{
  "best_metric": 0.8618482947349548,
  "best_model_checkpoint": "data/Mistral-7B_task-3_180-samples_config-1_full/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": 1.0328681468963623,
      "learning_rate": 1.1764705882352942e-06,
      "loss": 1.2342,
      "step": 1
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 1.1054006814956665,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 1.2937,
      "step": 2
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 1.2496098279953003,
      "learning_rate": 4.705882352941177e-06,
      "loss": 1.2794,
      "step": 4
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 1.1380996704101562,
      "learning_rate": 7.058823529411765e-06,
      "loss": 1.298,
      "step": 6
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.9065995812416077,
      "learning_rate": 9.411764705882354e-06,
      "loss": 1.2421,
      "step": 8
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 0.7735101580619812,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.1975,
      "step": 10
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 0.7356392741203308,
      "learning_rate": 1.411764705882353e-05,
      "loss": 1.1687,
      "step": 12
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 0.729520320892334,
      "learning_rate": 1.647058823529412e-05,
      "loss": 1.1902,
      "step": 14
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.5356112122535706,
      "learning_rate": 1.8823529411764708e-05,
      "loss": 1.15,
      "step": 16
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.1231297254562378,
      "eval_runtime": 39.0656,
      "eval_samples_per_second": 0.922,
      "eval_steps_per_second": 0.922,
      "step": 17
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 0.46936744451522827,
      "learning_rate": 2.1176470588235296e-05,
      "loss": 1.1338,
      "step": 18
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.3670711815357208,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 1.1263,
      "step": 20
    },
    {
      "epoch": 1.2941176470588236,
      "grad_norm": 0.3451801836490631,
      "learning_rate": 2.5882352941176475e-05,
      "loss": 1.0767,
      "step": 22
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 0.35216888785362244,
      "learning_rate": 2.823529411764706e-05,
      "loss": 1.0429,
      "step": 24
    },
    {
      "epoch": 1.5294117647058822,
      "grad_norm": 0.3135659694671631,
      "learning_rate": 3.058823529411765e-05,
      "loss": 1.0308,
      "step": 26
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 0.3610193431377411,
      "learning_rate": 3.294117647058824e-05,
      "loss": 1.0184,
      "step": 28
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 0.4803563952445984,
      "learning_rate": 3.529411764705883e-05,
      "loss": 1.017,
      "step": 30
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 0.5359921455383301,
      "learning_rate": 3.7647058823529415e-05,
      "loss": 0.97,
      "step": 32
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5332412123680115,
      "learning_rate": 4e-05,
      "loss": 0.9609,
      "step": 34
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.9486725926399231,
      "eval_runtime": 39.0655,
      "eval_samples_per_second": 0.922,
      "eval_steps_per_second": 0.922,
      "step": 34
    },
    {
      "epoch": 2.1176470588235294,
      "grad_norm": 0.4894848167896271,
      "learning_rate": 4.235294117647059e-05,
      "loss": 0.9046,
      "step": 36
    },
    {
      "epoch": 2.235294117647059,
      "grad_norm": 0.33591827750205994,
      "learning_rate": 4.470588235294118e-05,
      "loss": 0.8824,
      "step": 38
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 0.3120097219944,
      "learning_rate": 4.705882352941177e-05,
      "loss": 0.8758,
      "step": 40
    },
    {
      "epoch": 2.4705882352941178,
      "grad_norm": 0.29227712750434875,
      "learning_rate": 4.9411764705882355e-05,
      "loss": 0.8759,
      "step": 42
    },
    {
      "epoch": 2.588235294117647,
      "grad_norm": 0.29439777135849,
      "learning_rate": 5.176470588235295e-05,
      "loss": 0.8422,
      "step": 44
    },
    {
      "epoch": 2.7058823529411766,
      "grad_norm": 0.36776840686798096,
      "learning_rate": 5.411764705882353e-05,
      "loss": 0.8729,
      "step": 46
    },
    {
      "epoch": 2.8235294117647056,
      "grad_norm": 0.2653949558734894,
      "learning_rate": 5.647058823529412e-05,
      "loss": 0.8629,
      "step": 48
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 0.28814321756362915,
      "learning_rate": 5.882352941176471e-05,
      "loss": 0.8559,
      "step": 50
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.8849623799324036,
      "eval_runtime": 39.0555,
      "eval_samples_per_second": 0.922,
      "eval_steps_per_second": 0.922,
      "step": 51
    },
    {
      "epoch": 3.0588235294117645,
      "grad_norm": 0.2426621913909912,
      "learning_rate": 6.11764705882353e-05,
      "loss": 0.8382,
      "step": 52
    },
    {
      "epoch": 3.176470588235294,
      "grad_norm": 0.259878933429718,
      "learning_rate": 6.352941176470588e-05,
      "loss": 0.8088,
      "step": 54
    },
    {
      "epoch": 3.2941176470588234,
      "grad_norm": 0.2670765221118927,
      "learning_rate": 6.588235294117648e-05,
      "loss": 0.8606,
      "step": 56
    },
    {
      "epoch": 3.411764705882353,
      "grad_norm": 0.29115286469459534,
      "learning_rate": 6.823529411764707e-05,
      "loss": 0.8211,
      "step": 58
    },
    {
      "epoch": 3.5294117647058822,
      "grad_norm": 0.2846333086490631,
      "learning_rate": 7.058823529411765e-05,
      "loss": 0.773,
      "step": 60
    },
    {
      "epoch": 3.6470588235294117,
      "grad_norm": 0.25920745730400085,
      "learning_rate": 7.294117647058823e-05,
      "loss": 0.863,
      "step": 62
    },
    {
      "epoch": 3.764705882352941,
      "grad_norm": 0.39433133602142334,
      "learning_rate": 7.529411764705883e-05,
      "loss": 0.8069,
      "step": 64
    },
    {
      "epoch": 3.8823529411764706,
      "grad_norm": 0.3108396828174591,
      "learning_rate": 7.764705882352942e-05,
      "loss": 0.7832,
      "step": 66
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.30900299549102783,
      "learning_rate": 8e-05,
      "loss": 0.7818,
      "step": 68
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.8655229210853577,
      "eval_runtime": 39.0651,
      "eval_samples_per_second": 0.922,
      "eval_steps_per_second": 0.922,
      "step": 68
    },
    {
      "epoch": 4.117647058823529,
      "grad_norm": 0.26082897186279297,
      "learning_rate": 8.23529411764706e-05,
      "loss": 0.833,
      "step": 70
    },
    {
      "epoch": 4.235294117647059,
      "grad_norm": 0.32163888216018677,
      "learning_rate": 8.470588235294118e-05,
      "loss": 0.7347,
      "step": 72
    },
    {
      "epoch": 4.352941176470588,
      "grad_norm": 0.32568153738975525,
      "learning_rate": 8.705882352941177e-05,
      "loss": 0.8005,
      "step": 74
    },
    {
      "epoch": 4.470588235294118,
      "grad_norm": 0.336098849773407,
      "learning_rate": 8.941176470588236e-05,
      "loss": 0.7377,
      "step": 76
    },
    {
      "epoch": 4.588235294117647,
      "grad_norm": 0.37323132157325745,
      "learning_rate": 9.176470588235295e-05,
      "loss": 0.7613,
      "step": 78
    },
    {
      "epoch": 4.705882352941177,
      "grad_norm": 0.3612486720085144,
      "learning_rate": 9.411764705882353e-05,
      "loss": 0.7825,
      "step": 80
    },
    {
      "epoch": 4.823529411764706,
      "grad_norm": 0.40557822585105896,
      "learning_rate": 9.647058823529412e-05,
      "loss": 0.744,
      "step": 82
    },
    {
      "epoch": 4.9411764705882355,
      "grad_norm": 0.3747648596763611,
      "learning_rate": 9.882352941176471e-05,
      "loss": 0.7523,
      "step": 84
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.8618482947349548,
      "eval_runtime": 39.0553,
      "eval_samples_per_second": 0.922,
      "eval_steps_per_second": 0.922,
      "step": 85
    },
    {
      "epoch": 5.0588235294117645,
      "grad_norm": 0.5036694407463074,
      "learning_rate": 9.99995783847866e-05,
      "loss": 0.6883,
      "step": 86
    },
    {
      "epoch": 5.176470588235294,
      "grad_norm": 0.4829659163951874,
      "learning_rate": 9.999620550574153e-05,
      "loss": 0.6848,
      "step": 88
    },
    {
      "epoch": 5.294117647058823,
      "grad_norm": 0.5315528512001038,
      "learning_rate": 9.998945997517956e-05,
      "loss": 0.7278,
      "step": 90
    },
    {
      "epoch": 5.411764705882353,
      "grad_norm": 0.6527894139289856,
      "learning_rate": 9.997934224814173e-05,
      "loss": 0.7326,
      "step": 92
    },
    {
      "epoch": 5.529411764705882,
      "grad_norm": 0.49610406160354614,
      "learning_rate": 9.996585300715116e-05,
      "loss": 0.6946,
      "step": 94
    },
    {
      "epoch": 5.647058823529412,
      "grad_norm": 0.5373050570487976,
      "learning_rate": 9.994899316216708e-05,
      "loss": 0.6896,
      "step": 96
    },
    {
      "epoch": 5.764705882352941,
      "grad_norm": 0.5481564998626709,
      "learning_rate": 9.992876385052345e-05,
      "loss": 0.7081,
      "step": 98
    },
    {
      "epoch": 5.882352941176471,
      "grad_norm": 0.5010173320770264,
      "learning_rate": 9.990516643685222e-05,
      "loss": 0.7197,
      "step": 100
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.6040236353874207,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.6583,
      "step": 102
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.8815975785255432,
      "eval_runtime": 39.0542,
      "eval_samples_per_second": 0.922,
      "eval_steps_per_second": 0.922,
      "step": 102
    },
    {
      "epoch": 6.117647058823529,
      "grad_norm": 0.5185869336128235,
      "learning_rate": 9.984787389787688e-05,
      "loss": 0.6024,
      "step": 104
    },
    {
      "epoch": 6.235294117647059,
      "grad_norm": 0.7614925503730774,
      "learning_rate": 9.981418263742148e-05,
      "loss": 0.6097,
      "step": 106
    },
    {
      "epoch": 6.352941176470588,
      "grad_norm": 0.696563720703125,
      "learning_rate": 9.977713100437509e-05,
      "loss": 0.5618,
      "step": 108
    },
    {
      "epoch": 6.470588235294118,
      "grad_norm": 0.8105670809745789,
      "learning_rate": 9.973672149817232e-05,
      "loss": 0.6194,
      "step": 110
    },
    {
      "epoch": 6.588235294117647,
      "grad_norm": 0.6536702513694763,
      "learning_rate": 9.96929568447637e-05,
      "loss": 0.5839,
      "step": 112
    },
    {
      "epoch": 6.705882352941177,
      "grad_norm": 0.6501868367195129,
      "learning_rate": 9.964583999643174e-05,
      "loss": 0.6535,
      "step": 114
    },
    {
      "epoch": 6.823529411764706,
      "grad_norm": 0.6075993180274963,
      "learning_rate": 9.95953741315919e-05,
      "loss": 0.6579,
      "step": 116
    },
    {
      "epoch": 6.9411764705882355,
      "grad_norm": 0.6628342866897583,
      "learning_rate": 9.954156265457801e-05,
      "loss": 0.6114,
      "step": 118
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.9061512351036072,
      "eval_runtime": 39.1065,
      "eval_samples_per_second": 0.921,
      "eval_steps_per_second": 0.921,
      "step": 119
    },
    {
      "epoch": 7.0588235294117645,
      "grad_norm": 0.7474973797798157,
      "learning_rate": 9.948440919541278e-05,
      "loss": 0.5799,
      "step": 120
    },
    {
      "epoch": 7.176470588235294,
      "grad_norm": 1.4596823453903198,
      "learning_rate": 9.942391760956277e-05,
      "loss": 0.5236,
      "step": 122
    },
    {
      "epoch": 7.294117647058823,
      "grad_norm": 0.7749144434928894,
      "learning_rate": 9.936009197767845e-05,
      "loss": 0.5175,
      "step": 124
    },
    {
      "epoch": 7.411764705882353,
      "grad_norm": 0.7761390805244446,
      "learning_rate": 9.929293660531888e-05,
      "loss": 0.4892,
      "step": 126
    },
    {
      "epoch": 7.529411764705882,
      "grad_norm": 1.2808239459991455,
      "learning_rate": 9.922245602266118e-05,
      "loss": 0.5032,
      "step": 128
    },
    {
      "epoch": 7.647058823529412,
      "grad_norm": 1.1731969118118286,
      "learning_rate": 9.91486549841951e-05,
      "loss": 0.5334,
      "step": 130
    },
    {
      "epoch": 7.764705882352941,
      "grad_norm": 0.9404990673065186,
      "learning_rate": 9.90715384684021e-05,
      "loss": 0.4766,
      "step": 132
    },
    {
      "epoch": 7.882352941176471,
      "grad_norm": 0.9003025889396667,
      "learning_rate": 9.899111167741966e-05,
      "loss": 0.5667,
      "step": 134
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.8581990599632263,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.4904,
      "step": 136
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.9384950995445251,
      "eval_runtime": 39.1126,
      "eval_samples_per_second": 0.92,
      "eval_steps_per_second": 0.92,
      "step": 136
    },
    {
      "epoch": 8.117647058823529,
      "grad_norm": 0.8830170035362244,
      "learning_rate": 9.882034919459555e-05,
      "loss": 0.4202,
      "step": 138
    },
    {
      "epoch": 8.235294117647058,
      "grad_norm": 1.2202011346817017,
      "learning_rate": 9.873002502207503e-05,
      "loss": 0.4041,
      "step": 140
    },
    {
      "epoch": 8.352941176470589,
      "grad_norm": 1.0072306394577026,
      "learning_rate": 9.863641361223024e-05,
      "loss": 0.4458,
      "step": 142
    },
    {
      "epoch": 8.470588235294118,
      "grad_norm": 0.9022138714790344,
      "learning_rate": 9.853952127991372e-05,
      "loss": 0.4421,
      "step": 144
    },
    {
      "epoch": 8.588235294117647,
      "grad_norm": 1.0054612159729004,
      "learning_rate": 9.843935456130295e-05,
      "loss": 0.4649,
      "step": 146
    },
    {
      "epoch": 8.705882352941176,
      "grad_norm": 1.1033481359481812,
      "learning_rate": 9.833592021345937e-05,
      "loss": 0.4509,
      "step": 148
    },
    {
      "epoch": 8.823529411764707,
      "grad_norm": 0.9894391298294067,
      "learning_rate": 9.822922521387276e-05,
      "loss": 0.403,
      "step": 150
    },
    {
      "epoch": 8.941176470588236,
      "grad_norm": 1.0071293115615845,
      "learning_rate": 9.811927675999036e-05,
      "loss": 0.396,
      "step": 152
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.002908706665039,
      "eval_runtime": 39.1131,
      "eval_samples_per_second": 0.92,
      "eval_steps_per_second": 0.92,
      "step": 153
    },
    {
      "epoch": 9.058823529411764,
      "grad_norm": 0.9654635190963745,
      "learning_rate": 9.800608226873142e-05,
      "loss": 0.4014,
      "step": 154
    },
    {
      "epoch": 9.176470588235293,
      "grad_norm": 1.223938226699829,
      "learning_rate": 9.788964937598689e-05,
      "loss": 0.3368,
      "step": 156
    },
    {
      "epoch": 9.294117647058824,
      "grad_norm": 1.0533758401870728,
      "learning_rate": 9.776998593610428e-05,
      "loss": 0.343,
      "step": 158
    },
    {
      "epoch": 9.411764705882353,
      "grad_norm": 1.0411851406097412,
      "learning_rate": 9.764710002135784e-05,
      "loss": 0.3608,
      "step": 160
    },
    {
      "epoch": 9.529411764705882,
      "grad_norm": 0.8981650471687317,
      "learning_rate": 9.752099992140399e-05,
      "loss": 0.3457,
      "step": 162
    },
    {
      "epoch": 9.647058823529411,
      "grad_norm": 1.113479495048523,
      "learning_rate": 9.739169414272217e-05,
      "loss": 0.3596,
      "step": 164
    },
    {
      "epoch": 9.764705882352942,
      "grad_norm": 1.1335539817810059,
      "learning_rate": 9.725919140804099e-05,
      "loss": 0.3671,
      "step": 166
    },
    {
      "epoch": 9.882352941176471,
      "grad_norm": 0.9517225027084351,
      "learning_rate": 9.71235006557497e-05,
      "loss": 0.2981,
      "step": 168
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.9978011250495911,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.3441,
      "step": 170
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.0624499320983887,
      "eval_runtime": 39.0542,
      "eval_samples_per_second": 0.922,
      "eval_steps_per_second": 0.922,
      "step": 170
    },
    {
      "epoch": 10.117647058823529,
      "grad_norm": 0.9326748847961426,
      "learning_rate": 9.684259192656553e-05,
      "loss": 0.2472,
      "step": 172
    },
    {
      "epoch": 10.235294117647058,
      "grad_norm": 1.5413657426834106,
      "learning_rate": 9.669739289925577e-05,
      "loss": 0.2742,
      "step": 174
    },
    {
      "epoch": 10.352941176470589,
      "grad_norm": 1.0099854469299316,
      "learning_rate": 9.654904375222385e-05,
      "loss": 0.2968,
      "step": 176
    },
    {
      "epoch": 10.470588235294118,
      "grad_norm": 0.9316913485527039,
      "learning_rate": 9.639755449282875e-05,
      "loss": 0.2512,
      "step": 178
    },
    {
      "epoch": 10.588235294117647,
      "grad_norm": 1.0400867462158203,
      "learning_rate": 9.62429353402556e-05,
      "loss": 0.2883,
      "step": 180
    },
    {
      "epoch": 10.705882352941176,
      "grad_norm": 1.0210511684417725,
      "learning_rate": 9.608519672482636e-05,
      "loss": 0.2599,
      "step": 182
    },
    {
      "epoch": 10.823529411764707,
      "grad_norm": 0.8698815107345581,
      "learning_rate": 9.592434928729616e-05,
      "loss": 0.2865,
      "step": 184
    },
    {
      "epoch": 10.941176470588236,
      "grad_norm": 1.144648790359497,
      "learning_rate": 9.576040387813552e-05,
      "loss": 0.3021,
      "step": 186
    },
    {
      "epoch": 11.0,
      "eval_loss": 1.1177419424057007,
      "eval_runtime": 39.056,
      "eval_samples_per_second": 0.922,
      "eval_steps_per_second": 0.922,
      "step": 187
    },
    {
      "epoch": 11.058823529411764,
      "grad_norm": 0.873058021068573,
      "learning_rate": 9.559337155679842e-05,
      "loss": 0.2612,
      "step": 188
    },
    {
      "epoch": 11.176470588235293,
      "grad_norm": 1.33427095413208,
      "learning_rate": 9.542326359097619e-05,
      "loss": 0.2186,
      "step": 190
    },
    {
      "epoch": 11.294117647058824,
      "grad_norm": 1.1905710697174072,
      "learning_rate": 9.525009145583745e-05,
      "loss": 0.2553,
      "step": 192
    },
    {
      "epoch": 11.411764705882353,
      "grad_norm": 0.8156754970550537,
      "learning_rate": 9.507386683325404e-05,
      "loss": 0.158,
      "step": 194
    },
    {
      "epoch": 11.529411764705882,
      "grad_norm": 0.9430420398712158,
      "learning_rate": 9.489460161101291e-05,
      "loss": 0.2475,
      "step": 196
    },
    {
      "epoch": 11.647058823529411,
      "grad_norm": 1.1319944858551025,
      "learning_rate": 9.471230788201429e-05,
      "loss": 0.2209,
      "step": 198
    },
    {
      "epoch": 11.764705882352942,
      "grad_norm": 1.0557358264923096,
      "learning_rate": 9.452699794345581e-05,
      "loss": 0.2232,
      "step": 200
    },
    {
      "epoch": 11.882352941176471,
      "grad_norm": 1.0566904544830322,
      "learning_rate": 9.43386842960031e-05,
      "loss": 0.2172,
      "step": 202
    },
    {
      "epoch": 12.0,
      "grad_norm": 1.0422923564910889,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.1931,
      "step": 204
    },
    {
      "epoch": 12.0,
      "eval_loss": 1.162467360496521,
      "eval_runtime": 39.0604,
      "eval_samples_per_second": 0.922,
      "eval_steps_per_second": 0.922,
      "step": 204
    },
    {
      "epoch": 12.0,
      "step": 204,
      "total_flos": 1.5906559966471782e+17,
      "train_loss": 0.6499113799894557,
      "train_runtime": 5899.8648,
      "train_samples_per_second": 1.153,
      "train_steps_per_second": 0.144
    }
  ],
  "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": 1.5906559966471782e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}