{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.015991045014791715,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015991045014791716,
      "grad_norm": 0.6504083275794983,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.4583,
      "step": 1
    },
    {
      "epoch": 0.00015991045014791716,
      "eval_loss": 1.474985122680664,
      "eval_runtime": 837.126,
      "eval_samples_per_second": 6.291,
      "eval_steps_per_second": 0.787,
      "step": 1
    },
    {
      "epoch": 0.0003198209002958343,
      "grad_norm": 0.6578736305236816,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.6315,
      "step": 2
    },
    {
      "epoch": 0.0004797313504437515,
      "grad_norm": 0.5738436579704285,
      "learning_rate": 6e-06,
      "loss": 1.4175,
      "step": 3
    },
    {
      "epoch": 0.0006396418005916686,
      "grad_norm": 0.6563103199005127,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.5265,
      "step": 4
    },
    {
      "epoch": 0.0007995522507395858,
      "grad_norm": 0.5647775530815125,
      "learning_rate": 1e-05,
      "loss": 1.324,
      "step": 5
    },
    {
      "epoch": 0.000959462700887503,
      "grad_norm": 0.5874689221382141,
      "learning_rate": 1.2e-05,
      "loss": 1.3594,
      "step": 6
    },
    {
      "epoch": 0.0011193731510354202,
      "grad_norm": 0.7175629138946533,
      "learning_rate": 1.4e-05,
      "loss": 1.4862,
      "step": 7
    },
    {
      "epoch": 0.0012792836011833373,
      "grad_norm": 0.5698773264884949,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.5141,
      "step": 8
    },
    {
      "epoch": 0.0014391940513312545,
      "grad_norm": 0.5724843740463257,
      "learning_rate": 1.8e-05,
      "loss": 1.4331,
      "step": 9
    },
    {
      "epoch": 0.0014391940513312545,
      "eval_loss": 1.4668989181518555,
      "eval_runtime": 839.5073,
      "eval_samples_per_second": 6.273,
      "eval_steps_per_second": 0.785,
      "step": 9
    },
    {
      "epoch": 0.0015991045014791716,
      "grad_norm": 0.542625904083252,
      "learning_rate": 2e-05,
      "loss": 1.3568,
      "step": 10
    },
    {
      "epoch": 0.001759014951627089,
      "grad_norm": 0.6550851464271545,
      "learning_rate": 1.999390827019096e-05,
      "loss": 1.4611,
      "step": 11
    },
    {
      "epoch": 0.001918925401775006,
      "grad_norm": 0.5612558722496033,
      "learning_rate": 1.9975640502598243e-05,
      "loss": 1.2845,
      "step": 12
    },
    {
      "epoch": 0.002078835851922923,
      "grad_norm": 0.6248297691345215,
      "learning_rate": 1.9945218953682736e-05,
      "loss": 1.4793,
      "step": 13
    },
    {
      "epoch": 0.0022387463020708404,
      "grad_norm": 0.5305907130241394,
      "learning_rate": 1.9902680687415704e-05,
      "loss": 1.3363,
      "step": 14
    },
    {
      "epoch": 0.0023986567522187576,
      "grad_norm": 0.6528483033180237,
      "learning_rate": 1.9848077530122083e-05,
      "loss": 1.3573,
      "step": 15
    },
    {
      "epoch": 0.0025585672023666745,
      "grad_norm": 0.5816062688827515,
      "learning_rate": 1.9781476007338058e-05,
      "loss": 1.5584,
      "step": 16
    },
    {
      "epoch": 0.002718477652514592,
      "grad_norm": 0.629796028137207,
      "learning_rate": 1.9702957262759964e-05,
      "loss": 1.3143,
      "step": 17
    },
    {
      "epoch": 0.002878388102662509,
      "grad_norm": 0.45958274602890015,
      "learning_rate": 1.961261695938319e-05,
      "loss": 1.1897,
      "step": 18
    },
    {
      "epoch": 0.002878388102662509,
      "eval_loss": 1.4167035818099976,
      "eval_runtime": 838.9269,
      "eval_samples_per_second": 6.277,
      "eval_steps_per_second": 0.786,
      "step": 18
    },
    {
      "epoch": 0.003038298552810426,
      "grad_norm": 0.5565961599349976,
      "learning_rate": 1.9510565162951538e-05,
      "loss": 1.2789,
      "step": 19
    },
    {
      "epoch": 0.0031982090029583432,
      "grad_norm": 0.5968546271324158,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 1.334,
      "step": 20
    },
    {
      "epoch": 0.0033581194531062605,
      "grad_norm": 0.4640100598335266,
      "learning_rate": 1.9271838545667876e-05,
      "loss": 1.1353,
      "step": 21
    },
    {
      "epoch": 0.003518029903254178,
      "grad_norm": 0.649774968624115,
      "learning_rate": 1.913545457642601e-05,
      "loss": 1.3492,
      "step": 22
    },
    {
      "epoch": 0.0036779403534020947,
      "grad_norm": 0.48623567819595337,
      "learning_rate": 1.8987940462991673e-05,
      "loss": 1.1991,
      "step": 23
    },
    {
      "epoch": 0.003837850803550012,
      "grad_norm": 0.5359298586845398,
      "learning_rate": 1.8829475928589272e-05,
      "loss": 1.3841,
      "step": 24
    },
    {
      "epoch": 0.003997761253697929,
      "grad_norm": 0.6157242059707642,
      "learning_rate": 1.866025403784439e-05,
      "loss": 1.4582,
      "step": 25
    },
    {
      "epoch": 0.004157671703845846,
      "grad_norm": 0.4564124047756195,
      "learning_rate": 1.848048096156426e-05,
      "loss": 1.2557,
      "step": 26
    },
    {
      "epoch": 0.004317582153993763,
      "grad_norm": 0.6731557846069336,
      "learning_rate": 1.8290375725550417e-05,
      "loss": 1.3825,
      "step": 27
    },
    {
      "epoch": 0.004317582153993763,
      "eval_loss": 1.3696609735488892,
      "eval_runtime": 838.9906,
      "eval_samples_per_second": 6.277,
      "eval_steps_per_second": 0.785,
      "step": 27
    },
    {
      "epoch": 0.004477492604141681,
      "grad_norm": 0.5301347374916077,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 1.3329,
      "step": 28
    },
    {
      "epoch": 0.004637403054289598,
      "grad_norm": 0.6744347810745239,
      "learning_rate": 1.788010753606722e-05,
      "loss": 1.2552,
      "step": 29
    },
    {
      "epoch": 0.004797313504437515,
      "grad_norm": 0.47487542033195496,
      "learning_rate": 1.766044443118978e-05,
      "loss": 1.3298,
      "step": 30
    },
    {
      "epoch": 0.004957223954585433,
      "grad_norm": 0.5701873302459717,
      "learning_rate": 1.7431448254773943e-05,
      "loss": 1.4192,
      "step": 31
    },
    {
      "epoch": 0.005117134404733349,
      "grad_norm": 0.6943455338478088,
      "learning_rate": 1.7193398003386514e-05,
      "loss": 1.3912,
      "step": 32
    },
    {
      "epoch": 0.005277044854881266,
      "grad_norm": 0.44916555285453796,
      "learning_rate": 1.6946583704589973e-05,
      "loss": 1.3954,
      "step": 33
    },
    {
      "epoch": 0.005436955305029184,
      "grad_norm": 0.5873166918754578,
      "learning_rate": 1.6691306063588583e-05,
      "loss": 1.4476,
      "step": 34
    },
    {
      "epoch": 0.005596865755177101,
      "grad_norm": 0.5698227882385254,
      "learning_rate": 1.6427876096865394e-05,
      "loss": 1.2139,
      "step": 35
    },
    {
      "epoch": 0.005756776205325018,
      "grad_norm": 0.5008086562156677,
      "learning_rate": 1.6156614753256583e-05,
      "loss": 1.3209,
      "step": 36
    },
    {
      "epoch": 0.005756776205325018,
      "eval_loss": 1.3212887048721313,
      "eval_runtime": 839.0577,
      "eval_samples_per_second": 6.276,
      "eval_steps_per_second": 0.785,
      "step": 36
    },
    {
      "epoch": 0.0059166866554729355,
      "grad_norm": 0.7312777042388916,
      "learning_rate": 1.5877852522924733e-05,
      "loss": 1.4531,
      "step": 37
    },
    {
      "epoch": 0.006076597105620852,
      "grad_norm": 0.6371181011199951,
      "learning_rate": 1.5591929034707468e-05,
      "loss": 1.4137,
      "step": 38
    },
    {
      "epoch": 0.006236507555768769,
      "grad_norm": 0.7950341701507568,
      "learning_rate": 1.529919264233205e-05,
      "loss": 1.5679,
      "step": 39
    },
    {
      "epoch": 0.0063964180059166865,
      "grad_norm": 0.49994805455207825,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 1.2783,
      "step": 40
    },
    {
      "epoch": 0.006556328456064604,
      "grad_norm": 0.5640048980712891,
      "learning_rate": 1.469471562785891e-05,
      "loss": 1.2761,
      "step": 41
    },
    {
      "epoch": 0.006716238906212521,
      "grad_norm": 0.5070842504501343,
      "learning_rate": 1.4383711467890776e-05,
      "loss": 1.0965,
      "step": 42
    },
    {
      "epoch": 0.006876149356360438,
      "grad_norm": 0.6632875204086304,
      "learning_rate": 1.4067366430758004e-05,
      "loss": 1.3255,
      "step": 43
    },
    {
      "epoch": 0.007036059806508356,
      "grad_norm": 0.8308796882629395,
      "learning_rate": 1.3746065934159123e-05,
      "loss": 1.4276,
      "step": 44
    },
    {
      "epoch": 0.007195970256656272,
      "grad_norm": 0.6819413900375366,
      "learning_rate": 1.342020143325669e-05,
      "loss": 1.4298,
      "step": 45
    },
    {
      "epoch": 0.007195970256656272,
      "eval_loss": 1.2887763977050781,
      "eval_runtime": 839.0005,
      "eval_samples_per_second": 6.277,
      "eval_steps_per_second": 0.785,
      "step": 45
    },
    {
      "epoch": 0.007355880706804189,
      "grad_norm": 1.1760120391845703,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 1.4493,
      "step": 46
    },
    {
      "epoch": 0.007515791156952107,
      "grad_norm": 0.7166178822517395,
      "learning_rate": 1.2756373558169992e-05,
      "loss": 1.2214,
      "step": 47
    },
    {
      "epoch": 0.007675701607100024,
      "grad_norm": 0.5573228597640991,
      "learning_rate": 1.2419218955996677e-05,
      "loss": 1.1598,
      "step": 48
    },
    {
      "epoch": 0.007835612057247941,
      "grad_norm": 0.6709251999855042,
      "learning_rate": 1.2079116908177592e-05,
      "loss": 1.2747,
      "step": 49
    },
    {
      "epoch": 0.007995522507395858,
      "grad_norm": 0.8962216973304749,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 1.3289,
      "step": 50
    },
    {
      "epoch": 0.008155432957543776,
      "grad_norm": 0.8980185985565186,
      "learning_rate": 1.1391731009600655e-05,
      "loss": 1.3383,
      "step": 51
    },
    {
      "epoch": 0.008315343407691692,
      "grad_norm": 0.458204448223114,
      "learning_rate": 1.1045284632676535e-05,
      "loss": 1.2216,
      "step": 52
    },
    {
      "epoch": 0.00847525385783961,
      "grad_norm": 0.7558490037918091,
      "learning_rate": 1.0697564737441254e-05,
      "loss": 1.1952,
      "step": 53
    },
    {
      "epoch": 0.008635164307987527,
      "grad_norm": 0.6034842133522034,
      "learning_rate": 1.0348994967025012e-05,
      "loss": 1.2106,
      "step": 54
    },
    {
      "epoch": 0.008635164307987527,
      "eval_loss": 1.2662858963012695,
      "eval_runtime": 838.9955,
      "eval_samples_per_second": 6.277,
      "eval_steps_per_second": 0.785,
      "step": 54
    },
    {
      "epoch": 0.008795074758135445,
      "grad_norm": 0.6426628828048706,
      "learning_rate": 1e-05,
      "loss": 1.2884,
      "step": 55
    },
    {
      "epoch": 0.008954985208283361,
      "grad_norm": 0.7023085355758667,
      "learning_rate": 9.651005032974994e-06,
      "loss": 0.994,
      "step": 56
    },
    {
      "epoch": 0.009114895658431278,
      "grad_norm": 0.7176782488822937,
      "learning_rate": 9.302435262558748e-06,
      "loss": 1.1677,
      "step": 57
    },
    {
      "epoch": 0.009274806108579196,
      "grad_norm": 0.4069592356681824,
      "learning_rate": 8.954715367323468e-06,
      "loss": 1.0885,
      "step": 58
    },
    {
      "epoch": 0.009434716558727112,
      "grad_norm": 0.4837009310722351,
      "learning_rate": 8.60826899039935e-06,
      "loss": 1.1502,
      "step": 59
    },
    {
      "epoch": 0.00959462700887503,
      "grad_norm": 0.5509238839149475,
      "learning_rate": 8.263518223330698e-06,
      "loss": 1.2594,
      "step": 60
    },
    {
      "epoch": 0.009754537459022947,
      "grad_norm": 0.7491636276245117,
      "learning_rate": 7.92088309182241e-06,
      "loss": 1.1517,
      "step": 61
    },
    {
      "epoch": 0.009914447909170865,
      "grad_norm": 0.736369788646698,
      "learning_rate": 7.580781044003324e-06,
      "loss": 1.1621,
      "step": 62
    },
    {
      "epoch": 0.010074358359318782,
      "grad_norm": 0.8290790319442749,
      "learning_rate": 7.243626441830009e-06,
      "loss": 1.2544,
      "step": 63
    },
    {
      "epoch": 0.010074358359318782,
      "eval_loss": 1.2528209686279297,
      "eval_runtime": 838.7124,
      "eval_samples_per_second": 6.279,
      "eval_steps_per_second": 0.786,
      "step": 63
    },
    {
      "epoch": 0.010234268809466698,
      "grad_norm": 0.9916802644729614,
      "learning_rate": 6.909830056250527e-06,
      "loss": 1.338,
      "step": 64
    },
    {
      "epoch": 0.010394179259614616,
      "grad_norm": 0.7258274555206299,
      "learning_rate": 6.579798566743314e-06,
      "loss": 1.257,
      "step": 65
    },
    {
      "epoch": 0.010554089709762533,
      "grad_norm": 0.5781669020652771,
      "learning_rate": 6.25393406584088e-06,
      "loss": 1.4254,
      "step": 66
    },
    {
      "epoch": 0.01071400015991045,
      "grad_norm": 0.428519070148468,
      "learning_rate": 5.932633569242e-06,
      "loss": 1.1492,
      "step": 67
    },
    {
      "epoch": 0.010873910610058367,
      "grad_norm": 0.5914924740791321,
      "learning_rate": 5.616288532109225e-06,
      "loss": 1.1125,
      "step": 68
    },
    {
      "epoch": 0.011033821060206284,
      "grad_norm": 0.45223116874694824,
      "learning_rate": 5.305284372141095e-06,
      "loss": 1.2498,
      "step": 69
    },
    {
      "epoch": 0.011193731510354202,
      "grad_norm": 0.5652313828468323,
      "learning_rate": 5.000000000000003e-06,
      "loss": 1.1569,
      "step": 70
    },
    {
      "epoch": 0.011353641960502118,
      "grad_norm": 0.7218504548072815,
      "learning_rate": 4.700807357667953e-06,
      "loss": 1.3124,
      "step": 71
    },
    {
      "epoch": 0.011513552410650036,
      "grad_norm": 0.43518903851509094,
      "learning_rate": 4.408070965292534e-06,
      "loss": 1.0015,
      "step": 72
    },
    {
      "epoch": 0.011513552410650036,
      "eval_loss": 1.2443398237228394,
      "eval_runtime": 841.8672,
      "eval_samples_per_second": 6.255,
      "eval_steps_per_second": 0.783,
      "step": 72
    },
    {
      "epoch": 0.011673462860797953,
      "grad_norm": 0.6252135634422302,
      "learning_rate": 4.12214747707527e-06,
      "loss": 1.2931,
      "step": 73
    },
    {
      "epoch": 0.011833373310945871,
      "grad_norm": 0.8882245421409607,
      "learning_rate": 3.8433852467434175e-06,
      "loss": 1.5188,
      "step": 74
    },
    {
      "epoch": 0.011993283761093787,
      "grad_norm": 0.5009152293205261,
      "learning_rate": 3.5721239031346067e-06,
      "loss": 1.2413,
      "step": 75
    },
    {
      "epoch": 0.012153194211241704,
      "grad_norm": 0.49447953701019287,
      "learning_rate": 3.308693936411421e-06,
      "loss": 1.1577,
      "step": 76
    },
    {
      "epoch": 0.012313104661389622,
      "grad_norm": 0.4388711750507355,
      "learning_rate": 3.0534162954100264e-06,
      "loss": 1.0974,
      "step": 77
    },
    {
      "epoch": 0.012473015111537538,
      "grad_norm": 0.6474374532699585,
      "learning_rate": 2.8066019966134907e-06,
      "loss": 1.3496,
      "step": 78
    },
    {
      "epoch": 0.012632925561685457,
      "grad_norm": 0.6256920099258423,
      "learning_rate": 2.5685517452260566e-06,
      "loss": 1.2734,
      "step": 79
    },
    {
      "epoch": 0.012792836011833373,
      "grad_norm": 0.5670042037963867,
      "learning_rate": 2.339555568810221e-06,
      "loss": 1.2581,
      "step": 80
    },
    {
      "epoch": 0.012952746461981291,
      "grad_norm": 0.5674775242805481,
      "learning_rate": 2.119892463932781e-06,
      "loss": 1.1723,
      "step": 81
    },
    {
      "epoch": 0.012952746461981291,
      "eval_loss": 1.2400349378585815,
      "eval_runtime": 840.1999,
      "eval_samples_per_second": 6.268,
      "eval_steps_per_second": 0.784,
      "step": 81
    },
    {
      "epoch": 0.013112656912129208,
      "grad_norm": 0.7550069093704224,
      "learning_rate": 1.9098300562505266e-06,
      "loss": 1.0939,
      "step": 82
    },
    {
      "epoch": 0.013272567362277124,
      "grad_norm": 0.5404236316680908,
      "learning_rate": 1.709624274449584e-06,
      "loss": 1.1308,
      "step": 83
    },
    {
      "epoch": 0.013432477812425042,
      "grad_norm": 0.6628828644752502,
      "learning_rate": 1.5195190384357405e-06,
      "loss": 1.1015,
      "step": 84
    },
    {
      "epoch": 0.013592388262572959,
      "grad_norm": 0.5285108089447021,
      "learning_rate": 1.339745962155613e-06,
      "loss": 1.1419,
      "step": 85
    },
    {
      "epoch": 0.013752298712720877,
      "grad_norm": 0.47901371121406555,
      "learning_rate": 1.1705240714107301e-06,
      "loss": 1.1131,
      "step": 86
    },
    {
      "epoch": 0.013912209162868793,
      "grad_norm": 0.6831851005554199,
      "learning_rate": 1.012059537008332e-06,
      "loss": 1.2382,
      "step": 87
    },
    {
      "epoch": 0.014072119613016711,
      "grad_norm": 0.8617517948150635,
      "learning_rate": 8.645454235739903e-07,
      "loss": 1.4122,
      "step": 88
    },
    {
      "epoch": 0.014232030063164628,
      "grad_norm": 0.45922762155532837,
      "learning_rate": 7.281614543321269e-07,
      "loss": 1.2546,
      "step": 89
    },
    {
      "epoch": 0.014391940513312544,
      "grad_norm": 0.5549640655517578,
      "learning_rate": 6.030737921409169e-07,
      "loss": 1.2034,
      "step": 90
    },
    {
      "epoch": 0.014391940513312544,
      "eval_loss": 1.2383006811141968,
      "eval_runtime": 839.2212,
      "eval_samples_per_second": 6.275,
      "eval_steps_per_second": 0.785,
      "step": 90
    },
    {
      "epoch": 0.014551850963460462,
      "grad_norm": 0.5994484424591064,
      "learning_rate": 4.894348370484648e-07,
      "loss": 1.3596,
      "step": 91
    },
    {
      "epoch": 0.014711761413608379,
      "grad_norm": 0.4706943929195404,
      "learning_rate": 3.8738304061681107e-07,
      "loss": 1.2152,
      "step": 92
    },
    {
      "epoch": 0.014871671863756297,
      "grad_norm": 0.6663210391998291,
      "learning_rate": 2.970427372400353e-07,
      "loss": 1.1396,
      "step": 93
    },
    {
      "epoch": 0.015031582313904213,
      "grad_norm": 0.5939822196960449,
      "learning_rate": 2.1852399266194312e-07,
      "loss": 1.278,
      "step": 94
    },
    {
      "epoch": 0.015191492764052131,
      "grad_norm": 0.5491092205047607,
      "learning_rate": 1.519224698779198e-07,
      "loss": 1.2787,
      "step": 95
    },
    {
      "epoch": 0.015351403214200048,
      "grad_norm": 0.6317628026008606,
      "learning_rate": 9.731931258429638e-08,
      "loss": 1.2231,
      "step": 96
    },
    {
      "epoch": 0.015511313664347964,
      "grad_norm": 0.6600462794303894,
      "learning_rate": 5.4781046317267103e-08,
      "loss": 1.1201,
      "step": 97
    },
    {
      "epoch": 0.015671224114495882,
      "grad_norm": 0.4828977882862091,
      "learning_rate": 2.4359497401758026e-08,
      "loss": 1.1111,
      "step": 98
    },
    {
      "epoch": 0.0158311345646438,
      "grad_norm": 0.5716835856437683,
      "learning_rate": 6.091729809042379e-09,
      "loss": 1.354,
      "step": 99
    },
    {
      "epoch": 0.0158311345646438,
      "eval_loss": 1.23794424533844,
      "eval_runtime": 838.9402,
      "eval_samples_per_second": 6.277,
      "eval_steps_per_second": 0.786,
      "step": 99
    },
    {
      "epoch": 0.015991045014791715,
      "grad_norm": 0.6959627866744995,
      "learning_rate": 0.0,
      "loss": 1.3134,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.083155433998254e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}