{
  "best_metric": 0.5244021415710449,
  "best_model_checkpoint": "./output_v2/7b_cluster00_Nous-Hermes-llama-2-7b_codellama_blob_1/checkpoint-200",
  "epoch": 0.5614035087719298,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 9.999999999999999e-06,
      "loss": 0.7795,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 0.6789,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 0.6846,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 3.9999999999999996e-05,
      "loss": 0.6883,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.9999999999999996e-05,
      "loss": 0.5963,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 0.6577,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 7e-05,
      "loss": 0.625,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.999999999999999e-05,
      "loss": 0.6864,
      "step": 8
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.999999999999999e-05,
      "loss": 0.5344,
      "step": 9
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.999999999999999e-05,
      "loss": 0.5956,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00010999999999999998,
      "loss": 0.6993,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.623,
      "step": 12
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00013,
      "loss": 0.5547,
      "step": 13
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00014,
      "loss": 0.5404,
      "step": 14
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00015,
      "loss": 0.5536,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00015999999999999999,
      "loss": 0.6886,
      "step": 16
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00016999999999999999,
      "loss": 0.8917,
      "step": 17
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.6834,
      "step": 18
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00018999999999999998,
      "loss": 0.4784,
      "step": 19
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019999999999999998,
      "loss": 0.5869,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.9495,
      "step": 21
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00021999999999999995,
      "loss": 0.8727,
      "step": 22
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00023,
      "loss": 0.671,
      "step": 23
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.6582,
      "step": 24
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00025,
      "loss": 0.6599,
      "step": 25
    },
    {
      "epoch": 0.07,
      "eval_loss": 0.6080610752105713,
      "eval_runtime": 26.3081,
      "eval_samples_per_second": 7.602,
      "eval_steps_per_second": 1.901,
      "step": 25
    },
    {
      "dharma_eval_accuracy": 0.45126789906203946,
      "dharma_eval_accuracy_ARC-Challenge": 0.5555555555555556,
      "dharma_eval_accuracy_ARC-Easy": 0.5555555555555556,
      "dharma_eval_accuracy_BoolQ": 0.7037037037037037,
      "dharma_eval_accuracy_MMLU": 0.3888888888888889,
      "dharma_eval_accuracy_agieval": 0.2711864406779661,
      "dharma_eval_accuracy_bigbench": 0.47540983606557374,
      "dharma_eval_accuracy_openbookqa": 0.35185185185185186,
      "dharma_eval_accuracy_truthful_qa": 0.42592592592592593,
      "dharma_eval_accuracy_winogrande": 0.3333333333333333,
      "dharma_loss": 2.3038411536216734,
      "epoch": 0.07,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00026,
      "loss": 0.568,
      "step": 26
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00027,
      "loss": 0.569,
      "step": 27
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00028,
      "loss": 0.4481,
      "step": 28
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00029,
      "loss": 0.5482,
      "step": 29
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 0.8189,
      "step": 30
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002999992132854894,
      "loss": 0.928,
      "step": 31
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002999968531502098,
      "loss": 0.6567,
      "step": 32
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002999929196189179,
      "loss": 0.469,
      "step": 33
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00029998741273287477,
      "loss": 0.6043,
      "step": 34
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002999803325498448,
      "loss": 0.6288,
      "step": 35
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002999716791440959,
      "loss": 0.6692,
      "step": 36
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00029996145260639806,
      "loss": 0.7591,
      "step": 37
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000299949653044023,
      "loss": 0.5729,
      "step": 38
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00029993628058074245,
      "loss": 0.4347,
      "step": 39
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00029992133535682725,
      "loss": 0.7718,
      "step": 40
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00029990481752904563,
      "loss": 0.7768,
      "step": 41
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002998867272706619,
      "loss": 0.7359,
      "step": 42
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002998670647714343,
      "loss": 0.5626,
      "step": 43
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00029984583023761317,
      "loss": 0.5444,
      "step": 44
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00029982302389193856,
      "loss": 0.5487,
      "step": 45
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00029979864597363845,
      "loss": 0.4916,
      "step": 46
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002997726967384255,
      "loss": 0.4817,
      "step": 47
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00029974517645849503,
      "loss": 0.6375,
      "step": 48
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002997160854225217,
      "loss": 0.5938,
      "step": 49
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002996854239356567,
      "loss": 0.5868,
      "step": 50
    },
    {
      "epoch": 0.14,
      "eval_loss": 0.5586252212524414,
      "eval_runtime": 26.2488,
      "eval_samples_per_second": 7.619,
      "eval_steps_per_second": 1.905,
      "step": 50
    },
    {
      "dharma_eval_accuracy": 0.4279315127544574,
      "dharma_eval_accuracy_ARC-Challenge": 0.5925925925925926,
      "dharma_eval_accuracy_ARC-Easy": 0.6481481481481481,
      "dharma_eval_accuracy_BoolQ": 0.7037037037037037,
      "dharma_eval_accuracy_MMLU": 0.4074074074074074,
      "dharma_eval_accuracy_agieval": 0.2542372881355932,
      "dharma_eval_accuracy_bigbench": 0.39344262295081966,
      "dharma_eval_accuracy_openbookqa": 0.3148148148148148,
      "dharma_eval_accuracy_truthful_qa": 0.4444444444444444,
      "dharma_eval_accuracy_winogrande": 0.09259259259259259,
      "dharma_loss": 2.1031297972202303,
      "epoch": 0.14,
      "step": 50
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00029965319231952455,
      "loss": 0.612,
      "step": 51
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002996193909122197,
      "loss": 0.8942,
      "step": 52
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00029958402006830274,
      "loss": 0.5766,
      "step": 53
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002995470801587973,
      "loss": 0.6238,
      "step": 54
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002995085715711854,
      "loss": 0.5561,
      "step": 55
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002994684947094039,
      "loss": 0.6203,
      "step": 56
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002994268499938403,
      "loss": 0.6534,
      "step": 57
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00029938363786132774,
      "loss": 0.594,
      "step": 58
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00029933885876514115,
      "loss": 0.5608,
      "step": 59
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002992925131749921,
      "loss": 0.6622,
      "step": 60
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00029924460157702376,
      "loss": 0.5207,
      "step": 61
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00029919512447380625,
      "loss": 0.5308,
      "step": 62
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002991440823843309,
      "loss": 0.6217,
      "step": 63
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002990914758440051,
      "loss": 0.6541,
      "step": 64
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00029903730540464666,
      "loss": 0.514,
      "step": 65
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00029898157163447763,
      "loss": 0.5923,
      "step": 66
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002989242751181191,
      "loss": 0.6156,
      "step": 67
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002988654164565843,
      "loss": 0.5406,
      "step": 68
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0002988049962672728,
      "loss": 0.4563,
      "step": 69
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00029874301518396376,
      "loss": 0.5448,
      "step": 70
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00029867947385680936,
      "loss": 0.6164,
      "step": 71
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002986143729523282,
      "loss": 0.5636,
      "step": 72
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00029854771315339785,
      "loss": 0.5301,
      "step": 73
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00029847949515924806,
      "loss": 0.6074,
      "step": 74
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002984097196854534,
      "loss": 0.5123,
      "step": 75
    },
    {
      "epoch": 0.21,
      "eval_loss": 0.541282057762146,
      "eval_runtime": 26.1496,
      "eval_samples_per_second": 7.648,
      "eval_steps_per_second": 1.912,
      "step": 75
    },
    {
      "dharma_eval_accuracy": 0.4466804336366869,
      "dharma_eval_accuracy_ARC-Challenge": 0.6296296296296297,
      "dharma_eval_accuracy_ARC-Easy": 0.5740740740740741,
      "dharma_eval_accuracy_BoolQ": 0.7037037037037037,
      "dharma_eval_accuracy_MMLU": 0.4074074074074074,
      "dharma_eval_accuracy_agieval": 0.2711864406779661,
      "dharma_eval_accuracy_bigbench": 0.5081967213114754,
      "dharma_eval_accuracy_openbookqa": 0.12962962962962962,
      "dharma_eval_accuracy_truthful_qa": 0.4074074074074074,
      "dharma_eval_accuracy_winogrande": 0.3888888888888889,
      "dharma_loss": 2.2732545466423035,
      "epoch": 0.21,
      "step": 75
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002983383874639254,
      "loss": 0.5206,
      "step": 76
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00029826549924290557,
      "loss": 0.6452,
      "step": 77
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00029819105578695655,
      "loss": 0.6085,
      "step": 78
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00029811505787695524,
      "loss": 0.5163,
      "step": 79
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00029803750631008356,
      "loss": 0.5511,
      "step": 80
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002979584018998209,
      "loss": 0.6395,
      "step": 81
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000297877745475935,
      "loss": 0.6281,
      "step": 82
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00029779553788447357,
      "loss": 0.4932,
      "step": 83
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00029771177998775536,
      "loss": 0.5497,
      "step": 84
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002976264726643611,
      "loss": 0.5496,
      "step": 85
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00029753961680912427,
      "loss": 0.4569,
      "step": 86
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00029745121333312163,
      "loss": 0.5152,
      "step": 87
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002973612631636638,
      "loss": 0.6928,
      "step": 88
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002972697672442856,
      "loss": 0.5503,
      "step": 89
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002971767265347358,
      "loss": 0.7074,
      "step": 90
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00029708214201096755,
      "loss": 0.6397,
      "step": 91
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002969860146651276,
      "loss": 0.7815,
      "step": 92
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00029688834550554646,
      "loss": 0.6274,
      "step": 93
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002967891355567273,
      "loss": 0.6196,
      "step": 94
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00029668838585933556,
      "loss": 0.5845,
      "step": 95
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002965860974701879,
      "loss": 0.5934,
      "step": 96
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002964822714622412,
      "loss": 0.6277,
      "step": 97
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.000296376908924581,
      "loss": 0.555,
      "step": 98
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00029627001096241057,
      "loss": 0.5478,
      "step": 99
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002961615786970389,
      "loss": 0.6851,
      "step": 100
    },
    {
      "epoch": 0.28,
      "eval_loss": 0.5322936177253723,
      "eval_runtime": 26.2408,
      "eval_samples_per_second": 7.622,
      "eval_steps_per_second": 1.905,
      "step": 100
    },
    {
      "dharma_eval_accuracy": 0.3837211296690781,
      "dharma_eval_accuracy_ARC-Challenge": 0.6296296296296297,
      "dharma_eval_accuracy_ARC-Easy": 0.5925925925925926,
      "dharma_eval_accuracy_BoolQ": 0.7037037037037037,
      "dharma_eval_accuracy_MMLU": 0.4444444444444444,
      "dharma_eval_accuracy_agieval": 0.22033898305084745,
      "dharma_eval_accuracy_bigbench": 0.3442622950819672,
      "dharma_eval_accuracy_openbookqa": 0.09259259259259259,
      "dharma_eval_accuracy_truthful_qa": 0.2777777777777778,
      "dharma_eval_accuracy_winogrande": 0.14814814814814814,
      "dharma_loss": 2.1400452837944033,
      "epoch": 0.28,
      "step": 100
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00029605161326586916,
      "loss": 0.5637,
      "step": 101
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002959401158223867,
      "loss": 0.5563,
      "step": 102
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002958270875361469,
      "loss": 0.7583,
      "step": 103
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002957125295927631,
      "loss": 0.4775,
      "step": 104
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002955964431938939,
      "loss": 0.6912,
      "step": 105
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002954788295572305,
      "loss": 0.7142,
      "step": 106
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00029535968991648454,
      "loss": 0.5264,
      "step": 107
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00029523902552137433,
      "loss": 0.509,
      "step": 108
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002951168376376124,
      "loss": 0.7375,
      "step": 109
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0002949931275468917,
      "loss": 0.4407,
      "step": 110
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00029486789654687253,
      "loss": 0.5361,
      "step": 111
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00029474114595116896,
      "loss": 0.6161,
      "step": 112
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00029461287708933473,
      "loss": 0.589,
      "step": 113
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002944830913068494,
      "loss": 0.5677,
      "step": 114
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00029435178996510455,
      "loss": 0.5946,
      "step": 115
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00029421897444138897,
      "loss": 0.526,
      "step": 116
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002940846461288748,
      "loss": 0.8164,
      "step": 117
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002939488064366024,
      "loss": 0.6519,
      "step": 118
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00029381145678946584,
      "loss": 0.6519,
      "step": 119
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00029367259862819804,
      "loss": 0.7479,
      "step": 120
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002935322334093553,
      "loss": 0.5756,
      "step": 121
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002933903626053024,
      "loss": 0.3582,
      "step": 122
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00029324698770419685,
      "loss": 0.5282,
      "step": 123
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002931021102099737,
      "loss": 0.5435,
      "step": 124
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002929557316423291,
      "loss": 0.7049,
      "step": 125
    },
    {
      "epoch": 0.35,
      "eval_loss": 0.539155125617981,
      "eval_runtime": 26.1963,
      "eval_samples_per_second": 7.635,
      "eval_steps_per_second": 1.909,
      "step": 125
    },
    {
      "dharma_eval_accuracy": 0.25951081518986185,
      "dharma_eval_accuracy_ARC-Challenge": 0.42592592592592593,
      "dharma_eval_accuracy_ARC-Easy": 0.46296296296296297,
      "dharma_eval_accuracy_BoolQ": 0.1111111111111111,
      "dharma_eval_accuracy_MMLU": 0.4074074074074074,
      "dharma_eval_accuracy_agieval": 0.2542372881355932,
      "dharma_eval_accuracy_bigbench": 0.22950819672131148,
      "dharma_eval_accuracy_openbookqa": 0.14814814814814814,
      "dharma_eval_accuracy_truthful_qa": 0.2962962962962963,
      "dharma_eval_accuracy_winogrande": 0.0,
      "dharma_loss": 2.083115490436554,
      "epoch": 0.35,
      "step": 125
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00029280785353670514,
      "loss": 0.5792,
      "step": 126
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00029265847744427303,
      "loss": 0.8134,
      "step": 127
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00029250760493191734,
      "loss": 0.6023,
      "step": 128
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002923552375822194,
      "loss": 0.6515,
      "step": 129
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00029220137699344055,
      "loss": 0.7513,
      "step": 130
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00029204602477950556,
      "loss": 0.6878,
      "step": 131
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00029188918256998564,
      "loss": 0.4415,
      "step": 132
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002917308520100814,
      "loss": 0.5476,
      "step": 133
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00029157103476060544,
      "loss": 0.5394,
      "step": 134
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002914097324979651,
      "loss": 0.4909,
      "step": 135
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002912469469141448,
      "loss": 0.4633,
      "step": 136
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002910826797166882,
      "loss": 0.6073,
      "step": 137
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00029091693262868067,
      "loss": 0.7209,
      "step": 138
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002907497073887305,
      "loss": 0.6085,
      "step": 139
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002905810057509515,
      "loss": 0.7864,
      "step": 140
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00029041082948494395,
      "loss": 0.5827,
      "step": 141
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00029023918037577635,
      "loss": 0.5981,
      "step": 142
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00029006606022396667,
      "loss": 0.5293,
      "step": 143
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00028989147084546333,
      "loss": 0.7339,
      "step": 144
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00028971541407162634,
      "loss": 0.6057,
      "step": 145
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002895378917492079,
      "loss": 0.5364,
      "step": 146
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0002893589057403332,
      "loss": 0.5716,
      "step": 147
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002891784579224808,
      "loss": 1.1362,
      "step": 148
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00028899655018846295,
      "loss": 0.5743,
      "step": 149
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002888131844464056,
      "loss": 0.5567,
      "step": 150
    },
    {
      "epoch": 0.42,
      "eval_loss": 0.5322738885879517,
      "eval_runtime": 26.2089,
      "eval_samples_per_second": 7.631,
      "eval_steps_per_second": 1.908,
      "step": 150
    },
    {
      "dharma_eval_accuracy": 0.38818510400122574,
      "dharma_eval_accuracy_ARC-Challenge": 0.4074074074074074,
      "dharma_eval_accuracy_ARC-Easy": 0.46296296296296297,
      "dharma_eval_accuracy_BoolQ": 0.7037037037037037,
      "dharma_eval_accuracy_MMLU": 0.37037037037037035,
      "dharma_eval_accuracy_agieval": 0.1864406779661017,
      "dharma_eval_accuracy_bigbench": 0.3442622950819672,
      "dharma_eval_accuracy_openbookqa": 0.2037037037037037,
      "dharma_eval_accuracy_truthful_qa": 0.4074074074074074,
      "dharma_eval_accuracy_winogrande": 0.4074074074074074,
      "dharma_loss": 2.3776819763183594,
      "epoch": 0.42,
      "step": 150
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002886283626197287,
      "loss": 0.6541,
      "step": 151
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00028844208664712575,
      "loss": 0.4995,
      "step": 152
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002882543584825435,
      "loss": 0.4582,
      "step": 153
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00028806518009516155,
      "loss": 0.7142,
      "step": 154
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002878745534693718,
      "loss": 0.5899,
      "step": 155
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00028768248060475726,
      "loss": 0.4097,
      "step": 156
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002874889635160714,
      "loss": 0.5437,
      "step": 157
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002872940042332169,
      "loss": 0.5694,
      "step": 158
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002870976048012244,
      "loss": 0.5558,
      "step": 159
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.000286899767280231,
      "loss": 0.6174,
      "step": 160
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0002867004937454587,
      "loss": 0.4809,
      "step": 161
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00028649978628719254,
      "loss": 0.7249,
      "step": 162
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00028629764701075885,
      "loss": 0.5729,
      "step": 163
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002860940780365029,
      "loss": 0.3942,
      "step": 164
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000285889081499767,
      "loss": 0.62,
      "step": 165
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00028568265955086774,
      "loss": 0.6196,
      "step": 166
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002854748143550738,
      "loss": 0.4698,
      "step": 167
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00028526554809258275,
      "loss": 0.53,
      "step": 168
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0002850548629584988,
      "loss": 0.6017,
      "step": 169
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00028484276116280926,
      "loss": 0.5452,
      "step": 170
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00028462924493036164,
      "loss": 0.5359,
      "step": 171
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00028441431650084016,
      "loss": 0.4914,
      "step": 172
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00028419797812874237,
      "loss": 0.44,
      "step": 173
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00028398023208335533,
      "loss": 0.4378,
      "step": 174
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00028376108064873215,
      "loss": 0.5328,
      "step": 175
    },
    {
      "epoch": 0.49,
      "eval_loss": 0.5265315771102905,
      "eval_runtime": 26.1903,
      "eval_samples_per_second": 7.636,
      "eval_steps_per_second": 1.909,
      "step": 175
    },
    {
      "dharma_eval_accuracy": 0.35997424982019466,
      "dharma_eval_accuracy_ARC-Challenge": 0.4444444444444444,
      "dharma_eval_accuracy_ARC-Easy": 0.5185185185185185,
      "dharma_eval_accuracy_BoolQ": 0.5925925925925926,
      "dharma_eval_accuracy_MMLU": 0.3888888888888889,
      "dharma_eval_accuracy_agieval": 0.22033898305084745,
      "dharma_eval_accuracy_bigbench": 0.2786885245901639,
      "dharma_eval_accuracy_openbookqa": 0.1111111111111111,
      "dharma_eval_accuracy_truthful_qa": 0.3333333333333333,
      "dharma_eval_accuracy_winogrande": 0.35185185185185186,
      "dharma_loss": 2.2151358013153075,
      "epoch": 0.49,
      "step": 175
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00028354052612366757,
      "loss": 0.7281,
      "step": 176
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002833185708216743,
      "loss": 0.6805,
      "step": 177
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002830952170709583,
      "loss": 0.5105,
      "step": 178
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00028287046721439484,
      "loss": 0.565,
      "step": 179
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00028264432360950353,
      "loss": 0.6562,
      "step": 180
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002824167886284237,
      "loss": 0.4868,
      "step": 181
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002821878646578898,
      "loss": 0.722,
      "step": 182
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0002819575540992058,
      "loss": 0.6236,
      "step": 183
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00028172585936822055,
      "loss": 0.6328,
      "step": 184
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00028149278289530213,
      "loss": 0.5526,
      "step": 185
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00028125832712531246,
      "loss": 0.6678,
      "step": 186
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002810224945175816,
      "loss": 0.6193,
      "step": 187
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00028078528754588205,
      "loss": 0.5589,
      "step": 188
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00028054670869840265,
      "loss": 0.5679,
      "step": 189
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00028030676047772265,
      "loss": 0.4394,
      "step": 190
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00028006544540078534,
      "loss": 0.7148,
      "step": 191
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002798227659988717,
      "loss": 0.7248,
      "step": 192
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00027957872481757374,
      "loss": 0.6304,
      "step": 193
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00027933332441676807,
      "loss": 0.5778,
      "step": 194
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002790865673705888,
      "loss": 0.4473,
      "step": 195
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00027883845626740044,
      "loss": 0.5202,
      "step": 196
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002785889937097712,
      "loss": 0.4966,
      "step": 197
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00027833818231444516,
      "loss": 0.6239,
      "step": 198
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00027808602471231524,
      "loss": 0.5887,
      "step": 199
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002778325235483954,
      "loss": 0.5363,
      "step": 200
    },
    {
      "epoch": 0.56,
      "eval_loss": 0.5244021415710449,
      "eval_runtime": 26.2022,
      "eval_samples_per_second": 7.633,
      "eval_steps_per_second": 1.908,
      "step": 200
    },
    {
      "dharma_eval_accuracy": 0.4286398713863134,
      "dharma_eval_accuracy_ARC-Challenge": 0.5185185185185185,
      "dharma_eval_accuracy_ARC-Easy": 0.5370370370370371,
      "dharma_eval_accuracy_BoolQ": 0.7777777777777778,
      "dharma_eval_accuracy_MMLU": 0.3888888888888889,
      "dharma_eval_accuracy_agieval": 0.2542372881355932,
      "dharma_eval_accuracy_bigbench": 0.3442622950819672,
      "dharma_eval_accuracy_openbookqa": 0.1111111111111111,
      "dharma_eval_accuracy_truthful_qa": 0.4444444444444444,
      "dharma_eval_accuracy_winogrande": 0.48148148148148145,
      "dharma_loss": 2.3920813593864443,
      "epoch": 0.56,
      "step": 200
    }
  ],
  "max_steps": 1000,
  "num_train_epochs": 3,
  "total_flos": 6.277915233887846e+16,
  "trial_name": null,
  "trial_params": null
}