{
  "best_metric": 0.8535944819450378,
  "best_model_checkpoint": "data/Mistral-7B_task-3_180-samples_config-1_full_auto/checkpoint-85",
  "epoch": 12.0,
  "eval_steps": 500,
  "global_step": 204,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.058823529411764705,
      "grad_norm": 1.006831169128418,
      "learning_rate": 1.1764705882352942e-06,
      "loss": 1.2204,
      "step": 1
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 1.0581775903701782,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 1.2637,
      "step": 2
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 1.1468743085861206,
      "learning_rate": 4.705882352941177e-06,
      "loss": 1.2479,
      "step": 4
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 1.0014772415161133,
      "learning_rate": 7.058823529411765e-06,
      "loss": 1.2599,
      "step": 6
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.9159674644470215,
      "learning_rate": 9.411764705882354e-06,
      "loss": 1.2265,
      "step": 8
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 0.7531934380531311,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.1748,
      "step": 10
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 0.715920627117157,
      "learning_rate": 1.411764705882353e-05,
      "loss": 1.1544,
      "step": 12
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 0.6371190547943115,
      "learning_rate": 1.647058823529412e-05,
      "loss": 1.1739,
      "step": 14
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.48628872632980347,
      "learning_rate": 1.8823529411764708e-05,
      "loss": 1.1289,
      "step": 16
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.10905122756958,
      "eval_runtime": 39.2544,
      "eval_samples_per_second": 0.917,
      "eval_steps_per_second": 0.917,
      "step": 17
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 0.42620494961738586,
      "learning_rate": 2.1176470588235296e-05,
      "loss": 1.1148,
      "step": 18
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.3535543978214264,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 1.1102,
      "step": 20
    },
    {
      "epoch": 1.2941176470588236,
      "grad_norm": 0.3400056064128876,
      "learning_rate": 2.5882352941176475e-05,
      "loss": 1.0581,
      "step": 22
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 0.35508406162261963,
      "learning_rate": 2.823529411764706e-05,
      "loss": 1.0388,
      "step": 24
    },
    {
      "epoch": 1.5294117647058822,
      "grad_norm": 0.30929434299468994,
      "learning_rate": 3.058823529411765e-05,
      "loss": 1.0202,
      "step": 26
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 0.36725738644599915,
      "learning_rate": 3.294117647058824e-05,
      "loss": 1.0127,
      "step": 28
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 0.5205434560775757,
      "learning_rate": 3.529411764705883e-05,
      "loss": 0.9881,
      "step": 30
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 0.4649356007575989,
      "learning_rate": 3.7647058823529415e-05,
      "loss": 0.96,
      "step": 32
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5073856115341187,
      "learning_rate": 4e-05,
      "loss": 0.9469,
      "step": 34
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.9380963444709778,
      "eval_runtime": 39.2614,
      "eval_samples_per_second": 0.917,
      "eval_steps_per_second": 0.917,
      "step": 34
    },
    {
      "epoch": 2.1176470588235294,
      "grad_norm": 0.40834659337997437,
      "learning_rate": 4.235294117647059e-05,
      "loss": 0.8899,
      "step": 36
    },
    {
      "epoch": 2.235294117647059,
      "grad_norm": 0.373359352350235,
      "learning_rate": 4.470588235294118e-05,
      "loss": 0.8759,
      "step": 38
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 0.3235837519168854,
      "learning_rate": 4.705882352941177e-05,
      "loss": 0.8659,
      "step": 40
    },
    {
      "epoch": 2.4705882352941178,
      "grad_norm": 0.28911545872688293,
      "learning_rate": 4.9411764705882355e-05,
      "loss": 0.8688,
      "step": 42
    },
    {
      "epoch": 2.588235294117647,
      "grad_norm": 0.31285884976387024,
      "learning_rate": 5.176470588235295e-05,
      "loss": 0.8292,
      "step": 44
    },
    {
      "epoch": 2.7058823529411766,
      "grad_norm": 0.38900378346443176,
      "learning_rate": 5.411764705882353e-05,
      "loss": 0.8591,
      "step": 46
    },
    {
      "epoch": 2.8235294117647056,
      "grad_norm": 0.2806384861469269,
      "learning_rate": 5.647058823529412e-05,
      "loss": 0.8531,
      "step": 48
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 0.2884605824947357,
      "learning_rate": 5.882352941176471e-05,
      "loss": 0.8431,
      "step": 50
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.8753496408462524,
      "eval_runtime": 39.2618,
      "eval_samples_per_second": 0.917,
      "eval_steps_per_second": 0.917,
      "step": 51
    },
    {
      "epoch": 3.0588235294117645,
      "grad_norm": 0.24852576851844788,
      "learning_rate": 6.11764705882353e-05,
      "loss": 0.8292,
      "step": 52
    },
    {
      "epoch": 3.176470588235294,
      "grad_norm": 0.30960407853126526,
      "learning_rate": 6.352941176470588e-05,
      "loss": 0.7893,
      "step": 54
    },
    {
      "epoch": 3.2941176470588234,
      "grad_norm": 0.27496299147605896,
      "learning_rate": 6.588235294117648e-05,
      "loss": 0.8491,
      "step": 56
    },
    {
      "epoch": 3.411764705882353,
      "grad_norm": 0.3357207477092743,
      "learning_rate": 6.823529411764707e-05,
      "loss": 0.8077,
      "step": 58
    },
    {
      "epoch": 3.5294117647058822,
      "grad_norm": 0.2762078046798706,
      "learning_rate": 7.058823529411765e-05,
      "loss": 0.7715,
      "step": 60
    },
    {
      "epoch": 3.6470588235294117,
      "grad_norm": 0.3182898461818695,
      "learning_rate": 7.294117647058823e-05,
      "loss": 0.8552,
      "step": 62
    },
    {
      "epoch": 3.764705882352941,
      "grad_norm": 0.37789037823677063,
      "learning_rate": 7.529411764705883e-05,
      "loss": 0.7889,
      "step": 64
    },
    {
      "epoch": 3.8823529411764706,
      "grad_norm": 0.30749833583831787,
      "learning_rate": 7.764705882352942e-05,
      "loss": 0.779,
      "step": 66
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.3048383593559265,
      "learning_rate": 8e-05,
      "loss": 0.777,
      "step": 68
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.8566266298294067,
      "eval_runtime": 39.2693,
      "eval_samples_per_second": 0.917,
      "eval_steps_per_second": 0.917,
      "step": 68
    },
    {
      "epoch": 4.117647058823529,
      "grad_norm": 0.265333890914917,
      "learning_rate": 8.23529411764706e-05,
      "loss": 0.8258,
      "step": 70
    },
    {
      "epoch": 4.235294117647059,
      "grad_norm": 0.35155731439590454,
      "learning_rate": 8.470588235294118e-05,
      "loss": 0.7214,
      "step": 72
    },
    {
      "epoch": 4.352941176470588,
      "grad_norm": 0.33545365929603577,
      "learning_rate": 8.705882352941177e-05,
      "loss": 0.7831,
      "step": 74
    },
    {
      "epoch": 4.470588235294118,
      "grad_norm": 0.3298399746417999,
      "learning_rate": 8.941176470588236e-05,
      "loss": 0.73,
      "step": 76
    },
    {
      "epoch": 4.588235294117647,
      "grad_norm": 0.37279918789863586,
      "learning_rate": 9.176470588235295e-05,
      "loss": 0.7484,
      "step": 78
    },
    {
      "epoch": 4.705882352941177,
      "grad_norm": 0.34875956177711487,
      "learning_rate": 9.411764705882353e-05,
      "loss": 0.7775,
      "step": 80
    },
    {
      "epoch": 4.823529411764706,
      "grad_norm": 0.4093116223812103,
      "learning_rate": 9.647058823529412e-05,
      "loss": 0.7367,
      "step": 82
    },
    {
      "epoch": 4.9411764705882355,
      "grad_norm": 0.3761855661869049,
      "learning_rate": 9.882352941176471e-05,
      "loss": 0.7472,
      "step": 84
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.8535944819450378,
      "eval_runtime": 39.246,
      "eval_samples_per_second": 0.917,
      "eval_steps_per_second": 0.917,
      "step": 85
    },
    {
      "epoch": 5.0588235294117645,
      "grad_norm": 0.49026307463645935,
      "learning_rate": 9.99995783847866e-05,
      "loss": 0.6786,
      "step": 86
    },
    {
      "epoch": 5.176470588235294,
      "grad_norm": 0.4592975080013275,
      "learning_rate": 9.999620550574153e-05,
      "loss": 0.6761,
      "step": 88
    },
    {
      "epoch": 5.294117647058823,
      "grad_norm": 0.5038520693778992,
      "learning_rate": 9.998945997517956e-05,
      "loss": 0.717,
      "step": 90
    },
    {
      "epoch": 5.411764705882353,
      "grad_norm": 0.5567565560340881,
      "learning_rate": 9.997934224814173e-05,
      "loss": 0.7264,
      "step": 92
    },
    {
      "epoch": 5.529411764705882,
      "grad_norm": 0.4944419860839844,
      "learning_rate": 9.996585300715116e-05,
      "loss": 0.6856,
      "step": 94
    },
    {
      "epoch": 5.647058823529412,
      "grad_norm": 0.5155047178268433,
      "learning_rate": 9.994899316216708e-05,
      "loss": 0.6846,
      "step": 96
    },
    {
      "epoch": 5.764705882352941,
      "grad_norm": 0.540981113910675,
      "learning_rate": 9.992876385052345e-05,
      "loss": 0.6964,
      "step": 98
    },
    {
      "epoch": 5.882352941176471,
      "grad_norm": 0.5093909502029419,
      "learning_rate": 9.990516643685222e-05,
      "loss": 0.7093,
      "step": 100
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.5550987720489502,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.6439,
      "step": 102
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.8731997013092041,
      "eval_runtime": 39.6921,
      "eval_samples_per_second": 0.907,
      "eval_steps_per_second": 0.907,
      "step": 102
    },
    {
      "epoch": 6.117647058823529,
      "grad_norm": 0.5347613096237183,
      "learning_rate": 9.984787389787688e-05,
      "loss": 0.5958,
      "step": 104
    },
    {
      "epoch": 6.235294117647059,
      "grad_norm": 0.7279263138771057,
      "learning_rate": 9.981418263742148e-05,
      "loss": 0.5987,
      "step": 106
    },
    {
      "epoch": 6.352941176470588,
      "grad_norm": 0.7128389477729797,
      "learning_rate": 9.977713100437509e-05,
      "loss": 0.5529,
      "step": 108
    },
    {
      "epoch": 6.470588235294118,
      "grad_norm": 0.8643244504928589,
      "learning_rate": 9.973672149817232e-05,
      "loss": 0.6111,
      "step": 110
    },
    {
      "epoch": 6.588235294117647,
      "grad_norm": 0.7364321947097778,
      "learning_rate": 9.96929568447637e-05,
      "loss": 0.5764,
      "step": 112
    },
    {
      "epoch": 6.705882352941177,
      "grad_norm": 0.6547777056694031,
      "learning_rate": 9.964583999643174e-05,
      "loss": 0.6471,
      "step": 114
    },
    {
      "epoch": 6.823529411764706,
      "grad_norm": 0.6347489953041077,
      "learning_rate": 9.95953741315919e-05,
      "loss": 0.6507,
      "step": 116
    },
    {
      "epoch": 6.9411764705882355,
      "grad_norm": 0.682847261428833,
      "learning_rate": 9.954156265457801e-05,
      "loss": 0.6021,
      "step": 118
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.8924597501754761,
      "eval_runtime": 39.6888,
      "eval_samples_per_second": 0.907,
      "eval_steps_per_second": 0.907,
      "step": 119
    },
    {
      "epoch": 7.0588235294117645,
      "grad_norm": 0.7113699913024902,
      "learning_rate": 9.948440919541278e-05,
      "loss": 0.5745,
      "step": 120
    },
    {
      "epoch": 7.176470588235294,
      "grad_norm": 1.007275104522705,
      "learning_rate": 9.942391760956277e-05,
      "loss": 0.5183,
      "step": 122
    },
    {
      "epoch": 7.294117647058823,
      "grad_norm": 0.891048789024353,
      "learning_rate": 9.936009197767845e-05,
      "loss": 0.5167,
      "step": 124
    },
    {
      "epoch": 7.411764705882353,
      "grad_norm": 0.8606879115104675,
      "learning_rate": 9.929293660531888e-05,
      "loss": 0.4857,
      "step": 126
    },
    {
      "epoch": 7.529411764705882,
      "grad_norm": 0.8929439187049866,
      "learning_rate": 9.922245602266118e-05,
      "loss": 0.4976,
      "step": 128
    },
    {
      "epoch": 7.647058823529412,
      "grad_norm": 1.078784704208374,
      "learning_rate": 9.91486549841951e-05,
      "loss": 0.5303,
      "step": 130
    },
    {
      "epoch": 7.764705882352941,
      "grad_norm": 1.2825535535812378,
      "learning_rate": 9.90715384684021e-05,
      "loss": 0.4733,
      "step": 132
    },
    {
      "epoch": 7.882352941176471,
      "grad_norm": 1.2167457342147827,
      "learning_rate": 9.899111167741966e-05,
      "loss": 0.5633,
      "step": 134
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.8761590123176575,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.4804,
      "step": 136
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.9462372660636902,
      "eval_runtime": 39.2558,
      "eval_samples_per_second": 0.917,
      "eval_steps_per_second": 0.917,
      "step": 136
    },
    {
      "epoch": 8.117647058823529,
      "grad_norm": 0.8890438079833984,
      "learning_rate": 9.882034919459555e-05,
      "loss": 0.4116,
      "step": 138
    },
    {
      "epoch": 8.235294117647058,
      "grad_norm": 1.226324439048767,
      "learning_rate": 9.873002502207503e-05,
      "loss": 0.4069,
      "step": 140
    },
    {
      "epoch": 8.352941176470589,
      "grad_norm": 0.9295585751533508,
      "learning_rate": 9.863641361223024e-05,
      "loss": 0.4283,
      "step": 142
    },
    {
      "epoch": 8.470588235294118,
      "grad_norm": 1.0363649129867554,
      "learning_rate": 9.853952127991372e-05,
      "loss": 0.4398,
      "step": 144
    },
    {
      "epoch": 8.588235294117647,
      "grad_norm": 1.0597994327545166,
      "learning_rate": 9.843935456130295e-05,
      "loss": 0.462,
      "step": 146
    },
    {
      "epoch": 8.705882352941176,
      "grad_norm": 1.2128883600234985,
      "learning_rate": 9.833592021345937e-05,
      "loss": 0.4501,
      "step": 148
    },
    {
      "epoch": 8.823529411764707,
      "grad_norm": 0.9421849846839905,
      "learning_rate": 9.822922521387276e-05,
      "loss": 0.3946,
      "step": 150
    },
    {
      "epoch": 8.941176470588236,
      "grad_norm": 0.9474720358848572,
      "learning_rate": 9.811927675999036e-05,
      "loss": 0.387,
      "step": 152
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.9822432398796082,
      "eval_runtime": 39.2609,
      "eval_samples_per_second": 0.917,
      "eval_steps_per_second": 0.917,
      "step": 153
    },
    {
      "epoch": 9.058823529411764,
      "grad_norm": 0.8546085357666016,
      "learning_rate": 9.800608226873142e-05,
      "loss": 0.4075,
      "step": 154
    },
    {
      "epoch": 9.176470588235293,
      "grad_norm": 1.0153013467788696,
      "learning_rate": 9.788964937598689e-05,
      "loss": 0.3345,
      "step": 156
    },
    {
      "epoch": 9.294117647058824,
      "grad_norm": 1.4712640047073364,
      "learning_rate": 9.776998593610428e-05,
      "loss": 0.3438,
      "step": 158
    },
    {
      "epoch": 9.411764705882353,
      "grad_norm": 0.9602189660072327,
      "learning_rate": 9.764710002135784e-05,
      "loss": 0.3503,
      "step": 160
    },
    {
      "epoch": 9.529411764705882,
      "grad_norm": 0.9028332233428955,
      "learning_rate": 9.752099992140399e-05,
      "loss": 0.3387,
      "step": 162
    },
    {
      "epoch": 9.647058823529411,
      "grad_norm": 0.9782208204269409,
      "learning_rate": 9.739169414272217e-05,
      "loss": 0.3506,
      "step": 164
    },
    {
      "epoch": 9.764705882352942,
      "grad_norm": 1.2242997884750366,
      "learning_rate": 9.725919140804099e-05,
      "loss": 0.3644,
      "step": 166
    },
    {
      "epoch": 9.882352941176471,
      "grad_norm": 0.9222318530082703,
      "learning_rate": 9.71235006557497e-05,
      "loss": 0.2964,
      "step": 168
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.9740263223648071,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.3473,
      "step": 170
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.0299735069274902,
      "eval_runtime": 39.2424,
      "eval_samples_per_second": 0.917,
      "eval_steps_per_second": 0.917,
      "step": 170
    },
    {
      "epoch": 10.117647058823529,
      "grad_norm": 0.8984984159469604,
      "learning_rate": 9.684259192656553e-05,
      "loss": 0.2512,
      "step": 172
    },
    {
      "epoch": 10.235294117647058,
      "grad_norm": 1.6402689218521118,
      "learning_rate": 9.669739289925577e-05,
      "loss": 0.2714,
      "step": 174
    },
    {
      "epoch": 10.352941176470589,
      "grad_norm": 1.1548532247543335,
      "learning_rate": 9.654904375222385e-05,
      "loss": 0.3002,
      "step": 176
    },
    {
      "epoch": 10.470588235294118,
      "grad_norm": 0.9068163633346558,
      "learning_rate": 9.639755449282875e-05,
      "loss": 0.2501,
      "step": 178
    },
    {
      "epoch": 10.588235294117647,
      "grad_norm": 0.9034165740013123,
      "learning_rate": 9.62429353402556e-05,
      "loss": 0.2905,
      "step": 180
    },
    {
      "epoch": 10.705882352941176,
      "grad_norm": 1.0328618288040161,
      "learning_rate": 9.608519672482636e-05,
      "loss": 0.2594,
      "step": 182
    },
    {
      "epoch": 10.823529411764707,
      "grad_norm": 0.9995335936546326,
      "learning_rate": 9.592434928729616e-05,
      "loss": 0.2863,
      "step": 184
    },
    {
      "epoch": 10.941176470588236,
      "grad_norm": 1.099188208580017,
      "learning_rate": 9.576040387813552e-05,
      "loss": 0.2927,
      "step": 186
    },
    {
      "epoch": 11.0,
      "eval_loss": 1.0959703922271729,
      "eval_runtime": 39.2464,
      "eval_samples_per_second": 0.917,
      "eval_steps_per_second": 0.917,
      "step": 187
    },
    {
      "epoch": 11.058823529411764,
      "grad_norm": 0.8442018628120422,
      "learning_rate": 9.559337155679842e-05,
      "loss": 0.2627,
      "step": 188
    },
    {
      "epoch": 11.176470588235293,
      "grad_norm": 0.8898816108703613,
      "learning_rate": 9.542326359097619e-05,
      "loss": 0.2173,
      "step": 190
    },
    {
      "epoch": 11.294117647058824,
      "grad_norm": 1.1321330070495605,
      "learning_rate": 9.525009145583745e-05,
      "loss": 0.2462,
      "step": 192
    },
    {
      "epoch": 11.411764705882353,
      "grad_norm": 1.0442326068878174,
      "learning_rate": 9.507386683325404e-05,
      "loss": 0.1592,
      "step": 194
    },
    {
      "epoch": 11.529411764705882,
      "grad_norm": 0.9421147108078003,
      "learning_rate": 9.489460161101291e-05,
      "loss": 0.2396,
      "step": 196
    },
    {
      "epoch": 11.647058823529411,
      "grad_norm": 1.037330985069275,
      "learning_rate": 9.471230788201429e-05,
      "loss": 0.2216,
      "step": 198
    },
    {
      "epoch": 11.764705882352942,
      "grad_norm": 1.0113916397094727,
      "learning_rate": 9.452699794345581e-05,
      "loss": 0.2243,
      "step": 200
    },
    {
      "epoch": 11.882352941176471,
      "grad_norm": 1.1335500478744507,
      "learning_rate": 9.43386842960031e-05,
      "loss": 0.2156,
      "step": 202
    },
    {
      "epoch": 12.0,
      "grad_norm": 1.0136862993240356,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.1918,
      "step": 204
    },
    {
      "epoch": 12.0,
      "eval_loss": 1.1832014322280884,
      "eval_runtime": 39.2459,
      "eval_samples_per_second": 0.917,
      "eval_steps_per_second": 0.917,
      "step": 204
    },
    {
      "epoch": 12.0,
      "step": 204,
      "total_flos": 1.6007026687187354e+17,
      "train_loss": 0.6416382959076002,
      "train_runtime": 5941.4459,
      "train_samples_per_second": 1.145,
      "train_steps_per_second": 0.143
    }
  ],
  "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": 1.6007026687187354e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}