{
  "best_metric": 0.9751780033111572,
  "best_model_checkpoint": "data/Gemma-2-2B_task-1_180-samples_config-1_auto/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": 1.7832472324371338,
      "learning_rate": 1.1764705882352942e-06,
      "loss": 1.542,
      "step": 1
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 1.7133058309555054,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 1.6612,
      "step": 2
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 1.720790147781372,
      "learning_rate": 4.705882352941177e-06,
      "loss": 1.566,
      "step": 4
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 1.5975037813186646,
      "learning_rate": 7.058823529411765e-06,
      "loss": 1.5771,
      "step": 6
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 1.8883123397827148,
      "learning_rate": 9.411764705882354e-06,
      "loss": 1.6311,
      "step": 8
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 1.7006659507751465,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.6513,
      "step": 10
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 2.0140461921691895,
      "learning_rate": 1.411764705882353e-05,
      "loss": 1.6034,
      "step": 12
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 2.025434732437134,
      "learning_rate": 1.647058823529412e-05,
      "loss": 1.6354,
      "step": 14
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 1.6752067804336548,
      "learning_rate": 1.8823529411764708e-05,
      "loss": 1.4834,
      "step": 16
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.4382081031799316,
      "eval_runtime": 3.2109,
      "eval_samples_per_second": 11.212,
      "eval_steps_per_second": 11.212,
      "step": 17
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 1.7361249923706055,
      "learning_rate": 2.1176470588235296e-05,
      "loss": 1.479,
      "step": 18
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 1.6204969882965088,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 1.3521,
      "step": 20
    },
    {
      "epoch": 1.2941176470588236,
      "grad_norm": 1.226993441581726,
      "learning_rate": 2.5882352941176475e-05,
      "loss": 1.2545,
      "step": 22
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 1.1633985042572021,
      "learning_rate": 2.823529411764706e-05,
      "loss": 1.2009,
      "step": 24
    },
    {
      "epoch": 1.5294117647058822,
      "grad_norm": 1.0998601913452148,
      "learning_rate": 3.058823529411765e-05,
      "loss": 1.1663,
      "step": 26
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 1.0703226327896118,
      "learning_rate": 3.294117647058824e-05,
      "loss": 1.0917,
      "step": 28
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 1.0329105854034424,
      "learning_rate": 3.529411764705883e-05,
      "loss": 1.0517,
      "step": 30
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 1.0319746732711792,
      "learning_rate": 3.7647058823529415e-05,
      "loss": 1.0224,
      "step": 32
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.9546714425086975,
      "learning_rate": 4e-05,
      "loss": 1.0602,
      "step": 34
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.0723085403442383,
      "eval_runtime": 3.2431,
      "eval_samples_per_second": 11.1,
      "eval_steps_per_second": 11.1,
      "step": 34
    },
    {
      "epoch": 2.1176470588235294,
      "grad_norm": 0.8920161724090576,
      "learning_rate": 4.235294117647059e-05,
      "loss": 0.9503,
      "step": 36
    },
    {
      "epoch": 2.235294117647059,
      "grad_norm": 0.8407706618309021,
      "learning_rate": 4.470588235294118e-05,
      "loss": 0.9154,
      "step": 38
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 0.8984105587005615,
      "learning_rate": 4.705882352941177e-05,
      "loss": 0.9394,
      "step": 40
    },
    {
      "epoch": 2.4705882352941178,
      "grad_norm": 0.9292290806770325,
      "learning_rate": 4.9411764705882355e-05,
      "loss": 0.9712,
      "step": 42
    },
    {
      "epoch": 2.588235294117647,
      "grad_norm": 0.9536141157150269,
      "learning_rate": 5.176470588235295e-05,
      "loss": 0.957,
      "step": 44
    },
    {
      "epoch": 2.7058823529411766,
      "grad_norm": 1.0470105409622192,
      "learning_rate": 5.411764705882353e-05,
      "loss": 0.9944,
      "step": 46
    },
    {
      "epoch": 2.8235294117647056,
      "grad_norm": 1.0039658546447754,
      "learning_rate": 5.647058823529412e-05,
      "loss": 0.9991,
      "step": 48
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 1.1521855592727661,
      "learning_rate": 5.882352941176471e-05,
      "loss": 0.9602,
      "step": 50
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.995959997177124,
      "eval_runtime": 3.2345,
      "eval_samples_per_second": 11.13,
      "eval_steps_per_second": 11.13,
      "step": 51
    },
    {
      "epoch": 3.0588235294117645,
      "grad_norm": 1.096779465675354,
      "learning_rate": 6.11764705882353e-05,
      "loss": 0.8858,
      "step": 52
    },
    {
      "epoch": 3.176470588235294,
      "grad_norm": 1.0280829668045044,
      "learning_rate": 6.352941176470588e-05,
      "loss": 0.8229,
      "step": 54
    },
    {
      "epoch": 3.2941176470588234,
      "grad_norm": 0.9136367440223694,
      "learning_rate": 6.588235294117648e-05,
      "loss": 0.8592,
      "step": 56
    },
    {
      "epoch": 3.411764705882353,
      "grad_norm": 0.9670653343200684,
      "learning_rate": 6.823529411764707e-05,
      "loss": 0.9084,
      "step": 58
    },
    {
      "epoch": 3.5294117647058822,
      "grad_norm": 0.9892047047615051,
      "learning_rate": 7.058823529411765e-05,
      "loss": 0.7741,
      "step": 60
    },
    {
      "epoch": 3.6470588235294117,
      "grad_norm": 1.0851653814315796,
      "learning_rate": 7.294117647058823e-05,
      "loss": 0.8384,
      "step": 62
    },
    {
      "epoch": 3.764705882352941,
      "grad_norm": 1.0466123819351196,
      "learning_rate": 7.529411764705883e-05,
      "loss": 0.7837,
      "step": 64
    },
    {
      "epoch": 3.8823529411764706,
      "grad_norm": 1.0727269649505615,
      "learning_rate": 7.764705882352942e-05,
      "loss": 0.7936,
      "step": 66
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.18294095993042,
      "learning_rate": 8e-05,
      "loss": 0.8255,
      "step": 68
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.9751780033111572,
      "eval_runtime": 3.1744,
      "eval_samples_per_second": 11.341,
      "eval_steps_per_second": 11.341,
      "step": 68
    },
    {
      "epoch": 4.117647058823529,
      "grad_norm": 1.1114113330841064,
      "learning_rate": 8.23529411764706e-05,
      "loss": 0.7502,
      "step": 70
    },
    {
      "epoch": 4.235294117647059,
      "grad_norm": 1.2956862449645996,
      "learning_rate": 8.470588235294118e-05,
      "loss": 0.6739,
      "step": 72
    },
    {
      "epoch": 4.352941176470588,
      "grad_norm": 1.0851770639419556,
      "learning_rate": 8.705882352941177e-05,
      "loss": 0.611,
      "step": 74
    },
    {
      "epoch": 4.470588235294118,
      "grad_norm": 1.397943377494812,
      "learning_rate": 8.941176470588236e-05,
      "loss": 0.6655,
      "step": 76
    },
    {
      "epoch": 4.588235294117647,
      "grad_norm": 1.464152216911316,
      "learning_rate": 9.176470588235295e-05,
      "loss": 0.7261,
      "step": 78
    },
    {
      "epoch": 4.705882352941177,
      "grad_norm": 1.427319049835205,
      "learning_rate": 9.411764705882353e-05,
      "loss": 0.6477,
      "step": 80
    },
    {
      "epoch": 4.823529411764706,
      "grad_norm": 1.4226312637329102,
      "learning_rate": 9.647058823529412e-05,
      "loss": 0.67,
      "step": 82
    },
    {
      "epoch": 4.9411764705882355,
      "grad_norm": 1.5121948719024658,
      "learning_rate": 9.882352941176471e-05,
      "loss": 0.6121,
      "step": 84
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.0406495332717896,
      "eval_runtime": 3.1678,
      "eval_samples_per_second": 11.364,
      "eval_steps_per_second": 11.364,
      "step": 85
    },
    {
      "epoch": 5.0588235294117645,
      "grad_norm": 1.461538314819336,
      "learning_rate": 9.99995783847866e-05,
      "loss": 0.5344,
      "step": 86
    },
    {
      "epoch": 5.176470588235294,
      "grad_norm": 1.3025084733963013,
      "learning_rate": 9.999620550574153e-05,
      "loss": 0.4857,
      "step": 88
    },
    {
      "epoch": 5.294117647058823,
      "grad_norm": 1.451460599899292,
      "learning_rate": 9.998945997517956e-05,
      "loss": 0.4771,
      "step": 90
    },
    {
      "epoch": 5.411764705882353,
      "grad_norm": 1.5744037628173828,
      "learning_rate": 9.997934224814173e-05,
      "loss": 0.4099,
      "step": 92
    },
    {
      "epoch": 5.529411764705882,
      "grad_norm": 1.8647046089172363,
      "learning_rate": 9.996585300715116e-05,
      "loss": 0.442,
      "step": 94
    },
    {
      "epoch": 5.647058823529412,
      "grad_norm": 2.1965537071228027,
      "learning_rate": 9.994899316216708e-05,
      "loss": 0.432,
      "step": 96
    },
    {
      "epoch": 5.764705882352941,
      "grad_norm": 2.083725690841675,
      "learning_rate": 9.992876385052345e-05,
      "loss": 0.4656,
      "step": 98
    },
    {
      "epoch": 5.882352941176471,
      "grad_norm": 2.478208541870117,
      "learning_rate": 9.990516643685222e-05,
      "loss": 0.4962,
      "step": 100
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.0873022079467773,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.5169,
      "step": 102
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.2141706943511963,
      "eval_runtime": 3.1516,
      "eval_samples_per_second": 11.423,
      "eval_steps_per_second": 11.423,
      "step": 102
    },
    {
      "epoch": 6.117647058823529,
      "grad_norm": 1.8249984979629517,
      "learning_rate": 9.984787389787688e-05,
      "loss": 0.2707,
      "step": 104
    },
    {
      "epoch": 6.235294117647059,
      "grad_norm": 1.4698922634124756,
      "learning_rate": 9.981418263742148e-05,
      "loss": 0.2932,
      "step": 106
    },
    {
      "epoch": 6.352941176470588,
      "grad_norm": 1.8357480764389038,
      "learning_rate": 9.977713100437509e-05,
      "loss": 0.3094,
      "step": 108
    },
    {
      "epoch": 6.470588235294118,
      "grad_norm": 2.1825873851776123,
      "learning_rate": 9.973672149817232e-05,
      "loss": 0.2849,
      "step": 110
    },
    {
      "epoch": 6.588235294117647,
      "grad_norm": 2.3892838954925537,
      "learning_rate": 9.96929568447637e-05,
      "loss": 0.2223,
      "step": 112
    },
    {
      "epoch": 6.705882352941177,
      "grad_norm": 2.1798770427703857,
      "learning_rate": 9.964583999643174e-05,
      "loss": 0.2582,
      "step": 114
    },
    {
      "epoch": 6.823529411764706,
      "grad_norm": 2.871042013168335,
      "learning_rate": 9.95953741315919e-05,
      "loss": 0.272,
      "step": 116
    },
    {
      "epoch": 6.9411764705882355,
      "grad_norm": 2.3403995037078857,
      "learning_rate": 9.954156265457801e-05,
      "loss": 0.2771,
      "step": 118
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.5290157794952393,
      "eval_runtime": 3.1574,
      "eval_samples_per_second": 11.402,
      "eval_steps_per_second": 11.402,
      "step": 119
    },
    {
      "epoch": 7.0588235294117645,
      "grad_norm": 1.461056113243103,
      "learning_rate": 9.948440919541278e-05,
      "loss": 0.241,
      "step": 120
    },
    {
      "epoch": 7.176470588235294,
      "grad_norm": 1.7191462516784668,
      "learning_rate": 9.942391760956277e-05,
      "loss": 0.1724,
      "step": 122
    },
    {
      "epoch": 7.294117647058823,
      "grad_norm": 1.7459657192230225,
      "learning_rate": 9.936009197767845e-05,
      "loss": 0.159,
      "step": 124
    },
    {
      "epoch": 7.411764705882353,
      "grad_norm": 2.06180477142334,
      "learning_rate": 9.929293660531888e-05,
      "loss": 0.15,
      "step": 126
    },
    {
      "epoch": 7.529411764705882,
      "grad_norm": 2.8976619243621826,
      "learning_rate": 9.922245602266118e-05,
      "loss": 0.1396,
      "step": 128
    },
    {
      "epoch": 7.647058823529412,
      "grad_norm": 2.6371238231658936,
      "learning_rate": 9.91486549841951e-05,
      "loss": 0.1722,
      "step": 130
    },
    {
      "epoch": 7.764705882352941,
      "grad_norm": 2.343116283416748,
      "learning_rate": 9.90715384684021e-05,
      "loss": 0.1383,
      "step": 132
    },
    {
      "epoch": 7.882352941176471,
      "grad_norm": 2.3471128940582275,
      "learning_rate": 9.899111167741966e-05,
      "loss": 0.2035,
      "step": 134
    },
    {
      "epoch": 8.0,
      "grad_norm": 2.6151411533355713,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.173,
      "step": 136
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.7919055223464966,
      "eval_runtime": 3.1797,
      "eval_samples_per_second": 11.322,
      "eval_steps_per_second": 11.322,
      "step": 136
    },
    {
      "epoch": 8.117647058823529,
      "grad_norm": 2.5747761726379395,
      "learning_rate": 9.882034919459555e-05,
      "loss": 0.0841,
      "step": 138
    },
    {
      "epoch": 8.235294117647058,
      "grad_norm": 2.4608640670776367,
      "learning_rate": 9.873002502207503e-05,
      "loss": 0.1029,
      "step": 140
    },
    {
      "epoch": 8.352941176470589,
      "grad_norm": 1.891782283782959,
      "learning_rate": 9.863641361223024e-05,
      "loss": 0.1029,
      "step": 142
    },
    {
      "epoch": 8.470588235294118,
      "grad_norm": 1.9493474960327148,
      "learning_rate": 9.853952127991372e-05,
      "loss": 0.1338,
      "step": 144
    },
    {
      "epoch": 8.588235294117647,
      "grad_norm": 1.933776617050171,
      "learning_rate": 9.843935456130295e-05,
      "loss": 0.1005,
      "step": 146
    },
    {
      "epoch": 8.705882352941176,
      "grad_norm": 2.018155813217163,
      "learning_rate": 9.833592021345937e-05,
      "loss": 0.0915,
      "step": 148
    },
    {
      "epoch": 8.823529411764707,
      "grad_norm": 1.6334080696105957,
      "learning_rate": 9.822922521387276e-05,
      "loss": 0.094,
      "step": 150
    },
    {
      "epoch": 8.941176470588236,
      "grad_norm": 3.4501752853393555,
      "learning_rate": 9.811927675999036e-05,
      "loss": 0.1303,
      "step": 152
    },
    {
      "epoch": 9.0,
      "eval_loss": 2.1344876289367676,
      "eval_runtime": 3.1535,
      "eval_samples_per_second": 11.416,
      "eval_steps_per_second": 11.416,
      "step": 153
    },
    {
      "epoch": 9.058823529411764,
      "grad_norm": 2.9836673736572266,
      "learning_rate": 9.800608226873142e-05,
      "loss": 0.0983,
      "step": 154
    },
    {
      "epoch": 9.176470588235293,
      "grad_norm": 1.2688862085342407,
      "learning_rate": 9.788964937598689e-05,
      "loss": 0.0734,
      "step": 156
    },
    {
      "epoch": 9.294117647058824,
      "grad_norm": 1.8167171478271484,
      "learning_rate": 9.776998593610428e-05,
      "loss": 0.0684,
      "step": 158
    },
    {
      "epoch": 9.411764705882353,
      "grad_norm": 2.509737253189087,
      "learning_rate": 9.764710002135784e-05,
      "loss": 0.0939,
      "step": 160
    },
    {
      "epoch": 9.529411764705882,
      "grad_norm": 2.171806573867798,
      "learning_rate": 9.752099992140399e-05,
      "loss": 0.0666,
      "step": 162
    },
    {
      "epoch": 9.647058823529411,
      "grad_norm": 2.0738728046417236,
      "learning_rate": 9.739169414272217e-05,
      "loss": 0.0769,
      "step": 164
    },
    {
      "epoch": 9.764705882352942,
      "grad_norm": 1.684583067893982,
      "learning_rate": 9.725919140804099e-05,
      "loss": 0.0936,
      "step": 166
    },
    {
      "epoch": 9.882352941176471,
      "grad_norm": 2.445774793624878,
      "learning_rate": 9.71235006557497e-05,
      "loss": 0.1032,
      "step": 168
    },
    {
      "epoch": 10.0,
      "grad_norm": 1.676518440246582,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0888,
      "step": 170
    },
    {
      "epoch": 10.0,
      "eval_loss": 2.136868715286255,
      "eval_runtime": 3.1661,
      "eval_samples_per_second": 11.371,
      "eval_steps_per_second": 11.371,
      "step": 170
    },
    {
      "epoch": 10.117647058823529,
      "grad_norm": 0.9767754077911377,
      "learning_rate": 9.684259192656553e-05,
      "loss": 0.0489,
      "step": 172
    },
    {
      "epoch": 10.235294117647058,
      "grad_norm": 3.620056629180908,
      "learning_rate": 9.669739289925577e-05,
      "loss": 0.057,
      "step": 174
    },
    {
      "epoch": 10.352941176470589,
      "grad_norm": 2.562175750732422,
      "learning_rate": 9.654904375222385e-05,
      "loss": 0.0649,
      "step": 176
    },
    {
      "epoch": 10.470588235294118,
      "grad_norm": 1.572275161743164,
      "learning_rate": 9.639755449282875e-05,
      "loss": 0.0643,
      "step": 178
    },
    {
      "epoch": 10.588235294117647,
      "grad_norm": 2.3751332759857178,
      "learning_rate": 9.62429353402556e-05,
      "loss": 0.0925,
      "step": 180
    },
    {
      "epoch": 10.705882352941176,
      "grad_norm": 1.5998344421386719,
      "learning_rate": 9.608519672482636e-05,
      "loss": 0.0785,
      "step": 182
    },
    {
      "epoch": 10.823529411764707,
      "grad_norm": 1.2910666465759277,
      "learning_rate": 9.592434928729616e-05,
      "loss": 0.0638,
      "step": 184
    },
    {
      "epoch": 10.941176470588236,
      "grad_norm": 2.2079696655273438,
      "learning_rate": 9.576040387813552e-05,
      "loss": 0.0918,
      "step": 186
    },
    {
      "epoch": 11.0,
      "eval_loss": 2.155510902404785,
      "eval_runtime": 3.1503,
      "eval_samples_per_second": 11.427,
      "eval_steps_per_second": 11.427,
      "step": 187
    },
    {
      "epoch": 11.0,
      "step": 187,
      "total_flos": 6632133967740928.0,
      "train_loss": 0.5791426639067617,
      "train_runtime": 644.3454,
      "train_samples_per_second": 10.553,
      "train_steps_per_second": 1.319
    }
  ],
  "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": 6632133967740928.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}