{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 33,
  "global_step": 168,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017857142857142856,
      "grad_norm": 6.941071033477783,
      "learning_rate": 0.0,
      "loss": 2.2705078125,
      "step": 1
    },
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 7.424960136413574,
      "learning_rate": 5.882352941176471e-06,
      "loss": 2.458984375,
      "step": 2
    },
    {
      "epoch": 0.05357142857142857,
      "grad_norm": 7.1218390464782715,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 2.48828125,
      "step": 3
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 7.222240924835205,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 2.5322265625,
      "step": 4
    },
    {
      "epoch": 0.08928571428571429,
      "grad_norm": 5.845511436462402,
      "learning_rate": 2.3529411764705884e-05,
      "loss": 2.232421875,
      "step": 5
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 5.019399166107178,
      "learning_rate": 2.9411764705882354e-05,
      "loss": 2.1015625,
      "step": 6
    },
    {
      "epoch": 0.125,
      "grad_norm": 3.254866361618042,
      "learning_rate": 3.529411764705883e-05,
      "loss": 1.814453125,
      "step": 7
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 2.1546192169189453,
      "learning_rate": 4.11764705882353e-05,
      "loss": 1.7998046875,
      "step": 8
    },
    {
      "epoch": 0.16071428571428573,
      "grad_norm": 1.6922756433486938,
      "learning_rate": 4.705882352941177e-05,
      "loss": 1.82421875,
      "step": 9
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 0.6866000294685364,
      "learning_rate": 5.294117647058824e-05,
      "loss": 1.6923828125,
      "step": 10
    },
    {
      "epoch": 0.19642857142857142,
      "grad_norm": 0.2825869619846344,
      "learning_rate": 5.882352941176471e-05,
      "loss": 1.6123046875,
      "step": 11
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 0.23961444199085236,
      "learning_rate": 6.470588235294118e-05,
      "loss": 1.6201171875,
      "step": 12
    },
    {
      "epoch": 0.23214285714285715,
      "grad_norm": 0.24167364835739136,
      "learning_rate": 7.058823529411765e-05,
      "loss": 1.7177734375,
      "step": 13
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.18511804938316345,
      "learning_rate": 7.647058823529411e-05,
      "loss": 1.63671875,
      "step": 14
    },
    {
      "epoch": 0.26785714285714285,
      "grad_norm": 0.18228590488433838,
      "learning_rate": 8.23529411764706e-05,
      "loss": 1.56640625,
      "step": 15
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.16492034494876862,
      "learning_rate": 8.823529411764706e-05,
      "loss": 1.5234375,
      "step": 16
    },
    {
      "epoch": 0.30357142857142855,
      "grad_norm": 0.17120489478111267,
      "learning_rate": 9.411764705882353e-05,
      "loss": 1.5869140625,
      "step": 17
    },
    {
      "epoch": 0.32142857142857145,
      "grad_norm": 0.16150017082691193,
      "learning_rate": 0.0001,
      "loss": 1.5654296875,
      "step": 18
    },
    {
      "epoch": 0.3392857142857143,
      "grad_norm": 0.15695668756961823,
      "learning_rate": 9.999026103728454e-05,
      "loss": 1.6728515625,
      "step": 19
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.1317329853773117,
      "learning_rate": 9.99610483645779e-05,
      "loss": 1.521484375,
      "step": 20
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.13089889287948608,
      "learning_rate": 9.991237462637478e-05,
      "loss": 1.630859375,
      "step": 21
    },
    {
      "epoch": 0.39285714285714285,
      "grad_norm": 0.1257891207933426,
      "learning_rate": 9.984426089075168e-05,
      "loss": 1.6083984375,
      "step": 22
    },
    {
      "epoch": 0.4107142857142857,
      "grad_norm": 0.10553042590618134,
      "learning_rate": 9.975673664024781e-05,
      "loss": 1.4521484375,
      "step": 23
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.07947301864624023,
      "learning_rate": 9.964983975910368e-05,
      "loss": 1.556640625,
      "step": 24
    },
    {
      "epoch": 0.44642857142857145,
      "grad_norm": 0.08297604322433472,
      "learning_rate": 9.952361651686332e-05,
      "loss": 1.455078125,
      "step": 25
    },
    {
      "epoch": 0.4642857142857143,
      "grad_norm": 0.07512954622507095,
      "learning_rate": 9.937812154834671e-05,
      "loss": 1.4580078125,
      "step": 26
    },
    {
      "epoch": 0.48214285714285715,
      "grad_norm": 0.07419554889202118,
      "learning_rate": 9.921341783000158e-05,
      "loss": 1.5634765625,
      "step": 27
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.07015231996774673,
      "learning_rate": 9.902957665264443e-05,
      "loss": 1.5390625,
      "step": 28
    },
    {
      "epoch": 0.5178571428571429,
      "grad_norm": 0.07289658486843109,
      "learning_rate": 9.882667759060298e-05,
      "loss": 1.587890625,
      "step": 29
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 0.06454391777515411,
      "learning_rate": 9.860480846727271e-05,
      "loss": 1.5673828125,
      "step": 30
    },
    {
      "epoch": 0.5535714285714286,
      "grad_norm": 0.06404420733451843,
      "learning_rate": 9.836406531710343e-05,
      "loss": 1.6552734375,
      "step": 31
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.05281953886151314,
      "learning_rate": 9.810455234403128e-05,
      "loss": 1.625,
      "step": 32
    },
    {
      "epoch": 0.5892857142857143,
      "grad_norm": 0.061630021780729294,
      "learning_rate": 9.782638187637489e-05,
      "loss": 1.6181640625,
      "step": 33
    },
    {
      "epoch": 0.6071428571428571,
      "grad_norm": 0.047608986496925354,
      "learning_rate": 9.752967431821485e-05,
      "loss": 1.5341796875,
      "step": 34
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.05047450587153435,
      "learning_rate": 9.721455809727766e-05,
      "loss": 1.373046875,
      "step": 35
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 0.04711677506566048,
      "learning_rate": 9.688116960934669e-05,
      "loss": 1.501953125,
      "step": 36
    },
    {
      "epoch": 0.6428571428571429,
      "eval_loss": 1.55859375,
      "eval_runtime": 9.9256,
      "eval_samples_per_second": 0.201,
      "eval_steps_per_second": 0.101,
      "step": 36
    },
    {
      "epoch": 0.6607142857142857,
      "grad_norm": 0.04698803275823593,
      "learning_rate": 9.652965315922438e-05,
      "loss": 1.6181640625,
      "step": 37
    },
    {
      "epoch": 0.6785714285714286,
      "grad_norm": 0.045602668076753616,
      "learning_rate": 9.616016089827078e-05,
      "loss": 1.404296875,
      "step": 38
    },
    {
      "epoch": 0.6964285714285714,
      "grad_norm": 0.04342078045010567,
      "learning_rate": 9.577285275854602e-05,
      "loss": 1.5,
      "step": 39
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.04809950664639473,
      "learning_rate": 9.536789638358488e-05,
      "loss": 1.7275390625,
      "step": 40
    },
    {
      "epoch": 0.7321428571428571,
      "grad_norm": 0.04545511677861214,
      "learning_rate": 9.494546705583345e-05,
      "loss": 1.5390625,
      "step": 41
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.044758349657058716,
      "learning_rate": 9.45057476207794e-05,
      "loss": 1.3662109375,
      "step": 42
    },
    {
      "epoch": 0.7678571428571429,
      "grad_norm": 0.039895955473184586,
      "learning_rate": 9.404892840780868e-05,
      "loss": 1.3681640625,
      "step": 43
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 0.03554367274045944,
      "learning_rate": 9.357520714782272e-05,
      "loss": 1.3485107421875,
      "step": 44
    },
    {
      "epoch": 0.8035714285714286,
      "grad_norm": 0.04424789547920227,
      "learning_rate": 9.308478888765214e-05,
      "loss": 1.28515625,
      "step": 45
    },
    {
      "epoch": 0.8214285714285714,
      "grad_norm": 0.04058537259697914,
      "learning_rate": 9.257788590130366e-05,
      "loss": 1.3555908203125,
      "step": 46
    },
    {
      "epoch": 0.8392857142857143,
      "grad_norm": 0.040706995874643326,
      "learning_rate": 9.205471759807875e-05,
      "loss": 1.5322265625,
      "step": 47
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.03654688596725464,
      "learning_rate": 9.151551042760408e-05,
      "loss": 1.4501953125,
      "step": 48
    },
    {
      "epoch": 0.875,
      "grad_norm": 0.03262929990887642,
      "learning_rate": 9.096049778181426e-05,
      "loss": 1.4765625,
      "step": 49
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 0.03735716640949249,
      "learning_rate": 9.038991989392991e-05,
      "loss": 1.60546875,
      "step": 50
    },
    {
      "epoch": 0.9107142857142857,
      "grad_norm": 0.03685036301612854,
      "learning_rate": 8.980402373447446e-05,
      "loss": 1.357421875,
      "step": 51
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 0.03257175534963608,
      "learning_rate": 8.920306290437463e-05,
      "loss": 1.5009765625,
      "step": 52
    },
    {
      "epoch": 0.9464285714285714,
      "grad_norm": 0.03679439052939415,
      "learning_rate": 8.858729752519122e-05,
      "loss": 1.4951171875,
      "step": 53
    },
    {
      "epoch": 0.9642857142857143,
      "grad_norm": 0.0431835800409317,
      "learning_rate": 8.795699412652731e-05,
      "loss": 1.6123046875,
      "step": 54
    },
    {
      "epoch": 0.9821428571428571,
      "grad_norm": 0.03260580450296402,
      "learning_rate": 8.731242553066286e-05,
      "loss": 1.48046875,
      "step": 55
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.028791066259145737,
      "learning_rate": 8.665387073446557e-05,
      "loss": 1.2091064453125,
      "step": 56
    },
    {
      "epoch": 1.0178571428571428,
      "grad_norm": 0.032193660736083984,
      "learning_rate": 8.598161478862901e-05,
      "loss": 1.4853515625,
      "step": 57
    },
    {
      "epoch": 1.0357142857142858,
      "grad_norm": 0.03401106595993042,
      "learning_rate": 8.529594867429059e-05,
      "loss": 1.5439453125,
      "step": 58
    },
    {
      "epoch": 1.0535714285714286,
      "grad_norm": 0.031666360795497894,
      "learning_rate": 8.459716917708248e-05,
      "loss": 1.58203125,
      "step": 59
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": 0.031007029116153717,
      "learning_rate": 8.388557875866996e-05,
      "loss": 1.6328125,
      "step": 60
    },
    {
      "epoch": 1.0892857142857142,
      "grad_norm": 0.03192567825317383,
      "learning_rate": 8.316148542583318e-05,
      "loss": 1.5244140625,
      "step": 61
    },
    {
      "epoch": 1.1071428571428572,
      "grad_norm": 0.0333578996360302,
      "learning_rate": 8.242520259714869e-05,
      "loss": 1.5830078125,
      "step": 62
    },
    {
      "epoch": 1.125,
      "grad_norm": 0.03258692845702171,
      "learning_rate": 8.167704896732829e-05,
      "loss": 1.4833984375,
      "step": 63
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.03526037558913231,
      "learning_rate": 8.091734836927447e-05,
      "loss": 1.533203125,
      "step": 64
    },
    {
      "epoch": 1.1607142857142858,
      "grad_norm": 0.03330685570836067,
      "learning_rate": 8.014642963391167e-05,
      "loss": 1.6318359375,
      "step": 65
    },
    {
      "epoch": 1.1785714285714286,
      "grad_norm": 0.03163750842213631,
      "learning_rate": 7.936462644785414e-05,
      "loss": 1.5634765625,
      "step": 66
    },
    {
      "epoch": 1.1964285714285714,
      "grad_norm": 0.032891903072595596,
      "learning_rate": 7.857227720897206e-05,
      "loss": 1.5244140625,
      "step": 67
    },
    {
      "epoch": 1.2142857142857142,
      "grad_norm": 0.03003869391977787,
      "learning_rate": 7.776972487991858e-05,
      "loss": 1.53515625,
      "step": 68
    },
    {
      "epoch": 1.2321428571428572,
      "grad_norm": 0.04649367928504944,
      "learning_rate": 7.695731683968077e-05,
      "loss": 1.6201171875,
      "step": 69
    },
    {
      "epoch": 1.2321428571428572,
      "eval_loss": 1.537109375,
      "eval_runtime": 0.8772,
      "eval_samples_per_second": 2.28,
      "eval_steps_per_second": 1.14,
      "step": 69
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.032294005155563354,
      "learning_rate": 7.613540473321927e-05,
      "loss": 1.5634765625,
      "step": 70
    },
    {
      "epoch": 1.2678571428571428,
      "grad_norm": 0.031688641756772995,
      "learning_rate": 7.530434431926118e-05,
      "loss": 1.49609375,
      "step": 71
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.03173067793250084,
      "learning_rate": 7.446449531631255e-05,
      "loss": 1.4560546875,
      "step": 72
    },
    {
      "epoch": 1.3035714285714286,
      "grad_norm": 0.034469932317733765,
      "learning_rate": 7.361622124695677e-05,
      "loss": 1.52734375,
      "step": 73
    },
    {
      "epoch": 1.3214285714285714,
      "grad_norm": 0.030841290950775146,
      "learning_rate": 7.275988928050644e-05,
      "loss": 1.5048828125,
      "step": 74
    },
    {
      "epoch": 1.3392857142857144,
      "grad_norm": 0.036480095237493515,
      "learning_rate": 7.189587007407686e-05,
      "loss": 1.62109375,
      "step": 75
    },
    {
      "epoch": 1.3571428571428572,
      "grad_norm": 0.031322281807661057,
      "learning_rate": 7.102453761214961e-05,
      "loss": 1.46875,
      "step": 76
    },
    {
      "epoch": 1.375,
      "grad_norm": 0.033672865480184555,
      "learning_rate": 7.014626904469629e-05,
      "loss": 1.5791015625,
      "step": 77
    },
    {
      "epoch": 1.3928571428571428,
      "grad_norm": 0.03220910206437111,
      "learning_rate": 6.926144452393163e-05,
      "loss": 1.5595703125,
      "step": 78
    },
    {
      "epoch": 1.4107142857142856,
      "grad_norm": 0.03739612177014351,
      "learning_rate": 6.837044703976753e-05,
      "loss": 1.404296875,
      "step": 79
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.03151741996407509,
      "learning_rate": 6.747366225403858e-05,
      "loss": 1.5166015625,
      "step": 80
    },
    {
      "epoch": 1.4464285714285714,
      "grad_norm": 0.036434777081012726,
      "learning_rate": 6.657147833357107e-05,
      "loss": 1.4140625,
      "step": 81
    },
    {
      "epoch": 1.4642857142857144,
      "grad_norm": 0.03737158700823784,
      "learning_rate": 6.566428578216786e-05,
      "loss": 1.421875,
      "step": 82
    },
    {
      "epoch": 1.4821428571428572,
      "grad_norm": 0.034982047975063324,
      "learning_rate": 6.475247727158154e-05,
      "loss": 1.533203125,
      "step": 83
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.03136328235268593,
      "learning_rate": 6.38364474715494e-05,
      "loss": 1.5029296875,
      "step": 84
    },
    {
      "epoch": 1.5178571428571428,
      "grad_norm": 0.03437354788184166,
      "learning_rate": 6.291659287896334e-05,
      "loss": 1.5556640625,
      "step": 85
    },
    {
      "epoch": 1.5357142857142856,
      "grad_norm": 0.034409910440444946,
      "learning_rate": 6.199331164624923e-05,
      "loss": 1.537109375,
      "step": 86
    },
    {
      "epoch": 1.5535714285714286,
      "grad_norm": 0.03298085182905197,
      "learning_rate": 6.10670034090293e-05,
      "loss": 1.6259765625,
      "step": 87
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.032122962176799774,
      "learning_rate": 6.0138069113142935e-05,
      "loss": 1.5966796875,
      "step": 88
    },
    {
      "epoch": 1.5892857142857144,
      "grad_norm": 0.036777496337890625,
      "learning_rate": 5.920691084110001e-05,
      "loss": 1.5859375,
      "step": 89
    },
    {
      "epoch": 1.6071428571428572,
      "grad_norm": 0.0312369242310524,
      "learning_rate": 5.827393163804249e-05,
      "loss": 1.5087890625,
      "step": 90
    },
    {
      "epoch": 1.625,
      "grad_norm": 0.03584510087966919,
      "learning_rate": 5.733953533728912e-05,
      "loss": 1.3466796875,
      "step": 91
    },
    {
      "epoch": 1.6428571428571428,
      "grad_norm": 0.035642072558403015,
      "learning_rate": 5.6404126385539266e-05,
      "loss": 1.474609375,
      "step": 92
    },
    {
      "epoch": 1.6607142857142856,
      "grad_norm": 0.03463999554514885,
      "learning_rate": 5.5468109667810896e-05,
      "loss": 1.5927734375,
      "step": 93
    },
    {
      "epoch": 1.6785714285714286,
      "grad_norm": 0.03212926164269447,
      "learning_rate": 5.4531890332189115e-05,
      "loss": 1.380859375,
      "step": 94
    },
    {
      "epoch": 1.6964285714285714,
      "grad_norm": 0.03418228402733803,
      "learning_rate": 5.359587361446073e-05,
      "loss": 1.4775390625,
      "step": 95
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.040222033858299255,
      "learning_rate": 5.26604646627109e-05,
      "loss": 1.7041015625,
      "step": 96
    },
    {
      "epoch": 1.7321428571428572,
      "grad_norm": 0.03230470046401024,
      "learning_rate": 5.172606836195753e-05,
      "loss": 1.5126953125,
      "step": 97
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.03400488570332527,
      "learning_rate": 5.0793089158899996e-05,
      "loss": 1.3447265625,
      "step": 98
    },
    {
      "epoch": 1.7678571428571428,
      "grad_norm": 0.033362630754709244,
      "learning_rate": 4.9861930886857075e-05,
      "loss": 1.3515625,
      "step": 99
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 0.03188500925898552,
      "learning_rate": 4.89329965909707e-05,
      "loss": 1.33062744140625,
      "step": 100
    },
    {
      "epoch": 1.8035714285714286,
      "grad_norm": 0.0368543304502964,
      "learning_rate": 4.8006688353750784e-05,
      "loss": 1.2705078125,
      "step": 101
    },
    {
      "epoch": 1.8214285714285714,
      "grad_norm": 0.039163682609796524,
      "learning_rate": 4.7083407121036674e-05,
      "loss": 1.3358154296875,
      "step": 102
    },
    {
      "epoch": 1.8214285714285714,
      "eval_loss": 1.537109375,
      "eval_runtime": 0.8766,
      "eval_samples_per_second": 2.282,
      "eval_steps_per_second": 1.141,
      "step": 102
    },
    {
      "epoch": 1.8392857142857144,
      "grad_norm": 0.03576352819800377,
      "learning_rate": 4.616355252845062e-05,
      "loss": 1.513671875,
      "step": 103
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.03252694755792618,
      "learning_rate": 4.524752272841847e-05,
      "loss": 1.43359375,
      "step": 104
    },
    {
      "epoch": 1.875,
      "grad_norm": 0.03241564333438873,
      "learning_rate": 4.4335714217832156e-05,
      "loss": 1.4619140625,
      "step": 105
    },
    {
      "epoch": 1.8928571428571428,
      "grad_norm": 0.03503812476992607,
      "learning_rate": 4.3428521666428945e-05,
      "loss": 1.5859375,
      "step": 106
    },
    {
      "epoch": 1.9107142857142856,
      "grad_norm": 0.0366126224398613,
      "learning_rate": 4.252633774596143e-05,
      "loss": 1.3427734375,
      "step": 107
    },
    {
      "epoch": 1.9285714285714286,
      "grad_norm": 0.0322301909327507,
      "learning_rate": 4.1629552960232464e-05,
      "loss": 1.4814453125,
      "step": 108
    },
    {
      "epoch": 1.9464285714285714,
      "grad_norm": 0.03486722707748413,
      "learning_rate": 4.073855547606838e-05,
      "loss": 1.474609375,
      "step": 109
    },
    {
      "epoch": 1.9642857142857144,
      "grad_norm": 0.03944855183362961,
      "learning_rate": 3.9853730955303724e-05,
      "loss": 1.5908203125,
      "step": 110
    },
    {
      "epoch": 1.9821428571428572,
      "grad_norm": 0.03148670867085457,
      "learning_rate": 3.897546238785039e-05,
      "loss": 1.4619140625,
      "step": 111
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.026970645412802696,
      "learning_rate": 3.810412992592317e-05,
      "loss": 1.1943359375,
      "step": 112
    },
    {
      "epoch": 2.017857142857143,
      "grad_norm": 0.030017025768756866,
      "learning_rate": 3.7240110719493574e-05,
      "loss": 1.46875,
      "step": 113
    },
    {
      "epoch": 2.0357142857142856,
      "grad_norm": 0.034159768372774124,
      "learning_rate": 3.638377875304324e-05,
      "loss": 1.52734375,
      "step": 114
    },
    {
      "epoch": 2.0535714285714284,
      "grad_norm": 0.03099321573972702,
      "learning_rate": 3.553550468368747e-05,
      "loss": 1.5615234375,
      "step": 115
    },
    {
      "epoch": 2.0714285714285716,
      "grad_norm": 0.031472716480493546,
      "learning_rate": 3.4695655680738835e-05,
      "loss": 1.615234375,
      "step": 116
    },
    {
      "epoch": 2.0892857142857144,
      "grad_norm": 0.03196612745523453,
      "learning_rate": 3.386459526678073e-05,
      "loss": 1.5126953125,
      "step": 117
    },
    {
      "epoch": 2.107142857142857,
      "grad_norm": 0.03274950012564659,
      "learning_rate": 3.304268316031922e-05,
      "loss": 1.5693359375,
      "step": 118
    },
    {
      "epoch": 2.125,
      "grad_norm": 0.03307091444730759,
      "learning_rate": 3.223027512008144e-05,
      "loss": 1.47265625,
      "step": 119
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.033927541226148605,
      "learning_rate": 3.142772279102795e-05,
      "loss": 1.517578125,
      "step": 120
    },
    {
      "epoch": 2.1607142857142856,
      "grad_norm": 0.03421061486005783,
      "learning_rate": 3.063537355214588e-05,
      "loss": 1.619140625,
      "step": 121
    },
    {
      "epoch": 2.1785714285714284,
      "grad_norm": 0.03192359209060669,
      "learning_rate": 2.9853570366088334e-05,
      "loss": 1.5498046875,
      "step": 122
    },
    {
      "epoch": 2.1964285714285716,
      "grad_norm": 0.03331408277153969,
      "learning_rate": 2.9082651630725545e-05,
      "loss": 1.513671875,
      "step": 123
    },
    {
      "epoch": 2.2142857142857144,
      "grad_norm": 0.02970796823501587,
      "learning_rate": 2.832295103267173e-05,
      "loss": 1.5185546875,
      "step": 124
    },
    {
      "epoch": 2.232142857142857,
      "grad_norm": 0.0461958684027195,
      "learning_rate": 2.7574797402851317e-05,
      "loss": 1.603515625,
      "step": 125
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.03370004892349243,
      "learning_rate": 2.683851457416681e-05,
      "loss": 1.552734375,
      "step": 126
    },
    {
      "epoch": 2.267857142857143,
      "grad_norm": 0.03142021223902702,
      "learning_rate": 2.611442124133005e-05,
      "loss": 1.4853515625,
      "step": 127
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.03187153860926628,
      "learning_rate": 2.5402830822917545e-05,
      "loss": 1.4462890625,
      "step": 128
    },
    {
      "epoch": 2.3035714285714284,
      "grad_norm": 0.033481065183877945,
      "learning_rate": 2.470405132570941e-05,
      "loss": 1.5185546875,
      "step": 129
    },
    {
      "epoch": 2.3214285714285716,
      "grad_norm": 0.03239769861102104,
      "learning_rate": 2.4018385211371003e-05,
      "loss": 1.4951171875,
      "step": 130
    },
    {
      "epoch": 2.3392857142857144,
      "grad_norm": 0.03460637107491493,
      "learning_rate": 2.334612926553444e-05,
      "loss": 1.609375,
      "step": 131
    },
    {
      "epoch": 2.357142857142857,
      "grad_norm": 0.03145774081349373,
      "learning_rate": 2.2687574469337146e-05,
      "loss": 1.4599609375,
      "step": 132
    },
    {
      "epoch": 2.375,
      "grad_norm": 0.031478624790906906,
      "learning_rate": 2.20430058734727e-05,
      "loss": 1.568359375,
      "step": 133
    },
    {
      "epoch": 2.392857142857143,
      "grad_norm": 0.030506815761327744,
      "learning_rate": 2.1412702474808782e-05,
      "loss": 1.5517578125,
      "step": 134
    },
    {
      "epoch": 2.4107142857142856,
      "grad_norm": 0.03574362397193909,
      "learning_rate": 2.0796937095625383e-05,
      "loss": 1.39453125,
      "step": 135
    },
    {
      "epoch": 2.4107142857142856,
      "eval_loss": 1.525390625,
      "eval_runtime": 0.8759,
      "eval_samples_per_second": 2.283,
      "eval_steps_per_second": 1.142,
      "step": 135
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.03553643077611923,
      "learning_rate": 2.0195976265525553e-05,
      "loss": 1.5087890625,
      "step": 136
    },
    {
      "epoch": 2.4464285714285716,
      "grad_norm": 0.03405848518013954,
      "learning_rate": 1.9610080106070086e-05,
      "loss": 1.40625,
      "step": 137
    },
    {
      "epoch": 2.4642857142857144,
      "grad_norm": 0.03616214916110039,
      "learning_rate": 1.903950221818575e-05,
      "loss": 1.416015625,
      "step": 138
    },
    {
      "epoch": 2.482142857142857,
      "grad_norm": 0.03406727313995361,
      "learning_rate": 1.8484489572395937e-05,
      "loss": 1.5244140625,
      "step": 139
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.03067430853843689,
      "learning_rate": 1.794528240192126e-05,
      "loss": 1.4951171875,
      "step": 140
    },
    {
      "epoch": 2.517857142857143,
      "grad_norm": 0.03360942751169205,
      "learning_rate": 1.742211409869636e-05,
      "loss": 1.5458984375,
      "step": 141
    },
    {
      "epoch": 2.5357142857142856,
      "grad_norm": 0.030988849699497223,
      "learning_rate": 1.6915211112347855e-05,
      "loss": 1.5322265625,
      "step": 142
    },
    {
      "epoch": 2.553571428571429,
      "grad_norm": 0.0331057533621788,
      "learning_rate": 1.642479285217728e-05,
      "loss": 1.6171875,
      "step": 143
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.0337509959936142,
      "learning_rate": 1.595107159219132e-05,
      "loss": 1.587890625,
      "step": 144
    },
    {
      "epoch": 2.5892857142857144,
      "grad_norm": 0.03541862219572067,
      "learning_rate": 1.54942523792206e-05,
      "loss": 1.5791015625,
      "step": 145
    },
    {
      "epoch": 2.607142857142857,
      "grad_norm": 0.03064841963350773,
      "learning_rate": 1.505453294416655e-05,
      "loss": 1.5009765625,
      "step": 146
    },
    {
      "epoch": 2.625,
      "grad_norm": 0.03626140207052231,
      "learning_rate": 1.4632103616415119e-05,
      "loss": 1.337890625,
      "step": 147
    },
    {
      "epoch": 2.642857142857143,
      "grad_norm": 0.03240932896733284,
      "learning_rate": 1.4227147241453987e-05,
      "loss": 1.46875,
      "step": 148
    },
    {
      "epoch": 2.6607142857142856,
      "grad_norm": 0.033992569893598557,
      "learning_rate": 1.3839839101729232e-05,
      "loss": 1.583984375,
      "step": 149
    },
    {
      "epoch": 2.678571428571429,
      "grad_norm": 0.0315067358314991,
      "learning_rate": 1.3470346840775633e-05,
      "loss": 1.3740234375,
      "step": 150
    },
    {
      "epoch": 2.696428571428571,
      "grad_norm": 0.03192545101046562,
      "learning_rate": 1.3118830390653319e-05,
      "loss": 1.4697265625,
      "step": 151
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 0.038087692111730576,
      "learning_rate": 1.2785441902722365e-05,
      "loss": 1.697265625,
      "step": 152
    },
    {
      "epoch": 2.732142857142857,
      "grad_norm": 0.03145887702703476,
      "learning_rate": 1.247032568178516e-05,
      "loss": 1.5078125,
      "step": 153
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.034711018204689026,
      "learning_rate": 1.2173618123625113e-05,
      "loss": 1.341796875,
      "step": 154
    },
    {
      "epoch": 2.767857142857143,
      "grad_norm": 0.03218483179807663,
      "learning_rate": 1.189544765596873e-05,
      "loss": 1.34375,
      "step": 155
    },
    {
      "epoch": 2.7857142857142856,
      "grad_norm": 0.02941996231675148,
      "learning_rate": 1.1635934682896586e-05,
      "loss": 1.32958984375,
      "step": 156
    },
    {
      "epoch": 2.803571428571429,
      "grad_norm": 0.03634077310562134,
      "learning_rate": 1.1395191532727306e-05,
      "loss": 1.26171875,
      "step": 157
    },
    {
      "epoch": 2.821428571428571,
      "grad_norm": 0.03490295261144638,
      "learning_rate": 1.1173322409397041e-05,
      "loss": 1.3328857421875,
      "step": 158
    },
    {
      "epoch": 2.8392857142857144,
      "grad_norm": 0.03278644382953644,
      "learning_rate": 1.0970423347355563e-05,
      "loss": 1.505859375,
      "step": 159
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.03167932853102684,
      "learning_rate": 1.0786582169998432e-05,
      "loss": 1.4267578125,
      "step": 160
    },
    {
      "epoch": 2.875,
      "grad_norm": 0.030594486743211746,
      "learning_rate": 1.0621878451653301e-05,
      "loss": 1.4541015625,
      "step": 161
    },
    {
      "epoch": 2.892857142857143,
      "grad_norm": 0.03259970620274544,
      "learning_rate": 1.0476383483136687e-05,
      "loss": 1.583984375,
      "step": 162
    },
    {
      "epoch": 2.9107142857142856,
      "grad_norm": 0.03628170117735863,
      "learning_rate": 1.0350160240896323e-05,
      "loss": 1.33984375,
      "step": 163
    },
    {
      "epoch": 2.928571428571429,
      "grad_norm": 0.032187044620513916,
      "learning_rate": 1.02432633597522e-05,
      "loss": 1.4775390625,
      "step": 164
    },
    {
      "epoch": 2.946428571428571,
      "grad_norm": 0.0323648639023304,
      "learning_rate": 1.0155739109248322e-05,
      "loss": 1.474609375,
      "step": 165
    },
    {
      "epoch": 2.9642857142857144,
      "grad_norm": 0.03791019693017006,
      "learning_rate": 1.0087625373625227e-05,
      "loss": 1.5859375,
      "step": 166
    },
    {
      "epoch": 2.982142857142857,
      "grad_norm": 0.03285396844148636,
      "learning_rate": 1.0038951635422105e-05,
      "loss": 1.4599609375,
      "step": 167
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.027538631111383438,
      "learning_rate": 1.0009738962715468e-05,
      "loss": 1.18939208984375,
      "step": 168
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.525390625,
      "eval_runtime": 0.8754,
      "eval_samples_per_second": 2.285,
      "eval_steps_per_second": 1.142,
      "step": 168
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 168,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.350376691386286e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}