{
  "best_metric": 0.8139402270317078,
  "best_model_checkpoint": "data/Mistral-7B_task-1_180-samples_config-1_full_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": 2.1213934421539307,
      "learning_rate": 1.1764705882352942e-06,
      "loss": 1.7235,
      "step": 1
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 2.114238977432251,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 1.799,
      "step": 2
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 1.9851863384246826,
      "learning_rate": 4.705882352941177e-06,
      "loss": 1.7056,
      "step": 4
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 2.191180944442749,
      "learning_rate": 7.058823529411765e-06,
      "loss": 1.7194,
      "step": 6
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 2.0361056327819824,
      "learning_rate": 9.411764705882354e-06,
      "loss": 1.7158,
      "step": 8
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 1.6054840087890625,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.629,
      "step": 10
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 1.697798252105713,
      "learning_rate": 1.411764705882353e-05,
      "loss": 1.6743,
      "step": 12
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 1.5540225505828857,
      "learning_rate": 1.647058823529412e-05,
      "loss": 1.6021,
      "step": 14
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 1.363179087638855,
      "learning_rate": 1.8823529411764708e-05,
      "loss": 1.4674,
      "step": 16
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.4008574485778809,
      "eval_runtime": 14.9621,
      "eval_samples_per_second": 2.406,
      "eval_steps_per_second": 2.406,
      "step": 17
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 1.1677181720733643,
      "learning_rate": 2.1176470588235296e-05,
      "loss": 1.4136,
      "step": 18
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 1.2462416887283325,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 1.3474,
      "step": 20
    },
    {
      "epoch": 1.2941176470588236,
      "grad_norm": 1.3484033346176147,
      "learning_rate": 2.5882352941176475e-05,
      "loss": 1.2832,
      "step": 22
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 1.4191542863845825,
      "learning_rate": 2.823529411764706e-05,
      "loss": 1.1599,
      "step": 24
    },
    {
      "epoch": 1.5294117647058822,
      "grad_norm": 1.1983416080474854,
      "learning_rate": 3.058823529411765e-05,
      "loss": 1.1254,
      "step": 26
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 1.231692910194397,
      "learning_rate": 3.294117647058824e-05,
      "loss": 1.0084,
      "step": 28
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 1.2172470092773438,
      "learning_rate": 3.529411764705883e-05,
      "loss": 0.9993,
      "step": 30
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 1.1073118448257446,
      "learning_rate": 3.7647058823529415e-05,
      "loss": 0.8991,
      "step": 32
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.933030366897583,
      "learning_rate": 4e-05,
      "loss": 0.9198,
      "step": 34
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.902515709400177,
      "eval_runtime": 14.9797,
      "eval_samples_per_second": 2.403,
      "eval_steps_per_second": 2.403,
      "step": 34
    },
    {
      "epoch": 2.1176470588235294,
      "grad_norm": 0.8091115951538086,
      "learning_rate": 4.235294117647059e-05,
      "loss": 0.8818,
      "step": 36
    },
    {
      "epoch": 2.235294117647059,
      "grad_norm": 0.7671001553535461,
      "learning_rate": 4.470588235294118e-05,
      "loss": 0.8501,
      "step": 38
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 0.8074772953987122,
      "learning_rate": 4.705882352941177e-05,
      "loss": 0.8214,
      "step": 40
    },
    {
      "epoch": 2.4705882352941178,
      "grad_norm": 0.8179394006729126,
      "learning_rate": 4.9411764705882355e-05,
      "loss": 0.8409,
      "step": 42
    },
    {
      "epoch": 2.588235294117647,
      "grad_norm": 0.7524192929267883,
      "learning_rate": 5.176470588235295e-05,
      "loss": 0.8125,
      "step": 44
    },
    {
      "epoch": 2.7058823529411766,
      "grad_norm": 0.8372642397880554,
      "learning_rate": 5.411764705882353e-05,
      "loss": 0.863,
      "step": 46
    },
    {
      "epoch": 2.8235294117647056,
      "grad_norm": 0.8221510648727417,
      "learning_rate": 5.647058823529412e-05,
      "loss": 0.8376,
      "step": 48
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 0.8239784836769104,
      "learning_rate": 5.882352941176471e-05,
      "loss": 0.8,
      "step": 50
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.8352473974227905,
      "eval_runtime": 14.9663,
      "eval_samples_per_second": 2.405,
      "eval_steps_per_second": 2.405,
      "step": 51
    },
    {
      "epoch": 3.0588235294117645,
      "grad_norm": 0.8199384212493896,
      "learning_rate": 6.11764705882353e-05,
      "loss": 0.725,
      "step": 52
    },
    {
      "epoch": 3.176470588235294,
      "grad_norm": 0.8523749709129333,
      "learning_rate": 6.352941176470588e-05,
      "loss": 0.7479,
      "step": 54
    },
    {
      "epoch": 3.2941176470588234,
      "grad_norm": 0.8729116916656494,
      "learning_rate": 6.588235294117648e-05,
      "loss": 0.7311,
      "step": 56
    },
    {
      "epoch": 3.411764705882353,
      "grad_norm": 0.9291346073150635,
      "learning_rate": 6.823529411764707e-05,
      "loss": 0.7652,
      "step": 58
    },
    {
      "epoch": 3.5294117647058822,
      "grad_norm": 0.9422364234924316,
      "learning_rate": 7.058823529411765e-05,
      "loss": 0.6952,
      "step": 60
    },
    {
      "epoch": 3.6470588235294117,
      "grad_norm": 0.9628893136978149,
      "learning_rate": 7.294117647058823e-05,
      "loss": 0.7115,
      "step": 62
    },
    {
      "epoch": 3.764705882352941,
      "grad_norm": 0.9511690139770508,
      "learning_rate": 7.529411764705883e-05,
      "loss": 0.6973,
      "step": 64
    },
    {
      "epoch": 3.8823529411764706,
      "grad_norm": 1.0223468542099,
      "learning_rate": 7.764705882352942e-05,
      "loss": 0.665,
      "step": 66
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.0688872337341309,
      "learning_rate": 8e-05,
      "loss": 0.6649,
      "step": 68
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.8139402270317078,
      "eval_runtime": 14.9615,
      "eval_samples_per_second": 2.406,
      "eval_steps_per_second": 2.406,
      "step": 68
    },
    {
      "epoch": 4.117647058823529,
      "grad_norm": 1.0038996934890747,
      "learning_rate": 8.23529411764706e-05,
      "loss": 0.5809,
      "step": 70
    },
    {
      "epoch": 4.235294117647059,
      "grad_norm": 1.0847755670547485,
      "learning_rate": 8.470588235294118e-05,
      "loss": 0.5621,
      "step": 72
    },
    {
      "epoch": 4.352941176470588,
      "grad_norm": 1.328791618347168,
      "learning_rate": 8.705882352941177e-05,
      "loss": 0.5584,
      "step": 74
    },
    {
      "epoch": 4.470588235294118,
      "grad_norm": 1.314184546470642,
      "learning_rate": 8.941176470588236e-05,
      "loss": 0.5285,
      "step": 76
    },
    {
      "epoch": 4.588235294117647,
      "grad_norm": 1.1576733589172363,
      "learning_rate": 9.176470588235295e-05,
      "loss": 0.5708,
      "step": 78
    },
    {
      "epoch": 4.705882352941177,
      "grad_norm": 1.3629945516586304,
      "learning_rate": 9.411764705882353e-05,
      "loss": 0.5278,
      "step": 80
    },
    {
      "epoch": 4.823529411764706,
      "grad_norm": 1.3482656478881836,
      "learning_rate": 9.647058823529412e-05,
      "loss": 0.5431,
      "step": 82
    },
    {
      "epoch": 4.9411764705882355,
      "grad_norm": 1.5334190130233765,
      "learning_rate": 9.882352941176471e-05,
      "loss": 0.5015,
      "step": 84
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.8608801364898682,
      "eval_runtime": 14.9724,
      "eval_samples_per_second": 2.404,
      "eval_steps_per_second": 2.404,
      "step": 85
    },
    {
      "epoch": 5.0588235294117645,
      "grad_norm": 1.3340182304382324,
      "learning_rate": 9.99995783847866e-05,
      "loss": 0.4351,
      "step": 86
    },
    {
      "epoch": 5.176470588235294,
      "grad_norm": 1.2677031755447388,
      "learning_rate": 9.999620550574153e-05,
      "loss": 0.3783,
      "step": 88
    },
    {
      "epoch": 5.294117647058823,
      "grad_norm": 1.824696660041809,
      "learning_rate": 9.998945997517956e-05,
      "loss": 0.3637,
      "step": 90
    },
    {
      "epoch": 5.411764705882353,
      "grad_norm": 1.586932897567749,
      "learning_rate": 9.997934224814173e-05,
      "loss": 0.3491,
      "step": 92
    },
    {
      "epoch": 5.529411764705882,
      "grad_norm": 1.6526200771331787,
      "learning_rate": 9.996585300715116e-05,
      "loss": 0.3423,
      "step": 94
    },
    {
      "epoch": 5.647058823529412,
      "grad_norm": 1.682108998298645,
      "learning_rate": 9.994899316216708e-05,
      "loss": 0.3275,
      "step": 96
    },
    {
      "epoch": 5.764705882352941,
      "grad_norm": 1.5482568740844727,
      "learning_rate": 9.992876385052345e-05,
      "loss": 0.3623,
      "step": 98
    },
    {
      "epoch": 5.882352941176471,
      "grad_norm": 1.7141402959823608,
      "learning_rate": 9.990516643685222e-05,
      "loss": 0.3721,
      "step": 100
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.6174116134643555,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.3493,
      "step": 102
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.9102272391319275,
      "eval_runtime": 14.9718,
      "eval_samples_per_second": 2.405,
      "eval_steps_per_second": 2.405,
      "step": 102
    },
    {
      "epoch": 6.117647058823529,
      "grad_norm": 1.3451955318450928,
      "learning_rate": 9.984787389787688e-05,
      "loss": 0.2168,
      "step": 104
    },
    {
      "epoch": 6.235294117647059,
      "grad_norm": 1.9440399408340454,
      "learning_rate": 9.981418263742148e-05,
      "loss": 0.2379,
      "step": 106
    },
    {
      "epoch": 6.352941176470588,
      "grad_norm": 1.8776825666427612,
      "learning_rate": 9.977713100437509e-05,
      "loss": 0.2343,
      "step": 108
    },
    {
      "epoch": 6.470588235294118,
      "grad_norm": 2.537928342819214,
      "learning_rate": 9.973672149817232e-05,
      "loss": 0.2402,
      "step": 110
    },
    {
      "epoch": 6.588235294117647,
      "grad_norm": 1.6730800867080688,
      "learning_rate": 9.96929568447637e-05,
      "loss": 0.2122,
      "step": 112
    },
    {
      "epoch": 6.705882352941177,
      "grad_norm": 1.6287802457809448,
      "learning_rate": 9.964583999643174e-05,
      "loss": 0.232,
      "step": 114
    },
    {
      "epoch": 6.823529411764706,
      "grad_norm": 1.5841904878616333,
      "learning_rate": 9.95953741315919e-05,
      "loss": 0.2299,
      "step": 116
    },
    {
      "epoch": 6.9411764705882355,
      "grad_norm": 1.5367815494537354,
      "learning_rate": 9.954156265457801e-05,
      "loss": 0.2426,
      "step": 118
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.0199217796325684,
      "eval_runtime": 14.9608,
      "eval_samples_per_second": 2.406,
      "eval_steps_per_second": 2.406,
      "step": 119
    },
    {
      "epoch": 7.0588235294117645,
      "grad_norm": 1.5127623081207275,
      "learning_rate": 9.948440919541278e-05,
      "loss": 0.2085,
      "step": 120
    },
    {
      "epoch": 7.176470588235294,
      "grad_norm": 1.2495055198669434,
      "learning_rate": 9.942391760956277e-05,
      "loss": 0.1687,
      "step": 122
    },
    {
      "epoch": 7.294117647058823,
      "grad_norm": 2.044674873352051,
      "learning_rate": 9.936009197767845e-05,
      "loss": 0.1529,
      "step": 124
    },
    {
      "epoch": 7.411764705882353,
      "grad_norm": 1.5975205898284912,
      "learning_rate": 9.929293660531888e-05,
      "loss": 0.1686,
      "step": 126
    },
    {
      "epoch": 7.529411764705882,
      "grad_norm": 1.9689905643463135,
      "learning_rate": 9.922245602266118e-05,
      "loss": 0.1865,
      "step": 128
    },
    {
      "epoch": 7.647058823529412,
      "grad_norm": 1.5307559967041016,
      "learning_rate": 9.91486549841951e-05,
      "loss": 0.1711,
      "step": 130
    },
    {
      "epoch": 7.764705882352941,
      "grad_norm": 1.508986473083496,
      "learning_rate": 9.90715384684021e-05,
      "loss": 0.1728,
      "step": 132
    },
    {
      "epoch": 7.882352941176471,
      "grad_norm": 1.1104421615600586,
      "learning_rate": 9.899111167741966e-05,
      "loss": 0.1795,
      "step": 134
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.6483793258666992,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.1984,
      "step": 136
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.141489863395691,
      "eval_runtime": 14.9659,
      "eval_samples_per_second": 2.405,
      "eval_steps_per_second": 2.405,
      "step": 136
    },
    {
      "epoch": 8.117647058823529,
      "grad_norm": 1.05375075340271,
      "learning_rate": 9.882034919459555e-05,
      "loss": 0.1344,
      "step": 138
    },
    {
      "epoch": 8.235294117647058,
      "grad_norm": 1.5862947702407837,
      "learning_rate": 9.873002502207503e-05,
      "loss": 0.1315,
      "step": 140
    },
    {
      "epoch": 8.352941176470589,
      "grad_norm": 1.5041707754135132,
      "learning_rate": 9.863641361223024e-05,
      "loss": 0.1351,
      "step": 142
    },
    {
      "epoch": 8.470588235294118,
      "grad_norm": 1.563441514968872,
      "learning_rate": 9.853952127991372e-05,
      "loss": 0.1583,
      "step": 144
    },
    {
      "epoch": 8.588235294117647,
      "grad_norm": 1.5371496677398682,
      "learning_rate": 9.843935456130295e-05,
      "loss": 0.1455,
      "step": 146
    },
    {
      "epoch": 8.705882352941176,
      "grad_norm": 1.061530590057373,
      "learning_rate": 9.833592021345937e-05,
      "loss": 0.1376,
      "step": 148
    },
    {
      "epoch": 8.823529411764707,
      "grad_norm": 1.3203407526016235,
      "learning_rate": 9.822922521387276e-05,
      "loss": 0.1555,
      "step": 150
    },
    {
      "epoch": 8.941176470588236,
      "grad_norm": 1.5236210823059082,
      "learning_rate": 9.811927675999036e-05,
      "loss": 0.1677,
      "step": 152
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.0862891674041748,
      "eval_runtime": 14.9773,
      "eval_samples_per_second": 2.404,
      "eval_steps_per_second": 2.404,
      "step": 153
    },
    {
      "epoch": 9.058823529411764,
      "grad_norm": 0.9704665541648865,
      "learning_rate": 9.800608226873142e-05,
      "loss": 0.1267,
      "step": 154
    },
    {
      "epoch": 9.176470588235293,
      "grad_norm": 0.9529500007629395,
      "learning_rate": 9.788964937598689e-05,
      "loss": 0.115,
      "step": 156
    },
    {
      "epoch": 9.294117647058824,
      "grad_norm": 1.099527359008789,
      "learning_rate": 9.776998593610428e-05,
      "loss": 0.118,
      "step": 158
    },
    {
      "epoch": 9.411764705882353,
      "grad_norm": 1.4279507398605347,
      "learning_rate": 9.764710002135784e-05,
      "loss": 0.1193,
      "step": 160
    },
    {
      "epoch": 9.529411764705882,
      "grad_norm": 1.0358731746673584,
      "learning_rate": 9.752099992140399e-05,
      "loss": 0.1162,
      "step": 162
    },
    {
      "epoch": 9.647058823529411,
      "grad_norm": 1.2888990640640259,
      "learning_rate": 9.739169414272217e-05,
      "loss": 0.1243,
      "step": 164
    },
    {
      "epoch": 9.764705882352942,
      "grad_norm": 1.3969851732254028,
      "learning_rate": 9.725919140804099e-05,
      "loss": 0.131,
      "step": 166
    },
    {
      "epoch": 9.882352941176471,
      "grad_norm": 1.304606556892395,
      "learning_rate": 9.71235006557497e-05,
      "loss": 0.1383,
      "step": 168
    },
    {
      "epoch": 10.0,
      "grad_norm": 1.6125257015228271,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.1384,
      "step": 170
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.1543630361557007,
      "eval_runtime": 14.9592,
      "eval_samples_per_second": 2.407,
      "eval_steps_per_second": 2.407,
      "step": 170
    },
    {
      "epoch": 10.117647058823529,
      "grad_norm": 0.9996251463890076,
      "learning_rate": 9.684259192656553e-05,
      "loss": 0.1054,
      "step": 172
    },
    {
      "epoch": 10.235294117647058,
      "grad_norm": 0.8701817393302917,
      "learning_rate": 9.669739289925577e-05,
      "loss": 0.1069,
      "step": 174
    },
    {
      "epoch": 10.352941176470589,
      "grad_norm": 1.151466965675354,
      "learning_rate": 9.654904375222385e-05,
      "loss": 0.1059,
      "step": 176
    },
    {
      "epoch": 10.470588235294118,
      "grad_norm": 1.5486702919006348,
      "learning_rate": 9.639755449282875e-05,
      "loss": 0.0963,
      "step": 178
    },
    {
      "epoch": 10.588235294117647,
      "grad_norm": 1.2436723709106445,
      "learning_rate": 9.62429353402556e-05,
      "loss": 0.1023,
      "step": 180
    },
    {
      "epoch": 10.705882352941176,
      "grad_norm": 1.2594785690307617,
      "learning_rate": 9.608519672482636e-05,
      "loss": 0.1154,
      "step": 182
    },
    {
      "epoch": 10.823529411764707,
      "grad_norm": 0.9442002773284912,
      "learning_rate": 9.592434928729616e-05,
      "loss": 0.1041,
      "step": 184
    },
    {
      "epoch": 10.941176470588236,
      "grad_norm": 0.9647455215454102,
      "learning_rate": 9.576040387813552e-05,
      "loss": 0.1134,
      "step": 186
    },
    {
      "epoch": 11.0,
      "eval_loss": 1.2206202745437622,
      "eval_runtime": 14.9593,
      "eval_samples_per_second": 2.407,
      "eval_steps_per_second": 2.407,
      "step": 187
    },
    {
      "epoch": 11.0,
      "step": 187,
      "total_flos": 2.518477261556941e+16,
      "train_loss": 0.543800364641901,
      "train_runtime": 1823.6143,
      "train_samples_per_second": 3.729,
      "train_steps_per_second": 0.466
    }
  ],
  "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": 2.518477261556941e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}