{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9849108367626886,
  "eval_steps": 500,
  "global_step": 359,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0027434842249657062,
      "grad_norm": 0.6074586510658264,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.1568,
      "step": 1
    },
    {
      "epoch": 0.0054869684499314125,
      "grad_norm": 0.5766327381134033,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.1465,
      "step": 2
    },
    {
      "epoch": 0.00823045267489712,
      "grad_norm": 0.5825018882751465,
      "learning_rate": 6e-06,
      "loss": 2.1461,
      "step": 3
    },
    {
      "epoch": 0.010973936899862825,
      "grad_norm": 0.5659400820732117,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.0544,
      "step": 4
    },
    {
      "epoch": 0.013717421124828532,
      "grad_norm": 0.5868792533874512,
      "learning_rate": 1e-05,
      "loss": 2.1412,
      "step": 5
    },
    {
      "epoch": 0.01646090534979424,
      "grad_norm": 0.632855236530304,
      "learning_rate": 1.2e-05,
      "loss": 2.1954,
      "step": 6
    },
    {
      "epoch": 0.019204389574759947,
      "grad_norm": 0.5979145169258118,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 2.1389,
      "step": 7
    },
    {
      "epoch": 0.02194787379972565,
      "grad_norm": 0.5753301382064819,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.0956,
      "step": 8
    },
    {
      "epoch": 0.024691358024691357,
      "grad_norm": 0.5195829272270203,
      "learning_rate": 1.8e-05,
      "loss": 2.0257,
      "step": 9
    },
    {
      "epoch": 0.027434842249657063,
      "grad_norm": 0.5357992649078369,
      "learning_rate": 2e-05,
      "loss": 2.092,
      "step": 10
    },
    {
      "epoch": 0.03017832647462277,
      "grad_norm": 0.5315608978271484,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 2.0833,
      "step": 11
    },
    {
      "epoch": 0.03292181069958848,
      "grad_norm": 0.5084061622619629,
      "learning_rate": 2.4e-05,
      "loss": 1.9991,
      "step": 12
    },
    {
      "epoch": 0.03566529492455418,
      "grad_norm": 0.5265762805938721,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 2.0377,
      "step": 13
    },
    {
      "epoch": 0.038408779149519894,
      "grad_norm": 0.4837256669998169,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 2.0174,
      "step": 14
    },
    {
      "epoch": 0.0411522633744856,
      "grad_norm": 0.45905888080596924,
      "learning_rate": 3e-05,
      "loss": 1.9344,
      "step": 15
    },
    {
      "epoch": 0.0438957475994513,
      "grad_norm": 0.4427603483200073,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 2.0227,
      "step": 16
    },
    {
      "epoch": 0.04663923182441701,
      "grad_norm": 0.4417799413204193,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 1.959,
      "step": 17
    },
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 0.4701274633407593,
      "learning_rate": 3.6e-05,
      "loss": 2.0069,
      "step": 18
    },
    {
      "epoch": 0.05212620027434842,
      "grad_norm": 0.4195023775100708,
      "learning_rate": 3.8e-05,
      "loss": 1.9276,
      "step": 19
    },
    {
      "epoch": 0.05486968449931413,
      "grad_norm": 0.432722270488739,
      "learning_rate": 4e-05,
      "loss": 1.905,
      "step": 20
    },
    {
      "epoch": 0.05761316872427984,
      "grad_norm": 0.4493827819824219,
      "learning_rate": 4.2e-05,
      "loss": 1.9643,
      "step": 21
    },
    {
      "epoch": 0.06035665294924554,
      "grad_norm": 0.40765661001205444,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.8516,
      "step": 22
    },
    {
      "epoch": 0.06310013717421124,
      "grad_norm": 0.3817967474460602,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.8219,
      "step": 23
    },
    {
      "epoch": 0.06584362139917696,
      "grad_norm": 0.43107396364212036,
      "learning_rate": 4.8e-05,
      "loss": 1.8238,
      "step": 24
    },
    {
      "epoch": 0.06858710562414266,
      "grad_norm": 0.4179345667362213,
      "learning_rate": 5e-05,
      "loss": 1.8012,
      "step": 25
    },
    {
      "epoch": 0.07133058984910837,
      "grad_norm": 0.40421223640441895,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 1.7196,
      "step": 26
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.41145938634872437,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 1.7499,
      "step": 27
    },
    {
      "epoch": 0.07681755829903979,
      "grad_norm": 0.428116112947464,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.7127,
      "step": 28
    },
    {
      "epoch": 0.07956104252400549,
      "grad_norm": 0.41948387026786804,
      "learning_rate": 5.8e-05,
      "loss": 1.7377,
      "step": 29
    },
    {
      "epoch": 0.0823045267489712,
      "grad_norm": 0.545695424079895,
      "learning_rate": 6e-05,
      "loss": 1.6356,
      "step": 30
    },
    {
      "epoch": 0.0850480109739369,
      "grad_norm": 0.5399971008300781,
      "learning_rate": 6.2e-05,
      "loss": 1.6001,
      "step": 31
    },
    {
      "epoch": 0.0877914951989026,
      "grad_norm": 0.5631967186927795,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.5407,
      "step": 32
    },
    {
      "epoch": 0.09053497942386832,
      "grad_norm": 0.5079742670059204,
      "learning_rate": 6.6e-05,
      "loss": 1.5016,
      "step": 33
    },
    {
      "epoch": 0.09327846364883402,
      "grad_norm": 0.49909377098083496,
      "learning_rate": 6.800000000000001e-05,
      "loss": 1.5218,
      "step": 34
    },
    {
      "epoch": 0.09602194787379972,
      "grad_norm": 0.48300525546073914,
      "learning_rate": 7e-05,
      "loss": 1.447,
      "step": 35
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 0.4457314610481262,
      "learning_rate": 7.2e-05,
      "loss": 1.3801,
      "step": 36
    },
    {
      "epoch": 0.10150891632373114,
      "grad_norm": 0.35193511843681335,
      "learning_rate": 7.4e-05,
      "loss": 1.4184,
      "step": 37
    },
    {
      "epoch": 0.10425240054869685,
      "grad_norm": 0.3083098232746124,
      "learning_rate": 7.6e-05,
      "loss": 1.3298,
      "step": 38
    },
    {
      "epoch": 0.10699588477366255,
      "grad_norm": 0.265586256980896,
      "learning_rate": 7.800000000000001e-05,
      "loss": 1.3629,
      "step": 39
    },
    {
      "epoch": 0.10973936899862825,
      "grad_norm": 0.2580513656139374,
      "learning_rate": 8e-05,
      "loss": 1.4442,
      "step": 40
    },
    {
      "epoch": 0.11248285322359397,
      "grad_norm": 0.2929367423057556,
      "learning_rate": 8.2e-05,
      "loss": 1.3633,
      "step": 41
    },
    {
      "epoch": 0.11522633744855967,
      "grad_norm": 0.31172481179237366,
      "learning_rate": 8.4e-05,
      "loss": 1.3732,
      "step": 42
    },
    {
      "epoch": 0.11796982167352538,
      "grad_norm": 0.2859499752521515,
      "learning_rate": 8.6e-05,
      "loss": 1.3587,
      "step": 43
    },
    {
      "epoch": 0.12071330589849108,
      "grad_norm": 0.2899646461009979,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.369,
      "step": 44
    },
    {
      "epoch": 0.12345679012345678,
      "grad_norm": 0.3195091485977173,
      "learning_rate": 9e-05,
      "loss": 1.303,
      "step": 45
    },
    {
      "epoch": 0.1262002743484225,
      "grad_norm": 0.31914758682250977,
      "learning_rate": 9.200000000000001e-05,
      "loss": 1.3926,
      "step": 46
    },
    {
      "epoch": 0.1289437585733882,
      "grad_norm": 0.33696621656417847,
      "learning_rate": 9.4e-05,
      "loss": 1.3604,
      "step": 47
    },
    {
      "epoch": 0.13168724279835392,
      "grad_norm": 0.4222099483013153,
      "learning_rate": 9.6e-05,
      "loss": 1.292,
      "step": 48
    },
    {
      "epoch": 0.13443072702331962,
      "grad_norm": 0.43175485730171204,
      "learning_rate": 9.8e-05,
      "loss": 1.3221,
      "step": 49
    },
    {
      "epoch": 0.13717421124828533,
      "grad_norm": 0.43971532583236694,
      "learning_rate": 0.0001,
      "loss": 1.3747,
      "step": 50
    },
    {
      "epoch": 0.13991769547325103,
      "grad_norm": 0.2968728542327881,
      "learning_rate": 0.00010200000000000001,
      "loss": 1.3216,
      "step": 51
    },
    {
      "epoch": 0.14266117969821673,
      "grad_norm": 0.13912682235240936,
      "learning_rate": 0.00010400000000000001,
      "loss": 1.3066,
      "step": 52
    },
    {
      "epoch": 0.14540466392318244,
      "grad_norm": 0.12393280118703842,
      "learning_rate": 0.00010600000000000002,
      "loss": 1.2595,
      "step": 53
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.12122661620378494,
      "learning_rate": 0.00010800000000000001,
      "loss": 1.3158,
      "step": 54
    },
    {
      "epoch": 0.15089163237311384,
      "grad_norm": 0.11796235293149948,
      "learning_rate": 0.00011000000000000002,
      "loss": 1.323,
      "step": 55
    },
    {
      "epoch": 0.15363511659807957,
      "grad_norm": 0.11092036217451096,
      "learning_rate": 0.00011200000000000001,
      "loss": 1.2877,
      "step": 56
    },
    {
      "epoch": 0.15637860082304528,
      "grad_norm": 0.10956224799156189,
      "learning_rate": 0.00011399999999999999,
      "loss": 1.3014,
      "step": 57
    },
    {
      "epoch": 0.15912208504801098,
      "grad_norm": 0.11713839322328568,
      "learning_rate": 0.000116,
      "loss": 1.2416,
      "step": 58
    },
    {
      "epoch": 0.16186556927297668,
      "grad_norm": 0.10647827386856079,
      "learning_rate": 0.000118,
      "loss": 1.297,
      "step": 59
    },
    {
      "epoch": 0.1646090534979424,
      "grad_norm": 0.10844046622514725,
      "learning_rate": 0.00012,
      "loss": 1.3334,
      "step": 60
    },
    {
      "epoch": 0.1673525377229081,
      "grad_norm": 0.10903957486152649,
      "learning_rate": 0.000122,
      "loss": 1.329,
      "step": 61
    },
    {
      "epoch": 0.1700960219478738,
      "grad_norm": 0.10837563127279282,
      "learning_rate": 0.000124,
      "loss": 1.2716,
      "step": 62
    },
    {
      "epoch": 0.1728395061728395,
      "grad_norm": 0.10441155731678009,
      "learning_rate": 0.000126,
      "loss": 1.2741,
      "step": 63
    },
    {
      "epoch": 0.1755829903978052,
      "grad_norm": 0.11086488515138626,
      "learning_rate": 0.00012800000000000002,
      "loss": 1.2547,
      "step": 64
    },
    {
      "epoch": 0.17832647462277093,
      "grad_norm": 0.10411722213029861,
      "learning_rate": 0.00013000000000000002,
      "loss": 1.2762,
      "step": 65
    },
    {
      "epoch": 0.18106995884773663,
      "grad_norm": 0.10952360183000565,
      "learning_rate": 0.000132,
      "loss": 1.276,
      "step": 66
    },
    {
      "epoch": 0.18381344307270234,
      "grad_norm": 0.10990023612976074,
      "learning_rate": 0.000134,
      "loss": 1.2748,
      "step": 67
    },
    {
      "epoch": 0.18655692729766804,
      "grad_norm": 0.10912292450666428,
      "learning_rate": 0.00013600000000000003,
      "loss": 1.2952,
      "step": 68
    },
    {
      "epoch": 0.18930041152263374,
      "grad_norm": 0.1177188903093338,
      "learning_rate": 0.000138,
      "loss": 1.2501,
      "step": 69
    },
    {
      "epoch": 0.19204389574759945,
      "grad_norm": 0.14742355048656464,
      "learning_rate": 0.00014,
      "loss": 1.2025,
      "step": 70
    },
    {
      "epoch": 0.19478737997256515,
      "grad_norm": 0.10663755238056183,
      "learning_rate": 0.000142,
      "loss": 1.2154,
      "step": 71
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.10446435958147049,
      "learning_rate": 0.000144,
      "loss": 1.2468,
      "step": 72
    },
    {
      "epoch": 0.20027434842249658,
      "grad_norm": 0.1086052656173706,
      "learning_rate": 0.000146,
      "loss": 1.2536,
      "step": 73
    },
    {
      "epoch": 0.2030178326474623,
      "grad_norm": 0.10914961248636246,
      "learning_rate": 0.000148,
      "loss": 1.288,
      "step": 74
    },
    {
      "epoch": 0.205761316872428,
      "grad_norm": 0.12009298801422119,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.2902,
      "step": 75
    },
    {
      "epoch": 0.2085048010973937,
      "grad_norm": 0.11917580664157867,
      "learning_rate": 0.000152,
      "loss": 1.2666,
      "step": 76
    },
    {
      "epoch": 0.2112482853223594,
      "grad_norm": 0.11255516856908798,
      "learning_rate": 0.000154,
      "loss": 1.2585,
      "step": 77
    },
    {
      "epoch": 0.2139917695473251,
      "grad_norm": 0.11256719380617142,
      "learning_rate": 0.00015600000000000002,
      "loss": 1.238,
      "step": 78
    },
    {
      "epoch": 0.2167352537722908,
      "grad_norm": 0.11584389209747314,
      "learning_rate": 0.00015800000000000002,
      "loss": 1.2805,
      "step": 79
    },
    {
      "epoch": 0.2194787379972565,
      "grad_norm": 0.11222156882286072,
      "learning_rate": 0.00016,
      "loss": 1.2619,
      "step": 80
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.11287487298250198,
      "learning_rate": 0.000162,
      "loss": 1.2731,
      "step": 81
    },
    {
      "epoch": 0.22496570644718794,
      "grad_norm": 0.11865682899951935,
      "learning_rate": 0.000164,
      "loss": 1.2132,
      "step": 82
    },
    {
      "epoch": 0.22770919067215364,
      "grad_norm": 0.11547867953777313,
      "learning_rate": 0.000166,
      "loss": 1.3127,
      "step": 83
    },
    {
      "epoch": 0.23045267489711935,
      "grad_norm": 0.1223239153623581,
      "learning_rate": 0.000168,
      "loss": 1.1529,
      "step": 84
    },
    {
      "epoch": 0.23319615912208505,
      "grad_norm": 0.11664437502622604,
      "learning_rate": 0.00017,
      "loss": 1.2285,
      "step": 85
    },
    {
      "epoch": 0.23593964334705075,
      "grad_norm": 0.10142400115728378,
      "learning_rate": 0.000172,
      "loss": 1.2452,
      "step": 86
    },
    {
      "epoch": 0.23868312757201646,
      "grad_norm": 0.11089029908180237,
      "learning_rate": 0.000174,
      "loss": 1.266,
      "step": 87
    },
    {
      "epoch": 0.24142661179698216,
      "grad_norm": 0.12981346249580383,
      "learning_rate": 0.00017600000000000002,
      "loss": 1.3085,
      "step": 88
    },
    {
      "epoch": 0.24417009602194786,
      "grad_norm": 0.12102894484996796,
      "learning_rate": 0.00017800000000000002,
      "loss": 1.2175,
      "step": 89
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 0.11174250394105911,
      "learning_rate": 0.00018,
      "loss": 1.2406,
      "step": 90
    },
    {
      "epoch": 0.2496570644718793,
      "grad_norm": 0.11943477392196655,
      "learning_rate": 0.000182,
      "loss": 1.2109,
      "step": 91
    },
    {
      "epoch": 0.252400548696845,
      "grad_norm": 0.12101837247610092,
      "learning_rate": 0.00018400000000000003,
      "loss": 1.3023,
      "step": 92
    },
    {
      "epoch": 0.2551440329218107,
      "grad_norm": 0.12371645122766495,
      "learning_rate": 0.00018600000000000002,
      "loss": 1.2499,
      "step": 93
    },
    {
      "epoch": 0.2578875171467764,
      "grad_norm": 0.11962620168924332,
      "learning_rate": 0.000188,
      "loss": 1.2133,
      "step": 94
    },
    {
      "epoch": 0.2606310013717421,
      "grad_norm": 0.12697076797485352,
      "learning_rate": 0.00019,
      "loss": 1.2719,
      "step": 95
    },
    {
      "epoch": 0.26337448559670784,
      "grad_norm": 0.1213022917509079,
      "learning_rate": 0.000192,
      "loss": 1.2774,
      "step": 96
    },
    {
      "epoch": 0.2661179698216735,
      "grad_norm": 0.11477193981409073,
      "learning_rate": 0.000194,
      "loss": 1.25,
      "step": 97
    },
    {
      "epoch": 0.26886145404663925,
      "grad_norm": 0.1269034892320633,
      "learning_rate": 0.000196,
      "loss": 1.1812,
      "step": 98
    },
    {
      "epoch": 0.2716049382716049,
      "grad_norm": 0.130995512008667,
      "learning_rate": 0.00019800000000000002,
      "loss": 1.2416,
      "step": 99
    },
    {
      "epoch": 0.27434842249657065,
      "grad_norm": 0.13366061449050903,
      "learning_rate": 0.0002,
      "loss": 1.205,
      "step": 100
    },
    {
      "epoch": 0.27709190672153633,
      "grad_norm": 0.12534968554973602,
      "learning_rate": 0.00019924242424242426,
      "loss": 1.2261,
      "step": 101
    },
    {
      "epoch": 0.27983539094650206,
      "grad_norm": 0.1289799064397812,
      "learning_rate": 0.0001984848484848485,
      "loss": 1.216,
      "step": 102
    },
    {
      "epoch": 0.2825788751714678,
      "grad_norm": 0.12676726281642914,
      "learning_rate": 0.00019772727272727273,
      "loss": 1.199,
      "step": 103
    },
    {
      "epoch": 0.28532235939643347,
      "grad_norm": 0.12478441745042801,
      "learning_rate": 0.00019696969696969698,
      "loss": 1.2309,
      "step": 104
    },
    {
      "epoch": 0.2880658436213992,
      "grad_norm": 0.12608006596565247,
      "learning_rate": 0.00019621212121212123,
      "loss": 1.1723,
      "step": 105
    },
    {
      "epoch": 0.2908093278463649,
      "grad_norm": 0.12472855299711227,
      "learning_rate": 0.00019545454545454548,
      "loss": 1.1948,
      "step": 106
    },
    {
      "epoch": 0.2935528120713306,
      "grad_norm": 0.1230730190873146,
      "learning_rate": 0.0001946969696969697,
      "loss": 1.1945,
      "step": 107
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.12836380302906036,
      "learning_rate": 0.00019393939393939395,
      "loss": 1.1905,
      "step": 108
    },
    {
      "epoch": 0.299039780521262,
      "grad_norm": 0.12363572418689728,
      "learning_rate": 0.0001931818181818182,
      "loss": 1.2501,
      "step": 109
    },
    {
      "epoch": 0.3017832647462277,
      "grad_norm": 0.1262073963880539,
      "learning_rate": 0.00019242424242424245,
      "loss": 1.1561,
      "step": 110
    },
    {
      "epoch": 0.3045267489711934,
      "grad_norm": 0.12661714851856232,
      "learning_rate": 0.00019166666666666667,
      "loss": 1.2528,
      "step": 111
    },
    {
      "epoch": 0.30727023319615915,
      "grad_norm": 0.12602461874485016,
      "learning_rate": 0.00019090909090909092,
      "loss": 1.2469,
      "step": 112
    },
    {
      "epoch": 0.3100137174211248,
      "grad_norm": 0.13765886425971985,
      "learning_rate": 0.00019015151515151517,
      "loss": 1.2512,
      "step": 113
    },
    {
      "epoch": 0.31275720164609055,
      "grad_norm": 0.12253059446811676,
      "learning_rate": 0.00018939393939393942,
      "loss": 1.2247,
      "step": 114
    },
    {
      "epoch": 0.31550068587105623,
      "grad_norm": 0.12371920049190521,
      "learning_rate": 0.00018863636363636364,
      "loss": 1.2557,
      "step": 115
    },
    {
      "epoch": 0.31824417009602196,
      "grad_norm": 0.15333350002765656,
      "learning_rate": 0.0001878787878787879,
      "loss": 1.1535,
      "step": 116
    },
    {
      "epoch": 0.32098765432098764,
      "grad_norm": 0.13202820718288422,
      "learning_rate": 0.00018712121212121212,
      "loss": 1.2743,
      "step": 117
    },
    {
      "epoch": 0.32373113854595337,
      "grad_norm": 0.13193227350711823,
      "learning_rate": 0.00018636363636363636,
      "loss": 1.2673,
      "step": 118
    },
    {
      "epoch": 0.32647462277091904,
      "grad_norm": 0.1348859667778015,
      "learning_rate": 0.00018560606060606061,
      "loss": 1.209,
      "step": 119
    },
    {
      "epoch": 0.3292181069958848,
      "grad_norm": 0.13861852884292603,
      "learning_rate": 0.00018484848484848484,
      "loss": 1.2291,
      "step": 120
    },
    {
      "epoch": 0.3319615912208505,
      "grad_norm": 0.1280914843082428,
      "learning_rate": 0.00018409090909090909,
      "loss": 1.1393,
      "step": 121
    },
    {
      "epoch": 0.3347050754458162,
      "grad_norm": 0.13869816064834595,
      "learning_rate": 0.00018333333333333334,
      "loss": 1.2277,
      "step": 122
    },
    {
      "epoch": 0.3374485596707819,
      "grad_norm": 0.1380138099193573,
      "learning_rate": 0.00018257575757575758,
      "loss": 1.2066,
      "step": 123
    },
    {
      "epoch": 0.3401920438957476,
      "grad_norm": 0.13708218932151794,
      "learning_rate": 0.00018181818181818183,
      "loss": 1.174,
      "step": 124
    },
    {
      "epoch": 0.3429355281207133,
      "grad_norm": 0.125443235039711,
      "learning_rate": 0.00018106060606060606,
      "loss": 1.2736,
      "step": 125
    },
    {
      "epoch": 0.345679012345679,
      "grad_norm": 0.13908280432224274,
      "learning_rate": 0.0001803030303030303,
      "loss": 1.2155,
      "step": 126
    },
    {
      "epoch": 0.3484224965706447,
      "grad_norm": 0.14227597415447235,
      "learning_rate": 0.00017954545454545456,
      "loss": 1.2282,
      "step": 127
    },
    {
      "epoch": 0.3511659807956104,
      "grad_norm": 0.13010729849338531,
      "learning_rate": 0.0001787878787878788,
      "loss": 1.2777,
      "step": 128
    },
    {
      "epoch": 0.35390946502057613,
      "grad_norm": 0.1324704885482788,
      "learning_rate": 0.00017803030303030303,
      "loss": 1.2535,
      "step": 129
    },
    {
      "epoch": 0.35665294924554186,
      "grad_norm": 0.13774098455905914,
      "learning_rate": 0.00017727272727272728,
      "loss": 1.2133,
      "step": 130
    },
    {
      "epoch": 0.35939643347050754,
      "grad_norm": 0.1329461932182312,
      "learning_rate": 0.00017651515151515153,
      "loss": 1.1306,
      "step": 131
    },
    {
      "epoch": 0.36213991769547327,
      "grad_norm": 0.13212774693965912,
      "learning_rate": 0.00017575757575757578,
      "loss": 1.2104,
      "step": 132
    },
    {
      "epoch": 0.36488340192043894,
      "grad_norm": 0.12930439412593842,
      "learning_rate": 0.000175,
      "loss": 1.1945,
      "step": 133
    },
    {
      "epoch": 0.3676268861454047,
      "grad_norm": 0.12622064352035522,
      "learning_rate": 0.00017424242424242425,
      "loss": 1.1859,
      "step": 134
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.13031360507011414,
      "learning_rate": 0.0001734848484848485,
      "loss": 1.093,
      "step": 135
    },
    {
      "epoch": 0.3731138545953361,
      "grad_norm": 0.13444660604000092,
      "learning_rate": 0.00017272727272727275,
      "loss": 1.1753,
      "step": 136
    },
    {
      "epoch": 0.37585733882030176,
      "grad_norm": 0.1323116570711136,
      "learning_rate": 0.00017196969696969697,
      "loss": 1.2346,
      "step": 137
    },
    {
      "epoch": 0.3786008230452675,
      "grad_norm": 0.13350705802440643,
      "learning_rate": 0.00017121212121212122,
      "loss": 1.2124,
      "step": 138
    },
    {
      "epoch": 0.3813443072702332,
      "grad_norm": 0.12250819057226181,
      "learning_rate": 0.00017045454545454547,
      "loss": 1.2065,
      "step": 139
    },
    {
      "epoch": 0.3840877914951989,
      "grad_norm": 0.138210266828537,
      "learning_rate": 0.00016969696969696972,
      "loss": 1.2053,
      "step": 140
    },
    {
      "epoch": 0.3868312757201646,
      "grad_norm": 0.1434732973575592,
      "learning_rate": 0.00016893939393939394,
      "loss": 1.1628,
      "step": 141
    },
    {
      "epoch": 0.3895747599451303,
      "grad_norm": 0.13517875969409943,
      "learning_rate": 0.0001681818181818182,
      "loss": 1.2118,
      "step": 142
    },
    {
      "epoch": 0.39231824417009603,
      "grad_norm": 0.13874825835227966,
      "learning_rate": 0.00016742424242424244,
      "loss": 1.1624,
      "step": 143
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.1482028067111969,
      "learning_rate": 0.0001666666666666667,
      "loss": 1.1854,
      "step": 144
    },
    {
      "epoch": 0.39780521262002744,
      "grad_norm": 0.13481967151165009,
      "learning_rate": 0.00016590909090909094,
      "loss": 1.1511,
      "step": 145
    },
    {
      "epoch": 0.40054869684499317,
      "grad_norm": 0.14075712859630585,
      "learning_rate": 0.00016515151515151516,
      "loss": 1.1971,
      "step": 146
    },
    {
      "epoch": 0.40329218106995884,
      "grad_norm": 0.14305728673934937,
      "learning_rate": 0.0001643939393939394,
      "loss": 1.176,
      "step": 147
    },
    {
      "epoch": 0.4060356652949246,
      "grad_norm": 0.13893045485019684,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.1677,
      "step": 148
    },
    {
      "epoch": 0.40877914951989025,
      "grad_norm": 0.1311769336462021,
      "learning_rate": 0.0001628787878787879,
      "loss": 1.1993,
      "step": 149
    },
    {
      "epoch": 0.411522633744856,
      "grad_norm": 0.14383293688297272,
      "learning_rate": 0.00016212121212121213,
      "loss": 1.166,
      "step": 150
    },
    {
      "epoch": 0.41426611796982166,
      "grad_norm": 0.13200797140598297,
      "learning_rate": 0.00016136363636363635,
      "loss": 1.265,
      "step": 151
    },
    {
      "epoch": 0.4170096021947874,
      "grad_norm": 0.14447088539600372,
      "learning_rate": 0.0001606060606060606,
      "loss": 1.1743,
      "step": 152
    },
    {
      "epoch": 0.41975308641975306,
      "grad_norm": 0.1543964296579361,
      "learning_rate": 0.00015984848484848485,
      "loss": 1.2143,
      "step": 153
    },
    {
      "epoch": 0.4224965706447188,
      "grad_norm": 0.13928011059761047,
      "learning_rate": 0.0001590909090909091,
      "loss": 1.1567,
      "step": 154
    },
    {
      "epoch": 0.4252400548696845,
      "grad_norm": 0.13484956324100494,
      "learning_rate": 0.00015833333333333332,
      "loss": 1.1713,
      "step": 155
    },
    {
      "epoch": 0.4279835390946502,
      "grad_norm": 0.13763906061649323,
      "learning_rate": 0.00015757575757575757,
      "loss": 1.1737,
      "step": 156
    },
    {
      "epoch": 0.43072702331961593,
      "grad_norm": 0.14292830228805542,
      "learning_rate": 0.00015681818181818182,
      "loss": 1.1901,
      "step": 157
    },
    {
      "epoch": 0.4334705075445816,
      "grad_norm": 0.12830933928489685,
      "learning_rate": 0.00015606060606060607,
      "loss": 1.2643,
      "step": 158
    },
    {
      "epoch": 0.43621399176954734,
      "grad_norm": 0.12799011170864105,
      "learning_rate": 0.0001553030303030303,
      "loss": 1.2154,
      "step": 159
    },
    {
      "epoch": 0.438957475994513,
      "grad_norm": 0.13630235195159912,
      "learning_rate": 0.00015454545454545454,
      "loss": 1.2379,
      "step": 160
    },
    {
      "epoch": 0.44170096021947874,
      "grad_norm": 0.13912957906723022,
      "learning_rate": 0.0001537878787878788,
      "loss": 1.2495,
      "step": 161
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.13462527096271515,
      "learning_rate": 0.00015303030303030304,
      "loss": 1.1617,
      "step": 162
    },
    {
      "epoch": 0.44718792866941015,
      "grad_norm": 0.13256517052650452,
      "learning_rate": 0.00015227272727272727,
      "loss": 1.1883,
      "step": 163
    },
    {
      "epoch": 0.4499314128943759,
      "grad_norm": 0.1430547535419464,
      "learning_rate": 0.00015151515151515152,
      "loss": 1.1523,
      "step": 164
    },
    {
      "epoch": 0.45267489711934156,
      "grad_norm": 0.1347552239894867,
      "learning_rate": 0.00015075757575757576,
      "loss": 1.2261,
      "step": 165
    },
    {
      "epoch": 0.4554183813443073,
      "grad_norm": 0.15575383603572845,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.2157,
      "step": 166
    },
    {
      "epoch": 0.45816186556927296,
      "grad_norm": 0.14620648324489594,
      "learning_rate": 0.00014924242424242426,
      "loss": 1.1921,
      "step": 167
    },
    {
      "epoch": 0.4609053497942387,
      "grad_norm": 0.13227321207523346,
      "learning_rate": 0.00014848484848484849,
      "loss": 1.207,
      "step": 168
    },
    {
      "epoch": 0.46364883401920437,
      "grad_norm": 0.14103803038597107,
      "learning_rate": 0.00014772727272727274,
      "loss": 1.1942,
      "step": 169
    },
    {
      "epoch": 0.4663923182441701,
      "grad_norm": 0.13593865931034088,
      "learning_rate": 0.00014696969696969698,
      "loss": 1.2715,
      "step": 170
    },
    {
      "epoch": 0.4691358024691358,
      "grad_norm": 0.13080817461013794,
      "learning_rate": 0.00014621212121212123,
      "loss": 1.2077,
      "step": 171
    },
    {
      "epoch": 0.4718792866941015,
      "grad_norm": 0.12909549474716187,
      "learning_rate": 0.00014545454545454546,
      "loss": 1.1956,
      "step": 172
    },
    {
      "epoch": 0.47462277091906724,
      "grad_norm": 0.13933488726615906,
      "learning_rate": 0.0001446969696969697,
      "loss": 1.0971,
      "step": 173
    },
    {
      "epoch": 0.4773662551440329,
      "grad_norm": 0.13717928528785706,
      "learning_rate": 0.00014393939393939396,
      "loss": 1.2211,
      "step": 174
    },
    {
      "epoch": 0.48010973936899864,
      "grad_norm": 0.13049401342868805,
      "learning_rate": 0.0001431818181818182,
      "loss": 1.185,
      "step": 175
    },
    {
      "epoch": 0.4828532235939643,
      "grad_norm": 0.1361015886068344,
      "learning_rate": 0.00014242424242424243,
      "loss": 1.1822,
      "step": 176
    },
    {
      "epoch": 0.48559670781893005,
      "grad_norm": 0.13388365507125854,
      "learning_rate": 0.00014166666666666668,
      "loss": 1.1982,
      "step": 177
    },
    {
      "epoch": 0.4883401920438957,
      "grad_norm": 0.13773706555366516,
      "learning_rate": 0.00014090909090909093,
      "loss": 1.1974,
      "step": 178
    },
    {
      "epoch": 0.49108367626886146,
      "grad_norm": 0.14087523519992828,
      "learning_rate": 0.00014015151515151518,
      "loss": 1.2194,
      "step": 179
    },
    {
      "epoch": 0.49382716049382713,
      "grad_norm": 0.14080990850925446,
      "learning_rate": 0.0001393939393939394,
      "loss": 1.1648,
      "step": 180
    },
    {
      "epoch": 0.49657064471879286,
      "grad_norm": 0.14020459353923798,
      "learning_rate": 0.00013863636363636365,
      "loss": 1.1467,
      "step": 181
    },
    {
      "epoch": 0.4993141289437586,
      "grad_norm": 0.14013905823230743,
      "learning_rate": 0.0001378787878787879,
      "loss": 1.1492,
      "step": 182
    },
    {
      "epoch": 0.5020576131687243,
      "grad_norm": 0.13879725337028503,
      "learning_rate": 0.00013712121212121212,
      "loss": 1.1987,
      "step": 183
    },
    {
      "epoch": 0.50480109739369,
      "grad_norm": 0.1356627494096756,
      "learning_rate": 0.00013636363636363637,
      "loss": 1.2085,
      "step": 184
    },
    {
      "epoch": 0.5075445816186557,
      "grad_norm": 0.13748306035995483,
      "learning_rate": 0.0001356060606060606,
      "loss": 1.172,
      "step": 185
    },
    {
      "epoch": 0.5102880658436214,
      "grad_norm": 0.13760589063167572,
      "learning_rate": 0.00013484848484848484,
      "loss": 1.2179,
      "step": 186
    },
    {
      "epoch": 0.5130315500685871,
      "grad_norm": 0.14484421908855438,
      "learning_rate": 0.0001340909090909091,
      "loss": 1.1694,
      "step": 187
    },
    {
      "epoch": 0.5157750342935528,
      "grad_norm": 0.14494763314723969,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.1867,
      "step": 188
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 0.14251911640167236,
      "learning_rate": 0.00013257575757575756,
      "loss": 1.1671,
      "step": 189
    },
    {
      "epoch": 0.5212620027434842,
      "grad_norm": 0.14094440639019012,
      "learning_rate": 0.0001318181818181818,
      "loss": 1.2064,
      "step": 190
    },
    {
      "epoch": 0.52400548696845,
      "grad_norm": 0.14112092554569244,
      "learning_rate": 0.00013106060606060606,
      "loss": 1.2272,
      "step": 191
    },
    {
      "epoch": 0.5267489711934157,
      "grad_norm": 0.14907369017601013,
      "learning_rate": 0.0001303030303030303,
      "loss": 1.1632,
      "step": 192
    },
    {
      "epoch": 0.5294924554183813,
      "grad_norm": 0.15514911711215973,
      "learning_rate": 0.00012954545454545456,
      "loss": 1.171,
      "step": 193
    },
    {
      "epoch": 0.532235939643347,
      "grad_norm": 0.14109738171100616,
      "learning_rate": 0.00012878787878787878,
      "loss": 1.1573,
      "step": 194
    },
    {
      "epoch": 0.5349794238683128,
      "grad_norm": 0.1382451355457306,
      "learning_rate": 0.00012803030303030303,
      "loss": 1.1504,
      "step": 195
    },
    {
      "epoch": 0.5377229080932785,
      "grad_norm": 0.13393574953079224,
      "learning_rate": 0.00012727272727272728,
      "loss": 1.1955,
      "step": 196
    },
    {
      "epoch": 0.5404663923182441,
      "grad_norm": 0.14956636726856232,
      "learning_rate": 0.00012651515151515153,
      "loss": 1.2071,
      "step": 197
    },
    {
      "epoch": 0.5432098765432098,
      "grad_norm": 0.15119844675064087,
      "learning_rate": 0.00012575757575757575,
      "loss": 1.1616,
      "step": 198
    },
    {
      "epoch": 0.5459533607681756,
      "grad_norm": 0.1471070796251297,
      "learning_rate": 0.000125,
      "loss": 1.1233,
      "step": 199
    },
    {
      "epoch": 0.5486968449931413,
      "grad_norm": 0.1441928595304489,
      "learning_rate": 0.00012424242424242425,
      "loss": 1.155,
      "step": 200
    },
    {
      "epoch": 0.551440329218107,
      "grad_norm": 0.14804790914058685,
      "learning_rate": 0.0001234848484848485,
      "loss": 1.1586,
      "step": 201
    },
    {
      "epoch": 0.5541838134430727,
      "grad_norm": 0.14373962581157684,
      "learning_rate": 0.00012272727272727272,
      "loss": 1.2196,
      "step": 202
    },
    {
      "epoch": 0.5569272976680384,
      "grad_norm": 0.13827867805957794,
      "learning_rate": 0.00012196969696969697,
      "loss": 1.1873,
      "step": 203
    },
    {
      "epoch": 0.5596707818930041,
      "grad_norm": 0.14825958013534546,
      "learning_rate": 0.00012121212121212122,
      "loss": 1.0936,
      "step": 204
    },
    {
      "epoch": 0.5624142661179699,
      "grad_norm": 0.1411331444978714,
      "learning_rate": 0.00012045454545454546,
      "loss": 1.1836,
      "step": 205
    },
    {
      "epoch": 0.5651577503429356,
      "grad_norm": 0.1412888914346695,
      "learning_rate": 0.00011969696969696971,
      "loss": 1.1326,
      "step": 206
    },
    {
      "epoch": 0.5679012345679012,
      "grad_norm": 0.14326925575733185,
      "learning_rate": 0.00011893939393939394,
      "loss": 1.1856,
      "step": 207
    },
    {
      "epoch": 0.5706447187928669,
      "grad_norm": 0.17105036973953247,
      "learning_rate": 0.0001181818181818182,
      "loss": 1.2073,
      "step": 208
    },
    {
      "epoch": 0.5733882030178327,
      "grad_norm": 0.14649122953414917,
      "learning_rate": 0.00011742424242424244,
      "loss": 1.1544,
      "step": 209
    },
    {
      "epoch": 0.5761316872427984,
      "grad_norm": 0.14801283180713654,
      "learning_rate": 0.00011666666666666668,
      "loss": 1.1841,
      "step": 210
    },
    {
      "epoch": 0.578875171467764,
      "grad_norm": 0.16375355422496796,
      "learning_rate": 0.00011590909090909093,
      "loss": 1.1342,
      "step": 211
    },
    {
      "epoch": 0.5816186556927297,
      "grad_norm": 0.1525164395570755,
      "learning_rate": 0.00011515151515151516,
      "loss": 1.2295,
      "step": 212
    },
    {
      "epoch": 0.5843621399176955,
      "grad_norm": 0.15184175968170166,
      "learning_rate": 0.00011439393939393941,
      "loss": 1.1239,
      "step": 213
    },
    {
      "epoch": 0.5871056241426612,
      "grad_norm": 0.15737642347812653,
      "learning_rate": 0.00011363636363636365,
      "loss": 1.1897,
      "step": 214
    },
    {
      "epoch": 0.5898491083676269,
      "grad_norm": 0.15543530881404877,
      "learning_rate": 0.0001128787878787879,
      "loss": 1.1136,
      "step": 215
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.14131884276866913,
      "learning_rate": 0.00011212121212121212,
      "loss": 1.1506,
      "step": 216
    },
    {
      "epoch": 0.5953360768175583,
      "grad_norm": 0.15615688264369965,
      "learning_rate": 0.00011136363636363636,
      "loss": 1.2084,
      "step": 217
    },
    {
      "epoch": 0.598079561042524,
      "grad_norm": 0.1592538207769394,
      "learning_rate": 0.00011060606060606061,
      "loss": 1.1689,
      "step": 218
    },
    {
      "epoch": 0.6008230452674898,
      "grad_norm": 0.15168730914592743,
      "learning_rate": 0.00010984848484848484,
      "loss": 1.1014,
      "step": 219
    },
    {
      "epoch": 0.6035665294924554,
      "grad_norm": 0.1536811888217926,
      "learning_rate": 0.00010909090909090909,
      "loss": 1.2057,
      "step": 220
    },
    {
      "epoch": 0.6063100137174211,
      "grad_norm": 0.1643233597278595,
      "learning_rate": 0.00010833333333333333,
      "loss": 1.1696,
      "step": 221
    },
    {
      "epoch": 0.6090534979423868,
      "grad_norm": 0.1531713455915451,
      "learning_rate": 0.00010757575757575758,
      "loss": 1.1284,
      "step": 222
    },
    {
      "epoch": 0.6117969821673526,
      "grad_norm": 0.1448834389448166,
      "learning_rate": 0.00010681818181818181,
      "loss": 1.1289,
      "step": 223
    },
    {
      "epoch": 0.6145404663923183,
      "grad_norm": 0.14703518152236938,
      "learning_rate": 0.00010606060606060606,
      "loss": 1.1442,
      "step": 224
    },
    {
      "epoch": 0.6172839506172839,
      "grad_norm": 0.1512955129146576,
      "learning_rate": 0.0001053030303030303,
      "loss": 1.2112,
      "step": 225
    },
    {
      "epoch": 0.6200274348422496,
      "grad_norm": 0.15667341649532318,
      "learning_rate": 0.00010454545454545455,
      "loss": 1.1136,
      "step": 226
    },
    {
      "epoch": 0.6227709190672154,
      "grad_norm": 0.14724792540073395,
      "learning_rate": 0.00010378787878787878,
      "loss": 1.1931,
      "step": 227
    },
    {
      "epoch": 0.6255144032921811,
      "grad_norm": 0.15891985595226288,
      "learning_rate": 0.00010303030303030303,
      "loss": 1.1633,
      "step": 228
    },
    {
      "epoch": 0.6282578875171467,
      "grad_norm": 0.14001834392547607,
      "learning_rate": 0.00010227272727272727,
      "loss": 1.1874,
      "step": 229
    },
    {
      "epoch": 0.6310013717421125,
      "grad_norm": 0.15052121877670288,
      "learning_rate": 0.00010151515151515152,
      "loss": 1.09,
      "step": 230
    },
    {
      "epoch": 0.6337448559670782,
      "grad_norm": 0.14121738076210022,
      "learning_rate": 0.00010075757575757576,
      "loss": 1.1497,
      "step": 231
    },
    {
      "epoch": 0.6364883401920439,
      "grad_norm": 0.1552361249923706,
      "learning_rate": 0.0001,
      "loss": 1.1817,
      "step": 232
    },
    {
      "epoch": 0.6392318244170097,
      "grad_norm": 0.1574372947216034,
      "learning_rate": 9.924242424242425e-05,
      "loss": 1.0996,
      "step": 233
    },
    {
      "epoch": 0.6419753086419753,
      "grad_norm": 0.14911417663097382,
      "learning_rate": 9.848484848484849e-05,
      "loss": 1.1423,
      "step": 234
    },
    {
      "epoch": 0.644718792866941,
      "grad_norm": 0.15630194544792175,
      "learning_rate": 9.772727272727274e-05,
      "loss": 1.1107,
      "step": 235
    },
    {
      "epoch": 0.6474622770919067,
      "grad_norm": 0.14229367673397064,
      "learning_rate": 9.696969696969698e-05,
      "loss": 1.1841,
      "step": 236
    },
    {
      "epoch": 0.6502057613168725,
      "grad_norm": 0.1572859138250351,
      "learning_rate": 9.621212121212123e-05,
      "loss": 1.1164,
      "step": 237
    },
    {
      "epoch": 0.6529492455418381,
      "grad_norm": 0.1567874550819397,
      "learning_rate": 9.545454545454546e-05,
      "loss": 1.1515,
      "step": 238
    },
    {
      "epoch": 0.6556927297668038,
      "grad_norm": 0.14123088121414185,
      "learning_rate": 9.469696969696971e-05,
      "loss": 1.154,
      "step": 239
    },
    {
      "epoch": 0.6584362139917695,
      "grad_norm": 0.1481737494468689,
      "learning_rate": 9.393939393939395e-05,
      "loss": 1.1871,
      "step": 240
    },
    {
      "epoch": 0.6611796982167353,
      "grad_norm": 0.13703057169914246,
      "learning_rate": 9.318181818181818e-05,
      "loss": 1.1566,
      "step": 241
    },
    {
      "epoch": 0.663923182441701,
      "grad_norm": 0.14939849078655243,
      "learning_rate": 9.242424242424242e-05,
      "loss": 1.2258,
      "step": 242
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.14865128695964813,
      "learning_rate": 9.166666666666667e-05,
      "loss": 1.1157,
      "step": 243
    },
    {
      "epoch": 0.6694101508916324,
      "grad_norm": 0.15554259717464447,
      "learning_rate": 9.090909090909092e-05,
      "loss": 1.098,
      "step": 244
    },
    {
      "epoch": 0.6721536351165981,
      "grad_norm": 0.16377362608909607,
      "learning_rate": 9.015151515151515e-05,
      "loss": 1.1505,
      "step": 245
    },
    {
      "epoch": 0.6748971193415638,
      "grad_norm": 0.15537135303020477,
      "learning_rate": 8.93939393939394e-05,
      "loss": 1.137,
      "step": 246
    },
    {
      "epoch": 0.6776406035665294,
      "grad_norm": 0.14978918433189392,
      "learning_rate": 8.863636363636364e-05,
      "loss": 1.1508,
      "step": 247
    },
    {
      "epoch": 0.6803840877914952,
      "grad_norm": 0.15097349882125854,
      "learning_rate": 8.787878787878789e-05,
      "loss": 1.15,
      "step": 248
    },
    {
      "epoch": 0.6831275720164609,
      "grad_norm": 0.15233929455280304,
      "learning_rate": 8.712121212121212e-05,
      "loss": 1.1539,
      "step": 249
    },
    {
      "epoch": 0.6858710562414266,
      "grad_norm": 0.15705512464046478,
      "learning_rate": 8.636363636363637e-05,
      "loss": 1.1405,
      "step": 250
    },
    {
      "epoch": 0.6886145404663924,
      "grad_norm": 0.15354318916797638,
      "learning_rate": 8.560606060606061e-05,
      "loss": 1.1616,
      "step": 251
    },
    {
      "epoch": 0.691358024691358,
      "grad_norm": 0.15249384939670563,
      "learning_rate": 8.484848484848486e-05,
      "loss": 1.1102,
      "step": 252
    },
    {
      "epoch": 0.6941015089163237,
      "grad_norm": 0.13984158635139465,
      "learning_rate": 8.40909090909091e-05,
      "loss": 1.1052,
      "step": 253
    },
    {
      "epoch": 0.6968449931412894,
      "grad_norm": 0.14617910981178284,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.1527,
      "step": 254
    },
    {
      "epoch": 0.6995884773662552,
      "grad_norm": 0.14850248396396637,
      "learning_rate": 8.257575757575758e-05,
      "loss": 1.1607,
      "step": 255
    },
    {
      "epoch": 0.7023319615912208,
      "grad_norm": 0.15168701112270355,
      "learning_rate": 8.181818181818183e-05,
      "loss": 1.1315,
      "step": 256
    },
    {
      "epoch": 0.7050754458161865,
      "grad_norm": 0.146399587392807,
      "learning_rate": 8.106060606060607e-05,
      "loss": 1.1245,
      "step": 257
    },
    {
      "epoch": 0.7078189300411523,
      "grad_norm": 0.14249610900878906,
      "learning_rate": 8.03030303030303e-05,
      "loss": 1.1591,
      "step": 258
    },
    {
      "epoch": 0.710562414266118,
      "grad_norm": 0.14735598862171173,
      "learning_rate": 7.954545454545455e-05,
      "loss": 1.1549,
      "step": 259
    },
    {
      "epoch": 0.7133058984910837,
      "grad_norm": 0.14987659454345703,
      "learning_rate": 7.878787878787879e-05,
      "loss": 1.1306,
      "step": 260
    },
    {
      "epoch": 0.7160493827160493,
      "grad_norm": 0.14539968967437744,
      "learning_rate": 7.803030303030304e-05,
      "loss": 1.1252,
      "step": 261
    },
    {
      "epoch": 0.7187928669410151,
      "grad_norm": 0.14629240334033966,
      "learning_rate": 7.727272727272727e-05,
      "loss": 1.2503,
      "step": 262
    },
    {
      "epoch": 0.7215363511659808,
      "grad_norm": 0.14406025409698486,
      "learning_rate": 7.651515151515152e-05,
      "loss": 1.2158,
      "step": 263
    },
    {
      "epoch": 0.7242798353909465,
      "grad_norm": 0.13776946067810059,
      "learning_rate": 7.575757575757576e-05,
      "loss": 1.1858,
      "step": 264
    },
    {
      "epoch": 0.7270233196159122,
      "grad_norm": 0.14212195575237274,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.1548,
      "step": 265
    },
    {
      "epoch": 0.7297668038408779,
      "grad_norm": 0.14300891757011414,
      "learning_rate": 7.424242424242424e-05,
      "loss": 1.0709,
      "step": 266
    },
    {
      "epoch": 0.7325102880658436,
      "grad_norm": 0.14611689746379852,
      "learning_rate": 7.348484848484849e-05,
      "loss": 1.1638,
      "step": 267
    },
    {
      "epoch": 0.7352537722908093,
      "grad_norm": 0.15235215425491333,
      "learning_rate": 7.272727272727273e-05,
      "loss": 1.1822,
      "step": 268
    },
    {
      "epoch": 0.7379972565157751,
      "grad_norm": 0.1419045776128769,
      "learning_rate": 7.196969696969698e-05,
      "loss": 1.17,
      "step": 269
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.1524955779314041,
      "learning_rate": 7.121212121212121e-05,
      "loss": 1.1364,
      "step": 270
    },
    {
      "epoch": 0.7434842249657064,
      "grad_norm": 0.14928361773490906,
      "learning_rate": 7.045454545454546e-05,
      "loss": 1.0939,
      "step": 271
    },
    {
      "epoch": 0.7462277091906722,
      "grad_norm": 0.1466515064239502,
      "learning_rate": 6.96969696969697e-05,
      "loss": 1.1515,
      "step": 272
    },
    {
      "epoch": 0.7489711934156379,
      "grad_norm": 0.14846271276474,
      "learning_rate": 6.893939393939395e-05,
      "loss": 1.1361,
      "step": 273
    },
    {
      "epoch": 0.7517146776406035,
      "grad_norm": 0.14629323780536652,
      "learning_rate": 6.818181818181818e-05,
      "loss": 1.1065,
      "step": 274
    },
    {
      "epoch": 0.7544581618655692,
      "grad_norm": 0.13390295207500458,
      "learning_rate": 6.742424242424242e-05,
      "loss": 1.1923,
      "step": 275
    },
    {
      "epoch": 0.757201646090535,
      "grad_norm": 0.14943355321884155,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.219,
      "step": 276
    },
    {
      "epoch": 0.7599451303155007,
      "grad_norm": 0.1472519487142563,
      "learning_rate": 6.59090909090909e-05,
      "loss": 1.1248,
      "step": 277
    },
    {
      "epoch": 0.7626886145404664,
      "grad_norm": 0.15139643847942352,
      "learning_rate": 6.515151515151516e-05,
      "loss": 1.1212,
      "step": 278
    },
    {
      "epoch": 0.7654320987654321,
      "grad_norm": 0.16161853075027466,
      "learning_rate": 6.439393939393939e-05,
      "loss": 1.1637,
      "step": 279
    },
    {
      "epoch": 0.7681755829903978,
      "grad_norm": 0.15895844995975494,
      "learning_rate": 6.363636363636364e-05,
      "loss": 1.1362,
      "step": 280
    },
    {
      "epoch": 0.7709190672153635,
      "grad_norm": 0.1536717712879181,
      "learning_rate": 6.287878787878788e-05,
      "loss": 1.1876,
      "step": 281
    },
    {
      "epoch": 0.7736625514403292,
      "grad_norm": 0.1485566794872284,
      "learning_rate": 6.212121212121213e-05,
      "loss": 1.1823,
      "step": 282
    },
    {
      "epoch": 0.7764060356652949,
      "grad_norm": 0.13889138400554657,
      "learning_rate": 6.136363636363636e-05,
      "loss": 1.1295,
      "step": 283
    },
    {
      "epoch": 0.7791495198902606,
      "grad_norm": 0.14785881340503693,
      "learning_rate": 6.060606060606061e-05,
      "loss": 1.1225,
      "step": 284
    },
    {
      "epoch": 0.7818930041152263,
      "grad_norm": 0.14757974445819855,
      "learning_rate": 5.9848484848484854e-05,
      "loss": 1.1954,
      "step": 285
    },
    {
      "epoch": 0.7846364883401921,
      "grad_norm": 0.15435774624347687,
      "learning_rate": 5.90909090909091e-05,
      "loss": 1.1889,
      "step": 286
    },
    {
      "epoch": 0.7873799725651578,
      "grad_norm": 0.15265783667564392,
      "learning_rate": 5.833333333333334e-05,
      "loss": 1.1436,
      "step": 287
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.15070180594921112,
      "learning_rate": 5.757575757575758e-05,
      "loss": 1.1299,
      "step": 288
    },
    {
      "epoch": 0.7928669410150891,
      "grad_norm": 0.1602925956249237,
      "learning_rate": 5.6818181818181825e-05,
      "loss": 1.1028,
      "step": 289
    },
    {
      "epoch": 0.7956104252400549,
      "grad_norm": 0.15184776484966278,
      "learning_rate": 5.606060606060606e-05,
      "loss": 1.1499,
      "step": 290
    },
    {
      "epoch": 0.7983539094650206,
      "grad_norm": 0.1467025876045227,
      "learning_rate": 5.5303030303030304e-05,
      "loss": 1.1864,
      "step": 291
    },
    {
      "epoch": 0.8010973936899863,
      "grad_norm": 0.15920227766036987,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 1.1399,
      "step": 292
    },
    {
      "epoch": 0.803840877914952,
      "grad_norm": 0.14726729691028595,
      "learning_rate": 5.378787878787879e-05,
      "loss": 1.162,
      "step": 293
    },
    {
      "epoch": 0.8065843621399177,
      "grad_norm": 0.140202596783638,
      "learning_rate": 5.303030303030303e-05,
      "loss": 1.2203,
      "step": 294
    },
    {
      "epoch": 0.8093278463648834,
      "grad_norm": 0.15306006371974945,
      "learning_rate": 5.2272727272727274e-05,
      "loss": 1.1606,
      "step": 295
    },
    {
      "epoch": 0.8120713305898491,
      "grad_norm": 0.14972694218158722,
      "learning_rate": 5.151515151515152e-05,
      "loss": 1.0759,
      "step": 296
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 0.15497860312461853,
      "learning_rate": 5.075757575757576e-05,
      "loss": 1.1851,
      "step": 297
    },
    {
      "epoch": 0.8175582990397805,
      "grad_norm": 0.1477072685956955,
      "learning_rate": 5e-05,
      "loss": 1.112,
      "step": 298
    },
    {
      "epoch": 0.8203017832647462,
      "grad_norm": 0.16297776997089386,
      "learning_rate": 4.9242424242424245e-05,
      "loss": 1.1104,
      "step": 299
    },
    {
      "epoch": 0.823045267489712,
      "grad_norm": 0.15384162962436676,
      "learning_rate": 4.848484848484849e-05,
      "loss": 1.0494,
      "step": 300
    },
    {
      "epoch": 0.8257887517146777,
      "grad_norm": 0.15182934701442719,
      "learning_rate": 4.772727272727273e-05,
      "loss": 1.0792,
      "step": 301
    },
    {
      "epoch": 0.8285322359396433,
      "grad_norm": 0.16001427173614502,
      "learning_rate": 4.696969696969697e-05,
      "loss": 1.1813,
      "step": 302
    },
    {
      "epoch": 0.831275720164609,
      "grad_norm": 0.14563636481761932,
      "learning_rate": 4.621212121212121e-05,
      "loss": 1.1813,
      "step": 303
    },
    {
      "epoch": 0.8340192043895748,
      "grad_norm": 0.15218865871429443,
      "learning_rate": 4.545454545454546e-05,
      "loss": 1.129,
      "step": 304
    },
    {
      "epoch": 0.8367626886145405,
      "grad_norm": 0.1515151560306549,
      "learning_rate": 4.46969696969697e-05,
      "loss": 1.1148,
      "step": 305
    },
    {
      "epoch": 0.8395061728395061,
      "grad_norm": 0.1410326212644577,
      "learning_rate": 4.3939393939393944e-05,
      "loss": 1.1645,
      "step": 306
    },
    {
      "epoch": 0.8422496570644719,
      "grad_norm": 0.1482207179069519,
      "learning_rate": 4.318181818181819e-05,
      "loss": 1.2049,
      "step": 307
    },
    {
      "epoch": 0.8449931412894376,
      "grad_norm": 0.14518232643604279,
      "learning_rate": 4.242424242424243e-05,
      "loss": 1.1141,
      "step": 308
    },
    {
      "epoch": 0.8477366255144033,
      "grad_norm": 0.14942567050457,
      "learning_rate": 4.166666666666667e-05,
      "loss": 1.2666,
      "step": 309
    },
    {
      "epoch": 0.850480109739369,
      "grad_norm": 0.15370970964431763,
      "learning_rate": 4.0909090909090915e-05,
      "loss": 1.1235,
      "step": 310
    },
    {
      "epoch": 0.8532235939643347,
      "grad_norm": 0.153873473405838,
      "learning_rate": 4.015151515151515e-05,
      "loss": 1.1202,
      "step": 311
    },
    {
      "epoch": 0.8559670781893004,
      "grad_norm": 0.1411074697971344,
      "learning_rate": 3.939393939393939e-05,
      "loss": 1.1945,
      "step": 312
    },
    {
      "epoch": 0.8587105624142661,
      "grad_norm": 0.14101877808570862,
      "learning_rate": 3.8636363636363636e-05,
      "loss": 1.1682,
      "step": 313
    },
    {
      "epoch": 0.8614540466392319,
      "grad_norm": 0.14634057879447937,
      "learning_rate": 3.787878787878788e-05,
      "loss": 1.2108,
      "step": 314
    },
    {
      "epoch": 0.8641975308641975,
      "grad_norm": 0.14322157204151154,
      "learning_rate": 3.712121212121212e-05,
      "loss": 1.2185,
      "step": 315
    },
    {
      "epoch": 0.8669410150891632,
      "grad_norm": 0.14218993484973907,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 1.1244,
      "step": 316
    },
    {
      "epoch": 0.869684499314129,
      "grad_norm": 0.1463925987482071,
      "learning_rate": 3.560606060606061e-05,
      "loss": 1.1561,
      "step": 317
    },
    {
      "epoch": 0.8724279835390947,
      "grad_norm": 0.15007935464382172,
      "learning_rate": 3.484848484848485e-05,
      "loss": 1.1036,
      "step": 318
    },
    {
      "epoch": 0.8751714677640604,
      "grad_norm": 0.14636731147766113,
      "learning_rate": 3.409090909090909e-05,
      "loss": 1.2131,
      "step": 319
    },
    {
      "epoch": 0.877914951989026,
      "grad_norm": 0.15288923680782318,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.134,
      "step": 320
    },
    {
      "epoch": 0.8806584362139918,
      "grad_norm": 0.14087167382240295,
      "learning_rate": 3.257575757575758e-05,
      "loss": 1.1895,
      "step": 321
    },
    {
      "epoch": 0.8834019204389575,
      "grad_norm": 0.15402238070964813,
      "learning_rate": 3.181818181818182e-05,
      "loss": 1.1526,
      "step": 322
    },
    {
      "epoch": 0.8861454046639232,
      "grad_norm": 0.15257412195205688,
      "learning_rate": 3.106060606060606e-05,
      "loss": 1.1202,
      "step": 323
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.14580829441547394,
      "learning_rate": 3.0303030303030306e-05,
      "loss": 1.1297,
      "step": 324
    },
    {
      "epoch": 0.8916323731138546,
      "grad_norm": 0.14685004949569702,
      "learning_rate": 2.954545454545455e-05,
      "loss": 1.1105,
      "step": 325
    },
    {
      "epoch": 0.8943758573388203,
      "grad_norm": 0.1504146009683609,
      "learning_rate": 2.878787878787879e-05,
      "loss": 1.1256,
      "step": 326
    },
    {
      "epoch": 0.897119341563786,
      "grad_norm": 0.14086957275867462,
      "learning_rate": 2.803030303030303e-05,
      "loss": 1.0429,
      "step": 327
    },
    {
      "epoch": 0.8998628257887518,
      "grad_norm": 0.14482632279396057,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 1.1514,
      "step": 328
    },
    {
      "epoch": 0.9026063100137174,
      "grad_norm": 0.14591720700263977,
      "learning_rate": 2.6515151515151516e-05,
      "loss": 1.2139,
      "step": 329
    },
    {
      "epoch": 0.9053497942386831,
      "grad_norm": 0.13567478954792023,
      "learning_rate": 2.575757575757576e-05,
      "loss": 1.1386,
      "step": 330
    },
    {
      "epoch": 0.9080932784636488,
      "grad_norm": 0.14164294302463531,
      "learning_rate": 2.5e-05,
      "loss": 1.1358,
      "step": 331
    },
    {
      "epoch": 0.9108367626886146,
      "grad_norm": 0.15024589002132416,
      "learning_rate": 2.4242424242424244e-05,
      "loss": 1.1203,
      "step": 332
    },
    {
      "epoch": 0.9135802469135802,
      "grad_norm": 0.1464141309261322,
      "learning_rate": 2.3484848484848487e-05,
      "loss": 1.1245,
      "step": 333
    },
    {
      "epoch": 0.9163237311385459,
      "grad_norm": 0.15468576550483704,
      "learning_rate": 2.272727272727273e-05,
      "loss": 1.1168,
      "step": 334
    },
    {
      "epoch": 0.9190672153635117,
      "grad_norm": 0.1508295089006424,
      "learning_rate": 2.1969696969696972e-05,
      "loss": 1.1164,
      "step": 335
    },
    {
      "epoch": 0.9218106995884774,
      "grad_norm": 0.15271519124507904,
      "learning_rate": 2.1212121212121215e-05,
      "loss": 1.1037,
      "step": 336
    },
    {
      "epoch": 0.9245541838134431,
      "grad_norm": 0.14702965319156647,
      "learning_rate": 2.0454545454545457e-05,
      "loss": 1.1342,
      "step": 337
    },
    {
      "epoch": 0.9272976680384087,
      "grad_norm": 0.1484672725200653,
      "learning_rate": 1.9696969696969697e-05,
      "loss": 1.1285,
      "step": 338
    },
    {
      "epoch": 0.9300411522633745,
      "grad_norm": 0.1447269767522812,
      "learning_rate": 1.893939393939394e-05,
      "loss": 1.1273,
      "step": 339
    },
    {
      "epoch": 0.9327846364883402,
      "grad_norm": 0.14323726296424866,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 1.155,
      "step": 340
    },
    {
      "epoch": 0.9355281207133059,
      "grad_norm": 0.1493808627128601,
      "learning_rate": 1.7424242424242425e-05,
      "loss": 1.1316,
      "step": 341
    },
    {
      "epoch": 0.9382716049382716,
      "grad_norm": 0.15357686579227448,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.1777,
      "step": 342
    },
    {
      "epoch": 0.9410150891632373,
      "grad_norm": 0.14901426434516907,
      "learning_rate": 1.590909090909091e-05,
      "loss": 1.0996,
      "step": 343
    },
    {
      "epoch": 0.943758573388203,
      "grad_norm": 0.1443529576063156,
      "learning_rate": 1.5151515151515153e-05,
      "loss": 1.1349,
      "step": 344
    },
    {
      "epoch": 0.9465020576131687,
      "grad_norm": 0.14175036549568176,
      "learning_rate": 1.4393939393939396e-05,
      "loss": 1.1526,
      "step": 345
    },
    {
      "epoch": 0.9492455418381345,
      "grad_norm": 0.14177238941192627,
      "learning_rate": 1.3636363636363637e-05,
      "loss": 1.132,
      "step": 346
    },
    {
      "epoch": 0.9519890260631001,
      "grad_norm": 0.13835884630680084,
      "learning_rate": 1.287878787878788e-05,
      "loss": 1.1599,
      "step": 347
    },
    {
      "epoch": 0.9547325102880658,
      "grad_norm": 0.14390669763088226,
      "learning_rate": 1.2121212121212122e-05,
      "loss": 1.15,
      "step": 348
    },
    {
      "epoch": 0.9574759945130316,
      "grad_norm": 0.14811821281909943,
      "learning_rate": 1.1363636363636365e-05,
      "loss": 1.0759,
      "step": 349
    },
    {
      "epoch": 0.9602194787379973,
      "grad_norm": 0.14959345757961273,
      "learning_rate": 1.0606060606060607e-05,
      "loss": 1.126,
      "step": 350
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 0.14656995236873627,
      "learning_rate": 9.848484848484848e-06,
      "loss": 1.1341,
      "step": 351
    },
    {
      "epoch": 0.9657064471879286,
      "grad_norm": 0.14695106446743011,
      "learning_rate": 9.090909090909091e-06,
      "loss": 1.1259,
      "step": 352
    },
    {
      "epoch": 0.9684499314128944,
      "grad_norm": 0.14155460894107819,
      "learning_rate": 8.333333333333334e-06,
      "loss": 1.1503,
      "step": 353
    },
    {
      "epoch": 0.9711934156378601,
      "grad_norm": 0.1382407397031784,
      "learning_rate": 7.5757575757575764e-06,
      "loss": 1.1417,
      "step": 354
    },
    {
      "epoch": 0.9739368998628258,
      "grad_norm": 0.14089229702949524,
      "learning_rate": 6.818181818181818e-06,
      "loss": 1.1551,
      "step": 355
    },
    {
      "epoch": 0.9766803840877915,
      "grad_norm": 0.14886945486068726,
      "learning_rate": 6.060606060606061e-06,
      "loss": 1.0973,
      "step": 356
    },
    {
      "epoch": 0.9794238683127572,
      "grad_norm": 0.1485728621482849,
      "learning_rate": 5.303030303030304e-06,
      "loss": 1.1028,
      "step": 357
    },
    {
      "epoch": 0.9821673525377229,
      "grad_norm": 0.1496025174856186,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 1.0941,
      "step": 358
    },
    {
      "epoch": 0.9849108367626886,
      "grad_norm": 0.1394403725862503,
      "learning_rate": 3.7878787878787882e-06,
      "loss": 1.1452,
      "step": 359
    }
  ],
  "logging_steps": 1,
  "max_steps": 364,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.3742608796698214e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}