{
  "best_metric": 0.9088978171348572,
  "best_model_checkpoint": "data/Mistral-7B_task-1_180-samples_config-1_full/checkpoint-68",
  "epoch": 11.0,
  "eval_steps": 500,
  "global_step": 187,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.058823529411764705,
      "grad_norm": 2.646308422088623,
      "learning_rate": 1.1764705882352942e-06,
      "loss": 2.0507,
      "step": 1
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 2.6624257564544678,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 2.0992,
      "step": 2
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 2.4988327026367188,
      "learning_rate": 4.705882352941177e-06,
      "loss": 2.0221,
      "step": 4
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 2.5717930793762207,
      "learning_rate": 7.058823529411765e-06,
      "loss": 2.0672,
      "step": 6
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 2.570204734802246,
      "learning_rate": 9.411764705882354e-06,
      "loss": 2.0224,
      "step": 8
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 2.1521692276000977,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.9503,
      "step": 10
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 2.092810869216919,
      "learning_rate": 1.411764705882353e-05,
      "loss": 1.9548,
      "step": 12
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 1.9483330249786377,
      "learning_rate": 1.647058823529412e-05,
      "loss": 1.8751,
      "step": 14
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 1.575180172920227,
      "learning_rate": 1.8823529411764708e-05,
      "loss": 1.7349,
      "step": 16
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.6283254623413086,
      "eval_runtime": 14.5491,
      "eval_samples_per_second": 2.474,
      "eval_steps_per_second": 2.474,
      "step": 17
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 1.2693557739257812,
      "learning_rate": 2.1176470588235296e-05,
      "loss": 1.6205,
      "step": 18
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 1.2702040672302246,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 1.5752,
      "step": 20
    },
    {
      "epoch": 1.2941176470588236,
      "grad_norm": 1.2988741397857666,
      "learning_rate": 2.5882352941176475e-05,
      "loss": 1.5106,
      "step": 22
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 1.4694032669067383,
      "learning_rate": 2.823529411764706e-05,
      "loss": 1.3668,
      "step": 24
    },
    {
      "epoch": 1.5294117647058822,
      "grad_norm": 1.3600854873657227,
      "learning_rate": 3.058823529411765e-05,
      "loss": 1.3131,
      "step": 26
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 1.3490387201309204,
      "learning_rate": 3.294117647058824e-05,
      "loss": 1.1859,
      "step": 28
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 1.2320514917373657,
      "learning_rate": 3.529411764705883e-05,
      "loss": 1.1607,
      "step": 30
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 0.9983924031257629,
      "learning_rate": 3.7647058823529415e-05,
      "loss": 1.0292,
      "step": 32
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.9114890694618225,
      "learning_rate": 4e-05,
      "loss": 1.0583,
      "step": 34
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.0366748571395874,
      "eval_runtime": 14.5523,
      "eval_samples_per_second": 2.474,
      "eval_steps_per_second": 2.474,
      "step": 34
    },
    {
      "epoch": 2.1176470588235294,
      "grad_norm": 0.8355625867843628,
      "learning_rate": 4.235294117647059e-05,
      "loss": 1.021,
      "step": 36
    },
    {
      "epoch": 2.235294117647059,
      "grad_norm": 0.808163583278656,
      "learning_rate": 4.470588235294118e-05,
      "loss": 1.0106,
      "step": 38
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 0.8241913914680481,
      "learning_rate": 4.705882352941177e-05,
      "loss": 0.9211,
      "step": 40
    },
    {
      "epoch": 2.4705882352941178,
      "grad_norm": 0.8242692947387695,
      "learning_rate": 4.9411764705882355e-05,
      "loss": 0.9908,
      "step": 42
    },
    {
      "epoch": 2.588235294117647,
      "grad_norm": 0.7766556739807129,
      "learning_rate": 5.176470588235295e-05,
      "loss": 0.9245,
      "step": 44
    },
    {
      "epoch": 2.7058823529411766,
      "grad_norm": 0.7745839953422546,
      "learning_rate": 5.411764705882353e-05,
      "loss": 0.9899,
      "step": 46
    },
    {
      "epoch": 2.8235294117647056,
      "grad_norm": 0.7987116575241089,
      "learning_rate": 5.647058823529412e-05,
      "loss": 0.9476,
      "step": 48
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 0.7803441882133484,
      "learning_rate": 5.882352941176471e-05,
      "loss": 0.8915,
      "step": 50
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.9446046352386475,
      "eval_runtime": 14.5479,
      "eval_samples_per_second": 2.475,
      "eval_steps_per_second": 2.475,
      "step": 51
    },
    {
      "epoch": 3.0588235294117645,
      "grad_norm": 0.7798807621002197,
      "learning_rate": 6.11764705882353e-05,
      "loss": 0.8388,
      "step": 52
    },
    {
      "epoch": 3.176470588235294,
      "grad_norm": 0.8820040822029114,
      "learning_rate": 6.352941176470588e-05,
      "loss": 0.8667,
      "step": 54
    },
    {
      "epoch": 3.2941176470588234,
      "grad_norm": 0.8988600969314575,
      "learning_rate": 6.588235294117648e-05,
      "loss": 0.8426,
      "step": 56
    },
    {
      "epoch": 3.411764705882353,
      "grad_norm": 0.9066359996795654,
      "learning_rate": 6.823529411764707e-05,
      "loss": 0.8502,
      "step": 58
    },
    {
      "epoch": 3.5294117647058822,
      "grad_norm": 0.9546484351158142,
      "learning_rate": 7.058823529411765e-05,
      "loss": 0.8084,
      "step": 60
    },
    {
      "epoch": 3.6470588235294117,
      "grad_norm": 0.9752851128578186,
      "learning_rate": 7.294117647058823e-05,
      "loss": 0.8097,
      "step": 62
    },
    {
      "epoch": 3.764705882352941,
      "grad_norm": 0.9530940055847168,
      "learning_rate": 7.529411764705883e-05,
      "loss": 0.7824,
      "step": 64
    },
    {
      "epoch": 3.8823529411764706,
      "grad_norm": 1.0503418445587158,
      "learning_rate": 7.764705882352942e-05,
      "loss": 0.7806,
      "step": 66
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.210681676864624,
      "learning_rate": 8e-05,
      "loss": 0.7315,
      "step": 68
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.9088978171348572,
      "eval_runtime": 14.5468,
      "eval_samples_per_second": 2.475,
      "eval_steps_per_second": 2.475,
      "step": 68
    },
    {
      "epoch": 4.117647058823529,
      "grad_norm": 0.9875113368034363,
      "learning_rate": 8.23529411764706e-05,
      "loss": 0.6596,
      "step": 70
    },
    {
      "epoch": 4.235294117647059,
      "grad_norm": 1.0360643863677979,
      "learning_rate": 8.470588235294118e-05,
      "loss": 0.6533,
      "step": 72
    },
    {
      "epoch": 4.352941176470588,
      "grad_norm": 1.34538996219635,
      "learning_rate": 8.705882352941177e-05,
      "loss": 0.6716,
      "step": 74
    },
    {
      "epoch": 4.470588235294118,
      "grad_norm": 1.291218876838684,
      "learning_rate": 8.941176470588236e-05,
      "loss": 0.6043,
      "step": 76
    },
    {
      "epoch": 4.588235294117647,
      "grad_norm": 1.2318148612976074,
      "learning_rate": 9.176470588235295e-05,
      "loss": 0.6416,
      "step": 78
    },
    {
      "epoch": 4.705882352941177,
      "grad_norm": 1.336338758468628,
      "learning_rate": 9.411764705882353e-05,
      "loss": 0.5976,
      "step": 80
    },
    {
      "epoch": 4.823529411764706,
      "grad_norm": 1.2969739437103271,
      "learning_rate": 9.647058823529412e-05,
      "loss": 0.6031,
      "step": 82
    },
    {
      "epoch": 4.9411764705882355,
      "grad_norm": 1.4019267559051514,
      "learning_rate": 9.882352941176471e-05,
      "loss": 0.6043,
      "step": 84
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.9266879558563232,
      "eval_runtime": 14.5488,
      "eval_samples_per_second": 2.474,
      "eval_steps_per_second": 2.474,
      "step": 85
    },
    {
      "epoch": 5.0588235294117645,
      "grad_norm": 1.3347663879394531,
      "learning_rate": 9.99995783847866e-05,
      "loss": 0.5214,
      "step": 86
    },
    {
      "epoch": 5.176470588235294,
      "grad_norm": 1.309258222579956,
      "learning_rate": 9.999620550574153e-05,
      "loss": 0.445,
      "step": 88
    },
    {
      "epoch": 5.294117647058823,
      "grad_norm": 1.9459764957427979,
      "learning_rate": 9.998945997517956e-05,
      "loss": 0.4399,
      "step": 90
    },
    {
      "epoch": 5.411764705882353,
      "grad_norm": 1.7618651390075684,
      "learning_rate": 9.997934224814173e-05,
      "loss": 0.4547,
      "step": 92
    },
    {
      "epoch": 5.529411764705882,
      "grad_norm": 1.969826579093933,
      "learning_rate": 9.996585300715116e-05,
      "loss": 0.3973,
      "step": 94
    },
    {
      "epoch": 5.647058823529412,
      "grad_norm": 1.4914029836654663,
      "learning_rate": 9.994899316216708e-05,
      "loss": 0.3673,
      "step": 96
    },
    {
      "epoch": 5.764705882352941,
      "grad_norm": 2.238896369934082,
      "learning_rate": 9.992876385052345e-05,
      "loss": 0.4314,
      "step": 98
    },
    {
      "epoch": 5.882352941176471,
      "grad_norm": 1.7188738584518433,
      "learning_rate": 9.990516643685222e-05,
      "loss": 0.4513,
      "step": 100
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.5939366817474365,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.4042,
      "step": 102
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.9957579374313354,
      "eval_runtime": 14.5477,
      "eval_samples_per_second": 2.475,
      "eval_steps_per_second": 2.475,
      "step": 102
    },
    {
      "epoch": 6.117647058823529,
      "grad_norm": 1.2552285194396973,
      "learning_rate": 9.984787389787688e-05,
      "loss": 0.2628,
      "step": 104
    },
    {
      "epoch": 6.235294117647059,
      "grad_norm": 1.7651152610778809,
      "learning_rate": 9.981418263742148e-05,
      "loss": 0.2745,
      "step": 106
    },
    {
      "epoch": 6.352941176470588,
      "grad_norm": 2.4100160598754883,
      "learning_rate": 9.977713100437509e-05,
      "loss": 0.2875,
      "step": 108
    },
    {
      "epoch": 6.470588235294118,
      "grad_norm": 2.1231443881988525,
      "learning_rate": 9.973672149817232e-05,
      "loss": 0.2731,
      "step": 110
    },
    {
      "epoch": 6.588235294117647,
      "grad_norm": 1.9286688566207886,
      "learning_rate": 9.96929568447637e-05,
      "loss": 0.2603,
      "step": 112
    },
    {
      "epoch": 6.705882352941177,
      "grad_norm": 2.144921064376831,
      "learning_rate": 9.964583999643174e-05,
      "loss": 0.2832,
      "step": 114
    },
    {
      "epoch": 6.823529411764706,
      "grad_norm": 1.4835938215255737,
      "learning_rate": 9.95953741315919e-05,
      "loss": 0.255,
      "step": 116
    },
    {
      "epoch": 6.9411764705882355,
      "grad_norm": 1.7913663387298584,
      "learning_rate": 9.954156265457801e-05,
      "loss": 0.2826,
      "step": 118
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.1042958498001099,
      "eval_runtime": 14.5532,
      "eval_samples_per_second": 2.474,
      "eval_steps_per_second": 2.474,
      "step": 119
    },
    {
      "epoch": 7.0588235294117645,
      "grad_norm": 1.4122477769851685,
      "learning_rate": 9.948440919541278e-05,
      "loss": 0.2374,
      "step": 120
    },
    {
      "epoch": 7.176470588235294,
      "grad_norm": 1.3399616479873657,
      "learning_rate": 9.942391760956277e-05,
      "loss": 0.1902,
      "step": 122
    },
    {
      "epoch": 7.294117647058823,
      "grad_norm": 1.7651268243789673,
      "learning_rate": 9.936009197767845e-05,
      "loss": 0.1724,
      "step": 124
    },
    {
      "epoch": 7.411764705882353,
      "grad_norm": 2.032838821411133,
      "learning_rate": 9.929293660531888e-05,
      "loss": 0.193,
      "step": 126
    },
    {
      "epoch": 7.529411764705882,
      "grad_norm": 1.9887888431549072,
      "learning_rate": 9.922245602266118e-05,
      "loss": 0.1827,
      "step": 128
    },
    {
      "epoch": 7.647058823529412,
      "grad_norm": 1.6022051572799683,
      "learning_rate": 9.91486549841951e-05,
      "loss": 0.1808,
      "step": 130
    },
    {
      "epoch": 7.764705882352941,
      "grad_norm": 1.624754786491394,
      "learning_rate": 9.90715384684021e-05,
      "loss": 0.1873,
      "step": 132
    },
    {
      "epoch": 7.882352941176471,
      "grad_norm": 1.6832681894302368,
      "learning_rate": 9.899111167741966e-05,
      "loss": 0.191,
      "step": 134
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.583979606628418,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.221,
      "step": 136
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.2135425806045532,
      "eval_runtime": 14.5498,
      "eval_samples_per_second": 2.474,
      "eval_steps_per_second": 2.474,
      "step": 136
    },
    {
      "epoch": 8.117647058823529,
      "grad_norm": 1.0766695737838745,
      "learning_rate": 9.882034919459555e-05,
      "loss": 0.1423,
      "step": 138
    },
    {
      "epoch": 8.235294117647058,
      "grad_norm": 1.3800048828125,
      "learning_rate": 9.873002502207503e-05,
      "loss": 0.1368,
      "step": 140
    },
    {
      "epoch": 8.352941176470589,
      "grad_norm": 2.4472179412841797,
      "learning_rate": 9.863641361223024e-05,
      "loss": 0.1472,
      "step": 142
    },
    {
      "epoch": 8.470588235294118,
      "grad_norm": 1.7869505882263184,
      "learning_rate": 9.853952127991372e-05,
      "loss": 0.1823,
      "step": 144
    },
    {
      "epoch": 8.588235294117647,
      "grad_norm": 1.6115949153900146,
      "learning_rate": 9.843935456130295e-05,
      "loss": 0.1597,
      "step": 146
    },
    {
      "epoch": 8.705882352941176,
      "grad_norm": 1.3529373407363892,
      "learning_rate": 9.833592021345937e-05,
      "loss": 0.1471,
      "step": 148
    },
    {
      "epoch": 8.823529411764707,
      "grad_norm": 1.4170416593551636,
      "learning_rate": 9.822922521387276e-05,
      "loss": 0.1638,
      "step": 150
    },
    {
      "epoch": 8.941176470588236,
      "grad_norm": 1.6301814317703247,
      "learning_rate": 9.811927675999036e-05,
      "loss": 0.1703,
      "step": 152
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.2570780515670776,
      "eval_runtime": 14.5592,
      "eval_samples_per_second": 2.473,
      "eval_steps_per_second": 2.473,
      "step": 153
    },
    {
      "epoch": 9.058823529411764,
      "grad_norm": 0.835446298122406,
      "learning_rate": 9.800608226873142e-05,
      "loss": 0.133,
      "step": 154
    },
    {
      "epoch": 9.176470588235293,
      "grad_norm": 1.547910451889038,
      "learning_rate": 9.788964937598689e-05,
      "loss": 0.1221,
      "step": 156
    },
    {
      "epoch": 9.294117647058824,
      "grad_norm": 1.556704044342041,
      "learning_rate": 9.776998593610428e-05,
      "loss": 0.1183,
      "step": 158
    },
    {
      "epoch": 9.411764705882353,
      "grad_norm": 1.6846866607666016,
      "learning_rate": 9.764710002135784e-05,
      "loss": 0.1298,
      "step": 160
    },
    {
      "epoch": 9.529411764705882,
      "grad_norm": 1.5772649049758911,
      "learning_rate": 9.752099992140399e-05,
      "loss": 0.1264,
      "step": 162
    },
    {
      "epoch": 9.647058823529411,
      "grad_norm": 1.2999879121780396,
      "learning_rate": 9.739169414272217e-05,
      "loss": 0.1277,
      "step": 164
    },
    {
      "epoch": 9.764705882352942,
      "grad_norm": 1.42393958568573,
      "learning_rate": 9.725919140804099e-05,
      "loss": 0.1339,
      "step": 166
    },
    {
      "epoch": 9.882352941176471,
      "grad_norm": 1.3733538389205933,
      "learning_rate": 9.71235006557497e-05,
      "loss": 0.1335,
      "step": 168
    },
    {
      "epoch": 10.0,
      "grad_norm": 1.2319905757904053,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.1375,
      "step": 170
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.3205113410949707,
      "eval_runtime": 14.5473,
      "eval_samples_per_second": 2.475,
      "eval_steps_per_second": 2.475,
      "step": 170
    },
    {
      "epoch": 10.117647058823529,
      "grad_norm": 1.1101229190826416,
      "learning_rate": 9.684259192656553e-05,
      "loss": 0.1068,
      "step": 172
    },
    {
      "epoch": 10.235294117647058,
      "grad_norm": 1.1369638442993164,
      "learning_rate": 9.669739289925577e-05,
      "loss": 0.1103,
      "step": 174
    },
    {
      "epoch": 10.352941176470589,
      "grad_norm": 3.8115272521972656,
      "learning_rate": 9.654904375222385e-05,
      "loss": 0.1116,
      "step": 176
    },
    {
      "epoch": 10.470588235294118,
      "grad_norm": 1.0857049226760864,
      "learning_rate": 9.639755449282875e-05,
      "loss": 0.1019,
      "step": 178
    },
    {
      "epoch": 10.588235294117647,
      "grad_norm": 1.3036538362503052,
      "learning_rate": 9.62429353402556e-05,
      "loss": 0.1106,
      "step": 180
    },
    {
      "epoch": 10.705882352941176,
      "grad_norm": 1.46515691280365,
      "learning_rate": 9.608519672482636e-05,
      "loss": 0.1164,
      "step": 182
    },
    {
      "epoch": 10.823529411764707,
      "grad_norm": 0.9066522717475891,
      "learning_rate": 9.592434928729616e-05,
      "loss": 0.1089,
      "step": 184
    },
    {
      "epoch": 10.941176470588236,
      "grad_norm": 1.4507081508636475,
      "learning_rate": 9.576040387813552e-05,
      "loss": 0.1211,
      "step": 186
    },
    {
      "epoch": 11.0,
      "eval_loss": 1.3942441940307617,
      "eval_runtime": 14.5455,
      "eval_samples_per_second": 2.475,
      "eval_steps_per_second": 2.475,
      "step": 187
    },
    {
      "epoch": 11.0,
      "step": 187,
      "total_flos": 2.3461897294577664e+16,
      "train_loss": 0.6285739533483663,
      "train_runtime": 1776.6248,
      "train_samples_per_second": 3.827,
      "train_steps_per_second": 0.478
    }
  ],
  "logging_steps": 2,
  "max_steps": 850,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 7,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.3461897294577664e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}