{
  "best_metric": 0.5707082748413086,
  "best_model_checkpoint": "data/Llama-31-8B_task-2_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": 0.40775999426841736,
      "learning_rate": 1.1764705882352942e-06,
      "loss": 0.8741,
      "step": 1
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 0.4408828020095825,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 0.9505,
      "step": 2
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 0.4879850149154663,
      "learning_rate": 4.705882352941177e-06,
      "loss": 0.9399,
      "step": 4
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 0.43116503953933716,
      "learning_rate": 7.058823529411765e-06,
      "loss": 0.8682,
      "step": 6
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.45176854729652405,
      "learning_rate": 9.411764705882354e-06,
      "loss": 0.8866,
      "step": 8
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 0.4210631251335144,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 0.9017,
      "step": 10
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 0.40909242630004883,
      "learning_rate": 1.411764705882353e-05,
      "loss": 0.8633,
      "step": 12
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 0.4104289710521698,
      "learning_rate": 1.647058823529412e-05,
      "loss": 0.8603,
      "step": 14
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.43323591351509094,
      "learning_rate": 1.8823529411764708e-05,
      "loss": 0.8506,
      "step": 16
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.8360564112663269,
      "eval_runtime": 38.0303,
      "eval_samples_per_second": 0.947,
      "eval_steps_per_second": 0.947,
      "step": 17
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 0.3573507070541382,
      "learning_rate": 2.1176470588235296e-05,
      "loss": 0.8249,
      "step": 18
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.34004563093185425,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 0.793,
      "step": 20
    },
    {
      "epoch": 1.2941176470588236,
      "grad_norm": 0.34051480889320374,
      "learning_rate": 2.5882352941176475e-05,
      "loss": 0.8108,
      "step": 22
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 0.32090651988983154,
      "learning_rate": 2.823529411764706e-05,
      "loss": 0.7375,
      "step": 24
    },
    {
      "epoch": 1.5294117647058822,
      "grad_norm": 0.3154449462890625,
      "learning_rate": 3.058823529411765e-05,
      "loss": 0.7609,
      "step": 26
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 0.332803875207901,
      "learning_rate": 3.294117647058824e-05,
      "loss": 0.7416,
      "step": 28
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 0.3490072190761566,
      "learning_rate": 3.529411764705883e-05,
      "loss": 0.7214,
      "step": 30
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 0.358589231967926,
      "learning_rate": 3.7647058823529415e-05,
      "loss": 0.6714,
      "step": 32
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.38075190782546997,
      "learning_rate": 4e-05,
      "loss": 0.7016,
      "step": 34
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6777597665786743,
      "eval_runtime": 38.0265,
      "eval_samples_per_second": 0.947,
      "eval_steps_per_second": 0.947,
      "step": 34
    },
    {
      "epoch": 2.1176470588235294,
      "grad_norm": 0.36093202233314514,
      "learning_rate": 4.235294117647059e-05,
      "loss": 0.6507,
      "step": 36
    },
    {
      "epoch": 2.235294117647059,
      "grad_norm": 0.3325224220752716,
      "learning_rate": 4.470588235294118e-05,
      "loss": 0.6094,
      "step": 38
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 0.3660614788532257,
      "learning_rate": 4.705882352941177e-05,
      "loss": 0.6064,
      "step": 40
    },
    {
      "epoch": 2.4705882352941178,
      "grad_norm": 0.34248554706573486,
      "learning_rate": 4.9411764705882355e-05,
      "loss": 0.6239,
      "step": 42
    },
    {
      "epoch": 2.588235294117647,
      "grad_norm": 0.377579927444458,
      "learning_rate": 5.176470588235295e-05,
      "loss": 0.6058,
      "step": 44
    },
    {
      "epoch": 2.7058823529411766,
      "grad_norm": 0.3909653425216675,
      "learning_rate": 5.411764705882353e-05,
      "loss": 0.6295,
      "step": 46
    },
    {
      "epoch": 2.8235294117647056,
      "grad_norm": 0.390480101108551,
      "learning_rate": 5.647058823529412e-05,
      "loss": 0.6168,
      "step": 48
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 0.3901604413986206,
      "learning_rate": 5.882352941176471e-05,
      "loss": 0.6047,
      "step": 50
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5986617207527161,
      "eval_runtime": 38.0274,
      "eval_samples_per_second": 0.947,
      "eval_steps_per_second": 0.947,
      "step": 51
    },
    {
      "epoch": 3.0588235294117645,
      "grad_norm": 0.3704307973384857,
      "learning_rate": 6.11764705882353e-05,
      "loss": 0.5345,
      "step": 52
    },
    {
      "epoch": 3.176470588235294,
      "grad_norm": 0.3697601854801178,
      "learning_rate": 6.352941176470588e-05,
      "loss": 0.5361,
      "step": 54
    },
    {
      "epoch": 3.2941176470588234,
      "grad_norm": 0.38733789324760437,
      "learning_rate": 6.588235294117648e-05,
      "loss": 0.5749,
      "step": 56
    },
    {
      "epoch": 3.411764705882353,
      "grad_norm": 0.4158814251422882,
      "learning_rate": 6.823529411764707e-05,
      "loss": 0.5555,
      "step": 58
    },
    {
      "epoch": 3.5294117647058822,
      "grad_norm": 0.4279491901397705,
      "learning_rate": 7.058823529411765e-05,
      "loss": 0.5092,
      "step": 60
    },
    {
      "epoch": 3.6470588235294117,
      "grad_norm": 0.4619697630405426,
      "learning_rate": 7.294117647058823e-05,
      "loss": 0.5531,
      "step": 62
    },
    {
      "epoch": 3.764705882352941,
      "grad_norm": 0.5522204041481018,
      "learning_rate": 7.529411764705883e-05,
      "loss": 0.5484,
      "step": 64
    },
    {
      "epoch": 3.8823529411764706,
      "grad_norm": 0.4337768852710724,
      "learning_rate": 7.764705882352942e-05,
      "loss": 0.5095,
      "step": 66
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.4109514355659485,
      "learning_rate": 8e-05,
      "loss": 0.5092,
      "step": 68
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.5707082748413086,
      "eval_runtime": 38.0212,
      "eval_samples_per_second": 0.947,
      "eval_steps_per_second": 0.947,
      "step": 68
    },
    {
      "epoch": 4.117647058823529,
      "grad_norm": 0.4325444996356964,
      "learning_rate": 8.23529411764706e-05,
      "loss": 0.5055,
      "step": 70
    },
    {
      "epoch": 4.235294117647059,
      "grad_norm": 0.4655042886734009,
      "learning_rate": 8.470588235294118e-05,
      "loss": 0.4526,
      "step": 72
    },
    {
      "epoch": 4.352941176470588,
      "grad_norm": 0.4314116835594177,
      "learning_rate": 8.705882352941177e-05,
      "loss": 0.4853,
      "step": 74
    },
    {
      "epoch": 4.470588235294118,
      "grad_norm": 0.5123972296714783,
      "learning_rate": 8.941176470588236e-05,
      "loss": 0.4669,
      "step": 76
    },
    {
      "epoch": 4.588235294117647,
      "grad_norm": 0.49299511313438416,
      "learning_rate": 9.176470588235295e-05,
      "loss": 0.4609,
      "step": 78
    },
    {
      "epoch": 4.705882352941177,
      "grad_norm": 0.5141043663024902,
      "learning_rate": 9.411764705882353e-05,
      "loss": 0.4534,
      "step": 80
    },
    {
      "epoch": 4.823529411764706,
      "grad_norm": 0.577174723148346,
      "learning_rate": 9.647058823529412e-05,
      "loss": 0.4589,
      "step": 82
    },
    {
      "epoch": 4.9411764705882355,
      "grad_norm": 0.5677844285964966,
      "learning_rate": 9.882352941176471e-05,
      "loss": 0.4367,
      "step": 84
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.5774327516555786,
      "eval_runtime": 38.025,
      "eval_samples_per_second": 0.947,
      "eval_steps_per_second": 0.947,
      "step": 85
    },
    {
      "epoch": 5.0588235294117645,
      "grad_norm": 0.5267917513847351,
      "learning_rate": 9.99995783847866e-05,
      "loss": 0.3785,
      "step": 86
    },
    {
      "epoch": 5.176470588235294,
      "grad_norm": 0.5194672346115112,
      "learning_rate": 9.999620550574153e-05,
      "loss": 0.3541,
      "step": 88
    },
    {
      "epoch": 5.294117647058823,
      "grad_norm": 0.6615413427352905,
      "learning_rate": 9.998945997517956e-05,
      "loss": 0.3645,
      "step": 90
    },
    {
      "epoch": 5.411764705882353,
      "grad_norm": 0.7008543610572815,
      "learning_rate": 9.997934224814173e-05,
      "loss": 0.3452,
      "step": 92
    },
    {
      "epoch": 5.529411764705882,
      "grad_norm": 0.7868872284889221,
      "learning_rate": 9.996585300715116e-05,
      "loss": 0.3373,
      "step": 94
    },
    {
      "epoch": 5.647058823529412,
      "grad_norm": 0.7311041951179504,
      "learning_rate": 9.994899316216708e-05,
      "loss": 0.3292,
      "step": 96
    },
    {
      "epoch": 5.764705882352941,
      "grad_norm": 0.6814704537391663,
      "learning_rate": 9.992876385052345e-05,
      "loss": 0.3508,
      "step": 98
    },
    {
      "epoch": 5.882352941176471,
      "grad_norm": 0.7336307764053345,
      "learning_rate": 9.990516643685222e-05,
      "loss": 0.3695,
      "step": 100
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.7040177583694458,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.3566,
      "step": 102
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.6305732727050781,
      "eval_runtime": 38.0339,
      "eval_samples_per_second": 0.947,
      "eval_steps_per_second": 0.947,
      "step": 102
    },
    {
      "epoch": 6.117647058823529,
      "grad_norm": 0.7306046485900879,
      "learning_rate": 9.984787389787688e-05,
      "loss": 0.2228,
      "step": 104
    },
    {
      "epoch": 6.235294117647059,
      "grad_norm": 0.7432003617286682,
      "learning_rate": 9.981418263742148e-05,
      "loss": 0.2271,
      "step": 106
    },
    {
      "epoch": 6.352941176470588,
      "grad_norm": 0.9761247634887695,
      "learning_rate": 9.977713100437509e-05,
      "loss": 0.244,
      "step": 108
    },
    {
      "epoch": 6.470588235294118,
      "grad_norm": 0.8622322678565979,
      "learning_rate": 9.973672149817232e-05,
      "loss": 0.2303,
      "step": 110
    },
    {
      "epoch": 6.588235294117647,
      "grad_norm": 0.6852889657020569,
      "learning_rate": 9.96929568447637e-05,
      "loss": 0.1796,
      "step": 112
    },
    {
      "epoch": 6.705882352941177,
      "grad_norm": 0.855422854423523,
      "learning_rate": 9.964583999643174e-05,
      "loss": 0.2058,
      "step": 114
    },
    {
      "epoch": 6.823529411764706,
      "grad_norm": 0.8779395222663879,
      "learning_rate": 9.95953741315919e-05,
      "loss": 0.2137,
      "step": 116
    },
    {
      "epoch": 6.9411764705882355,
      "grad_norm": 0.9580168128013611,
      "learning_rate": 9.954156265457801e-05,
      "loss": 0.2122,
      "step": 118
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.7395129799842834,
      "eval_runtime": 38.0236,
      "eval_samples_per_second": 0.947,
      "eval_steps_per_second": 0.947,
      "step": 119
    },
    {
      "epoch": 7.0588235294117645,
      "grad_norm": 0.5869453549385071,
      "learning_rate": 9.948440919541278e-05,
      "loss": 0.1693,
      "step": 120
    },
    {
      "epoch": 7.176470588235294,
      "grad_norm": 0.7213175296783447,
      "learning_rate": 9.942391760956277e-05,
      "loss": 0.1257,
      "step": 122
    },
    {
      "epoch": 7.294117647058823,
      "grad_norm": 0.820663332939148,
      "learning_rate": 9.936009197767845e-05,
      "loss": 0.1163,
      "step": 124
    },
    {
      "epoch": 7.411764705882353,
      "grad_norm": 1.0266770124435425,
      "learning_rate": 9.929293660531888e-05,
      "loss": 0.1078,
      "step": 126
    },
    {
      "epoch": 7.529411764705882,
      "grad_norm": 0.9780458807945251,
      "learning_rate": 9.922245602266118e-05,
      "loss": 0.1129,
      "step": 128
    },
    {
      "epoch": 7.647058823529412,
      "grad_norm": 0.7580817937850952,
      "learning_rate": 9.91486549841951e-05,
      "loss": 0.1047,
      "step": 130
    },
    {
      "epoch": 7.764705882352941,
      "grad_norm": 0.8334915041923523,
      "learning_rate": 9.90715384684021e-05,
      "loss": 0.1019,
      "step": 132
    },
    {
      "epoch": 7.882352941176471,
      "grad_norm": 0.7268296480178833,
      "learning_rate": 9.899111167741966e-05,
      "loss": 0.1244,
      "step": 134
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.7360743284225464,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.1165,
      "step": 136
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.8462986946105957,
      "eval_runtime": 38.0475,
      "eval_samples_per_second": 0.946,
      "eval_steps_per_second": 0.946,
      "step": 136
    },
    {
      "epoch": 8.117647058823529,
      "grad_norm": 0.5657596588134766,
      "learning_rate": 9.882034919459555e-05,
      "loss": 0.0577,
      "step": 138
    },
    {
      "epoch": 8.235294117647058,
      "grad_norm": 0.6155261397361755,
      "learning_rate": 9.873002502207503e-05,
      "loss": 0.0566,
      "step": 140
    },
    {
      "epoch": 8.352941176470589,
      "grad_norm": 1.0285184383392334,
      "learning_rate": 9.863641361223024e-05,
      "loss": 0.0679,
      "step": 142
    },
    {
      "epoch": 8.470588235294118,
      "grad_norm": 0.8026372790336609,
      "learning_rate": 9.853952127991372e-05,
      "loss": 0.0658,
      "step": 144
    },
    {
      "epoch": 8.588235294117647,
      "grad_norm": 0.8783811926841736,
      "learning_rate": 9.843935456130295e-05,
      "loss": 0.0645,
      "step": 146
    },
    {
      "epoch": 8.705882352941176,
      "grad_norm": 0.7183992266654968,
      "learning_rate": 9.833592021345937e-05,
      "loss": 0.0595,
      "step": 148
    },
    {
      "epoch": 8.823529411764707,
      "grad_norm": 0.7481778264045715,
      "learning_rate": 9.822922521387276e-05,
      "loss": 0.0592,
      "step": 150
    },
    {
      "epoch": 8.941176470588236,
      "grad_norm": 0.708199143409729,
      "learning_rate": 9.811927675999036e-05,
      "loss": 0.0708,
      "step": 152
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.900741696357727,
      "eval_runtime": 38.0417,
      "eval_samples_per_second": 0.946,
      "eval_steps_per_second": 0.946,
      "step": 153
    },
    {
      "epoch": 9.058823529411764,
      "grad_norm": 0.5321359038352966,
      "learning_rate": 9.800608226873142e-05,
      "loss": 0.0519,
      "step": 154
    },
    {
      "epoch": 9.176470588235293,
      "grad_norm": 0.5751078724861145,
      "learning_rate": 9.788964937598689e-05,
      "loss": 0.0475,
      "step": 156
    },
    {
      "epoch": 9.294117647058824,
      "grad_norm": 0.6371670961380005,
      "learning_rate": 9.776998593610428e-05,
      "loss": 0.0381,
      "step": 158
    },
    {
      "epoch": 9.411764705882353,
      "grad_norm": 0.842196524143219,
      "learning_rate": 9.764710002135784e-05,
      "loss": 0.0504,
      "step": 160
    },
    {
      "epoch": 9.529411764705882,
      "grad_norm": 0.6026459336280823,
      "learning_rate": 9.752099992140399e-05,
      "loss": 0.035,
      "step": 162
    },
    {
      "epoch": 9.647058823529411,
      "grad_norm": 0.9877235889434814,
      "learning_rate": 9.739169414272217e-05,
      "loss": 0.0397,
      "step": 164
    },
    {
      "epoch": 9.764705882352942,
      "grad_norm": 0.8170956969261169,
      "learning_rate": 9.725919140804099e-05,
      "loss": 0.0473,
      "step": 166
    },
    {
      "epoch": 9.882352941176471,
      "grad_norm": 0.7951951622962952,
      "learning_rate": 9.71235006557497e-05,
      "loss": 0.0411,
      "step": 168
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.7205672860145569,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0449,
      "step": 170
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.9731310606002808,
      "eval_runtime": 38.0429,
      "eval_samples_per_second": 0.946,
      "eval_steps_per_second": 0.946,
      "step": 170
    },
    {
      "epoch": 10.117647058823529,
      "grad_norm": 0.5359066128730774,
      "learning_rate": 9.684259192656553e-05,
      "loss": 0.0223,
      "step": 172
    },
    {
      "epoch": 10.235294117647058,
      "grad_norm": 0.7688780426979065,
      "learning_rate": 9.669739289925577e-05,
      "loss": 0.0315,
      "step": 174
    },
    {
      "epoch": 10.352941176470589,
      "grad_norm": 0.5604031682014465,
      "learning_rate": 9.654904375222385e-05,
      "loss": 0.0283,
      "step": 176
    },
    {
      "epoch": 10.470588235294118,
      "grad_norm": 0.6732109785079956,
      "learning_rate": 9.639755449282875e-05,
      "loss": 0.0264,
      "step": 178
    },
    {
      "epoch": 10.588235294117647,
      "grad_norm": 0.7116648554801941,
      "learning_rate": 9.62429353402556e-05,
      "loss": 0.0319,
      "step": 180
    },
    {
      "epoch": 10.705882352941176,
      "grad_norm": 0.7844197154045105,
      "learning_rate": 9.608519672482636e-05,
      "loss": 0.0356,
      "step": 182
    },
    {
      "epoch": 10.823529411764707,
      "grad_norm": 0.6466414332389832,
      "learning_rate": 9.592434928729616e-05,
      "loss": 0.0317,
      "step": 184
    },
    {
      "epoch": 10.941176470588236,
      "grad_norm": 0.8546337485313416,
      "learning_rate": 9.576040387813552e-05,
      "loss": 0.0388,
      "step": 186
    },
    {
      "epoch": 11.0,
      "eval_loss": 1.069735050201416,
      "eval_runtime": 38.04,
      "eval_samples_per_second": 0.946,
      "eval_steps_per_second": 0.946,
      "step": 187
    },
    {
      "epoch": 11.0,
      "step": 187,
      "total_flos": 1.4852394126934016e+17,
      "train_loss": 0.36900092757003194,
      "train_runtime": 5279.5531,
      "train_samples_per_second": 1.288,
      "train_steps_per_second": 0.161
    }
  ],
  "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": 1.4852394126934016e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}