{
  "best_metric": 0.5395250916481018,
  "best_model_checkpoint": "data/Mistral-7B_task-2_180-samples_config-1/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": 2.5286571979522705,
      "learning_rate": 1.1764705882352942e-06,
      "loss": 1.0178,
      "step": 1
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 2.3744826316833496,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 1.0661,
      "step": 2
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 3.055227041244507,
      "learning_rate": 4.705882352941177e-06,
      "loss": 1.0937,
      "step": 4
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 2.71893572807312,
      "learning_rate": 7.058823529411765e-06,
      "loss": 1.0652,
      "step": 6
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 2.3261265754699707,
      "learning_rate": 9.411764705882354e-06,
      "loss": 0.9794,
      "step": 8
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 1.9898451566696167,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 0.9443,
      "step": 10
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 1.6569874286651611,
      "learning_rate": 1.411764705882353e-05,
      "loss": 0.8305,
      "step": 12
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 1.4791032075881958,
      "learning_rate": 1.647058823529412e-05,
      "loss": 0.8637,
      "step": 14
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 1.545494794845581,
      "learning_rate": 1.8823529411764708e-05,
      "loss": 0.6925,
      "step": 16
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.7248361706733704,
      "eval_runtime": 45.6396,
      "eval_samples_per_second": 0.789,
      "eval_steps_per_second": 0.789,
      "step": 17
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 0.9634544849395752,
      "learning_rate": 2.1176470588235296e-05,
      "loss": 0.7559,
      "step": 18
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.7148199677467346,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 0.7022,
      "step": 20
    },
    {
      "epoch": 1.2941176470588236,
      "grad_norm": 0.6760066747665405,
      "learning_rate": 2.5882352941176475e-05,
      "loss": 0.6634,
      "step": 22
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 0.6285112500190735,
      "learning_rate": 2.823529411764706e-05,
      "loss": 0.6419,
      "step": 24
    },
    {
      "epoch": 1.5294117647058822,
      "grad_norm": 0.5825430154800415,
      "learning_rate": 3.058823529411765e-05,
      "loss": 0.5883,
      "step": 26
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 0.5539379715919495,
      "learning_rate": 3.294117647058824e-05,
      "loss": 0.6007,
      "step": 28
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 0.8018637895584106,
      "learning_rate": 3.529411764705883e-05,
      "loss": 0.6572,
      "step": 30
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 0.555174708366394,
      "learning_rate": 3.7647058823529415e-05,
      "loss": 0.5679,
      "step": 32
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5744386911392212,
      "learning_rate": 4e-05,
      "loss": 0.6328,
      "step": 34
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6001158356666565,
      "eval_runtime": 45.6376,
      "eval_samples_per_second": 0.789,
      "eval_steps_per_second": 0.789,
      "step": 34
    },
    {
      "epoch": 2.1176470588235294,
      "grad_norm": 0.569065272808075,
      "learning_rate": 4.235294117647059e-05,
      "loss": 0.569,
      "step": 36
    },
    {
      "epoch": 2.235294117647059,
      "grad_norm": 0.46159255504608154,
      "learning_rate": 4.470588235294118e-05,
      "loss": 0.5554,
      "step": 38
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 0.4986919164657593,
      "learning_rate": 4.705882352941177e-05,
      "loss": 0.5,
      "step": 40
    },
    {
      "epoch": 2.4705882352941178,
      "grad_norm": 0.5344809889793396,
      "learning_rate": 4.9411764705882355e-05,
      "loss": 0.548,
      "step": 42
    },
    {
      "epoch": 2.588235294117647,
      "grad_norm": 0.5360327363014221,
      "learning_rate": 5.176470588235295e-05,
      "loss": 0.5404,
      "step": 44
    },
    {
      "epoch": 2.7058823529411766,
      "grad_norm": 0.6767789125442505,
      "learning_rate": 5.411764705882353e-05,
      "loss": 0.5502,
      "step": 46
    },
    {
      "epoch": 2.8235294117647056,
      "grad_norm": 0.5001493692398071,
      "learning_rate": 5.647058823529412e-05,
      "loss": 0.5447,
      "step": 48
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 0.6502465605735779,
      "learning_rate": 5.882352941176471e-05,
      "loss": 0.5326,
      "step": 50
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5514732003211975,
      "eval_runtime": 45.6373,
      "eval_samples_per_second": 0.789,
      "eval_steps_per_second": 0.789,
      "step": 51
    },
    {
      "epoch": 3.0588235294117645,
      "grad_norm": 0.5305119156837463,
      "learning_rate": 6.11764705882353e-05,
      "loss": 0.4911,
      "step": 52
    },
    {
      "epoch": 3.176470588235294,
      "grad_norm": 0.5339085459709167,
      "learning_rate": 6.352941176470588e-05,
      "loss": 0.485,
      "step": 54
    },
    {
      "epoch": 3.2941176470588234,
      "grad_norm": 0.5168776512145996,
      "learning_rate": 6.588235294117648e-05,
      "loss": 0.4702,
      "step": 56
    },
    {
      "epoch": 3.411764705882353,
      "grad_norm": 0.6228866577148438,
      "learning_rate": 6.823529411764707e-05,
      "loss": 0.5102,
      "step": 58
    },
    {
      "epoch": 3.5294117647058822,
      "grad_norm": 0.6762785911560059,
      "learning_rate": 7.058823529411765e-05,
      "loss": 0.4403,
      "step": 60
    },
    {
      "epoch": 3.6470588235294117,
      "grad_norm": 0.6562156081199646,
      "learning_rate": 7.294117647058823e-05,
      "loss": 0.4807,
      "step": 62
    },
    {
      "epoch": 3.764705882352941,
      "grad_norm": 0.8110491633415222,
      "learning_rate": 7.529411764705883e-05,
      "loss": 0.4323,
      "step": 64
    },
    {
      "epoch": 3.8823529411764706,
      "grad_norm": 0.7151264548301697,
      "learning_rate": 7.764705882352942e-05,
      "loss": 0.4448,
      "step": 66
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.9353557229042053,
      "learning_rate": 8e-05,
      "loss": 0.3885,
      "step": 68
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.5395250916481018,
      "eval_runtime": 45.7032,
      "eval_samples_per_second": 0.788,
      "eval_steps_per_second": 0.788,
      "step": 68
    },
    {
      "epoch": 4.117647058823529,
      "grad_norm": 0.7566824555397034,
      "learning_rate": 8.23529411764706e-05,
      "loss": 0.4164,
      "step": 70
    },
    {
      "epoch": 4.235294117647059,
      "grad_norm": 0.729512095451355,
      "learning_rate": 8.470588235294118e-05,
      "loss": 0.3405,
      "step": 72
    },
    {
      "epoch": 4.352941176470588,
      "grad_norm": 0.8966187238693237,
      "learning_rate": 8.705882352941177e-05,
      "loss": 0.3548,
      "step": 74
    },
    {
      "epoch": 4.470588235294118,
      "grad_norm": 1.0607943534851074,
      "learning_rate": 8.941176470588236e-05,
      "loss": 0.3331,
      "step": 76
    },
    {
      "epoch": 4.588235294117647,
      "grad_norm": 0.9669933319091797,
      "learning_rate": 9.176470588235295e-05,
      "loss": 0.3306,
      "step": 78
    },
    {
      "epoch": 4.705882352941177,
      "grad_norm": 0.8662776947021484,
      "learning_rate": 9.411764705882353e-05,
      "loss": 0.3147,
      "step": 80
    },
    {
      "epoch": 4.823529411764706,
      "grad_norm": 0.9427347183227539,
      "learning_rate": 9.647058823529412e-05,
      "loss": 0.3232,
      "step": 82
    },
    {
      "epoch": 4.9411764705882355,
      "grad_norm": 1.0095247030258179,
      "learning_rate": 9.882352941176471e-05,
      "loss": 0.3484,
      "step": 84
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.5736069083213806,
      "eval_runtime": 45.6683,
      "eval_samples_per_second": 0.788,
      "eval_steps_per_second": 0.788,
      "step": 85
    },
    {
      "epoch": 5.0588235294117645,
      "grad_norm": 1.022907018661499,
      "learning_rate": 9.99995783847866e-05,
      "loss": 0.2898,
      "step": 86
    },
    {
      "epoch": 5.176470588235294,
      "grad_norm": 0.90144944190979,
      "learning_rate": 9.999620550574153e-05,
      "loss": 0.2061,
      "step": 88
    },
    {
      "epoch": 5.294117647058823,
      "grad_norm": 1.330431342124939,
      "learning_rate": 9.998945997517956e-05,
      "loss": 0.224,
      "step": 90
    },
    {
      "epoch": 5.411764705882353,
      "grad_norm": 2.265726327896118,
      "learning_rate": 9.997934224814173e-05,
      "loss": 0.2291,
      "step": 92
    },
    {
      "epoch": 5.529411764705882,
      "grad_norm": 1.3978240489959717,
      "learning_rate": 9.996585300715116e-05,
      "loss": 0.2062,
      "step": 94
    },
    {
      "epoch": 5.647058823529412,
      "grad_norm": 1.0012567043304443,
      "learning_rate": 9.994899316216708e-05,
      "loss": 0.1806,
      "step": 96
    },
    {
      "epoch": 5.764705882352941,
      "grad_norm": 1.1725634336471558,
      "learning_rate": 9.992876385052345e-05,
      "loss": 0.2119,
      "step": 98
    },
    {
      "epoch": 5.882352941176471,
      "grad_norm": 0.9966250658035278,
      "learning_rate": 9.990516643685222e-05,
      "loss": 0.2095,
      "step": 100
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.3456579446792603,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.1757,
      "step": 102
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.6781781315803528,
      "eval_runtime": 45.6123,
      "eval_samples_per_second": 0.789,
      "eval_steps_per_second": 0.789,
      "step": 102
    },
    {
      "epoch": 6.117647058823529,
      "grad_norm": 0.9284908771514893,
      "learning_rate": 9.984787389787688e-05,
      "loss": 0.0952,
      "step": 104
    },
    {
      "epoch": 6.235294117647059,
      "grad_norm": 1.3222594261169434,
      "learning_rate": 9.981418263742148e-05,
      "loss": 0.0961,
      "step": 106
    },
    {
      "epoch": 6.352941176470588,
      "grad_norm": 1.4640154838562012,
      "learning_rate": 9.977713100437509e-05,
      "loss": 0.0885,
      "step": 108
    },
    {
      "epoch": 6.470588235294118,
      "grad_norm": 1.5303505659103394,
      "learning_rate": 9.973672149817232e-05,
      "loss": 0.1048,
      "step": 110
    },
    {
      "epoch": 6.588235294117647,
      "grad_norm": 1.3062849044799805,
      "learning_rate": 9.96929568447637e-05,
      "loss": 0.0911,
      "step": 112
    },
    {
      "epoch": 6.705882352941177,
      "grad_norm": 1.2243715524673462,
      "learning_rate": 9.964583999643174e-05,
      "loss": 0.1258,
      "step": 114
    },
    {
      "epoch": 6.823529411764706,
      "grad_norm": 1.033158302307129,
      "learning_rate": 9.95953741315919e-05,
      "loss": 0.1074,
      "step": 116
    },
    {
      "epoch": 6.9411764705882355,
      "grad_norm": 1.206876516342163,
      "learning_rate": 9.954156265457801e-05,
      "loss": 0.1039,
      "step": 118
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.7553205490112305,
      "eval_runtime": 45.6202,
      "eval_samples_per_second": 0.789,
      "eval_steps_per_second": 0.789,
      "step": 119
    },
    {
      "epoch": 7.0588235294117645,
      "grad_norm": 0.8786742687225342,
      "learning_rate": 9.948440919541278e-05,
      "loss": 0.0785,
      "step": 120
    },
    {
      "epoch": 7.176470588235294,
      "grad_norm": 0.8730283975601196,
      "learning_rate": 9.942391760956277e-05,
      "loss": 0.0463,
      "step": 122
    },
    {
      "epoch": 7.294117647058823,
      "grad_norm": 1.0248425006866455,
      "learning_rate": 9.936009197767845e-05,
      "loss": 0.0452,
      "step": 124
    },
    {
      "epoch": 7.411764705882353,
      "grad_norm": 1.3386567831039429,
      "learning_rate": 9.929293660531888e-05,
      "loss": 0.045,
      "step": 126
    },
    {
      "epoch": 7.529411764705882,
      "grad_norm": 1.3237050771713257,
      "learning_rate": 9.922245602266118e-05,
      "loss": 0.0442,
      "step": 128
    },
    {
      "epoch": 7.647058823529412,
      "grad_norm": 1.5747888088226318,
      "learning_rate": 9.91486549841951e-05,
      "loss": 0.0584,
      "step": 130
    },
    {
      "epoch": 7.764705882352941,
      "grad_norm": 1.3215928077697754,
      "learning_rate": 9.90715384684021e-05,
      "loss": 0.0469,
      "step": 132
    },
    {
      "epoch": 7.882352941176471,
      "grad_norm": 1.3094322681427002,
      "learning_rate": 9.899111167741966e-05,
      "loss": 0.0603,
      "step": 134
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.3538932800292969,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0696,
      "step": 136
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.8766400814056396,
      "eval_runtime": 45.6045,
      "eval_samples_per_second": 0.789,
      "eval_steps_per_second": 0.789,
      "step": 136
    },
    {
      "epoch": 8.117647058823529,
      "grad_norm": 0.7851260304450989,
      "learning_rate": 9.882034919459555e-05,
      "loss": 0.0277,
      "step": 138
    },
    {
      "epoch": 8.235294117647058,
      "grad_norm": 0.8018227815628052,
      "learning_rate": 9.873002502207503e-05,
      "loss": 0.0259,
      "step": 140
    },
    {
      "epoch": 8.352941176470589,
      "grad_norm": 0.9784229397773743,
      "learning_rate": 9.863641361223024e-05,
      "loss": 0.0299,
      "step": 142
    },
    {
      "epoch": 8.470588235294118,
      "grad_norm": 1.256463885307312,
      "learning_rate": 9.853952127991372e-05,
      "loss": 0.0369,
      "step": 144
    },
    {
      "epoch": 8.588235294117647,
      "grad_norm": 0.7432540655136108,
      "learning_rate": 9.843935456130295e-05,
      "loss": 0.0251,
      "step": 146
    },
    {
      "epoch": 8.705882352941176,
      "grad_norm": 0.9313145279884338,
      "learning_rate": 9.833592021345937e-05,
      "loss": 0.0277,
      "step": 148
    },
    {
      "epoch": 8.823529411764707,
      "grad_norm": 1.1375666856765747,
      "learning_rate": 9.822922521387276e-05,
      "loss": 0.0246,
      "step": 150
    },
    {
      "epoch": 8.941176470588236,
      "grad_norm": 1.4463223218917847,
      "learning_rate": 9.811927675999036e-05,
      "loss": 0.0283,
      "step": 152
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.9679501056671143,
      "eval_runtime": 45.5975,
      "eval_samples_per_second": 0.79,
      "eval_steps_per_second": 0.79,
      "step": 153
    },
    {
      "epoch": 9.058823529411764,
      "grad_norm": 0.5147568583488464,
      "learning_rate": 9.800608226873142e-05,
      "loss": 0.0166,
      "step": 154
    },
    {
      "epoch": 9.176470588235293,
      "grad_norm": 0.9345383048057556,
      "learning_rate": 9.788964937598689e-05,
      "loss": 0.0192,
      "step": 156
    },
    {
      "epoch": 9.294117647058824,
      "grad_norm": 0.5755206346511841,
      "learning_rate": 9.776998593610428e-05,
      "loss": 0.0132,
      "step": 158
    },
    {
      "epoch": 9.411764705882353,
      "grad_norm": 0.7219722270965576,
      "learning_rate": 9.764710002135784e-05,
      "loss": 0.015,
      "step": 160
    },
    {
      "epoch": 9.529411764705882,
      "grad_norm": 0.9252334237098694,
      "learning_rate": 9.752099992140399e-05,
      "loss": 0.0194,
      "step": 162
    },
    {
      "epoch": 9.647058823529411,
      "grad_norm": 0.7918896675109863,
      "learning_rate": 9.739169414272217e-05,
      "loss": 0.0154,
      "step": 164
    },
    {
      "epoch": 9.764705882352942,
      "grad_norm": 0.7386484742164612,
      "learning_rate": 9.725919140804099e-05,
      "loss": 0.019,
      "step": 166
    },
    {
      "epoch": 9.882352941176471,
      "grad_norm": 0.9785451889038086,
      "learning_rate": 9.71235006557497e-05,
      "loss": 0.0253,
      "step": 168
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.9260119795799255,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0201,
      "step": 170
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.9799950122833252,
      "eval_runtime": 45.5984,
      "eval_samples_per_second": 0.79,
      "eval_steps_per_second": 0.79,
      "step": 170
    },
    {
      "epoch": 10.117647058823529,
      "grad_norm": 0.6813646554946899,
      "learning_rate": 9.684259192656553e-05,
      "loss": 0.0092,
      "step": 172
    },
    {
      "epoch": 10.235294117647058,
      "grad_norm": 0.47431835532188416,
      "learning_rate": 9.669739289925577e-05,
      "loss": 0.0109,
      "step": 174
    },
    {
      "epoch": 10.352941176470589,
      "grad_norm": 0.5983676314353943,
      "learning_rate": 9.654904375222385e-05,
      "loss": 0.0112,
      "step": 176
    },
    {
      "epoch": 10.470588235294118,
      "grad_norm": 0.6158457398414612,
      "learning_rate": 9.639755449282875e-05,
      "loss": 0.012,
      "step": 178
    },
    {
      "epoch": 10.588235294117647,
      "grad_norm": 0.6749003529548645,
      "learning_rate": 9.62429353402556e-05,
      "loss": 0.0109,
      "step": 180
    },
    {
      "epoch": 10.705882352941176,
      "grad_norm": 0.8362804651260376,
      "learning_rate": 9.608519672482636e-05,
      "loss": 0.0134,
      "step": 182
    },
    {
      "epoch": 10.823529411764707,
      "grad_norm": 0.766984224319458,
      "learning_rate": 9.592434928729616e-05,
      "loss": 0.0136,
      "step": 184
    },
    {
      "epoch": 10.941176470588236,
      "grad_norm": 0.9381007552146912,
      "learning_rate": 9.576040387813552e-05,
      "loss": 0.0135,
      "step": 186
    },
    {
      "epoch": 11.0,
      "eval_loss": 1.0321534872055054,
      "eval_runtime": 45.6141,
      "eval_samples_per_second": 0.789,
      "eval_steps_per_second": 0.789,
      "step": 187
    },
    {
      "epoch": 11.0,
      "step": 187,
      "total_flos": 1.7726772045728973e+17,
      "train_loss": 0.302630395822745,
      "train_runtime": 6437.892,
      "train_samples_per_second": 1.056,
      "train_steps_per_second": 0.132
    }
  ],
  "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": 1.7726772045728973e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}