{
  "best_metric": 0.05875943973660469,
  "best_model_checkpoint": "saves/psy-course-doc-info/Llama3-OpenBioLLM-8B/train/fold8/checkpoint-110",
  "epoch": 4.938271604938271,
  "eval_steps": 10,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03950617283950617,
      "grad_norm": 0.5292360782623291,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.3985,
      "step": 1
    },
    {
      "epoch": 0.07901234567901234,
      "grad_norm": 0.5238520503044128,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.3943,
      "step": 2
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 0.6243822574615479,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.4091,
      "step": 3
    },
    {
      "epoch": 0.1580246913580247,
      "grad_norm": 0.5004846453666687,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.3742,
      "step": 4
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.4548310935497284,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.3424,
      "step": 5
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 0.5590171813964844,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.373,
      "step": 6
    },
    {
      "epoch": 0.2765432098765432,
      "grad_norm": 0.513456404209137,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.3384,
      "step": 7
    },
    {
      "epoch": 0.3160493827160494,
      "grad_norm": 0.5335837602615356,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.3198,
      "step": 8
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.44757384061813354,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.299,
      "step": 9
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.4834142327308655,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.2704,
      "step": 10
    },
    {
      "epoch": 0.3950617283950617,
      "eval_loss": 0.2542249262332916,
      "eval_runtime": 29.1566,
      "eval_samples_per_second": 1.543,
      "eval_steps_per_second": 1.543,
      "step": 10
    },
    {
      "epoch": 0.4345679012345679,
      "grad_norm": 0.402045339345932,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.2731,
      "step": 11
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 0.4409458637237549,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.2402,
      "step": 12
    },
    {
      "epoch": 0.5135802469135803,
      "grad_norm": 0.4003790020942688,
      "learning_rate": 0.0001,
      "loss": 0.2081,
      "step": 13
    },
    {
      "epoch": 0.5530864197530864,
      "grad_norm": 0.4281858503818512,
      "learning_rate": 9.998033131915266e-05,
      "loss": 0.1948,
      "step": 14
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.4399724304676056,
      "learning_rate": 9.992134075089084e-05,
      "loss": 0.1831,
      "step": 15
    },
    {
      "epoch": 0.6320987654320988,
      "grad_norm": 0.45563286542892456,
      "learning_rate": 9.982307470588098e-05,
      "loss": 0.1799,
      "step": 16
    },
    {
      "epoch": 0.671604938271605,
      "grad_norm": 0.29667672514915466,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.1765,
      "step": 17
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.26607605814933777,
      "learning_rate": 9.950905626682228e-05,
      "loss": 0.152,
      "step": 18
    },
    {
      "epoch": 0.7506172839506173,
      "grad_norm": 0.3229130506515503,
      "learning_rate": 9.92935509259118e-05,
      "loss": 0.1587,
      "step": 19
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.26843205094337463,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1353,
      "step": 20
    },
    {
      "epoch": 0.7901234567901234,
      "eval_loss": 0.14046554267406464,
      "eval_runtime": 28.8765,
      "eval_samples_per_second": 1.558,
      "eval_steps_per_second": 1.558,
      "step": 20
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 0.36189424991607666,
      "learning_rate": 9.874639560909117e-05,
      "loss": 0.1507,
      "step": 21
    },
    {
      "epoch": 0.8691358024691358,
      "grad_norm": 0.6486225128173828,
      "learning_rate": 9.841517610611309e-05,
      "loss": 0.1286,
      "step": 22
    },
    {
      "epoch": 0.908641975308642,
      "grad_norm": 0.26178908348083496,
      "learning_rate": 9.804586609725499e-05,
      "loss": 0.12,
      "step": 23
    },
    {
      "epoch": 0.9481481481481482,
      "grad_norm": 0.3001941442489624,
      "learning_rate": 9.763875613614482e-05,
      "loss": 0.1337,
      "step": 24
    },
    {
      "epoch": 0.9876543209876543,
      "grad_norm": 0.3841504156589508,
      "learning_rate": 9.719416651541839e-05,
      "loss": 0.1293,
      "step": 25
    },
    {
      "epoch": 1.0271604938271606,
      "grad_norm": 0.5809849500656128,
      "learning_rate": 9.671244701472999e-05,
      "loss": 0.2039,
      "step": 26
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.4042055904865265,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.103,
      "step": 27
    },
    {
      "epoch": 1.106172839506173,
      "grad_norm": 0.533566951751709,
      "learning_rate": 9.563916325306594e-05,
      "loss": 0.1191,
      "step": 28
    },
    {
      "epoch": 1.145679012345679,
      "grad_norm": 0.3494681715965271,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1124,
      "step": 29
    },
    {
      "epoch": 1.1851851851851851,
      "grad_norm": 0.2729981243610382,
      "learning_rate": 9.442228179894362e-05,
      "loss": 0.0936,
      "step": 30
    },
    {
      "epoch": 1.1851851851851851,
      "eval_loss": 0.10264386981725693,
      "eval_runtime": 28.8731,
      "eval_samples_per_second": 1.559,
      "eval_steps_per_second": 1.559,
      "step": 30
    },
    {
      "epoch": 1.2246913580246914,
      "grad_norm": 0.42651042342185974,
      "learning_rate": 9.376117109543769e-05,
      "loss": 0.0709,
      "step": 31
    },
    {
      "epoch": 1.2641975308641975,
      "grad_norm": 0.34063801169395447,
      "learning_rate": 9.306563141162046e-05,
      "loss": 0.1118,
      "step": 32
    },
    {
      "epoch": 1.3037037037037038,
      "grad_norm": 0.23011094331741333,
      "learning_rate": 9.233620996141421e-05,
      "loss": 0.084,
      "step": 33
    },
    {
      "epoch": 1.34320987654321,
      "grad_norm": 0.2625843286514282,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0922,
      "step": 34
    },
    {
      "epoch": 1.382716049382716,
      "grad_norm": 0.31042736768722534,
      "learning_rate": 9.077804344796302e-05,
      "loss": 0.0898,
      "step": 35
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.34055107831954956,
      "learning_rate": 8.995052426791247e-05,
      "loss": 0.0862,
      "step": 36
    },
    {
      "epoch": 1.4617283950617284,
      "grad_norm": 0.3294934928417206,
      "learning_rate": 8.90915741234015e-05,
      "loss": 0.0761,
      "step": 37
    },
    {
      "epoch": 1.5012345679012347,
      "grad_norm": 0.3585388660430908,
      "learning_rate": 8.820186879108038e-05,
      "loss": 0.0879,
      "step": 38
    },
    {
      "epoch": 1.5407407407407407,
      "grad_norm": 0.5858510136604309,
      "learning_rate": 8.728210824415827e-05,
      "loss": 0.0919,
      "step": 39
    },
    {
      "epoch": 1.5802469135802468,
      "grad_norm": 0.34292086958885193,
      "learning_rate": 8.633301610170135e-05,
      "loss": 0.0699,
      "step": 40
    },
    {
      "epoch": 1.5802469135802468,
      "eval_loss": 0.09213875979185104,
      "eval_runtime": 28.8699,
      "eval_samples_per_second": 1.559,
      "eval_steps_per_second": 1.559,
      "step": 40
    },
    {
      "epoch": 1.6197530864197531,
      "grad_norm": 0.6664292812347412,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1028,
      "step": 41
    },
    {
      "epoch": 1.6592592592592592,
      "grad_norm": 0.2346915900707245,
      "learning_rate": 8.434984630174509e-05,
      "loss": 0.0633,
      "step": 42
    },
    {
      "epoch": 1.6987654320987655,
      "grad_norm": 0.23697040975093842,
      "learning_rate": 8.33173288976002e-05,
      "loss": 0.0817,
      "step": 43
    },
    {
      "epoch": 1.7382716049382716,
      "grad_norm": 0.23535865545272827,
      "learning_rate": 8.225859917710439e-05,
      "loss": 0.0806,
      "step": 44
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.32034656405448914,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.0621,
      "step": 45
    },
    {
      "epoch": 1.817283950617284,
      "grad_norm": 0.3022051453590393,
      "learning_rate": 8.006585456492029e-05,
      "loss": 0.0649,
      "step": 46
    },
    {
      "epoch": 1.8567901234567903,
      "grad_norm": 0.34929460287094116,
      "learning_rate": 7.89335648089903e-05,
      "loss": 0.1043,
      "step": 47
    },
    {
      "epoch": 1.8962962962962964,
      "grad_norm": 0.33460837602615356,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0655,
      "step": 48
    },
    {
      "epoch": 1.9358024691358025,
      "grad_norm": 0.295312762260437,
      "learning_rate": 7.660160382576683e-05,
      "loss": 0.0709,
      "step": 49
    },
    {
      "epoch": 1.9753086419753085,
      "grad_norm": 0.2986871302127838,
      "learning_rate": 7.540376726232648e-05,
      "loss": 0.0669,
      "step": 50
    },
    {
      "epoch": 1.9753086419753085,
      "eval_loss": 0.07618217915296555,
      "eval_runtime": 29.0161,
      "eval_samples_per_second": 1.551,
      "eval_steps_per_second": 1.551,
      "step": 50
    },
    {
      "epoch": 2.0148148148148146,
      "grad_norm": 0.4982636570930481,
      "learning_rate": 7.4185944355262e-05,
      "loss": 0.0967,
      "step": 51
    },
    {
      "epoch": 2.054320987654321,
      "grad_norm": 0.269115686416626,
      "learning_rate": 7.294909322337689e-05,
      "loss": 0.0567,
      "step": 52
    },
    {
      "epoch": 2.093827160493827,
      "grad_norm": 0.2859558165073395,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.0475,
      "step": 53
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.3045737147331238,
      "learning_rate": 7.042221284679982e-05,
      "loss": 0.067,
      "step": 54
    },
    {
      "epoch": 2.1728395061728394,
      "grad_norm": 0.23094934225082397,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.059,
      "step": 55
    },
    {
      "epoch": 2.212345679012346,
      "grad_norm": 0.2435174435377121,
      "learning_rate": 6.783107663311565e-05,
      "loss": 0.0551,
      "step": 56
    },
    {
      "epoch": 2.251851851851852,
      "grad_norm": 0.2753399908542633,
      "learning_rate": 6.651395309775837e-05,
      "loss": 0.0553,
      "step": 57
    },
    {
      "epoch": 2.291358024691358,
      "grad_norm": 0.21308325231075287,
      "learning_rate": 6.518383725548074e-05,
      "loss": 0.0608,
      "step": 58
    },
    {
      "epoch": 2.330864197530864,
      "grad_norm": 0.23701149225234985,
      "learning_rate": 6.384177557124247e-05,
      "loss": 0.0583,
      "step": 59
    },
    {
      "epoch": 2.3703703703703702,
      "grad_norm": 0.2702789008617401,
      "learning_rate": 6.248882390836135e-05,
      "loss": 0.0588,
      "step": 60
    },
    {
      "epoch": 2.3703703703703702,
      "eval_loss": 0.06888000667095184,
      "eval_runtime": 28.872,
      "eval_samples_per_second": 1.559,
      "eval_steps_per_second": 1.559,
      "step": 60
    },
    {
      "epoch": 2.4098765432098768,
      "grad_norm": 0.2512145936489105,
      "learning_rate": 6.112604669781572e-05,
      "loss": 0.0566,
      "step": 61
    },
    {
      "epoch": 2.449382716049383,
      "grad_norm": 0.2276078313589096,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0504,
      "step": 62
    },
    {
      "epoch": 2.488888888888889,
      "grad_norm": 0.2561245560646057,
      "learning_rate": 5.837531116523682e-05,
      "loss": 0.0642,
      "step": 63
    },
    {
      "epoch": 2.528395061728395,
      "grad_norm": 0.28686603903770447,
      "learning_rate": 5.698951697677498e-05,
      "loss": 0.0624,
      "step": 64
    },
    {
      "epoch": 2.567901234567901,
      "grad_norm": 0.27583783864974976,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.0691,
      "step": 65
    },
    {
      "epoch": 2.6074074074074076,
      "grad_norm": 0.2391774207353592,
      "learning_rate": 5.420252624646238e-05,
      "loss": 0.0636,
      "step": 66
    },
    {
      "epoch": 2.6469135802469137,
      "grad_norm": 0.2027847170829773,
      "learning_rate": 5.2803522361859594e-05,
      "loss": 0.0616,
      "step": 67
    },
    {
      "epoch": 2.68641975308642,
      "grad_norm": 0.23949837684631348,
      "learning_rate": 5.140231281379345e-05,
      "loss": 0.0484,
      "step": 68
    },
    {
      "epoch": 2.725925925925926,
      "grad_norm": 0.2478315830230713,
      "learning_rate": 5e-05,
      "loss": 0.0625,
      "step": 69
    },
    {
      "epoch": 2.765432098765432,
      "grad_norm": 0.23141150176525116,
      "learning_rate": 4.859768718620656e-05,
      "loss": 0.0504,
      "step": 70
    },
    {
      "epoch": 2.765432098765432,
      "eval_loss": 0.06366074830293655,
      "eval_runtime": 28.7953,
      "eval_samples_per_second": 1.563,
      "eval_steps_per_second": 1.563,
      "step": 70
    },
    {
      "epoch": 2.8049382716049385,
      "grad_norm": 0.18038898706436157,
      "learning_rate": 4.7196477638140404e-05,
      "loss": 0.0555,
      "step": 71
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": 0.2886255383491516,
      "learning_rate": 4.579747375353763e-05,
      "loss": 0.0594,
      "step": 72
    },
    {
      "epoch": 2.8839506172839506,
      "grad_norm": 0.38132917881011963,
      "learning_rate": 4.4401776194834613e-05,
      "loss": 0.0507,
      "step": 73
    },
    {
      "epoch": 2.9234567901234567,
      "grad_norm": 0.28990426659584045,
      "learning_rate": 4.3010483023225045e-05,
      "loss": 0.0594,
      "step": 74
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.15174922347068787,
      "learning_rate": 4.162468883476319e-05,
      "loss": 0.0419,
      "step": 75
    },
    {
      "epoch": 3.0024691358024693,
      "grad_norm": 0.3690943717956543,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0958,
      "step": 76
    },
    {
      "epoch": 3.0419753086419754,
      "grad_norm": 0.2531915009021759,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.0485,
      "step": 77
    },
    {
      "epoch": 3.0814814814814815,
      "grad_norm": 0.19611580669879913,
      "learning_rate": 3.7511176091638653e-05,
      "loss": 0.038,
      "step": 78
    },
    {
      "epoch": 3.1209876543209876,
      "grad_norm": 0.22277683019638062,
      "learning_rate": 3.6158224428757535e-05,
      "loss": 0.0475,
      "step": 79
    },
    {
      "epoch": 3.1604938271604937,
      "grad_norm": 0.18994340300559998,
      "learning_rate": 3.4816162744519263e-05,
      "loss": 0.0506,
      "step": 80
    },
    {
      "epoch": 3.1604938271604937,
      "eval_loss": 0.06252085417509079,
      "eval_runtime": 28.7625,
      "eval_samples_per_second": 1.565,
      "eval_steps_per_second": 1.565,
      "step": 80
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.19616547226905823,
      "learning_rate": 3.3486046902241664e-05,
      "loss": 0.0475,
      "step": 81
    },
    {
      "epoch": 3.2395061728395063,
      "grad_norm": 0.18008606135845184,
      "learning_rate": 3.216892336688435e-05,
      "loss": 0.0463,
      "step": 82
    },
    {
      "epoch": 3.2790123456790123,
      "grad_norm": 0.24431699514389038,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0413,
      "step": 83
    },
    {
      "epoch": 3.3185185185185184,
      "grad_norm": 0.5251120328903198,
      "learning_rate": 2.9577787153200197e-05,
      "loss": 0.043,
      "step": 84
    },
    {
      "epoch": 3.3580246913580245,
      "grad_norm": 0.2262587547302246,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 0.0496,
      "step": 85
    },
    {
      "epoch": 3.397530864197531,
      "grad_norm": 0.24220603704452515,
      "learning_rate": 2.705090677662311e-05,
      "loss": 0.0539,
      "step": 86
    },
    {
      "epoch": 3.437037037037037,
      "grad_norm": 0.21658729016780853,
      "learning_rate": 2.581405564473801e-05,
      "loss": 0.0469,
      "step": 87
    },
    {
      "epoch": 3.476543209876543,
      "grad_norm": 0.34485307335853577,
      "learning_rate": 2.459623273767354e-05,
      "loss": 0.0538,
      "step": 88
    },
    {
      "epoch": 3.5160493827160493,
      "grad_norm": 0.21435955166816711,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.046,
      "step": 89
    },
    {
      "epoch": 3.5555555555555554,
      "grad_norm": 0.24011144042015076,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.055,
      "step": 90
    },
    {
      "epoch": 3.5555555555555554,
      "eval_loss": 0.0600549690425396,
      "eval_runtime": 28.75,
      "eval_samples_per_second": 1.565,
      "eval_steps_per_second": 1.565,
      "step": 90
    },
    {
      "epoch": 3.595061728395062,
      "grad_norm": 0.38919126987457275,
      "learning_rate": 2.1066435191009715e-05,
      "loss": 0.0507,
      "step": 91
    },
    {
      "epoch": 3.634567901234568,
      "grad_norm": 0.15967682003974915,
      "learning_rate": 1.9934145435079702e-05,
      "loss": 0.0376,
      "step": 92
    },
    {
      "epoch": 3.674074074074074,
      "grad_norm": 0.25223422050476074,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 0.0417,
      "step": 93
    },
    {
      "epoch": 3.71358024691358,
      "grad_norm": 0.2764740288257599,
      "learning_rate": 1.774140082289563e-05,
      "loss": 0.0524,
      "step": 94
    },
    {
      "epoch": 3.753086419753086,
      "grad_norm": 0.2607303261756897,
      "learning_rate": 1.6682671102399805e-05,
      "loss": 0.049,
      "step": 95
    },
    {
      "epoch": 3.7925925925925927,
      "grad_norm": 0.29611456394195557,
      "learning_rate": 1.5650153698254916e-05,
      "loss": 0.0392,
      "step": 96
    },
    {
      "epoch": 3.832098765432099,
      "grad_norm": 0.2231958508491516,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0474,
      "step": 97
    },
    {
      "epoch": 3.871604938271605,
      "grad_norm": 0.2251063585281372,
      "learning_rate": 1.3666983898298657e-05,
      "loss": 0.0474,
      "step": 98
    },
    {
      "epoch": 3.911111111111111,
      "grad_norm": 0.2181674689054489,
      "learning_rate": 1.2717891755841722e-05,
      "loss": 0.0444,
      "step": 99
    },
    {
      "epoch": 3.950617283950617,
      "grad_norm": 0.22630761563777924,
      "learning_rate": 1.1798131208919627e-05,
      "loss": 0.0466,
      "step": 100
    },
    {
      "epoch": 3.950617283950617,
      "eval_loss": 0.05923856049776077,
      "eval_runtime": 28.7669,
      "eval_samples_per_second": 1.564,
      "eval_steps_per_second": 1.564,
      "step": 100
    },
    {
      "epoch": 3.9901234567901236,
      "grad_norm": 0.1919824182987213,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0531,
      "step": 101
    },
    {
      "epoch": 4.029629629629629,
      "grad_norm": 0.3160097301006317,
      "learning_rate": 1.004947573208756e-05,
      "loss": 0.0763,
      "step": 102
    },
    {
      "epoch": 4.069135802469136,
      "grad_norm": 0.17580732703208923,
      "learning_rate": 9.221956552036992e-06,
      "loss": 0.0418,
      "step": 103
    },
    {
      "epoch": 4.108641975308642,
      "grad_norm": 0.18130230903625488,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0354,
      "step": 104
    },
    {
      "epoch": 4.148148148148148,
      "grad_norm": 0.21970264613628387,
      "learning_rate": 7.663790038585793e-06,
      "loss": 0.0531,
      "step": 105
    },
    {
      "epoch": 4.187654320987654,
      "grad_norm": 0.20478364825248718,
      "learning_rate": 6.934368588379553e-06,
      "loss": 0.05,
      "step": 106
    },
    {
      "epoch": 4.22716049382716,
      "grad_norm": 0.3399154245853424,
      "learning_rate": 6.238828904562316e-06,
      "loss": 0.0392,
      "step": 107
    },
    {
      "epoch": 4.266666666666667,
      "grad_norm": 0.20683470368385315,
      "learning_rate": 5.577718201056392e-06,
      "loss": 0.0456,
      "step": 108
    },
    {
      "epoch": 4.306172839506173,
      "grad_norm": 0.18971897661685944,
      "learning_rate": 4.951556604879048e-06,
      "loss": 0.0423,
      "step": 109
    },
    {
      "epoch": 4.345679012345679,
      "grad_norm": 0.17349012196063995,
      "learning_rate": 4.360836746934055e-06,
      "loss": 0.0341,
      "step": 110
    },
    {
      "epoch": 4.345679012345679,
      "eval_loss": 0.05875943973660469,
      "eval_runtime": 28.789,
      "eval_samples_per_second": 1.563,
      "eval_steps_per_second": 1.563,
      "step": 110
    },
    {
      "epoch": 4.385185185185185,
      "grad_norm": 0.18210552632808685,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0407,
      "step": 111
    },
    {
      "epoch": 4.424691358024692,
      "grad_norm": 0.19626383483409882,
      "learning_rate": 3.2875529852700147e-06,
      "loss": 0.0383,
      "step": 112
    },
    {
      "epoch": 4.4641975308641975,
      "grad_norm": 0.19993366301059723,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0405,
      "step": 113
    },
    {
      "epoch": 4.503703703703704,
      "grad_norm": 0.20129625499248505,
      "learning_rate": 2.361243863855184e-06,
      "loss": 0.0506,
      "step": 114
    },
    {
      "epoch": 4.54320987654321,
      "grad_norm": 0.1955385059118271,
      "learning_rate": 1.9541339027450256e-06,
      "loss": 0.036,
      "step": 115
    },
    {
      "epoch": 4.582716049382716,
      "grad_norm": 0.19023007154464722,
      "learning_rate": 1.584823893886933e-06,
      "loss": 0.0448,
      "step": 116
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 0.17877797782421112,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 0.0414,
      "step": 117
    },
    {
      "epoch": 4.661728395061728,
      "grad_norm": 0.21489191055297852,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0515,
      "step": 118
    },
    {
      "epoch": 4.701234567901235,
      "grad_norm": 0.1945088654756546,
      "learning_rate": 7.064490740882057e-07,
      "loss": 0.0421,
      "step": 119
    },
    {
      "epoch": 4.7407407407407405,
      "grad_norm": 0.2054254114627838,
      "learning_rate": 4.909437331777179e-07,
      "loss": 0.0453,
      "step": 120
    },
    {
      "epoch": 4.7407407407407405,
      "eval_loss": 0.05881137773394585,
      "eval_runtime": 28.7682,
      "eval_samples_per_second": 1.564,
      "eval_steps_per_second": 1.564,
      "step": 120
    },
    {
      "epoch": 4.780246913580247,
      "grad_norm": 0.20341403782367706,
      "learning_rate": 3.143895053378698e-07,
      "loss": 0.0381,
      "step": 121
    },
    {
      "epoch": 4.8197530864197535,
      "grad_norm": 0.17649434506893158,
      "learning_rate": 1.7692529411904578e-07,
      "loss": 0.038,
      "step": 122
    },
    {
      "epoch": 4.859259259259259,
      "grad_norm": 0.18537993729114532,
      "learning_rate": 7.865924910916977e-08,
      "loss": 0.0447,
      "step": 123
    },
    {
      "epoch": 4.898765432098766,
      "grad_norm": 0.20147761702537537,
      "learning_rate": 1.9668680847356735e-08,
      "loss": 0.0405,
      "step": 124
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 0.160012349486351,
      "learning_rate": 0.0,
      "loss": 0.0436,
      "step": 125
    },
    {
      "epoch": 4.938271604938271,
      "step": 125,
      "total_flos": 1.69693907337216e+17,
      "train_loss": 0.09710262235999108,
      "train_runtime": 4847.4127,
      "train_samples_per_second": 0.418,
      "train_steps_per_second": 0.026
    }
  ],
  "logging_steps": 1,
  "max_steps": 125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.69693907337216e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}