{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9574759945130316,
  "eval_steps": 500,
  "global_step": 349,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0027434842249657062,
      "grad_norm": 1.902702808380127,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.0959,
      "step": 1
    },
    {
      "epoch": 0.0054869684499314125,
      "grad_norm": 1.8936893939971924,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.099,
      "step": 2
    },
    {
      "epoch": 0.00823045267489712,
      "grad_norm": 1.9235605001449585,
      "learning_rate": 6e-06,
      "loss": 2.1045,
      "step": 3
    },
    {
      "epoch": 0.010973936899862825,
      "grad_norm": 1.7873843908309937,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.0144,
      "step": 4
    },
    {
      "epoch": 0.013717421124828532,
      "grad_norm": 1.8321126699447632,
      "learning_rate": 1e-05,
      "loss": 2.0872,
      "step": 5
    },
    {
      "epoch": 0.01646090534979424,
      "grad_norm": 2.0333194732666016,
      "learning_rate": 1.2e-05,
      "loss": 2.1146,
      "step": 6
    },
    {
      "epoch": 0.019204389574759947,
      "grad_norm": 1.763102650642395,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 2.036,
      "step": 7
    },
    {
      "epoch": 0.02194787379972565,
      "grad_norm": 1.5287824869155884,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.984,
      "step": 8
    },
    {
      "epoch": 0.024691358024691357,
      "grad_norm": 1.2035481929779053,
      "learning_rate": 1.8e-05,
      "loss": 1.928,
      "step": 9
    },
    {
      "epoch": 0.027434842249657063,
      "grad_norm": 1.0602883100509644,
      "learning_rate": 2e-05,
      "loss": 1.9322,
      "step": 10
    },
    {
      "epoch": 0.03017832647462277,
      "grad_norm": 0.9456723928451538,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 1.9257,
      "step": 11
    },
    {
      "epoch": 0.03292181069958848,
      "grad_norm": 0.7646191120147705,
      "learning_rate": 2.4e-05,
      "loss": 1.8057,
      "step": 12
    },
    {
      "epoch": 0.03566529492455418,
      "grad_norm": 0.6718866229057312,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.8535,
      "step": 13
    },
    {
      "epoch": 0.038408779149519894,
      "grad_norm": 0.5136308073997498,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 1.8533,
      "step": 14
    },
    {
      "epoch": 0.0411522633744856,
      "grad_norm": 0.4066430628299713,
      "learning_rate": 3e-05,
      "loss": 1.7867,
      "step": 15
    },
    {
      "epoch": 0.0438957475994513,
      "grad_norm": 0.3591379225254059,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.8729,
      "step": 16
    },
    {
      "epoch": 0.04663923182441701,
      "grad_norm": 0.3689568340778351,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 1.8186,
      "step": 17
    },
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 0.3991197645664215,
      "learning_rate": 3.6e-05,
      "loss": 1.8485,
      "step": 18
    },
    {
      "epoch": 0.05212620027434842,
      "grad_norm": 0.3603827655315399,
      "learning_rate": 3.8e-05,
      "loss": 1.8081,
      "step": 19
    },
    {
      "epoch": 0.05486968449931413,
      "grad_norm": 0.3805089592933655,
      "learning_rate": 4e-05,
      "loss": 1.7553,
      "step": 20
    },
    {
      "epoch": 0.05761316872427984,
      "grad_norm": 0.42597419023513794,
      "learning_rate": 4.2e-05,
      "loss": 1.8115,
      "step": 21
    },
    {
      "epoch": 0.06035665294924554,
      "grad_norm": 0.37801623344421387,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.7161,
      "step": 22
    },
    {
      "epoch": 0.06310013717421124,
      "grad_norm": 0.35600143671035767,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.7315,
      "step": 23
    },
    {
      "epoch": 0.06584362139917696,
      "grad_norm": 0.4111214280128479,
      "learning_rate": 4.8e-05,
      "loss": 1.7091,
      "step": 24
    },
    {
      "epoch": 0.06858710562414266,
      "grad_norm": 0.4117395579814911,
      "learning_rate": 5e-05,
      "loss": 1.7026,
      "step": 25
    },
    {
      "epoch": 0.07133058984910837,
      "grad_norm": 0.4069993197917938,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 1.6733,
      "step": 26
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.4196024239063263,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 1.6999,
      "step": 27
    },
    {
      "epoch": 0.07681755829903979,
      "grad_norm": 0.45915013551712036,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.6613,
      "step": 28
    },
    {
      "epoch": 0.07956104252400549,
      "grad_norm": 0.44673749804496765,
      "learning_rate": 5.8e-05,
      "loss": 1.7039,
      "step": 29
    },
    {
      "epoch": 0.0823045267489712,
      "grad_norm": 0.5381506085395813,
      "learning_rate": 6e-05,
      "loss": 1.5768,
      "step": 30
    },
    {
      "epoch": 0.0850480109739369,
      "grad_norm": 0.4311385750770569,
      "learning_rate": 6.2e-05,
      "loss": 1.5598,
      "step": 31
    },
    {
      "epoch": 0.0877914951989026,
      "grad_norm": 0.38209667801856995,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.511,
      "step": 32
    },
    {
      "epoch": 0.09053497942386832,
      "grad_norm": 0.35374918580055237,
      "learning_rate": 6.6e-05,
      "loss": 1.4692,
      "step": 33
    },
    {
      "epoch": 0.09327846364883402,
      "grad_norm": 0.4020269215106964,
      "learning_rate": 6.800000000000001e-05,
      "loss": 1.5276,
      "step": 34
    },
    {
      "epoch": 0.09602194787379972,
      "grad_norm": 0.46055856347084045,
      "learning_rate": 7e-05,
      "loss": 1.4634,
      "step": 35
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 0.4301123023033142,
      "learning_rate": 7.2e-05,
      "loss": 1.4151,
      "step": 36
    },
    {
      "epoch": 0.10150891632373114,
      "grad_norm": 0.34214499592781067,
      "learning_rate": 7.4e-05,
      "loss": 1.4451,
      "step": 37
    },
    {
      "epoch": 0.10425240054869685,
      "grad_norm": 0.24707239866256714,
      "learning_rate": 7.6e-05,
      "loss": 1.3434,
      "step": 38
    },
    {
      "epoch": 0.10699588477366255,
      "grad_norm": 0.16371050477027893,
      "learning_rate": 7.800000000000001e-05,
      "loss": 1.4134,
      "step": 39
    },
    {
      "epoch": 0.10973936899862825,
      "grad_norm": 0.11528003960847855,
      "learning_rate": 8e-05,
      "loss": 1.4896,
      "step": 40
    },
    {
      "epoch": 0.11248285322359397,
      "grad_norm": 0.11622235178947449,
      "learning_rate": 8.2e-05,
      "loss": 1.3957,
      "step": 41
    },
    {
      "epoch": 0.11522633744855967,
      "grad_norm": 0.10983709245920181,
      "learning_rate": 8.4e-05,
      "loss": 1.421,
      "step": 42
    },
    {
      "epoch": 0.11796982167352538,
      "grad_norm": 0.10124485194683075,
      "learning_rate": 8.6e-05,
      "loss": 1.4127,
      "step": 43
    },
    {
      "epoch": 0.12071330589849108,
      "grad_norm": 0.10291855037212372,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.4187,
      "step": 44
    },
    {
      "epoch": 0.12345679012345678,
      "grad_norm": 0.10925430059432983,
      "learning_rate": 9e-05,
      "loss": 1.3476,
      "step": 45
    },
    {
      "epoch": 0.1262002743484225,
      "grad_norm": 0.10825473070144653,
      "learning_rate": 9.200000000000001e-05,
      "loss": 1.4427,
      "step": 46
    },
    {
      "epoch": 0.1289437585733882,
      "grad_norm": 0.10768264532089233,
      "learning_rate": 9.4e-05,
      "loss": 1.4292,
      "step": 47
    },
    {
      "epoch": 0.13168724279835392,
      "grad_norm": 0.11937709152698517,
      "learning_rate": 9.6e-05,
      "loss": 1.3234,
      "step": 48
    },
    {
      "epoch": 0.13443072702331962,
      "grad_norm": 0.11960555613040924,
      "learning_rate": 9.8e-05,
      "loss": 1.3566,
      "step": 49
    },
    {
      "epoch": 0.13717421124828533,
      "grad_norm": 0.12491138279438019,
      "learning_rate": 0.0001,
      "loss": 1.4201,
      "step": 50
    },
    {
      "epoch": 0.13991769547325103,
      "grad_norm": 0.11906778067350388,
      "learning_rate": 0.00010200000000000001,
      "loss": 1.3745,
      "step": 51
    },
    {
      "epoch": 0.14266117969821673,
      "grad_norm": 0.12701214849948883,
      "learning_rate": 0.00010400000000000001,
      "loss": 1.3592,
      "step": 52
    },
    {
      "epoch": 0.14540466392318244,
      "grad_norm": 0.14920316636562347,
      "learning_rate": 0.00010600000000000002,
      "loss": 1.3139,
      "step": 53
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.157944455742836,
      "learning_rate": 0.00010800000000000001,
      "loss": 1.3704,
      "step": 54
    },
    {
      "epoch": 0.15089163237311384,
      "grad_norm": 0.15193891525268555,
      "learning_rate": 0.00011000000000000002,
      "loss": 1.3694,
      "step": 55
    },
    {
      "epoch": 0.15363511659807957,
      "grad_norm": 0.15829141438007355,
      "learning_rate": 0.00011200000000000001,
      "loss": 1.3351,
      "step": 56
    },
    {
      "epoch": 0.15637860082304528,
      "grad_norm": 0.16939309239387512,
      "learning_rate": 0.00011399999999999999,
      "loss": 1.3487,
      "step": 57
    },
    {
      "epoch": 0.15912208504801098,
      "grad_norm": 0.19683969020843506,
      "learning_rate": 0.000116,
      "loss": 1.2837,
      "step": 58
    },
    {
      "epoch": 0.16186556927297668,
      "grad_norm": 0.17148783802986145,
      "learning_rate": 0.000118,
      "loss": 1.3372,
      "step": 59
    },
    {
      "epoch": 0.1646090534979424,
      "grad_norm": 0.17560726404190063,
      "learning_rate": 0.00012,
      "loss": 1.3896,
      "step": 60
    },
    {
      "epoch": 0.1673525377229081,
      "grad_norm": 0.17536282539367676,
      "learning_rate": 0.000122,
      "loss": 1.4028,
      "step": 61
    },
    {
      "epoch": 0.1700960219478738,
      "grad_norm": 0.16491512954235077,
      "learning_rate": 0.000124,
      "loss": 1.3366,
      "step": 62
    },
    {
      "epoch": 0.1728395061728395,
      "grad_norm": 0.1202845573425293,
      "learning_rate": 0.000126,
      "loss": 1.3201,
      "step": 63
    },
    {
      "epoch": 0.1755829903978052,
      "grad_norm": 0.10146432369947433,
      "learning_rate": 0.00012800000000000002,
      "loss": 1.3083,
      "step": 64
    },
    {
      "epoch": 0.17832647462277093,
      "grad_norm": 0.0989551916718483,
      "learning_rate": 0.00013000000000000002,
      "loss": 1.3216,
      "step": 65
    },
    {
      "epoch": 0.18106995884773663,
      "grad_norm": 0.09368593990802765,
      "learning_rate": 0.000132,
      "loss": 1.3409,
      "step": 66
    },
    {
      "epoch": 0.18381344307270234,
      "grad_norm": 0.09617207944393158,
      "learning_rate": 0.000134,
      "loss": 1.3192,
      "step": 67
    },
    {
      "epoch": 0.18655692729766804,
      "grad_norm": 0.08890332281589508,
      "learning_rate": 0.00013600000000000003,
      "loss": 1.354,
      "step": 68
    },
    {
      "epoch": 0.18930041152263374,
      "grad_norm": 0.11371646821498871,
      "learning_rate": 0.000138,
      "loss": 1.3201,
      "step": 69
    },
    {
      "epoch": 0.19204389574759945,
      "grad_norm": 0.09785107523202896,
      "learning_rate": 0.00014,
      "loss": 1.2413,
      "step": 70
    },
    {
      "epoch": 0.19478737997256515,
      "grad_norm": 0.09149904549121857,
      "learning_rate": 0.000142,
      "loss": 1.2548,
      "step": 71
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.08837990462779999,
      "learning_rate": 0.000144,
      "loss": 1.3014,
      "step": 72
    },
    {
      "epoch": 0.20027434842249658,
      "grad_norm": 0.08963413536548615,
      "learning_rate": 0.000146,
      "loss": 1.3128,
      "step": 73
    },
    {
      "epoch": 0.2030178326474623,
      "grad_norm": 0.08815225213766098,
      "learning_rate": 0.000148,
      "loss": 1.3321,
      "step": 74
    },
    {
      "epoch": 0.205761316872428,
      "grad_norm": 0.09394700825214386,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.3341,
      "step": 75
    },
    {
      "epoch": 0.2085048010973937,
      "grad_norm": 0.10041660070419312,
      "learning_rate": 0.000152,
      "loss": 1.2944,
      "step": 76
    },
    {
      "epoch": 0.2112482853223594,
      "grad_norm": 0.09344102442264557,
      "learning_rate": 0.000154,
      "loss": 1.3226,
      "step": 77
    },
    {
      "epoch": 0.2139917695473251,
      "grad_norm": 0.09259933233261108,
      "learning_rate": 0.00015600000000000002,
      "loss": 1.2942,
      "step": 78
    },
    {
      "epoch": 0.2167352537722908,
      "grad_norm": 0.09426167607307434,
      "learning_rate": 0.00015800000000000002,
      "loss": 1.333,
      "step": 79
    },
    {
      "epoch": 0.2194787379972565,
      "grad_norm": 0.09674811363220215,
      "learning_rate": 0.00016,
      "loss": 1.3242,
      "step": 80
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.09802138805389404,
      "learning_rate": 0.000162,
      "loss": 1.3322,
      "step": 81
    },
    {
      "epoch": 0.22496570644718794,
      "grad_norm": 0.09528470784425735,
      "learning_rate": 0.000164,
      "loss": 1.2384,
      "step": 82
    },
    {
      "epoch": 0.22770919067215364,
      "grad_norm": 0.0997876301407814,
      "learning_rate": 0.000166,
      "loss": 1.3646,
      "step": 83
    },
    {
      "epoch": 0.23045267489711935,
      "grad_norm": 0.09820306301116943,
      "learning_rate": 0.000168,
      "loss": 1.1982,
      "step": 84
    },
    {
      "epoch": 0.23319615912208505,
      "grad_norm": 0.10137173533439636,
      "learning_rate": 0.00017,
      "loss": 1.2697,
      "step": 85
    },
    {
      "epoch": 0.23593964334705075,
      "grad_norm": 0.09000196307897568,
      "learning_rate": 0.000172,
      "loss": 1.3122,
      "step": 86
    },
    {
      "epoch": 0.23868312757201646,
      "grad_norm": 0.12272510677576065,
      "learning_rate": 0.000174,
      "loss": 1.3238,
      "step": 87
    },
    {
      "epoch": 0.24142661179698216,
      "grad_norm": 0.10101604461669922,
      "learning_rate": 0.00017600000000000002,
      "loss": 1.3637,
      "step": 88
    },
    {
      "epoch": 0.24417009602194786,
      "grad_norm": 0.10622192174196243,
      "learning_rate": 0.00017800000000000002,
      "loss": 1.2577,
      "step": 89
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 0.10139253735542297,
      "learning_rate": 0.00018,
      "loss": 1.303,
      "step": 90
    },
    {
      "epoch": 0.2496570644718793,
      "grad_norm": 0.09918926656246185,
      "learning_rate": 0.000182,
      "loss": 1.2377,
      "step": 91
    },
    {
      "epoch": 0.252400548696845,
      "grad_norm": 0.11826573312282562,
      "learning_rate": 0.00018400000000000003,
      "loss": 1.3773,
      "step": 92
    },
    {
      "epoch": 0.2551440329218107,
      "grad_norm": 0.10880250483751297,
      "learning_rate": 0.00018600000000000002,
      "loss": 1.3056,
      "step": 93
    },
    {
      "epoch": 0.2578875171467764,
      "grad_norm": 0.1100454330444336,
      "learning_rate": 0.000188,
      "loss": 1.258,
      "step": 94
    },
    {
      "epoch": 0.2606310013717421,
      "grad_norm": 0.1200387105345726,
      "learning_rate": 0.00019,
      "loss": 1.3362,
      "step": 95
    },
    {
      "epoch": 0.26337448559670784,
      "grad_norm": 0.10868213325738907,
      "learning_rate": 0.000192,
      "loss": 1.3175,
      "step": 96
    },
    {
      "epoch": 0.2661179698216735,
      "grad_norm": 0.11683013290166855,
      "learning_rate": 0.000194,
      "loss": 1.301,
      "step": 97
    },
    {
      "epoch": 0.26886145404663925,
      "grad_norm": 0.11990080773830414,
      "learning_rate": 0.000196,
      "loss": 1.2372,
      "step": 98
    },
    {
      "epoch": 0.2716049382716049,
      "grad_norm": 0.1380293071269989,
      "learning_rate": 0.00019800000000000002,
      "loss": 1.2915,
      "step": 99
    },
    {
      "epoch": 0.27434842249657065,
      "grad_norm": 0.14780984818935394,
      "learning_rate": 0.0002,
      "loss": 1.2423,
      "step": 100
    },
    {
      "epoch": 0.27709190672153633,
      "grad_norm": 0.11625576764345169,
      "learning_rate": 0.00019924242424242426,
      "loss": 1.2613,
      "step": 101
    },
    {
      "epoch": 0.27983539094650206,
      "grad_norm": 0.16299262642860413,
      "learning_rate": 0.0001984848484848485,
      "loss": 1.2527,
      "step": 102
    },
    {
      "epoch": 0.2825788751714678,
      "grad_norm": 0.12003400921821594,
      "learning_rate": 0.00019772727272727273,
      "loss": 1.2459,
      "step": 103
    },
    {
      "epoch": 0.28532235939643347,
      "grad_norm": 0.11611975729465485,
      "learning_rate": 0.00019696969696969698,
      "loss": 1.2736,
      "step": 104
    },
    {
      "epoch": 0.2880658436213992,
      "grad_norm": 0.12332016229629517,
      "learning_rate": 0.00019621212121212123,
      "loss": 1.2161,
      "step": 105
    },
    {
      "epoch": 0.2908093278463649,
      "grad_norm": 0.12996245920658112,
      "learning_rate": 0.00019545454545454548,
      "loss": 1.2254,
      "step": 106
    },
    {
      "epoch": 0.2935528120713306,
      "grad_norm": 0.11514672636985779,
      "learning_rate": 0.0001946969696969697,
      "loss": 1.2367,
      "step": 107
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.13371898233890533,
      "learning_rate": 0.00019393939393939395,
      "loss": 1.2172,
      "step": 108
    },
    {
      "epoch": 0.299039780521262,
      "grad_norm": 0.1204146221280098,
      "learning_rate": 0.0001931818181818182,
      "loss": 1.3121,
      "step": 109
    },
    {
      "epoch": 0.3017832647462277,
      "grad_norm": 0.11520334333181381,
      "learning_rate": 0.00019242424242424245,
      "loss": 1.2051,
      "step": 110
    },
    {
      "epoch": 0.3045267489711934,
      "grad_norm": 0.15397988259792328,
      "learning_rate": 0.00019166666666666667,
      "loss": 1.2829,
      "step": 111
    },
    {
      "epoch": 0.30727023319615915,
      "grad_norm": 0.12115694582462311,
      "learning_rate": 0.00019090909090909092,
      "loss": 1.3109,
      "step": 112
    },
    {
      "epoch": 0.3100137174211248,
      "grad_norm": 0.12799453735351562,
      "learning_rate": 0.00019015151515151517,
      "loss": 1.2836,
      "step": 113
    },
    {
      "epoch": 0.31275720164609055,
      "grad_norm": 0.1297687143087387,
      "learning_rate": 0.00018939393939393942,
      "loss": 1.2813,
      "step": 114
    },
    {
      "epoch": 0.31550068587105623,
      "grad_norm": 0.13718412816524506,
      "learning_rate": 0.00018863636363636364,
      "loss": 1.3138,
      "step": 115
    },
    {
      "epoch": 0.31824417009602196,
      "grad_norm": 0.12237361073493958,
      "learning_rate": 0.0001878787878787879,
      "loss": 1.1938,
      "step": 116
    },
    {
      "epoch": 0.32098765432098764,
      "grad_norm": 0.12502606213092804,
      "learning_rate": 0.00018712121212121212,
      "loss": 1.3258,
      "step": 117
    },
    {
      "epoch": 0.32373113854595337,
      "grad_norm": 0.13772045075893402,
      "learning_rate": 0.00018636363636363636,
      "loss": 1.3305,
      "step": 118
    },
    {
      "epoch": 0.32647462277091904,
      "grad_norm": 0.1165667474269867,
      "learning_rate": 0.00018560606060606061,
      "loss": 1.2473,
      "step": 119
    },
    {
      "epoch": 0.3292181069958848,
      "grad_norm": 0.12208285182714462,
      "learning_rate": 0.00018484848484848484,
      "loss": 1.2755,
      "step": 120
    },
    {
      "epoch": 0.3319615912208505,
      "grad_norm": 0.13750925660133362,
      "learning_rate": 0.00018409090909090909,
      "loss": 1.178,
      "step": 121
    },
    {
      "epoch": 0.3347050754458162,
      "grad_norm": 0.12554235756397247,
      "learning_rate": 0.00018333333333333334,
      "loss": 1.2727,
      "step": 122
    },
    {
      "epoch": 0.3374485596707819,
      "grad_norm": 0.153937429189682,
      "learning_rate": 0.00018257575757575758,
      "loss": 1.2232,
      "step": 123
    },
    {
      "epoch": 0.3401920438957476,
      "grad_norm": 0.12629558145999908,
      "learning_rate": 0.00018181818181818183,
      "loss": 1.1856,
      "step": 124
    },
    {
      "epoch": 0.3429355281207133,
      "grad_norm": 0.13697242736816406,
      "learning_rate": 0.00018106060606060606,
      "loss": 1.3235,
      "step": 125
    },
    {
      "epoch": 0.345679012345679,
      "grad_norm": 0.15304319560527802,
      "learning_rate": 0.0001803030303030303,
      "loss": 1.2457,
      "step": 126
    },
    {
      "epoch": 0.3484224965706447,
      "grad_norm": 0.1399148851633072,
      "learning_rate": 0.00017954545454545456,
      "loss": 1.2907,
      "step": 127
    },
    {
      "epoch": 0.3511659807956104,
      "grad_norm": 0.1822618842124939,
      "learning_rate": 0.0001787878787878788,
      "loss": 1.3335,
      "step": 128
    },
    {
      "epoch": 0.35390946502057613,
      "grad_norm": 0.16444697976112366,
      "learning_rate": 0.00017803030303030303,
      "loss": 1.3234,
      "step": 129
    },
    {
      "epoch": 0.35665294924554186,
      "grad_norm": 0.15233512222766876,
      "learning_rate": 0.00017727272727272728,
      "loss": 1.2672,
      "step": 130
    },
    {
      "epoch": 0.35939643347050754,
      "grad_norm": 0.16545739769935608,
      "learning_rate": 0.00017651515151515153,
      "loss": 1.175,
      "step": 131
    },
    {
      "epoch": 0.36213991769547327,
      "grad_norm": 0.13627974689006805,
      "learning_rate": 0.00017575757575757578,
      "loss": 1.2611,
      "step": 132
    },
    {
      "epoch": 0.36488340192043894,
      "grad_norm": 0.1535719484090805,
      "learning_rate": 0.000175,
      "loss": 1.2334,
      "step": 133
    },
    {
      "epoch": 0.3676268861454047,
      "grad_norm": 0.1347316950559616,
      "learning_rate": 0.00017424242424242425,
      "loss": 1.2259,
      "step": 134
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.1347058117389679,
      "learning_rate": 0.0001734848484848485,
      "loss": 1.135,
      "step": 135
    },
    {
      "epoch": 0.3731138545953361,
      "grad_norm": 0.1388654112815857,
      "learning_rate": 0.00017272727272727275,
      "loss": 1.2217,
      "step": 136
    },
    {
      "epoch": 0.37585733882030176,
      "grad_norm": 0.14038826525211334,
      "learning_rate": 0.00017196969696969697,
      "loss": 1.2837,
      "step": 137
    },
    {
      "epoch": 0.3786008230452675,
      "grad_norm": 0.1578507125377655,
      "learning_rate": 0.00017121212121212122,
      "loss": 1.2717,
      "step": 138
    },
    {
      "epoch": 0.3813443072702332,
      "grad_norm": 0.13014937937259674,
      "learning_rate": 0.00017045454545454547,
      "loss": 1.2604,
      "step": 139
    },
    {
      "epoch": 0.3840877914951989,
      "grad_norm": 0.16863836348056793,
      "learning_rate": 0.00016969696969696972,
      "loss": 1.2479,
      "step": 140
    },
    {
      "epoch": 0.3868312757201646,
      "grad_norm": 0.1496235728263855,
      "learning_rate": 0.00016893939393939394,
      "loss": 1.1911,
      "step": 141
    },
    {
      "epoch": 0.3895747599451303,
      "grad_norm": 0.15035606920719147,
      "learning_rate": 0.0001681818181818182,
      "loss": 1.2756,
      "step": 142
    },
    {
      "epoch": 0.39231824417009603,
      "grad_norm": 0.14892420172691345,
      "learning_rate": 0.00016742424242424244,
      "loss": 1.199,
      "step": 143
    },
    {
      "epoch": 0.3950617283950617,
      "grad_norm": 0.1547059863805771,
      "learning_rate": 0.0001666666666666667,
      "loss": 1.2301,
      "step": 144
    },
    {
      "epoch": 0.39780521262002744,
      "grad_norm": 0.13619515299797058,
      "learning_rate": 0.00016590909090909094,
      "loss": 1.1821,
      "step": 145
    },
    {
      "epoch": 0.40054869684499317,
      "grad_norm": 0.15868829190731049,
      "learning_rate": 0.00016515151515151516,
      "loss": 1.2416,
      "step": 146
    },
    {
      "epoch": 0.40329218106995884,
      "grad_norm": 0.13451522588729858,
      "learning_rate": 0.0001643939393939394,
      "loss": 1.2108,
      "step": 147
    },
    {
      "epoch": 0.4060356652949246,
      "grad_norm": 0.14629404246807098,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.2176,
      "step": 148
    },
    {
      "epoch": 0.40877914951989025,
      "grad_norm": 0.14986877143383026,
      "learning_rate": 0.0001628787878787879,
      "loss": 1.2373,
      "step": 149
    },
    {
      "epoch": 0.411522633744856,
      "grad_norm": 0.14896810054779053,
      "learning_rate": 0.00016212121212121213,
      "loss": 1.2124,
      "step": 150
    },
    {
      "epoch": 0.41426611796982166,
      "grad_norm": 0.1467796117067337,
      "learning_rate": 0.00016136363636363635,
      "loss": 1.3202,
      "step": 151
    },
    {
      "epoch": 0.4170096021947874,
      "grad_norm": 0.1488669067621231,
      "learning_rate": 0.0001606060606060606,
      "loss": 1.2315,
      "step": 152
    },
    {
      "epoch": 0.41975308641975306,
      "grad_norm": 0.14375552535057068,
      "learning_rate": 0.00015984848484848485,
      "loss": 1.2641,
      "step": 153
    },
    {
      "epoch": 0.4224965706447188,
      "grad_norm": 0.1794748306274414,
      "learning_rate": 0.0001590909090909091,
      "loss": 1.1754,
      "step": 154
    },
    {
      "epoch": 0.4252400548696845,
      "grad_norm": 0.13613805174827576,
      "learning_rate": 0.00015833333333333332,
      "loss": 1.2114,
      "step": 155
    },
    {
      "epoch": 0.4279835390946502,
      "grad_norm": 0.1772301197052002,
      "learning_rate": 0.00015757575757575757,
      "loss": 1.2146,
      "step": 156
    },
    {
      "epoch": 0.43072702331961593,
      "grad_norm": 0.18257774412631989,
      "learning_rate": 0.00015681818181818182,
      "loss": 1.2129,
      "step": 157
    },
    {
      "epoch": 0.4334705075445816,
      "grad_norm": 0.1565171182155609,
      "learning_rate": 0.00015606060606060607,
      "loss": 1.3144,
      "step": 158
    },
    {
      "epoch": 0.43621399176954734,
      "grad_norm": 0.14858128130435944,
      "learning_rate": 0.0001553030303030303,
      "loss": 1.262,
      "step": 159
    },
    {
      "epoch": 0.438957475994513,
      "grad_norm": 0.16517716646194458,
      "learning_rate": 0.00015454545454545454,
      "loss": 1.2895,
      "step": 160
    },
    {
      "epoch": 0.44170096021947874,
      "grad_norm": 0.16663017868995667,
      "learning_rate": 0.0001537878787878788,
      "loss": 1.2847,
      "step": 161
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.17813093960285187,
      "learning_rate": 0.00015303030303030304,
      "loss": 1.1901,
      "step": 162
    },
    {
      "epoch": 0.44718792866941015,
      "grad_norm": 0.2013212889432907,
      "learning_rate": 0.00015227272727272727,
      "loss": 1.2106,
      "step": 163
    },
    {
      "epoch": 0.4499314128943759,
      "grad_norm": 0.16856490075588226,
      "learning_rate": 0.00015151515151515152,
      "loss": 1.1806,
      "step": 164
    },
    {
      "epoch": 0.45267489711934156,
      "grad_norm": 0.18135228753089905,
      "learning_rate": 0.00015075757575757576,
      "loss": 1.2848,
      "step": 165
    },
    {
      "epoch": 0.4554183813443073,
      "grad_norm": 0.18058203160762787,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.2576,
      "step": 166
    },
    {
      "epoch": 0.45816186556927296,
      "grad_norm": 0.14680561423301697,
      "learning_rate": 0.00014924242424242426,
      "loss": 1.2322,
      "step": 167
    },
    {
      "epoch": 0.4609053497942387,
      "grad_norm": 0.1470465362071991,
      "learning_rate": 0.00014848484848484849,
      "loss": 1.241,
      "step": 168
    },
    {
      "epoch": 0.46364883401920437,
      "grad_norm": 0.14876408874988556,
      "learning_rate": 0.00014772727272727274,
      "loss": 1.2268,
      "step": 169
    },
    {
      "epoch": 0.4663923182441701,
      "grad_norm": 0.14918828010559082,
      "learning_rate": 0.00014696969696969698,
      "loss": 1.3067,
      "step": 170
    },
    {
      "epoch": 0.4691358024691358,
      "grad_norm": 0.14815697073936462,
      "learning_rate": 0.00014621212121212123,
      "loss": 1.2492,
      "step": 171
    },
    {
      "epoch": 0.4718792866941015,
      "grad_norm": 0.13748030364513397,
      "learning_rate": 0.00014545454545454546,
      "loss": 1.2281,
      "step": 172
    },
    {
      "epoch": 0.47462277091906724,
      "grad_norm": 0.14712287485599518,
      "learning_rate": 0.0001446969696969697,
      "loss": 1.1438,
      "step": 173
    },
    {
      "epoch": 0.4773662551440329,
      "grad_norm": 0.13734129071235657,
      "learning_rate": 0.00014393939393939396,
      "loss": 1.2528,
      "step": 174
    },
    {
      "epoch": 0.48010973936899864,
      "grad_norm": 0.15113233029842377,
      "learning_rate": 0.0001431818181818182,
      "loss": 1.2387,
      "step": 175
    },
    {
      "epoch": 0.4828532235939643,
      "grad_norm": 0.14522749185562134,
      "learning_rate": 0.00014242424242424243,
      "loss": 1.2214,
      "step": 176
    },
    {
      "epoch": 0.48559670781893005,
      "grad_norm": 0.14445781707763672,
      "learning_rate": 0.00014166666666666668,
      "loss": 1.2424,
      "step": 177
    },
    {
      "epoch": 0.4883401920438957,
      "grad_norm": 0.15134842693805695,
      "learning_rate": 0.00014090909090909093,
      "loss": 1.2522,
      "step": 178
    },
    {
      "epoch": 0.49108367626886146,
      "grad_norm": 0.15704961121082306,
      "learning_rate": 0.00014015151515151518,
      "loss": 1.2584,
      "step": 179
    },
    {
      "epoch": 0.49382716049382713,
      "grad_norm": 0.153547003865242,
      "learning_rate": 0.0001393939393939394,
      "loss": 1.1958,
      "step": 180
    },
    {
      "epoch": 0.49657064471879286,
      "grad_norm": 0.16817179322242737,
      "learning_rate": 0.00013863636363636365,
      "loss": 1.1739,
      "step": 181
    },
    {
      "epoch": 0.4993141289437586,
      "grad_norm": 0.14305363595485687,
      "learning_rate": 0.0001378787878787879,
      "loss": 1.1919,
      "step": 182
    },
    {
      "epoch": 0.5020576131687243,
      "grad_norm": 0.1474563330411911,
      "learning_rate": 0.00013712121212121212,
      "loss": 1.2232,
      "step": 183
    },
    {
      "epoch": 0.50480109739369,
      "grad_norm": 0.1495485007762909,
      "learning_rate": 0.00013636363636363637,
      "loss": 1.2423,
      "step": 184
    },
    {
      "epoch": 0.5075445816186557,
      "grad_norm": 0.1455039083957672,
      "learning_rate": 0.0001356060606060606,
      "loss": 1.2178,
      "step": 185
    },
    {
      "epoch": 0.5102880658436214,
      "grad_norm": 0.1525765359401703,
      "learning_rate": 0.00013484848484848484,
      "loss": 1.2798,
      "step": 186
    },
    {
      "epoch": 0.5130315500685871,
      "grad_norm": 0.15652745962142944,
      "learning_rate": 0.0001340909090909091,
      "loss": 1.1691,
      "step": 187
    },
    {
      "epoch": 0.5157750342935528,
      "grad_norm": 0.1435556709766388,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.2331,
      "step": 188
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 0.14547987282276154,
      "learning_rate": 0.00013257575757575756,
      "loss": 1.2087,
      "step": 189
    },
    {
      "epoch": 0.5212620027434842,
      "grad_norm": 0.15346300601959229,
      "learning_rate": 0.0001318181818181818,
      "loss": 1.2744,
      "step": 190
    },
    {
      "epoch": 0.52400548696845,
      "grad_norm": 0.155302494764328,
      "learning_rate": 0.00013106060606060606,
      "loss": 1.2769,
      "step": 191
    },
    {
      "epoch": 0.5267489711934157,
      "grad_norm": 0.1592315286397934,
      "learning_rate": 0.0001303030303030303,
      "loss": 1.1989,
      "step": 192
    },
    {
      "epoch": 0.5294924554183813,
      "grad_norm": 0.1477937400341034,
      "learning_rate": 0.00012954545454545456,
      "loss": 1.195,
      "step": 193
    },
    {
      "epoch": 0.532235939643347,
      "grad_norm": 0.1779361218214035,
      "learning_rate": 0.00012878787878787878,
      "loss": 1.1984,
      "step": 194
    },
    {
      "epoch": 0.5349794238683128,
      "grad_norm": 0.16755440831184387,
      "learning_rate": 0.00012803030303030303,
      "loss": 1.1867,
      "step": 195
    },
    {
      "epoch": 0.5377229080932785,
      "grad_norm": 0.14698271453380585,
      "learning_rate": 0.00012727272727272728,
      "loss": 1.2407,
      "step": 196
    },
    {
      "epoch": 0.5404663923182441,
      "grad_norm": 0.22619858384132385,
      "learning_rate": 0.00012651515151515153,
      "loss": 1.2623,
      "step": 197
    },
    {
      "epoch": 0.5432098765432098,
      "grad_norm": 0.15332822501659393,
      "learning_rate": 0.00012575757575757575,
      "loss": 1.2113,
      "step": 198
    },
    {
      "epoch": 0.5459533607681756,
      "grad_norm": 0.15453462302684784,
      "learning_rate": 0.000125,
      "loss": 1.157,
      "step": 199
    },
    {
      "epoch": 0.5486968449931413,
      "grad_norm": 0.18716047704219818,
      "learning_rate": 0.00012424242424242425,
      "loss": 1.1896,
      "step": 200
    },
    {
      "epoch": 0.551440329218107,
      "grad_norm": 0.1628562957048416,
      "learning_rate": 0.0001234848484848485,
      "loss": 1.2035,
      "step": 201
    },
    {
      "epoch": 0.5541838134430727,
      "grad_norm": 0.15352866053581238,
      "learning_rate": 0.00012272727272727272,
      "loss": 1.2529,
      "step": 202
    },
    {
      "epoch": 0.5569272976680384,
      "grad_norm": 0.1607903093099594,
      "learning_rate": 0.00012196969696969697,
      "loss": 1.224,
      "step": 203
    },
    {
      "epoch": 0.5596707818930041,
      "grad_norm": 0.19524335861206055,
      "learning_rate": 0.00012121212121212122,
      "loss": 1.0918,
      "step": 204
    },
    {
      "epoch": 0.5624142661179699,
      "grad_norm": 0.17055654525756836,
      "learning_rate": 0.00012045454545454546,
      "loss": 1.2339,
      "step": 205
    },
    {
      "epoch": 0.5651577503429356,
      "grad_norm": 0.1699044108390808,
      "learning_rate": 0.00011969696969696971,
      "loss": 1.1918,
      "step": 206
    },
    {
      "epoch": 0.5679012345679012,
      "grad_norm": 0.20004670321941376,
      "learning_rate": 0.00011893939393939394,
      "loss": 1.2308,
      "step": 207
    },
    {
      "epoch": 0.5706447187928669,
      "grad_norm": 0.20924247801303864,
      "learning_rate": 0.0001181818181818182,
      "loss": 1.2527,
      "step": 208
    },
    {
      "epoch": 0.5733882030178327,
      "grad_norm": 0.16315655410289764,
      "learning_rate": 0.00011742424242424244,
      "loss": 1.1913,
      "step": 209
    },
    {
      "epoch": 0.5761316872427984,
      "grad_norm": 0.224049374461174,
      "learning_rate": 0.00011666666666666668,
      "loss": 1.2381,
      "step": 210
    },
    {
      "epoch": 0.578875171467764,
      "grad_norm": 0.24203604459762573,
      "learning_rate": 0.00011590909090909093,
      "loss": 1.1433,
      "step": 211
    },
    {
      "epoch": 0.5816186556927297,
      "grad_norm": 0.18014276027679443,
      "learning_rate": 0.00011515151515151516,
      "loss": 1.2695,
      "step": 212
    },
    {
      "epoch": 0.5843621399176955,
      "grad_norm": 0.22670245170593262,
      "learning_rate": 0.00011439393939393941,
      "loss": 1.1642,
      "step": 213
    },
    {
      "epoch": 0.5871056241426612,
      "grad_norm": 0.250273197889328,
      "learning_rate": 0.00011363636363636365,
      "loss": 1.2256,
      "step": 214
    },
    {
      "epoch": 0.5898491083676269,
      "grad_norm": 0.18230263888835907,
      "learning_rate": 0.0001128787878787879,
      "loss": 1.1579,
      "step": 215
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.17414681613445282,
      "learning_rate": 0.00011212121212121212,
      "loss": 1.185,
      "step": 216
    },
    {
      "epoch": 0.5953360768175583,
      "grad_norm": 0.25959229469299316,
      "learning_rate": 0.00011136363636363636,
      "loss": 1.2697,
      "step": 217
    },
    {
      "epoch": 0.598079561042524,
      "grad_norm": 0.21464407444000244,
      "learning_rate": 0.00011060606060606061,
      "loss": 1.2269,
      "step": 218
    },
    {
      "epoch": 0.6008230452674898,
      "grad_norm": 0.1585656851530075,
      "learning_rate": 0.00010984848484848484,
      "loss": 1.116,
      "step": 219
    },
    {
      "epoch": 0.6035665294924554,
      "grad_norm": 0.28340986371040344,
      "learning_rate": 0.00010909090909090909,
      "loss": 1.2534,
      "step": 220
    },
    {
      "epoch": 0.6063100137174211,
      "grad_norm": 0.2463023066520691,
      "learning_rate": 0.00010833333333333333,
      "loss": 1.2119,
      "step": 221
    },
    {
      "epoch": 0.6090534979423868,
      "grad_norm": 0.1642024666070938,
      "learning_rate": 0.00010757575757575758,
      "loss": 1.1755,
      "step": 222
    },
    {
      "epoch": 0.6117969821673526,
      "grad_norm": 0.2119123786687851,
      "learning_rate": 0.00010681818181818181,
      "loss": 1.1784,
      "step": 223
    },
    {
      "epoch": 0.6145404663923183,
      "grad_norm": 0.20988301932811737,
      "learning_rate": 0.00010606060606060606,
      "loss": 1.1841,
      "step": 224
    },
    {
      "epoch": 0.6172839506172839,
      "grad_norm": 0.1982959508895874,
      "learning_rate": 0.0001053030303030303,
      "loss": 1.2508,
      "step": 225
    },
    {
      "epoch": 0.6200274348422496,
      "grad_norm": 0.1641291379928589,
      "learning_rate": 0.00010454545454545455,
      "loss": 1.1552,
      "step": 226
    },
    {
      "epoch": 0.6227709190672154,
      "grad_norm": 0.2212403416633606,
      "learning_rate": 0.00010378787878787878,
      "loss": 1.2479,
      "step": 227
    },
    {
      "epoch": 0.6255144032921811,
      "grad_norm": 0.2342177778482437,
      "learning_rate": 0.00010303030303030303,
      "loss": 1.2185,
      "step": 228
    },
    {
      "epoch": 0.6282578875171467,
      "grad_norm": 0.15451593697071075,
      "learning_rate": 0.00010227272727272727,
      "loss": 1.2433,
      "step": 229
    },
    {
      "epoch": 0.6310013717421125,
      "grad_norm": 0.16344501078128815,
      "learning_rate": 0.00010151515151515152,
      "loss": 1.1227,
      "step": 230
    },
    {
      "epoch": 0.6337448559670782,
      "grad_norm": 0.15936411917209625,
      "learning_rate": 0.00010075757575757576,
      "loss": 1.1841,
      "step": 231
    },
    {
      "epoch": 0.6364883401920439,
      "grad_norm": 0.2086990624666214,
      "learning_rate": 0.0001,
      "loss": 1.2414,
      "step": 232
    },
    {
      "epoch": 0.6392318244170097,
      "grad_norm": 0.18307948112487793,
      "learning_rate": 9.924242424242425e-05,
      "loss": 1.1255,
      "step": 233
    },
    {
      "epoch": 0.6419753086419753,
      "grad_norm": 0.1552293747663498,
      "learning_rate": 9.848484848484849e-05,
      "loss": 1.1812,
      "step": 234
    },
    {
      "epoch": 0.644718792866941,
      "grad_norm": 0.19036468863487244,
      "learning_rate": 9.772727272727274e-05,
      "loss": 1.1467,
      "step": 235
    },
    {
      "epoch": 0.6474622770919067,
      "grad_norm": 0.15272115170955658,
      "learning_rate": 9.696969696969698e-05,
      "loss": 1.2155,
      "step": 236
    },
    {
      "epoch": 0.6502057613168725,
      "grad_norm": 0.19770941138267517,
      "learning_rate": 9.621212121212123e-05,
      "loss": 1.1268,
      "step": 237
    },
    {
      "epoch": 0.6529492455418381,
      "grad_norm": 0.1657804250717163,
      "learning_rate": 9.545454545454546e-05,
      "loss": 1.1862,
      "step": 238
    },
    {
      "epoch": 0.6556927297668038,
      "grad_norm": 0.1653299182653427,
      "learning_rate": 9.469696969696971e-05,
      "loss": 1.2015,
      "step": 239
    },
    {
      "epoch": 0.6584362139917695,
      "grad_norm": 0.17784593999385834,
      "learning_rate": 9.393939393939395e-05,
      "loss": 1.2368,
      "step": 240
    },
    {
      "epoch": 0.6611796982167353,
      "grad_norm": 0.15533973276615143,
      "learning_rate": 9.318181818181818e-05,
      "loss": 1.2155,
      "step": 241
    },
    {
      "epoch": 0.663923182441701,
      "grad_norm": 0.16223277151584625,
      "learning_rate": 9.242424242424242e-05,
      "loss": 1.2732,
      "step": 242
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.16092891991138458,
      "learning_rate": 9.166666666666667e-05,
      "loss": 1.1607,
      "step": 243
    },
    {
      "epoch": 0.6694101508916324,
      "grad_norm": 0.1687157154083252,
      "learning_rate": 9.090909090909092e-05,
      "loss": 1.1149,
      "step": 244
    },
    {
      "epoch": 0.6721536351165981,
      "grad_norm": 0.18511663377285004,
      "learning_rate": 9.015151515151515e-05,
      "loss": 1.1934,
      "step": 245
    },
    {
      "epoch": 0.6748971193415638,
      "grad_norm": 0.16487190127372742,
      "learning_rate": 8.93939393939394e-05,
      "loss": 1.1912,
      "step": 246
    },
    {
      "epoch": 0.6776406035665294,
      "grad_norm": 0.16145478188991547,
      "learning_rate": 8.863636363636364e-05,
      "loss": 1.1957,
      "step": 247
    },
    {
      "epoch": 0.6803840877914952,
      "grad_norm": 0.16441555321216583,
      "learning_rate": 8.787878787878789e-05,
      "loss": 1.198,
      "step": 248
    },
    {
      "epoch": 0.6831275720164609,
      "grad_norm": 0.16603751480579376,
      "learning_rate": 8.712121212121212e-05,
      "loss": 1.1924,
      "step": 249
    },
    {
      "epoch": 0.6858710562414266,
      "grad_norm": 0.16935844719409943,
      "learning_rate": 8.636363636363637e-05,
      "loss": 1.1622,
      "step": 250
    },
    {
      "epoch": 0.6886145404663924,
      "grad_norm": 0.16669955849647522,
      "learning_rate": 8.560606060606061e-05,
      "loss": 1.1737,
      "step": 251
    },
    {
      "epoch": 0.691358024691358,
      "grad_norm": 0.18938620388507843,
      "learning_rate": 8.484848484848486e-05,
      "loss": 1.148,
      "step": 252
    },
    {
      "epoch": 0.6941015089163237,
      "grad_norm": 0.14747262001037598,
      "learning_rate": 8.40909090909091e-05,
      "loss": 1.1205,
      "step": 253
    },
    {
      "epoch": 0.6968449931412894,
      "grad_norm": 0.1583009511232376,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.2027,
      "step": 254
    },
    {
      "epoch": 0.6995884773662552,
      "grad_norm": 0.16166453063488007,
      "learning_rate": 8.257575757575758e-05,
      "loss": 1.2026,
      "step": 255
    },
    {
      "epoch": 0.7023319615912208,
      "grad_norm": 0.16367658972740173,
      "learning_rate": 8.181818181818183e-05,
      "loss": 1.1858,
      "step": 256
    },
    {
      "epoch": 0.7050754458161865,
      "grad_norm": 0.1652062088251114,
      "learning_rate": 8.106060606060607e-05,
      "loss": 1.1592,
      "step": 257
    },
    {
      "epoch": 0.7078189300411523,
      "grad_norm": 0.15651218593120575,
      "learning_rate": 8.03030303030303e-05,
      "loss": 1.201,
      "step": 258
    },
    {
      "epoch": 0.710562414266118,
      "grad_norm": 0.16143658757209778,
      "learning_rate": 7.954545454545455e-05,
      "loss": 1.188,
      "step": 259
    },
    {
      "epoch": 0.7133058984910837,
      "grad_norm": 0.170159250497818,
      "learning_rate": 7.878787878787879e-05,
      "loss": 1.1713,
      "step": 260
    },
    {
      "epoch": 0.7160493827160493,
      "grad_norm": 0.16383200883865356,
      "learning_rate": 7.803030303030304e-05,
      "loss": 1.1593,
      "step": 261
    },
    {
      "epoch": 0.7187928669410151,
      "grad_norm": 0.16724437475204468,
      "learning_rate": 7.727272727272727e-05,
      "loss": 1.3,
      "step": 262
    },
    {
      "epoch": 0.7215363511659808,
      "grad_norm": 0.18244515359401703,
      "learning_rate": 7.651515151515152e-05,
      "loss": 1.264,
      "step": 263
    },
    {
      "epoch": 0.7242798353909465,
      "grad_norm": 0.15599456429481506,
      "learning_rate": 7.575757575757576e-05,
      "loss": 1.2125,
      "step": 264
    },
    {
      "epoch": 0.7270233196159122,
      "grad_norm": 0.1578194946050644,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.2006,
      "step": 265
    },
    {
      "epoch": 0.7297668038408779,
      "grad_norm": 0.15539692342281342,
      "learning_rate": 7.424242424242424e-05,
      "loss": 1.1045,
      "step": 266
    },
    {
      "epoch": 0.7325102880658436,
      "grad_norm": 0.15170246362686157,
      "learning_rate": 7.348484848484849e-05,
      "loss": 1.1653,
      "step": 267
    },
    {
      "epoch": 0.7352537722908093,
      "grad_norm": 0.18623769283294678,
      "learning_rate": 7.272727272727273e-05,
      "loss": 1.2259,
      "step": 268
    },
    {
      "epoch": 0.7379972565157751,
      "grad_norm": 0.15109026432037354,
      "learning_rate": 7.196969696969698e-05,
      "loss": 1.2103,
      "step": 269
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.15917524695396423,
      "learning_rate": 7.121212121212121e-05,
      "loss": 1.1641,
      "step": 270
    },
    {
      "epoch": 0.7434842249657064,
      "grad_norm": 0.16973435878753662,
      "learning_rate": 7.045454545454546e-05,
      "loss": 1.1128,
      "step": 271
    },
    {
      "epoch": 0.7462277091906722,
      "grad_norm": 0.16686728596687317,
      "learning_rate": 6.96969696969697e-05,
      "loss": 1.1665,
      "step": 272
    },
    {
      "epoch": 0.7489711934156379,
      "grad_norm": 0.16650721430778503,
      "learning_rate": 6.893939393939395e-05,
      "loss": 1.1626,
      "step": 273
    },
    {
      "epoch": 0.7517146776406035,
      "grad_norm": 0.1571473777294159,
      "learning_rate": 6.818181818181818e-05,
      "loss": 1.1167,
      "step": 274
    },
    {
      "epoch": 0.7544581618655692,
      "grad_norm": 0.15378378331661224,
      "learning_rate": 6.742424242424242e-05,
      "loss": 1.2406,
      "step": 275
    },
    {
      "epoch": 0.757201646090535,
      "grad_norm": 0.16972492635250092,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.2506,
      "step": 276
    },
    {
      "epoch": 0.7599451303155007,
      "grad_norm": 0.16112364828586578,
      "learning_rate": 6.59090909090909e-05,
      "loss": 1.1676,
      "step": 277
    },
    {
      "epoch": 0.7626886145404664,
      "grad_norm": 0.1625635176897049,
      "learning_rate": 6.515151515151516e-05,
      "loss": 1.1607,
      "step": 278
    },
    {
      "epoch": 0.7654320987654321,
      "grad_norm": 0.164581760764122,
      "learning_rate": 6.439393939393939e-05,
      "loss": 1.2018,
      "step": 279
    },
    {
      "epoch": 0.7681755829903978,
      "grad_norm": 0.1688939481973648,
      "learning_rate": 6.363636363636364e-05,
      "loss": 1.1698,
      "step": 280
    },
    {
      "epoch": 0.7709190672153635,
      "grad_norm": 0.1699894666671753,
      "learning_rate": 6.287878787878788e-05,
      "loss": 1.2385,
      "step": 281
    },
    {
      "epoch": 0.7736625514403292,
      "grad_norm": 0.16270920634269714,
      "learning_rate": 6.212121212121213e-05,
      "loss": 1.2186,
      "step": 282
    },
    {
      "epoch": 0.7764060356652949,
      "grad_norm": 0.1695300042629242,
      "learning_rate": 6.136363636363636e-05,
      "loss": 1.1761,
      "step": 283
    },
    {
      "epoch": 0.7791495198902606,
      "grad_norm": 0.15952111780643463,
      "learning_rate": 6.060606060606061e-05,
      "loss": 1.1664,
      "step": 284
    },
    {
      "epoch": 0.7818930041152263,
      "grad_norm": 0.16307595372200012,
      "learning_rate": 5.9848484848484854e-05,
      "loss": 1.2355,
      "step": 285
    },
    {
      "epoch": 0.7846364883401921,
      "grad_norm": 0.16836188733577728,
      "learning_rate": 5.90909090909091e-05,
      "loss": 1.2188,
      "step": 286
    },
    {
      "epoch": 0.7873799725651578,
      "grad_norm": 0.17626118659973145,
      "learning_rate": 5.833333333333334e-05,
      "loss": 1.1807,
      "step": 287
    },
    {
      "epoch": 0.7901234567901234,
      "grad_norm": 0.15906862914562225,
      "learning_rate": 5.757575757575758e-05,
      "loss": 1.1282,
      "step": 288
    },
    {
      "epoch": 0.7928669410150891,
      "grad_norm": 0.16204234957695007,
      "learning_rate": 5.6818181818181825e-05,
      "loss": 1.1278,
      "step": 289
    },
    {
      "epoch": 0.7956104252400549,
      "grad_norm": 0.16730915009975433,
      "learning_rate": 5.606060606060606e-05,
      "loss": 1.1749,
      "step": 290
    },
    {
      "epoch": 0.7983539094650206,
      "grad_norm": 0.1525382548570633,
      "learning_rate": 5.5303030303030304e-05,
      "loss": 1.2134,
      "step": 291
    },
    {
      "epoch": 0.8010973936899863,
      "grad_norm": 0.17000265419483185,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 1.1661,
      "step": 292
    },
    {
      "epoch": 0.803840877914952,
      "grad_norm": 0.16208770871162415,
      "learning_rate": 5.378787878787879e-05,
      "loss": 1.1965,
      "step": 293
    },
    {
      "epoch": 0.8065843621399177,
      "grad_norm": 0.15758417546749115,
      "learning_rate": 5.303030303030303e-05,
      "loss": 1.2708,
      "step": 294
    },
    {
      "epoch": 0.8093278463648834,
      "grad_norm": 0.16219446063041687,
      "learning_rate": 5.2272727272727274e-05,
      "loss": 1.175,
      "step": 295
    },
    {
      "epoch": 0.8120713305898491,
      "grad_norm": 0.181773379445076,
      "learning_rate": 5.151515151515152e-05,
      "loss": 1.0874,
      "step": 296
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 0.1878584921360016,
      "learning_rate": 5.075757575757576e-05,
      "loss": 1.2115,
      "step": 297
    },
    {
      "epoch": 0.8175582990397805,
      "grad_norm": 0.1562959998846054,
      "learning_rate": 5e-05,
      "loss": 1.1326,
      "step": 298
    },
    {
      "epoch": 0.8203017832647462,
      "grad_norm": 0.1604573130607605,
      "learning_rate": 4.9242424242424245e-05,
      "loss": 1.1464,
      "step": 299
    },
    {
      "epoch": 0.823045267489712,
      "grad_norm": 0.17849043011665344,
      "learning_rate": 4.848484848484849e-05,
      "loss": 1.0647,
      "step": 300
    },
    {
      "epoch": 0.8257887517146777,
      "grad_norm": 0.1586693972349167,
      "learning_rate": 4.772727272727273e-05,
      "loss": 1.0934,
      "step": 301
    },
    {
      "epoch": 0.8285322359396433,
      "grad_norm": 0.16506658494472504,
      "learning_rate": 4.696969696969697e-05,
      "loss": 1.2328,
      "step": 302
    },
    {
      "epoch": 0.831275720164609,
      "grad_norm": 0.1512569636106491,
      "learning_rate": 4.621212121212121e-05,
      "loss": 1.2138,
      "step": 303
    },
    {
      "epoch": 0.8340192043895748,
      "grad_norm": 0.1551409214735031,
      "learning_rate": 4.545454545454546e-05,
      "loss": 1.1493,
      "step": 304
    },
    {
      "epoch": 0.8367626886145405,
      "grad_norm": 0.16985191404819489,
      "learning_rate": 4.46969696969697e-05,
      "loss": 1.1409,
      "step": 305
    },
    {
      "epoch": 0.8395061728395061,
      "grad_norm": 0.15144294500350952,
      "learning_rate": 4.3939393939393944e-05,
      "loss": 1.2017,
      "step": 306
    },
    {
      "epoch": 0.8422496570644719,
      "grad_norm": 0.16904205083847046,
      "learning_rate": 4.318181818181819e-05,
      "loss": 1.2454,
      "step": 307
    },
    {
      "epoch": 0.8449931412894376,
      "grad_norm": 0.15679828822612762,
      "learning_rate": 4.242424242424243e-05,
      "loss": 1.1626,
      "step": 308
    },
    {
      "epoch": 0.8477366255144033,
      "grad_norm": 0.1584944874048233,
      "learning_rate": 4.166666666666667e-05,
      "loss": 1.2979,
      "step": 309
    },
    {
      "epoch": 0.850480109739369,
      "grad_norm": 0.16384479403495789,
      "learning_rate": 4.0909090909090915e-05,
      "loss": 1.1728,
      "step": 310
    },
    {
      "epoch": 0.8532235939643347,
      "grad_norm": 0.16321486234664917,
      "learning_rate": 4.015151515151515e-05,
      "loss": 1.1622,
      "step": 311
    },
    {
      "epoch": 0.8559670781893004,
      "grad_norm": 0.1510697901248932,
      "learning_rate": 3.939393939393939e-05,
      "loss": 1.2212,
      "step": 312
    },
    {
      "epoch": 0.8587105624142661,
      "grad_norm": 0.15566690266132355,
      "learning_rate": 3.8636363636363636e-05,
      "loss": 1.2098,
      "step": 313
    },
    {
      "epoch": 0.8614540466392319,
      "grad_norm": 0.1588331162929535,
      "learning_rate": 3.787878787878788e-05,
      "loss": 1.2401,
      "step": 314
    },
    {
      "epoch": 0.8641975308641975,
      "grad_norm": 0.15694394707679749,
      "learning_rate": 3.712121212121212e-05,
      "loss": 1.2619,
      "step": 315
    },
    {
      "epoch": 0.8669410150891632,
      "grad_norm": 0.15612713992595673,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 1.1761,
      "step": 316
    },
    {
      "epoch": 0.869684499314129,
      "grad_norm": 0.15668469667434692,
      "learning_rate": 3.560606060606061e-05,
      "loss": 1.1711,
      "step": 317
    },
    {
      "epoch": 0.8724279835390947,
      "grad_norm": 0.16212019324302673,
      "learning_rate": 3.484848484848485e-05,
      "loss": 1.1346,
      "step": 318
    },
    {
      "epoch": 0.8751714677640604,
      "grad_norm": 0.16122637689113617,
      "learning_rate": 3.409090909090909e-05,
      "loss": 1.2463,
      "step": 319
    },
    {
      "epoch": 0.877914951989026,
      "grad_norm": 0.1728198379278183,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.1552,
      "step": 320
    },
    {
      "epoch": 0.8806584362139918,
      "grad_norm": 0.15141616761684418,
      "learning_rate": 3.257575757575758e-05,
      "loss": 1.2216,
      "step": 321
    },
    {
      "epoch": 0.8834019204389575,
      "grad_norm": 0.18166609108448029,
      "learning_rate": 3.181818181818182e-05,
      "loss": 1.1831,
      "step": 322
    },
    {
      "epoch": 0.8861454046639232,
      "grad_norm": 0.1654902696609497,
      "learning_rate": 3.106060606060606e-05,
      "loss": 1.1447,
      "step": 323
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.15685853362083435,
      "learning_rate": 3.0303030303030306e-05,
      "loss": 1.1643,
      "step": 324
    },
    {
      "epoch": 0.8916323731138546,
      "grad_norm": 0.16564173996448517,
      "learning_rate": 2.954545454545455e-05,
      "loss": 1.1338,
      "step": 325
    },
    {
      "epoch": 0.8943758573388203,
      "grad_norm": 0.16028645634651184,
      "learning_rate": 2.878787878787879e-05,
      "loss": 1.1408,
      "step": 326
    },
    {
      "epoch": 0.897119341563786,
      "grad_norm": 0.1589888632297516,
      "learning_rate": 2.803030303030303e-05,
      "loss": 1.0775,
      "step": 327
    },
    {
      "epoch": 0.8998628257887518,
      "grad_norm": 0.16097234189510345,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 1.1833,
      "step": 328
    },
    {
      "epoch": 0.9026063100137174,
      "grad_norm": 0.15900030732154846,
      "learning_rate": 2.6515151515151516e-05,
      "loss": 1.2392,
      "step": 329
    },
    {
      "epoch": 0.9053497942386831,
      "grad_norm": 0.15157172083854675,
      "learning_rate": 2.575757575757576e-05,
      "loss": 1.1812,
      "step": 330
    },
    {
      "epoch": 0.9080932784636488,
      "grad_norm": 0.1556706726551056,
      "learning_rate": 2.5e-05,
      "loss": 1.1528,
      "step": 331
    },
    {
      "epoch": 0.9108367626886146,
      "grad_norm": 0.16983263194561005,
      "learning_rate": 2.4242424242424244e-05,
      "loss": 1.1711,
      "step": 332
    },
    {
      "epoch": 0.9135802469135802,
      "grad_norm": 0.15927070379257202,
      "learning_rate": 2.3484848484848487e-05,
      "loss": 1.1595,
      "step": 333
    },
    {
      "epoch": 0.9163237311385459,
      "grad_norm": 0.16879941523075104,
      "learning_rate": 2.272727272727273e-05,
      "loss": 1.1557,
      "step": 334
    },
    {
      "epoch": 0.9190672153635117,
      "grad_norm": 0.15948091447353363,
      "learning_rate": 2.1969696969696972e-05,
      "loss": 1.149,
      "step": 335
    },
    {
      "epoch": 0.9218106995884774,
      "grad_norm": 0.16563957929611206,
      "learning_rate": 2.1212121212121215e-05,
      "loss": 1.1512,
      "step": 336
    },
    {
      "epoch": 0.9245541838134431,
      "grad_norm": 0.16133056581020355,
      "learning_rate": 2.0454545454545457e-05,
      "loss": 1.1601,
      "step": 337
    },
    {
      "epoch": 0.9272976680384087,
      "grad_norm": 0.16423514485359192,
      "learning_rate": 1.9696969696969697e-05,
      "loss": 1.1818,
      "step": 338
    },
    {
      "epoch": 0.9300411522633745,
      "grad_norm": 0.15817779302597046,
      "learning_rate": 1.893939393939394e-05,
      "loss": 1.1535,
      "step": 339
    },
    {
      "epoch": 0.9327846364883402,
      "grad_norm": 0.15314935147762299,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 1.1903,
      "step": 340
    },
    {
      "epoch": 0.9355281207133059,
      "grad_norm": 0.16656365990638733,
      "learning_rate": 1.7424242424242425e-05,
      "loss": 1.1524,
      "step": 341
    },
    {
      "epoch": 0.9382716049382716,
      "grad_norm": 0.17102104425430298,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.2069,
      "step": 342
    },
    {
      "epoch": 0.9410150891632373,
      "grad_norm": 0.1725992113351822,
      "learning_rate": 1.590909090909091e-05,
      "loss": 1.1236,
      "step": 343
    },
    {
      "epoch": 0.943758573388203,
      "grad_norm": 0.17219319939613342,
      "learning_rate": 1.5151515151515153e-05,
      "loss": 1.1849,
      "step": 344
    },
    {
      "epoch": 0.9465020576131687,
      "grad_norm": 0.15850085020065308,
      "learning_rate": 1.4393939393939396e-05,
      "loss": 1.1708,
      "step": 345
    },
    {
      "epoch": 0.9492455418381345,
      "grad_norm": 0.15814326703548431,
      "learning_rate": 1.3636363636363637e-05,
      "loss": 1.1695,
      "step": 346
    },
    {
      "epoch": 0.9519890260631001,
      "grad_norm": 0.15282317996025085,
      "learning_rate": 1.287878787878788e-05,
      "loss": 1.2195,
      "step": 347
    },
    {
      "epoch": 0.9547325102880658,
      "grad_norm": 0.16384905576705933,
      "learning_rate": 1.2121212121212122e-05,
      "loss": 1.1989,
      "step": 348
    },
    {
      "epoch": 0.9574759945130316,
      "grad_norm": 0.16359828412532806,
      "learning_rate": 1.1363636363636365e-05,
      "loss": 1.0967,
      "step": 349
    }
  ],
  "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": 4.323960827284808e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}