{
  "best_metric": 0.7682260870933533,
  "best_model_checkpoint": "data/Mistral-7B_task-2_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": 0.9529680013656616,
      "learning_rate": 1.1764705882352942e-06,
      "loss": 1.1173,
      "step": 1
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 0.9802116751670837,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 1.1747,
      "step": 2
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 1.1585707664489746,
      "learning_rate": 4.705882352941177e-06,
      "loss": 1.1598,
      "step": 4
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 1.033600926399231,
      "learning_rate": 7.058823529411765e-06,
      "loss": 1.1559,
      "step": 6
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.8660223484039307,
      "learning_rate": 9.411764705882354e-06,
      "loss": 1.1283,
      "step": 8
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 0.7578140497207642,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.0845,
      "step": 10
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 0.6900975108146667,
      "learning_rate": 1.411764705882353e-05,
      "loss": 1.0564,
      "step": 12
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 0.636638879776001,
      "learning_rate": 1.647058823529412e-05,
      "loss": 1.047,
      "step": 14
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.5010765790939331,
      "learning_rate": 1.8823529411764708e-05,
      "loss": 1.0296,
      "step": 16
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.008569359779358,
      "eval_runtime": 46.773,
      "eval_samples_per_second": 0.77,
      "eval_steps_per_second": 0.77,
      "step": 17
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 0.39401063323020935,
      "learning_rate": 2.1176470588235296e-05,
      "loss": 1.0085,
      "step": 18
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.33269256353378296,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 0.9917,
      "step": 20
    },
    {
      "epoch": 1.2941176470588236,
      "grad_norm": 0.3291841745376587,
      "learning_rate": 2.5882352941176475e-05,
      "loss": 0.9713,
      "step": 22
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 0.3407091200351715,
      "learning_rate": 2.823529411764706e-05,
      "loss": 0.9352,
      "step": 24
    },
    {
      "epoch": 1.5294117647058822,
      "grad_norm": 0.31771546602249146,
      "learning_rate": 3.058823529411765e-05,
      "loss": 0.9298,
      "step": 26
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 0.3569824695587158,
      "learning_rate": 3.294117647058824e-05,
      "loss": 0.9182,
      "step": 28
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 0.4640268385410309,
      "learning_rate": 3.529411764705883e-05,
      "loss": 0.8983,
      "step": 30
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 0.5204550623893738,
      "learning_rate": 3.7647058823529415e-05,
      "loss": 0.8666,
      "step": 32
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.4071232080459595,
      "learning_rate": 4e-05,
      "loss": 0.8629,
      "step": 34
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.8535005450248718,
      "eval_runtime": 46.7731,
      "eval_samples_per_second": 0.77,
      "eval_steps_per_second": 0.77,
      "step": 34
    },
    {
      "epoch": 2.1176470588235294,
      "grad_norm": 0.40852048993110657,
      "learning_rate": 4.235294117647059e-05,
      "loss": 0.8152,
      "step": 36
    },
    {
      "epoch": 2.235294117647059,
      "grad_norm": 0.3210791349411011,
      "learning_rate": 4.470588235294118e-05,
      "loss": 0.7852,
      "step": 38
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 0.3204159438610077,
      "learning_rate": 4.705882352941177e-05,
      "loss": 0.7818,
      "step": 40
    },
    {
      "epoch": 2.4705882352941178,
      "grad_norm": 0.28976207971572876,
      "learning_rate": 4.9411764705882355e-05,
      "loss": 0.7797,
      "step": 42
    },
    {
      "epoch": 2.588235294117647,
      "grad_norm": 0.3102598190307617,
      "learning_rate": 5.176470588235295e-05,
      "loss": 0.7465,
      "step": 44
    },
    {
      "epoch": 2.7058823529411766,
      "grad_norm": 0.35742253065109253,
      "learning_rate": 5.411764705882353e-05,
      "loss": 0.7766,
      "step": 46
    },
    {
      "epoch": 2.8235294117647056,
      "grad_norm": 0.2735128700733185,
      "learning_rate": 5.647058823529412e-05,
      "loss": 0.7769,
      "step": 48
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 0.2667198181152344,
      "learning_rate": 5.882352941176471e-05,
      "loss": 0.7661,
      "step": 50
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.7902934551239014,
      "eval_runtime": 46.7813,
      "eval_samples_per_second": 0.77,
      "eval_steps_per_second": 0.77,
      "step": 51
    },
    {
      "epoch": 3.0588235294117645,
      "grad_norm": 0.24059735238552094,
      "learning_rate": 6.11764705882353e-05,
      "loss": 0.7377,
      "step": 52
    },
    {
      "epoch": 3.176470588235294,
      "grad_norm": 0.2501852512359619,
      "learning_rate": 6.352941176470588e-05,
      "loss": 0.7193,
      "step": 54
    },
    {
      "epoch": 3.2941176470588234,
      "grad_norm": 0.2530383765697479,
      "learning_rate": 6.588235294117648e-05,
      "loss": 0.7683,
      "step": 56
    },
    {
      "epoch": 3.411764705882353,
      "grad_norm": 0.2647169530391693,
      "learning_rate": 6.823529411764707e-05,
      "loss": 0.7407,
      "step": 58
    },
    {
      "epoch": 3.5294117647058822,
      "grad_norm": 0.27116823196411133,
      "learning_rate": 7.058823529411765e-05,
      "loss": 0.6932,
      "step": 60
    },
    {
      "epoch": 3.6470588235294117,
      "grad_norm": 0.2503696382045746,
      "learning_rate": 7.294117647058823e-05,
      "loss": 0.7698,
      "step": 62
    },
    {
      "epoch": 3.764705882352941,
      "grad_norm": 0.342696875333786,
      "learning_rate": 7.529411764705883e-05,
      "loss": 0.7138,
      "step": 64
    },
    {
      "epoch": 3.8823529411764706,
      "grad_norm": 0.30938082933425903,
      "learning_rate": 7.764705882352942e-05,
      "loss": 0.6883,
      "step": 66
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.2871076464653015,
      "learning_rate": 8e-05,
      "loss": 0.693,
      "step": 68
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.7716789841651917,
      "eval_runtime": 46.7875,
      "eval_samples_per_second": 0.769,
      "eval_steps_per_second": 0.769,
      "step": 68
    },
    {
      "epoch": 4.117647058823529,
      "grad_norm": 0.27054253220558167,
      "learning_rate": 8.23529411764706e-05,
      "loss": 0.7462,
      "step": 70
    },
    {
      "epoch": 4.235294117647059,
      "grad_norm": 0.3078412711620331,
      "learning_rate": 8.470588235294118e-05,
      "loss": 0.6448,
      "step": 72
    },
    {
      "epoch": 4.352941176470588,
      "grad_norm": 0.3041563034057617,
      "learning_rate": 8.705882352941177e-05,
      "loss": 0.7104,
      "step": 74
    },
    {
      "epoch": 4.470588235294118,
      "grad_norm": 0.31636837124824524,
      "learning_rate": 8.941176470588236e-05,
      "loss": 0.6582,
      "step": 76
    },
    {
      "epoch": 4.588235294117647,
      "grad_norm": 0.33388981223106384,
      "learning_rate": 9.176470588235295e-05,
      "loss": 0.6751,
      "step": 78
    },
    {
      "epoch": 4.705882352941177,
      "grad_norm": 0.3267267048358917,
      "learning_rate": 9.411764705882353e-05,
      "loss": 0.6977,
      "step": 80
    },
    {
      "epoch": 4.823529411764706,
      "grad_norm": 0.3967256247997284,
      "learning_rate": 9.647058823529412e-05,
      "loss": 0.668,
      "step": 82
    },
    {
      "epoch": 4.9411764705882355,
      "grad_norm": 0.37619009613990784,
      "learning_rate": 9.882352941176471e-05,
      "loss": 0.6638,
      "step": 84
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.7682260870933533,
      "eval_runtime": 46.7749,
      "eval_samples_per_second": 0.77,
      "eval_steps_per_second": 0.77,
      "step": 85
    },
    {
      "epoch": 5.0588235294117645,
      "grad_norm": 0.42833760380744934,
      "learning_rate": 9.99995783847866e-05,
      "loss": 0.6032,
      "step": 86
    },
    {
      "epoch": 5.176470588235294,
      "grad_norm": 0.3832778334617615,
      "learning_rate": 9.999620550574153e-05,
      "loss": 0.6133,
      "step": 88
    },
    {
      "epoch": 5.294117647058823,
      "grad_norm": 0.4214220941066742,
      "learning_rate": 9.998945997517956e-05,
      "loss": 0.6471,
      "step": 90
    },
    {
      "epoch": 5.411764705882353,
      "grad_norm": 0.3985895812511444,
      "learning_rate": 9.997934224814173e-05,
      "loss": 0.6451,
      "step": 92
    },
    {
      "epoch": 5.529411764705882,
      "grad_norm": 0.4214719831943512,
      "learning_rate": 9.996585300715116e-05,
      "loss": 0.6119,
      "step": 94
    },
    {
      "epoch": 5.647058823529412,
      "grad_norm": 0.4165622293949127,
      "learning_rate": 9.994899316216708e-05,
      "loss": 0.6107,
      "step": 96
    },
    {
      "epoch": 5.764705882352941,
      "grad_norm": 0.45749929547309875,
      "learning_rate": 9.992876385052345e-05,
      "loss": 0.6279,
      "step": 98
    },
    {
      "epoch": 5.882352941176471,
      "grad_norm": 0.46676045656204224,
      "learning_rate": 9.990516643685222e-05,
      "loss": 0.6359,
      "step": 100
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.454730361700058,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.5866,
      "step": 102
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.7786874175071716,
      "eval_runtime": 46.7785,
      "eval_samples_per_second": 0.77,
      "eval_steps_per_second": 0.77,
      "step": 102
    },
    {
      "epoch": 6.117647058823529,
      "grad_norm": 0.44919857382774353,
      "learning_rate": 9.984787389787688e-05,
      "loss": 0.5386,
      "step": 104
    },
    {
      "epoch": 6.235294117647059,
      "grad_norm": 0.5968506336212158,
      "learning_rate": 9.981418263742148e-05,
      "loss": 0.5425,
      "step": 106
    },
    {
      "epoch": 6.352941176470588,
      "grad_norm": 0.5549154281616211,
      "learning_rate": 9.977713100437509e-05,
      "loss": 0.5012,
      "step": 108
    },
    {
      "epoch": 6.470588235294118,
      "grad_norm": 0.5988807678222656,
      "learning_rate": 9.973672149817232e-05,
      "loss": 0.5477,
      "step": 110
    },
    {
      "epoch": 6.588235294117647,
      "grad_norm": 0.641643762588501,
      "learning_rate": 9.96929568447637e-05,
      "loss": 0.517,
      "step": 112
    },
    {
      "epoch": 6.705882352941177,
      "grad_norm": 0.6178411841392517,
      "learning_rate": 9.964583999643174e-05,
      "loss": 0.5789,
      "step": 114
    },
    {
      "epoch": 6.823529411764706,
      "grad_norm": 0.5194504261016846,
      "learning_rate": 9.95953741315919e-05,
      "loss": 0.5873,
      "step": 116
    },
    {
      "epoch": 6.9411764705882355,
      "grad_norm": 0.6164565086364746,
      "learning_rate": 9.954156265457801e-05,
      "loss": 0.5466,
      "step": 118
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.8051445484161377,
      "eval_runtime": 46.7737,
      "eval_samples_per_second": 0.77,
      "eval_steps_per_second": 0.77,
      "step": 119
    },
    {
      "epoch": 7.0588235294117645,
      "grad_norm": 0.595158040523529,
      "learning_rate": 9.948440919541278e-05,
      "loss": 0.5222,
      "step": 120
    },
    {
      "epoch": 7.176470588235294,
      "grad_norm": 0.7633479833602905,
      "learning_rate": 9.942391760956277e-05,
      "loss": 0.4721,
      "step": 122
    },
    {
      "epoch": 7.294117647058823,
      "grad_norm": 0.7221975922584534,
      "learning_rate": 9.936009197767845e-05,
      "loss": 0.467,
      "step": 124
    },
    {
      "epoch": 7.411764705882353,
      "grad_norm": 0.7696866989135742,
      "learning_rate": 9.929293660531888e-05,
      "loss": 0.4445,
      "step": 126
    },
    {
      "epoch": 7.529411764705882,
      "grad_norm": 0.8333733081817627,
      "learning_rate": 9.922245602266118e-05,
      "loss": 0.4552,
      "step": 128
    },
    {
      "epoch": 7.647058823529412,
      "grad_norm": 0.965686023235321,
      "learning_rate": 9.91486549841951e-05,
      "loss": 0.4771,
      "step": 130
    },
    {
      "epoch": 7.764705882352941,
      "grad_norm": 0.7875787615776062,
      "learning_rate": 9.90715384684021e-05,
      "loss": 0.4253,
      "step": 132
    },
    {
      "epoch": 7.882352941176471,
      "grad_norm": 0.662136971950531,
      "learning_rate": 9.899111167741966e-05,
      "loss": 0.5099,
      "step": 134
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.7472110390663147,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.4416,
      "step": 136
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.8420692086219788,
      "eval_runtime": 46.7838,
      "eval_samples_per_second": 0.769,
      "eval_steps_per_second": 0.769,
      "step": 136
    },
    {
      "epoch": 8.117647058823529,
      "grad_norm": 0.7371023893356323,
      "learning_rate": 9.882034919459555e-05,
      "loss": 0.3783,
      "step": 138
    },
    {
      "epoch": 8.235294117647058,
      "grad_norm": 1.2120952606201172,
      "learning_rate": 9.873002502207503e-05,
      "loss": 0.3788,
      "step": 140
    },
    {
      "epoch": 8.352941176470589,
      "grad_norm": 0.9600831270217896,
      "learning_rate": 9.863641361223024e-05,
      "loss": 0.3988,
      "step": 142
    },
    {
      "epoch": 8.470588235294118,
      "grad_norm": 0.8414990305900574,
      "learning_rate": 9.853952127991372e-05,
      "loss": 0.4026,
      "step": 144
    },
    {
      "epoch": 8.588235294117647,
      "grad_norm": 0.8318824172019958,
      "learning_rate": 9.843935456130295e-05,
      "loss": 0.4247,
      "step": 146
    },
    {
      "epoch": 8.705882352941176,
      "grad_norm": 0.8579779863357544,
      "learning_rate": 9.833592021345937e-05,
      "loss": 0.4086,
      "step": 148
    },
    {
      "epoch": 8.823529411764707,
      "grad_norm": 0.8009016513824463,
      "learning_rate": 9.822922521387276e-05,
      "loss": 0.3689,
      "step": 150
    },
    {
      "epoch": 8.941176470588236,
      "grad_norm": 0.810413122177124,
      "learning_rate": 9.811927675999036e-05,
      "loss": 0.3585,
      "step": 152
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.8835746645927429,
      "eval_runtime": 46.7825,
      "eval_samples_per_second": 0.77,
      "eval_steps_per_second": 0.77,
      "step": 153
    },
    {
      "epoch": 9.058823529411764,
      "grad_norm": 0.7984738349914551,
      "learning_rate": 9.800608226873142e-05,
      "loss": 0.3768,
      "step": 154
    },
    {
      "epoch": 9.176470588235293,
      "grad_norm": 0.9628229737281799,
      "learning_rate": 9.788964937598689e-05,
      "loss": 0.3105,
      "step": 156
    },
    {
      "epoch": 9.294117647058824,
      "grad_norm": 0.9498036503791809,
      "learning_rate": 9.776998593610428e-05,
      "loss": 0.3173,
      "step": 158
    },
    {
      "epoch": 9.411764705882353,
      "grad_norm": 0.8465449213981628,
      "learning_rate": 9.764710002135784e-05,
      "loss": 0.3311,
      "step": 160
    },
    {
      "epoch": 9.529411764705882,
      "grad_norm": 0.890710711479187,
      "learning_rate": 9.752099992140399e-05,
      "loss": 0.3114,
      "step": 162
    },
    {
      "epoch": 9.647058823529411,
      "grad_norm": 0.9933630228042603,
      "learning_rate": 9.739169414272217e-05,
      "loss": 0.3331,
      "step": 164
    },
    {
      "epoch": 9.764705882352942,
      "grad_norm": 0.9540209174156189,
      "learning_rate": 9.725919140804099e-05,
      "loss": 0.3395,
      "step": 166
    },
    {
      "epoch": 9.882352941176471,
      "grad_norm": 0.9312388300895691,
      "learning_rate": 9.71235006557497e-05,
      "loss": 0.2859,
      "step": 168
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.810813307762146,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.3201,
      "step": 170
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.9439077377319336,
      "eval_runtime": 46.7835,
      "eval_samples_per_second": 0.77,
      "eval_steps_per_second": 0.77,
      "step": 170
    },
    {
      "epoch": 10.117647058823529,
      "grad_norm": 0.8292504549026489,
      "learning_rate": 9.684259192656553e-05,
      "loss": 0.2356,
      "step": 172
    },
    {
      "epoch": 10.235294117647058,
      "grad_norm": 1.088440179824829,
      "learning_rate": 9.669739289925577e-05,
      "loss": 0.2556,
      "step": 174
    },
    {
      "epoch": 10.352941176470589,
      "grad_norm": 0.8578810691833496,
      "learning_rate": 9.654904375222385e-05,
      "loss": 0.271,
      "step": 176
    },
    {
      "epoch": 10.470588235294118,
      "grad_norm": 0.7711437344551086,
      "learning_rate": 9.639755449282875e-05,
      "loss": 0.2326,
      "step": 178
    },
    {
      "epoch": 10.588235294117647,
      "grad_norm": 0.8039439916610718,
      "learning_rate": 9.62429353402556e-05,
      "loss": 0.2701,
      "step": 180
    },
    {
      "epoch": 10.705882352941176,
      "grad_norm": 0.9787544012069702,
      "learning_rate": 9.608519672482636e-05,
      "loss": 0.2518,
      "step": 182
    },
    {
      "epoch": 10.823529411764707,
      "grad_norm": 0.9241171479225159,
      "learning_rate": 9.592434928729616e-05,
      "loss": 0.2725,
      "step": 184
    },
    {
      "epoch": 10.941176470588236,
      "grad_norm": 1.057631015777588,
      "learning_rate": 9.576040387813552e-05,
      "loss": 0.2796,
      "step": 186
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.9902241230010986,
      "eval_runtime": 46.7777,
      "eval_samples_per_second": 0.77,
      "eval_steps_per_second": 0.77,
      "step": 187
    },
    {
      "epoch": 11.058823529411764,
      "grad_norm": 0.7045416235923767,
      "learning_rate": 9.559337155679842e-05,
      "loss": 0.2536,
      "step": 188
    },
    {
      "epoch": 11.176470588235293,
      "grad_norm": 0.8750964999198914,
      "learning_rate": 9.542326359097619e-05,
      "loss": 0.2046,
      "step": 190
    },
    {
      "epoch": 11.294117647058824,
      "grad_norm": 1.0650678873062134,
      "learning_rate": 9.525009145583745e-05,
      "loss": 0.2328,
      "step": 192
    },
    {
      "epoch": 11.411764705882353,
      "grad_norm": 0.8350070714950562,
      "learning_rate": 9.507386683325404e-05,
      "loss": 0.1556,
      "step": 194
    },
    {
      "epoch": 11.529411764705882,
      "grad_norm": 0.8495131134986877,
      "learning_rate": 9.489460161101291e-05,
      "loss": 0.2246,
      "step": 196
    },
    {
      "epoch": 11.647058823529411,
      "grad_norm": 0.9573360085487366,
      "learning_rate": 9.471230788201429e-05,
      "loss": 0.2066,
      "step": 198
    },
    {
      "epoch": 11.764705882352942,
      "grad_norm": 0.8888539671897888,
      "learning_rate": 9.452699794345581e-05,
      "loss": 0.2097,
      "step": 200
    },
    {
      "epoch": 11.882352941176471,
      "grad_norm": 0.8400151133537292,
      "learning_rate": 9.43386842960031e-05,
      "loss": 0.2008,
      "step": 202
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.8557886481285095,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.1842,
      "step": 204
    },
    {
      "epoch": 12.0,
      "eval_loss": 1.0511090755462646,
      "eval_runtime": 46.781,
      "eval_samples_per_second": 0.77,
      "eval_steps_per_second": 0.77,
      "step": 204
    },
    {
      "epoch": 12.0,
      "step": 204,
      "total_flos": 1.9964384743574733e+17,
      "train_loss": 0.5838122264135117,
      "train_runtime": 7213.0418,
      "train_samples_per_second": 0.943,
      "train_steps_per_second": 0.118
    }
  ],
  "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": 1.9964384743574733e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}