{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 100,
  "global_step": 1026,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0029239766081871343,
      "grad_norm": 6.1624870962638925,
      "learning_rate": 1.941747572815534e-07,
      "loss": 0.913,
      "step": 1
    },
    {
      "epoch": 0.014619883040935672,
      "grad_norm": 11.812860926129314,
      "learning_rate": 9.70873786407767e-07,
      "loss": 0.8859,
      "step": 5
    },
    {
      "epoch": 0.029239766081871343,
      "grad_norm": 2.6140064947786015,
      "learning_rate": 1.941747572815534e-06,
      "loss": 0.8409,
      "step": 10
    },
    {
      "epoch": 0.043859649122807015,
      "grad_norm": 2.2391899324318154,
      "learning_rate": 2.912621359223301e-06,
      "loss": 0.8325,
      "step": 15
    },
    {
      "epoch": 0.05847953216374269,
      "grad_norm": 2.11742528178852,
      "learning_rate": 3.883495145631068e-06,
      "loss": 0.8169,
      "step": 20
    },
    {
      "epoch": 0.07309941520467836,
      "grad_norm": 2.088530291916816,
      "learning_rate": 4.854368932038836e-06,
      "loss": 0.8168,
      "step": 25
    },
    {
      "epoch": 0.08771929824561403,
      "grad_norm": 2.028716635962563,
      "learning_rate": 5.825242718446602e-06,
      "loss": 0.8075,
      "step": 30
    },
    {
      "epoch": 0.1023391812865497,
      "grad_norm": 2.3256620167562234,
      "learning_rate": 6.79611650485437e-06,
      "loss": 0.7953,
      "step": 35
    },
    {
      "epoch": 0.11695906432748537,
      "grad_norm": 2.349007546868107,
      "learning_rate": 7.766990291262136e-06,
      "loss": 0.7841,
      "step": 40
    },
    {
      "epoch": 0.13157894736842105,
      "grad_norm": 2.2423399474385666,
      "learning_rate": 8.737864077669904e-06,
      "loss": 0.7888,
      "step": 45
    },
    {
      "epoch": 0.14619883040935672,
      "grad_norm": 1.942782247095399,
      "learning_rate": 9.708737864077671e-06,
      "loss": 0.8042,
      "step": 50
    },
    {
      "epoch": 0.1608187134502924,
      "grad_norm": 2.1945226195890033,
      "learning_rate": 1.0679611650485437e-05,
      "loss": 0.8018,
      "step": 55
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 1.8960792380527152,
      "learning_rate": 1.1650485436893204e-05,
      "loss": 0.7832,
      "step": 60
    },
    {
      "epoch": 0.19005847953216373,
      "grad_norm": 2.050931671194075,
      "learning_rate": 1.2621359223300974e-05,
      "loss": 0.8048,
      "step": 65
    },
    {
      "epoch": 0.2046783625730994,
      "grad_norm": 2.0914042301099043,
      "learning_rate": 1.359223300970874e-05,
      "loss": 0.7988,
      "step": 70
    },
    {
      "epoch": 0.21929824561403508,
      "grad_norm": 2.1780402538204804,
      "learning_rate": 1.4563106796116507e-05,
      "loss": 0.8046,
      "step": 75
    },
    {
      "epoch": 0.23391812865497075,
      "grad_norm": 2.2507384711871077,
      "learning_rate": 1.5533980582524273e-05,
      "loss": 0.8101,
      "step": 80
    },
    {
      "epoch": 0.24853801169590642,
      "grad_norm": 2.0740107954310987,
      "learning_rate": 1.650485436893204e-05,
      "loss": 0.7992,
      "step": 85
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 2.1703649782676426,
      "learning_rate": 1.7475728155339808e-05,
      "loss": 0.8168,
      "step": 90
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 2.4978786575354817,
      "learning_rate": 1.8446601941747575e-05,
      "loss": 0.806,
      "step": 95
    },
    {
      "epoch": 0.29239766081871343,
      "grad_norm": 2.0698254347384983,
      "learning_rate": 1.9417475728155343e-05,
      "loss": 0.8286,
      "step": 100
    },
    {
      "epoch": 0.29239766081871343,
      "eval_loss": 0.8580158948898315,
      "eval_runtime": 94.9126,
      "eval_samples_per_second": 22.99,
      "eval_steps_per_second": 0.369,
      "step": 100
    },
    {
      "epoch": 0.30701754385964913,
      "grad_norm": 2.0735037748593723,
      "learning_rate": 1.999976830073192e-05,
      "loss": 0.8281,
      "step": 105
    },
    {
      "epoch": 0.3216374269005848,
      "grad_norm": 2.095073626207817,
      "learning_rate": 1.99971618072711e-05,
      "loss": 0.8174,
      "step": 110
    },
    {
      "epoch": 0.3362573099415205,
      "grad_norm": 2.1603082170396455,
      "learning_rate": 1.9991659953668803e-05,
      "loss": 0.8217,
      "step": 115
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 2.0326092354167637,
      "learning_rate": 1.998326433336204e-05,
      "loss": 0.8381,
      "step": 120
    },
    {
      "epoch": 0.3654970760233918,
      "grad_norm": 2.226630427942925,
      "learning_rate": 1.997197737787537e-05,
      "loss": 0.8261,
      "step": 125
    },
    {
      "epoch": 0.38011695906432746,
      "grad_norm": 2.119406491731454,
      "learning_rate": 1.9957802356116665e-05,
      "loss": 0.8208,
      "step": 130
    },
    {
      "epoch": 0.39473684210526316,
      "grad_norm": 2.8253278464362084,
      "learning_rate": 1.994074337343041e-05,
      "loss": 0.8129,
      "step": 135
    },
    {
      "epoch": 0.4093567251461988,
      "grad_norm": 2.4882232695538464,
      "learning_rate": 1.9920805370408695e-05,
      "loss": 0.8135,
      "step": 140
    },
    {
      "epoch": 0.4239766081871345,
      "grad_norm": 4.780582760365185,
      "learning_rate": 1.9897994121460322e-05,
      "loss": 0.8364,
      "step": 145
    },
    {
      "epoch": 0.43859649122807015,
      "grad_norm": 11.5182408239238,
      "learning_rate": 1.9872316233138463e-05,
      "loss": 0.8277,
      "step": 150
    },
    {
      "epoch": 0.45321637426900585,
      "grad_norm": 12.627096663789404,
      "learning_rate": 1.9843779142227258e-05,
      "loss": 0.8196,
      "step": 155
    },
    {
      "epoch": 0.4678362573099415,
      "grad_norm": 2.740111270404608,
      "learning_rate": 1.981239111358799e-05,
      "loss": 0.8042,
      "step": 160
    },
    {
      "epoch": 0.4824561403508772,
      "grad_norm": 2.174778620165311,
      "learning_rate": 1.9778161237765438e-05,
      "loss": 0.8064,
      "step": 165
    },
    {
      "epoch": 0.49707602339181284,
      "grad_norm": 1.9246861870071321,
      "learning_rate": 1.9741099428355075e-05,
      "loss": 0.8024,
      "step": 170
    },
    {
      "epoch": 0.5116959064327485,
      "grad_norm": 9.798315852556506,
      "learning_rate": 1.9701216419131934e-05,
      "loss": 0.8352,
      "step": 175
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 2.9139360459829082,
      "learning_rate": 1.9658523760941882e-05,
      "loss": 0.8033,
      "step": 180
    },
    {
      "epoch": 0.5409356725146199,
      "grad_norm": 14.543721579870974,
      "learning_rate": 1.9613033818356322e-05,
      "loss": 0.8631,
      "step": 185
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 11.532560091003726,
      "learning_rate": 1.956475976609114e-05,
      "loss": 0.8304,
      "step": 190
    },
    {
      "epoch": 0.5701754385964912,
      "grad_norm": 10.191690209836944,
      "learning_rate": 1.951371558519111e-05,
      "loss": 0.8021,
      "step": 195
    },
    {
      "epoch": 0.5847953216374269,
      "grad_norm": 2.490323350347935,
      "learning_rate": 1.9459916058980707e-05,
      "loss": 0.798,
      "step": 200
    },
    {
      "epoch": 0.5847953216374269,
      "eval_loss": 0.8706345558166504,
      "eval_runtime": 94.8283,
      "eval_samples_per_second": 23.01,
      "eval_steps_per_second": 0.369,
      "step": 200
    },
    {
      "epoch": 0.5994152046783626,
      "grad_norm": 2.025711297854962,
      "learning_rate": 1.9403376768782592e-05,
      "loss": 0.7884,
      "step": 205
    },
    {
      "epoch": 0.6140350877192983,
      "grad_norm": 1.9488358870140705,
      "learning_rate": 1.9344114089404983e-05,
      "loss": 0.7804,
      "step": 210
    },
    {
      "epoch": 0.6286549707602339,
      "grad_norm": 1.8564140890417253,
      "learning_rate": 1.9282145184399197e-05,
      "loss": 0.808,
      "step": 215
    },
    {
      "epoch": 0.6432748538011696,
      "grad_norm": 2.0881170345282727,
      "learning_rate": 1.9217488001088784e-05,
      "loss": 0.799,
      "step": 220
    },
    {
      "epoch": 0.6578947368421053,
      "grad_norm": 1.9678597098298427,
      "learning_rate": 1.9150161265371663e-05,
      "loss": 0.795,
      "step": 225
    },
    {
      "epoch": 0.672514619883041,
      "grad_norm": 2.865460519803586,
      "learning_rate": 1.908018447629674e-05,
      "loss": 0.7915,
      "step": 230
    },
    {
      "epoch": 0.6871345029239766,
      "grad_norm": 2.398699191637217,
      "learning_rate": 1.9007577900416648e-05,
      "loss": 0.7814,
      "step": 235
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 2.1260051093101353,
      "learning_rate": 1.8932362565918167e-05,
      "loss": 0.7983,
      "step": 240
    },
    {
      "epoch": 0.716374269005848,
      "grad_norm": 5.80073712189035,
      "learning_rate": 1.8854560256532098e-05,
      "loss": 0.7691,
      "step": 245
    },
    {
      "epoch": 0.7309941520467836,
      "grad_norm": 2.5341535901655896,
      "learning_rate": 1.877419350522429e-05,
      "loss": 0.8155,
      "step": 250
    },
    {
      "epoch": 0.7456140350877193,
      "grad_norm": 1.95626689403789,
      "learning_rate": 1.869128558766965e-05,
      "loss": 0.7878,
      "step": 255
    },
    {
      "epoch": 0.7602339181286549,
      "grad_norm": 15.120401535093198,
      "learning_rate": 1.8605860515511158e-05,
      "loss": 0.7883,
      "step": 260
    },
    {
      "epoch": 0.7748538011695907,
      "grad_norm": 2.2607309079656135,
      "learning_rate": 1.8517943029405577e-05,
      "loss": 0.7999,
      "step": 265
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 2.295750513860874,
      "learning_rate": 1.8427558591858164e-05,
      "loss": 0.7697,
      "step": 270
    },
    {
      "epoch": 0.804093567251462,
      "grad_norm": 4.1135088544849445,
      "learning_rate": 1.833473337984823e-05,
      "loss": 0.8065,
      "step": 275
    },
    {
      "epoch": 0.8187134502923976,
      "grad_norm": 3.2241188905244895,
      "learning_rate": 1.823949427724785e-05,
      "loss": 0.799,
      "step": 280
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 1.6843445283218286,
      "learning_rate": 1.8141868867035745e-05,
      "loss": 0.7909,
      "step": 285
    },
    {
      "epoch": 0.847953216374269,
      "grad_norm": 1.7626650921963332,
      "learning_rate": 1.8041885423308808e-05,
      "loss": 0.781,
      "step": 290
    },
    {
      "epoch": 0.8625730994152047,
      "grad_norm": 10.38812175281534,
      "learning_rate": 1.7939572903093383e-05,
      "loss": 0.7923,
      "step": 295
    },
    {
      "epoch": 0.8771929824561403,
      "grad_norm": 3.1451964354292596,
      "learning_rate": 1.7834960937958775e-05,
      "loss": 0.7677,
      "step": 300
    },
    {
      "epoch": 0.8771929824561403,
      "eval_loss": 0.8726791739463806,
      "eval_runtime": 93.9416,
      "eval_samples_per_second": 23.227,
      "eval_steps_per_second": 0.373,
      "step": 300
    },
    {
      "epoch": 0.8918128654970761,
      "grad_norm": 1.9970765983454766,
      "learning_rate": 1.7728079825435426e-05,
      "loss": 0.7966,
      "step": 305
    },
    {
      "epoch": 0.9064327485380117,
      "grad_norm": 1.8313570465257998,
      "learning_rate": 1.761896052024019e-05,
      "loss": 0.7784,
      "step": 310
    },
    {
      "epoch": 0.9210526315789473,
      "grad_norm": 2.028945141590537,
      "learning_rate": 1.7507634625311283e-05,
      "loss": 0.7569,
      "step": 315
    },
    {
      "epoch": 0.935672514619883,
      "grad_norm": 3.1385176933971706,
      "learning_rate": 1.7394134382655496e-05,
      "loss": 0.7805,
      "step": 320
    },
    {
      "epoch": 0.9502923976608187,
      "grad_norm": 1.7723196199368927,
      "learning_rate": 1.7278492664010326e-05,
      "loss": 0.7681,
      "step": 325
    },
    {
      "epoch": 0.9649122807017544,
      "grad_norm": 1.7577488585231846,
      "learning_rate": 1.7160742961323714e-05,
      "loss": 0.7672,
      "step": 330
    },
    {
      "epoch": 0.97953216374269,
      "grad_norm": 2.3636063665348757,
      "learning_rate": 1.7040919377054182e-05,
      "loss": 0.7795,
      "step": 335
    },
    {
      "epoch": 0.9941520467836257,
      "grad_norm": 1.7709587208644213,
      "learning_rate": 1.6919056614294133e-05,
      "loss": 0.7624,
      "step": 340
    },
    {
      "epoch": 1.0087719298245614,
      "grad_norm": 3.8073195101773765,
      "learning_rate": 1.6795189966719182e-05,
      "loss": 0.6426,
      "step": 345
    },
    {
      "epoch": 1.023391812865497,
      "grad_norm": 2.787413972058394,
      "learning_rate": 1.666935530836651e-05,
      "loss": 0.5366,
      "step": 350
    },
    {
      "epoch": 1.0380116959064327,
      "grad_norm": 2.362170165993678,
      "learning_rate": 1.654158908324504e-05,
      "loss": 0.5377,
      "step": 355
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 2.311139734884461,
      "learning_rate": 1.6411928294780626e-05,
      "loss": 0.5252,
      "step": 360
    },
    {
      "epoch": 1.067251461988304,
      "grad_norm": 1.886267380269756,
      "learning_rate": 1.6280410495099165e-05,
      "loss": 0.5028,
      "step": 365
    },
    {
      "epoch": 1.0818713450292399,
      "grad_norm": 1.8701236760118256,
      "learning_rate": 1.6147073774150834e-05,
      "loss": 0.5121,
      "step": 370
    },
    {
      "epoch": 1.0964912280701755,
      "grad_norm": 1.7743194110147134,
      "learning_rate": 1.601195674867853e-05,
      "loss": 0.5189,
      "step": 375
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 36.55479744540479,
      "learning_rate": 1.5875098551033765e-05,
      "loss": 0.5071,
      "step": 380
    },
    {
      "epoch": 1.1257309941520468,
      "grad_norm": 2.1840870340337823,
      "learning_rate": 1.5736538817843228e-05,
      "loss": 0.5489,
      "step": 385
    },
    {
      "epoch": 1.1403508771929824,
      "grad_norm": 2.096047543627006,
      "learning_rate": 1.559631767852929e-05,
      "loss": 0.5115,
      "step": 390
    },
    {
      "epoch": 1.154970760233918,
      "grad_norm": 8.700584160621043,
      "learning_rate": 1.54544757436878e-05,
      "loss": 0.5061,
      "step": 395
    },
    {
      "epoch": 1.1695906432748537,
      "grad_norm": 1.7774756036197978,
      "learning_rate": 1.5311054093326508e-05,
      "loss": 0.5584,
      "step": 400
    },
    {
      "epoch": 1.1695906432748537,
      "eval_loss": 0.9159147143363953,
      "eval_runtime": 94.2366,
      "eval_samples_per_second": 23.154,
      "eval_steps_per_second": 0.371,
      "step": 400
    },
    {
      "epoch": 1.1842105263157894,
      "grad_norm": 2.550427212943654,
      "learning_rate": 1.5166094264967553e-05,
      "loss": 0.5166,
      "step": 405
    },
    {
      "epoch": 1.198830409356725,
      "grad_norm": 1.9907997528305226,
      "learning_rate": 1.5019638241617429e-05,
      "loss": 0.5131,
      "step": 410
    },
    {
      "epoch": 1.213450292397661,
      "grad_norm": 1.7648223360572315,
      "learning_rate": 1.4871728439607967e-05,
      "loss": 0.5182,
      "step": 415
    },
    {
      "epoch": 1.2280701754385965,
      "grad_norm": 2.23899567188947,
      "learning_rate": 1.472240769631176e-05,
      "loss": 0.5062,
      "step": 420
    },
    {
      "epoch": 1.2426900584795322,
      "grad_norm": 1.763198949927548,
      "learning_rate": 1.4571719257735702e-05,
      "loss": 0.5203,
      "step": 425
    },
    {
      "epoch": 1.2573099415204678,
      "grad_norm": 4.030641844892038,
      "learning_rate": 1.4419706765996153e-05,
      "loss": 0.5176,
      "step": 430
    },
    {
      "epoch": 1.2719298245614035,
      "grad_norm": 1.8591284929042133,
      "learning_rate": 1.4266414246679379e-05,
      "loss": 0.5099,
      "step": 435
    },
    {
      "epoch": 1.286549707602339,
      "grad_norm": 1.8559628967021533,
      "learning_rate": 1.4111886096090953e-05,
      "loss": 0.5129,
      "step": 440
    },
    {
      "epoch": 1.301169590643275,
      "grad_norm": 2.862306979981545,
      "learning_rate": 1.3956167068397756e-05,
      "loss": 0.5075,
      "step": 445
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 1.8928522544167012,
      "learning_rate": 1.3799302262666388e-05,
      "loss": 0.5177,
      "step": 450
    },
    {
      "epoch": 1.3304093567251463,
      "grad_norm": 1.8170476120999561,
      "learning_rate": 1.364133710980162e-05,
      "loss": 0.516,
      "step": 455
    },
    {
      "epoch": 1.345029239766082,
      "grad_norm": 1.735070100858528,
      "learning_rate": 1.3482317359388806e-05,
      "loss": 0.5086,
      "step": 460
    },
    {
      "epoch": 1.3596491228070176,
      "grad_norm": 2.0140408558653737,
      "learning_rate": 1.3322289066443947e-05,
      "loss": 0.5169,
      "step": 465
    },
    {
      "epoch": 1.3742690058479532,
      "grad_norm": 1.7311234684729015,
      "learning_rate": 1.316129857807534e-05,
      "loss": 0.5077,
      "step": 470
    },
    {
      "epoch": 1.3888888888888888,
      "grad_norm": 1.7834637989309219,
      "learning_rate": 1.2999392520060594e-05,
      "loss": 0.5181,
      "step": 475
    },
    {
      "epoch": 1.4035087719298245,
      "grad_norm": 1.725680916190487,
      "learning_rate": 1.2836617783342968e-05,
      "loss": 0.5102,
      "step": 480
    },
    {
      "epoch": 1.4181286549707601,
      "grad_norm": 1.8726265727670828,
      "learning_rate": 1.2673021510450893e-05,
      "loss": 0.5169,
      "step": 485
    },
    {
      "epoch": 1.4327485380116958,
      "grad_norm": 2.056653138512768,
      "learning_rate": 1.250865108184464e-05,
      "loss": 0.5085,
      "step": 490
    },
    {
      "epoch": 1.4473684210526316,
      "grad_norm": 1.6627221599390933,
      "learning_rate": 1.2343554102194073e-05,
      "loss": 0.4981,
      "step": 495
    },
    {
      "epoch": 1.4619883040935673,
      "grad_norm": 1.7476089665186805,
      "learning_rate": 1.2177778386591475e-05,
      "loss": 0.5186,
      "step": 500
    },
    {
      "epoch": 1.4619883040935673,
      "eval_loss": 0.8920474648475647,
      "eval_runtime": 93.9752,
      "eval_samples_per_second": 23.219,
      "eval_steps_per_second": 0.372,
      "step": 500
    },
    {
      "epoch": 1.476608187134503,
      "grad_norm": 1.6946408040860308,
      "learning_rate": 1.2011371946703416e-05,
      "loss": 0.5197,
      "step": 505
    },
    {
      "epoch": 1.4912280701754386,
      "grad_norm": 1.7569189927952173,
      "learning_rate": 1.1844382976865714e-05,
      "loss": 0.515,
      "step": 510
    },
    {
      "epoch": 1.5058479532163744,
      "grad_norm": 1.9990864745103767,
      "learning_rate": 1.1676859840125468e-05,
      "loss": 0.5188,
      "step": 515
    },
    {
      "epoch": 1.52046783625731,
      "grad_norm": 1.659671819522036,
      "learning_rate": 1.1508851054234236e-05,
      "loss": 0.4952,
      "step": 520
    },
    {
      "epoch": 1.5350877192982457,
      "grad_norm": 1.8125623588878788,
      "learning_rate": 1.1340405277596427e-05,
      "loss": 0.5029,
      "step": 525
    },
    {
      "epoch": 1.5497076023391814,
      "grad_norm": 1.6209359235184773,
      "learning_rate": 1.1171571295176915e-05,
      "loss": 0.5016,
      "step": 530
    },
    {
      "epoch": 1.564327485380117,
      "grad_norm": 1.7381191339168205,
      "learning_rate": 1.1002398004372048e-05,
      "loss": 0.4938,
      "step": 535
    },
    {
      "epoch": 1.5789473684210527,
      "grad_norm": 1.7440328988243268,
      "learning_rate": 1.0832934400848063e-05,
      "loss": 0.508,
      "step": 540
    },
    {
      "epoch": 1.5935672514619883,
      "grad_norm": 1.6873580611700445,
      "learning_rate": 1.066322956435104e-05,
      "loss": 0.4994,
      "step": 545
    },
    {
      "epoch": 1.608187134502924,
      "grad_norm": 1.6955737592784719,
      "learning_rate": 1.0493332644492534e-05,
      "loss": 0.494,
      "step": 550
    },
    {
      "epoch": 1.6228070175438596,
      "grad_norm": 1.8639586363579819,
      "learning_rate": 1.0323292846514927e-05,
      "loss": 0.5086,
      "step": 555
    },
    {
      "epoch": 1.6374269005847952,
      "grad_norm": 1.6602403945581443,
      "learning_rate": 1.015315941704071e-05,
      "loss": 0.4958,
      "step": 560
    },
    {
      "epoch": 1.6520467836257309,
      "grad_norm": 1.6463228018665035,
      "learning_rate": 9.982981629809776e-06,
      "loss": 0.4947,
      "step": 565
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 1.8439520823673021,
      "learning_rate": 9.812808771408804e-06,
      "loss": 0.4943,
      "step": 570
    },
    {
      "epoch": 1.6812865497076024,
      "grad_norm": 1.6567753225002235,
      "learning_rate": 9.64269012699702e-06,
      "loss": 0.4815,
      "step": 575
    },
    {
      "epoch": 1.695906432748538,
      "grad_norm": 1.6625638574779524,
      "learning_rate": 9.472674966032276e-06,
      "loss": 0.5006,
      "step": 580
    },
    {
      "epoch": 1.7105263157894737,
      "grad_norm": 1.898719426059897,
      "learning_rate": 9.302812528001741e-06,
      "loss": 0.5086,
      "step": 585
    },
    {
      "epoch": 1.7251461988304093,
      "grad_norm": 1.8795535435362318,
      "learning_rate": 9.133152008161235e-06,
      "loss": 0.5094,
      "step": 590
    },
    {
      "epoch": 1.7397660818713452,
      "grad_norm": 1.7067878022572074,
      "learning_rate": 8.963742543287397e-06,
      "loss": 0.5001,
      "step": 595
    },
    {
      "epoch": 1.7543859649122808,
      "grad_norm": 1.6684322823190847,
      "learning_rate": 8.79463319744677e-06,
      "loss": 0.5067,
      "step": 600
    },
    {
      "epoch": 1.7543859649122808,
      "eval_loss": 0.8780078291893005,
      "eval_runtime": 94.1156,
      "eval_samples_per_second": 23.184,
      "eval_steps_per_second": 0.372,
      "step": 600
    },
    {
      "epoch": 1.7690058479532165,
      "grad_norm": 1.575226401438412,
      "learning_rate": 8.625872947785968e-06,
      "loss": 0.5163,
      "step": 605
    },
    {
      "epoch": 1.7836257309941521,
      "grad_norm": 1.665839831059325,
      "learning_rate": 8.457510670346976e-06,
      "loss": 0.5185,
      "step": 610
    },
    {
      "epoch": 1.7982456140350878,
      "grad_norm": 1.668476308962127,
      "learning_rate": 8.2895951259118e-06,
      "loss": 0.4891,
      "step": 615
    },
    {
      "epoch": 1.8128654970760234,
      "grad_norm": 1.6099746797995087,
      "learning_rate": 8.122174945880409e-06,
      "loss": 0.4941,
      "step": 620
    },
    {
      "epoch": 1.827485380116959,
      "grad_norm": 1.5972670521003787,
      "learning_rate": 7.955298618186227e-06,
      "loss": 0.4983,
      "step": 625
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 1.6567002288888941,
      "learning_rate": 7.78901447325314e-06,
      "loss": 0.4923,
      "step": 630
    },
    {
      "epoch": 1.8567251461988303,
      "grad_norm": 1.633625117649634,
      "learning_rate": 7.623370669998115e-06,
      "loss": 0.4952,
      "step": 635
    },
    {
      "epoch": 1.871345029239766,
      "grad_norm": 1.6702231621007573,
      "learning_rate": 7.458415181883506e-06,
      "loss": 0.4781,
      "step": 640
    },
    {
      "epoch": 1.8859649122807016,
      "grad_norm": 1.5695315130710974,
      "learning_rate": 7.294195783023072e-06,
      "loss": 0.4772,
      "step": 645
    },
    {
      "epoch": 1.9005847953216373,
      "grad_norm": 1.5932464772328656,
      "learning_rate": 7.130760034345708e-06,
      "loss": 0.4766,
      "step": 650
    },
    {
      "epoch": 1.9152046783625731,
      "grad_norm": 1.5938375889822713,
      "learning_rate": 6.968155269820951e-06,
      "loss": 0.4954,
      "step": 655
    },
    {
      "epoch": 1.9298245614035088,
      "grad_norm": 1.6068162124707588,
      "learning_rate": 6.806428582750191e-06,
      "loss": 0.5031,
      "step": 660
    },
    {
      "epoch": 1.9444444444444444,
      "grad_norm": 1.6369099221197159,
      "learning_rate": 6.645626812127588e-06,
      "loss": 0.4871,
      "step": 665
    },
    {
      "epoch": 1.95906432748538,
      "grad_norm": 1.8488127966750827,
      "learning_rate": 6.485796529074662e-06,
      "loss": 0.4793,
      "step": 670
    },
    {
      "epoch": 1.973684210526316,
      "grad_norm": 1.5795572120040184,
      "learning_rate": 6.326984023352435e-06,
      "loss": 0.4728,
      "step": 675
    },
    {
      "epoch": 1.9883040935672516,
      "grad_norm": 1.8151786682783004,
      "learning_rate": 6.169235289955073e-06,
      "loss": 0.4659,
      "step": 680
    },
    {
      "epoch": 2.002923976608187,
      "grad_norm": 3.8300611957194977,
      "learning_rate": 6.012596015788903e-06,
      "loss": 0.4261,
      "step": 685
    },
    {
      "epoch": 2.017543859649123,
      "grad_norm": 2.621763538813387,
      "learning_rate": 5.8571115664406655e-06,
      "loss": 0.2426,
      "step": 690
    },
    {
      "epoch": 2.0321637426900585,
      "grad_norm": 1.8343232864531938,
      "learning_rate": 5.702826973038776e-06,
      "loss": 0.24,
      "step": 695
    },
    {
      "epoch": 2.046783625730994,
      "grad_norm": 1.9497619965124309,
      "learning_rate": 5.549786919211532e-06,
      "loss": 0.2223,
      "step": 700
    },
    {
      "epoch": 2.046783625730994,
      "eval_loss": 0.951133131980896,
      "eval_runtime": 93.9878,
      "eval_samples_per_second": 23.216,
      "eval_steps_per_second": 0.372,
      "step": 700
    },
    {
      "epoch": 2.06140350877193,
      "grad_norm": 1.7439743078429233,
      "learning_rate": 5.3980357281459e-06,
      "loss": 0.229,
      "step": 705
    },
    {
      "epoch": 2.0760233918128654,
      "grad_norm": 1.5354726993504848,
      "learning_rate": 5.247617349750717e-06,
      "loss": 0.2083,
      "step": 710
    },
    {
      "epoch": 2.090643274853801,
      "grad_norm": 7.788063462658685,
      "learning_rate": 5.0985753479279824e-06,
      "loss": 0.2391,
      "step": 715
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 1.5764797068116867,
      "learning_rate": 4.950952887955992e-06,
      "loss": 0.2146,
      "step": 720
    },
    {
      "epoch": 2.1198830409356724,
      "grad_norm": 1.5338239957853983,
      "learning_rate": 4.80479272398786e-06,
      "loss": 0.2145,
      "step": 725
    },
    {
      "epoch": 2.134502923976608,
      "grad_norm": 1.5400470674701994,
      "learning_rate": 4.660137186669131e-06,
      "loss": 0.2131,
      "step": 730
    },
    {
      "epoch": 2.1491228070175437,
      "grad_norm": 1.5891715585976705,
      "learning_rate": 4.5170281708780865e-06,
      "loss": 0.2273,
      "step": 735
    },
    {
      "epoch": 2.1637426900584797,
      "grad_norm": 1.6323196857228797,
      "learning_rate": 4.375507123592194e-06,
      "loss": 0.2221,
      "step": 740
    },
    {
      "epoch": 2.1783625730994154,
      "grad_norm": 3.4202645186771896,
      "learning_rate": 4.235615031884326e-06,
      "loss": 0.2139,
      "step": 745
    },
    {
      "epoch": 2.192982456140351,
      "grad_norm": 1.6425009664630226,
      "learning_rate": 4.097392411052149e-06,
      "loss": 0.2165,
      "step": 750
    },
    {
      "epoch": 2.2076023391812867,
      "grad_norm": 1.5960953283192305,
      "learning_rate": 3.9608792928841596e-06,
      "loss": 0.201,
      "step": 755
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 1.5527267754127971,
      "learning_rate": 3.826115214065739e-06,
      "loss": 0.2162,
      "step": 760
    },
    {
      "epoch": 2.236842105263158,
      "grad_norm": 1.5345330165293922,
      "learning_rate": 3.693139204728623e-06,
      "loss": 0.2033,
      "step": 765
    },
    {
      "epoch": 2.2514619883040936,
      "grad_norm": 1.5602344960819443,
      "learning_rate": 3.561989777147059e-06,
      "loss": 0.2175,
      "step": 770
    },
    {
      "epoch": 2.2660818713450293,
      "grad_norm": 1.543288744735399,
      "learning_rate": 3.4327049145839496e-06,
      "loss": 0.2044,
      "step": 775
    },
    {
      "epoch": 2.280701754385965,
      "grad_norm": 1.5668680143830462,
      "learning_rate": 3.3053220602902057e-06,
      "loss": 0.2067,
      "step": 780
    },
    {
      "epoch": 2.2953216374269005,
      "grad_norm": 1.4653721970803488,
      "learning_rate": 3.1798781066605076e-06,
      "loss": 0.2072,
      "step": 785
    },
    {
      "epoch": 2.309941520467836,
      "grad_norm": 1.5895314411422212,
      "learning_rate": 3.056409384548575e-06,
      "loss": 0.2077,
      "step": 790
    },
    {
      "epoch": 2.324561403508772,
      "grad_norm": 1.5324432023481178,
      "learning_rate": 2.934951652745123e-06,
      "loss": 0.2067,
      "step": 795
    },
    {
      "epoch": 2.3391812865497075,
      "grad_norm": 1.6877695775778203,
      "learning_rate": 2.8155400876214365e-06,
      "loss": 0.2114,
      "step": 800
    },
    {
      "epoch": 2.3391812865497075,
      "eval_loss": 0.9491869807243347,
      "eval_runtime": 94.0592,
      "eval_samples_per_second": 23.198,
      "eval_steps_per_second": 0.372,
      "step": 800
    },
    {
      "epoch": 2.353801169590643,
      "grad_norm": 1.797333972810049,
      "learning_rate": 2.698209272941659e-06,
      "loss": 0.2066,
      "step": 805
    },
    {
      "epoch": 2.3684210526315788,
      "grad_norm": 1.4817024828655516,
      "learning_rate": 2.5829931898467143e-06,
      "loss": 0.2003,
      "step": 810
    },
    {
      "epoch": 2.383040935672515,
      "grad_norm": 1.5944694035375513,
      "learning_rate": 2.469925207012741e-06,
      "loss": 0.2111,
      "step": 815
    },
    {
      "epoch": 2.39766081871345,
      "grad_norm": 1.5437718528241764,
      "learning_rate": 2.3590380709869175e-06,
      "loss": 0.2036,
      "step": 820
    },
    {
      "epoch": 2.412280701754386,
      "grad_norm": 1.5545155179428847,
      "learning_rate": 2.2503638967034668e-06,
      "loss": 0.2119,
      "step": 825
    },
    {
      "epoch": 2.426900584795322,
      "grad_norm": 1.5090412576695187,
      "learning_rate": 2.1439341581825855e-06,
      "loss": 0.2079,
      "step": 830
    },
    {
      "epoch": 2.4415204678362574,
      "grad_norm": 1.5651792272296057,
      "learning_rate": 2.039779679414996e-06,
      "loss": 0.2049,
      "step": 835
    },
    {
      "epoch": 2.456140350877193,
      "grad_norm": 1.629599771732464,
      "learning_rate": 1.9379306254347487e-06,
      "loss": 0.2063,
      "step": 840
    },
    {
      "epoch": 2.4707602339181287,
      "grad_norm": 1.517424552525727,
      "learning_rate": 1.838416493582893e-06,
      "loss": 0.2054,
      "step": 845
    },
    {
      "epoch": 2.4853801169590644,
      "grad_norm": 1.5665838306665794,
      "learning_rate": 1.7412661049645097e-06,
      "loss": 0.2072,
      "step": 850
    },
    {
      "epoch": 2.5,
      "grad_norm": 1.5709890486248266,
      "learning_rate": 1.6465075961015697e-06,
      "loss": 0.1969,
      "step": 855
    },
    {
      "epoch": 2.5146198830409356,
      "grad_norm": 1.433926747309705,
      "learning_rate": 1.554168410784117e-06,
      "loss": 0.2025,
      "step": 860
    },
    {
      "epoch": 2.5292397660818713,
      "grad_norm": 1.56024876676377,
      "learning_rate": 1.4642752921220272e-06,
      "loss": 0.2019,
      "step": 865
    },
    {
      "epoch": 2.543859649122807,
      "grad_norm": 1.4917168419123434,
      "learning_rate": 1.3768542747997215e-06,
      "loss": 0.2092,
      "step": 870
    },
    {
      "epoch": 2.5584795321637426,
      "grad_norm": 1.5176036989413515,
      "learning_rate": 1.2919306775360495e-06,
      "loss": 0.2053,
      "step": 875
    },
    {
      "epoch": 2.573099415204678,
      "grad_norm": 1.5727527454387282,
      "learning_rate": 1.209529095751527e-06,
      "loss": 0.2014,
      "step": 880
    },
    {
      "epoch": 2.587719298245614,
      "grad_norm": 1.489918411889695,
      "learning_rate": 1.1296733944450445e-06,
      "loss": 0.2012,
      "step": 885
    },
    {
      "epoch": 2.60233918128655,
      "grad_norm": 1.5532738891332698,
      "learning_rate": 1.0523867012821444e-06,
      "loss": 0.2031,
      "step": 890
    },
    {
      "epoch": 2.616959064327485,
      "grad_norm": 1.4483198492727338,
      "learning_rate": 9.776913998968196e-07,
      "loss": 0.2012,
      "step": 895
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 1.5331083693362297,
      "learning_rate": 9.056091234088038e-07,
      "loss": 0.1983,
      "step": 900
    },
    {
      "epoch": 2.6315789473684212,
      "eval_loss": 0.9508408904075623,
      "eval_runtime": 93.8904,
      "eval_samples_per_second": 23.24,
      "eval_steps_per_second": 0.373,
      "step": 900
    },
    {
      "epoch": 2.646198830409357,
      "grad_norm": 1.4959941578534954,
      "learning_rate": 8.361607481582312e-07,
      "loss": 0.2031,
      "step": 905
    },
    {
      "epoch": 2.6608187134502925,
      "grad_norm": 1.533846604598029,
      "learning_rate": 7.693663876594648e-07,
      "loss": 0.2086,
      "step": 910
    },
    {
      "epoch": 2.675438596491228,
      "grad_norm": 1.4882252878887594,
      "learning_rate": 7.052453867758525e-07,
      "loss": 0.2044,
      "step": 915
    },
    {
      "epoch": 2.690058479532164,
      "grad_norm": 1.463561383109587,
      "learning_rate": 6.438163161171096e-07,
      "loss": 0.199,
      "step": 920
    },
    {
      "epoch": 2.7046783625730995,
      "grad_norm": 1.4904086029449222,
      "learning_rate": 5.850969666609363e-07,
      "loss": 0.1949,
      "step": 925
    },
    {
      "epoch": 2.719298245614035,
      "grad_norm": 1.4484608706071034,
      "learning_rate": 5.291043446004074e-07,
      "loss": 0.1941,
      "step": 930
    },
    {
      "epoch": 2.7339181286549707,
      "grad_norm": 1.4693647586602272,
      "learning_rate": 4.7585466641868696e-07,
      "loss": 0.1925,
      "step": 935
    },
    {
      "epoch": 2.7485380116959064,
      "grad_norm": 1.4804496226260073,
      "learning_rate": 4.25363354192434e-07,
      "loss": 0.2027,
      "step": 940
    },
    {
      "epoch": 2.763157894736842,
      "grad_norm": 1.5177590267070082,
      "learning_rate": 3.776450311252866e-07,
      "loss": 0.2068,
      "step": 945
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 1.4962603716375011,
      "learning_rate": 3.3271351731271717e-07,
      "loss": 0.1993,
      "step": 950
    },
    {
      "epoch": 2.7923976608187133,
      "grad_norm": 1.53541672293609,
      "learning_rate": 2.905818257394799e-07,
      "loss": 0.2126,
      "step": 955
    },
    {
      "epoch": 2.807017543859649,
      "grad_norm": 1.4669550373356948,
      "learning_rate": 2.512621585108155e-07,
      "loss": 0.2021,
      "step": 960
    },
    {
      "epoch": 2.821637426900585,
      "grad_norm": 1.4475885818879743,
      "learning_rate": 2.1476590331849566e-07,
      "loss": 0.195,
      "step": 965
    },
    {
      "epoch": 2.8362573099415203,
      "grad_norm": 1.487795902053431,
      "learning_rate": 1.811036301427449e-07,
      "loss": 0.2073,
      "step": 970
    },
    {
      "epoch": 2.8508771929824563,
      "grad_norm": 1.4972431353793751,
      "learning_rate": 1.502850881909801e-07,
      "loss": 0.2017,
      "step": 975
    },
    {
      "epoch": 2.8654970760233915,
      "grad_norm": 1.506977096918749,
      "learning_rate": 1.2231920307425927e-07,
      "loss": 0.2081,
      "step": 980
    },
    {
      "epoch": 2.8801169590643276,
      "grad_norm": 1.5752046829905806,
      "learning_rate": 9.721407422226492e-08,
      "loss": 0.2089,
      "step": 985
    },
    {
      "epoch": 2.8947368421052633,
      "grad_norm": 1.4564645802512894,
      "learning_rate": 7.497697253756265e-08,
      "loss": 0.1933,
      "step": 990
    },
    {
      "epoch": 2.909356725146199,
      "grad_norm": 1.493498674859337,
      "learning_rate": 5.5614338289812216e-08,
      "loss": 0.1974,
      "step": 995
    },
    {
      "epoch": 2.9239766081871346,
      "grad_norm": 1.4762567685805037,
      "learning_rate": 3.913177925055189e-08,
      "loss": 0.2014,
      "step": 1000
    },
    {
      "epoch": 2.9239766081871346,
      "eval_loss": 0.946516215801239,
      "eval_runtime": 94.0428,
      "eval_samples_per_second": 23.202,
      "eval_steps_per_second": 0.372,
      "step": 1000
    },
    {
      "epoch": 2.93859649122807,
      "grad_norm": 1.47647651184245,
      "learning_rate": 2.5534069069081957e-08,
      "loss": 0.2044,
      "step": 1005
    },
    {
      "epoch": 2.953216374269006,
      "grad_norm": 1.4575732503367402,
      "learning_rate": 1.482514588993067e-08,
      "loss": 0.2001,
      "step": 1010
    },
    {
      "epoch": 2.9678362573099415,
      "grad_norm": 1.5453006830413416,
      "learning_rate": 7.0081112122966086e-09,
      "loss": 0.2042,
      "step": 1015
    },
    {
      "epoch": 2.982456140350877,
      "grad_norm": 1.7014593329310401,
      "learning_rate": 2.0852289917971947e-09,
      "loss": 0.1995,
      "step": 1020
    },
    {
      "epoch": 2.997076023391813,
      "grad_norm": 1.5593115324810627,
      "learning_rate": 5.792498478651709e-11,
      "loss": 0.2055,
      "step": 1025
    },
    {
      "epoch": 3.0,
      "step": 1026,
      "total_flos": 429437673799680.0,
      "train_loss": 0.5057662985420134,
      "train_runtime": 26805.8841,
      "train_samples_per_second": 4.896,
      "train_steps_per_second": 0.038
    }
  ],
  "logging_steps": 5,
  "max_steps": 1026,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 429437673799680.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}