{
  "best_metric": 0.8879411220550537,
  "best_model_checkpoint": "data/Llama-31-8B_task-1_180-samples_config-1_auto/checkpoint-51",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 170,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.058823529411764705,
      "grad_norm": 0.8497962355613708,
      "learning_rate": 1.1764705882352942e-06,
      "loss": 1.152,
      "step": 1
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 0.7685027718544006,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 1.1245,
      "step": 2
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 0.8295040726661682,
      "learning_rate": 4.705882352941177e-06,
      "loss": 1.1305,
      "step": 4
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 0.7829303741455078,
      "learning_rate": 7.058823529411765e-06,
      "loss": 1.1529,
      "step": 6
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.9397178888320923,
      "learning_rate": 9.411764705882354e-06,
      "loss": 1.2086,
      "step": 8
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 0.8592646718025208,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.146,
      "step": 10
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 0.8117731213569641,
      "learning_rate": 1.411764705882353e-05,
      "loss": 1.1521,
      "step": 12
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 0.942381739616394,
      "learning_rate": 1.647058823529412e-05,
      "loss": 1.1951,
      "step": 14
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.8439870476722717,
      "learning_rate": 1.8823529411764708e-05,
      "loss": 1.063,
      "step": 16
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.0966124534606934,
      "eval_runtime": 14.8546,
      "eval_samples_per_second": 2.423,
      "eval_steps_per_second": 2.423,
      "step": 17
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 0.6530096530914307,
      "learning_rate": 2.1176470588235296e-05,
      "loss": 1.0444,
      "step": 18
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.6262273192405701,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 1.0208,
      "step": 20
    },
    {
      "epoch": 1.2941176470588236,
      "grad_norm": 0.48974114656448364,
      "learning_rate": 2.5882352941176475e-05,
      "loss": 0.9786,
      "step": 22
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 0.4904261529445648,
      "learning_rate": 2.823529411764706e-05,
      "loss": 0.985,
      "step": 24
    },
    {
      "epoch": 1.5294117647058822,
      "grad_norm": 0.5825740098953247,
      "learning_rate": 3.058823529411765e-05,
      "loss": 0.9792,
      "step": 26
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 0.5803666114807129,
      "learning_rate": 3.294117647058824e-05,
      "loss": 0.967,
      "step": 28
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 0.7749001383781433,
      "learning_rate": 3.529411764705883e-05,
      "loss": 0.9196,
      "step": 30
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 0.5416077375411987,
      "learning_rate": 3.7647058823529415e-05,
      "loss": 0.9206,
      "step": 32
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.4670708179473877,
      "learning_rate": 4e-05,
      "loss": 0.8972,
      "step": 34
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.9599697589874268,
      "eval_runtime": 14.8593,
      "eval_samples_per_second": 2.423,
      "eval_steps_per_second": 2.423,
      "step": 34
    },
    {
      "epoch": 2.1176470588235294,
      "grad_norm": 0.48657140135765076,
      "learning_rate": 4.235294117647059e-05,
      "loss": 0.8047,
      "step": 36
    },
    {
      "epoch": 2.235294117647059,
      "grad_norm": 0.4843344986438751,
      "learning_rate": 4.470588235294118e-05,
      "loss": 0.8273,
      "step": 38
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 0.5899777412414551,
      "learning_rate": 4.705882352941177e-05,
      "loss": 0.8531,
      "step": 40
    },
    {
      "epoch": 2.4705882352941178,
      "grad_norm": 0.6686798930168152,
      "learning_rate": 4.9411764705882355e-05,
      "loss": 0.8578,
      "step": 42
    },
    {
      "epoch": 2.588235294117647,
      "grad_norm": 0.5812777876853943,
      "learning_rate": 5.176470588235295e-05,
      "loss": 0.8388,
      "step": 44
    },
    {
      "epoch": 2.7058823529411766,
      "grad_norm": 0.6418431997299194,
      "learning_rate": 5.411764705882353e-05,
      "loss": 0.8559,
      "step": 46
    },
    {
      "epoch": 2.8235294117647056,
      "grad_norm": 0.6979645490646362,
      "learning_rate": 5.647058823529412e-05,
      "loss": 0.8861,
      "step": 48
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 0.7628887295722961,
      "learning_rate": 5.882352941176471e-05,
      "loss": 0.8866,
      "step": 50
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.8879411220550537,
      "eval_runtime": 14.8984,
      "eval_samples_per_second": 2.416,
      "eval_steps_per_second": 2.416,
      "step": 51
    },
    {
      "epoch": 3.0588235294117645,
      "grad_norm": 0.6387588381767273,
      "learning_rate": 6.11764705882353e-05,
      "loss": 0.7612,
      "step": 52
    },
    {
      "epoch": 3.176470588235294,
      "grad_norm": 0.6679393649101257,
      "learning_rate": 6.352941176470588e-05,
      "loss": 0.729,
      "step": 54
    },
    {
      "epoch": 3.2941176470588234,
      "grad_norm": 0.5764548182487488,
      "learning_rate": 6.588235294117648e-05,
      "loss": 0.7458,
      "step": 56
    },
    {
      "epoch": 3.411764705882353,
      "grad_norm": 0.7429522275924683,
      "learning_rate": 6.823529411764707e-05,
      "loss": 0.8209,
      "step": 58
    },
    {
      "epoch": 3.5294117647058822,
      "grad_norm": 0.7595254182815552,
      "learning_rate": 7.058823529411765e-05,
      "loss": 0.7054,
      "step": 60
    },
    {
      "epoch": 3.6470588235294117,
      "grad_norm": 0.8727766275405884,
      "learning_rate": 7.294117647058823e-05,
      "loss": 0.7305,
      "step": 62
    },
    {
      "epoch": 3.764705882352941,
      "grad_norm": 0.8094116449356079,
      "learning_rate": 7.529411764705883e-05,
      "loss": 0.7282,
      "step": 64
    },
    {
      "epoch": 3.8823529411764706,
      "grad_norm": 0.8250320553779602,
      "learning_rate": 7.764705882352942e-05,
      "loss": 0.6685,
      "step": 66
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.9825006723403931,
      "learning_rate": 8e-05,
      "loss": 0.7569,
      "step": 68
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.8909105658531189,
      "eval_runtime": 14.85,
      "eval_samples_per_second": 2.424,
      "eval_steps_per_second": 2.424,
      "step": 68
    },
    {
      "epoch": 4.117647058823529,
      "grad_norm": 0.8551511764526367,
      "learning_rate": 8.23529411764706e-05,
      "loss": 0.6476,
      "step": 70
    },
    {
      "epoch": 4.235294117647059,
      "grad_norm": 0.9041043519973755,
      "learning_rate": 8.470588235294118e-05,
      "loss": 0.5779,
      "step": 72
    },
    {
      "epoch": 4.352941176470588,
      "grad_norm": 0.8559205532073975,
      "learning_rate": 8.705882352941177e-05,
      "loss": 0.556,
      "step": 74
    },
    {
      "epoch": 4.470588235294118,
      "grad_norm": 1.0176703929901123,
      "learning_rate": 8.941176470588236e-05,
      "loss": 0.5848,
      "step": 76
    },
    {
      "epoch": 4.588235294117647,
      "grad_norm": 1.060314655303955,
      "learning_rate": 9.176470588235295e-05,
      "loss": 0.6266,
      "step": 78
    },
    {
      "epoch": 4.705882352941177,
      "grad_norm": 1.0777111053466797,
      "learning_rate": 9.411764705882353e-05,
      "loss": 0.5796,
      "step": 80
    },
    {
      "epoch": 4.823529411764706,
      "grad_norm": 0.9776031374931335,
      "learning_rate": 9.647058823529412e-05,
      "loss": 0.5944,
      "step": 82
    },
    {
      "epoch": 4.9411764705882355,
      "grad_norm": 1.0351969003677368,
      "learning_rate": 9.882352941176471e-05,
      "loss": 0.5434,
      "step": 84
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.9380133152008057,
      "eval_runtime": 14.8489,
      "eval_samples_per_second": 2.424,
      "eval_steps_per_second": 2.424,
      "step": 85
    },
    {
      "epoch": 5.0588235294117645,
      "grad_norm": 1.1650046110153198,
      "learning_rate": 9.99995783847866e-05,
      "loss": 0.45,
      "step": 86
    },
    {
      "epoch": 5.176470588235294,
      "grad_norm": 1.0582606792449951,
      "learning_rate": 9.999620550574153e-05,
      "loss": 0.4109,
      "step": 88
    },
    {
      "epoch": 5.294117647058823,
      "grad_norm": 1.3925597667694092,
      "learning_rate": 9.998945997517956e-05,
      "loss": 0.3884,
      "step": 90
    },
    {
      "epoch": 5.411764705882353,
      "grad_norm": 1.4229979515075684,
      "learning_rate": 9.997934224814173e-05,
      "loss": 0.3328,
      "step": 92
    },
    {
      "epoch": 5.529411764705882,
      "grad_norm": 1.7364519834518433,
      "learning_rate": 9.996585300715116e-05,
      "loss": 0.3646,
      "step": 94
    },
    {
      "epoch": 5.647058823529412,
      "grad_norm": 1.492929220199585,
      "learning_rate": 9.994899316216708e-05,
      "loss": 0.3347,
      "step": 96
    },
    {
      "epoch": 5.764705882352941,
      "grad_norm": 1.3663392066955566,
      "learning_rate": 9.992876385052345e-05,
      "loss": 0.4038,
      "step": 98
    },
    {
      "epoch": 5.882352941176471,
      "grad_norm": 1.2712633609771729,
      "learning_rate": 9.990516643685222e-05,
      "loss": 0.4136,
      "step": 100
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.1909713745117188,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.4043,
      "step": 102
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.0244461297988892,
      "eval_runtime": 14.8677,
      "eval_samples_per_second": 2.421,
      "eval_steps_per_second": 2.421,
      "step": 102
    },
    {
      "epoch": 6.117647058823529,
      "grad_norm": 0.9694238305091858,
      "learning_rate": 9.984787389787688e-05,
      "loss": 0.2091,
      "step": 104
    },
    {
      "epoch": 6.235294117647059,
      "grad_norm": 1.199276089668274,
      "learning_rate": 9.981418263742148e-05,
      "loss": 0.2182,
      "step": 106
    },
    {
      "epoch": 6.352941176470588,
      "grad_norm": 1.8628352880477905,
      "learning_rate": 9.977713100437509e-05,
      "loss": 0.2409,
      "step": 108
    },
    {
      "epoch": 6.470588235294118,
      "grad_norm": 1.8579826354980469,
      "learning_rate": 9.973672149817232e-05,
      "loss": 0.2414,
      "step": 110
    },
    {
      "epoch": 6.588235294117647,
      "grad_norm": 1.615858554840088,
      "learning_rate": 9.96929568447637e-05,
      "loss": 0.1668,
      "step": 112
    },
    {
      "epoch": 6.705882352941177,
      "grad_norm": 1.4381364583969116,
      "learning_rate": 9.964583999643174e-05,
      "loss": 0.1802,
      "step": 114
    },
    {
      "epoch": 6.823529411764706,
      "grad_norm": 1.4709198474884033,
      "learning_rate": 9.95953741315919e-05,
      "loss": 0.2125,
      "step": 116
    },
    {
      "epoch": 6.9411764705882355,
      "grad_norm": 1.218277096748352,
      "learning_rate": 9.954156265457801e-05,
      "loss": 0.2016,
      "step": 118
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.2543505430221558,
      "eval_runtime": 14.8652,
      "eval_samples_per_second": 2.422,
      "eval_steps_per_second": 2.422,
      "step": 119
    },
    {
      "epoch": 7.0588235294117645,
      "grad_norm": 0.8317411541938782,
      "learning_rate": 9.948440919541278e-05,
      "loss": 0.1703,
      "step": 120
    },
    {
      "epoch": 7.176470588235294,
      "grad_norm": 1.2203559875488281,
      "learning_rate": 9.942391760956277e-05,
      "loss": 0.1316,
      "step": 122
    },
    {
      "epoch": 7.294117647058823,
      "grad_norm": 1.245187520980835,
      "learning_rate": 9.936009197767845e-05,
      "loss": 0.1145,
      "step": 124
    },
    {
      "epoch": 7.411764705882353,
      "grad_norm": 1.4678796529769897,
      "learning_rate": 9.929293660531888e-05,
      "loss": 0.1171,
      "step": 126
    },
    {
      "epoch": 7.529411764705882,
      "grad_norm": 1.8378161191940308,
      "learning_rate": 9.922245602266118e-05,
      "loss": 0.1225,
      "step": 128
    },
    {
      "epoch": 7.647058823529412,
      "grad_norm": 1.6163164377212524,
      "learning_rate": 9.91486549841951e-05,
      "loss": 0.1153,
      "step": 130
    },
    {
      "epoch": 7.764705882352941,
      "grad_norm": 1.88551664352417,
      "learning_rate": 9.90715384684021e-05,
      "loss": 0.1057,
      "step": 132
    },
    {
      "epoch": 7.882352941176471,
      "grad_norm": 1.2052146196365356,
      "learning_rate": 9.899111167741966e-05,
      "loss": 0.1279,
      "step": 134
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.574941873550415,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.1537,
      "step": 136
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.4365975856781006,
      "eval_runtime": 14.8515,
      "eval_samples_per_second": 2.424,
      "eval_steps_per_second": 2.424,
      "step": 136
    },
    {
      "epoch": 8.117647058823529,
      "grad_norm": 0.8787940144538879,
      "learning_rate": 9.882034919459555e-05,
      "loss": 0.081,
      "step": 138
    },
    {
      "epoch": 8.235294117647058,
      "grad_norm": 1.0354961156845093,
      "learning_rate": 9.873002502207503e-05,
      "loss": 0.0836,
      "step": 140
    },
    {
      "epoch": 8.352941176470589,
      "grad_norm": 1.1069930791854858,
      "learning_rate": 9.863641361223024e-05,
      "loss": 0.0896,
      "step": 142
    },
    {
      "epoch": 8.470588235294118,
      "grad_norm": 0.8952913880348206,
      "learning_rate": 9.853952127991372e-05,
      "loss": 0.0912,
      "step": 144
    },
    {
      "epoch": 8.588235294117647,
      "grad_norm": 1.3685219287872314,
      "learning_rate": 9.843935456130295e-05,
      "loss": 0.0712,
      "step": 146
    },
    {
      "epoch": 8.705882352941176,
      "grad_norm": 1.4462240934371948,
      "learning_rate": 9.833592021345937e-05,
      "loss": 0.0835,
      "step": 148
    },
    {
      "epoch": 8.823529411764707,
      "grad_norm": 1.395073652267456,
      "learning_rate": 9.822922521387276e-05,
      "loss": 0.0853,
      "step": 150
    },
    {
      "epoch": 8.941176470588236,
      "grad_norm": 1.7228752374649048,
      "learning_rate": 9.811927675999036e-05,
      "loss": 0.1035,
      "step": 152
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.5816410779953003,
      "eval_runtime": 14.8567,
      "eval_samples_per_second": 2.423,
      "eval_steps_per_second": 2.423,
      "step": 153
    },
    {
      "epoch": 9.058823529411764,
      "grad_norm": 1.1363343000411987,
      "learning_rate": 9.800608226873142e-05,
      "loss": 0.0681,
      "step": 154
    },
    {
      "epoch": 9.176470588235293,
      "grad_norm": 1.0412440299987793,
      "learning_rate": 9.788964937598689e-05,
      "loss": 0.056,
      "step": 156
    },
    {
      "epoch": 9.294117647058824,
      "grad_norm": 1.0078048706054688,
      "learning_rate": 9.776998593610428e-05,
      "loss": 0.0527,
      "step": 158
    },
    {
      "epoch": 9.411764705882353,
      "grad_norm": 1.0799468755722046,
      "learning_rate": 9.764710002135784e-05,
      "loss": 0.0574,
      "step": 160
    },
    {
      "epoch": 9.529411764705882,
      "grad_norm": 1.0495719909667969,
      "learning_rate": 9.752099992140399e-05,
      "loss": 0.0515,
      "step": 162
    },
    {
      "epoch": 9.647058823529411,
      "grad_norm": 1.273497223854065,
      "learning_rate": 9.739169414272217e-05,
      "loss": 0.0729,
      "step": 164
    },
    {
      "epoch": 9.764705882352942,
      "grad_norm": 1.1731970310211182,
      "learning_rate": 9.725919140804099e-05,
      "loss": 0.0769,
      "step": 166
    },
    {
      "epoch": 9.882352941176471,
      "grad_norm": 1.1258608102798462,
      "learning_rate": 9.71235006557497e-05,
      "loss": 0.0703,
      "step": 168
    },
    {
      "epoch": 10.0,
      "grad_norm": 1.2797598838806152,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.058,
      "step": 170
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.5976319313049316,
      "eval_runtime": 14.856,
      "eval_samples_per_second": 2.423,
      "eval_steps_per_second": 2.423,
      "step": 170
    },
    {
      "epoch": 10.0,
      "step": 170,
      "total_flos": 2.3077113934381056e+16,
      "train_loss": 0.5135380078764523,
      "train_runtime": 1642.2115,
      "train_samples_per_second": 4.141,
      "train_steps_per_second": 0.518
    }
  ],
  "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": 2.3077113934381056e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}