{
  "best_metric": 1.2944130897521973,
  "best_model_checkpoint": "data/Gemma-2-2B_task-1_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": 2.3742620944976807,
      "learning_rate": 1.1764705882352942e-06,
      "loss": 2.3722,
      "step": 1
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 2.114546060562134,
      "learning_rate": 2.3529411764705885e-06,
      "loss": 2.1534,
      "step": 2
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 2.2990877628326416,
      "learning_rate": 4.705882352941177e-06,
      "loss": 2.3038,
      "step": 4
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 2.2031772136688232,
      "learning_rate": 7.058823529411765e-06,
      "loss": 2.3959,
      "step": 6
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 2.795652389526367,
      "learning_rate": 9.411764705882354e-06,
      "loss": 2.3385,
      "step": 8
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 2.440237045288086,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 2.398,
      "step": 10
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 2.7962543964385986,
      "learning_rate": 1.411764705882353e-05,
      "loss": 2.3769,
      "step": 12
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 2.3405168056488037,
      "learning_rate": 1.647058823529412e-05,
      "loss": 2.2561,
      "step": 14
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 2.2001473903656006,
      "learning_rate": 1.8823529411764708e-05,
      "loss": 2.2103,
      "step": 16
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.0467443466186523,
      "eval_runtime": 3.3644,
      "eval_samples_per_second": 10.7,
      "eval_steps_per_second": 10.7,
      "step": 17
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 2.1891188621520996,
      "learning_rate": 2.1176470588235296e-05,
      "loss": 2.041,
      "step": 18
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 1.9718151092529297,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 1.997,
      "step": 20
    },
    {
      "epoch": 1.2941176470588236,
      "grad_norm": 2.0198118686676025,
      "learning_rate": 2.5882352941176475e-05,
      "loss": 1.8479,
      "step": 22
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 1.4697847366333008,
      "learning_rate": 2.823529411764706e-05,
      "loss": 1.8289,
      "step": 24
    },
    {
      "epoch": 1.5294117647058822,
      "grad_norm": 1.70875084400177,
      "learning_rate": 3.058823529411765e-05,
      "loss": 1.6903,
      "step": 26
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 1.6988343000411987,
      "learning_rate": 3.294117647058824e-05,
      "loss": 1.6114,
      "step": 28
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 1.1806720495224,
      "learning_rate": 3.529411764705883e-05,
      "loss": 1.5349,
      "step": 30
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 1.1410810947418213,
      "learning_rate": 3.7647058823529415e-05,
      "loss": 1.5025,
      "step": 32
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.161216139793396,
      "learning_rate": 4e-05,
      "loss": 1.4945,
      "step": 34
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.5311051607131958,
      "eval_runtime": 3.3134,
      "eval_samples_per_second": 10.865,
      "eval_steps_per_second": 10.865,
      "step": 34
    },
    {
      "epoch": 2.1176470588235294,
      "grad_norm": 1.1853833198547363,
      "learning_rate": 4.235294117647059e-05,
      "loss": 1.3852,
      "step": 36
    },
    {
      "epoch": 2.235294117647059,
      "grad_norm": 1.0828124284744263,
      "learning_rate": 4.470588235294118e-05,
      "loss": 1.4792,
      "step": 38
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 1.092732548713684,
      "learning_rate": 4.705882352941177e-05,
      "loss": 1.293,
      "step": 40
    },
    {
      "epoch": 2.4705882352941178,
      "grad_norm": 1.0283308029174805,
      "learning_rate": 4.9411764705882355e-05,
      "loss": 1.4767,
      "step": 42
    },
    {
      "epoch": 2.588235294117647,
      "grad_norm": 1.1445075273513794,
      "learning_rate": 5.176470588235295e-05,
      "loss": 1.3437,
      "step": 44
    },
    {
      "epoch": 2.7058823529411766,
      "grad_norm": 0.9679731130599976,
      "learning_rate": 5.411764705882353e-05,
      "loss": 1.3751,
      "step": 46
    },
    {
      "epoch": 2.8235294117647056,
      "grad_norm": 1.2099288702011108,
      "learning_rate": 5.647058823529412e-05,
      "loss": 1.3604,
      "step": 48
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 1.1182951927185059,
      "learning_rate": 5.882352941176471e-05,
      "loss": 1.2419,
      "step": 50
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.3480626344680786,
      "eval_runtime": 3.3006,
      "eval_samples_per_second": 10.907,
      "eval_steps_per_second": 10.907,
      "step": 51
    },
    {
      "epoch": 3.0588235294117645,
      "grad_norm": 1.1668429374694824,
      "learning_rate": 6.11764705882353e-05,
      "loss": 1.2737,
      "step": 52
    },
    {
      "epoch": 3.176470588235294,
      "grad_norm": 1.161204218864441,
      "learning_rate": 6.352941176470588e-05,
      "loss": 1.1813,
      "step": 54
    },
    {
      "epoch": 3.2941176470588234,
      "grad_norm": 1.0769901275634766,
      "learning_rate": 6.588235294117648e-05,
      "loss": 1.1814,
      "step": 56
    },
    {
      "epoch": 3.411764705882353,
      "grad_norm": 1.1852420568466187,
      "learning_rate": 6.823529411764707e-05,
      "loss": 1.1604,
      "step": 58
    },
    {
      "epoch": 3.5294117647058822,
      "grad_norm": 1.4165881872177124,
      "learning_rate": 7.058823529411765e-05,
      "loss": 1.2121,
      "step": 60
    },
    {
      "epoch": 3.6470588235294117,
      "grad_norm": 1.4424504041671753,
      "learning_rate": 7.294117647058823e-05,
      "loss": 1.1227,
      "step": 62
    },
    {
      "epoch": 3.764705882352941,
      "grad_norm": 1.141609787940979,
      "learning_rate": 7.529411764705883e-05,
      "loss": 1.0559,
      "step": 64
    },
    {
      "epoch": 3.8823529411764706,
      "grad_norm": 1.3261938095092773,
      "learning_rate": 7.764705882352942e-05,
      "loss": 1.1307,
      "step": 66
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.5281033515930176,
      "learning_rate": 8e-05,
      "loss": 1.055,
      "step": 68
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.2944130897521973,
      "eval_runtime": 3.3156,
      "eval_samples_per_second": 10.858,
      "eval_steps_per_second": 10.858,
      "step": 68
    },
    {
      "epoch": 4.117647058823529,
      "grad_norm": 1.3359092473983765,
      "learning_rate": 8.23529411764706e-05,
      "loss": 0.9957,
      "step": 70
    },
    {
      "epoch": 4.235294117647059,
      "grad_norm": 1.366309404373169,
      "learning_rate": 8.470588235294118e-05,
      "loss": 0.9876,
      "step": 72
    },
    {
      "epoch": 4.352941176470588,
      "grad_norm": 1.5352916717529297,
      "learning_rate": 8.705882352941177e-05,
      "loss": 0.9747,
      "step": 74
    },
    {
      "epoch": 4.470588235294118,
      "grad_norm": 1.771458625793457,
      "learning_rate": 8.941176470588236e-05,
      "loss": 0.8759,
      "step": 76
    },
    {
      "epoch": 4.588235294117647,
      "grad_norm": 1.6756799221038818,
      "learning_rate": 9.176470588235295e-05,
      "loss": 0.9329,
      "step": 78
    },
    {
      "epoch": 4.705882352941177,
      "grad_norm": 1.8614811897277832,
      "learning_rate": 9.411764705882353e-05,
      "loss": 0.8917,
      "step": 80
    },
    {
      "epoch": 4.823529411764706,
      "grad_norm": 1.9968886375427246,
      "learning_rate": 9.647058823529412e-05,
      "loss": 0.8884,
      "step": 82
    },
    {
      "epoch": 4.9411764705882355,
      "grad_norm": 1.9924709796905518,
      "learning_rate": 9.882352941176471e-05,
      "loss": 0.9312,
      "step": 84
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.3498785495758057,
      "eval_runtime": 3.3323,
      "eval_samples_per_second": 10.803,
      "eval_steps_per_second": 10.803,
      "step": 85
    },
    {
      "epoch": 5.0588235294117645,
      "grad_norm": 1.7810460329055786,
      "learning_rate": 9.99995783847866e-05,
      "loss": 0.8287,
      "step": 86
    },
    {
      "epoch": 5.176470588235294,
      "grad_norm": 1.6286009550094604,
      "learning_rate": 9.999620550574153e-05,
      "loss": 0.6943,
      "step": 88
    },
    {
      "epoch": 5.294117647058823,
      "grad_norm": 1.8658010959625244,
      "learning_rate": 9.998945997517956e-05,
      "loss": 0.7088,
      "step": 90
    },
    {
      "epoch": 5.411764705882353,
      "grad_norm": 2.1254475116729736,
      "learning_rate": 9.997934224814173e-05,
      "loss": 0.7516,
      "step": 92
    },
    {
      "epoch": 5.529411764705882,
      "grad_norm": 2.627861976623535,
      "learning_rate": 9.996585300715116e-05,
      "loss": 0.6164,
      "step": 94
    },
    {
      "epoch": 5.647058823529412,
      "grad_norm": 2.7860474586486816,
      "learning_rate": 9.994899316216708e-05,
      "loss": 0.5625,
      "step": 96
    },
    {
      "epoch": 5.764705882352941,
      "grad_norm": 2.716407537460327,
      "learning_rate": 9.992876385052345e-05,
      "loss": 0.6713,
      "step": 98
    },
    {
      "epoch": 5.882352941176471,
      "grad_norm": 2.8562090396881104,
      "learning_rate": 9.990516643685222e-05,
      "loss": 0.7582,
      "step": 100
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.4960057735443115,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.6594,
      "step": 102
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.4708161354064941,
      "eval_runtime": 3.3173,
      "eval_samples_per_second": 10.852,
      "eval_steps_per_second": 10.852,
      "step": 102
    },
    {
      "epoch": 6.117647058823529,
      "grad_norm": 2.10386323928833,
      "learning_rate": 9.984787389787688e-05,
      "loss": 0.4298,
      "step": 104
    },
    {
      "epoch": 6.235294117647059,
      "grad_norm": 2.0866518020629883,
      "learning_rate": 9.981418263742148e-05,
      "loss": 0.4315,
      "step": 106
    },
    {
      "epoch": 6.352941176470588,
      "grad_norm": 2.3499813079833984,
      "learning_rate": 9.977713100437509e-05,
      "loss": 0.4312,
      "step": 108
    },
    {
      "epoch": 6.470588235294118,
      "grad_norm": 2.9931962490081787,
      "learning_rate": 9.973672149817232e-05,
      "loss": 0.429,
      "step": 110
    },
    {
      "epoch": 6.588235294117647,
      "grad_norm": 4.55004358291626,
      "learning_rate": 9.96929568447637e-05,
      "loss": 0.4084,
      "step": 112
    },
    {
      "epoch": 6.705882352941177,
      "grad_norm": 4.7611212730407715,
      "learning_rate": 9.964583999643174e-05,
      "loss": 0.4956,
      "step": 114
    },
    {
      "epoch": 6.823529411764706,
      "grad_norm": 3.259488582611084,
      "learning_rate": 9.95953741315919e-05,
      "loss": 0.3864,
      "step": 116
    },
    {
      "epoch": 6.9411764705882355,
      "grad_norm": 3.1064391136169434,
      "learning_rate": 9.954156265457801e-05,
      "loss": 0.3964,
      "step": 118
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.7099087238311768,
      "eval_runtime": 3.3525,
      "eval_samples_per_second": 10.738,
      "eval_steps_per_second": 10.738,
      "step": 119
    },
    {
      "epoch": 7.0588235294117645,
      "grad_norm": 2.349405288696289,
      "learning_rate": 9.948440919541278e-05,
      "loss": 0.3708,
      "step": 120
    },
    {
      "epoch": 7.176470588235294,
      "grad_norm": 2.191848039627075,
      "learning_rate": 9.942391760956277e-05,
      "loss": 0.2431,
      "step": 122
    },
    {
      "epoch": 7.294117647058823,
      "grad_norm": 2.949573516845703,
      "learning_rate": 9.936009197767845e-05,
      "loss": 0.2487,
      "step": 124
    },
    {
      "epoch": 7.411764705882353,
      "grad_norm": 3.274458885192871,
      "learning_rate": 9.929293660531888e-05,
      "loss": 0.2619,
      "step": 126
    },
    {
      "epoch": 7.529411764705882,
      "grad_norm": 3.0538015365600586,
      "learning_rate": 9.922245602266118e-05,
      "loss": 0.2117,
      "step": 128
    },
    {
      "epoch": 7.647058823529412,
      "grad_norm": 3.2455408573150635,
      "learning_rate": 9.91486549841951e-05,
      "loss": 0.1629,
      "step": 130
    },
    {
      "epoch": 7.764705882352941,
      "grad_norm": 3.695833444595337,
      "learning_rate": 9.90715384684021e-05,
      "loss": 0.2443,
      "step": 132
    },
    {
      "epoch": 7.882352941176471,
      "grad_norm": 3.594637155532837,
      "learning_rate": 9.899111167741966e-05,
      "loss": 0.2119,
      "step": 134
    },
    {
      "epoch": 8.0,
      "grad_norm": 3.7565574645996094,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.2489,
      "step": 136
    },
    {
      "epoch": 8.0,
      "eval_loss": 2.3134381771087646,
      "eval_runtime": 3.4368,
      "eval_samples_per_second": 10.475,
      "eval_steps_per_second": 10.475,
      "step": 136
    },
    {
      "epoch": 8.117647058823529,
      "grad_norm": 2.838242530822754,
      "learning_rate": 9.882034919459555e-05,
      "loss": 0.1516,
      "step": 138
    },
    {
      "epoch": 8.235294117647058,
      "grad_norm": 3.118826389312744,
      "learning_rate": 9.873002502207503e-05,
      "loss": 0.0929,
      "step": 140
    },
    {
      "epoch": 8.352941176470589,
      "grad_norm": 2.7981090545654297,
      "learning_rate": 9.863641361223024e-05,
      "loss": 0.1222,
      "step": 142
    },
    {
      "epoch": 8.470588235294118,
      "grad_norm": 3.995842456817627,
      "learning_rate": 9.853952127991372e-05,
      "loss": 0.1334,
      "step": 144
    },
    {
      "epoch": 8.588235294117647,
      "grad_norm": 3.8893682956695557,
      "learning_rate": 9.843935456130295e-05,
      "loss": 0.1346,
      "step": 146
    },
    {
      "epoch": 8.705882352941176,
      "grad_norm": 4.304506301879883,
      "learning_rate": 9.833592021345937e-05,
      "loss": 0.0991,
      "step": 148
    },
    {
      "epoch": 8.823529411764707,
      "grad_norm": 3.510660409927368,
      "learning_rate": 9.822922521387276e-05,
      "loss": 0.1218,
      "step": 150
    },
    {
      "epoch": 8.941176470588236,
      "grad_norm": 4.43711519241333,
      "learning_rate": 9.811927675999036e-05,
      "loss": 0.1183,
      "step": 152
    },
    {
      "epoch": 9.0,
      "eval_loss": 2.579131841659546,
      "eval_runtime": 3.3134,
      "eval_samples_per_second": 10.865,
      "eval_steps_per_second": 10.865,
      "step": 153
    },
    {
      "epoch": 9.058823529411764,
      "grad_norm": 2.4607386589050293,
      "learning_rate": 9.800608226873142e-05,
      "loss": 0.0852,
      "step": 154
    },
    {
      "epoch": 9.176470588235293,
      "grad_norm": 2.762890338897705,
      "learning_rate": 9.788964937598689e-05,
      "loss": 0.0691,
      "step": 156
    },
    {
      "epoch": 9.294117647058824,
      "grad_norm": 2.920292854309082,
      "learning_rate": 9.776998593610428e-05,
      "loss": 0.0802,
      "step": 158
    },
    {
      "epoch": 9.411764705882353,
      "grad_norm": 2.338898181915283,
      "learning_rate": 9.764710002135784e-05,
      "loss": 0.0607,
      "step": 160
    },
    {
      "epoch": 9.529411764705882,
      "grad_norm": 3.0876760482788086,
      "learning_rate": 9.752099992140399e-05,
      "loss": 0.0832,
      "step": 162
    },
    {
      "epoch": 9.647058823529411,
      "grad_norm": 4.488657474517822,
      "learning_rate": 9.739169414272217e-05,
      "loss": 0.0987,
      "step": 164
    },
    {
      "epoch": 9.764705882352942,
      "grad_norm": 3.517573595046997,
      "learning_rate": 9.725919140804099e-05,
      "loss": 0.1006,
      "step": 166
    },
    {
      "epoch": 9.882352941176471,
      "grad_norm": 3.7536239624023438,
      "learning_rate": 9.71235006557497e-05,
      "loss": 0.0982,
      "step": 168
    },
    {
      "epoch": 10.0,
      "grad_norm": 2.2880020141601562,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0799,
      "step": 170
    },
    {
      "epoch": 10.0,
      "eval_loss": 2.6094090938568115,
      "eval_runtime": 3.316,
      "eval_samples_per_second": 10.857,
      "eval_steps_per_second": 10.857,
      "step": 170
    },
    {
      "epoch": 10.117647058823529,
      "grad_norm": 3.735913038253784,
      "learning_rate": 9.684259192656553e-05,
      "loss": 0.0501,
      "step": 172
    },
    {
      "epoch": 10.235294117647058,
      "grad_norm": 2.304825782775879,
      "learning_rate": 9.669739289925577e-05,
      "loss": 0.0536,
      "step": 174
    },
    {
      "epoch": 10.352941176470589,
      "grad_norm": 2.4161999225616455,
      "learning_rate": 9.654904375222385e-05,
      "loss": 0.0701,
      "step": 176
    },
    {
      "epoch": 10.470588235294118,
      "grad_norm": 1.8710284233093262,
      "learning_rate": 9.639755449282875e-05,
      "loss": 0.0526,
      "step": 178
    },
    {
      "epoch": 10.588235294117647,
      "grad_norm": 1.7402461767196655,
      "learning_rate": 9.62429353402556e-05,
      "loss": 0.0427,
      "step": 180
    },
    {
      "epoch": 10.705882352941176,
      "grad_norm": 3.507913112640381,
      "learning_rate": 9.608519672482636e-05,
      "loss": 0.0782,
      "step": 182
    },
    {
      "epoch": 10.823529411764707,
      "grad_norm": 3.430429458618164,
      "learning_rate": 9.592434928729616e-05,
      "loss": 0.0961,
      "step": 184
    },
    {
      "epoch": 10.941176470588236,
      "grad_norm": 2.6616289615631104,
      "learning_rate": 9.576040387813552e-05,
      "loss": 0.0689,
      "step": 186
    },
    {
      "epoch": 11.0,
      "eval_loss": 2.9233055114746094,
      "eval_runtime": 3.3506,
      "eval_samples_per_second": 10.744,
      "eval_steps_per_second": 10.744,
      "step": 187
    },
    {
      "epoch": 11.0,
      "step": 187,
      "total_flos": 6214883632742400.0,
      "train_loss": 0.8238636347101652,
      "train_runtime": 647.9451,
      "train_samples_per_second": 10.495,
      "train_steps_per_second": 1.312
    }
  ],
  "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": 6214883632742400.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}