{
  "best_metric": 0.5163459777832031,
  "best_model_checkpoint": "./output_v2/7b_cluster00_Nous-Hermes-llama-2-7b_codellama_blob_1/checkpoint-400",
  "epoch": 1.1228070175438596,
  "global_step": 400,
  "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
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00027757768148179275,
      "loss": 0.4511,
      "step": 201
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00027732150118568017,
      "loss": 0.5601,
      "step": 202
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00027706398534726757,
      "loss": 0.4554,
      "step": 203
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00027680513666777435,
      "loss": 0.472,
      "step": 204
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00027654495786240066,
      "loss": 0.464,
      "step": 205
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00027628345166029906,
      "loss": 0.526,
      "step": 206
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00027602062080454577,
      "loss": 0.6065,
      "step": 207
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002757564680521122,
      "loss": 0.5417,
      "step": 208
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002754909961738357,
      "loss": 0.6115,
      "step": 209
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00027522420795439065,
      "loss": 0.7071,
      "step": 210
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002749561061922592,
      "loss": 0.5509,
      "step": 211
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00027468669369970207,
      "loss": 0.5462,
      "step": 212
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002744159733027287,
      "loss": 0.6335,
      "step": 213
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002741439478410681,
      "loss": 0.6087,
      "step": 214
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002738706201681384,
      "loss": 0.6883,
      "step": 215
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00027359599315101787,
      "loss": 0.5886,
      "step": 216
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00027332006967041366,
      "loss": 0.6278,
      "step": 217
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002730428526206327,
      "loss": 0.4986,
      "step": 218
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002727643449095507,
      "loss": 0.7309,
      "step": 219
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002724845494585816,
      "loss": 0.6104,
      "step": 220
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002722034692026474,
      "loss": 0.745,
      "step": 221
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00027192110709014697,
      "loss": 0.549,
      "step": 222
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002716374660829252,
      "loss": 0.563,
      "step": 223
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002713525491562421,
      "loss": 0.6249,
      "step": 224
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00027106635929874135,
      "loss": 0.6111,
      "step": 225
    },
    {
      "epoch": 0.63,
      "eval_loss": 0.5195571184158325,
      "eval_runtime": 26.3108,
      "eval_samples_per_second": 7.601,
      "eval_steps_per_second": 1.9,
      "step": 225
    },
    {
      "dharma_eval_accuracy": 0.4018291546462952,
      "dharma_eval_accuracy_ARC-Challenge": 0.5740740740740741,
      "dharma_eval_accuracy_ARC-Easy": 0.6296296296296297,
      "dharma_eval_accuracy_BoolQ": 0.7407407407407407,
      "dharma_eval_accuracy_MMLU": 0.37037037037037035,
      "dharma_eval_accuracy_agieval": 0.23728813559322035,
      "dharma_eval_accuracy_bigbench": 0.36065573770491804,
      "dharma_eval_accuracy_openbookqa": 0.09259259259259259,
      "dharma_eval_accuracy_truthful_qa": 0.2777777777777778,
      "dharma_eval_accuracy_winogrande": 0.3333333333333333,
      "dharma_loss": 2.2894758434295652,
      "epoch": 0.63,
      "step": 225
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002707788995124192,
      "loss": 0.6386,
      "step": 226
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00027049017281259276,
      "loss": 0.5923,
      "step": 227
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002702001822278685,
      "loss": 0.411,
      "step": 228
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00026990893080011035,
      "loss": 0.5807,
      "step": 229
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002696164215844081,
      "loss": 0.5582,
      "step": 230
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00026932265764904493,
      "loss": 0.5324,
      "step": 231
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002690276420754655,
      "loss": 0.4203,
      "step": 232
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0002687313779582436,
      "loss": 0.5673,
      "step": 233
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002684338684050497,
      "loss": 0.6918,
      "step": 234
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00026813511653661816,
      "loss": 0.5747,
      "step": 235
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002678351254867147,
      "loss": 0.589,
      "step": 236
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002675338984021035,
      "loss": 0.2718,
      "step": 237
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00026723143844251416,
      "loss": 0.6372,
      "step": 238
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002669277487806085,
      "loss": 0.4913,
      "step": 239
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002666228326019474,
      "loss": 0.5037,
      "step": 240
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002663166931049572,
      "loss": 0.5732,
      "step": 241
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00026600933350089654,
      "loss": 0.5557,
      "step": 242
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00026570075701382213,
      "loss": 0.7603,
      "step": 243
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002653909668805553,
      "loss": 0.6386,
      "step": 244
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00026507996635064787,
      "loss": 0.5421,
      "step": 245
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002647677586863484,
      "loss": 0.6066,
      "step": 246
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0002644543471625675,
      "loss": 0.6434,
      "step": 247
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00026413973506684364,
      "loss": 0.5883,
      "step": 248
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.000263823925699309,
      "loss": 0.5793,
      "step": 249
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00026350692237265427,
      "loss": 0.5622,
      "step": 250
    },
    {
      "epoch": 0.7,
      "eval_loss": 0.5192391276359558,
      "eval_runtime": 26.26,
      "eval_samples_per_second": 7.616,
      "eval_steps_per_second": 1.904,
      "step": 250
    },
    {
      "dharma_eval_accuracy": 0.37803139189326707,
      "dharma_eval_accuracy_ARC-Challenge": 0.5,
      "dharma_eval_accuracy_ARC-Easy": 0.5185185185185185,
      "dharma_eval_accuracy_BoolQ": 0.7592592592592593,
      "dharma_eval_accuracy_MMLU": 0.42592592592592593,
      "dharma_eval_accuracy_agieval": 0.288135593220339,
      "dharma_eval_accuracy_bigbench": 0.26229508196721313,
      "dharma_eval_accuracy_openbookqa": 0.09259259259259259,
      "dharma_eval_accuracy_truthful_qa": 0.3333333333333333,
      "dharma_eval_accuracy_winogrande": 0.2222222222222222,
      "dharma_loss": 2.7471679282188415,
      "epoch": 0.7,
      "step": 250
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00026318872841209445,
      "loss": 0.361,
      "step": 251
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002628693471553335,
      "loss": 0.5178,
      "step": 252
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00026254878195252983,
      "loss": 0.4308,
      "step": 253
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00026222703616626055,
      "loss": 0.4397,
      "step": 254
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00026190411317148686,
      "loss": 0.5298,
      "step": 255
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00026158001635551815,
      "loss": 0.6231,
      "step": 256
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00026125474911797657,
      "loss": 0.6699,
      "step": 257
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002609283148707616,
      "loss": 0.5838,
      "step": 258
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.000260600717038014,
      "loss": 0.8865,
      "step": 259
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00026027195905608006,
      "loss": 0.4901,
      "step": 260
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00025994204437347537,
      "loss": 0.5792,
      "step": 261
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00025961097645084885,
      "loss": 0.6365,
      "step": 262
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002592787587609465,
      "loss": 0.4429,
      "step": 263
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00025894539478857445,
      "loss": 0.6505,
      "step": 264
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00025861088803056325,
      "loss": 0.4626,
      "step": 265
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002582752419957303,
      "loss": 0.4521,
      "step": 266
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002579384602048438,
      "loss": 0.5703,
      "step": 267
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00025760054619058535,
      "loss": 0.6705,
      "step": 268
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00025726150349751305,
      "loss": 0.5355,
      "step": 269
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002569213356820244,
      "loss": 0.6653,
      "step": 270
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002565800463123187,
      "loss": 0.6273,
      "step": 271
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002562376389683599,
      "loss": 0.5154,
      "step": 272
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00025589411724183923,
      "loss": 0.5249,
      "step": 273
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002555494847361369,
      "loss": 0.5534,
      "step": 274
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002552037450662849,
      "loss": 0.5484,
      "step": 275
    },
    {
      "epoch": 0.77,
      "eval_loss": 0.5245066285133362,
      "eval_runtime": 26.2644,
      "eval_samples_per_second": 7.615,
      "eval_steps_per_second": 1.904,
      "step": 275
    },
    {
      "dharma_eval_accuracy": 0.41176847249521764,
      "dharma_eval_accuracy_ARC-Challenge": 0.5740740740740741,
      "dharma_eval_accuracy_ARC-Easy": 0.5370370370370371,
      "dharma_eval_accuracy_BoolQ": 0.7037037037037037,
      "dharma_eval_accuracy_MMLU": 0.42592592592592593,
      "dharma_eval_accuracy_agieval": 0.2711864406779661,
      "dharma_eval_accuracy_bigbench": 0.36065573770491804,
      "dharma_eval_accuracy_openbookqa": 0.09259259259259259,
      "dharma_eval_accuracy_truthful_qa": 0.35185185185185186,
      "dharma_eval_accuracy_winogrande": 0.3888888888888889,
      "dharma_loss": 2.512154397010803,
      "epoch": 0.77,
      "step": 275
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0002548569018589286,
      "loss": 0.5051,
      "step": 276
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002545089587522893,
      "loss": 0.6745,
      "step": 277
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002541599193961254,
      "loss": 0.5438,
      "step": 278
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002538097874516947,
      "loss": 0.5899,
      "step": 279
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00025345856659171563,
      "loss": 0.4745,
      "step": 280
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002531062605003287,
      "loss": 0.4939,
      "step": 281
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00025275287287305814,
      "loss": 0.487,
      "step": 282
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00025239840741677304,
      "loss": 0.4682,
      "step": 283
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00025204286784964817,
      "loss": 0.8083,
      "step": 284
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00025168625790112547,
      "loss": 0.4625,
      "step": 285
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00025132858131187444,
      "loss": 0.5517,
      "step": 286
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00025096984183375334,
      "loss": 0.5384,
      "step": 287
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0002506100432297695,
      "loss": 0.5904,
      "step": 288
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00025024918927404004,
      "loss": 0.5956,
      "step": 289
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00024988728375175214,
      "loss": 0.5965,
      "step": 290
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00024952433045912354,
      "loss": 0.4771,
      "step": 291
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00024916033320336264,
      "loss": 0.6467,
      "step": 292
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00024879529580262817,
      "loss": 0.544,
      "step": 293
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00024842922208598994,
      "loss": 0.6526,
      "step": 294
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002480621158933879,
      "loss": 0.5648,
      "step": 295
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00024769398107559224,
      "loss": 0.5017,
      "step": 296
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002473248214941632,
      "loss": 0.5809,
      "step": 297
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00024695464102141,
      "loss": 0.4759,
      "step": 298
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002465834435403506,
      "loss": 0.4493,
      "step": 299
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00024621123294467096,
      "loss": 0.5887,
      "step": 300
    },
    {
      "epoch": 0.84,
      "eval_loss": 0.5127784609794617,
      "eval_runtime": 26.3008,
      "eval_samples_per_second": 7.604,
      "eval_steps_per_second": 1.901,
      "step": 300
    },
    {
      "dharma_eval_accuracy": 0.4206398210751272,
      "dharma_eval_accuracy_ARC-Challenge": 0.48148148148148145,
      "dharma_eval_accuracy_ARC-Easy": 0.5185185185185185,
      "dharma_eval_accuracy_BoolQ": 0.7037037037037037,
      "dharma_eval_accuracy_MMLU": 0.37037037037037035,
      "dharma_eval_accuracy_agieval": 0.2711864406779661,
      "dharma_eval_accuracy_bigbench": 0.45901639344262296,
      "dharma_eval_accuracy_openbookqa": 0.09259259259259259,
      "dharma_eval_accuracy_truthful_qa": 0.4074074074074074,
      "dharma_eval_accuracy_winogrande": 0.48148148148148145,
      "dharma_loss": 2.5652906007766725,
      "epoch": 0.84,
      "step": 300
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00024583801313868416,
      "loss": 0.419,
      "step": 301
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002454637880372892,
      "loss": 0.4721,
      "step": 302
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0002450885615659305,
      "loss": 0.4429,
      "step": 303
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00024471233766055605,
      "loss": 0.6384,
      "step": 304
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00024433512026757664,
      "loss": 0.6378,
      "step": 305
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00024395691334382427,
      "loss": 0.5599,
      "step": 306
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00024357772085651055,
      "loss": 0.4861,
      "step": 307
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00024319754678318528,
      "loss": 0.4794,
      "step": 308
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00024281639511169456,
      "loss": 0.394,
      "step": 309
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002424342698401391,
      "loss": 0.703,
      "step": 310
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00024205117497683209,
      "loss": 0.5961,
      "step": 311
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002416671145402575,
      "loss": 0.5959,
      "step": 312
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002412820925590275,
      "loss": 0.7628,
      "step": 313
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00024089611307184048,
      "loss": 0.4302,
      "step": 314
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002405091801274387,
      "loss": 0.4601,
      "step": 315
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00024012129778456552,
      "loss": 0.5376,
      "step": 316
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00023973247011192325,
      "loss": 0.6526,
      "step": 317
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002393427011881302,
      "loss": 0.7244,
      "step": 318
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0002389519951016779,
      "loss": 0.7522,
      "step": 319
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00023856035595088839,
      "loss": 0.901,
      "step": 320
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00023816778784387094,
      "loss": 0.6776,
      "step": 321
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00023777429489847934,
      "loss": 0.6197,
      "step": 322
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002373798812422683,
      "loss": 0.3997,
      "step": 323
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002369845510124505,
      "loss": 0.3073,
      "step": 324
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002365883083558529,
      "loss": 0.5186,
      "step": 325
    },
    {
      "epoch": 0.91,
      "eval_loss": 0.5124163627624512,
      "eval_runtime": 26.2196,
      "eval_samples_per_second": 7.628,
      "eval_steps_per_second": 1.907,
      "step": 325
    },
    {
      "dharma_eval_accuracy": 0.3996080301226793,
      "dharma_eval_accuracy_ARC-Challenge": 0.5,
      "dharma_eval_accuracy_ARC-Easy": 0.48148148148148145,
      "dharma_eval_accuracy_BoolQ": 0.7037037037037037,
      "dharma_eval_accuracy_MMLU": 0.42592592592592593,
      "dharma_eval_accuracy_agieval": 0.3220338983050847,
      "dharma_eval_accuracy_bigbench": 0.3114754098360656,
      "dharma_eval_accuracy_openbookqa": 0.09259259259259259,
      "dharma_eval_accuracy_truthful_qa": 0.42592592592592593,
      "dharma_eval_accuracy_winogrande": 0.3333333333333333,
      "dharma_loss": 2.396534740447998,
      "epoch": 0.91,
      "step": 325
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00023619115742887356,
      "loss": 0.3524,
      "step": 326
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00023579310239743773,
      "loss": 0.5638,
      "step": 327
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00023539414743695437,
      "loss": 0.4728,
      "step": 328
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00023499429673227222,
      "loss": 0.6048,
      "step": 329
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00023459355447763596,
      "loss": 0.5342,
      "step": 330
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00023419192487664217,
      "loss": 0.5119,
      "step": 331
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002337894121421954,
      "loss": 0.4893,
      "step": 332
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002333860204964637,
      "loss": 0.5625,
      "step": 333
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00023298175417083459,
      "loss": 0.6029,
      "step": 334
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002325766174058705,
      "loss": 0.5609,
      "step": 335
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0002321706144512644,
      "loss": 0.4422,
      "step": 336
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002317637495657952,
      "loss": 0.4773,
      "step": 337
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.000231356027017283,
      "loss": 0.5279,
      "step": 338
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00023094745108254435,
      "loss": 0.5441,
      "step": 339
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00023053802604734757,
      "loss": 0.6003,
      "step": 340
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00023012775620636746,
      "loss": 0.5532,
      "step": 341
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00022971664586314054,
      "loss": 0.6534,
      "step": 342
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00022930469933001975,
      "loss": 0.5123,
      "step": 343
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00022889192092812938,
      "loss": 0.4821,
      "step": 344
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002284783149873195,
      "loss": 0.6106,
      "step": 345
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00022806388584612066,
      "loss": 0.6158,
      "step": 346
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00022764863785169854,
      "loss": 0.595,
      "step": 347
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.000227232575359808,
      "loss": 0.5091,
      "step": 348
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002268157027347478,
      "loss": 0.3905,
      "step": 349
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00022639802434931444,
      "loss": 0.6038,
      "step": 350
    },
    {
      "epoch": 0.98,
      "eval_loss": 0.5118417143821716,
      "eval_runtime": 26.228,
      "eval_samples_per_second": 7.625,
      "eval_steps_per_second": 1.906,
      "step": 350
    },
    {
      "dharma_eval_accuracy": 0.40288626127285015,
      "dharma_eval_accuracy_ARC-Challenge": 0.4074074074074074,
      "dharma_eval_accuracy_ARC-Easy": 0.5555555555555556,
      "dharma_eval_accuracy_BoolQ": 0.7407407407407407,
      "dharma_eval_accuracy_MMLU": 0.3148148148148148,
      "dharma_eval_accuracy_agieval": 0.2033898305084746,
      "dharma_eval_accuracy_bigbench": 0.3114754098360656,
      "dharma_eval_accuracy_openbookqa": 0.18518518518518517,
      "dharma_eval_accuracy_truthful_qa": 0.4444444444444444,
      "dharma_eval_accuracy_winogrande": 0.46296296296296297,
      "dharma_loss": 2.5560754494667055,
      "epoch": 0.98,
      "step": 350
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002259795445847566,
      "loss": 0.5352,
      "step": 351
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00022556026783072895,
      "loss": 0.374,
      "step": 352
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00022514019848524628,
      "loss": 0.5222,
      "step": 353
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00022471934095463723,
      "loss": 0.4099,
      "step": 354
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00022429769965349815,
      "loss": 0.4797,
      "step": 355
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00022387527900464673,
      "loss": 0.454,
      "step": 356
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00022345208343907576,
      "loss": 0.6351,
      "step": 357
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00022302811739590642,
      "loss": 0.4919,
      "step": 358
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00022260338532234194,
      "loss": 0.4066,
      "step": 359
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00022217789167362073,
      "loss": 0.5947,
      "step": 360
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00022175164091296987,
      "loss": 0.6658,
      "step": 361
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00022132463751155812,
      "loss": 0.6098,
      "step": 362
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00022089688594844915,
      "loss": 0.5961,
      "step": 363
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00022046839071055435,
      "loss": 0.3676,
      "step": 364
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00022003915629258605,
      "loss": 0.485,
      "step": 365
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00021960918719701026,
      "loss": 0.506,
      "step": 366
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00021917848793399924,
      "loss": 0.4384,
      "step": 367
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00021874706302138448,
      "loss": 0.5722,
      "step": 368
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00021831491698460923,
      "loss": 0.4142,
      "step": 369
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00021788205435668083,
      "loss": 0.4151,
      "step": 370
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002174484796781235,
      "loss": 0.4785,
      "step": 371
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00021701419749693034,
      "loss": 0.406,
      "step": 372
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00021657921236851603,
      "loss": 0.3883,
      "step": 373
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00021614352885566872,
      "loss": 0.508,
      "step": 374
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00021570715152850232,
      "loss": 0.481,
      "step": 375
    },
    {
      "epoch": 1.05,
      "eval_loss": 0.5141562223434448,
      "eval_runtime": 26.3236,
      "eval_samples_per_second": 7.598,
      "eval_steps_per_second": 1.899,
      "step": 375
    },
    {
      "dharma_eval_accuracy": 0.41410737093179745,
      "dharma_eval_accuracy_ARC-Challenge": 0.24074074074074073,
      "dharma_eval_accuracy_ARC-Easy": 0.35185185185185186,
      "dharma_eval_accuracy_BoolQ": 0.7037037037037037,
      "dharma_eval_accuracy_MMLU": 0.2222222222222222,
      "dharma_eval_accuracy_agieval": 0.23728813559322035,
      "dharma_eval_accuracy_bigbench": 0.5081967213114754,
      "dharma_eval_accuracy_openbookqa": 0.25925925925925924,
      "dharma_eval_accuracy_truthful_qa": 0.7037037037037037,
      "dharma_eval_accuracy_winogrande": 0.5,
      "dharma_loss": 2.894161937713623,
      "epoch": 1.05,
      "step": 375
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00021527008496440846,
      "loss": 0.6044,
      "step": 376
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00021483233374800862,
      "loss": 0.5436,
      "step": 377
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00021439390247110588,
      "loss": 0.336,
      "step": 378
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00021395479573263688,
      "loss": 0.6639,
      "step": 379
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00021351501813862356,
      "loss": 0.4795,
      "step": 380
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00021307457430212468,
      "loss": 0.4301,
      "step": 381
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00021263346884318777,
      "loss": 0.6004,
      "step": 382
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00021219170638880037,
      "loss": 0.3414,
      "step": 383
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00021174929157284156,
      "loss": 0.3466,
      "step": 384
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00021130622903603344,
      "loss": 0.4323,
      "step": 385
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002108625234258923,
      "loss": 0.4462,
      "step": 386
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00021041817939668005,
      "loss": 0.5546,
      "step": 387
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00020997320160935534,
      "loss": 0.3643,
      "step": 388
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00020952759473152457,
      "loss": 0.3303,
      "step": 389
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00020908136343739307,
      "loss": 0.4555,
      "step": 390
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00020863451240771592,
      "loss": 0.4731,
      "step": 391
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00020818704632974896,
      "loss": 0.4177,
      "step": 392
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00020773896989719965,
      "loss": 0.4841,
      "step": 393
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00020729028781017777,
      "loss": 0.4863,
      "step": 394
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.000206841004775146,
      "loss": 0.3087,
      "step": 395
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00020639112550487084,
      "loss": 0.5821,
      "step": 396
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.000205940654718373,
      "loss": 0.521,
      "step": 397
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002054895971408778,
      "loss": 0.4498,
      "step": 398
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002050379575037658,
      "loss": 0.4921,
      "step": 399
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00020458574054452313,
      "loss": 0.4947,
      "step": 400
    },
    {
      "epoch": 1.12,
      "eval_loss": 0.5163459777832031,
      "eval_runtime": 26.3481,
      "eval_samples_per_second": 7.591,
      "eval_steps_per_second": 1.898,
      "step": 400
    },
    {
      "dharma_eval_accuracy": 0.38530078656965755,
      "dharma_eval_accuracy_ARC-Challenge": 0.2777777777777778,
      "dharma_eval_accuracy_ARC-Easy": 0.3888888888888889,
      "dharma_eval_accuracy_BoolQ": 0.7037037037037037,
      "dharma_eval_accuracy_MMLU": 0.2222222222222222,
      "dharma_eval_accuracy_agieval": 0.23728813559322035,
      "dharma_eval_accuracy_bigbench": 0.5081967213114754,
      "dharma_eval_accuracy_openbookqa": 0.09259259259259259,
      "dharma_eval_accuracy_truthful_qa": 0.5370370370370371,
      "dharma_eval_accuracy_winogrande": 0.5,
      "dharma_loss": 2.720780613183975,
      "epoch": 1.12,
      "step": 400
    }
  ],
  "max_steps": 1000,
  "num_train_epochs": 3,
  "total_flos": 1.2906498742913434e+17,
  "trial_name": null,
  "trial_params": null
}