 1.5738396624472575,
      "grad_norm": 0.43816477060317993,
      "learning_rate": 0.0001812587243542061,
      "loss": 0.6912158727645874,
      "step": 3730
    },
    {
      "epoch": 1.5746835443037974,
      "grad_norm": 0.40546250343322754,
      "learning_rate": 0.00018123072164039913,
      "loss": 0.7415492534637451,
      "step": 3732
    },
    {
      "epoch": 1.5755274261603376,
      "grad_norm": 0.4253178536891937,
      "learning_rate": 0.00018120270018822477,
      "loss": 0.7664727568626404,
      "step": 3734
    },
    {
      "epoch": 1.5763713080168777,
      "grad_norm": 0.503524661064148,
      "learning_rate": 0.000181174660004147,
      "loss": 0.782779335975647,
      "step": 3736
    },
    {
      "epoch": 1.5772151898734177,
      "grad_norm": 0.5260395407676697,
      "learning_rate": 0.00018114660109463414,
      "loss": 0.806460976600647,
      "step": 3738
    },
    {
      "epoch": 1.5780590717299579,
      "grad_norm": 0.3641359806060791,
      "learning_rate": 0.0001811185234661589,
      "loss": 0.6859704852104187,
      "step": 3740
    },
    {
      "epoch": 1.578902953586498,
      "grad_norm": 0.4468916058540344,
      "learning_rate": 0.00018109042712519818,
      "loss": 0.7798553109169006,
      "step": 3742
    },
    {
      "epoch": 1.579746835443038,
      "grad_norm": 0.4078207015991211,
      "learning_rate": 0.00018106231207823327,
      "loss": 0.7086471915245056,
      "step": 3744
    },
    {
      "epoch": 1.580590717299578,
      "grad_norm": 0.39144742488861084,
      "learning_rate": 0.00018103417833174981,
      "loss": 0.6669760346412659,
      "step": 3746
    },
    {
      "epoch": 1.5814345991561183,
      "grad_norm": 0.4366845190525055,
      "learning_rate": 0.0001810060258922377,
      "loss": 0.7296954989433289,
      "step": 3748
    },
    {
      "epoch": 1.5822784810126582,
      "grad_norm": 0.46795082092285156,
      "learning_rate": 0.00018097785476619118,
      "loss": 0.7663856148719788,
      "step": 3750
    },
    {
      "epoch": 1.5831223628691982,
      "grad_norm": 0.40331873297691345,
      "learning_rate": 0.00018094966496010878,
      "loss": 0.7105234861373901,
      "step": 3752
    },
    {
      "epoch": 1.5839662447257385,
      "grad_norm": 0.38210469484329224,
      "learning_rate": 0.00018092145648049334,
      "loss": 0.666635274887085,
      "step": 3754
    },
    {
      "epoch": 1.5848101265822785,
      "grad_norm": 0.45946040749549866,
      "learning_rate": 0.000180893229333852,
      "loss": 0.7287175059318542,
      "step": 3756
    },
    {
      "epoch": 1.5856540084388184,
      "grad_norm": 0.4035777747631073,
      "learning_rate": 0.00018086498352669624,
      "loss": 0.7145618796348572,
      "step": 3758
    },
    {
      "epoch": 1.5864978902953588,
      "grad_norm": 0.42843320965766907,
      "learning_rate": 0.0001808367190655418,
      "loss": 0.6550979018211365,
      "step": 3760
    },
    {
      "epoch": 1.5873417721518988,
      "grad_norm": 0.4016468822956085,
      "learning_rate": 0.0001808084359569088,
      "loss": 0.7040430307388306,
      "step": 3762
    },
    {
      "epoch": 1.5881856540084387,
      "grad_norm": 0.4126848578453064,
      "learning_rate": 0.00018078013420732157,
      "loss": 0.7523179054260254,
      "step": 3764
    },
    {
      "epoch": 1.5890295358649789,
      "grad_norm": 0.45878592133522034,
      "learning_rate": 0.00018075181382330878,
      "loss": 0.7497967481613159,
      "step": 3766
    },
    {
      "epoch": 1.589873417721519,
      "grad_norm": 0.44179272651672363,
      "learning_rate": 0.00018072347481140345,
      "loss": 0.7694459557533264,
      "step": 3768
    },
    {
      "epoch": 1.590717299578059,
      "grad_norm": 0.3706412613391876,
      "learning_rate": 0.00018069511717814276,
      "loss": 0.6766634583473206,
      "step": 3770
    },
    {
      "epoch": 1.5915611814345991,
      "grad_norm": 0.40555453300476074,
      "learning_rate": 0.0001806667409300683,
      "loss": 0.6394028067588806,
      "step": 3772
    },
    {
      "epoch": 1.5924050632911393,
      "grad_norm": 0.3752219080924988,
      "learning_rate": 0.000180638346073726,
      "loss": 0.6775637865066528,
      "step": 3774
    },
    {
      "epoch": 1.5932489451476792,
      "grad_norm": 0.40960127115249634,
      "learning_rate": 0.00018060993261566593,
      "loss": 0.7200632095336914,
      "step": 3776
    },
    {
      "epoch": 1.5940928270042194,
      "grad_norm": 0.4215535521507263,
      "learning_rate": 0.00018058150056244254,
      "loss": 0.7314276695251465,
      "step": 3778
    },
    {
      "epoch": 1.5949367088607596,
      "grad_norm": 0.42734605073928833,
      "learning_rate": 0.00018055304992061456,
      "loss": 0.7954897284507751,
      "step": 3780
    },
    {
      "epoch": 1.5957805907172995,
      "grad_norm": 0.3980397582054138,
      "learning_rate": 0.00018052458069674505,
      "loss": 0.6552245020866394,
      "step": 3782
    },
    {
      "epoch": 1.5966244725738397,
      "grad_norm": 0.44602933526039124,
      "learning_rate": 0.00018049609289740124,
      "loss": 0.7638092041015625,
      "step": 3784
    },
    {
      "epoch": 1.5974683544303798,
      "grad_norm": 0.43835216760635376,
      "learning_rate": 0.00018046758652915474,
      "loss": 0.6886481046676636,
      "step": 3786
    },
    {
      "epoch": 1.5983122362869198,
      "grad_norm": 0.38229402899742126,
      "learning_rate": 0.00018043906159858147,
      "loss": 0.6726123690605164,
      "step": 3788
    },
    {
      "epoch": 1.59915611814346,
      "grad_norm": 0.43049392104148865,
      "learning_rate": 0.00018041051811226155,
      "loss": 0.7416896224021912,
      "step": 3790
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.4027816951274872,
      "learning_rate": 0.00018038195607677943,
      "loss": 0.682691752910614,
      "step": 3792
    },
    {
      "epoch": 1.60084388185654,
      "grad_norm": 0.4143599569797516,
      "learning_rate": 0.00018035337549872376,
      "loss": 0.7199558615684509,
      "step": 3794
    },
    {
      "epoch": 1.6016877637130802,
      "grad_norm": 0.41221415996551514,
      "learning_rate": 0.00018032477638468762,
      "loss": 0.6586267948150635,
      "step": 3796
    },
    {
      "epoch": 1.6025316455696204,
      "grad_norm": 0.40655994415283203,
      "learning_rate": 0.0001802961587412682,
      "loss": 0.7579189538955688,
      "step": 3798
    },
    {
      "epoch": 1.6033755274261603,
      "grad_norm": 0.4163990914821625,
      "learning_rate": 0.00018026752257506708,
      "loss": 0.7246071100234985,
      "step": 3800
    },
    {
      "epoch": 1.6033755274261603,
      "eval_loss": 0.778353214263916,
      "eval_runtime": 692.5522,
      "eval_samples_per_second": 3.042,
      "eval_steps_per_second": 3.042,
      "step": 3800
    },
    {
      "epoch": 1.6042194092827005,
      "grad_norm": 0.378628671169281,
      "learning_rate": 0.0001802388678926901,
      "loss": 0.7114223837852478,
      "step": 3802
    },
    {
      "epoch": 1.6050632911392406,
      "grad_norm": 0.5050750374794006,
      "learning_rate": 0.0001802101947007473,
      "loss": 0.7519527077674866,
      "step": 3804
    },
    {
      "epoch": 1.6059071729957806,
      "grad_norm": 0.5003950595855713,
      "learning_rate": 0.00018018150300585305,
      "loss": 0.7553771138191223,
      "step": 3806
    },
    {
      "epoch": 1.6067510548523207,
      "grad_norm": 0.3851728141307831,
      "learning_rate": 0.00018015279281462595,
      "loss": 0.6584326028823853,
      "step": 3808
    },
    {
      "epoch": 1.6075949367088609,
      "grad_norm": 0.41256240010261536,
      "learning_rate": 0.00018012406413368893,
      "loss": 0.7215287089347839,
      "step": 3810
    },
    {
      "epoch": 1.6084388185654008,
      "grad_norm": 0.41479718685150146,
      "learning_rate": 0.00018009531696966912,
      "loss": 0.7753872275352478,
      "step": 3812
    },
    {
      "epoch": 1.6092827004219408,
      "grad_norm": 0.398509681224823,
      "learning_rate": 0.00018006655132919797,
      "loss": 0.6984832882881165,
      "step": 3814
    },
    {
      "epoch": 1.6101265822784812,
      "grad_norm": 0.42210307717323303,
      "learning_rate": 0.0001800377672189111,
      "loss": 0.8117644786834717,
      "step": 3816
    },
    {
      "epoch": 1.610970464135021,
      "grad_norm": 0.3714556396007538,
      "learning_rate": 0.0001800089646454485,
      "loss": 0.6302977204322815,
      "step": 3818
    },
    {
      "epoch": 1.611814345991561,
      "grad_norm": 0.4478890299797058,
      "learning_rate": 0.00017998014361545438,
      "loss": 0.7327325940132141,
      "step": 3820
    },
    {
      "epoch": 1.6126582278481014,
      "grad_norm": 0.43516477942466736,
      "learning_rate": 0.00017995130413557713,
      "loss": 0.6877713203430176,
      "step": 3822
    },
    {
      "epoch": 1.6135021097046414,
      "grad_norm": 0.42912542819976807,
      "learning_rate": 0.0001799224462124695,
      "loss": 0.6797093152999878,
      "step": 3824
    },
    {
      "epoch": 1.6143459915611813,
      "grad_norm": 0.40646228194236755,
      "learning_rate": 0.00017989356985278853,
      "loss": 0.7402470111846924,
      "step": 3826
    },
    {
      "epoch": 1.6151898734177215,
      "grad_norm": 0.42576655745506287,
      "learning_rate": 0.00017986467506319535,
      "loss": 0.6698583364486694,
      "step": 3828
    },
    {
      "epoch": 1.6160337552742616,
      "grad_norm": 0.4298654794692993,
      "learning_rate": 0.0001798357618503555,
      "loss": 0.6736086010932922,
      "step": 3830
    },
    {
      "epoch": 1.6168776371308016,
      "grad_norm": 0.4205976128578186,
      "learning_rate": 0.0001798068302209386,
      "loss": 0.7724249958992004,
      "step": 3832
    },
    {
      "epoch": 1.6177215189873417,
      "grad_norm": 0.39669108390808105,
      "learning_rate": 0.00017977788018161872,
      "loss": 0.6468521952629089,
      "step": 3834
    },
    {
      "epoch": 1.618565400843882,
      "grad_norm": 0.428551584482193,
      "learning_rate": 0.00017974891173907405,
      "loss": 0.7086918950080872,
      "step": 3836
    },
    {
      "epoch": 1.6194092827004218,
      "grad_norm": 0.43773409724235535,
      "learning_rate": 0.00017971992489998703,
      "loss": 0.6483711004257202,
      "step": 3838
    },
    {
      "epoch": 1.620253164556962,
      "grad_norm": 0.40540891885757446,
      "learning_rate": 0.00017969091967104438,
      "loss": 0.6947301030158997,
      "step": 3840
    },
    {
      "epoch": 1.6210970464135022,
      "grad_norm": 0.3685019016265869,
      "learning_rate": 0.00017966189605893708,
      "loss": 0.667517900466919,
      "step": 3842
    },
    {
      "epoch": 1.621940928270042,
      "grad_norm": 0.44813284277915955,
      "learning_rate": 0.0001796328540703603,
      "loss": 0.6957448124885559,
      "step": 3844
    },
    {
      "epoch": 1.6227848101265823,
      "grad_norm": 0.4524349868297577,
      "learning_rate": 0.00017960379371201345,
      "loss": 0.7735851407051086,
      "step": 3846
    },
    {
      "epoch": 1.6236286919831224,
      "grad_norm": 0.42349138855934143,
      "learning_rate": 0.0001795747149906002,
      "loss": 0.7052056193351746,
      "step": 3848
    },
    {
      "epoch": 1.6244725738396624,
      "grad_norm": 0.47317537665367126,
      "learning_rate": 0.0001795456179128285,
      "loss": 0.7402311563491821,
      "step": 3850
    },
    {
      "epoch": 1.6253164556962025,
      "grad_norm": 0.38915711641311646,
      "learning_rate": 0.0001795165024854104,
      "loss": 0.6743243932723999,
      "step": 3852
    },
    {
      "epoch": 1.6261603375527427,
      "grad_norm": 0.4430672526359558,
      "learning_rate": 0.00017948736871506235,
      "loss": 0.6983860731124878,
      "step": 3854
    },
    {
      "epoch": 1.6270042194092826,
      "grad_norm": 0.44286689162254333,
      "learning_rate": 0.00017945821660850494,
      "loss": 0.8012514710426331,
      "step": 3856
    },
    {
      "epoch": 1.6278481012658228,
      "grad_norm": 0.43364086747169495,
      "learning_rate": 0.00017942904617246295,
      "loss": 0.8064966201782227,
      "step": 3858
    },
    {
      "epoch": 1.628691983122363,
      "grad_norm": 0.45848122239112854,
      "learning_rate": 0.00017939985741366547,
      "loss": 0.7069969177246094,
      "step": 3860
    },
    {
      "epoch": 1.629535864978903,
      "grad_norm": 0.4199717044830322,
      "learning_rate": 0.0001793706503388458,
      "loss": 0.6722052097320557,
      "step": 3862
    },
    {
      "epoch": 1.630379746835443,
      "grad_norm": 0.3820365071296692,
      "learning_rate": 0.00017934142495474142,
      "loss": 0.663442075252533,
      "step": 3864
    },
    {
      "epoch": 1.6312236286919832,
      "grad_norm": 0.4470944106578827,
      "learning_rate": 0.00017931218126809412,
      "loss": 0.70677250623703,
      "step": 3866
    },
    {
      "epoch": 1.6320675105485232,
      "grad_norm": 0.3941600024700165,
      "learning_rate": 0.0001792829192856498,
      "loss": 0.7125341892242432,
      "step": 3868
    },
    {
      "epoch": 1.6329113924050633,
      "grad_norm": 0.44924396276474,
      "learning_rate": 0.00017925363901415863,
      "loss": 0.7245699763298035,
      "step": 3870
    },
    {
      "epoch": 1.6337552742616035,
      "grad_norm": 0.4070027470588684,
      "learning_rate": 0.00017922434046037508,
      "loss": 0.6977120637893677,
      "step": 3872
    },
    {
      "epoch": 1.6345991561181434,
      "grad_norm": 0.45040908455848694,
      "learning_rate": 0.00017919502363105772,
      "loss": 0.7631482481956482,
      "step": 3874
    },
    {
      "epoch": 1.6354430379746834,
      "grad_norm": 0.4083724617958069,
      "learning_rate": 0.00017916568853296934,
      "loss": 0.6656452417373657,
      "step": 3876
    },
    {
      "epoch": 1.6362869198312238,
      "grad_norm": 0.3762308359146118,
      "learning_rate": 0.00017913633517287704,
      "loss": 0.6302213072776794,
      "step": 3878
    },
    {
      "epoch": 1.6371308016877637,
      "grad_norm": 0.36366912722587585,
      "learning_rate": 0.00017910696355755205,
      "loss": 0.7119566202163696,
      "step": 3880
    },
    {
      "epoch": 1.6379746835443036,
      "grad_norm": 0.43168532848358154,
      "learning_rate": 0.00017907757369376985,
      "loss": 0.7271678447723389,
      "step": 3882
    },
    {
      "epoch": 1.638818565400844,
      "grad_norm": 0.37720009684562683,
      "learning_rate": 0.00017904816558831014,
      "loss": 0.6340095400810242,
      "step": 3884
    },
    {
      "epoch": 1.639662447257384,
      "grad_norm": 0.36539995670318604,
      "learning_rate": 0.00017901873924795677,
      "loss": 0.6910572052001953,
      "step": 3886
    },
    {
      "epoch": 1.640506329113924,
      "grad_norm": 0.42437905073165894,
      "learning_rate": 0.00017898929467949782,
      "loss": 0.7570282220840454,
      "step": 3888
    },
    {
      "epoch": 1.6413502109704643,
      "grad_norm": 0.43482181429862976,
      "learning_rate": 0.00017895983188972558,
      "loss": 0.7835264205932617,
      "step": 3890
    },
    {
      "epoch": 1.6421940928270042,
      "grad_norm": 0.40460237860679626,
      "learning_rate": 0.00017893035088543662,
      "loss": 0.7058968544006348,
      "step": 3892
    },
    {
      "epoch": 1.6430379746835442,
      "grad_norm": 0.39779701828956604,
      "learning_rate": 0.00017890085167343158,
      "loss": 0.723969042301178,
      "step": 3894
    },
    {
      "epoch": 1.6438818565400843,
      "grad_norm": 0.46131494641304016,
      "learning_rate": 0.00017887133426051536,
      "loss": 0.7773922681808472,
      "step": 3896
    },
    {
      "epoch": 1.6447257383966245,
      "grad_norm": 0.48412877321243286,
      "learning_rate": 0.0001788417986534971,
      "loss": 0.7742162942886353,
      "step": 3898
    },
    {
      "epoch": 1.6455696202531644,
      "grad_norm": 0.40083935856819153,
      "learning_rate": 0.00017881224485919006,
      "loss": 0.6674869656562805,
      "step": 3900
    },
    {
      "epoch": 1.6455696202531644,
      "eval_loss": 0.7763351202011108,
      "eval_runtime": 682.0824,
      "eval_samples_per_second": 3.089,
      "eval_steps_per_second": 3.089,
      "step": 3900
    },
    {
      "epoch": 1.6464135021097046,
      "grad_norm": 0.3944476842880249,
      "learning_rate": 0.00017878267288441176,
      "loss": 0.6777821183204651,
      "step": 3902
    },
    {
      "epoch": 1.6472573839662448,
      "grad_norm": 0.44863224029541016,
      "learning_rate": 0.0001787530827359839,
      "loss": 0.7398322224617004,
      "step": 3904
    },
    {
      "epoch": 1.6481012658227847,
      "grad_norm": 0.4665529131889343,
      "learning_rate": 0.00017872347442073232,
      "loss": 0.7203068733215332,
      "step": 3906
    },
    {
      "epoch": 1.6489451476793249,
      "grad_norm": 0.3603050410747528,
      "learning_rate": 0.00017869384794548708,
      "loss": 0.6232115030288696,
      "step": 3908
    },
    {
      "epoch": 1.649789029535865,
      "grad_norm": 0.3545325696468353,
      "learning_rate": 0.0001786642033170825,
      "loss": 0.6120040416717529,
      "step": 3910
    },
    {
      "epoch": 1.650632911392405,
      "grad_norm": 0.3947487473487854,
      "learning_rate": 0.00017863454054235697,
      "loss": 0.7285997867584229,
      "step": 3912
    },
    {
      "epoch": 1.6514767932489451,
      "grad_norm": 0.33153054118156433,
      "learning_rate": 0.00017860485962815312,
      "loss": 0.6486109495162964,
      "step": 3914
    },
    {
      "epoch": 1.6523206751054853,
      "grad_norm": 0.3886185884475708,
      "learning_rate": 0.00017857516058131782,
      "loss": 0.6870376467704773,
      "step": 3916
    },
    {
      "epoch": 1.6531645569620252,
      "grad_norm": 0.46399059891700745,
      "learning_rate": 0.00017854544340870201,
      "loss": 0.7351298928260803,
      "step": 3918
    },
    {
      "epoch": 1.6540084388185654,
      "grad_norm": 0.49280229210853577,
      "learning_rate": 0.00017851570811716093,
      "loss": 0.7283915281295776,
      "step": 3920
    },
    {
      "epoch": 1.6548523206751056,
      "grad_norm": 0.41570642590522766,
      "learning_rate": 0.00017848595471355388,
      "loss": 0.7436906099319458,
      "step": 3922
    },
    {
      "epoch": 1.6556962025316455,
      "grad_norm": 0.44591766595840454,
      "learning_rate": 0.00017845618320474444,
      "loss": 0.7427505254745483,
      "step": 3924
    },
    {
      "epoch": 1.6565400843881857,
      "grad_norm": 0.4804318845272064,
      "learning_rate": 0.00017842639359760032,
      "loss": 0.7642725706100464,
      "step": 3926
    },
    {
      "epoch": 1.6573839662447258,
      "grad_norm": 0.4164349138736725,
      "learning_rate": 0.00017839658589899343,
      "loss": 0.7097790837287903,
      "step": 3928
    },
    {
      "epoch": 1.6582278481012658,
      "grad_norm": 0.5307883620262146,
      "learning_rate": 0.00017836676011579976,
      "loss": 0.8346033096313477,
      "step": 3930
    },
    {
      "epoch": 1.659071729957806,
      "grad_norm": 0.37231504917144775,
      "learning_rate": 0.0001783369162548996,
      "loss": 0.6327160596847534,
      "step": 3932
    },
    {
      "epoch": 1.659915611814346,
      "grad_norm": 0.4178757965564728,
      "learning_rate": 0.00017830705432317738,
      "loss": 0.6441237330436707,
      "step": 3934
    },
    {
      "epoch": 1.660759493670886,
      "grad_norm": 0.42698073387145996,
      "learning_rate": 0.00017827717432752162,
      "loss": 0.7267951369285583,
      "step": 3936
    },
    {
      "epoch": 1.6616033755274262,
      "grad_norm": 0.48763108253479004,
      "learning_rate": 0.0001782472762748251,
      "loss": 0.7248380780220032,
      "step": 3938
    },
    {
      "epoch": 1.6624472573839664,
      "grad_norm": 0.38882505893707275,
      "learning_rate": 0.0001782173601719847,
      "loss": 0.6665275692939758,
      "step": 3940
    },
    {
      "epoch": 1.6632911392405063,
      "grad_norm": 0.4684160649776459,
      "learning_rate": 0.0001781874260259015,
      "loss": 0.8017846941947937,
      "step": 3942
    },
    {
      "epoch": 1.6641350210970463,
      "grad_norm": 0.4200204908847809,
      "learning_rate": 0.00017815747384348075,
      "loss": 0.6810902953147888,
      "step": 3944
    },
    {
      "epoch": 1.6649789029535866,
      "grad_norm": 0.45843279361724854,
      "learning_rate": 0.0001781275036316318,
      "loss": 0.714082658290863,
      "step": 3946
    },
    {
      "epoch": 1.6658227848101266,
      "grad_norm": 0.522654116153717,
      "learning_rate": 0.00017809751539726824,
      "loss": 0.842085599899292,
      "step": 3948
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.43468809127807617,
      "learning_rate": 0.00017806750914730777,
      "loss": 0.6917972564697266,
      "step": 3950
    },
    {
      "epoch": 1.667510548523207,
      "grad_norm": 0.4071558117866516,
      "learning_rate": 0.00017803748488867224,
      "loss": 0.6676424741744995,
      "step": 3952
    },
    {
      "epoch": 1.6683544303797468,
      "grad_norm": 0.4478702247142792,
      "learning_rate": 0.00017800744262828772,
      "loss": 0.7563748359680176,
      "step": 3954
    },
    {
      "epoch": 1.6691983122362868,
      "grad_norm": 0.42986053228378296,
      "learning_rate": 0.00017797738237308432,
      "loss": 0.685714066028595,
      "step": 3956
    },
    {
      "epoch": 1.6700421940928272,
      "grad_norm": 0.4410569667816162,
      "learning_rate": 0.0001779473041299964,
      "loss": 0.7753605842590332,
      "step": 3958
    },
    {
      "epoch": 1.6708860759493671,
      "grad_norm": 0.44055965542793274,
      "learning_rate": 0.00017791720790596242,
      "loss": 0.7826018333435059,
      "step": 3960
    },
    {
      "epoch": 1.671729957805907,
      "grad_norm": 0.4660222828388214,
      "learning_rate": 0.00017788709370792502,
      "loss": 0.7012629508972168,
      "step": 3962
    },
    {
      "epoch": 1.6725738396624472,
      "grad_norm": 0.3655732274055481,
      "learning_rate": 0.00017785696154283093,
      "loss": 0.6647007465362549,
      "step": 3964
    },
    {
      "epoch": 1.6734177215189874,
      "grad_norm": 0.45735979080200195,
      "learning_rate": 0.0001778268114176311,
      "loss": 0.7238346338272095,
      "step": 3966
    },
    {
      "epoch": 1.6742616033755273,
      "grad_norm": 0.4894043207168579,
      "learning_rate": 0.00017779664333928053,
      "loss": 0.7595300078392029,
      "step": 3968
    },
    {
      "epoch": 1.6751054852320675,
      "grad_norm": 0.3613647222518921,
      "learning_rate": 0.00017776645731473848,
      "loss": 0.6534504294395447,
      "step": 3970
    },
    {
      "epoch": 1.6759493670886076,
      "grad_norm": 0.4402320683002472,
      "learning_rate": 0.00017773625335096828,
      "loss": 0.7699148058891296,
      "step": 3972
    },
    {
      "epoch": 1.6767932489451476,
      "grad_norm": 0.4391469955444336,
      "learning_rate": 0.0001777060314549374,
      "loss": 0.771800696849823,
      "step": 3974
    },
    {
      "epoch": 1.6776371308016877,
      "grad_norm": 0.41348180174827576,
      "learning_rate": 0.00017767579163361735,
      "loss": 0.6957393884658813,
      "step": 3976
    },
    {
      "epoch": 1.678481012658228,
      "grad_norm": 0.4115046560764313,
      "learning_rate": 0.00017764553389398407,
      "loss": 0.6666664481163025,
      "step": 3978
    },
    {
      "epoch": 1.6793248945147679,
      "grad_norm": 0.44647306203842163,
      "learning_rate": 0.00017761525824301725,
      "loss": 0.7364352345466614,
      "step": 3980
    },
    {
      "epoch": 1.680168776371308,
      "grad_norm": 0.424234002828598,
      "learning_rate": 0.00017758496468770103,
      "loss": 0.7229774594306946,
      "step": 3982
    },
    {
      "epoch": 1.6810126582278482,
      "grad_norm": 0.4850127696990967,
      "learning_rate": 0.00017755465323502346,
      "loss": 0.6992678642272949,
      "step": 3984
    },
    {
      "epoch": 1.6818565400843881,
      "grad_norm": 0.44637173414230347,
      "learning_rate": 0.00017752432389197688,
      "loss": 0.6957634091377258,
      "step": 3986
    },
    {
      "epoch": 1.6827004219409283,
      "grad_norm": 0.477393239736557,
      "learning_rate": 0.00017749397666555768,
      "loss": 0.6842859983444214,
      "step": 3988
    },
    {
      "epoch": 1.6835443037974684,
      "grad_norm": 0.3634146451950073,
      "learning_rate": 0.00017746361156276632,
      "loss": 0.6478199362754822,
      "step": 3990
    },
    {
      "epoch": 1.6843881856540084,
      "grad_norm": 0.4806389808654785,
      "learning_rate": 0.00017743322859060752,
      "loss": 0.7166973352432251,
      "step": 3992
    },
    {
      "epoch": 1.6852320675105485,
      "grad_norm": 0.4273380935192108,
      "learning_rate": 0.00017740282775609,
      "loss": 0.6624643206596375,
      "step": 3994
    },
    {
      "epoch": 1.6860759493670887,
      "grad_norm": 0.4340716600418091,
      "learning_rate": 0.0001773724090662267,
      "loss": 0.6408489346504211,
      "step": 3996
    },
    {
      "epoch": 1.6869198312236287,
      "grad_norm": 0.50480717420578,
      "learning_rate": 0.00017734197252803458,
      "loss": 0.8096797466278076,
      "step": 3998
    },
    {
      "epoch": 1.6877637130801688,
      "grad_norm": 0.4549327790737152,
      "learning_rate": 0.00017731151814853475,
      "loss": 0.6902434825897217,
      "step": 4000
    },
    {
      "epoch": 1.6877637130801688,
      "eval_loss": 0.7721371650695801,
      "eval_runtime": 668.395,
      "eval_samples_per_second": 3.152,
      "eval_steps_per_second": 3.152,
      "step": 4000
    },
    {
      "epoch": 1.688607594936709,
      "grad_norm": 0.38909077644348145,
      "learning_rate": 0.00017728104593475247,
      "loss": 0.6510542035102844,
      "step": 4002
    },
    {
      "epoch": 1.689451476793249,
      "grad_norm": 0.444608598947525,
      "learning_rate": 0.00017725055589371715,
      "loss": 0.7331066727638245,
      "step": 4004
    },
    {
      "epoch": 1.690295358649789,
      "grad_norm": 0.3364178538322449,
      "learning_rate": 0.0001772200480324622,
      "loss": 0.5950609445571899,
      "step": 4006
    },
    {
      "epoch": 1.6911392405063292,
      "grad_norm": 0.37264227867126465,
      "learning_rate": 0.0001771895223580252,
      "loss": 0.7024590969085693,
      "step": 4008
    },
    {
      "epoch": 1.6919831223628692,
      "grad_norm": 0.3576899766921997,
      "learning_rate": 0.00017715897887744784,
      "loss": 0.6620895266532898,
      "step": 4010
    },
    {
      "epoch": 1.6928270042194091,
      "grad_norm": 0.45855066180229187,
      "learning_rate": 0.00017712841759777591,
      "loss": 0.6726759076118469,
      "step": 4012
    },
    {
      "epoch": 1.6936708860759495,
      "grad_norm": 0.44610634446144104,
      "learning_rate": 0.00017709783852605933,
      "loss": 0.6550953984260559,
      "step": 4014
    },
    {
      "epoch": 1.6945147679324895,
      "grad_norm": 0.4262036681175232,
      "learning_rate": 0.00017706724166935208,
      "loss": 0.7338476777076721,
      "step": 4016
    },
    {
      "epoch": 1.6953586497890294,
      "grad_norm": 0.44584009051322937,
      "learning_rate": 0.0001770366270347123,
      "loss": 0.6785868406295776,
      "step": 4018
    },
    {
      "epoch": 1.6962025316455698,
      "grad_norm": 0.44828134775161743,
      "learning_rate": 0.0001770059946292022,
      "loss": 0.7113003134727478,
      "step": 4020
    },
    {
      "epoch": 1.6970464135021097,
      "grad_norm": 0.39716270565986633,
      "learning_rate": 0.00017697534445988803,
      "loss": 0.6420866847038269,
      "step": 4022
    },
    {
      "epoch": 1.6978902953586497,
      "grad_norm": 0.43546608090400696,
      "learning_rate": 0.00017694467653384024,
      "loss": 0.8087385892868042,
      "step": 4024
    },
    {
      "epoch": 1.6987341772151898,
      "grad_norm": 0.3698647618293762,
      "learning_rate": 0.00017691399085813334,
      "loss": 0.6378461718559265,
      "step": 4026
    },
    {
      "epoch": 1.69957805907173,
      "grad_norm": 0.4256688058376312,
      "learning_rate": 0.0001768832874398459,
      "loss": 0.6504215002059937,
      "step": 4028
    },
    {
      "epoch": 1.70042194092827,
      "grad_norm": 0.4014805555343628,
      "learning_rate": 0.00017685256628606063,
      "loss": 0.6648795008659363,
      "step": 4030
    },
    {
      "epoch": 1.70126582278481,
      "grad_norm": 0.43924233317375183,
      "learning_rate": 0.00017682182740386427,
      "loss": 0.6905859112739563,
      "step": 4032
    },
    {
      "epoch": 1.7021097046413503,
      "grad_norm": 0.43565094470977783,
      "learning_rate": 0.00017679107080034774,
      "loss": 0.7800544500350952,
      "step": 4034
    },
    {
      "epoch": 1.7029535864978902,
      "grad_norm": 0.4681089520454407,
      "learning_rate": 0.00017676029648260597,
      "loss": 0.7487648725509644,
      "step": 4036
    },
    {
      "epoch": 1.7037974683544304,
      "grad_norm": 0.41400185227394104,
      "learning_rate": 0.00017672950445773804,
      "loss": 0.7374032735824585,
      "step": 4038
    },
    {
      "epoch": 1.7046413502109705,
      "grad_norm": 0.5120159983634949,
      "learning_rate": 0.00017669869473284702,
      "loss": 0.7539847493171692,
      "step": 4040
    },
    {
      "epoch": 1.7054852320675105,
      "grad_norm": 0.4043315052986145,
      "learning_rate": 0.00017666786731504013,
      "loss": 0.7029932737350464,
      "step": 4042
    },
    {
      "epoch": 1.7063291139240506,
      "grad_norm": 0.462801992893219,
      "learning_rate": 0.00017663702221142874,
      "loss": 0.6464276313781738,
      "step": 4044
    },
    {
      "epoch": 1.7071729957805908,
      "grad_norm": 0.4751932621002197,
      "learning_rate": 0.00017660615942912813,
      "loss": 0.7646113634109497,
      "step": 4046
    },
    {
      "epoch": 1.7080168776371307,
      "grad_norm": 0.41720855236053467,
      "learning_rate": 0.0001765752789752578,
      "loss": 0.7191748023033142,
      "step": 4048
    },
    {
      "epoch": 1.7088607594936709,
      "grad_norm": 0.40235280990600586,
      "learning_rate": 0.00017654438085694128,
      "loss": 0.6946488618850708,
      "step": 4050
    },
    {
      "epoch": 1.709704641350211,
      "grad_norm": 0.4385916292667389,
      "learning_rate": 0.00017651346508130612,
      "loss": 0.7655195593833923,
      "step": 4052
    },
    {
      "epoch": 1.710548523206751,
      "grad_norm": 0.4192262887954712,
      "learning_rate": 0.00017648253165548406,
      "loss": 0.7192418575286865,
      "step": 4054
    },
    {
      "epoch": 1.7113924050632912,
      "grad_norm": 0.4348951280117035,
      "learning_rate": 0.00017645158058661082,
      "loss": 0.6501081585884094,
      "step": 4056
    },
    {
      "epoch": 1.7122362869198313,
      "grad_norm": 0.4178772270679474,
      "learning_rate": 0.0001764206118818262,
      "loss": 0.741439163684845,
      "step": 4058
    },
    {
      "epoch": 1.7130801687763713,
      "grad_norm": 0.46996670961380005,
      "learning_rate": 0.00017638962554827414,
      "loss": 0.7087798714637756,
      "step": 4060
    },
    {
      "epoch": 1.7139240506329114,
      "grad_norm": 0.4775761365890503,
      "learning_rate": 0.00017635862159310253,
      "loss": 0.6716644167900085,
      "step": 4062
    },
    {
      "epoch": 1.7147679324894516,
      "grad_norm": 0.4094069004058838,
      "learning_rate": 0.00017632760002346345,
      "loss": 0.6630500555038452,
      "step": 4064
    },
    {
      "epoch": 1.7156118143459915,
      "grad_norm": 0.3968847393989563,
      "learning_rate": 0.0001762965608465129,
      "loss": 0.7678145170211792,
      "step": 4066
    },
    {
      "epoch": 1.7164556962025317,
      "grad_norm": 0.43751946091651917,
      "learning_rate": 0.0001762655040694111,
      "loss": 0.6981875896453857,
      "step": 4068
    },
    {
      "epoch": 1.7172995780590719,
      "grad_norm": 0.44504284858703613,
      "learning_rate": 0.00017623442969932218,
      "loss": 0.6919799447059631,
      "step": 4070
    },
    {
      "epoch": 1.7181434599156118,
      "grad_norm": 0.36895114183425903,
      "learning_rate": 0.00017620333774341447,
      "loss": 0.6310772895812988,
      "step": 4072
    },
    {
      "epoch": 1.7189873417721517,
      "grad_norm": 0.4312762916088104,
      "learning_rate": 0.00017617222820886022,
      "loss": 0.6954092383384705,
      "step": 4074
    },
    {
      "epoch": 1.7198312236286921,
      "grad_norm": 0.40909886360168457,
      "learning_rate": 0.00017614110110283587,
      "loss": 0.6973698139190674,
      "step": 4076
    },
    {
      "epoch": 1.720675105485232,
      "grad_norm": 0.43111470341682434,
      "learning_rate": 0.0001761099564325218,
      "loss": 0.6775513291358948,
      "step": 4078
    },
    {
      "epoch": 1.721518987341772,
      "grad_norm": 0.45573189854621887,
      "learning_rate": 0.0001760787942051025,
      "loss": 0.6889033913612366,
      "step": 4080
    },
    {
      "epoch": 1.7223628691983124,
      "grad_norm": 0.44934743642807007,
      "learning_rate": 0.0001760476144277665,
      "loss": 0.6894892454147339,
      "step": 4082
    },
    {
      "epoch": 1.7232067510548523,
      "grad_norm": 0.39716506004333496,
      "learning_rate": 0.0001760164171077064,
      "loss": 0.6841691732406616,
      "step": 4084
    },
    {
      "epoch": 1.7240506329113923,
      "grad_norm": 0.4486255645751953,
      "learning_rate": 0.00017598520225211876,
      "loss": 0.7197495102882385,
      "step": 4086
    },
    {
      "epoch": 1.7248945147679327,
      "grad_norm": 0.40130025148391724,
      "learning_rate": 0.00017595396986820432,
      "loss": 0.7388272881507874,
      "step": 4088
    },
    {
      "epoch": 1.7257383966244726,
      "grad_norm": 0.40419334173202515,
      "learning_rate": 0.0001759227199631677,
      "loss": 0.7447546720504761,
      "step": 4090
    },
    {
      "epoch": 1.7265822784810125,
      "grad_norm": 0.39778804779052734,
      "learning_rate": 0.00017589145254421774,
      "loss": 0.6348387598991394,
      "step": 4092
    },
    {
      "epoch": 1.7274261603375527,
      "grad_norm": 0.3934648036956787,
      "learning_rate": 0.0001758601676185672,
      "loss": 0.6813296675682068,
      "step": 4094
    },
    {
      "epoch": 1.7282700421940929,
      "grad_norm": 0.4080725908279419,
      "learning_rate": 0.0001758288651934329,
      "loss": 0.6369423270225525,
      "step": 4096
    },
    {
      "epoch": 1.7291139240506328,
      "grad_norm": 0.5186997652053833,
      "learning_rate": 0.00017579754527603575,
      "loss": 0.6664180159568787,
      "step": 4098
    },
    {
      "epoch": 1.729957805907173,
      "grad_norm": 0.45290765166282654,
      "learning_rate": 0.0001757662078736006,
      "loss": 0.7181394696235657,
      "step": 4100
    },
    {
      "epoch": 1.729957805907173,
      "eval_loss": 0.7690847516059875,
      "eval_runtime": 673.6323,
      "eval_samples_per_second": 3.128,
      "eval_steps_per_second": 3.128,
      "step": 4100
    },
    {
      "epoch": 1.7308016877637131,
      "grad_norm": 0.45677125453948975,
      "learning_rate": 0.00017573485299335643,
      "loss": 0.6850123405456543,
      "step": 4102
    },
    {
      "epoch": 1.731645569620253,
      "grad_norm": 0.4854084253311157,
      "learning_rate": 0.0001757034806425362,
      "loss": 0.7225809693336487,
      "step": 4104
    },
    {
      "epoch": 1.7324894514767932,
      "grad_norm": 0.486583411693573,
      "learning_rate": 0.0001756720908283769,
      "loss": 0.7303882837295532,
      "step": 4106
    },
    {
      "epoch": 1.7333333333333334,
      "grad_norm": 0.4609545171260834,
      "learning_rate": 0.00017564068355811952,
      "loss": 0.6789878010749817,
      "step": 4108
    },
    {
      "epoch": 1.7341772151898733,
      "grad_norm": 0.3853047788143158,
      "learning_rate": 0.00017560925883900914,
      "loss": 0.7311062812805176,
      "step": 4110
    },
    {
      "epoch": 1.7350210970464135,
      "grad_norm": 0.41957035660743713,
      "learning_rate": 0.00017557781667829487,
      "loss": 0.7106070518493652,
      "step": 4112
    },
    {
      "epoch": 1.7358649789029537,
      "grad_norm": 0.37419262528419495,
      "learning_rate": 0.0001755463570832298,
      "loss": 0.6345783472061157,
      "step": 4114
    },
    {
      "epoch": 1.7367088607594936,
      "grad_norm": 0.5050614476203918,
      "learning_rate": 0.00017551488006107104,
      "loss": 0.7923876047134399,
      "step": 4116
    },
    {
      "epoch": 1.7375527426160338,
      "grad_norm": 0.49726125597953796,
      "learning_rate": 0.00017548338561907976,
      "loss": 0.7502455115318298,
      "step": 4118
    },
    {
      "epoch": 1.738396624472574,
      "grad_norm": 0.38956591486930847,
      "learning_rate": 0.00017545187376452105,
      "loss": 0.6333624720573425,
      "step": 4120
    },
    {
      "epoch": 1.7392405063291139,
      "grad_norm": 0.430318146944046,
      "learning_rate": 0.0001754203445046642,
      "loss": 0.6884907484054565,
      "step": 4122
    },
    {
      "epoch": 1.740084388185654,
      "grad_norm": 0.39826440811157227,
      "learning_rate": 0.0001753887978467823,
      "loss": 0.7345985174179077,
      "step": 4124
    },
    {
      "epoch": 1.7409282700421942,
      "grad_norm": 0.4263492822647095,
      "learning_rate": 0.00017535723379815267,
      "loss": 0.6537752151489258,
      "step": 4126
    },
    {
      "epoch": 1.7417721518987341,
      "grad_norm": 0.4012296199798584,
      "learning_rate": 0.0001753256523660564,
      "loss": 0.6368000507354736,
      "step": 4128
    },
    {
      "epoch": 1.7426160337552743,
      "grad_norm": 0.3881204426288605,
      "learning_rate": 0.0001752940535577788,
      "loss": 0.6038334369659424,
      "step": 4130
    },
    {
      "epoch": 1.7434599156118145,
      "grad_norm": 0.38410526514053345,
      "learning_rate": 0.0001752624373806091,
      "loss": 0.6657052636146545,
      "step": 4132
    },
    {
      "epoch": 1.7443037974683544,
      "grad_norm": 0.3970552980899811,
      "learning_rate": 0.00017523080384184057,
      "loss": 0.6518114805221558,
      "step": 4134
    },
    {
      "epoch": 1.7451476793248946,
      "grad_norm": 0.37542012333869934,
      "learning_rate": 0.0001751991529487704,
      "loss": 0.609853208065033,
      "step": 4136
    },
    {
      "epoch": 1.7459915611814347,
      "grad_norm": 0.49812132120132446,
      "learning_rate": 0.00017516748470869988,
      "loss": 0.7356346845626831,
      "step": 4138
    },
    {
      "epoch": 1.7468354430379747,
      "grad_norm": 0.48197710514068604,
      "learning_rate": 0.00017513579912893426,
      "loss": 0.7198674082756042,
      "step": 4140
    },
    {
      "epoch": 1.7476793248945146,
      "grad_norm": 0.38266444206237793,
      "learning_rate": 0.0001751040962167828,
      "loss": 0.6841102242469788,
      "step": 4142
    },
    {
      "epoch": 1.748523206751055,
      "grad_norm": 0.4165695309638977,
      "learning_rate": 0.0001750723759795587,
      "loss": 0.7348533272743225,
      "step": 4144
    },
    {
      "epoch": 1.749367088607595,
      "grad_norm": 0.4414960443973541,
      "learning_rate": 0.0001750406384245793,
      "loss": 0.7344526648521423,
      "step": 4146
    },
    {
      "epoch": 1.7502109704641349,
      "grad_norm": 0.4324318468570709,
      "learning_rate": 0.00017500888355916576,
      "loss": 0.7047654986381531,
      "step": 4148
    },
    {
      "epoch": 1.7510548523206753,
      "grad_norm": 0.44670364260673523,
      "learning_rate": 0.00017497711139064336,
      "loss": 0.7317671179771423,
      "step": 4150
    },
    {
      "epoch": 1.7518987341772152,
      "grad_norm": 0.43074679374694824,
      "learning_rate": 0.00017494532192634138,
      "loss": 0.7447407245635986,
      "step": 4152
    },
    {
      "epoch": 1.7527426160337551,
      "grad_norm": 0.43057894706726074,
      "learning_rate": 0.00017491351517359292,
      "loss": 0.7352449893951416,
      "step": 4154
    },
    {
      "epoch": 1.7535864978902953,
      "grad_norm": 0.49488556385040283,
      "learning_rate": 0.00017488169113973528,
      "loss": 0.7244091033935547,
      "step": 4156
    },
    {
      "epoch": 1.7544303797468355,
      "grad_norm": 0.4565380811691284,
      "learning_rate": 0.0001748498498321096,
      "loss": 0.7515795230865479,
      "step": 4158
    },
    {
      "epoch": 1.7552742616033754,
      "grad_norm": 0.45722341537475586,
      "learning_rate": 0.0001748179912580611,
      "loss": 0.7451042532920837,
      "step": 4160
    },
    {
      "epoch": 1.7561181434599156,
      "grad_norm": 0.47247326374053955,
      "learning_rate": 0.0001747861154249389,
      "loss": 0.7133217453956604,
      "step": 4162
    },
    {
      "epoch": 1.7569620253164557,
      "grad_norm": 0.48307132720947266,
      "learning_rate": 0.00017475422234009623,
      "loss": 0.643742561340332,
      "step": 4164
    },
    {
      "epoch": 1.7578059071729957,
      "grad_norm": 0.49163761734962463,
      "learning_rate": 0.00017472231201089012,
      "loss": 0.7587857842445374,
      "step": 4166
    },
    {
      "epoch": 1.7586497890295358,
      "grad_norm": 0.4726962149143219,
      "learning_rate": 0.00017469038444468165,
      "loss": 0.6980416774749756,
      "step": 4168
    },
    {
      "epoch": 1.759493670886076,
      "grad_norm": 0.4192392826080322,
      "learning_rate": 0.00017465843964883598,
      "loss": 0.6929903626441956,
      "step": 4170
    },
    {
      "epoch": 1.760337552742616,
      "grad_norm": 0.43000563979148865,
      "learning_rate": 0.00017462647763072216,
      "loss": 0.7076222896575928,
      "step": 4172
    },
    {
      "epoch": 1.761181434599156,
      "grad_norm": 0.45402681827545166,
      "learning_rate": 0.00017459449839771313,
      "loss": 0.7260748147964478,
      "step": 4174
    },
    {
      "epoch": 1.7620253164556963,
      "grad_norm": 0.4077165126800537,
      "learning_rate": 0.00017456250195718595,
      "loss": 0.6901930570602417,
      "step": 4176
    },
    {
      "epoch": 1.7628691983122362,
      "grad_norm": 0.4167994558811188,
      "learning_rate": 0.00017453048831652157,
      "loss": 0.7085300087928772,
      "step": 4178
    },
    {
      "epoch": 1.7637130801687764,
      "grad_norm": 0.45262131094932556,
      "learning_rate": 0.00017449845748310493,
      "loss": 0.7646799087524414,
      "step": 4180
    },
    {
      "epoch": 1.7645569620253165,
      "grad_norm": 0.4639943540096283,
      "learning_rate": 0.0001744664094643249,
      "loss": 0.7847923040390015,
      "step": 4182
    },
    {
      "epoch": 1.7654008438818565,
      "grad_norm": 0.33605465292930603,
      "learning_rate": 0.00017443434426757439,
      "loss": 0.7192286252975464,
      "step": 4184
    },
    {
      "epoch": 1.7662447257383966,
      "grad_norm": 0.4036388099193573,
      "learning_rate": 0.00017440226190025015,
      "loss": 0.6554746627807617,
      "step": 4186
    },
    {
      "epoch": 1.7670886075949368,
      "grad_norm": 0.45648789405822754,
      "learning_rate": 0.00017437016236975303,
      "loss": 0.6433794498443604,
      "step": 4188
    },
    {
      "epoch": 1.7679324894514767,
      "grad_norm": 0.38929006457328796,
      "learning_rate": 0.00017433804568348776,
      "loss": 0.6608775854110718,
      "step": 4190
    },
    {
      "epoch": 1.768776371308017,
      "grad_norm": 0.37158843874931335,
      "learning_rate": 0.00017430591184886308,
      "loss": 0.6470816135406494,
      "step": 4192
    },
    {
      "epoch": 1.769620253164557,
      "grad_norm": 0.39842307567596436,
      "learning_rate": 0.00017427376087329158,
      "loss": 0.6825124025344849,
      "step": 4194
    },
    {
      "epoch": 1.770464135021097,
      "grad_norm": 0.44220465421676636,
      "learning_rate": 0.00017424159276418987,
      "loss": 0.7641696333885193,
      "step": 4196
    },
    {
      "epoch": 1.7713080168776372,
      "grad_norm": 0.44530072808265686,
      "learning_rate": 0.0001742094075289786,
      "loss": 0.7783681154251099,
      "step": 4198
    },
    {
      "epoch": 1.7721518987341773,
      "grad_norm": 0.4497349262237549,
      "learning_rate": 0.00017417720517508216,
      "loss": 0.6718224883079529,
      "step": 4200
    },
    {
      "epoch": 1.7721518987341773,
      "eval_loss": 0.7676366567611694,
      "eval_runtime": 687.9619,
      "eval_samples_per_second": 3.063,
      "eval_steps_per_second": 3.063,
      "step": 4200
    },
    {
      "epoch": 1.7729957805907173,
      "grad_norm": 0.3857066333293915,
      "learning_rate": 0.00017414498570992914,
      "loss": 0.7050814032554626,
      "step": 4202
    },
    {
      "epoch": 1.7738396624472574,
      "grad_norm": 0.4533625543117523,
      "learning_rate": 0.00017411274914095188,
      "loss": 0.7222742438316345,
      "step": 4204
    },
    {
      "epoch": 1.7746835443037976,
      "grad_norm": 0.40805840492248535,
      "learning_rate": 0.00017408049547558676,
      "loss": 0.6434906125068665,
      "step": 4206
    },
    {
      "epoch": 1.7755274261603375,
      "grad_norm": 0.5041740536689758,
      "learning_rate": 0.00017404822472127406,
      "loss": 0.686283528804779,
      "step": 4208
    },
    {
      "epoch": 1.7763713080168775,
      "grad_norm": 0.41846802830696106,
      "learning_rate": 0.00017401593688545807,
      "loss": 0.6785043478012085,
      "step": 4210
    },
    {
      "epoch": 1.7772151898734179,
      "grad_norm": 0.4696303606033325,
      "learning_rate": 0.00017398363197558694,
      "loss": 0.7566665410995483,
      "step": 4212
    },
    {
      "epoch": 1.7780590717299578,
      "grad_norm": 0.3731461763381958,
      "learning_rate": 0.0001739513099991128,
      "loss": 0.6178455948829651,
      "step": 4214
    },
    {
      "epoch": 1.7789029535864977,
      "grad_norm": 0.48098450899124146,
      "learning_rate": 0.00017391897096349167,
      "loss": 0.771265983581543,
      "step": 4216
    },
    {
      "epoch": 1.7797468354430381,
      "grad_norm": 0.4164000451564789,
      "learning_rate": 0.0001738866148761836,
      "loss": 0.6372597813606262,
      "step": 4218
    },
    {
      "epoch": 1.780590717299578,
      "grad_norm": 0.4490415155887604,
      "learning_rate": 0.00017385424174465251,
      "loss": 0.7213301658630371,
      "step": 4220
    },
    {
      "epoch": 1.781434599156118,
      "grad_norm": 0.44518229365348816,
      "learning_rate": 0.00017382185157636623,
      "loss": 0.7575726509094238,
      "step": 4222
    },
    {
      "epoch": 1.7822784810126582,
      "grad_norm": 0.34899434447288513,
      "learning_rate": 0.00017378944437879658,
      "loss": 0.6473780274391174,
      "step": 4224
    },
    {
      "epoch": 1.7831223628691983,
      "grad_norm": 0.4068683087825775,
      "learning_rate": 0.00017375702015941924,
      "loss": 0.7238336205482483,
      "step": 4226
    },
    {
      "epoch": 1.7839662447257383,
      "grad_norm": 0.4025551974773407,
      "learning_rate": 0.0001737245789257139,
      "loss": 0.7797979116439819,
      "step": 4228
    },
    {
      "epoch": 1.7848101265822784,
      "grad_norm": 0.35764896869659424,
      "learning_rate": 0.00017369212068516412,
      "loss": 0.6304885149002075,
      "step": 4230
    },
    {
      "epoch": 1.7856540084388186,
      "grad_norm": 0.43337100744247437,
      "learning_rate": 0.00017365964544525738,
      "loss": 0.6606637835502625,
      "step": 4232
    },
    {
      "epoch": 1.7864978902953585,
      "grad_norm": 0.4630814492702484,
      "learning_rate": 0.0001736271532134851,
      "loss": 0.712163507938385,
      "step": 4234
    },
    {
      "epoch": 1.7873417721518987,
      "grad_norm": 0.38714799284935,
      "learning_rate": 0.00017359464399734255,
      "loss": 0.6649466753005981,
      "step": 4236
    },
    {
      "epoch": 1.7881856540084389,
      "grad_norm": 0.38999977707862854,
      "learning_rate": 0.0001735621178043291,
      "loss": 0.6223326921463013,
      "step": 4238
    },
    {
      "epoch": 1.7890295358649788,
      "grad_norm": 0.4736211597919464,
      "learning_rate": 0.00017352957464194786,
      "loss": 0.7207517027854919,
      "step": 4240
    },
    {
      "epoch": 1.789873417721519,
      "grad_norm": 0.423476904630661,
      "learning_rate": 0.00017349701451770588,
      "loss": 0.7203661203384399,
      "step": 4242
    },
    {
      "epoch": 1.7907172995780591,
      "grad_norm": 0.4487479627132416,
      "learning_rate": 0.0001734644374391142,
      "loss": 0.709998607635498,
      "step": 4244
    },
    {
      "epoch": 1.791561181434599,
      "grad_norm": 0.43721267580986023,
      "learning_rate": 0.00017343184341368773,
      "loss": 0.7079582214355469,
      "step": 4246
    },
    {
      "epoch": 1.7924050632911392,
      "grad_norm": 0.426864892244339,
      "learning_rate": 0.00017339923244894524,
      "loss": 0.6772971749305725,
      "step": 4248
    },
    {
      "epoch": 1.7932489451476794,
      "grad_norm": 0.3580208420753479,
      "learning_rate": 0.0001733666045524095,
      "loss": 0.6882370710372925,
      "step": 4250
    },
    {
      "epoch": 1.7940928270042193,
      "grad_norm": 0.487248957157135,
      "learning_rate": 0.00017333395973160714,
      "loss": 0.7534610629081726,
      "step": 4252
    },
    {
      "epoch": 1.7949367088607595,
      "grad_norm": 0.44908860325813293,
      "learning_rate": 0.00017330129799406866,
      "loss": 0.6897269487380981,
      "step": 4254
    },
    {
      "epoch": 1.7957805907172997,
      "grad_norm": 0.43617817759513855,
      "learning_rate": 0.00017326861934732852,
      "loss": 0.7081538438796997,
      "step": 4256
    },
    {
      "epoch": 1.7966244725738396,
      "grad_norm": 0.428666353225708,
      "learning_rate": 0.00017323592379892504,
      "loss": 0.6852753758430481,
      "step": 4258
    },
    {
      "epoch": 1.7974683544303798,
      "grad_norm": 0.4522199034690857,
      "learning_rate": 0.00017320321135640045,
      "loss": 0.7463182210922241,
      "step": 4260
    },
    {
      "epoch": 1.79831223628692,
      "grad_norm": 0.38632410764694214,
      "learning_rate": 0.00017317048202730088,
      "loss": 0.6643774509429932,
      "step": 4262
    },
    {
      "epoch": 1.7991561181434599,
      "grad_norm": 0.41171637177467346,
      "learning_rate": 0.00017313773581917642,
      "loss": 0.6726668477058411,
      "step": 4264
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.398520290851593,
      "learning_rate": 0.0001731049727395809,
      "loss": 0.6278629302978516,
      "step": 4266
    },
    {
      "epoch": 1.8008438818565402,
      "grad_norm": 0.4000356197357178,
      "learning_rate": 0.0001730721927960722,
      "loss": 0.5823352336883545,
      "step": 4268
    },
    {
      "epoch": 1.8016877637130801,
      "grad_norm": 0.47376710176467896,
      "learning_rate": 0.000173039395996212,
      "loss": 0.7492824196815491,
      "step": 4270
    },
    {
      "epoch": 1.80253164556962,
      "grad_norm": 0.4624378979206085,
      "learning_rate": 0.00017300658234756588,
      "loss": 0.7630324363708496,
      "step": 4272
    },
    {
      "epoch": 1.8033755274261605,
      "grad_norm": 0.4178096354007721,
      "learning_rate": 0.00017297375185770336,
      "loss": 0.6484803557395935,
      "step": 4274
    },
    {
      "epoch": 1.8042194092827004,
      "grad_norm": 0.511215329170227,
      "learning_rate": 0.00017294090453419774,
      "loss": 0.776732325553894,
      "step": 4276
    },
    {
      "epoch": 1.8050632911392404,
      "grad_norm": 0.44643548130989075,
      "learning_rate": 0.00017290804038462633,
      "loss": 0.6801077723503113,
      "step": 4278
    },
    {
      "epoch": 1.8059071729957807,
      "grad_norm": 0.5090142488479614,
      "learning_rate": 0.0001728751594165702,
      "loss": 0.8024200797080994,
      "step": 4280
    },
    {
      "epoch": 1.8067510548523207,
      "grad_norm": 0.45888981223106384,
      "learning_rate": 0.00017284226163761436,
      "loss": 0.7810231447219849,
      "step": 4282
    },
    {
      "epoch": 1.8075949367088606,
      "grad_norm": 0.3985820710659027,
      "learning_rate": 0.0001728093470553478,
      "loss": 0.6768189072608948,
      "step": 4284
    },
    {
      "epoch": 1.808438818565401,
      "grad_norm": 0.3988003730773926,
      "learning_rate": 0.00017277641567736316,
      "loss": 0.6093943119049072,
      "step": 4286
    },
    {
      "epoch": 1.809282700421941,
      "grad_norm": 0.46131962537765503,
      "learning_rate": 0.0001727434675112571,
      "loss": 0.6836619973182678,
      "step": 4288
    },
    {
      "epoch": 1.810126582278481,
      "grad_norm": 0.42959487438201904,
      "learning_rate": 0.0001727105025646302,
      "loss": 0.7144147157669067,
      "step": 4290
    },
    {
      "epoch": 1.810970464135021,
      "grad_norm": 0.4110259413719177,
      "learning_rate": 0.00017267752084508675,
      "loss": 0.7190625667572021,
      "step": 4292
    },
    {
      "epoch": 1.8118143459915612,
      "grad_norm": 0.4501377046108246,
      "learning_rate": 0.00017264452236023505,
      "loss": 0.7272495031356812,
      "step": 4294
    },
    {
      "epoch": 1.8126582278481012,
      "grad_norm": 0.467817097902298,
      "learning_rate": 0.0001726115071176872,
      "loss": 0.758166491985321,
      "step": 4296
    },
    {
      "epoch": 1.8135021097046413,
      "grad_norm": 0.42394939064979553,
      "learning_rate": 0.0001725784751250592,
      "loss": 0.6712231040000916,
      "step": 4298
    },
    {
      "epoch": 1.8143459915611815,
      "grad_norm": 0.37668925523757935,
      "learning_rate": 0.00017254542638997088,
      "loss": 0.5999719500541687,
      "step": 4300
    },
    {
      "epoch": 1.8143459915611815,
      "eval_loss": 0.7672964930534363,
      "eval_runtime": 688.4249,
      "eval_samples_per_second": 3.061,
      "eval_steps_per_second": 3.061,
      "step": 4300
    },
    {
      "epoch": 1.8151898734177214,
      "grad_norm": 0.44964465498924255,
      "learning_rate": 0.00017251236092004596,
      "loss": 0.7188607454299927,
      "step": 4302
    },
    {
      "epoch": 1.8160337552742616,
      "grad_norm": 0.4108492434024811,
      "learning_rate": 0.000172479278722912,
      "loss": 0.707834005355835,
      "step": 4304
    },
    {
      "epoch": 1.8168776371308017,
      "grad_norm": 0.4455305337905884,
      "learning_rate": 0.00017244617980620043,
      "loss": 0.6915075182914734,
      "step": 4306
    },
    {
      "epoch": 1.8177215189873417,
      "grad_norm": 0.3977123200893402,
      "learning_rate": 0.00017241306417754655,
      "loss": 0.6591874361038208,
      "step": 4308
    },
    {
      "epoch": 1.8185654008438819,
      "grad_norm": 0.4028434157371521,
      "learning_rate": 0.00017237993184458946,
      "loss": 0.6254785060882568,
      "step": 4310
    },
    {
      "epoch": 1.819409282700422,
      "grad_norm": 0.41024482250213623,
      "learning_rate": 0.00017234678281497217,
      "loss": 0.6968662142753601,
      "step": 4312
    },
    {
      "epoch": 1.820253164556962,
      "grad_norm": 0.45941361784935,
      "learning_rate": 0.00017231361709634153,
      "loss": 0.6535647511482239,
      "step": 4314
    },
    {
      "epoch": 1.8210970464135021,
      "grad_norm": 0.39477071166038513,
      "learning_rate": 0.00017228043469634825,
      "loss": 0.6378563642501831,
      "step": 4316
    },
    {
      "epoch": 1.8219409282700423,
      "grad_norm": 0.403826504945755,
      "learning_rate": 0.00017224723562264687,
      "loss": 0.7021255493164062,
      "step": 4318
    },
    {
      "epoch": 1.8227848101265822,
      "grad_norm": 0.4179201126098633,
      "learning_rate": 0.00017221401988289575,
      "loss": 0.7411118745803833,
      "step": 4320
    },
    {
      "epoch": 1.8236286919831224,
      "grad_norm": 0.4719425141811371,
      "learning_rate": 0.0001721807874847571,
      "loss": 0.7435210943222046,
      "step": 4322
    },
    {
      "epoch": 1.8244725738396625,
      "grad_norm": 0.39946448802948,
      "learning_rate": 0.0001721475384358971,
      "loss": 0.6813794374465942,
      "step": 4324
    },
    {
      "epoch": 1.8253164556962025,
      "grad_norm": 0.4367005527019501,
      "learning_rate": 0.00017211427274398559,
      "loss": 0.6468828320503235,
      "step": 4326
    },
    {
      "epoch": 1.8261603375527427,
      "grad_norm": 0.4078138470649719,
      "learning_rate": 0.00017208099041669632,
      "loss": 0.6628729701042175,
      "step": 4328
    },
    {
      "epoch": 1.8270042194092828,
      "grad_norm": 0.4141235649585724,
      "learning_rate": 0.0001720476914617069,
      "loss": 0.7028043866157532,
      "step": 4330
    },
    {
      "epoch": 1.8278481012658228,
      "grad_norm": 0.448733925819397,
      "learning_rate": 0.00017201437588669878,
      "loss": 0.6710682511329651,
      "step": 4332
    },
    {
      "epoch": 1.828691983122363,
      "grad_norm": 0.5084340572357178,
      "learning_rate": 0.00017198104369935718,
      "loss": 0.792453408241272,
      "step": 4334
    },
    {
      "epoch": 1.829535864978903,
      "grad_norm": 0.43463611602783203,
      "learning_rate": 0.00017194769490737124,
      "loss": 0.7536583542823792,
      "step": 4336
    },
    {
      "epoch": 1.830379746835443,
      "grad_norm": 0.46039044857025146,
      "learning_rate": 0.00017191432951843387,
      "loss": 0.7445555925369263,
      "step": 4338
    },
    {
      "epoch": 1.831223628691983,
      "grad_norm": 0.3894030451774597,
      "learning_rate": 0.0001718809475402418,
      "loss": 0.7003044486045837,
      "step": 4340
    },
    {
      "epoch": 1.8320675105485233,
      "grad_norm": 0.5851747393608093,
      "learning_rate": 0.00017184754898049568,
      "loss": 0.6948950886726379,
      "step": 4342
    },
    {
      "epoch": 1.8329113924050633,
      "grad_norm": 0.40906789898872375,
      "learning_rate": 0.00017181413384689982,
      "loss": 0.675811231136322,
      "step": 4344
    },
    {
      "epoch": 1.8337552742616032,
      "grad_norm": 0.4235765039920807,
      "learning_rate": 0.0001717807021471625,
      "loss": 0.7422580122947693,
      "step": 4346
    },
    {
      "epoch": 1.8345991561181436,
      "grad_norm": 0.3898368775844574,
      "learning_rate": 0.0001717472538889958,
      "loss": 0.7014731168746948,
      "step": 4348
    },
    {
      "epoch": 1.8354430379746836,
      "grad_norm": 0.4122314751148224,
      "learning_rate": 0.00017171378908011553,
      "loss": 0.6952776312828064,
      "step": 4350
    },
    {
      "epoch": 1.8362869198312235,
      "grad_norm": 0.38085612654685974,
      "learning_rate": 0.00017168030772824144,
      "loss": 0.6758598685264587,
      "step": 4352
    },
    {
      "epoch": 1.8371308016877637,
      "grad_norm": 0.43519729375839233,
      "learning_rate": 0.00017164680984109695,
      "loss": 0.7139424085617065,
      "step": 4354
    },
    {
      "epoch": 1.8379746835443038,
      "grad_norm": 0.4404325783252716,
      "learning_rate": 0.0001716132954264095,
      "loss": 0.7125198841094971,
      "step": 4356
    },
    {
      "epoch": 1.8388185654008438,
      "grad_norm": 0.3965512812137604,
      "learning_rate": 0.00017157976449191012,
      "loss": 0.7011314630508423,
      "step": 4358
    },
    {
      "epoch": 1.839662447257384,
      "grad_norm": 0.4273630976676941,
      "learning_rate": 0.0001715462170453338,
      "loss": 0.6485645174980164,
      "step": 4360
    },
    {
      "epoch": 1.840506329113924,
      "grad_norm": 0.4639208912849426,
      "learning_rate": 0.00017151265309441925,
      "loss": 0.6669548153877258,
      "step": 4362
    },
    {
      "epoch": 1.841350210970464,
      "grad_norm": 0.4190906286239624,
      "learning_rate": 0.00017147907264690907,
      "loss": 0.6276374459266663,
      "step": 4364
    },
    {
      "epoch": 1.8421940928270042,
      "grad_norm": 0.4146515130996704,
      "learning_rate": 0.00017144547571054962,
      "loss": 0.5975915193557739,
      "step": 4366
    },
    {
      "epoch": 1.8430379746835444,
      "grad_norm": 0.38717755675315857,
      "learning_rate": 0.00017141186229309105,
      "loss": 0.6536507606506348,
      "step": 4368
    },
    {
      "epoch": 1.8438818565400843,
      "grad_norm": 0.3988541066646576,
      "learning_rate": 0.00017137823240228735,
      "loss": 0.7078962326049805,
      "step": 4370
    },
    {
      "epoch": 1.8447257383966245,
      "grad_norm": 0.43783870339393616,
      "learning_rate": 0.00017134458604589628,
      "loss": 0.6795231699943542,
      "step": 4372
    },
    {
      "epoch": 1.8455696202531646,
      "grad_norm": 0.439636766910553,
      "learning_rate": 0.00017131092323167938,
      "loss": 0.7030490040779114,
      "step": 4374
    },
    {
      "epoch": 1.8464135021097046,
      "grad_norm": 0.4426078498363495,
      "learning_rate": 0.00017127724396740206,
      "loss": 0.7611671686172485,
      "step": 4376
    },
    {
      "epoch": 1.8472573839662447,
      "grad_norm": 0.40058812499046326,
      "learning_rate": 0.00017124354826083348,
      "loss": 0.737910270690918,
      "step": 4378
    },
    {
      "epoch": 1.8481012658227849,
      "grad_norm": 0.43037283420562744,
      "learning_rate": 0.00017120983611974654,
      "loss": 0.683937132358551,
      "step": 4380
    },
    {
      "epoch": 1.8489451476793248,
      "grad_norm": 0.4479113221168518,
      "learning_rate": 0.00017117610755191807,
      "loss": 0.6987335681915283,
      "step": 4382
    },
    {
      "epoch": 1.849789029535865,
      "grad_norm": 0.4218229651451111,
      "learning_rate": 0.0001711423625651285,
      "loss": 0.6964257955551147,
      "step": 4384
    },
    {
      "epoch": 1.8506329113924052,
      "grad_norm": 0.397733211517334,
      "learning_rate": 0.00017110860116716222,
      "loss": 0.6983811855316162,
      "step": 4386
    },
    {
      "epoch": 1.851476793248945,
      "grad_norm": 0.4844493865966797,
      "learning_rate": 0.00017107482336580735,
      "loss": 0.7579324245452881,
      "step": 4388
    },
    {
      "epoch": 1.8523206751054853,
      "grad_norm": 0.4494120478630066,
      "learning_rate": 0.0001710410291688557,
      "loss": 0.703558623790741,
      "step": 4390
    },
    {
      "epoch": 1.8531645569620254,
      "grad_norm": 0.4721727967262268,
      "learning_rate": 0.000171007218584103,
      "loss": 0.7386981248855591,
      "step": 4392
    },
    {
      "epoch": 1.8540084388185654,
      "grad_norm": 0.4816451370716095,
      "learning_rate": 0.0001709733916193487,
      "loss": 0.7769017219543457,
      "step": 4394
    },
    {
      "epoch": 1.8548523206751055,
      "grad_norm": 0.43638876080513,
      "learning_rate": 0.00017093954828239602,
      "loss": 0.7315034866333008,
      "step": 4396
    },
    {
      "epoch": 1.8556962025316457,
      "grad_norm": 0.4035055935382843,
      "learning_rate": 0.000170905688581052,
      "loss": 0.7289890050888062,
      "step": 4398
    },
    {
      "epoch": 1.8565400843881856,
      "grad_norm": 0.44265708327293396,
      "learning_rate": 0.00017087181252312735,
      "loss": 0.7190408110618591,
      "step": 4400
    },
    {
      "epoch": 1.8565400843881856,
      "eval_loss": 0.7635221481323242,
      "eval_runtime": 678.243,
      "eval_samples_per_second": 3.107,
      "eval_steps_per_second": 3.107,
      "step": 4400
    },
    {
      "epoch": 1.8573839662447258,
      "grad_norm": 0.39691466093063354,
      "learning_rate": 0.0001708379201164367,
      "loss": 0.6318185925483704,
      "step": 4402
    },
    {
      "epoch": 1.858227848101266,
      "grad_norm": 0.47801393270492554,
      "learning_rate": 0.0001708040113687983,
      "loss": 0.7040913105010986,
      "step": 4404
    },
    {
      "epoch": 1.859071729957806,
      "grad_norm": 0.47457239031791687,
      "learning_rate": 0.00017077008628803436,
      "loss": 0.7834659218788147,
      "step": 4406
    },
    {
      "epoch": 1.8599156118143458,
      "grad_norm": 0.41362807154655457,
      "learning_rate": 0.00017073614488197065,
      "loss": 0.7027983665466309,
      "step": 4408
    },
    {
      "epoch": 1.8607594936708862,
      "grad_norm": 0.457927942276001,
      "learning_rate": 0.0001707021871584368,
      "loss": 0.7143591642379761,
      "step": 4410
    },
    {
      "epoch": 1.8616033755274262,
      "grad_norm": 0.42931967973709106,
      "learning_rate": 0.00017066821312526625,
      "loss": 0.7328225374221802,
      "step": 4412
    },
    {
      "epoch": 1.862447257383966,
      "grad_norm": 0.3821638524532318,
      "learning_rate": 0.00017063422279029616,
      "loss": 0.7199252843856812,
      "step": 4414
    },
    {
      "epoch": 1.8632911392405065,
      "grad_norm": 0.3954671621322632,
      "learning_rate": 0.00017060021616136742,
      "loss": 0.7345157265663147,
      "step": 4416
    },
    {
      "epoch": 1.8641350210970464,
      "grad_norm": 0.38824960589408875,
      "learning_rate": 0.0001705661932463247,
      "loss": 0.587895393371582,
      "step": 4418
    },
    {
      "epoch": 1.8649789029535864,
      "grad_norm": 0.510923445224762,
      "learning_rate": 0.00017053215405301648,
      "loss": 0.7227945327758789,
      "step": 4420
    },
    {
      "epoch": 1.8658227848101265,
      "grad_norm": 0.38688936829566956,
      "learning_rate": 0.0001704980985892949,
      "loss": 0.6605637073516846,
      "step": 4422
    },
    {
      "epoch": 1.8666666666666667,
      "grad_norm": 0.4886745512485504,
      "learning_rate": 0.0001704640268630159,
      "loss": 0.7581667304039001,
      "step": 4424
    },
    {
      "epoch": 1.8675105485232066,
      "grad_norm": 0.4214446246623993,
      "learning_rate": 0.0001704299388820392,
      "loss": 0.7051677107810974,
      "step": 4426
    },
    {
      "epoch": 1.8683544303797468,
      "grad_norm": 0.4189293384552002,
      "learning_rate": 0.00017039583465422824,
      "loss": 0.6489346623420715,
      "step": 4428
    },
    {
      "epoch": 1.869198312236287,
      "grad_norm": 0.4264903962612152,
      "learning_rate": 0.0001703617141874502,
      "loss": 0.6896629929542542,
      "step": 4430
    },
    {
      "epoch": 1.870042194092827,
      "grad_norm": 0.5351413488388062,
      "learning_rate": 0.00017032757748957603,
      "loss": 0.7468283772468567,
      "step": 4432
    },
    {
      "epoch": 1.870886075949367,
      "grad_norm": 0.40163540840148926,
      "learning_rate": 0.00017029342456848035,
      "loss": 0.6029976010322571,
      "step": 4434
    },
    {
      "epoch": 1.8717299578059072,
      "grad_norm": 0.3786795139312744,
      "learning_rate": 0.0001702592554320417,
      "loss": 0.6891162991523743,
      "step": 4436
    },
    {
      "epoch": 1.8725738396624472,
      "grad_norm": 0.4266849458217621,
      "learning_rate": 0.00017022507008814214,
      "loss": 0.6189853549003601,
      "step": 4438
    },
    {
      "epoch": 1.8734177215189873,
      "grad_norm": 0.4076935052871704,
      "learning_rate": 0.0001701908685446676,
      "loss": 0.6858769655227661,
      "step": 4440
    },
    {
      "epoch": 1.8742616033755275,
      "grad_norm": 0.4209558665752411,
      "learning_rate": 0.00017015665080950774,
      "loss": 0.6650485396385193,
      "step": 4442
    },
    {
      "epoch": 1.8751054852320674,
      "grad_norm": 0.4114036560058594,
      "learning_rate": 0.0001701224168905559,
      "loss": 0.6887878179550171,
      "step": 4444
    },
    {
      "epoch": 1.8759493670886076,
      "grad_norm": 0.34596455097198486,
      "learning_rate": 0.00017008816679570926,
      "loss": 0.6950712203979492,
      "step": 4446
    },
    {
      "epoch": 1.8767932489451478,
      "grad_norm": 0.45132747292518616,
      "learning_rate": 0.0001700539005328686,
      "loss": 0.7360581159591675,
      "step": 4448
    },
    {
      "epoch": 1.8776371308016877,
      "grad_norm": 0.4258243441581726,
      "learning_rate": 0.00017001961810993846,
      "loss": 0.6672278046607971,
      "step": 4450
    },
    {
      "epoch": 1.8784810126582279,
      "grad_norm": 0.39144474267959595,
      "learning_rate": 0.0001699853195348272,
      "loss": 0.6740089654922485,
      "step": 4452
    },
    {
      "epoch": 1.879324894514768,
      "grad_norm": 0.42183035612106323,
      "learning_rate": 0.00016995100481544681,
      "loss": 0.7747141122817993,
      "step": 4454
    },
    {
      "epoch": 1.880168776371308,
      "grad_norm": 0.4110005795955658,
      "learning_rate": 0.00016991667395971303,
      "loss": 0.7189701199531555,
      "step": 4456
    },
    {
      "epoch": 1.8810126582278481,
      "grad_norm": 0.4073067307472229,
      "learning_rate": 0.00016988232697554538,
      "loss": 0.6880105137825012,
      "step": 4458
    },
    {
      "epoch": 1.8818565400843883,
      "grad_norm": 0.467443585395813,
      "learning_rate": 0.00016984796387086698,
      "loss": 0.6994736790657043,
      "step": 4460
    },
    {
      "epoch": 1.8827004219409282,
      "grad_norm": 0.4769018292427063,
      "learning_rate": 0.00016981358465360482,
      "loss": 0.7389267683029175,
      "step": 4462
    },
    {
      "epoch": 1.8835443037974684,
      "grad_norm": 0.3834097981452942,
      "learning_rate": 0.00016977918933168938,
      "loss": 0.6375740170478821,
      "step": 4464
    },
    {
      "epoch": 1.8843881856540086,
      "grad_norm": 0.44548940658569336,
      "learning_rate": 0.00016974477791305517,
      "loss": 0.6845629811286926,
      "step": 4466
    },
    {
      "epoch": 1.8852320675105485,
      "grad_norm": 0.39344266057014465,
      "learning_rate": 0.00016971035040564016,
      "loss": 0.7307721376419067,
      "step": 4468
    },
    {
      "epoch": 1.8860759493670884,
      "grad_norm": 0.37901216745376587,
      "learning_rate": 0.0001696759068173861,
      "loss": 0.6733962297439575,
      "step": 4470
    },
    {
      "epoch": 1.8869198312236288,
      "grad_norm": 0.44465333223342896,
      "learning_rate": 0.00016964144715623852,
      "loss": 0.7294619679450989,
      "step": 4472
    },
    {
      "epoch": 1.8877637130801688,
      "grad_norm": 0.39566636085510254,
      "learning_rate": 0.00016960697143014657,
      "loss": 0.6537288427352905,
      "step": 4474
    },
    {
      "epoch": 1.8886075949367087,
      "grad_norm": 0.4047028124332428,
      "learning_rate": 0.0001695724796470631,
      "loss": 0.623903751373291,
      "step": 4476
    },
    {
      "epoch": 1.889451476793249,
      "grad_norm": 0.4559679329395294,
      "learning_rate": 0.00016953797181494475,
      "loss": 0.661283552646637,
      "step": 4478
    },
    {
      "epoch": 1.890295358649789,
      "grad_norm": 0.3980371952056885,
      "learning_rate": 0.00016950344794175183,
      "loss": 0.6587702035903931,
      "step": 4480
    },
    {
      "epoch": 1.891139240506329,
      "grad_norm": 0.41418227553367615,
      "learning_rate": 0.0001694689080354483,
      "loss": 0.7898983955383301,
      "step": 4482
    },
    {
      "epoch": 1.8919831223628694,
      "grad_norm": 0.41184720396995544,
      "learning_rate": 0.00016943435210400184,
      "loss": 0.6213424205780029,
      "step": 4484
    },
    {
      "epoch": 1.8928270042194093,
      "grad_norm": 0.39218711853027344,
      "learning_rate": 0.00016939978015538388,
      "loss": 0.6624190807342529,
      "step": 4486
    },
    {
      "epoch": 1.8936708860759492,
      "grad_norm": 0.4875730872154236,
      "learning_rate": 0.0001693651921975695,
      "loss": 0.7063044309616089,
      "step": 4488
    },
    {
      "epoch": 1.8945147679324894,
      "grad_norm": 0.38058432936668396,
      "learning_rate": 0.00016933058823853748,
      "loss": 0.6471660137176514,
      "step": 4490
    },
    {
      "epoch": 1.8953586497890296,
      "grad_norm": 0.5368654131889343,
      "learning_rate": 0.0001692959682862702,
      "loss": 0.7694545388221741,
      "step": 4492
    },
    {
      "epoch": 1.8962025316455695,
      "grad_norm": 0.41736599802970886,
      "learning_rate": 0.00016926133234875396,
      "loss": 0.700016438961029,
      "step": 4494
    },
    {
      "epoch": 1.8970464135021097,
      "grad_norm": 0.4086865484714508,
      "learning_rate": 0.0001692266804339785,
      "loss": 0.6926955580711365,
      "step": 4496
    },
    {
      "epoch": 1.8978902953586498,
      "grad_norm": 0.447516530752182,
      "learning_rate": 0.00016919201254993738,
      "loss": 0.6776167154312134,
      "step": 4498
    },
    {
      "epoch": 1.8987341772151898,
      "grad_norm": 0.43951377272605896,
      "learning_rate": 0.00016915732870462783,
      "loss": 0.6860454678535461,
      "step": 4500
    },
    {
      "epoch": 1.8987341772151898,
      "eval_loss": 0.7600579857826233,
      "eval_runtime": 674.2593,
      "eval_samples_per_second": 3.125,
      "eval_steps_per_second": 3.125,
      "step": 4500
    },
    {
      "epoch": 1.89957805907173,
      "grad_norm": 0.380329966545105,
      "learning_rate": 0.00016912262890605076,
      "loss": 0.6525024175643921,
      "step": 4502
    },
    {
      "epoch": 1.90042194092827,
      "grad_norm": 0.3461032807826996,
      "learning_rate": 0.00016908791316221073,
      "loss": 0.6473777294158936,
      "step": 4504
    },
    {
      "epoch": 1.90126582278481,
      "grad_norm": 0.47325965762138367,
      "learning_rate": 0.00016905318148111595,
      "loss": 0.760007381439209,
      "step": 4506
    },
    {
      "epoch": 1.9021097046413502,
      "grad_norm": 0.39158931374549866,
      "learning_rate": 0.00016901843387077844,
      "loss": 0.659562349319458,
      "step": 4508
    },
    {
      "epoch": 1.9029535864978904,
      "grad_norm": 0.36785584688186646,
      "learning_rate": 0.0001689836703392137,
      "loss": 0.5873214602470398,
      "step": 4510
    },
    {
      "epoch": 1.9037974683544303,
      "grad_norm": 0.3843834102153778,
      "learning_rate": 0.00016894889089444115,
      "loss": 0.6236514449119568,
      "step": 4512
    },
    {
      "epoch": 1.9046413502109705,
      "grad_norm": 0.41675102710723877,
      "learning_rate": 0.0001689140955444836,
      "loss": 0.7129080891609192,
      "step": 4514
    },
    {
      "epoch": 1.9054852320675106,
      "grad_norm": 0.46025362610816956,
      "learning_rate": 0.00016887928429736775,
      "loss": 0.7348461747169495,
      "step": 4516
    },
    {
      "epoch": 1.9063291139240506,
      "grad_norm": 0.43589887022972107,
      "learning_rate": 0.00016884445716112387,
      "loss": 0.6797979474067688,
      "step": 4518
    },
    {
      "epoch": 1.9071729957805907,
      "grad_norm": 0.4301862120628357,
      "learning_rate": 0.0001688096141437859,
      "loss": 0.6754241585731506,
      "step": 4520
    },
    {
      "epoch": 1.908016877637131,
      "grad_norm": 0.41446763277053833,
      "learning_rate": 0.00016877475525339146,
      "loss": 0.681866466999054,
      "step": 4522
    },
    {
      "epoch": 1.9088607594936708,
      "grad_norm": 0.4051108658313751,
      "learning_rate": 0.0001687398804979818,
      "loss": 0.6626620888710022,
      "step": 4524
    },
    {
      "epoch": 1.909704641350211,
      "grad_norm": 0.3896785080432892,
      "learning_rate": 0.00016870498988560192,
      "loss": 0.6753385066986084,
      "step": 4526
    },
    {
      "epoch": 1.9105485232067512,
      "grad_norm": 0.4307839274406433,
      "learning_rate": 0.00016867008342430037,
      "loss": 0.6971913576126099,
      "step": 4528
    },
    {
      "epoch": 1.9113924050632911,
      "grad_norm": 0.4120950698852539,
      "learning_rate": 0.0001686351611221294,
      "loss": 0.7674229145050049,
      "step": 4530
    },
    {
      "epoch": 1.9122362869198313,
      "grad_norm": 0.4321785569190979,
      "learning_rate": 0.00016860022298714492,
      "loss": 0.7074664235115051,
      "step": 4532
    },
    {
      "epoch": 1.9130801687763714,
      "grad_norm": 0.38313060998916626,
      "learning_rate": 0.00016856526902740652,
      "loss": 0.6178744435310364,
      "step": 4534
    },
    {
      "epoch": 1.9139240506329114,
      "grad_norm": 0.3940589129924774,
      "learning_rate": 0.0001685302992509773,
      "loss": 0.7168449759483337,
      "step": 4536
    },
    {
      "epoch": 1.9147679324894513,
      "grad_norm": 0.3719513416290283,
      "learning_rate": 0.0001684953136659243,
      "loss": 0.6892635226249695,
      "step": 4538
    },
    {
      "epoch": 1.9156118143459917,
      "grad_norm": 0.40150535106658936,
      "learning_rate": 0.00016846031228031784,
      "loss": 0.7352524399757385,
      "step": 4540
    },
    {
      "epoch": 1.9164556962025316,
      "grad_norm": 0.4212523102760315,
      "learning_rate": 0.00016842529510223213,
      "loss": 0.6469122767448425,
      "step": 4542
    },
    {
      "epoch": 1.9172995780590716,
      "grad_norm": 0.45365604758262634,
      "learning_rate": 0.00016839026213974503,
      "loss": 0.6883940696716309,
      "step": 4544
    },
    {
      "epoch": 1.918143459915612,
      "grad_norm": 0.436541885137558,
      "learning_rate": 0.00016835521340093787,
      "loss": 0.7378416657447815,
      "step": 4546
    },
    {
      "epoch": 1.918987341772152,
      "grad_norm": 0.41461536288261414,
      "learning_rate": 0.0001683201488938958,
      "loss": 0.7432116270065308,
      "step": 4548
    },
    {
      "epoch": 1.9198312236286919,
      "grad_norm": 0.40218585729599,
      "learning_rate": 0.00016828506862670746,
      "loss": 0.6801432967185974,
      "step": 4550
    },
    {
      "epoch": 1.920675105485232,
      "grad_norm": 0.3994768559932709,
      "learning_rate": 0.00016824997260746525,
      "loss": 0.6835547685623169,
      "step": 4552
    },
    {
      "epoch": 1.9215189873417722,
      "grad_norm": 0.460328072309494,
      "learning_rate": 0.00016821486084426512,
      "loss": 0.7723629474639893,
      "step": 4554
    },
    {
      "epoch": 1.9223628691983121,
      "grad_norm": 0.4739786386489868,
      "learning_rate": 0.00016817973334520668,
      "loss": 0.7513449192047119,
      "step": 4556
    },
    {
      "epoch": 1.9232067510548523,
      "grad_norm": 0.46618419885635376,
      "learning_rate": 0.00016814459011839315,
      "loss": 0.7000700235366821,
      "step": 4558
    },
    {
      "epoch": 1.9240506329113924,
      "grad_norm": 0.4187009632587433,
      "learning_rate": 0.00016810943117193146,
      "loss": 0.6381427049636841,
      "step": 4560
    },
    {
      "epoch": 1.9248945147679324,
      "grad_norm": 0.5057410597801208,
      "learning_rate": 0.00016807425651393207,
      "loss": 0.7823911309242249,
      "step": 4562
    },
    {
      "epoch": 1.9257383966244725,
      "grad_norm": 0.4235171973705292,
      "learning_rate": 0.00016803906615250907,
      "loss": 0.7210549712181091,
      "step": 4564
    },
    {
      "epoch": 1.9265822784810127,
      "grad_norm": 0.45755431056022644,
      "learning_rate": 0.00016800386009578025,
      "loss": 0.794435441493988,
      "step": 4566
    },
    {
      "epoch": 1.9274261603375527,
      "grad_norm": 0.4225042760372162,
      "learning_rate": 0.0001679686383518669,
      "loss": 0.6490750312805176,
      "step": 4568
    },
    {
      "epoch": 1.9282700421940928,
      "grad_norm": 0.41081616282463074,
      "learning_rate": 0.00016793340092889408,
      "loss": 0.6976916790008545,
      "step": 4570
    },
    {
      "epoch": 1.929113924050633,
      "grad_norm": 0.42354175448417664,
      "learning_rate": 0.00016789814783499033,
      "loss": 0.6559295058250427,
      "step": 4572
    },
    {
      "epoch": 1.929957805907173,
      "grad_norm": 0.39702117443084717,
      "learning_rate": 0.0001678628790782879,
      "loss": 0.7900391817092896,
      "step": 4574
    },
    {
      "epoch": 1.930801687763713,
      "grad_norm": 0.4400629997253418,
      "learning_rate": 0.00016782759466692256,
      "loss": 0.7020596265792847,
      "step": 4576
    },
    {
      "epoch": 1.9316455696202532,
      "grad_norm": 0.42563396692276,
      "learning_rate": 0.00016779229460903383,
      "loss": 0.7107458710670471,
      "step": 4578
    },
    {
      "epoch": 1.9324894514767932,
      "grad_norm": 0.40650051832199097,
      "learning_rate": 0.0001677569789127647,
      "loss": 0.58088618516922,
      "step": 4580
    },
    {
      "epoch": 1.9333333333333333,
      "grad_norm": 0.42461681365966797,
      "learning_rate": 0.00016772164758626184,
      "loss": 0.6815688610076904,
      "step": 4582
    },
    {
      "epoch": 1.9341772151898735,
      "grad_norm": 0.4248030483722687,
      "learning_rate": 0.0001676863006376755,
      "loss": 0.6617820262908936,
      "step": 4584
    },
    {
      "epoch": 1.9350210970464135,
      "grad_norm": 0.4336024522781372,
      "learning_rate": 0.0001676509380751595,
      "loss": 0.7462296485900879,
      "step": 4586
    },
    {
      "epoch": 1.9358649789029536,
      "grad_norm": 0.42542141675949097,
      "learning_rate": 0.00016761555990687136,
      "loss": 0.7801896333694458,
      "step": 4588
    },
    {
      "epoch": 1.9367088607594938,
      "grad_norm": 0.41240575909614563,
      "learning_rate": 0.00016758016614097217,
      "loss": 0.7308001518249512,
      "step": 4590
    },
    {
      "epoch": 1.9375527426160337,
      "grad_norm": 0.3811012804508209,
      "learning_rate": 0.00016754475678562654,
      "loss": 0.7126680016517639,
      "step": 4592
    },
    {
      "epoch": 1.9383966244725739,
      "grad_norm": 0.4859951436519623,
      "learning_rate": 0.00016750933184900272,
      "loss": 0.679752767086029,
      "step": 4594
    },
    {
      "epoch": 1.939240506329114,
      "grad_norm": 0.36403799057006836,
      "learning_rate": 0.00016747389133927261,
      "loss": 0.6077587604522705,
      "step": 4596
    },
    {
      "epoch": 1.940084388185654,
      "grad_norm": 0.3960701525211334,
      "learning_rate": 0.00016743843526461158,
      "loss": 0.6919949650764465,
      "step": 4598
    },
    {
      "epoch": 1.9409282700421941,
      "grad_norm": 0.4058634042739868,
      "learning_rate": 0.00016740296363319877,
      "loss": 0.728607177734375,
      "step": 4600
    },
    {
      "epoch": 1.9409282700421941,
      "eval_loss": 0.7585541009902954,
      "eval_runtime": 679.0866,
      "eval_samples_per_second": 3.103,
      "eval_steps_per_second": 3.103,
      "step": 4600
    },
    {
      "epoch": 1.9417721518987343,
      "grad_norm": 0.45107272267341614,
      "learning_rate": 0.00016736747645321672,
      "loss": 0.669603168964386,
      "step": 4602
    },
    {
      "epoch": 1.9426160337552743,
      "grad_norm": 0.4244096577167511,
      "learning_rate": 0.00016733197373285165,
      "loss": 0.6975913643836975,
      "step": 4604
    },
    {
      "epoch": 1.9434599156118142,
      "grad_norm": 0.37567681074142456,
      "learning_rate": 0.00016729645548029342,
      "loss": 0.5990989804267883,
      "step": 4606
    },
    {
      "epoch": 1.9443037974683546,
      "grad_norm": 0.40256237983703613,
      "learning_rate": 0.00016726092170373533,
      "loss": 0.723430871963501,
      "step": 4608
    },
    {
      "epoch": 1.9451476793248945,
      "grad_norm": 0.4884983003139496,
      "learning_rate": 0.0001672253724113744,
      "loss": 0.7460100650787354,
      "step": 4610
    },
    {
      "epoch": 1.9459915611814345,
      "grad_norm": 0.3629630208015442,
      "learning_rate": 0.0001671898076114111,
      "loss": 0.5577017664909363,
      "step": 4612
    },
    {
      "epoch": 1.9468354430379748,
      "grad_norm": 0.42751777172088623,
      "learning_rate": 0.00016715422731204967,
      "loss": 0.7394112944602966,
      "step": 4614
    },
    {
      "epoch": 1.9476793248945148,
      "grad_norm": 0.35809609293937683,
      "learning_rate": 0.00016711863152149765,
      "loss": 0.5905179381370544,
      "step": 4616
    },
    {
      "epoch": 1.9485232067510547,
      "grad_norm": 0.4111083745956421,
      "learning_rate": 0.0001670830202479664,
      "loss": 0.7035338878631592,
      "step": 4618
    },
    {
      "epoch": 1.9493670886075949,
      "grad_norm": 0.4530862867832184,
      "learning_rate": 0.0001670473934996707,
      "loss": 0.7048936486244202,
      "step": 4620
    },
    {
      "epoch": 1.950210970464135,
      "grad_norm": 0.41778260469436646,
      "learning_rate": 0.00016701175128482903,
      "loss": 0.6594944596290588,
      "step": 4622
    },
    {
      "epoch": 1.951054852320675,
      "grad_norm": 0.40512707829475403,
      "learning_rate": 0.0001669760936116633,
      "loss": 0.6902912259101868,
      "step": 4624
    },
    {
      "epoch": 1.9518987341772152,
      "grad_norm": 0.4226403832435608,
      "learning_rate": 0.0001669404204883991,
      "loss": 0.7086893320083618,
      "step": 4626
    },
    {
      "epoch": 1.9527426160337553,
      "grad_norm": 0.397930383682251,
      "learning_rate": 0.00016690473192326549,
      "loss": 0.6647822856903076,
      "step": 4628
    },
    {
      "epoch": 1.9535864978902953,
      "grad_norm": 0.3985617458820343,
      "learning_rate": 0.00016686902792449515,
      "loss": 0.747227668762207,
      "step": 4630
    },
    {
      "epoch": 1.9544303797468354,
      "grad_norm": 0.4174083173274994,
      "learning_rate": 0.00016683330850032432,
      "loss": 0.7526347637176514,
      "step": 4632
    },
    {
      "epoch": 1.9552742616033756,
      "grad_norm": 0.425070583820343,
      "learning_rate": 0.00016679757365899275,
      "loss": 0.6674112677574158,
      "step": 4634
    },
    {
      "epoch": 1.9561181434599155,
      "grad_norm": 0.4049135148525238,
      "learning_rate": 0.00016676182340874386,
      "loss": 0.6515055298805237,
      "step": 4636
    },
    {
      "epoch": 1.9569620253164557,
      "grad_norm": 0.4312315285205841,
      "learning_rate": 0.00016672605775782447,
      "loss": 0.645137369632721,
      "step": 4638
    },
    {
      "epoch": 1.9578059071729959,
      "grad_norm": 0.39540281891822815,
      "learning_rate": 0.00016669027671448503,
      "loss": 0.6519104838371277,
      "step": 4640
    },
    {
      "epoch": 1.9586497890295358,
      "grad_norm": 0.5028185844421387,
      "learning_rate": 0.00016665448028697961,
      "loss": 0.6815812587738037,
      "step": 4642
    },
    {
      "epoch": 1.959493670886076,
      "grad_norm": 0.4395635724067688,
      "learning_rate": 0.00016661866848356567,
      "loss": 0.6713913083076477,
      "step": 4644
    },
    {
      "epoch": 1.9603375527426161,
      "grad_norm": 0.42733073234558105,
      "learning_rate": 0.00016658284131250436,
      "loss": 0.6989195942878723,
      "step": 4646
    },
    {
      "epoch": 1.961181434599156,
      "grad_norm": 0.41415879130363464,
      "learning_rate": 0.00016654699878206031,
      "loss": 0.6501366496086121,
      "step": 4648
    },
    {
      "epoch": 1.9620253164556962,
      "grad_norm": 0.39072170853614807,
      "learning_rate": 0.0001665111409005017,
      "loss": 0.6437955498695374,
      "step": 4650
    },
    {
      "epoch": 1.9628691983122364,
      "grad_norm": 0.41802850365638733,
      "learning_rate": 0.00016647526767610025,
      "loss": 0.6521314382553101,
      "step": 4652
    },
    {
      "epoch": 1.9637130801687763,
      "grad_norm": 0.41475021839141846,
      "learning_rate": 0.00016643937911713124,
      "loss": 0.7300742864608765,
      "step": 4654
    },
    {
      "epoch": 1.9645569620253165,
      "grad_norm": 0.41763070225715637,
      "learning_rate": 0.00016640347523187344,
      "loss": 0.6217485070228577,
      "step": 4656
    },
    {
      "epoch": 1.9654008438818567,
      "grad_norm": 0.4488297402858734,
      "learning_rate": 0.00016636755602860922,
      "loss": 0.7974472641944885,
      "step": 4658
    },
    {
      "epoch": 1.9662447257383966,
      "grad_norm": 0.37688007950782776,
      "learning_rate": 0.00016633162151562445,
      "loss": 0.728827714920044,
      "step": 4660
    },
    {
      "epoch": 1.9670886075949368,
      "grad_norm": 0.4636184275150299,
      "learning_rate": 0.0001662956717012085,
      "loss": 0.7563744783401489,
      "step": 4662
    },
    {
      "epoch": 1.967932489451477,
      "grad_norm": 0.432020902633667,
      "learning_rate": 0.00016625970659365434,
      "loss": 0.7408145666122437,
      "step": 4664
    },
    {
      "epoch": 1.9687763713080169,
      "grad_norm": 0.4098186790943146,
      "learning_rate": 0.0001662237262012584,
      "loss": 0.6961510181427002,
      "step": 4666
    },
    {
      "epoch": 1.9696202531645568,
      "grad_norm": 0.44124510884284973,
      "learning_rate": 0.00016618773053232068,
      "loss": 0.6959825754165649,
      "step": 4668
    },
    {
      "epoch": 1.9704641350210972,
      "grad_norm": 0.3729988634586334,
      "learning_rate": 0.00016615171959514466,
      "loss": 0.6693721413612366,
      "step": 4670
    },
    {
      "epoch": 1.9713080168776371,
      "grad_norm": 0.4506371021270752,
      "learning_rate": 0.00016611569339803744,
      "loss": 0.6943060159683228,
      "step": 4672
    },
    {
      "epoch": 1.972151898734177,
      "grad_norm": 0.43713298439979553,
      "learning_rate": 0.00016607965194930947,
      "loss": 0.6915813684463501,
      "step": 4674
    },
    {
      "epoch": 1.9729957805907175,
      "grad_norm": 0.4375544786453247,
      "learning_rate": 0.00016604359525727492,
      "loss": 0.7430137991905212,
      "step": 4676
    },
    {
      "epoch": 1.9738396624472574,
      "grad_norm": 0.4393104314804077,
      "learning_rate": 0.00016600752333025134,
      "loss": 0.7260952591896057,
      "step": 4678
    },
    {
      "epoch": 1.9746835443037973,
      "grad_norm": 0.4471568167209625,
      "learning_rate": 0.00016597143617655982,
      "loss": 0.7350760102272034,
      "step": 4680
    },
    {
      "epoch": 1.9755274261603377,
      "grad_norm": 0.39821380376815796,
      "learning_rate": 0.00016593533380452499,
      "loss": 0.7295693159103394,
      "step": 4682
    },
    {
      "epoch": 1.9763713080168777,
      "grad_norm": 0.40367990732192993,
      "learning_rate": 0.00016589921622247493,
      "loss": 0.6461828947067261,
      "step": 4684
    },
    {
      "epoch": 1.9772151898734176,
      "grad_norm": 0.4723254442214966,
      "learning_rate": 0.00016586308343874136,
      "loss": 0.699313223361969,
      "step": 4686
    },
    {
      "epoch": 1.9780590717299578,
      "grad_norm": 0.45741328597068787,
      "learning_rate": 0.0001658269354616593,
      "loss": 0.7299131751060486,
      "step": 4688
    },
    {
      "epoch": 1.978902953586498,
      "grad_norm": 0.4011725187301636,
      "learning_rate": 0.0001657907722995675,
      "loss": 0.7643240690231323,
      "step": 4690
    },
    {
      "epoch": 1.9797468354430379,
      "grad_norm": 0.3904820382595062,
      "learning_rate": 0.00016575459396080805,
      "loss": 0.6945428848266602,
      "step": 4692
    },
    {
      "epoch": 1.980590717299578,
      "grad_norm": 0.3643582761287689,
      "learning_rate": 0.00016571840045372663,
      "loss": 0.5986754298210144,
      "step": 4694
    },
    {
      "epoch": 1.9814345991561182,
      "grad_norm": 0.4371087849140167,
      "learning_rate": 0.00016568219178667235,
      "loss": 0.7462178468704224,
      "step": 4696
    },
    {
      "epoch": 1.9822784810126581,
      "grad_norm": 0.4440254867076874,
      "learning_rate": 0.0001656459679679979,
      "loss": 0.7553940415382385,
      "step": 4698
    },
    {
      "epoch": 1.9831223628691983,
      "grad_norm": 0.41370099782943726,
      "learning_rate": 0.00016560972900605937,
      "loss": 0.7119964361190796,
      "step": 4700
    },
    {
      "epoch": 1.9831223628691983,
      "eval_loss": 0.7582268714904785,
      "eval_runtime": 690.081,
      "eval_samples_per_second": 3.053,
      "eval_steps_per_second": 3.053,
      "step": 4700
    },
    {
      "epoch": 1.9839662447257385,
      "grad_norm": 0.4408273696899414,
      "learning_rate": 0.0001655734749092164,
      "loss": 0.6260318160057068,
      "step": 4702
    },
    {
      "epoch": 1.9848101265822784,
      "grad_norm": 0.4697865843772888,
      "learning_rate": 0.0001655372056858322,
      "loss": 0.7382199168205261,
      "step": 4704
    },
    {
      "epoch": 1.9856540084388186,
      "grad_norm": 0.423520028591156,
      "learning_rate": 0.00016550092134427327,
      "loss": 0.7037063241004944,
      "step": 4706
    },
    {
      "epoch": 1.9864978902953587,
      "grad_norm": 0.38633009791374207,
      "learning_rate": 0.00016546462189290974,
      "loss": 0.7173316478729248,
      "step": 4708
    },
    {
      "epoch": 1.9873417721518987,
      "grad_norm": 0.410230815410614,
      "learning_rate": 0.00016542830734011523,
      "loss": 0.6884669065475464,
      "step": 4710
    },
    {
      "epoch": 1.9881856540084388,
      "grad_norm": 0.4486774802207947,
      "learning_rate": 0.00016539197769426678,
      "loss": 0.7181811332702637,
      "step": 4712
    },
    {
      "epoch": 1.989029535864979,
      "grad_norm": 0.47757431864738464,
      "learning_rate": 0.00016535563296374495,
      "loss": 0.7737504243850708,
      "step": 4714
    },
    {
      "epoch": 1.989873417721519,
      "grad_norm": 0.40281420946121216,
      "learning_rate": 0.00016531927315693382,
      "loss": 0.683630645275116,
      "step": 4716
    },
    {
      "epoch": 1.990717299578059,
      "grad_norm": 0.42349720001220703,
      "learning_rate": 0.00016528289828222082,
      "loss": 0.7447960376739502,
      "step": 4718
    },
    {
      "epoch": 1.9915611814345993,
      "grad_norm": 0.40754765272140503,
      "learning_rate": 0.00016524650834799694,
      "loss": 0.6800103783607483,
      "step": 4720
    },
    {
      "epoch": 1.9924050632911392,
      "grad_norm": 0.3766736090183258,
      "learning_rate": 0.0001652101033626567,
      "loss": 0.6609475612640381,
      "step": 4722
    },
    {
      "epoch": 1.9932489451476794,
      "grad_norm": 0.3600929081439972,
      "learning_rate": 0.00016517368333459798,
      "loss": 0.6496920585632324,
      "step": 4724
    },
    {
      "epoch": 1.9940928270042195,
      "grad_norm": 0.39590612053871155,
      "learning_rate": 0.00016513724827222227,
      "loss": 0.6305265426635742,
      "step": 4726
    },
    {
      "epoch": 1.9949367088607595,
      "grad_norm": 0.41002732515335083,
      "learning_rate": 0.00016510079818393426,
      "loss": 0.712282657623291,
      "step": 4728
    },
    {
      "epoch": 1.9957805907172996,
      "grad_norm": 0.41948413848876953,
      "learning_rate": 0.00016506433307814246,
      "loss": 0.6974884271621704,
      "step": 4730
    },
    {
      "epoch": 1.9966244725738398,
      "grad_norm": 0.4283764958381653,
      "learning_rate": 0.00016502785296325858,
      "loss": 0.6844019889831543,
      "step": 4732
    },
    {
      "epoch": 1.9974683544303797,
      "grad_norm": 0.39830246567726135,
      "learning_rate": 0.0001649913578476979,
      "loss": 0.7453671097755432,
      "step": 4734
    },
    {
      "epoch": 1.9983122362869197,
      "grad_norm": 0.3875660300254822,
      "learning_rate": 0.00016495484773987917,
      "loss": 0.6571418046951294,
      "step": 4736
    },
    {
      "epoch": 1.99915611814346,
      "grad_norm": 0.379986971616745,
      "learning_rate": 0.00016491832264822453,
      "loss": 0.6844568848609924,
      "step": 4738
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.38605886697769165,
      "learning_rate": 0.00016488178258115965,
      "loss": 0.6115277409553528,
      "step": 4740
    },
    {
      "epoch": 2.00084388185654,
      "grad_norm": 0.3991186022758484,
      "learning_rate": 0.0001648452275471136,
      "loss": 0.6192594170570374,
      "step": 4742
    },
    {
      "epoch": 2.0016877637130803,
      "grad_norm": 0.41378065943717957,
      "learning_rate": 0.00016480865755451893,
      "loss": 0.6478689312934875,
      "step": 4744
    },
    {
      "epoch": 2.0025316455696203,
      "grad_norm": 0.41938909888267517,
      "learning_rate": 0.00016477207261181162,
      "loss": 0.6162620186805725,
      "step": 4746
    },
    {
      "epoch": 2.00337552742616,
      "grad_norm": 0.40436387062072754,
      "learning_rate": 0.00016473547272743115,
      "loss": 0.5328736901283264,
      "step": 4748
    },
    {
      "epoch": 2.0042194092827006,
      "grad_norm": 0.4148593544960022,
      "learning_rate": 0.00016469885790982037,
      "loss": 0.547049880027771,
      "step": 4750
    },
    {
      "epoch": 2.0050632911392405,
      "grad_norm": 0.42139601707458496,
      "learning_rate": 0.00016466222816742564,
      "loss": 0.5509368181228638,
      "step": 4752
    },
    {
      "epoch": 2.0059071729957805,
      "grad_norm": 0.4509783089160919,
      "learning_rate": 0.00016462558350869677,
      "loss": 0.5994526147842407,
      "step": 4754
    },
    {
      "epoch": 2.006751054852321,
      "grad_norm": 0.4232040345668793,
      "learning_rate": 0.0001645889239420869,
      "loss": 0.6348381638526917,
      "step": 4756
    },
    {
      "epoch": 2.007594936708861,
      "grad_norm": 0.4259628355503082,
      "learning_rate": 0.00016455224947605274,
      "loss": 0.5487880110740662,
      "step": 4758
    },
    {
      "epoch": 2.0084388185654007,
      "grad_norm": 0.5485594868659973,
      "learning_rate": 0.0001645155601190544,
      "loss": 0.5468270778656006,
      "step": 4760
    },
    {
      "epoch": 2.009282700421941,
      "grad_norm": 0.4243668019771576,
      "learning_rate": 0.00016447885587955537,
      "loss": 0.6165785789489746,
      "step": 4762
    },
    {
      "epoch": 2.010126582278481,
      "grad_norm": 0.46513810753822327,
      "learning_rate": 0.00016444213676602263,
      "loss": 0.5868126749992371,
      "step": 4764
    },
    {
      "epoch": 2.010970464135021,
      "grad_norm": 0.4555842876434326,
      "learning_rate": 0.00016440540278692654,
      "loss": 0.548373818397522,
      "step": 4766
    },
    {
      "epoch": 2.0118143459915614,
      "grad_norm": 0.4402005672454834,
      "learning_rate": 0.000164368653950741,
      "loss": 0.6254384517669678,
      "step": 4768
    },
    {
      "epoch": 2.0126582278481013,
      "grad_norm": 0.5100982785224915,
      "learning_rate": 0.0001643318902659432,
      "loss": 0.6335576772689819,
      "step": 4770
    },
    {
      "epoch": 2.0135021097046413,
      "grad_norm": 0.508076548576355,
      "learning_rate": 0.0001642951117410138,
      "loss": 0.6601388454437256,
      "step": 4772
    },
    {
      "epoch": 2.014345991561181,
      "grad_norm": 0.47249099612236023,
      "learning_rate": 0.000164258318384437,
      "loss": 0.6183612942695618,
      "step": 4774
    },
    {
      "epoch": 2.0151898734177216,
      "grad_norm": 0.459249883890152,
      "learning_rate": 0.00016422151020470022,
      "loss": 0.6172632575035095,
      "step": 4776
    },
    {
      "epoch": 2.0160337552742615,
      "grad_norm": 0.44374513626098633,
      "learning_rate": 0.00016418468721029442,
      "loss": 0.6392593383789062,
      "step": 4778
    },
    {
      "epoch": 2.0168776371308015,
      "grad_norm": 0.4633971154689789,
      "learning_rate": 0.000164147849409714,
      "loss": 0.6331546902656555,
      "step": 4780
    },
    {
      "epoch": 2.017721518987342,
      "grad_norm": 0.4080882668495178,
      "learning_rate": 0.00016411099681145667,
      "loss": 0.5368412137031555,
      "step": 4782
    },
    {
      "epoch": 2.018565400843882,
      "grad_norm": 0.3852706253528595,
      "learning_rate": 0.00016407412942402366,
      "loss": 0.4763215184211731,
      "step": 4784
    },
    {
      "epoch": 2.0194092827004217,
      "grad_norm": 0.45222651958465576,
      "learning_rate": 0.00016403724725591958,
      "loss": 0.6510329842567444,
      "step": 4786
    },
    {
      "epoch": 2.020253164556962,
      "grad_norm": 0.4027794897556305,
      "learning_rate": 0.00016400035031565238,
      "loss": 0.5856698751449585,
      "step": 4788
    },
    {
      "epoch": 2.021097046413502,
      "grad_norm": 0.3780474066734314,
      "learning_rate": 0.00016396343861173356,
      "loss": 0.5960753560066223,
      "step": 4790
    },
    {
      "epoch": 2.021940928270042,
      "grad_norm": 0.4297144412994385,
      "learning_rate": 0.00016392651215267785,
      "loss": 0.5696688890457153,
      "step": 4792
    },
    {
      "epoch": 2.0227848101265824,
      "grad_norm": 0.4521540701389313,
      "learning_rate": 0.00016388957094700356,
      "loss": 0.6610676050186157,
      "step": 4794
    },
    {
      "epoch": 2.0236286919831223,
      "grad_norm": 0.41184982657432556,
      "learning_rate": 0.00016385261500323224,
      "loss": 0.5387522578239441,
      "step": 4796
    },
    {
      "epoch": 2.0244725738396623,
      "grad_norm": 0.489391565322876,
      "learning_rate": 0.00016381564432988897,
      "loss": 0.6614878177642822,
      "step": 4798
    },
    {
      "epoch": 2.0253164556962027,
      "grad_norm": 0.3741590678691864,
      "learning_rate": 0.00016377865893550214,
      "loss": 0.5513694286346436,
      "step": 4800
    },
    {
      "epoch": 2.0253164556962027,
      "eval_loss": 0.7633068561553955,
      "eval_runtime": 688.8684,
      "eval_samples_per_second": 3.059,
      "eval_steps_per_second": 3.059,
      "step": 4800
    },
    {
      "epoch": 2.0261603375527426,
      "grad_norm": 0.45757874846458435,
      "learning_rate": 0.0001637416588286036,
      "loss": 0.5732831358909607,
      "step": 4802
    },
    {
      "epoch": 2.0270042194092825,
      "grad_norm": 0.4009305238723755,
      "learning_rate": 0.00016370464401772853,
      "loss": 0.5994226932525635,
      "step": 4804
    },
    {
      "epoch": 2.027848101265823,
      "grad_norm": 0.44907137751579285,
      "learning_rate": 0.0001636676145114156,
      "loss": 0.6229469776153564,
      "step": 4806
    },
    {
      "epoch": 2.028691983122363,
      "grad_norm": 0.4153282344341278,
      "learning_rate": 0.00016363057031820673,
      "loss": 0.5126086473464966,
      "step": 4808
    },
    {
      "epoch": 2.029535864978903,
      "grad_norm": 0.41859957575798035,
      "learning_rate": 0.0001635935114466473,
      "loss": 0.5779650211334229,
      "step": 4810
    },
    {
      "epoch": 2.030379746835443,
      "grad_norm": 0.44624394178390503,
      "learning_rate": 0.00016355643790528617,
      "loss": 0.5561378598213196,
      "step": 4812
    },
    {
      "epoch": 2.031223628691983,
      "grad_norm": 0.44554266333580017,
      "learning_rate": 0.00016351934970267542,
      "loss": 0.5381612181663513,
      "step": 4814
    },
    {
      "epoch": 2.032067510548523,
      "grad_norm": 0.4529551565647125,
      "learning_rate": 0.00016348224684737065,
      "loss": 0.6434502601623535,
      "step": 4816
    },
    {
      "epoch": 2.0329113924050635,
      "grad_norm": 0.891188383102417,
      "learning_rate": 0.00016344512934793066,
      "loss": 0.6316392421722412,
      "step": 4818
    },
    {
      "epoch": 2.0337552742616034,
      "grad_norm": 0.4621472656726837,
      "learning_rate": 0.00016340799721291783,
      "loss": 0.5569570064544678,
      "step": 4820
    },
    {
      "epoch": 2.0345991561181433,
      "grad_norm": 0.38671162724494934,
      "learning_rate": 0.00016337085045089786,
      "loss": 0.5403776168823242,
      "step": 4822
    },
    {
      "epoch": 2.0354430379746837,
      "grad_norm": 0.3896256685256958,
      "learning_rate": 0.00016333368907043972,
      "loss": 0.5629472732543945,
      "step": 4824
    },
    {
      "epoch": 2.0362869198312237,
      "grad_norm": 0.4890784025192261,
      "learning_rate": 0.00016329651308011583,
      "loss": 0.5740808844566345,
      "step": 4826
    },
    {
      "epoch": 2.0371308016877636,
      "grad_norm": 0.493118554353714,
      "learning_rate": 0.00016325932248850207,
      "loss": 0.6362084746360779,
      "step": 4828
    },
    {
      "epoch": 2.037974683544304,
      "grad_norm": 0.4112105965614319,
      "learning_rate": 0.0001632221173041775,
      "loss": 0.5512531399726868,
      "step": 4830
    },
    {
      "epoch": 2.038818565400844,
      "grad_norm": 0.48197677731513977,
      "learning_rate": 0.00016318489753572464,
      "loss": 0.5507554411888123,
      "step": 4832
    },
    {
      "epoch": 2.039662447257384,
      "grad_norm": 0.5130576491355896,
      "learning_rate": 0.00016314766319172947,
      "loss": 0.7607873678207397,
      "step": 4834
    },
    {
      "epoch": 2.0405063291139243,
      "grad_norm": 0.4454704523086548,
      "learning_rate": 0.00016311041428078112,
      "loss": 0.6044831275939941,
      "step": 4836
    },
    {
      "epoch": 2.041350210970464,
      "grad_norm": 0.4688933789730072,
      "learning_rate": 0.00016307315081147227,
      "loss": 0.587941586971283,
      "step": 4838
    },
    {
      "epoch": 2.042194092827004,
      "grad_norm": 0.45465248823165894,
      "learning_rate": 0.0001630358727923989,
      "loss": 0.5822482109069824,
      "step": 4840
    },
    {
      "epoch": 2.043037974683544,
      "grad_norm": 0.4670163691043854,
      "learning_rate": 0.00016299858023216028,
      "loss": 0.584092378616333,
      "step": 4842
    },
    {
      "epoch": 2.0438818565400845,
      "grad_norm": 0.43894922733306885,
      "learning_rate": 0.0001629612731393591,
      "loss": 0.5876650214195251,
      "step": 4844
    },
    {
      "epoch": 2.0447257383966244,
      "grad_norm": 0.4144253730773926,
      "learning_rate": 0.0001629239515226014,
      "loss": 0.5628184676170349,
      "step": 4846
    },
    {
      "epoch": 2.0455696202531644,
      "grad_norm": 0.47422146797180176,
      "learning_rate": 0.0001628866153904966,
      "loss": 0.6156699657440186,
      "step": 4848
    },
    {
      "epoch": 2.0464135021097047,
      "grad_norm": 0.46102508902549744,
      "learning_rate": 0.00016284926475165735,
      "loss": 0.5761739015579224,
      "step": 4850
    },
    {
      "epoch": 2.0472573839662447,
      "grad_norm": 0.4987565577030182,
      "learning_rate": 0.00016281189961469977,
      "loss": 0.6326378583908081,
      "step": 4852
    },
    {
      "epoch": 2.0481012658227846,
      "grad_norm": 0.46640047430992126,
      "learning_rate": 0.0001627745199882433,
      "loss": 0.6072084903717041,
      "step": 4854
    },
    {
      "epoch": 2.048945147679325,
      "grad_norm": 0.5362635254859924,
      "learning_rate": 0.00016273712588091066,
      "loss": 0.6507929563522339,
      "step": 4856
    },
    {
      "epoch": 2.049789029535865,
      "grad_norm": 0.459285706281662,
      "learning_rate": 0.00016269971730132796,
      "loss": 0.6264472007751465,
      "step": 4858
    },
    {
      "epoch": 2.050632911392405,
      "grad_norm": 0.4467318058013916,
      "learning_rate": 0.00016266229425812467,
      "loss": 0.6185184717178345,
      "step": 4860
    },
    {
      "epoch": 2.0514767932489453,
      "grad_norm": 0.4965224266052246,
      "learning_rate": 0.0001626248567599335,
      "loss": 0.5723293423652649,
      "step": 4862
    },
    {
      "epoch": 2.052320675105485,
      "grad_norm": 0.46917736530303955,
      "learning_rate": 0.0001625874048153907,
      "loss": 0.578831672668457,
      "step": 4864
    },
    {
      "epoch": 2.053164556962025,
      "grad_norm": 0.498439222574234,
      "learning_rate": 0.00016254993843313554,
      "loss": 0.6448227763175964,
      "step": 4866
    },
    {
      "epoch": 2.0540084388185655,
      "grad_norm": 0.4801621735095978,
      "learning_rate": 0.00016251245762181088,
      "loss": 0.6240531802177429,
      "step": 4868
    },
    {
      "epoch": 2.0548523206751055,
      "grad_norm": 0.3652440309524536,
      "learning_rate": 0.00016247496239006287,
      "loss": 0.4955635070800781,
      "step": 4870
    },
    {
      "epoch": 2.0556962025316454,
      "grad_norm": 0.504094123840332,
      "learning_rate": 0.00016243745274654084,
      "loss": 0.6184053421020508,
      "step": 4872
    },
    {
      "epoch": 2.056540084388186,
      "grad_norm": 0.4311911463737488,
      "learning_rate": 0.0001623999286998976,
      "loss": 0.5592952370643616,
      "step": 4874
    },
    {
      "epoch": 2.0573839662447257,
      "grad_norm": 0.5173681974411011,
      "learning_rate": 0.00016236239025878928,
      "loss": 0.6024063229560852,
      "step": 4876
    },
    {
      "epoch": 2.0582278481012657,
      "grad_norm": 0.41021528840065,
      "learning_rate": 0.0001623248374318752,
      "loss": 0.5788836479187012,
      "step": 4878
    },
    {
      "epoch": 2.059071729957806,
      "grad_norm": 0.5167528986930847,
      "learning_rate": 0.00016228727022781807,
      "loss": 0.6215962767601013,
      "step": 4880
    },
    {
      "epoch": 2.059915611814346,
      "grad_norm": 0.5254554152488708,
      "learning_rate": 0.00016224968865528395,
      "loss": 0.5767302513122559,
      "step": 4882
    },
    {
      "epoch": 2.060759493670886,
      "grad_norm": 0.3826330602169037,
      "learning_rate": 0.00016221209272294218,
      "loss": 0.5494593381881714,
      "step": 4884
    },
    {
      "epoch": 2.0616033755274263,
      "grad_norm": 0.48100414872169495,
      "learning_rate": 0.00016217448243946542,
      "loss": 0.5395565032958984,
      "step": 4886
    },
    {
      "epoch": 2.0624472573839663,
      "grad_norm": 0.4237285852432251,
      "learning_rate": 0.00016213685781352966,
      "loss": 0.5737000107765198,
      "step": 4888
    },
    {
      "epoch": 2.0632911392405062,
      "grad_norm": 0.46409112215042114,
      "learning_rate": 0.0001620992188538142,
      "loss": 0.6150708794593811,
      "step": 4890
    },
    {
      "epoch": 2.0641350210970466,
      "grad_norm": 0.5053852200508118,
      "learning_rate": 0.0001620615655690015,
      "loss": 0.5868361592292786,
      "step": 4892
    },
    {
      "epoch": 2.0649789029535865,
      "grad_norm": 0.4552644193172455,
      "learning_rate": 0.00016202389796777763,
      "loss": 0.543509304523468,
      "step": 4894
    },
    {
      "epoch": 2.0658227848101265,
      "grad_norm": 0.49399474263191223,
      "learning_rate": 0.00016198621605883164,
      "loss": 0.6006189584732056,
      "step": 4896
    },
    {
      "epoch": 2.066666666666667,
      "grad_norm": 0.4846300184726715,
      "learning_rate": 0.00016194851985085608,
      "loss": 0.6238788962364197,
      "step": 4898
    },
    {
      "epoch": 2.067510548523207,
      "grad_norm": 0.4207721948623657,
      "learning_rate": 0.00016191080935254673,
      "loss": 0.5164834856987,
      "step": 4900
    },
    {
      "epoch": 2.067510548523207,
      "eval_loss": 0.7676681280136108,
      "eval_runtime": 676.0104,
      "eval_samples_per_second": 3.117,
      "eval_steps_per_second": 3.117,
      "step": 4900
    },
    {
      "epoch": 2.0683544303797468,
      "grad_norm": 0.49213138222694397,
      "learning_rate": 0.00016187308457260268,
      "loss": 0.6363024115562439,
      "step": 4902
    },
    {
      "epoch": 2.0691983122362867,
      "grad_norm": 0.4619614779949188,
      "learning_rate": 0.00016183534551972634,
      "loss": 0.5472462177276611,
      "step": 4904
    },
    {
      "epoch": 2.070042194092827,
      "grad_norm": 0.45133984088897705,
      "learning_rate": 0.00016179759220262335,
      "loss": 0.5588397979736328,
      "step": 4906
    },
    {
      "epoch": 2.070886075949367,
      "grad_norm": 0.43284907937049866,
      "learning_rate": 0.00016175982463000266,
      "loss": 0.6439877152442932,
      "step": 4908
    },
    {
      "epoch": 2.071729957805907,
      "grad_norm": 0.4439920485019684,
      "learning_rate": 0.00016172204281057656,
      "loss": 0.5987089276313782,
      "step": 4910
    },
    {
      "epoch": 2.0725738396624473,
      "grad_norm": 0.376004695892334,
      "learning_rate": 0.0001616842467530606,
      "loss": 0.53819739818573,
      "step": 4912
    },
    {
      "epoch": 2.0734177215189873,
      "grad_norm": 0.42577606439590454,
      "learning_rate": 0.00016164643646617358,
      "loss": 0.5739918947219849,
      "step": 4914
    },
    {
      "epoch": 2.0742616033755272,
      "grad_norm": 0.4607972502708435,
      "learning_rate": 0.00016160861195863756,
      "loss": 0.580957293510437,
      "step": 4916
    },
    {
      "epoch": 2.0751054852320676,
      "grad_norm": 0.4114130735397339,
      "learning_rate": 0.00016157077323917802,
      "loss": 0.6063762903213501,
      "step": 4918
    },
    {
      "epoch": 2.0759493670886076,
      "grad_norm": 0.4415706694126129,
      "learning_rate": 0.00016153292031652358,
      "loss": 0.5996072292327881,
      "step": 4920
    },
    {
      "epoch": 2.0767932489451475,
      "grad_norm": 0.5539509654045105,
      "learning_rate": 0.00016149505319940617,
      "loss": 0.6442107558250427,
      "step": 4922
    },
    {
      "epoch": 2.077637130801688,
      "grad_norm": 0.510313868522644,
      "learning_rate": 0.00016145717189656105,
      "loss": 0.6175990104675293,
      "step": 4924
    },
    {
      "epoch": 2.078481012658228,
      "grad_norm": 0.442271888256073,
      "learning_rate": 0.00016141927641672666,
      "loss": 0.6108829975128174,
      "step": 4926
    },
    {
      "epoch": 2.0793248945147678,
      "grad_norm": 0.4499345123767853,
      "learning_rate": 0.00016138136676864477,
      "loss": 0.6193580031394958,
      "step": 4928
    },
    {
      "epoch": 2.080168776371308,
      "grad_norm": 0.36362606287002563,
      "learning_rate": 0.00016134344296106043,
      "loss": 0.5283842086791992,
      "step": 4930
    },
    {
      "epoch": 2.081012658227848,
      "grad_norm": 0.460282564163208,
      "learning_rate": 0.00016130550500272195,
      "loss": 0.5338225960731506,
      "step": 4932
    },
    {
      "epoch": 2.081856540084388,
      "grad_norm": 0.4316645860671997,
      "learning_rate": 0.0001612675529023808,
      "loss": 0.6192039251327515,
      "step": 4934
    },
    {
      "epoch": 2.0827004219409284,
      "grad_norm": 0.4333813488483429,
      "learning_rate": 0.0001612295866687919,
      "loss": 0.5953296422958374,
      "step": 4936
    },
    {
      "epoch": 2.0835443037974684,
      "grad_norm": 0.560342013835907,
      "learning_rate": 0.0001611916063107133,
      "loss": 0.6765958070755005,
      "step": 4938
    },
    {
      "epoch": 2.0843881856540083,
      "grad_norm": 0.4263869822025299,
      "learning_rate": 0.00016115361183690631,
      "loss": 0.5475618243217468,
      "step": 4940
    },
    {
      "epoch": 2.0852320675105487,
      "grad_norm": 0.41631078720092773,
      "learning_rate": 0.00016111560325613553,
      "loss": 0.570278525352478,
      "step": 4942
    },
    {
      "epoch": 2.0860759493670886,
      "grad_norm": 0.3922317326068878,
      "learning_rate": 0.00016107758057716884,
      "loss": 0.5691710710525513,
      "step": 4944
    },
    {
      "epoch": 2.0869198312236286,
      "grad_norm": 0.518889307975769,
      "learning_rate": 0.00016103954380877736,
      "loss": 0.6014654040336609,
      "step": 4946
    },
    {
      "epoch": 2.087763713080169,
      "grad_norm": 0.560624897480011,
      "learning_rate": 0.00016100149295973537,
      "loss": 0.6084938049316406,
      "step": 4948
    },
    {
      "epoch": 2.088607594936709,
      "grad_norm": 0.46847012639045715,
      "learning_rate": 0.00016096342803882053,
      "loss": 0.6078231334686279,
      "step": 4950
    },
    {
      "epoch": 2.089451476793249,
      "grad_norm": 0.43910443782806396,
      "learning_rate": 0.00016092534905481367,
      "loss": 0.5664147734642029,
      "step": 4952
    },
    {
      "epoch": 2.090295358649789,
      "grad_norm": 0.40413206815719604,
      "learning_rate": 0.00016088725601649887,
      "loss": 0.5793747901916504,
      "step": 4954
    },
    {
      "epoch": 2.091139240506329,
      "grad_norm": 0.47664782404899597,
      "learning_rate": 0.00016084914893266347,
      "loss": 0.6121629476547241,
      "step": 4956
    },
    {
      "epoch": 2.091983122362869,
      "grad_norm": 0.4575684070587158,
      "learning_rate": 0.00016081102781209805,
      "loss": 0.6086400747299194,
      "step": 4958
    },
    {
      "epoch": 2.0928270042194095,
      "grad_norm": 0.4286920726299286,
      "learning_rate": 0.0001607728926635964,
      "loss": 0.5971894860267639,
      "step": 4960
    },
    {
      "epoch": 2.0936708860759494,
      "grad_norm": 0.5314067006111145,
      "learning_rate": 0.00016073474349595555,
      "loss": 0.6195604801177979,
      "step": 4962
    },
    {
      "epoch": 2.0945147679324894,
      "grad_norm": 0.5221946239471436,
      "learning_rate": 0.00016069658031797585,
      "loss": 0.6141531467437744,
      "step": 4964
    },
    {
      "epoch": 2.0953586497890297,
      "grad_norm": 0.46874696016311646,
      "learning_rate": 0.00016065840313846076,
      "loss": 0.6354720592498779,
      "step": 4966
    },
    {
      "epoch": 2.0962025316455697,
      "grad_norm": 0.44518616795539856,
      "learning_rate": 0.00016062021196621703,
      "loss": 0.5759334564208984,
      "step": 4968
    },
    {
      "epoch": 2.0970464135021096,
      "grad_norm": 0.44092273712158203,
      "learning_rate": 0.00016058200681005462,
      "loss": 0.5387811064720154,
      "step": 4970
    },
    {
      "epoch": 2.09789029535865,
      "grad_norm": 0.4952426552772522,
      "learning_rate": 0.00016054378767878678,
      "loss": 0.5712288022041321,
      "step": 4972
    },
    {
      "epoch": 2.09873417721519,
      "grad_norm": 0.4890255331993103,
      "learning_rate": 0.00016050555458122984,
      "loss": 0.6320934891700745,
      "step": 4974
    },
    {
      "epoch": 2.09957805907173,
      "grad_norm": 0.5182738304138184,
      "learning_rate": 0.00016046730752620352,
      "loss": 0.6141278147697449,
      "step": 4976
    },
    {
      "epoch": 2.10042194092827,
      "grad_norm": 0.5344594717025757,
      "learning_rate": 0.00016042904652253064,
      "loss": 0.6079437732696533,
      "step": 4978
    },
    {
      "epoch": 2.1012658227848102,
      "grad_norm": 0.436641126871109,
      "learning_rate": 0.0001603907715790373,
      "loss": 0.5634552836418152,
      "step": 4980
    },
    {
      "epoch": 2.10210970464135,
      "grad_norm": 0.44045236706733704,
      "learning_rate": 0.00016035248270455273,
      "loss": 0.5707821846008301,
      "step": 4982
    },
    {
      "epoch": 2.10295358649789,
      "grad_norm": 0.43434852361679077,
      "learning_rate": 0.00016031417990790953,
      "loss": 0.5635452270507812,
      "step": 4984
    },
    {
      "epoch": 2.1037974683544305,
      "grad_norm": 0.5538138747215271,
      "learning_rate": 0.00016027586319794341,
      "loss": 0.632486879825592,
      "step": 4986
    },
    {
      "epoch": 2.1046413502109704,
      "grad_norm": 0.5425865054130554,
      "learning_rate": 0.00016023753258349323,
      "loss": 0.6509168744087219,
      "step": 4988
    },
    {
      "epoch": 2.1054852320675104,
      "grad_norm": 0.4603687524795532,
      "learning_rate": 0.0001601991880734012,
      "loss": 0.615444540977478,
      "step": 4990
    },
    {
      "epoch": 2.1063291139240508,
      "grad_norm": 0.4866391718387604,
      "learning_rate": 0.0001601608296765126,
      "loss": 0.684465765953064,
      "step": 4992
    },
    {
      "epoch": 2.1071729957805907,
      "grad_norm": 0.47539305686950684,
      "learning_rate": 0.000160122457401676,
      "loss": 0.5981772541999817,
      "step": 4994
    },
    {
      "epoch": 2.1080168776371306,
      "grad_norm": 0.4135447144508362,
      "learning_rate": 0.00016008407125774315,
      "loss": 0.6041272878646851,
      "step": 4996
    },
    {
      "epoch": 2.108860759493671,
      "grad_norm": 0.5324689745903015,
      "learning_rate": 0.00016004567125356905,
      "loss": 0.6491074562072754,
      "step": 4998
    },
    {
      "epoch": 2.109704641350211,
      "grad_norm": 0.4004698395729065,
      "learning_rate": 0.00016000725739801172,
      "loss": 0.6178454756736755,
      "step": 5000
    },
    {
      "epoch": 2.109704641350211,
      "eval_loss": 0.7635271549224854,
      "eval_runtime": 669.5049,
      "eval_samples_per_second": 3.147,
      "eval_steps_per_second": 3.147,
      "step": 5000
    }
  ],
  "logging_steps": 2,
  "max_steps": 14220,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.001
      },
      "attributes": {
        "early_stopping_patience_counter": 4
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.9899897855995863e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}