{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9991668980838657,
  "eval_steps": 500,
  "global_step": 1350,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0022216051096917524,
      "grad_norm": 0.002978345612064004,
      "learning_rate": 0.0,
      "loss": 0.6591,
      "step": 1
    },
    {
      "epoch": 0.004443210219383505,
      "grad_norm": 0.0013871944975107908,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.4939,
      "step": 2
    },
    {
      "epoch": 0.006664815329075257,
      "grad_norm": 0.0016968267736956477,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.7284,
      "step": 3
    },
    {
      "epoch": 0.00888642043876701,
      "grad_norm": 0.0019407571526244283,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.6134,
      "step": 4
    },
    {
      "epoch": 0.011108025548458762,
      "grad_norm": 0.0023587460163980722,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.5502,
      "step": 5
    },
    {
      "epoch": 0.013329630658150514,
      "grad_norm": 0.0016757827252149582,
      "learning_rate": 0.0001111111111111111,
      "loss": 0.6668,
      "step": 6
    },
    {
      "epoch": 0.015551235767842266,
      "grad_norm": 0.0019603732507675886,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.631,
      "step": 7
    },
    {
      "epoch": 0.01777284087753402,
      "grad_norm": 0.0016572908498346806,
      "learning_rate": 0.00015555555555555556,
      "loss": 0.6591,
      "step": 8
    },
    {
      "epoch": 0.01999444598722577,
      "grad_norm": 0.002483464078977704,
      "learning_rate": 0.00017777777777777779,
      "loss": 0.7424,
      "step": 9
    },
    {
      "epoch": 0.022216051096917523,
      "grad_norm": 0.0016225713770836592,
      "learning_rate": 0.0002,
      "loss": 0.6104,
      "step": 10
    },
    {
      "epoch": 0.024437656206609277,
      "grad_norm": 0.0015255049802362919,
      "learning_rate": 0.0002222222222222222,
      "loss": 0.5474,
      "step": 11
    },
    {
      "epoch": 0.026659261316301027,
      "grad_norm": 0.002024372573941946,
      "learning_rate": 0.0002444444444444445,
      "loss": 0.6242,
      "step": 12
    },
    {
      "epoch": 0.02888086642599278,
      "grad_norm": 0.0016474858857691288,
      "learning_rate": 0.0002666666666666667,
      "loss": 0.5601,
      "step": 13
    },
    {
      "epoch": 0.03110247153568453,
      "grad_norm": 0.0030031136702746153,
      "learning_rate": 0.0002888888888888889,
      "loss": 0.7242,
      "step": 14
    },
    {
      "epoch": 0.03332407664537628,
      "grad_norm": 0.0017679812153801322,
      "learning_rate": 0.0003111111111111111,
      "loss": 0.7104,
      "step": 15
    },
    {
      "epoch": 0.03554568175506804,
      "grad_norm": 0.0014827997656539083,
      "learning_rate": 0.0003333333333333333,
      "loss": 0.5902,
      "step": 16
    },
    {
      "epoch": 0.03776728686475979,
      "grad_norm": 0.0017735514556989074,
      "learning_rate": 0.00035555555555555557,
      "loss": 0.6007,
      "step": 17
    },
    {
      "epoch": 0.03998889197445154,
      "grad_norm": 0.0025237284135073423,
      "learning_rate": 0.00037777777777777777,
      "loss": 0.7005,
      "step": 18
    },
    {
      "epoch": 0.042210497084143296,
      "grad_norm": 0.002557172207161784,
      "learning_rate": 0.0004,
      "loss": 0.8006,
      "step": 19
    },
    {
      "epoch": 0.044432102193835046,
      "grad_norm": 0.00220920005813241,
      "learning_rate": 0.00042222222222222227,
      "loss": 0.7215,
      "step": 20
    },
    {
      "epoch": 0.0466537073035268,
      "grad_norm": 0.0013707042671740055,
      "learning_rate": 0.0004444444444444444,
      "loss": 0.4922,
      "step": 21
    },
    {
      "epoch": 0.048875312413218554,
      "grad_norm": 0.0008604795439168811,
      "learning_rate": 0.00046666666666666666,
      "loss": 0.5522,
      "step": 22
    },
    {
      "epoch": 0.051096917522910304,
      "grad_norm": 0.0026402759831398726,
      "learning_rate": 0.000488888888888889,
      "loss": 0.6233,
      "step": 23
    },
    {
      "epoch": 0.053318522632602054,
      "grad_norm": 0.0017297494923695922,
      "learning_rate": 0.0005111111111111112,
      "loss": 0.6557,
      "step": 24
    },
    {
      "epoch": 0.055540127742293804,
      "grad_norm": 0.0022551107686012983,
      "learning_rate": 0.0005333333333333334,
      "loss": 0.6477,
      "step": 25
    },
    {
      "epoch": 0.05776173285198556,
      "grad_norm": 0.0019956438336521387,
      "learning_rate": 0.0005555555555555556,
      "loss": 0.7574,
      "step": 26
    },
    {
      "epoch": 0.05998333796167731,
      "grad_norm": 0.0016538758063688874,
      "learning_rate": 0.0005777777777777778,
      "loss": 0.6065,
      "step": 27
    },
    {
      "epoch": 0.06220494307136906,
      "grad_norm": 0.0017617472913116217,
      "learning_rate": 0.0006000000000000001,
      "loss": 0.7523,
      "step": 28
    },
    {
      "epoch": 0.06442654818106082,
      "grad_norm": 0.001698676380328834,
      "learning_rate": 0.0006222222222222223,
      "loss": 0.682,
      "step": 29
    },
    {
      "epoch": 0.06664815329075256,
      "grad_norm": 0.0018153442069888115,
      "learning_rate": 0.0006444444444444444,
      "loss": 0.6639,
      "step": 30
    },
    {
      "epoch": 0.06886975840044432,
      "grad_norm": 0.003996333107352257,
      "learning_rate": 0.0006666666666666666,
      "loss": 0.654,
      "step": 31
    },
    {
      "epoch": 0.07109136351013608,
      "grad_norm": 0.002476347843185067,
      "learning_rate": 0.000688888888888889,
      "loss": 0.7648,
      "step": 32
    },
    {
      "epoch": 0.07331296861982782,
      "grad_norm": 0.0020105133298784494,
      "learning_rate": 0.0007111111111111111,
      "loss": 0.6186,
      "step": 33
    },
    {
      "epoch": 0.07553457372951958,
      "grad_norm": 0.0015922179445624352,
      "learning_rate": 0.0007333333333333333,
      "loss": 0.6831,
      "step": 34
    },
    {
      "epoch": 0.07775617883921133,
      "grad_norm": 0.0028106248937547207,
      "learning_rate": 0.0007555555555555555,
      "loss": 0.7692,
      "step": 35
    },
    {
      "epoch": 0.07997778394890308,
      "grad_norm": 0.0028889004606753588,
      "learning_rate": 0.0007777777777777777,
      "loss": 0.5085,
      "step": 36
    },
    {
      "epoch": 0.08219938905859484,
      "grad_norm": 0.0027827643789350986,
      "learning_rate": 0.0008,
      "loss": 0.6481,
      "step": 37
    },
    {
      "epoch": 0.08442099416828659,
      "grad_norm": 0.0026504015550017357,
      "learning_rate": 0.0008222222222222222,
      "loss": 0.5612,
      "step": 38
    },
    {
      "epoch": 0.08664259927797834,
      "grad_norm": 0.0032035443000495434,
      "learning_rate": 0.0008444444444444445,
      "loss": 0.7215,
      "step": 39
    },
    {
      "epoch": 0.08886420438767009,
      "grad_norm": 0.005165774375200272,
      "learning_rate": 0.0008666666666666666,
      "loss": 0.6939,
      "step": 40
    },
    {
      "epoch": 0.09108580949736185,
      "grad_norm": 0.002177528338506818,
      "learning_rate": 0.0008888888888888888,
      "loss": 0.7129,
      "step": 41
    },
    {
      "epoch": 0.0933074146070536,
      "grad_norm": 0.0028440060559660196,
      "learning_rate": 0.0009111111111111111,
      "loss": 0.7806,
      "step": 42
    },
    {
      "epoch": 0.09552901971674535,
      "grad_norm": 0.003377707442268729,
      "learning_rate": 0.0009333333333333333,
      "loss": 0.6896,
      "step": 43
    },
    {
      "epoch": 0.09775062482643711,
      "grad_norm": 0.0022622300311923027,
      "learning_rate": 0.0009555555555555556,
      "loss": 0.6273,
      "step": 44
    },
    {
      "epoch": 0.09997222993612885,
      "grad_norm": 0.0021498145069926977,
      "learning_rate": 0.000977777777777778,
      "loss": 0.52,
      "step": 45
    },
    {
      "epoch": 0.10219383504582061,
      "grad_norm": 0.0020568969193845987,
      "learning_rate": 0.001,
      "loss": 0.671,
      "step": 46
    },
    {
      "epoch": 0.10441544015551235,
      "grad_norm": 0.001877099508419633,
      "learning_rate": 0.0010222222222222223,
      "loss": 0.8283,
      "step": 47
    },
    {
      "epoch": 0.10663704526520411,
      "grad_norm": 0.0070748962461948395,
      "learning_rate": 0.0010444444444444444,
      "loss": 0.6469,
      "step": 48
    },
    {
      "epoch": 0.10885865037489587,
      "grad_norm": 0.0017249450320377946,
      "learning_rate": 0.0010666666666666667,
      "loss": 0.6326,
      "step": 49
    },
    {
      "epoch": 0.11108025548458761,
      "grad_norm": 0.004852880258113146,
      "learning_rate": 0.001088888888888889,
      "loss": 0.5728,
      "step": 50
    },
    {
      "epoch": 0.11330186059427937,
      "grad_norm": 0.004102539736777544,
      "learning_rate": 0.0011111111111111111,
      "loss": 0.7024,
      "step": 51
    },
    {
      "epoch": 0.11552346570397112,
      "grad_norm": 0.003420061431825161,
      "learning_rate": 0.0011333333333333334,
      "loss": 0.5515,
      "step": 52
    },
    {
      "epoch": 0.11774507081366287,
      "grad_norm": 0.0017662738682702184,
      "learning_rate": 0.0011555555555555555,
      "loss": 0.6062,
      "step": 53
    },
    {
      "epoch": 0.11996667592335462,
      "grad_norm": 0.0073768808506429195,
      "learning_rate": 0.0011777777777777778,
      "loss": 0.6246,
      "step": 54
    },
    {
      "epoch": 0.12218828103304638,
      "grad_norm": 0.001454327953979373,
      "learning_rate": 0.0012000000000000001,
      "loss": 0.5378,
      "step": 55
    },
    {
      "epoch": 0.12440988614273812,
      "grad_norm": 0.0027155750431120396,
      "learning_rate": 0.0012222222222222222,
      "loss": 0.6561,
      "step": 56
    },
    {
      "epoch": 0.12663149125242987,
      "grad_norm": 0.002913674106821418,
      "learning_rate": 0.0012444444444444445,
      "loss": 0.6416,
      "step": 57
    },
    {
      "epoch": 0.12885309636212164,
      "grad_norm": 0.0054724751971662045,
      "learning_rate": 0.0012666666666666666,
      "loss": 0.5742,
      "step": 58
    },
    {
      "epoch": 0.13107470147181338,
      "grad_norm": 0.0024632643908262253,
      "learning_rate": 0.001288888888888889,
      "loss": 0.553,
      "step": 59
    },
    {
      "epoch": 0.13329630658150513,
      "grad_norm": 0.003835581708699465,
      "learning_rate": 0.0013111111111111112,
      "loss": 0.7029,
      "step": 60
    },
    {
      "epoch": 0.1355179116911969,
      "grad_norm": 0.0020944341085851192,
      "learning_rate": 0.0013333333333333333,
      "loss": 0.7039,
      "step": 61
    },
    {
      "epoch": 0.13773951680088864,
      "grad_norm": 0.0016415991121903062,
      "learning_rate": 0.0013555555555555556,
      "loss": 0.6375,
      "step": 62
    },
    {
      "epoch": 0.13996112191058038,
      "grad_norm": 0.0028381466399878263,
      "learning_rate": 0.001377777777777778,
      "loss": 0.6652,
      "step": 63
    },
    {
      "epoch": 0.14218272702027215,
      "grad_norm": 0.006451457738876343,
      "learning_rate": 0.0014,
      "loss": 0.7621,
      "step": 64
    },
    {
      "epoch": 0.1444043321299639,
      "grad_norm": 0.0017908411100506783,
      "learning_rate": 0.0014222222222222223,
      "loss": 0.5331,
      "step": 65
    },
    {
      "epoch": 0.14662593723965564,
      "grad_norm": 0.0018273793393746018,
      "learning_rate": 0.0014444444444444444,
      "loss": 0.7655,
      "step": 66
    },
    {
      "epoch": 0.1488475423493474,
      "grad_norm": 0.004190357401967049,
      "learning_rate": 0.0014666666666666667,
      "loss": 0.8985,
      "step": 67
    },
    {
      "epoch": 0.15106914745903915,
      "grad_norm": 0.002071850700303912,
      "learning_rate": 0.001488888888888889,
      "loss": 0.6844,
      "step": 68
    },
    {
      "epoch": 0.1532907525687309,
      "grad_norm": 0.0029427469708025455,
      "learning_rate": 0.001511111111111111,
      "loss": 0.6433,
      "step": 69
    },
    {
      "epoch": 0.15551235767842267,
      "grad_norm": 0.002799464389681816,
      "learning_rate": 0.0015333333333333332,
      "loss": 0.5143,
      "step": 70
    },
    {
      "epoch": 0.1577339627881144,
      "grad_norm": 0.00132674106862396,
      "learning_rate": 0.0015555555555555555,
      "loss": 0.5482,
      "step": 71
    },
    {
      "epoch": 0.15995556789780616,
      "grad_norm": 0.004294063430279493,
      "learning_rate": 0.0015777777777777778,
      "loss": 0.5998,
      "step": 72
    },
    {
      "epoch": 0.16217717300749793,
      "grad_norm": 0.0027393323834985495,
      "learning_rate": 0.0016,
      "loss": 0.6376,
      "step": 73
    },
    {
      "epoch": 0.16439877811718967,
      "grad_norm": 0.002440163865685463,
      "learning_rate": 0.0016222222222222222,
      "loss": 0.6393,
      "step": 74
    },
    {
      "epoch": 0.1666203832268814,
      "grad_norm": 0.0018057947745546699,
      "learning_rate": 0.0016444444444444445,
      "loss": 0.6526,
      "step": 75
    },
    {
      "epoch": 0.16884198833657318,
      "grad_norm": 0.0038268628995865583,
      "learning_rate": 0.0016666666666666668,
      "loss": 0.6248,
      "step": 76
    },
    {
      "epoch": 0.17106359344626493,
      "grad_norm": 0.0014695205027237535,
      "learning_rate": 0.001688888888888889,
      "loss": 0.5354,
      "step": 77
    },
    {
      "epoch": 0.17328519855595667,
      "grad_norm": 0.00252461526542902,
      "learning_rate": 0.0017111111111111114,
      "loss": 0.5942,
      "step": 78
    },
    {
      "epoch": 0.17550680366564844,
      "grad_norm": 0.0024841027334332466,
      "learning_rate": 0.0017333333333333333,
      "loss": 0.7636,
      "step": 79
    },
    {
      "epoch": 0.17772840877534019,
      "grad_norm": 0.0017661625752225518,
      "learning_rate": 0.0017555555555555556,
      "loss": 0.6604,
      "step": 80
    },
    {
      "epoch": 0.17995001388503193,
      "grad_norm": 0.001713680219836533,
      "learning_rate": 0.0017777777777777776,
      "loss": 0.6251,
      "step": 81
    },
    {
      "epoch": 0.1821716189947237,
      "grad_norm": 0.0012396598467603326,
      "learning_rate": 0.0018,
      "loss": 0.5461,
      "step": 82
    },
    {
      "epoch": 0.18439322410441544,
      "grad_norm": 0.0017101755365729332,
      "learning_rate": 0.0018222222222222223,
      "loss": 0.617,
      "step": 83
    },
    {
      "epoch": 0.1866148292141072,
      "grad_norm": 0.002272373763844371,
      "learning_rate": 0.0018444444444444446,
      "loss": 0.6311,
      "step": 84
    },
    {
      "epoch": 0.18883643432379896,
      "grad_norm": 0.0023803103249520063,
      "learning_rate": 0.0018666666666666666,
      "loss": 0.5571,
      "step": 85
    },
    {
      "epoch": 0.1910580394334907,
      "grad_norm": 0.0013279503909870982,
      "learning_rate": 0.001888888888888889,
      "loss": 0.6996,
      "step": 86
    },
    {
      "epoch": 0.19327964454318244,
      "grad_norm": 0.0018786260625347495,
      "learning_rate": 0.0019111111111111113,
      "loss": 0.6082,
      "step": 87
    },
    {
      "epoch": 0.19550124965287421,
      "grad_norm": 0.0023911159951239824,
      "learning_rate": 0.0019333333333333336,
      "loss": 0.5551,
      "step": 88
    },
    {
      "epoch": 0.19772285476256596,
      "grad_norm": 0.002580540021881461,
      "learning_rate": 0.001955555555555556,
      "loss": 0.7681,
      "step": 89
    },
    {
      "epoch": 0.1999444598722577,
      "grad_norm": 0.0023858866188675165,
      "learning_rate": 0.0019777777777777775,
      "loss": 0.6405,
      "step": 90
    },
    {
      "epoch": 0.20216606498194944,
      "grad_norm": 0.002875383011996746,
      "learning_rate": 0.002,
      "loss": 0.7206,
      "step": 91
    },
    {
      "epoch": 0.20438767009164122,
      "grad_norm": 0.002432236447930336,
      "learning_rate": 0.002022222222222222,
      "loss": 0.6539,
      "step": 92
    },
    {
      "epoch": 0.20660927520133296,
      "grad_norm": 0.0016363706672564149,
      "learning_rate": 0.0020444444444444447,
      "loss": 0.5866,
      "step": 93
    },
    {
      "epoch": 0.2088308803110247,
      "grad_norm": 0.0028457841835916042,
      "learning_rate": 0.0020666666666666667,
      "loss": 0.6581,
      "step": 94
    },
    {
      "epoch": 0.21105248542071647,
      "grad_norm": 0.0015321681275963783,
      "learning_rate": 0.002088888888888889,
      "loss": 0.5968,
      "step": 95
    },
    {
      "epoch": 0.21327409053040822,
      "grad_norm": 0.002201031194999814,
      "learning_rate": 0.0021111111111111113,
      "loss": 0.6268,
      "step": 96
    },
    {
      "epoch": 0.21549569564009996,
      "grad_norm": 0.0014836075715720654,
      "learning_rate": 0.0021333333333333334,
      "loss": 0.6569,
      "step": 97
    },
    {
      "epoch": 0.21771730074979173,
      "grad_norm": 0.0018127993680536747,
      "learning_rate": 0.0021555555555555555,
      "loss": 0.5488,
      "step": 98
    },
    {
      "epoch": 0.21993890585948347,
      "grad_norm": 0.0022028337698429823,
      "learning_rate": 0.002177777777777778,
      "loss": 0.6088,
      "step": 99
    },
    {
      "epoch": 0.22216051096917522,
      "grad_norm": 0.0025130962021648884,
      "learning_rate": 0.0021999999999999997,
      "loss": 0.6773,
      "step": 100
    },
    {
      "epoch": 0.224382116078867,
      "grad_norm": 0.0014663820620626211,
      "learning_rate": 0.0022222222222222222,
      "loss": 0.6142,
      "step": 101
    },
    {
      "epoch": 0.22660372118855873,
      "grad_norm": 0.002425346989184618,
      "learning_rate": 0.0022444444444444443,
      "loss": 0.493,
      "step": 102
    },
    {
      "epoch": 0.22882532629825048,
      "grad_norm": 0.0017977328971028328,
      "learning_rate": 0.002266666666666667,
      "loss": 0.4999,
      "step": 103
    },
    {
      "epoch": 0.23104693140794225,
      "grad_norm": 0.004254640080034733,
      "learning_rate": 0.002288888888888889,
      "loss": 0.7027,
      "step": 104
    },
    {
      "epoch": 0.233268536517634,
      "grad_norm": 0.0023587141185998917,
      "learning_rate": 0.002311111111111111,
      "loss": 0.5627,
      "step": 105
    },
    {
      "epoch": 0.23549014162732573,
      "grad_norm": 0.0014495557406917214,
      "learning_rate": 0.0023333333333333335,
      "loss": 0.6247,
      "step": 106
    },
    {
      "epoch": 0.2377117467370175,
      "grad_norm": 0.0014492189511656761,
      "learning_rate": 0.0023555555555555556,
      "loss": 0.6148,
      "step": 107
    },
    {
      "epoch": 0.23993335184670925,
      "grad_norm": 0.0021560671739280224,
      "learning_rate": 0.002377777777777778,
      "loss": 0.5968,
      "step": 108
    },
    {
      "epoch": 0.242154956956401,
      "grad_norm": 0.001538675744086504,
      "learning_rate": 0.0024000000000000002,
      "loss": 0.6815,
      "step": 109
    },
    {
      "epoch": 0.24437656206609276,
      "grad_norm": 0.001505226013250649,
      "learning_rate": 0.0024222222222222223,
      "loss": 0.6563,
      "step": 110
    },
    {
      "epoch": 0.2465981671757845,
      "grad_norm": 0.0022637355141341686,
      "learning_rate": 0.0024444444444444444,
      "loss": 0.5982,
      "step": 111
    },
    {
      "epoch": 0.24881977228547625,
      "grad_norm": 0.0022962612565606833,
      "learning_rate": 0.0024666666666666665,
      "loss": 0.6864,
      "step": 112
    },
    {
      "epoch": 0.251041377395168,
      "grad_norm": 0.0015861426945775747,
      "learning_rate": 0.002488888888888889,
      "loss": 0.5909,
      "step": 113
    },
    {
      "epoch": 0.25326298250485973,
      "grad_norm": 0.0016854581190273166,
      "learning_rate": 0.002511111111111111,
      "loss": 0.6506,
      "step": 114
    },
    {
      "epoch": 0.2554845876145515,
      "grad_norm": 0.002033884869888425,
      "learning_rate": 0.002533333333333333,
      "loss": 0.5596,
      "step": 115
    },
    {
      "epoch": 0.2577061927242433,
      "grad_norm": 0.0015449731145054102,
      "learning_rate": 0.0025555555555555557,
      "loss": 0.7478,
      "step": 116
    },
    {
      "epoch": 0.259927797833935,
      "grad_norm": 0.0012192435096949339,
      "learning_rate": 0.002577777777777778,
      "loss": 0.5802,
      "step": 117
    },
    {
      "epoch": 0.26214940294362676,
      "grad_norm": 0.0030470327474176884,
      "learning_rate": 0.0026000000000000003,
      "loss": 0.6025,
      "step": 118
    },
    {
      "epoch": 0.26437100805331853,
      "grad_norm": 0.0011102311545982957,
      "learning_rate": 0.0026222222222222224,
      "loss": 0.5882,
      "step": 119
    },
    {
      "epoch": 0.26659261316301025,
      "grad_norm": 0.006781211122870445,
      "learning_rate": 0.0026444444444444445,
      "loss": 0.9272,
      "step": 120
    },
    {
      "epoch": 0.268814218272702,
      "grad_norm": 0.002074405550956726,
      "learning_rate": 0.0026666666666666666,
      "loss": 0.8835,
      "step": 121
    },
    {
      "epoch": 0.2710358233823938,
      "grad_norm": 0.0017659831792116165,
      "learning_rate": 0.0026888888888888887,
      "loss": 0.6341,
      "step": 122
    },
    {
      "epoch": 0.2732574284920855,
      "grad_norm": 0.0025901361368596554,
      "learning_rate": 0.002711111111111111,
      "loss": 0.6695,
      "step": 123
    },
    {
      "epoch": 0.2754790336017773,
      "grad_norm": 0.0013919497141614556,
      "learning_rate": 0.0027333333333333333,
      "loss": 0.6147,
      "step": 124
    },
    {
      "epoch": 0.27770063871146905,
      "grad_norm": 0.0022205966524779797,
      "learning_rate": 0.002755555555555556,
      "loss": 0.5724,
      "step": 125
    },
    {
      "epoch": 0.27992224382116077,
      "grad_norm": 0.002219931688159704,
      "learning_rate": 0.002777777777777778,
      "loss": 0.6109,
      "step": 126
    },
    {
      "epoch": 0.28214384893085254,
      "grad_norm": 0.0018487212946638465,
      "learning_rate": 0.0028,
      "loss": 0.6376,
      "step": 127
    },
    {
      "epoch": 0.2843654540405443,
      "grad_norm": 0.0025875235442072153,
      "learning_rate": 0.0028222222222222225,
      "loss": 0.6711,
      "step": 128
    },
    {
      "epoch": 0.286587059150236,
      "grad_norm": 0.0018475636607035995,
      "learning_rate": 0.0028444444444444446,
      "loss": 0.6137,
      "step": 129
    },
    {
      "epoch": 0.2888086642599278,
      "grad_norm": 0.0021733460016548634,
      "learning_rate": 0.0028666666666666667,
      "loss": 0.6284,
      "step": 130
    },
    {
      "epoch": 0.29103026936961957,
      "grad_norm": 0.0016470282571390271,
      "learning_rate": 0.0028888888888888888,
      "loss": 0.7187,
      "step": 131
    },
    {
      "epoch": 0.2932518744793113,
      "grad_norm": 0.0015948446234688163,
      "learning_rate": 0.002911111111111111,
      "loss": 0.657,
      "step": 132
    },
    {
      "epoch": 0.29547347958900305,
      "grad_norm": 0.0021042751614004374,
      "learning_rate": 0.0029333333333333334,
      "loss": 0.621,
      "step": 133
    },
    {
      "epoch": 0.2976950846986948,
      "grad_norm": 0.0036005896981805563,
      "learning_rate": 0.0029555555555555555,
      "loss": 0.7061,
      "step": 134
    },
    {
      "epoch": 0.29991668980838654,
      "grad_norm": 0.002359282923862338,
      "learning_rate": 0.002977777777777778,
      "loss": 0.7754,
      "step": 135
    },
    {
      "epoch": 0.3021382949180783,
      "grad_norm": 0.00216419855132699,
      "learning_rate": 0.003,
      "loss": 0.5726,
      "step": 136
    },
    {
      "epoch": 0.3043599000277701,
      "grad_norm": 0.002016279613599181,
      "learning_rate": 0.0029975308641975312,
      "loss": 0.6776,
      "step": 137
    },
    {
      "epoch": 0.3065815051374618,
      "grad_norm": 0.002253867918625474,
      "learning_rate": 0.0029950617283950615,
      "loss": 0.7355,
      "step": 138
    },
    {
      "epoch": 0.30880311024715357,
      "grad_norm": 0.0019491558196023107,
      "learning_rate": 0.0029925925925925927,
      "loss": 0.7555,
      "step": 139
    },
    {
      "epoch": 0.31102471535684534,
      "grad_norm": 0.001537105767056346,
      "learning_rate": 0.0029901234567901234,
      "loss": 0.5927,
      "step": 140
    },
    {
      "epoch": 0.31324632046653705,
      "grad_norm": 0.0018077421700581908,
      "learning_rate": 0.0029876543209876546,
      "loss": 0.5128,
      "step": 141
    },
    {
      "epoch": 0.3154679255762288,
      "grad_norm": 0.001842755707912147,
      "learning_rate": 0.002985185185185185,
      "loss": 0.6051,
      "step": 142
    },
    {
      "epoch": 0.3176895306859206,
      "grad_norm": 0.0017385258106514812,
      "learning_rate": 0.002982716049382716,
      "loss": 0.4971,
      "step": 143
    },
    {
      "epoch": 0.3199111357956123,
      "grad_norm": 0.002259904285892844,
      "learning_rate": 0.0029802469135802472,
      "loss": 0.7983,
      "step": 144
    },
    {
      "epoch": 0.3221327409053041,
      "grad_norm": 0.002299521816894412,
      "learning_rate": 0.002977777777777778,
      "loss": 0.6682,
      "step": 145
    },
    {
      "epoch": 0.32435434601499585,
      "grad_norm": 0.0025398312136530876,
      "learning_rate": 0.0029753086419753087,
      "loss": 0.6634,
      "step": 146
    },
    {
      "epoch": 0.32657595112468757,
      "grad_norm": 0.002047490095719695,
      "learning_rate": 0.0029728395061728394,
      "loss": 0.5549,
      "step": 147
    },
    {
      "epoch": 0.32879755623437934,
      "grad_norm": 0.0018858283292502165,
      "learning_rate": 0.0029703703703703706,
      "loss": 0.6083,
      "step": 148
    },
    {
      "epoch": 0.3310191613440711,
      "grad_norm": 0.002706357045099139,
      "learning_rate": 0.0029679012345679013,
      "loss": 0.5578,
      "step": 149
    },
    {
      "epoch": 0.3332407664537628,
      "grad_norm": 0.002534697065129876,
      "learning_rate": 0.002965432098765432,
      "loss": 0.7501,
      "step": 150
    },
    {
      "epoch": 0.3354623715634546,
      "grad_norm": 0.002316315658390522,
      "learning_rate": 0.002962962962962963,
      "loss": 0.6416,
      "step": 151
    },
    {
      "epoch": 0.33768397667314637,
      "grad_norm": 0.002252229256555438,
      "learning_rate": 0.002960493827160494,
      "loss": 0.5011,
      "step": 152
    },
    {
      "epoch": 0.3399055817828381,
      "grad_norm": 0.0024687203112989664,
      "learning_rate": 0.0029580246913580247,
      "loss": 0.6448,
      "step": 153
    },
    {
      "epoch": 0.34212718689252986,
      "grad_norm": 0.001848176820203662,
      "learning_rate": 0.0029555555555555555,
      "loss": 0.5618,
      "step": 154
    },
    {
      "epoch": 0.3443487920022216,
      "grad_norm": 0.0018136342987418175,
      "learning_rate": 0.0029530864197530866,
      "loss": 0.5538,
      "step": 155
    },
    {
      "epoch": 0.34657039711191334,
      "grad_norm": 0.002565361326560378,
      "learning_rate": 0.0029506172839506174,
      "loss": 0.7248,
      "step": 156
    },
    {
      "epoch": 0.3487920022216051,
      "grad_norm": 0.0033237517345696688,
      "learning_rate": 0.002948148148148148,
      "loss": 0.5542,
      "step": 157
    },
    {
      "epoch": 0.3510136073312969,
      "grad_norm": 0.0020103573333472013,
      "learning_rate": 0.002945679012345679,
      "loss": 0.7314,
      "step": 158
    },
    {
      "epoch": 0.3532352124409886,
      "grad_norm": 0.002449741819873452,
      "learning_rate": 0.00294320987654321,
      "loss": 0.6582,
      "step": 159
    },
    {
      "epoch": 0.35545681755068037,
      "grad_norm": 0.004268160555511713,
      "learning_rate": 0.0029407407407407407,
      "loss": 0.4959,
      "step": 160
    },
    {
      "epoch": 0.35767842266037214,
      "grad_norm": 0.0020266843494027853,
      "learning_rate": 0.0029382716049382715,
      "loss": 0.6745,
      "step": 161
    },
    {
      "epoch": 0.35990002777006386,
      "grad_norm": 0.003203684464097023,
      "learning_rate": 0.0029358024691358026,
      "loss": 0.5652,
      "step": 162
    },
    {
      "epoch": 0.36212163287975563,
      "grad_norm": 0.0025999690406024456,
      "learning_rate": 0.0029333333333333334,
      "loss": 0.6317,
      "step": 163
    },
    {
      "epoch": 0.3643432379894474,
      "grad_norm": 0.0022936356253921986,
      "learning_rate": 0.002930864197530864,
      "loss": 0.6372,
      "step": 164
    },
    {
      "epoch": 0.3665648430991391,
      "grad_norm": 0.0020697296131402254,
      "learning_rate": 0.002928395061728395,
      "loss": 0.5894,
      "step": 165
    },
    {
      "epoch": 0.3687864482088309,
      "grad_norm": 0.0013470306294038892,
      "learning_rate": 0.002925925925925926,
      "loss": 0.5388,
      "step": 166
    },
    {
      "epoch": 0.37100805331852266,
      "grad_norm": 0.0031622450333088636,
      "learning_rate": 0.002923456790123457,
      "loss": 0.62,
      "step": 167
    },
    {
      "epoch": 0.3732296584282144,
      "grad_norm": 0.002153768204152584,
      "learning_rate": 0.0029209876543209875,
      "loss": 0.4687,
      "step": 168
    },
    {
      "epoch": 0.37545126353790614,
      "grad_norm": 0.0023543303832411766,
      "learning_rate": 0.0029185185185185186,
      "loss": 0.6153,
      "step": 169
    },
    {
      "epoch": 0.3776728686475979,
      "grad_norm": 0.0024460828863084316,
      "learning_rate": 0.0029160493827160494,
      "loss": 0.5166,
      "step": 170
    },
    {
      "epoch": 0.37989447375728963,
      "grad_norm": 0.0015486665070056915,
      "learning_rate": 0.0029135802469135805,
      "loss": 0.5378,
      "step": 171
    },
    {
      "epoch": 0.3821160788669814,
      "grad_norm": 0.002441336400806904,
      "learning_rate": 0.002911111111111111,
      "loss": 0.4576,
      "step": 172
    },
    {
      "epoch": 0.3843376839766732,
      "grad_norm": 0.0027466551400721073,
      "learning_rate": 0.002908641975308642,
      "loss": 0.6743,
      "step": 173
    },
    {
      "epoch": 0.3865592890863649,
      "grad_norm": 0.003346341894939542,
      "learning_rate": 0.002906172839506173,
      "loss": 0.6676,
      "step": 174
    },
    {
      "epoch": 0.38878089419605666,
      "grad_norm": 0.0024875456001609564,
      "learning_rate": 0.002903703703703704,
      "loss": 0.5988,
      "step": 175
    },
    {
      "epoch": 0.39100249930574843,
      "grad_norm": 0.003013547509908676,
      "learning_rate": 0.0029012345679012346,
      "loss": 0.5765,
      "step": 176
    },
    {
      "epoch": 0.39322410441544015,
      "grad_norm": 0.004528356716036797,
      "learning_rate": 0.0028987654320987654,
      "loss": 0.7045,
      "step": 177
    },
    {
      "epoch": 0.3954457095251319,
      "grad_norm": 0.0031471021939069033,
      "learning_rate": 0.0028962962962962966,
      "loss": 0.6967,
      "step": 178
    },
    {
      "epoch": 0.3976673146348237,
      "grad_norm": 0.003111990401521325,
      "learning_rate": 0.0028938271604938273,
      "loss": 0.65,
      "step": 179
    },
    {
      "epoch": 0.3998889197445154,
      "grad_norm": 0.00214124983176589,
      "learning_rate": 0.002891358024691358,
      "loss": 0.524,
      "step": 180
    },
    {
      "epoch": 0.4021105248542072,
      "grad_norm": 0.003025785554200411,
      "learning_rate": 0.0028888888888888888,
      "loss": 0.627,
      "step": 181
    },
    {
      "epoch": 0.4043321299638989,
      "grad_norm": 0.0020541504491120577,
      "learning_rate": 0.00288641975308642,
      "loss": 0.4417,
      "step": 182
    },
    {
      "epoch": 0.40655373507359066,
      "grad_norm": 0.002211057348176837,
      "learning_rate": 0.0028839506172839507,
      "loss": 0.598,
      "step": 183
    },
    {
      "epoch": 0.40877534018328243,
      "grad_norm": 0.002206510631367564,
      "learning_rate": 0.0028814814814814814,
      "loss": 0.6057,
      "step": 184
    },
    {
      "epoch": 0.41099694529297415,
      "grad_norm": 0.002676305128261447,
      "learning_rate": 0.0028790123456790126,
      "loss": 0.6136,
      "step": 185
    },
    {
      "epoch": 0.4132185504026659,
      "grad_norm": 0.003763971384614706,
      "learning_rate": 0.0028765432098765433,
      "loss": 0.5199,
      "step": 186
    },
    {
      "epoch": 0.4154401555123577,
      "grad_norm": 0.0025718265678733587,
      "learning_rate": 0.002874074074074074,
      "loss": 0.6756,
      "step": 187
    },
    {
      "epoch": 0.4176617606220494,
      "grad_norm": 0.002096599666401744,
      "learning_rate": 0.0028716049382716048,
      "loss": 0.5455,
      "step": 188
    },
    {
      "epoch": 0.4198833657317412,
      "grad_norm": 0.0027435633819550276,
      "learning_rate": 0.002869135802469136,
      "loss": 0.7243,
      "step": 189
    },
    {
      "epoch": 0.42210497084143295,
      "grad_norm": 0.0031869688536971807,
      "learning_rate": 0.0028666666666666667,
      "loss": 0.572,
      "step": 190
    },
    {
      "epoch": 0.42432657595112466,
      "grad_norm": 0.004681820049881935,
      "learning_rate": 0.0028641975308641974,
      "loss": 0.6916,
      "step": 191
    },
    {
      "epoch": 0.42654818106081643,
      "grad_norm": 0.002824948402121663,
      "learning_rate": 0.0028617283950617286,
      "loss": 0.766,
      "step": 192
    },
    {
      "epoch": 0.4287697861705082,
      "grad_norm": 0.0033437544479966164,
      "learning_rate": 0.0028592592592592593,
      "loss": 0.6327,
      "step": 193
    },
    {
      "epoch": 0.4309913912801999,
      "grad_norm": 0.003899123053997755,
      "learning_rate": 0.00285679012345679,
      "loss": 0.4647,
      "step": 194
    },
    {
      "epoch": 0.4332129963898917,
      "grad_norm": 0.002369069494307041,
      "learning_rate": 0.0028543209876543208,
      "loss": 0.4334,
      "step": 195
    },
    {
      "epoch": 0.43543460149958346,
      "grad_norm": 0.0041612284258008,
      "learning_rate": 0.002851851851851852,
      "loss": 0.6051,
      "step": 196
    },
    {
      "epoch": 0.4376562066092752,
      "grad_norm": 0.00360001134686172,
      "learning_rate": 0.002849382716049383,
      "loss": 0.5895,
      "step": 197
    },
    {
      "epoch": 0.43987781171896695,
      "grad_norm": 0.003197331912815571,
      "learning_rate": 0.0028469135802469134,
      "loss": 0.5514,
      "step": 198
    },
    {
      "epoch": 0.4420994168286587,
      "grad_norm": 0.0020615330431610346,
      "learning_rate": 0.0028444444444444446,
      "loss": 0.5804,
      "step": 199
    },
    {
      "epoch": 0.44432102193835044,
      "grad_norm": 0.002680217381566763,
      "learning_rate": 0.0028419753086419753,
      "loss": 0.5724,
      "step": 200
    },
    {
      "epoch": 0.4465426270480422,
      "grad_norm": 0.003323337994515896,
      "learning_rate": 0.0028395061728395065,
      "loss": 0.555,
      "step": 201
    },
    {
      "epoch": 0.448764232157734,
      "grad_norm": 0.003802269697189331,
      "learning_rate": 0.002837037037037037,
      "loss": 0.5494,
      "step": 202
    },
    {
      "epoch": 0.4509858372674257,
      "grad_norm": 0.0034679423552006483,
      "learning_rate": 0.002834567901234568,
      "loss": 0.6645,
      "step": 203
    },
    {
      "epoch": 0.45320744237711746,
      "grad_norm": 0.00545097142457962,
      "learning_rate": 0.002832098765432099,
      "loss": 0.5702,
      "step": 204
    },
    {
      "epoch": 0.45542904748680924,
      "grad_norm": 0.0043219635263085365,
      "learning_rate": 0.00282962962962963,
      "loss": 0.4529,
      "step": 205
    },
    {
      "epoch": 0.45765065259650095,
      "grad_norm": 0.003569464199244976,
      "learning_rate": 0.0028271604938271606,
      "loss": 0.6052,
      "step": 206
    },
    {
      "epoch": 0.4598722577061927,
      "grad_norm": 0.0036608849186450243,
      "learning_rate": 0.0028246913580246913,
      "loss": 0.6457,
      "step": 207
    },
    {
      "epoch": 0.4620938628158845,
      "grad_norm": 0.005097015295177698,
      "learning_rate": 0.0028222222222222225,
      "loss": 0.5965,
      "step": 208
    },
    {
      "epoch": 0.4643154679255762,
      "grad_norm": 0.007548067718744278,
      "learning_rate": 0.0028197530864197532,
      "loss": 0.5616,
      "step": 209
    },
    {
      "epoch": 0.466537073035268,
      "grad_norm": 0.003794566262513399,
      "learning_rate": 0.002817283950617284,
      "loss": 0.6368,
      "step": 210
    },
    {
      "epoch": 0.46875867814495975,
      "grad_norm": 0.0054336972534656525,
      "learning_rate": 0.0028148148148148147,
      "loss": 0.6916,
      "step": 211
    },
    {
      "epoch": 0.47098028325465147,
      "grad_norm": 0.003949135076254606,
      "learning_rate": 0.002812345679012346,
      "loss": 0.7036,
      "step": 212
    },
    {
      "epoch": 0.47320188836434324,
      "grad_norm": 0.005990898702293634,
      "learning_rate": 0.0028098765432098766,
      "loss": 0.5515,
      "step": 213
    },
    {
      "epoch": 0.475423493474035,
      "grad_norm": 0.008312515914440155,
      "learning_rate": 0.0028074074074074073,
      "loss": 0.602,
      "step": 214
    },
    {
      "epoch": 0.4776450985837267,
      "grad_norm": 0.003537189681082964,
      "learning_rate": 0.0028049382716049385,
      "loss": 0.628,
      "step": 215
    },
    {
      "epoch": 0.4798667036934185,
      "grad_norm": 0.010555767454206944,
      "learning_rate": 0.0028024691358024692,
      "loss": 0.6172,
      "step": 216
    },
    {
      "epoch": 0.48208830880311027,
      "grad_norm": 0.00863946694880724,
      "learning_rate": 0.0028,
      "loss": 0.5877,
      "step": 217
    },
    {
      "epoch": 0.484309913912802,
      "grad_norm": 0.004469176754355431,
      "learning_rate": 0.0027975308641975307,
      "loss": 0.6463,
      "step": 218
    },
    {
      "epoch": 0.48653151902249375,
      "grad_norm": 0.00839470699429512,
      "learning_rate": 0.002795061728395062,
      "loss": 0.6153,
      "step": 219
    },
    {
      "epoch": 0.4887531241321855,
      "grad_norm": 0.002844468457624316,
      "learning_rate": 0.0027925925925925926,
      "loss": 0.5857,
      "step": 220
    },
    {
      "epoch": 0.49097472924187724,
      "grad_norm": 0.003875668393447995,
      "learning_rate": 0.0027901234567901233,
      "loss": 0.5902,
      "step": 221
    },
    {
      "epoch": 0.493196334351569,
      "grad_norm": 0.0032737874425947666,
      "learning_rate": 0.0027876543209876545,
      "loss": 0.6904,
      "step": 222
    },
    {
      "epoch": 0.4954179394612608,
      "grad_norm": 0.0038598868995904922,
      "learning_rate": 0.0027851851851851852,
      "loss": 0.5537,
      "step": 223
    },
    {
      "epoch": 0.4976395445709525,
      "grad_norm": 0.004370929207652807,
      "learning_rate": 0.002782716049382716,
      "loss": 0.5135,
      "step": 224
    },
    {
      "epoch": 0.49986114968064427,
      "grad_norm": 0.0038837166503071785,
      "learning_rate": 0.0027802469135802467,
      "loss": 0.722,
      "step": 225
    },
    {
      "epoch": 0.502082754790336,
      "grad_norm": 0.0027602133341133595,
      "learning_rate": 0.002777777777777778,
      "loss": 0.6496,
      "step": 226
    },
    {
      "epoch": 0.5043043599000278,
      "grad_norm": 0.003243820508942008,
      "learning_rate": 0.002775308641975309,
      "loss": 0.5887,
      "step": 227
    },
    {
      "epoch": 0.5065259650097195,
      "grad_norm": 0.0030429232865571976,
      "learning_rate": 0.0027728395061728394,
      "loss": 0.6333,
      "step": 228
    },
    {
      "epoch": 0.5087475701194113,
      "grad_norm": 0.004051642492413521,
      "learning_rate": 0.0027703703703703705,
      "loss": 0.5973,
      "step": 229
    },
    {
      "epoch": 0.510969175229103,
      "grad_norm": 0.0037287184968590736,
      "learning_rate": 0.0027679012345679013,
      "loss": 0.5813,
      "step": 230
    },
    {
      "epoch": 0.5131907803387947,
      "grad_norm": 0.006910861935466528,
      "learning_rate": 0.0027654320987654324,
      "loss": 0.7342,
      "step": 231
    },
    {
      "epoch": 0.5154123854484866,
      "grad_norm": 0.008508576080203056,
      "learning_rate": 0.0027629629629629627,
      "loss": 0.5862,
      "step": 232
    },
    {
      "epoch": 0.5176339905581783,
      "grad_norm": 0.003042088123038411,
      "learning_rate": 0.002760493827160494,
      "loss": 0.5499,
      "step": 233
    },
    {
      "epoch": 0.51985559566787,
      "grad_norm": 0.010323191992938519,
      "learning_rate": 0.0027580246913580246,
      "loss": 0.9087,
      "step": 234
    },
    {
      "epoch": 0.5220772007775618,
      "grad_norm": 0.004118815064430237,
      "learning_rate": 0.002755555555555556,
      "loss": 0.478,
      "step": 235
    },
    {
      "epoch": 0.5242988058872535,
      "grad_norm": 0.0028632564935833216,
      "learning_rate": 0.0027530864197530865,
      "loss": 0.5756,
      "step": 236
    },
    {
      "epoch": 0.5265204109969452,
      "grad_norm": 0.005326977465301752,
      "learning_rate": 0.0027506172839506173,
      "loss": 0.7118,
      "step": 237
    },
    {
      "epoch": 0.5287420161066371,
      "grad_norm": 0.004526427015662193,
      "learning_rate": 0.0027481481481481484,
      "loss": 0.7436,
      "step": 238
    },
    {
      "epoch": 0.5309636212163288,
      "grad_norm": 0.003828528104349971,
      "learning_rate": 0.002745679012345679,
      "loss": 0.7301,
      "step": 239
    },
    {
      "epoch": 0.5331852263260205,
      "grad_norm": 0.0030387018341571093,
      "learning_rate": 0.00274320987654321,
      "loss": 0.6704,
      "step": 240
    },
    {
      "epoch": 0.5354068314357123,
      "grad_norm": 0.00491207605227828,
      "learning_rate": 0.0027407407407407406,
      "loss": 0.5622,
      "step": 241
    },
    {
      "epoch": 0.537628436545404,
      "grad_norm": 0.004040584899485111,
      "learning_rate": 0.002738271604938272,
      "loss": 0.5649,
      "step": 242
    },
    {
      "epoch": 0.5398500416550958,
      "grad_norm": 0.002259825123474002,
      "learning_rate": 0.0027358024691358025,
      "loss": 0.5168,
      "step": 243
    },
    {
      "epoch": 0.5420716467647876,
      "grad_norm": 0.0036081322468817234,
      "learning_rate": 0.0027333333333333333,
      "loss": 0.5453,
      "step": 244
    },
    {
      "epoch": 0.5442932518744793,
      "grad_norm": 0.004304562695324421,
      "learning_rate": 0.0027308641975308644,
      "loss": 0.5719,
      "step": 245
    },
    {
      "epoch": 0.546514856984171,
      "grad_norm": 0.003469942370429635,
      "learning_rate": 0.002728395061728395,
      "loss": 0.6918,
      "step": 246
    },
    {
      "epoch": 0.5487364620938628,
      "grad_norm": 0.004439477808773518,
      "learning_rate": 0.002725925925925926,
      "loss": 0.6891,
      "step": 247
    },
    {
      "epoch": 0.5509580672035546,
      "grad_norm": 0.003568201558664441,
      "learning_rate": 0.0027234567901234566,
      "loss": 0.6829,
      "step": 248
    },
    {
      "epoch": 0.5531796723132463,
      "grad_norm": 0.0038554947823286057,
      "learning_rate": 0.002720987654320988,
      "loss": 0.5439,
      "step": 249
    },
    {
      "epoch": 0.5554012774229381,
      "grad_norm": 0.0034962035715579987,
      "learning_rate": 0.0027185185185185185,
      "loss": 0.3991,
      "step": 250
    },
    {
      "epoch": 0.5576228825326298,
      "grad_norm": 0.0031802747398614883,
      "learning_rate": 0.0027160493827160493,
      "loss": 0.6607,
      "step": 251
    },
    {
      "epoch": 0.5598444876423215,
      "grad_norm": 0.004424621816724539,
      "learning_rate": 0.0027135802469135805,
      "loss": 0.6938,
      "step": 252
    },
    {
      "epoch": 0.5620660927520134,
      "grad_norm": 0.0035756451543420553,
      "learning_rate": 0.002711111111111111,
      "loss": 0.643,
      "step": 253
    },
    {
      "epoch": 0.5642876978617051,
      "grad_norm": 0.004862331785261631,
      "learning_rate": 0.002708641975308642,
      "loss": 0.6575,
      "step": 254
    },
    {
      "epoch": 0.5665093029713968,
      "grad_norm": 0.0029297638684511185,
      "learning_rate": 0.0027061728395061727,
      "loss": 0.4576,
      "step": 255
    },
    {
      "epoch": 0.5687309080810886,
      "grad_norm": 0.003273774404078722,
      "learning_rate": 0.002703703703703704,
      "loss": 0.6769,
      "step": 256
    },
    {
      "epoch": 0.5709525131907803,
      "grad_norm": 0.00262522604316473,
      "learning_rate": 0.002701234567901235,
      "loss": 0.6733,
      "step": 257
    },
    {
      "epoch": 0.573174118300472,
      "grad_norm": 0.0031837797723710537,
      "learning_rate": 0.0026987654320987653,
      "loss": 0.5415,
      "step": 258
    },
    {
      "epoch": 0.5753957234101639,
      "grad_norm": 0.003672185121104121,
      "learning_rate": 0.0026962962962962965,
      "loss": 0.7819,
      "step": 259
    },
    {
      "epoch": 0.5776173285198556,
      "grad_norm": 0.004703978542238474,
      "learning_rate": 0.002693827160493827,
      "loss": 0.5284,
      "step": 260
    },
    {
      "epoch": 0.5798389336295473,
      "grad_norm": 0.006893855985254049,
      "learning_rate": 0.0026913580246913584,
      "loss": 0.6413,
      "step": 261
    },
    {
      "epoch": 0.5820605387392391,
      "grad_norm": 0.003471763338893652,
      "learning_rate": 0.0026888888888888887,
      "loss": 0.5801,
      "step": 262
    },
    {
      "epoch": 0.5842821438489308,
      "grad_norm": 0.004124249331653118,
      "learning_rate": 0.00268641975308642,
      "loss": 0.6128,
      "step": 263
    },
    {
      "epoch": 0.5865037489586226,
      "grad_norm": 0.015182813629508018,
      "learning_rate": 0.0026839506172839506,
      "loss": 0.7247,
      "step": 264
    },
    {
      "epoch": 0.5887253540683144,
      "grad_norm": 0.005122669972479343,
      "learning_rate": 0.0026814814814814817,
      "loss": 0.6428,
      "step": 265
    },
    {
      "epoch": 0.5909469591780061,
      "grad_norm": 0.003239765064790845,
      "learning_rate": 0.0026790123456790125,
      "loss": 0.661,
      "step": 266
    },
    {
      "epoch": 0.5931685642876978,
      "grad_norm": 0.003797185141593218,
      "learning_rate": 0.002676543209876543,
      "loss": 0.6597,
      "step": 267
    },
    {
      "epoch": 0.5953901693973896,
      "grad_norm": 0.007958168163895607,
      "learning_rate": 0.0026740740740740744,
      "loss": 0.6138,
      "step": 268
    },
    {
      "epoch": 0.5976117745070814,
      "grad_norm": 0.004778054542839527,
      "learning_rate": 0.0026716049382716047,
      "loss": 0.5176,
      "step": 269
    },
    {
      "epoch": 0.5998333796167731,
      "grad_norm": 0.004042231477797031,
      "learning_rate": 0.002669135802469136,
      "loss": 0.5694,
      "step": 270
    },
    {
      "epoch": 0.6020549847264649,
      "grad_norm": 0.00788301695138216,
      "learning_rate": 0.0026666666666666666,
      "loss": 0.6937,
      "step": 271
    },
    {
      "epoch": 0.6042765898361566,
      "grad_norm": 0.0031971109565347433,
      "learning_rate": 0.0026641975308641977,
      "loss": 0.5241,
      "step": 272
    },
    {
      "epoch": 0.6064981949458483,
      "grad_norm": 0.005144648719578981,
      "learning_rate": 0.0026617283950617285,
      "loss": 0.5722,
      "step": 273
    },
    {
      "epoch": 0.6087198000555402,
      "grad_norm": 0.010556294582784176,
      "learning_rate": 0.002659259259259259,
      "loss": 0.7572,
      "step": 274
    },
    {
      "epoch": 0.6109414051652319,
      "grad_norm": 0.0038042475935071707,
      "learning_rate": 0.0026567901234567904,
      "loss": 0.6584,
      "step": 275
    },
    {
      "epoch": 0.6131630102749236,
      "grad_norm": 0.005082122981548309,
      "learning_rate": 0.002654320987654321,
      "loss": 0.5855,
      "step": 276
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.00340622803196311,
      "learning_rate": 0.002651851851851852,
      "loss": 0.656,
      "step": 277
    },
    {
      "epoch": 0.6176062204943071,
      "grad_norm": 0.003464913461357355,
      "learning_rate": 0.0026493827160493826,
      "loss": 0.596,
      "step": 278
    },
    {
      "epoch": 0.6198278256039988,
      "grad_norm": 0.0036390626337379217,
      "learning_rate": 0.0026469135802469138,
      "loss": 0.6158,
      "step": 279
    },
    {
      "epoch": 0.6220494307136907,
      "grad_norm": 0.0036427758168429136,
      "learning_rate": 0.0026444444444444445,
      "loss": 0.5853,
      "step": 280
    },
    {
      "epoch": 0.6242710358233824,
      "grad_norm": 0.003733893157914281,
      "learning_rate": 0.0026419753086419752,
      "loss": 0.5347,
      "step": 281
    },
    {
      "epoch": 0.6264926409330741,
      "grad_norm": 0.003095749532803893,
      "learning_rate": 0.0026395061728395064,
      "loss": 0.5423,
      "step": 282
    },
    {
      "epoch": 0.6287142460427659,
      "grad_norm": 0.0026196488179266453,
      "learning_rate": 0.002637037037037037,
      "loss": 0.6963,
      "step": 283
    },
    {
      "epoch": 0.6309358511524576,
      "grad_norm": 0.0032207604963332415,
      "learning_rate": 0.002634567901234568,
      "loss": 0.5612,
      "step": 284
    },
    {
      "epoch": 0.6331574562621494,
      "grad_norm": 0.0033923375885933638,
      "learning_rate": 0.0026320987654320986,
      "loss": 0.5924,
      "step": 285
    },
    {
      "epoch": 0.6353790613718412,
      "grad_norm": 0.0029925594571977854,
      "learning_rate": 0.0026296296296296298,
      "loss": 0.587,
      "step": 286
    },
    {
      "epoch": 0.6376006664815329,
      "grad_norm": 0.0032753029372543097,
      "learning_rate": 0.0026271604938271605,
      "loss": 0.5584,
      "step": 287
    },
    {
      "epoch": 0.6398222715912246,
      "grad_norm": 0.00321926549077034,
      "learning_rate": 0.0026246913580246912,
      "loss": 0.6075,
      "step": 288
    },
    {
      "epoch": 0.6420438767009164,
      "grad_norm": 0.002244879025965929,
      "learning_rate": 0.0026222222222222224,
      "loss": 0.4865,
      "step": 289
    },
    {
      "epoch": 0.6442654818106082,
      "grad_norm": 0.004219688009470701,
      "learning_rate": 0.002619753086419753,
      "loss": 0.7833,
      "step": 290
    },
    {
      "epoch": 0.6464870869202999,
      "grad_norm": 0.003852980677038431,
      "learning_rate": 0.002617283950617284,
      "loss": 0.6661,
      "step": 291
    },
    {
      "epoch": 0.6487086920299917,
      "grad_norm": 0.004814931191504002,
      "learning_rate": 0.0026148148148148146,
      "loss": 0.6045,
      "step": 292
    },
    {
      "epoch": 0.6509302971396834,
      "grad_norm": 0.004808618221431971,
      "learning_rate": 0.0026123456790123458,
      "loss": 0.7521,
      "step": 293
    },
    {
      "epoch": 0.6531519022493751,
      "grad_norm": 0.004967833869159222,
      "learning_rate": 0.0026098765432098765,
      "loss": 0.61,
      "step": 294
    },
    {
      "epoch": 0.655373507359067,
      "grad_norm": 0.004623797256499529,
      "learning_rate": 0.0026074074074074072,
      "loss": 0.5688,
      "step": 295
    },
    {
      "epoch": 0.6575951124687587,
      "grad_norm": 0.003422793932259083,
      "learning_rate": 0.0026049382716049384,
      "loss": 0.5164,
      "step": 296
    },
    {
      "epoch": 0.6598167175784504,
      "grad_norm": 0.0030826223082840443,
      "learning_rate": 0.002602469135802469,
      "loss": 0.5447,
      "step": 297
    },
    {
      "epoch": 0.6620383226881422,
      "grad_norm": 0.0032569672912359238,
      "learning_rate": 0.0026000000000000003,
      "loss": 0.5581,
      "step": 298
    },
    {
      "epoch": 0.6642599277978339,
      "grad_norm": 0.0038745421916246414,
      "learning_rate": 0.0025975308641975306,
      "loss": 0.5496,
      "step": 299
    },
    {
      "epoch": 0.6664815329075257,
      "grad_norm": 0.0028549537528306246,
      "learning_rate": 0.002595061728395062,
      "loss": 0.4795,
      "step": 300
    },
    {
      "epoch": 0.6687031380172175,
      "grad_norm": 0.0034294293727725744,
      "learning_rate": 0.0025925925925925925,
      "loss": 0.6508,
      "step": 301
    },
    {
      "epoch": 0.6709247431269092,
      "grad_norm": 0.003943558316677809,
      "learning_rate": 0.0025901234567901237,
      "loss": 0.6378,
      "step": 302
    },
    {
      "epoch": 0.6731463482366009,
      "grad_norm": 0.0035818808246403933,
      "learning_rate": 0.0025876543209876544,
      "loss": 0.5815,
      "step": 303
    },
    {
      "epoch": 0.6753679533462927,
      "grad_norm": 0.005865993443876505,
      "learning_rate": 0.002585185185185185,
      "loss": 0.5702,
      "step": 304
    },
    {
      "epoch": 0.6775895584559845,
      "grad_norm": 0.0035970883909612894,
      "learning_rate": 0.0025827160493827163,
      "loss": 0.5494,
      "step": 305
    },
    {
      "epoch": 0.6798111635656762,
      "grad_norm": 0.0029156345408409834,
      "learning_rate": 0.002580246913580247,
      "loss": 0.5274,
      "step": 306
    },
    {
      "epoch": 0.682032768675368,
      "grad_norm": 0.004319177940487862,
      "learning_rate": 0.002577777777777778,
      "loss": 0.6721,
      "step": 307
    },
    {
      "epoch": 0.6842543737850597,
      "grad_norm": 0.0036983725149184465,
      "learning_rate": 0.0025753086419753085,
      "loss": 0.533,
      "step": 308
    },
    {
      "epoch": 0.6864759788947514,
      "grad_norm": 0.004536773543804884,
      "learning_rate": 0.0025728395061728397,
      "loss": 0.5563,
      "step": 309
    },
    {
      "epoch": 0.6886975840044433,
      "grad_norm": 0.003818794386461377,
      "learning_rate": 0.0025703703703703704,
      "loss": 0.5063,
      "step": 310
    },
    {
      "epoch": 0.690919189114135,
      "grad_norm": 0.002968676621094346,
      "learning_rate": 0.002567901234567901,
      "loss": 0.5734,
      "step": 311
    },
    {
      "epoch": 0.6931407942238267,
      "grad_norm": 0.0026814427692443132,
      "learning_rate": 0.0025654320987654323,
      "loss": 0.5076,
      "step": 312
    },
    {
      "epoch": 0.6953623993335185,
      "grad_norm": 0.004992303438484669,
      "learning_rate": 0.002562962962962963,
      "loss": 0.5847,
      "step": 313
    },
    {
      "epoch": 0.6975840044432102,
      "grad_norm": 0.003369976067915559,
      "learning_rate": 0.002560493827160494,
      "loss": 0.6034,
      "step": 314
    },
    {
      "epoch": 0.6998056095529019,
      "grad_norm": 0.0033550166990607977,
      "learning_rate": 0.0025580246913580245,
      "loss": 0.7165,
      "step": 315
    },
    {
      "epoch": 0.7020272146625938,
      "grad_norm": 0.0034440108574926853,
      "learning_rate": 0.0025555555555555557,
      "loss": 0.6196,
      "step": 316
    },
    {
      "epoch": 0.7042488197722855,
      "grad_norm": 0.003737369319424033,
      "learning_rate": 0.0025530864197530864,
      "loss": 0.6118,
      "step": 317
    },
    {
      "epoch": 0.7064704248819772,
      "grad_norm": 0.00249027949757874,
      "learning_rate": 0.002550617283950617,
      "loss": 0.5472,
      "step": 318
    },
    {
      "epoch": 0.708692029991669,
      "grad_norm": 0.0035954206250607967,
      "learning_rate": 0.0025481481481481483,
      "loss": 0.4992,
      "step": 319
    },
    {
      "epoch": 0.7109136351013607,
      "grad_norm": 0.01148600596934557,
      "learning_rate": 0.002545679012345679,
      "loss": 0.6443,
      "step": 320
    },
    {
      "epoch": 0.7131352402110525,
      "grad_norm": 0.003548436099663377,
      "learning_rate": 0.00254320987654321,
      "loss": 0.5335,
      "step": 321
    },
    {
      "epoch": 0.7153568453207443,
      "grad_norm": 0.0034592736046761274,
      "learning_rate": 0.0025407407407407405,
      "loss": 0.5762,
      "step": 322
    },
    {
      "epoch": 0.717578450430436,
      "grad_norm": 0.003586721373721957,
      "learning_rate": 0.0025382716049382717,
      "loss": 0.658,
      "step": 323
    },
    {
      "epoch": 0.7198000555401277,
      "grad_norm": 0.003633026732131839,
      "learning_rate": 0.0025358024691358024,
      "loss": 0.6495,
      "step": 324
    },
    {
      "epoch": 0.7220216606498195,
      "grad_norm": 0.004130194894969463,
      "learning_rate": 0.002533333333333333,
      "loss": 0.5625,
      "step": 325
    },
    {
      "epoch": 0.7242432657595113,
      "grad_norm": 0.0030712943989783525,
      "learning_rate": 0.0025308641975308644,
      "loss": 0.3768,
      "step": 326
    },
    {
      "epoch": 0.726464870869203,
      "grad_norm": 0.002559950342401862,
      "learning_rate": 0.002528395061728395,
      "loss": 0.5931,
      "step": 327
    },
    {
      "epoch": 0.7286864759788948,
      "grad_norm": 0.0032671683002263308,
      "learning_rate": 0.0025259259259259263,
      "loss": 0.5787,
      "step": 328
    },
    {
      "epoch": 0.7309080810885865,
      "grad_norm": 0.0027972394600510597,
      "learning_rate": 0.0025234567901234566,
      "loss": 0.4439,
      "step": 329
    },
    {
      "epoch": 0.7331296861982782,
      "grad_norm": 0.0030303564853966236,
      "learning_rate": 0.0025209876543209877,
      "loss": 0.5526,
      "step": 330
    },
    {
      "epoch": 0.7353512913079701,
      "grad_norm": 0.0029875573236495256,
      "learning_rate": 0.0025185185185185185,
      "loss": 0.5382,
      "step": 331
    },
    {
      "epoch": 0.7375728964176618,
      "grad_norm": 0.003598060691729188,
      "learning_rate": 0.0025160493827160496,
      "loss": 0.6131,
      "step": 332
    },
    {
      "epoch": 0.7397945015273535,
      "grad_norm": 0.0032824308145791292,
      "learning_rate": 0.0025135802469135804,
      "loss": 0.7169,
      "step": 333
    },
    {
      "epoch": 0.7420161066370453,
      "grad_norm": 0.0035338052548468113,
      "learning_rate": 0.002511111111111111,
      "loss": 0.6025,
      "step": 334
    },
    {
      "epoch": 0.744237711746737,
      "grad_norm": 0.003536518895998597,
      "learning_rate": 0.0025086419753086423,
      "loss": 0.7386,
      "step": 335
    },
    {
      "epoch": 0.7464593168564287,
      "grad_norm": 0.003579159965738654,
      "learning_rate": 0.002506172839506173,
      "loss": 0.6009,
      "step": 336
    },
    {
      "epoch": 0.7486809219661206,
      "grad_norm": 0.002911963500082493,
      "learning_rate": 0.0025037037037037037,
      "loss": 0.5362,
      "step": 337
    },
    {
      "epoch": 0.7509025270758123,
      "grad_norm": 0.004015322308987379,
      "learning_rate": 0.0025012345679012345,
      "loss": 0.7284,
      "step": 338
    },
    {
      "epoch": 0.753124132185504,
      "grad_norm": 0.0028095219749957323,
      "learning_rate": 0.0024987654320987656,
      "loss": 0.5639,
      "step": 339
    },
    {
      "epoch": 0.7553457372951958,
      "grad_norm": 0.002429201966151595,
      "learning_rate": 0.0024962962962962964,
      "loss": 0.39,
      "step": 340
    },
    {
      "epoch": 0.7575673424048875,
      "grad_norm": 0.003337994683533907,
      "learning_rate": 0.002493827160493827,
      "loss": 0.6243,
      "step": 341
    },
    {
      "epoch": 0.7597889475145793,
      "grad_norm": 0.00444022286683321,
      "learning_rate": 0.0024913580246913583,
      "loss": 0.5489,
      "step": 342
    },
    {
      "epoch": 0.7620105526242711,
      "grad_norm": 0.002425000537186861,
      "learning_rate": 0.002488888888888889,
      "loss": 0.5603,
      "step": 343
    },
    {
      "epoch": 0.7642321577339628,
      "grad_norm": 0.005820452235639095,
      "learning_rate": 0.0024864197530864197,
      "loss": 0.5786,
      "step": 344
    },
    {
      "epoch": 0.7664537628436545,
      "grad_norm": 0.002839145716279745,
      "learning_rate": 0.0024839506172839505,
      "loss": 0.5427,
      "step": 345
    },
    {
      "epoch": 0.7686753679533463,
      "grad_norm": 0.0033332209568470716,
      "learning_rate": 0.0024814814814814816,
      "loss": 0.593,
      "step": 346
    },
    {
      "epoch": 0.7708969730630381,
      "grad_norm": 0.004556423518806696,
      "learning_rate": 0.0024790123456790124,
      "loss": 0.5206,
      "step": 347
    },
    {
      "epoch": 0.7731185781727298,
      "grad_norm": 0.005054152105003595,
      "learning_rate": 0.002476543209876543,
      "loss": 0.6147,
      "step": 348
    },
    {
      "epoch": 0.7753401832824216,
      "grad_norm": 0.004854215774685144,
      "learning_rate": 0.0024740740740740743,
      "loss": 0.5485,
      "step": 349
    },
    {
      "epoch": 0.7775617883921133,
      "grad_norm": 0.0029648367781192064,
      "learning_rate": 0.002471604938271605,
      "loss": 0.5484,
      "step": 350
    },
    {
      "epoch": 0.779783393501805,
      "grad_norm": 0.003661908907815814,
      "learning_rate": 0.0024691358024691358,
      "loss": 0.5562,
      "step": 351
    },
    {
      "epoch": 0.7820049986114969,
      "grad_norm": 0.0022980873472988605,
      "learning_rate": 0.0024666666666666665,
      "loss": 0.5,
      "step": 352
    },
    {
      "epoch": 0.7842266037211886,
      "grad_norm": 0.0025679622776806355,
      "learning_rate": 0.0024641975308641977,
      "loss": 0.5795,
      "step": 353
    },
    {
      "epoch": 0.7864482088308803,
      "grad_norm": 0.0033696633763611317,
      "learning_rate": 0.0024617283950617284,
      "loss": 0.5131,
      "step": 354
    },
    {
      "epoch": 0.7886698139405721,
      "grad_norm": 0.005437337793409824,
      "learning_rate": 0.002459259259259259,
      "loss": 0.5412,
      "step": 355
    },
    {
      "epoch": 0.7908914190502638,
      "grad_norm": 0.0031412579119205475,
      "learning_rate": 0.0024567901234567903,
      "loss": 0.6161,
      "step": 356
    },
    {
      "epoch": 0.7931130241599555,
      "grad_norm": 0.0037726720329374075,
      "learning_rate": 0.002454320987654321,
      "loss": 0.4974,
      "step": 357
    },
    {
      "epoch": 0.7953346292696474,
      "grad_norm": 0.004330432042479515,
      "learning_rate": 0.002451851851851852,
      "loss": 0.5606,
      "step": 358
    },
    {
      "epoch": 0.7975562343793391,
      "grad_norm": 0.003397724824026227,
      "learning_rate": 0.0024493827160493825,
      "loss": 0.6929,
      "step": 359
    },
    {
      "epoch": 0.7997778394890308,
      "grad_norm": 0.0034366364125162363,
      "learning_rate": 0.0024469135802469137,
      "loss": 0.4951,
      "step": 360
    },
    {
      "epoch": 0.8019994445987225,
      "grad_norm": 0.006353253033012152,
      "learning_rate": 0.0024444444444444444,
      "loss": 0.6012,
      "step": 361
    },
    {
      "epoch": 0.8042210497084143,
      "grad_norm": 0.004412444308400154,
      "learning_rate": 0.0024419753086419756,
      "loss": 0.603,
      "step": 362
    },
    {
      "epoch": 0.8064426548181061,
      "grad_norm": 0.007685389835387468,
      "learning_rate": 0.0024395061728395063,
      "loss": 0.66,
      "step": 363
    },
    {
      "epoch": 0.8086642599277978,
      "grad_norm": 0.003752264427021146,
      "learning_rate": 0.002437037037037037,
      "loss": 0.5343,
      "step": 364
    },
    {
      "epoch": 0.8108858650374896,
      "grad_norm": 0.0027078662533313036,
      "learning_rate": 0.002434567901234568,
      "loss": 0.504,
      "step": 365
    },
    {
      "epoch": 0.8131074701471813,
      "grad_norm": 0.0028683270793408155,
      "learning_rate": 0.002432098765432099,
      "loss": 0.7096,
      "step": 366
    },
    {
      "epoch": 0.815329075256873,
      "grad_norm": 0.006473261397331953,
      "learning_rate": 0.0024296296296296297,
      "loss": 0.623,
      "step": 367
    },
    {
      "epoch": 0.8175506803665649,
      "grad_norm": 0.004484425764530897,
      "learning_rate": 0.0024271604938271604,
      "loss": 0.4911,
      "step": 368
    },
    {
      "epoch": 0.8197722854762566,
      "grad_norm": 0.0054881395772099495,
      "learning_rate": 0.0024246913580246916,
      "loss": 0.7035,
      "step": 369
    },
    {
      "epoch": 0.8219938905859483,
      "grad_norm": 0.00630323588848114,
      "learning_rate": 0.0024222222222222223,
      "loss": 0.6213,
      "step": 370
    },
    {
      "epoch": 0.8242154956956401,
      "grad_norm": 0.004021724686026573,
      "learning_rate": 0.002419753086419753,
      "loss": 0.4925,
      "step": 371
    },
    {
      "epoch": 0.8264371008053318,
      "grad_norm": 0.003189081558957696,
      "learning_rate": 0.002417283950617284,
      "loss": 0.6244,
      "step": 372
    },
    {
      "epoch": 0.8286587059150236,
      "grad_norm": 0.004239731002599001,
      "learning_rate": 0.002414814814814815,
      "loss": 0.5185,
      "step": 373
    },
    {
      "epoch": 0.8308803110247154,
      "grad_norm": 0.004147727508097887,
      "learning_rate": 0.0024123456790123457,
      "loss": 0.7568,
      "step": 374
    },
    {
      "epoch": 0.8331019161344071,
      "grad_norm": 0.005153963807970285,
      "learning_rate": 0.0024098765432098764,
      "loss": 0.7588,
      "step": 375
    },
    {
      "epoch": 0.8353235212440988,
      "grad_norm": 0.00458773598074913,
      "learning_rate": 0.0024074074074074076,
      "loss": 0.6562,
      "step": 376
    },
    {
      "epoch": 0.8375451263537906,
      "grad_norm": 0.0036384700797498226,
      "learning_rate": 0.0024049382716049383,
      "loss": 0.539,
      "step": 377
    },
    {
      "epoch": 0.8397667314634824,
      "grad_norm": 0.006117165554314852,
      "learning_rate": 0.002402469135802469,
      "loss": 0.874,
      "step": 378
    },
    {
      "epoch": 0.8419883365731741,
      "grad_norm": 0.003970074933022261,
      "learning_rate": 0.0024000000000000002,
      "loss": 0.6281,
      "step": 379
    },
    {
      "epoch": 0.8442099416828659,
      "grad_norm": 0.00349601567722857,
      "learning_rate": 0.002397530864197531,
      "loss": 0.4696,
      "step": 380
    },
    {
      "epoch": 0.8464315467925576,
      "grad_norm": 0.003540361998602748,
      "learning_rate": 0.0023950617283950617,
      "loss": 0.6108,
      "step": 381
    },
    {
      "epoch": 0.8486531519022493,
      "grad_norm": 0.004053393844515085,
      "learning_rate": 0.0023925925925925924,
      "loss": 0.5517,
      "step": 382
    },
    {
      "epoch": 0.8508747570119412,
      "grad_norm": 0.0032337645534425974,
      "learning_rate": 0.0023901234567901236,
      "loss": 0.5733,
      "step": 383
    },
    {
      "epoch": 0.8530963621216329,
      "grad_norm": 0.0043442887254059315,
      "learning_rate": 0.0023876543209876543,
      "loss": 0.5179,
      "step": 384
    },
    {
      "epoch": 0.8553179672313246,
      "grad_norm": 0.0042138188146054745,
      "learning_rate": 0.002385185185185185,
      "loss": 0.7154,
      "step": 385
    },
    {
      "epoch": 0.8575395723410164,
      "grad_norm": 0.005650511011481285,
      "learning_rate": 0.0023827160493827162,
      "loss": 0.5486,
      "step": 386
    },
    {
      "epoch": 0.8597611774507081,
      "grad_norm": 0.0030148783698678017,
      "learning_rate": 0.002380246913580247,
      "loss": 0.5619,
      "step": 387
    },
    {
      "epoch": 0.8619827825603998,
      "grad_norm": 0.0028637272771447897,
      "learning_rate": 0.002377777777777778,
      "loss": 0.6435,
      "step": 388
    },
    {
      "epoch": 0.8642043876700917,
      "grad_norm": 0.002455574693158269,
      "learning_rate": 0.0023753086419753084,
      "loss": 0.5355,
      "step": 389
    },
    {
      "epoch": 0.8664259927797834,
      "grad_norm": 0.003773071337491274,
      "learning_rate": 0.0023728395061728396,
      "loss": 0.6396,
      "step": 390
    },
    {
      "epoch": 0.8686475978894751,
      "grad_norm": 0.004251331090927124,
      "learning_rate": 0.0023703703703703703,
      "loss": 0.5072,
      "step": 391
    },
    {
      "epoch": 0.8708692029991669,
      "grad_norm": 0.0034750693012028933,
      "learning_rate": 0.0023679012345679015,
      "loss": 0.631,
      "step": 392
    },
    {
      "epoch": 0.8730908081088586,
      "grad_norm": 0.00786822009831667,
      "learning_rate": 0.0023654320987654322,
      "loss": 0.5248,
      "step": 393
    },
    {
      "epoch": 0.8753124132185504,
      "grad_norm": 0.003589491592720151,
      "learning_rate": 0.002362962962962963,
      "loss": 0.7626,
      "step": 394
    },
    {
      "epoch": 0.8775340183282422,
      "grad_norm": 0.0025286353193223476,
      "learning_rate": 0.002360493827160494,
      "loss": 0.5487,
      "step": 395
    },
    {
      "epoch": 0.8797556234379339,
      "grad_norm": 0.0031163638923317194,
      "learning_rate": 0.002358024691358025,
      "loss": 0.5048,
      "step": 396
    },
    {
      "epoch": 0.8819772285476256,
      "grad_norm": 0.002588153351098299,
      "learning_rate": 0.0023555555555555556,
      "loss": 0.5642,
      "step": 397
    },
    {
      "epoch": 0.8841988336573174,
      "grad_norm": 0.006615334656089544,
      "learning_rate": 0.0023530864197530863,
      "loss": 0.6398,
      "step": 398
    },
    {
      "epoch": 0.8864204387670092,
      "grad_norm": 0.00417927885428071,
      "learning_rate": 0.0023506172839506175,
      "loss": 0.5826,
      "step": 399
    },
    {
      "epoch": 0.8886420438767009,
      "grad_norm": 0.003998046740889549,
      "learning_rate": 0.002348148148148148,
      "loss": 0.5926,
      "step": 400
    },
    {
      "epoch": 0.8908636489863927,
      "grad_norm": 0.0031526628881692886,
      "learning_rate": 0.002345679012345679,
      "loss": 0.613,
      "step": 401
    },
    {
      "epoch": 0.8930852540960844,
      "grad_norm": 0.0044812653213739395,
      "learning_rate": 0.00234320987654321,
      "loss": 0.6486,
      "step": 402
    },
    {
      "epoch": 0.8953068592057761,
      "grad_norm": 0.003260153578594327,
      "learning_rate": 0.002340740740740741,
      "loss": 0.5623,
      "step": 403
    },
    {
      "epoch": 0.897528464315468,
      "grad_norm": 0.014513269066810608,
      "learning_rate": 0.0023382716049382716,
      "loss": 0.5706,
      "step": 404
    },
    {
      "epoch": 0.8997500694251597,
      "grad_norm": 0.0038354208227247,
      "learning_rate": 0.0023358024691358024,
      "loss": 0.4893,
      "step": 405
    },
    {
      "epoch": 0.9019716745348514,
      "grad_norm": 0.00491585535928607,
      "learning_rate": 0.0023333333333333335,
      "loss": 0.7385,
      "step": 406
    },
    {
      "epoch": 0.9041932796445432,
      "grad_norm": 0.0030055842362344265,
      "learning_rate": 0.0023308641975308643,
      "loss": 0.6275,
      "step": 407
    },
    {
      "epoch": 0.9064148847542349,
      "grad_norm": 0.003999483305960894,
      "learning_rate": 0.002328395061728395,
      "loss": 0.4762,
      "step": 408
    },
    {
      "epoch": 0.9086364898639266,
      "grad_norm": 0.005231029819697142,
      "learning_rate": 0.002325925925925926,
      "loss": 0.7629,
      "step": 409
    },
    {
      "epoch": 0.9108580949736185,
      "grad_norm": 0.0038291928358376026,
      "learning_rate": 0.002323456790123457,
      "loss": 0.6206,
      "step": 410
    },
    {
      "epoch": 0.9130797000833102,
      "grad_norm": 0.003498692763969302,
      "learning_rate": 0.0023209876543209876,
      "loss": 0.4684,
      "step": 411
    },
    {
      "epoch": 0.9153013051930019,
      "grad_norm": 0.006064687855541706,
      "learning_rate": 0.0023185185185185184,
      "loss": 0.6728,
      "step": 412
    },
    {
      "epoch": 0.9175229103026937,
      "grad_norm": 0.004032844211906195,
      "learning_rate": 0.0023160493827160495,
      "loss": 0.6855,
      "step": 413
    },
    {
      "epoch": 0.9197445154123854,
      "grad_norm": 0.0027241965290158987,
      "learning_rate": 0.0023135802469135803,
      "loss": 0.6335,
      "step": 414
    },
    {
      "epoch": 0.9219661205220772,
      "grad_norm": 0.005813247989863157,
      "learning_rate": 0.002311111111111111,
      "loss": 0.6042,
      "step": 415
    },
    {
      "epoch": 0.924187725631769,
      "grad_norm": 0.004378427751362324,
      "learning_rate": 0.002308641975308642,
      "loss": 0.4301,
      "step": 416
    },
    {
      "epoch": 0.9264093307414607,
      "grad_norm": 0.002686593681573868,
      "learning_rate": 0.002306172839506173,
      "loss": 0.5278,
      "step": 417
    },
    {
      "epoch": 0.9286309358511524,
      "grad_norm": 0.0038369051180779934,
      "learning_rate": 0.0023037037037037036,
      "loss": 0.5652,
      "step": 418
    },
    {
      "epoch": 0.9308525409608442,
      "grad_norm": 0.004146692343056202,
      "learning_rate": 0.0023012345679012344,
      "loss": 0.4958,
      "step": 419
    },
    {
      "epoch": 0.933074146070536,
      "grad_norm": 0.002964880084618926,
      "learning_rate": 0.0022987654320987655,
      "loss": 0.6525,
      "step": 420
    },
    {
      "epoch": 0.9352957511802277,
      "grad_norm": 0.004729856736958027,
      "learning_rate": 0.0022962962962962963,
      "loss": 0.6346,
      "step": 421
    },
    {
      "epoch": 0.9375173562899195,
      "grad_norm": 0.004113280680030584,
      "learning_rate": 0.002293827160493827,
      "loss": 0.6293,
      "step": 422
    },
    {
      "epoch": 0.9397389613996112,
      "grad_norm": 0.005205397028476,
      "learning_rate": 0.002291358024691358,
      "loss": 0.6123,
      "step": 423
    },
    {
      "epoch": 0.9419605665093029,
      "grad_norm": 0.004207682330161333,
      "learning_rate": 0.002288888888888889,
      "loss": 0.5975,
      "step": 424
    },
    {
      "epoch": 0.9441821716189948,
      "grad_norm": 0.0030375937931239605,
      "learning_rate": 0.00228641975308642,
      "loss": 0.6302,
      "step": 425
    },
    {
      "epoch": 0.9464037767286865,
      "grad_norm": 0.008805288933217525,
      "learning_rate": 0.0022839506172839504,
      "loss": 0.7296,
      "step": 426
    },
    {
      "epoch": 0.9486253818383782,
      "grad_norm": 0.0047098794020712376,
      "learning_rate": 0.0022814814814814816,
      "loss": 0.6338,
      "step": 427
    },
    {
      "epoch": 0.95084698694807,
      "grad_norm": 0.004767929203808308,
      "learning_rate": 0.0022790123456790123,
      "loss": 0.5436,
      "step": 428
    },
    {
      "epoch": 0.9530685920577617,
      "grad_norm": 0.002492051338776946,
      "learning_rate": 0.0022765432098765435,
      "loss": 0.4741,
      "step": 429
    },
    {
      "epoch": 0.9552901971674534,
      "grad_norm": 0.0027404548600316048,
      "learning_rate": 0.0022740740740740738,
      "loss": 0.5788,
      "step": 430
    },
    {
      "epoch": 0.9575118022771453,
      "grad_norm": 0.005378858186304569,
      "learning_rate": 0.002271604938271605,
      "loss": 0.6233,
      "step": 431
    },
    {
      "epoch": 0.959733407386837,
      "grad_norm": 0.002960503101348877,
      "learning_rate": 0.002269135802469136,
      "loss": 0.5805,
      "step": 432
    },
    {
      "epoch": 0.9619550124965287,
      "grad_norm": 0.003167921444401145,
      "learning_rate": 0.002266666666666667,
      "loss": 0.4924,
      "step": 433
    },
    {
      "epoch": 0.9641766176062205,
      "grad_norm": 0.004847987554967403,
      "learning_rate": 0.0022641975308641976,
      "loss": 0.5163,
      "step": 434
    },
    {
      "epoch": 0.9663982227159122,
      "grad_norm": 0.003521460574120283,
      "learning_rate": 0.0022617283950617283,
      "loss": 0.5183,
      "step": 435
    },
    {
      "epoch": 0.968619827825604,
      "grad_norm": 0.004077150020748377,
      "learning_rate": 0.0022592592592592595,
      "loss": 0.5198,
      "step": 436
    },
    {
      "epoch": 0.9708414329352958,
      "grad_norm": 0.005523703992366791,
      "learning_rate": 0.00225679012345679,
      "loss": 0.6171,
      "step": 437
    },
    {
      "epoch": 0.9730630380449875,
      "grad_norm": 0.003572586691007018,
      "learning_rate": 0.002254320987654321,
      "loss": 0.5917,
      "step": 438
    },
    {
      "epoch": 0.9752846431546792,
      "grad_norm": 0.002715351525694132,
      "learning_rate": 0.002251851851851852,
      "loss": 0.6044,
      "step": 439
    },
    {
      "epoch": 0.977506248264371,
      "grad_norm": 0.00663193641230464,
      "learning_rate": 0.002249382716049383,
      "loss": 0.5446,
      "step": 440
    },
    {
      "epoch": 0.9797278533740628,
      "grad_norm": 0.0032933761831372976,
      "learning_rate": 0.0022469135802469136,
      "loss": 0.6377,
      "step": 441
    },
    {
      "epoch": 0.9819494584837545,
      "grad_norm": 0.0030887683387845755,
      "learning_rate": 0.0022444444444444443,
      "loss": 0.6587,
      "step": 442
    },
    {
      "epoch": 0.9841710635934463,
      "grad_norm": 0.0051888274028897285,
      "learning_rate": 0.0022419753086419755,
      "loss": 0.4908,
      "step": 443
    },
    {
      "epoch": 0.986392668703138,
      "grad_norm": 0.009865401312708855,
      "learning_rate": 0.002239506172839506,
      "loss": 0.4719,
      "step": 444
    },
    {
      "epoch": 0.9886142738128297,
      "grad_norm": 0.0034925967920571566,
      "learning_rate": 0.002237037037037037,
      "loss": 0.4566,
      "step": 445
    },
    {
      "epoch": 0.9908358789225216,
      "grad_norm": 0.004528706427663565,
      "learning_rate": 0.002234567901234568,
      "loss": 0.7285,
      "step": 446
    },
    {
      "epoch": 0.9930574840322133,
      "grad_norm": 0.0038661977741867304,
      "learning_rate": 0.002232098765432099,
      "loss": 0.6834,
      "step": 447
    },
    {
      "epoch": 0.995279089141905,
      "grad_norm": 0.0036816399078816175,
      "learning_rate": 0.0022296296296296296,
      "loss": 0.6294,
      "step": 448
    },
    {
      "epoch": 0.9975006942515968,
      "grad_norm": 0.004029538482427597,
      "learning_rate": 0.0022271604938271603,
      "loss": 0.6781,
      "step": 449
    },
    {
      "epoch": 0.9997222993612885,
      "grad_norm": 0.0024761701934039593,
      "learning_rate": 0.0022246913580246915,
      "loss": 0.5744,
      "step": 450
    },
    {
      "epoch": 1.0019439044709804,
      "grad_norm": 0.0034036000724881887,
      "learning_rate": 0.0022222222222222222,
      "loss": 0.7029,
      "step": 451
    },
    {
      "epoch": 1.004165509580672,
      "grad_norm": 0.004908540286123753,
      "learning_rate": 0.002219753086419753,
      "loss": 0.5481,
      "step": 452
    },
    {
      "epoch": 1.0063871146903638,
      "grad_norm": 0.002627804409712553,
      "learning_rate": 0.002217283950617284,
      "loss": 0.5482,
      "step": 453
    },
    {
      "epoch": 1.0086087198000555,
      "grad_norm": 0.0031112139113247395,
      "learning_rate": 0.002214814814814815,
      "loss": 0.5601,
      "step": 454
    },
    {
      "epoch": 1.0108303249097472,
      "grad_norm": 0.004290361423045397,
      "learning_rate": 0.002212345679012346,
      "loss": 0.5098,
      "step": 455
    },
    {
      "epoch": 1.013051930019439,
      "grad_norm": 0.002927265129983425,
      "learning_rate": 0.0022098765432098763,
      "loss": 0.4745,
      "step": 456
    },
    {
      "epoch": 1.0152735351291309,
      "grad_norm": 0.0034060748293995857,
      "learning_rate": 0.0022074074074074075,
      "loss": 0.5653,
      "step": 457
    },
    {
      "epoch": 1.0174951402388226,
      "grad_norm": 0.0029068312142044306,
      "learning_rate": 0.0022049382716049382,
      "loss": 0.4244,
      "step": 458
    },
    {
      "epoch": 1.0197167453485143,
      "grad_norm": 0.007531351409852505,
      "learning_rate": 0.0022024691358024694,
      "loss": 0.4703,
      "step": 459
    },
    {
      "epoch": 1.021938350458206,
      "grad_norm": 0.007849762216210365,
      "learning_rate": 0.0021999999999999997,
      "loss": 0.6257,
      "step": 460
    },
    {
      "epoch": 1.0241599555678977,
      "grad_norm": 0.005377442110329866,
      "learning_rate": 0.002197530864197531,
      "loss": 0.6516,
      "step": 461
    },
    {
      "epoch": 1.0263815606775895,
      "grad_norm": 0.0037501309998333454,
      "learning_rate": 0.002195061728395062,
      "loss": 0.5766,
      "step": 462
    },
    {
      "epoch": 1.0286031657872814,
      "grad_norm": 0.0033901797141879797,
      "learning_rate": 0.0021925925925925928,
      "loss": 0.627,
      "step": 463
    },
    {
      "epoch": 1.030824770896973,
      "grad_norm": 0.0028652562759816647,
      "learning_rate": 0.0021901234567901235,
      "loss": 0.6553,
      "step": 464
    },
    {
      "epoch": 1.0330463760066648,
      "grad_norm": 0.004467955324798822,
      "learning_rate": 0.0021876543209876542,
      "loss": 0.6463,
      "step": 465
    },
    {
      "epoch": 1.0352679811163565,
      "grad_norm": 0.0031666981521993876,
      "learning_rate": 0.0021851851851851854,
      "loss": 0.4648,
      "step": 466
    },
    {
      "epoch": 1.0374895862260483,
      "grad_norm": 0.0037445444613695145,
      "learning_rate": 0.002182716049382716,
      "loss": 0.5184,
      "step": 467
    },
    {
      "epoch": 1.03971119133574,
      "grad_norm": 0.002937782322987914,
      "learning_rate": 0.002180246913580247,
      "loss": 0.4796,
      "step": 468
    },
    {
      "epoch": 1.041932796445432,
      "grad_norm": 0.0030679309275001287,
      "learning_rate": 0.002177777777777778,
      "loss": 0.6525,
      "step": 469
    },
    {
      "epoch": 1.0441544015551236,
      "grad_norm": 0.002860837848857045,
      "learning_rate": 0.0021753086419753088,
      "loss": 0.5082,
      "step": 470
    },
    {
      "epoch": 1.0463760066648153,
      "grad_norm": 0.0033034072257578373,
      "learning_rate": 0.0021728395061728395,
      "loss": 0.5688,
      "step": 471
    },
    {
      "epoch": 1.048597611774507,
      "grad_norm": 0.0039884052239358425,
      "learning_rate": 0.0021703703703703702,
      "loss": 0.7388,
      "step": 472
    },
    {
      "epoch": 1.0508192168841988,
      "grad_norm": 0.0031493529677391052,
      "learning_rate": 0.0021679012345679014,
      "loss": 0.5827,
      "step": 473
    },
    {
      "epoch": 1.0530408219938905,
      "grad_norm": 0.004402320832014084,
      "learning_rate": 0.002165432098765432,
      "loss": 0.5087,
      "step": 474
    },
    {
      "epoch": 1.0552624271035824,
      "grad_norm": 0.0027146884240210056,
      "learning_rate": 0.002162962962962963,
      "loss": 0.5162,
      "step": 475
    },
    {
      "epoch": 1.0574840322132741,
      "grad_norm": 0.0038403505459427834,
      "learning_rate": 0.002160493827160494,
      "loss": 0.6148,
      "step": 476
    },
    {
      "epoch": 1.0597056373229659,
      "grad_norm": 0.0032594793010503054,
      "learning_rate": 0.002158024691358025,
      "loss": 0.6288,
      "step": 477
    },
    {
      "epoch": 1.0619272424326576,
      "grad_norm": 0.004398996941745281,
      "learning_rate": 0.0021555555555555555,
      "loss": 0.4748,
      "step": 478
    },
    {
      "epoch": 1.0641488475423493,
      "grad_norm": 0.005373988766223192,
      "learning_rate": 0.0021530864197530863,
      "loss": 0.4286,
      "step": 479
    },
    {
      "epoch": 1.066370452652041,
      "grad_norm": 0.003866120707243681,
      "learning_rate": 0.0021506172839506174,
      "loss": 0.4143,
      "step": 480
    },
    {
      "epoch": 1.068592057761733,
      "grad_norm": 0.002855597762390971,
      "learning_rate": 0.002148148148148148,
      "loss": 0.6499,
      "step": 481
    },
    {
      "epoch": 1.0708136628714247,
      "grad_norm": 0.003230711445212364,
      "learning_rate": 0.002145679012345679,
      "loss": 0.6193,
      "step": 482
    },
    {
      "epoch": 1.0730352679811164,
      "grad_norm": 0.004454646725207567,
      "learning_rate": 0.0021432098765432096,
      "loss": 0.6738,
      "step": 483
    },
    {
      "epoch": 1.075256873090808,
      "grad_norm": 0.002642315346747637,
      "learning_rate": 0.002140740740740741,
      "loss": 0.7253,
      "step": 484
    },
    {
      "epoch": 1.0774784782004998,
      "grad_norm": 0.0033827172592282295,
      "learning_rate": 0.002138271604938272,
      "loss": 0.6711,
      "step": 485
    },
    {
      "epoch": 1.0797000833101915,
      "grad_norm": 0.00396899227052927,
      "learning_rate": 0.0021358024691358023,
      "loss": 0.6213,
      "step": 486
    },
    {
      "epoch": 1.0819216884198835,
      "grad_norm": 0.0025311079807579517,
      "learning_rate": 0.0021333333333333334,
      "loss": 0.7069,
      "step": 487
    },
    {
      "epoch": 1.0841432935295752,
      "grad_norm": 0.0029104494024068117,
      "learning_rate": 0.002130864197530864,
      "loss": 0.6153,
      "step": 488
    },
    {
      "epoch": 1.0863648986392669,
      "grad_norm": 0.0027129852678626776,
      "learning_rate": 0.0021283950617283953,
      "loss": 0.6217,
      "step": 489
    },
    {
      "epoch": 1.0885865037489586,
      "grad_norm": 0.0036984067410230637,
      "learning_rate": 0.0021259259259259256,
      "loss": 0.4849,
      "step": 490
    },
    {
      "epoch": 1.0908081088586503,
      "grad_norm": 0.002878529718145728,
      "learning_rate": 0.002123456790123457,
      "loss": 0.4421,
      "step": 491
    },
    {
      "epoch": 1.093029713968342,
      "grad_norm": 0.0032739052549004555,
      "learning_rate": 0.002120987654320988,
      "loss": 0.5601,
      "step": 492
    },
    {
      "epoch": 1.095251319078034,
      "grad_norm": 0.003050233004614711,
      "learning_rate": 0.0021185185185185187,
      "loss": 0.737,
      "step": 493
    },
    {
      "epoch": 1.0974729241877257,
      "grad_norm": 0.0031104902736842632,
      "learning_rate": 0.0021160493827160494,
      "loss": 0.5783,
      "step": 494
    },
    {
      "epoch": 1.0996945292974174,
      "grad_norm": 0.003510261420160532,
      "learning_rate": 0.00211358024691358,
      "loss": 0.6965,
      "step": 495
    },
    {
      "epoch": 1.1019161344071091,
      "grad_norm": 0.003008113009855151,
      "learning_rate": 0.0021111111111111113,
      "loss": 0.5208,
      "step": 496
    },
    {
      "epoch": 1.1041377395168008,
      "grad_norm": 0.0031856040004640818,
      "learning_rate": 0.002108641975308642,
      "loss": 0.5636,
      "step": 497
    },
    {
      "epoch": 1.1063593446264925,
      "grad_norm": 0.003651995211839676,
      "learning_rate": 0.002106172839506173,
      "loss": 0.5777,
      "step": 498
    },
    {
      "epoch": 1.1085809497361845,
      "grad_norm": 0.003181158797815442,
      "learning_rate": 0.002103703703703704,
      "loss": 0.5131,
      "step": 499
    },
    {
      "epoch": 1.1108025548458762,
      "grad_norm": 0.003947989549487829,
      "learning_rate": 0.0021012345679012347,
      "loss": 0.5752,
      "step": 500
    },
    {
      "epoch": 1.113024159955568,
      "grad_norm": 0.004313067067414522,
      "learning_rate": 0.0020987654320987655,
      "loss": 0.6217,
      "step": 501
    },
    {
      "epoch": 1.1152457650652596,
      "grad_norm": 0.003061728784814477,
      "learning_rate": 0.002096296296296296,
      "loss": 0.642,
      "step": 502
    },
    {
      "epoch": 1.1174673701749513,
      "grad_norm": 0.007577250711619854,
      "learning_rate": 0.0020938271604938274,
      "loss": 0.6191,
      "step": 503
    },
    {
      "epoch": 1.119688975284643,
      "grad_norm": 0.004099675919860601,
      "learning_rate": 0.002091358024691358,
      "loss": 0.5628,
      "step": 504
    },
    {
      "epoch": 1.121910580394335,
      "grad_norm": 0.002807199489325285,
      "learning_rate": 0.002088888888888889,
      "loss": 0.6415,
      "step": 505
    },
    {
      "epoch": 1.1241321855040267,
      "grad_norm": 0.003774695098400116,
      "learning_rate": 0.00208641975308642,
      "loss": 0.4696,
      "step": 506
    },
    {
      "epoch": 1.1263537906137184,
      "grad_norm": 0.0033181814942508936,
      "learning_rate": 0.0020839506172839507,
      "loss": 0.6567,
      "step": 507
    },
    {
      "epoch": 1.1285753957234101,
      "grad_norm": 0.003979125060141087,
      "learning_rate": 0.0020814814814814815,
      "loss": 0.5628,
      "step": 508
    },
    {
      "epoch": 1.1307970008331019,
      "grad_norm": 0.004043088760226965,
      "learning_rate": 0.002079012345679012,
      "loss": 0.5229,
      "step": 509
    },
    {
      "epoch": 1.1330186059427936,
      "grad_norm": 0.0035265632905066013,
      "learning_rate": 0.0020765432098765434,
      "loss": 0.71,
      "step": 510
    },
    {
      "epoch": 1.1352402110524855,
      "grad_norm": 0.004061999265104532,
      "learning_rate": 0.002074074074074074,
      "loss": 0.6754,
      "step": 511
    },
    {
      "epoch": 1.1374618161621772,
      "grad_norm": 0.003862738609313965,
      "learning_rate": 0.002071604938271605,
      "loss": 0.5412,
      "step": 512
    },
    {
      "epoch": 1.139683421271869,
      "grad_norm": 0.0039508771151304245,
      "learning_rate": 0.0020691358024691356,
      "loss": 0.4319,
      "step": 513
    },
    {
      "epoch": 1.1419050263815607,
      "grad_norm": 0.0041371420957148075,
      "learning_rate": 0.0020666666666666667,
      "loss": 0.7497,
      "step": 514
    },
    {
      "epoch": 1.1441266314912524,
      "grad_norm": 0.0028333235532045364,
      "learning_rate": 0.002064197530864198,
      "loss": 0.5591,
      "step": 515
    },
    {
      "epoch": 1.146348236600944,
      "grad_norm": 0.0029881077352911234,
      "learning_rate": 0.002061728395061728,
      "loss": 0.5059,
      "step": 516
    },
    {
      "epoch": 1.148569841710636,
      "grad_norm": 0.0036789770238101482,
      "learning_rate": 0.0020592592592592594,
      "loss": 0.6301,
      "step": 517
    },
    {
      "epoch": 1.1507914468203277,
      "grad_norm": 0.003822365775704384,
      "learning_rate": 0.00205679012345679,
      "loss": 0.4984,
      "step": 518
    },
    {
      "epoch": 1.1530130519300195,
      "grad_norm": 0.004626292269676924,
      "learning_rate": 0.0020543209876543213,
      "loss": 0.5772,
      "step": 519
    },
    {
      "epoch": 1.1552346570397112,
      "grad_norm": 0.006125049665570259,
      "learning_rate": 0.0020518518518518516,
      "loss": 0.5301,
      "step": 520
    },
    {
      "epoch": 1.157456262149403,
      "grad_norm": 0.004094207193702459,
      "learning_rate": 0.0020493827160493827,
      "loss": 0.7114,
      "step": 521
    },
    {
      "epoch": 1.1596778672590946,
      "grad_norm": 0.0028030688408762217,
      "learning_rate": 0.002046913580246914,
      "loss": 0.5134,
      "step": 522
    },
    {
      "epoch": 1.1618994723687863,
      "grad_norm": 0.00576319545507431,
      "learning_rate": 0.0020444444444444447,
      "loss": 0.716,
      "step": 523
    },
    {
      "epoch": 1.1641210774784783,
      "grad_norm": 0.007689573336392641,
      "learning_rate": 0.0020419753086419754,
      "loss": 0.4731,
      "step": 524
    },
    {
      "epoch": 1.16634268258817,
      "grad_norm": 0.00245383707806468,
      "learning_rate": 0.002039506172839506,
      "loss": 0.5331,
      "step": 525
    },
    {
      "epoch": 1.1685642876978617,
      "grad_norm": 0.0029423378873616457,
      "learning_rate": 0.0020370370370370373,
      "loss": 0.6516,
      "step": 526
    },
    {
      "epoch": 1.1707858928075534,
      "grad_norm": 0.003864219645038247,
      "learning_rate": 0.002034567901234568,
      "loss": 0.4495,
      "step": 527
    },
    {
      "epoch": 1.1730074979172451,
      "grad_norm": 0.0022841922473162413,
      "learning_rate": 0.0020320987654320988,
      "loss": 0.5158,
      "step": 528
    },
    {
      "epoch": 1.175229103026937,
      "grad_norm": 0.0030370629392564297,
      "learning_rate": 0.00202962962962963,
      "loss": 0.59,
      "step": 529
    },
    {
      "epoch": 1.1774507081366288,
      "grad_norm": 0.003963683266192675,
      "learning_rate": 0.0020271604938271607,
      "loss": 0.6646,
      "step": 530
    },
    {
      "epoch": 1.1796723132463205,
      "grad_norm": 0.004812866915017366,
      "learning_rate": 0.0020246913580246914,
      "loss": 0.5474,
      "step": 531
    },
    {
      "epoch": 1.1818939183560122,
      "grad_norm": 0.0024670660495758057,
      "learning_rate": 0.002022222222222222,
      "loss": 0.6036,
      "step": 532
    },
    {
      "epoch": 1.184115523465704,
      "grad_norm": 0.003874443704262376,
      "learning_rate": 0.0020197530864197533,
      "loss": 0.5898,
      "step": 533
    },
    {
      "epoch": 1.1863371285753956,
      "grad_norm": 0.0034770045895129442,
      "learning_rate": 0.002017283950617284,
      "loss": 0.5105,
      "step": 534
    },
    {
      "epoch": 1.1885587336850874,
      "grad_norm": 0.0038992036134004593,
      "learning_rate": 0.0020148148148148148,
      "loss": 0.4876,
      "step": 535
    },
    {
      "epoch": 1.1907803387947793,
      "grad_norm": 0.00521100452169776,
      "learning_rate": 0.002012345679012346,
      "loss": 0.5794,
      "step": 536
    },
    {
      "epoch": 1.193001943904471,
      "grad_norm": 0.00323618296533823,
      "learning_rate": 0.0020098765432098767,
      "loss": 0.5984,
      "step": 537
    },
    {
      "epoch": 1.1952235490141627,
      "grad_norm": 0.003101322567090392,
      "learning_rate": 0.0020074074074074074,
      "loss": 0.4959,
      "step": 538
    },
    {
      "epoch": 1.1974451541238544,
      "grad_norm": 0.0023185794707387686,
      "learning_rate": 0.002004938271604938,
      "loss": 0.5058,
      "step": 539
    },
    {
      "epoch": 1.1996667592335462,
      "grad_norm": 0.0031076017767190933,
      "learning_rate": 0.0020024691358024693,
      "loss": 0.522,
      "step": 540
    },
    {
      "epoch": 1.201888364343238,
      "grad_norm": 0.0034083579666912556,
      "learning_rate": 0.002,
      "loss": 0.5361,
      "step": 541
    },
    {
      "epoch": 1.2041099694529298,
      "grad_norm": 0.003984251990914345,
      "learning_rate": 0.0019975308641975308,
      "loss": 0.5425,
      "step": 542
    },
    {
      "epoch": 1.2063315745626215,
      "grad_norm": 0.0022866425570100546,
      "learning_rate": 0.0019950617283950615,
      "loss": 0.6073,
      "step": 543
    },
    {
      "epoch": 1.2085531796723132,
      "grad_norm": 0.00248312228359282,
      "learning_rate": 0.0019925925925925927,
      "loss": 0.6031,
      "step": 544
    },
    {
      "epoch": 1.210774784782005,
      "grad_norm": 0.0027841816190630198,
      "learning_rate": 0.001990123456790124,
      "loss": 0.5136,
      "step": 545
    },
    {
      "epoch": 1.2129963898916967,
      "grad_norm": 0.002171856816858053,
      "learning_rate": 0.001987654320987654,
      "loss": 0.6498,
      "step": 546
    },
    {
      "epoch": 1.2152179950013884,
      "grad_norm": 0.0033986468333750963,
      "learning_rate": 0.0019851851851851853,
      "loss": 0.5395,
      "step": 547
    },
    {
      "epoch": 1.2174396001110803,
      "grad_norm": 0.002358189085498452,
      "learning_rate": 0.001982716049382716,
      "loss": 0.5821,
      "step": 548
    },
    {
      "epoch": 1.219661205220772,
      "grad_norm": 0.002177860587835312,
      "learning_rate": 0.001980246913580247,
      "loss": 0.437,
      "step": 549
    },
    {
      "epoch": 1.2218828103304638,
      "grad_norm": 0.002709499327465892,
      "learning_rate": 0.0019777777777777775,
      "loss": 0.5141,
      "step": 550
    },
    {
      "epoch": 1.2241044154401555,
      "grad_norm": 0.010446878150105476,
      "learning_rate": 0.0019753086419753087,
      "loss": 0.5323,
      "step": 551
    },
    {
      "epoch": 1.2263260205498472,
      "grad_norm": 0.003707973985001445,
      "learning_rate": 0.00197283950617284,
      "loss": 0.5019,
      "step": 552
    },
    {
      "epoch": 1.2285476256595391,
      "grad_norm": 0.002721167169511318,
      "learning_rate": 0.00197037037037037,
      "loss": 0.4439,
      "step": 553
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.004831823520362377,
      "learning_rate": 0.0019679012345679013,
      "loss": 0.6292,
      "step": 554
    },
    {
      "epoch": 1.2329908358789226,
      "grad_norm": 0.002899094019085169,
      "learning_rate": 0.001965432098765432,
      "loss": 0.555,
      "step": 555
    },
    {
      "epoch": 1.2352124409886143,
      "grad_norm": 0.0027406744193285704,
      "learning_rate": 0.0019629629629629632,
      "loss": 0.6323,
      "step": 556
    },
    {
      "epoch": 1.237434046098306,
      "grad_norm": 0.003889733459800482,
      "learning_rate": 0.0019604938271604935,
      "loss": 0.6391,
      "step": 557
    },
    {
      "epoch": 1.2396556512079977,
      "grad_norm": 0.0032302718609571457,
      "learning_rate": 0.0019580246913580247,
      "loss": 0.5974,
      "step": 558
    },
    {
      "epoch": 1.2418772563176894,
      "grad_norm": 0.0037884984631091356,
      "learning_rate": 0.001955555555555556,
      "loss": 0.5524,
      "step": 559
    },
    {
      "epoch": 1.2440988614273814,
      "grad_norm": 0.003793758573010564,
      "learning_rate": 0.0019530864197530864,
      "loss": 0.7401,
      "step": 560
    },
    {
      "epoch": 1.246320466537073,
      "grad_norm": 0.00403350917622447,
      "learning_rate": 0.0019506172839506173,
      "loss": 0.834,
      "step": 561
    },
    {
      "epoch": 1.2485420716467648,
      "grad_norm": 0.0028759280685335398,
      "learning_rate": 0.001948148148148148,
      "loss": 0.5176,
      "step": 562
    },
    {
      "epoch": 1.2507636767564565,
      "grad_norm": 0.005347745958715677,
      "learning_rate": 0.001945679012345679,
      "loss": 0.5291,
      "step": 563
    },
    {
      "epoch": 1.2529852818661482,
      "grad_norm": 0.003934317734092474,
      "learning_rate": 0.0019432098765432098,
      "loss": 0.5393,
      "step": 564
    },
    {
      "epoch": 1.2552068869758402,
      "grad_norm": 0.0030212788842618465,
      "learning_rate": 0.0019407407407407407,
      "loss": 0.5089,
      "step": 565
    },
    {
      "epoch": 1.2574284920855319,
      "grad_norm": 0.0051995511166751385,
      "learning_rate": 0.0019382716049382714,
      "loss": 0.5997,
      "step": 566
    },
    {
      "epoch": 1.2596500971952236,
      "grad_norm": 0.006413669791072607,
      "learning_rate": 0.0019358024691358024,
      "loss": 0.7406,
      "step": 567
    },
    {
      "epoch": 1.2618717023049153,
      "grad_norm": 0.005932685919106007,
      "learning_rate": 0.0019333333333333336,
      "loss": 0.6754,
      "step": 568
    },
    {
      "epoch": 1.264093307414607,
      "grad_norm": 0.003121372777968645,
      "learning_rate": 0.001930864197530864,
      "loss": 0.5495,
      "step": 569
    },
    {
      "epoch": 1.2663149125242987,
      "grad_norm": 0.004301845096051693,
      "learning_rate": 0.0019283950617283952,
      "loss": 0.6118,
      "step": 570
    },
    {
      "epoch": 1.2685365176339904,
      "grad_norm": 0.0033724934328347445,
      "learning_rate": 0.0019259259259259258,
      "loss": 0.6294,
      "step": 571
    },
    {
      "epoch": 1.2707581227436824,
      "grad_norm": 0.003460286883637309,
      "learning_rate": 0.001923456790123457,
      "loss": 0.6173,
      "step": 572
    },
    {
      "epoch": 1.272979727853374,
      "grad_norm": 0.003339044051244855,
      "learning_rate": 0.0019209876543209875,
      "loss": 0.5678,
      "step": 573
    },
    {
      "epoch": 1.2752013329630658,
      "grad_norm": 0.0035982022527605295,
      "learning_rate": 0.0019185185185185186,
      "loss": 0.6607,
      "step": 574
    },
    {
      "epoch": 1.2774229380727575,
      "grad_norm": 0.0029454901814460754,
      "learning_rate": 0.0019160493827160496,
      "loss": 0.7301,
      "step": 575
    },
    {
      "epoch": 1.2796445431824492,
      "grad_norm": 0.004255762789398432,
      "learning_rate": 0.0019135802469135803,
      "loss": 0.5712,
      "step": 576
    },
    {
      "epoch": 1.2818661482921412,
      "grad_norm": 0.0058178165927529335,
      "learning_rate": 0.0019111111111111113,
      "loss": 0.4849,
      "step": 577
    },
    {
      "epoch": 1.284087753401833,
      "grad_norm": 0.004176292102783918,
      "learning_rate": 0.001908641975308642,
      "loss": 0.62,
      "step": 578
    },
    {
      "epoch": 1.2863093585115246,
      "grad_norm": 0.003570188768208027,
      "learning_rate": 0.001906172839506173,
      "loss": 0.5417,
      "step": 579
    },
    {
      "epoch": 1.2885309636212163,
      "grad_norm": 0.004796928726136684,
      "learning_rate": 0.0019037037037037037,
      "loss": 0.4944,
      "step": 580
    },
    {
      "epoch": 1.290752568730908,
      "grad_norm": 0.003928246907889843,
      "learning_rate": 0.0019012345679012346,
      "loss": 0.6144,
      "step": 581
    },
    {
      "epoch": 1.2929741738405998,
      "grad_norm": 0.002615460893139243,
      "learning_rate": 0.0018987654320987656,
      "loss": 0.5093,
      "step": 582
    },
    {
      "epoch": 1.2951957789502915,
      "grad_norm": 0.004718590993434191,
      "learning_rate": 0.0018962962962962963,
      "loss": 0.5341,
      "step": 583
    },
    {
      "epoch": 1.2974173840599834,
      "grad_norm": 0.003221541177481413,
      "learning_rate": 0.0018938271604938273,
      "loss": 0.5611,
      "step": 584
    },
    {
      "epoch": 1.2996389891696751,
      "grad_norm": 0.0025036963634192944,
      "learning_rate": 0.001891358024691358,
      "loss": 0.5498,
      "step": 585
    },
    {
      "epoch": 1.3018605942793668,
      "grad_norm": 0.0028646509163081646,
      "learning_rate": 0.001888888888888889,
      "loss": 0.8047,
      "step": 586
    },
    {
      "epoch": 1.3040821993890586,
      "grad_norm": 0.0032708642538636923,
      "learning_rate": 0.0018864197530864197,
      "loss": 0.605,
      "step": 587
    },
    {
      "epoch": 1.3063038044987503,
      "grad_norm": 0.0067271157167851925,
      "learning_rate": 0.0018839506172839506,
      "loss": 0.6305,
      "step": 588
    },
    {
      "epoch": 1.3085254096084422,
      "grad_norm": 0.004268982447683811,
      "learning_rate": 0.0018814814814814816,
      "loss": 0.5331,
      "step": 589
    },
    {
      "epoch": 1.310747014718134,
      "grad_norm": 0.0028686050791293383,
      "learning_rate": 0.0018790123456790123,
      "loss": 0.4811,
      "step": 590
    },
    {
      "epoch": 1.3129686198278256,
      "grad_norm": 0.0033989776857197285,
      "learning_rate": 0.0018765432098765433,
      "loss": 0.4762,
      "step": 591
    },
    {
      "epoch": 1.3151902249375174,
      "grad_norm": 0.0031995431054383516,
      "learning_rate": 0.001874074074074074,
      "loss": 0.653,
      "step": 592
    },
    {
      "epoch": 1.317411830047209,
      "grad_norm": 0.0027181783225387335,
      "learning_rate": 0.001871604938271605,
      "loss": 0.6121,
      "step": 593
    },
    {
      "epoch": 1.3196334351569008,
      "grad_norm": 0.006007140502333641,
      "learning_rate": 0.0018691358024691357,
      "loss": 0.5913,
      "step": 594
    },
    {
      "epoch": 1.3218550402665925,
      "grad_norm": 0.0032474491745233536,
      "learning_rate": 0.0018666666666666666,
      "loss": 0.5967,
      "step": 595
    },
    {
      "epoch": 1.3240766453762844,
      "grad_norm": 0.002645711647346616,
      "learning_rate": 0.0018641975308641974,
      "loss": 0.5887,
      "step": 596
    },
    {
      "epoch": 1.3262982504859762,
      "grad_norm": 0.0027695014141499996,
      "learning_rate": 0.0018617283950617283,
      "loss": 0.4978,
      "step": 597
    },
    {
      "epoch": 1.3285198555956679,
      "grad_norm": 0.0026522765401750803,
      "learning_rate": 0.0018592592592592595,
      "loss": 0.5477,
      "step": 598
    },
    {
      "epoch": 1.3307414607053596,
      "grad_norm": 0.004308013711124659,
      "learning_rate": 0.00185679012345679,
      "loss": 0.4383,
      "step": 599
    },
    {
      "epoch": 1.3329630658150513,
      "grad_norm": 0.004021518398076296,
      "learning_rate": 0.0018543209876543212,
      "loss": 0.6703,
      "step": 600
    },
    {
      "epoch": 1.3351846709247432,
      "grad_norm": 0.0031054369173943996,
      "learning_rate": 0.0018518518518518517,
      "loss": 0.6539,
      "step": 601
    },
    {
      "epoch": 1.337406276034435,
      "grad_norm": 0.0028947195969522,
      "learning_rate": 0.0018493827160493829,
      "loss": 0.5402,
      "step": 602
    },
    {
      "epoch": 1.3396278811441267,
      "grad_norm": 0.0026377076283097267,
      "learning_rate": 0.0018469135802469134,
      "loss": 0.4581,
      "step": 603
    },
    {
      "epoch": 1.3418494862538184,
      "grad_norm": 0.0025072831194847822,
      "learning_rate": 0.0018444444444444446,
      "loss": 0.6446,
      "step": 604
    },
    {
      "epoch": 1.34407109136351,
      "grad_norm": 0.003908316604793072,
      "learning_rate": 0.0018419753086419755,
      "loss": 0.6176,
      "step": 605
    },
    {
      "epoch": 1.3462926964732018,
      "grad_norm": 0.0033429411705583334,
      "learning_rate": 0.0018395061728395062,
      "loss": 0.5922,
      "step": 606
    },
    {
      "epoch": 1.3485143015828935,
      "grad_norm": 0.003995128441601992,
      "learning_rate": 0.0018370370370370372,
      "loss": 0.5947,
      "step": 607
    },
    {
      "epoch": 1.3507359066925855,
      "grad_norm": 0.0035881008952856064,
      "learning_rate": 0.001834567901234568,
      "loss": 0.7505,
      "step": 608
    },
    {
      "epoch": 1.3529575118022772,
      "grad_norm": 0.003577308263629675,
      "learning_rate": 0.0018320987654320989,
      "loss": 0.5918,
      "step": 609
    },
    {
      "epoch": 1.355179116911969,
      "grad_norm": 0.002450640080496669,
      "learning_rate": 0.0018296296296296296,
      "loss": 0.463,
      "step": 610
    },
    {
      "epoch": 1.3574007220216606,
      "grad_norm": 0.02011699415743351,
      "learning_rate": 0.0018271604938271606,
      "loss": 0.7372,
      "step": 611
    },
    {
      "epoch": 1.3596223271313523,
      "grad_norm": 0.0035429662093520164,
      "learning_rate": 0.0018246913580246915,
      "loss": 0.5962,
      "step": 612
    },
    {
      "epoch": 1.3618439322410443,
      "grad_norm": 0.0030228542163968086,
      "learning_rate": 0.0018222222222222223,
      "loss": 0.5768,
      "step": 613
    },
    {
      "epoch": 1.364065537350736,
      "grad_norm": 0.0030523091554641724,
      "learning_rate": 0.0018197530864197532,
      "loss": 0.5375,
      "step": 614
    },
    {
      "epoch": 1.3662871424604277,
      "grad_norm": 0.0027934941463172436,
      "learning_rate": 0.001817283950617284,
      "loss": 0.489,
      "step": 615
    },
    {
      "epoch": 1.3685087475701194,
      "grad_norm": 0.0026975416112691164,
      "learning_rate": 0.001814814814814815,
      "loss": 0.5236,
      "step": 616
    },
    {
      "epoch": 1.3707303526798111,
      "grad_norm": 0.002342597348615527,
      "learning_rate": 0.0018123456790123456,
      "loss": 0.4123,
      "step": 617
    },
    {
      "epoch": 1.3729519577895029,
      "grad_norm": 0.0042744530364871025,
      "learning_rate": 0.0018098765432098766,
      "loss": 0.5958,
      "step": 618
    },
    {
      "epoch": 1.3751735628991946,
      "grad_norm": 0.0034821974113583565,
      "learning_rate": 0.0018074074074074075,
      "loss": 0.5621,
      "step": 619
    },
    {
      "epoch": 1.3773951680088863,
      "grad_norm": 0.004259610548615456,
      "learning_rate": 0.0018049382716049383,
      "loss": 0.7341,
      "step": 620
    },
    {
      "epoch": 1.3796167731185782,
      "grad_norm": 0.004141299985349178,
      "learning_rate": 0.0018024691358024692,
      "loss": 0.7549,
      "step": 621
    },
    {
      "epoch": 1.38183837822827,
      "grad_norm": 0.002960772253572941,
      "learning_rate": 0.0018,
      "loss": 0.5797,
      "step": 622
    },
    {
      "epoch": 1.3840599833379617,
      "grad_norm": 0.003686953103169799,
      "learning_rate": 0.001797530864197531,
      "loss": 0.5873,
      "step": 623
    },
    {
      "epoch": 1.3862815884476534,
      "grad_norm": 0.002905501052737236,
      "learning_rate": 0.0017950617283950616,
      "loss": 0.527,
      "step": 624
    },
    {
      "epoch": 1.3885031935573453,
      "grad_norm": 0.003499584970995784,
      "learning_rate": 0.0017925925925925926,
      "loss": 0.5441,
      "step": 625
    },
    {
      "epoch": 1.390724798667037,
      "grad_norm": 0.005964672192931175,
      "learning_rate": 0.0017901234567901233,
      "loss": 0.5037,
      "step": 626
    },
    {
      "epoch": 1.3929464037767287,
      "grad_norm": 0.01750410534441471,
      "learning_rate": 0.0017876543209876543,
      "loss": 0.6992,
      "step": 627
    },
    {
      "epoch": 1.3951680088864205,
      "grad_norm": 0.004507698118686676,
      "learning_rate": 0.0017851851851851854,
      "loss": 0.617,
      "step": 628
    },
    {
      "epoch": 1.3973896139961122,
      "grad_norm": 0.003846382489427924,
      "learning_rate": 0.001782716049382716,
      "loss": 0.5747,
      "step": 629
    },
    {
      "epoch": 1.3996112191058039,
      "grad_norm": 0.0029720603488385677,
      "learning_rate": 0.0017802469135802471,
      "loss": 0.5242,
      "step": 630
    },
    {
      "epoch": 1.4018328242154956,
      "grad_norm": 0.0036139879375696182,
      "learning_rate": 0.0017777777777777776,
      "loss": 0.6485,
      "step": 631
    },
    {
      "epoch": 1.4040544293251873,
      "grad_norm": 0.0025792866945266724,
      "learning_rate": 0.0017753086419753088,
      "loss": 0.6277,
      "step": 632
    },
    {
      "epoch": 1.4062760344348793,
      "grad_norm": 0.0030939981807023287,
      "learning_rate": 0.0017728395061728393,
      "loss": 0.5254,
      "step": 633
    },
    {
      "epoch": 1.408497639544571,
      "grad_norm": 0.004006258212029934,
      "learning_rate": 0.0017703703703703705,
      "loss": 0.658,
      "step": 634
    },
    {
      "epoch": 1.4107192446542627,
      "grad_norm": 0.0037182308733463287,
      "learning_rate": 0.0017679012345679015,
      "loss": 0.5098,
      "step": 635
    },
    {
      "epoch": 1.4129408497639544,
      "grad_norm": 0.003229330526664853,
      "learning_rate": 0.0017654320987654322,
      "loss": 0.566,
      "step": 636
    },
    {
      "epoch": 1.4151624548736463,
      "grad_norm": 0.00321108172647655,
      "learning_rate": 0.0017629629629629631,
      "loss": 0.6975,
      "step": 637
    },
    {
      "epoch": 1.417384059983338,
      "grad_norm": 0.0027737407945096493,
      "learning_rate": 0.0017604938271604939,
      "loss": 0.6501,
      "step": 638
    },
    {
      "epoch": 1.4196056650930298,
      "grad_norm": 0.005712875630706549,
      "learning_rate": 0.0017580246913580248,
      "loss": 0.4956,
      "step": 639
    },
    {
      "epoch": 1.4218272702027215,
      "grad_norm": 0.003645273856818676,
      "learning_rate": 0.0017555555555555556,
      "loss": 0.618,
      "step": 640
    },
    {
      "epoch": 1.4240488753124132,
      "grad_norm": 0.0024144197814166546,
      "learning_rate": 0.0017530864197530865,
      "loss": 0.5955,
      "step": 641
    },
    {
      "epoch": 1.426270480422105,
      "grad_norm": 0.0037695346400141716,
      "learning_rate": 0.0017506172839506175,
      "loss": 0.5441,
      "step": 642
    },
    {
      "epoch": 1.4284920855317966,
      "grad_norm": 0.0030315883923321962,
      "learning_rate": 0.0017481481481481482,
      "loss": 0.5306,
      "step": 643
    },
    {
      "epoch": 1.4307136906414883,
      "grad_norm": 0.0035895765759050846,
      "learning_rate": 0.0017456790123456791,
      "loss": 0.4161,
      "step": 644
    },
    {
      "epoch": 1.4329352957511803,
      "grad_norm": 0.006286819465458393,
      "learning_rate": 0.0017432098765432099,
      "loss": 0.492,
      "step": 645
    },
    {
      "epoch": 1.435156900860872,
      "grad_norm": 0.0034148076083511114,
      "learning_rate": 0.0017407407407407408,
      "loss": 0.6873,
      "step": 646
    },
    {
      "epoch": 1.4373785059705637,
      "grad_norm": 0.003498445264995098,
      "learning_rate": 0.0017382716049382716,
      "loss": 0.5565,
      "step": 647
    },
    {
      "epoch": 1.4396001110802554,
      "grad_norm": 0.00425930367782712,
      "learning_rate": 0.0017358024691358025,
      "loss": 0.5092,
      "step": 648
    },
    {
      "epoch": 1.4418217161899474,
      "grad_norm": 0.0025932439602911472,
      "learning_rate": 0.0017333333333333333,
      "loss": 0.5628,
      "step": 649
    },
    {
      "epoch": 1.444043321299639,
      "grad_norm": 0.00299049005843699,
      "learning_rate": 0.0017308641975308642,
      "loss": 0.5527,
      "step": 650
    },
    {
      "epoch": 1.4462649264093308,
      "grad_norm": 0.011893363669514656,
      "learning_rate": 0.0017283950617283952,
      "loss": 0.5347,
      "step": 651
    },
    {
      "epoch": 1.4484865315190225,
      "grad_norm": 0.0036340556107461452,
      "learning_rate": 0.0017259259259259259,
      "loss": 0.6274,
      "step": 652
    },
    {
      "epoch": 1.4507081366287142,
      "grad_norm": 0.003059562761336565,
      "learning_rate": 0.0017234567901234568,
      "loss": 0.6945,
      "step": 653
    },
    {
      "epoch": 1.452929741738406,
      "grad_norm": 0.0032673149835318327,
      "learning_rate": 0.0017209876543209876,
      "loss": 0.4516,
      "step": 654
    },
    {
      "epoch": 1.4551513468480977,
      "grad_norm": 0.003782423911616206,
      "learning_rate": 0.0017185185185185185,
      "loss": 0.5895,
      "step": 655
    },
    {
      "epoch": 1.4573729519577894,
      "grad_norm": 0.002838927088305354,
      "learning_rate": 0.0017160493827160493,
      "loss": 0.5312,
      "step": 656
    },
    {
      "epoch": 1.4595945570674813,
      "grad_norm": 0.002996872877702117,
      "learning_rate": 0.0017135802469135802,
      "loss": 0.5033,
      "step": 657
    },
    {
      "epoch": 1.461816162177173,
      "grad_norm": 0.0035727221984416246,
      "learning_rate": 0.0017111111111111114,
      "loss": 0.6114,
      "step": 658
    },
    {
      "epoch": 1.4640377672868647,
      "grad_norm": 0.006776684429496527,
      "learning_rate": 0.001708641975308642,
      "loss": 0.5786,
      "step": 659
    },
    {
      "epoch": 1.4662593723965565,
      "grad_norm": 0.0027407784946262836,
      "learning_rate": 0.001706172839506173,
      "loss": 0.6871,
      "step": 660
    },
    {
      "epoch": 1.4684809775062484,
      "grad_norm": 0.003831593319773674,
      "learning_rate": 0.0017037037037037036,
      "loss": 0.6969,
      "step": 661
    },
    {
      "epoch": 1.4707025826159401,
      "grad_norm": 0.003636818379163742,
      "learning_rate": 0.0017012345679012348,
      "loss": 0.5772,
      "step": 662
    },
    {
      "epoch": 1.4729241877256318,
      "grad_norm": 0.003934764768928289,
      "learning_rate": 0.0016987654320987653,
      "loss": 0.4952,
      "step": 663
    },
    {
      "epoch": 1.4751457928353235,
      "grad_norm": 0.0033533370587974787,
      "learning_rate": 0.0016962962962962964,
      "loss": 0.5875,
      "step": 664
    },
    {
      "epoch": 1.4773673979450153,
      "grad_norm": 0.009648958221077919,
      "learning_rate": 0.0016938271604938274,
      "loss": 0.6756,
      "step": 665
    },
    {
      "epoch": 1.479589003054707,
      "grad_norm": 0.0022536625619977713,
      "learning_rate": 0.0016913580246913581,
      "loss": 0.5504,
      "step": 666
    },
    {
      "epoch": 1.4818106081643987,
      "grad_norm": 0.005803670268505812,
      "learning_rate": 0.001688888888888889,
      "loss": 0.5955,
      "step": 667
    },
    {
      "epoch": 1.4840322132740904,
      "grad_norm": 0.004117312375456095,
      "learning_rate": 0.0016864197530864198,
      "loss": 0.571,
      "step": 668
    },
    {
      "epoch": 1.4862538183837823,
      "grad_norm": 0.004236884880810976,
      "learning_rate": 0.0016839506172839508,
      "loss": 0.6874,
      "step": 669
    },
    {
      "epoch": 1.488475423493474,
      "grad_norm": 0.0037447402719408274,
      "learning_rate": 0.0016814814814814813,
      "loss": 0.5258,
      "step": 670
    },
    {
      "epoch": 1.4906970286031658,
      "grad_norm": 0.002551557030528784,
      "learning_rate": 0.0016790123456790125,
      "loss": 0.6656,
      "step": 671
    },
    {
      "epoch": 1.4929186337128575,
      "grad_norm": 0.004450269043445587,
      "learning_rate": 0.0016765432098765434,
      "loss": 0.5213,
      "step": 672
    },
    {
      "epoch": 1.4951402388225494,
      "grad_norm": 0.0031617963686585426,
      "learning_rate": 0.0016740740740740741,
      "loss": 0.6013,
      "step": 673
    },
    {
      "epoch": 1.4973618439322411,
      "grad_norm": 0.003102413844317198,
      "learning_rate": 0.001671604938271605,
      "loss": 0.625,
      "step": 674
    },
    {
      "epoch": 1.4995834490419329,
      "grad_norm": 0.0034140474162995815,
      "learning_rate": 0.0016691358024691358,
      "loss": 0.6282,
      "step": 675
    },
    {
      "epoch": 1.5018050541516246,
      "grad_norm": 0.004314281977713108,
      "learning_rate": 0.0016666666666666668,
      "loss": 0.6607,
      "step": 676
    },
    {
      "epoch": 1.5040266592613163,
      "grad_norm": 0.0032425487879663706,
      "learning_rate": 0.0016641975308641975,
      "loss": 0.591,
      "step": 677
    },
    {
      "epoch": 1.506248264371008,
      "grad_norm": 0.002422985853627324,
      "learning_rate": 0.0016617283950617285,
      "loss": 0.5654,
      "step": 678
    },
    {
      "epoch": 1.5084698694806997,
      "grad_norm": 0.0032028350979089737,
      "learning_rate": 0.0016592592592592592,
      "loss": 0.4826,
      "step": 679
    },
    {
      "epoch": 1.5106914745903914,
      "grad_norm": 0.00402708537876606,
      "learning_rate": 0.0016567901234567901,
      "loss": 0.5097,
      "step": 680
    },
    {
      "epoch": 1.5129130797000832,
      "grad_norm": 0.007427522912621498,
      "learning_rate": 0.001654320987654321,
      "loss": 0.5484,
      "step": 681
    },
    {
      "epoch": 1.515134684809775,
      "grad_norm": 0.0036908802576363087,
      "learning_rate": 0.0016518518518518518,
      "loss": 0.532,
      "step": 682
    },
    {
      "epoch": 1.5173562899194668,
      "grad_norm": 0.0036775078624486923,
      "learning_rate": 0.0016493827160493828,
      "loss": 0.6546,
      "step": 683
    },
    {
      "epoch": 1.5195778950291585,
      "grad_norm": 0.009719415567815304,
      "learning_rate": 0.0016469135802469135,
      "loss": 0.4763,
      "step": 684
    },
    {
      "epoch": 1.5217995001388505,
      "grad_norm": 0.002881912514567375,
      "learning_rate": 0.0016444444444444445,
      "loss": 0.4712,
      "step": 685
    },
    {
      "epoch": 1.5240211052485422,
      "grad_norm": 0.002484705997630954,
      "learning_rate": 0.0016419753086419752,
      "loss": 0.7636,
      "step": 686
    },
    {
      "epoch": 1.526242710358234,
      "grad_norm": 0.0027705689426511526,
      "learning_rate": 0.0016395061728395062,
      "loss": 0.6299,
      "step": 687
    },
    {
      "epoch": 1.5284643154679256,
      "grad_norm": 0.002772523323073983,
      "learning_rate": 0.001637037037037037,
      "loss": 0.7414,
      "step": 688
    },
    {
      "epoch": 1.5306859205776173,
      "grad_norm": 0.002874620957300067,
      "learning_rate": 0.0016345679012345678,
      "loss": 0.5107,
      "step": 689
    },
    {
      "epoch": 1.532907525687309,
      "grad_norm": 0.003313458990305662,
      "learning_rate": 0.0016320987654320988,
      "loss": 0.5831,
      "step": 690
    },
    {
      "epoch": 1.5351291307970008,
      "grad_norm": 0.003404456889256835,
      "learning_rate": 0.0016296296296296295,
      "loss": 0.5505,
      "step": 691
    },
    {
      "epoch": 1.5373507359066925,
      "grad_norm": 0.0034930193796753883,
      "learning_rate": 0.0016271604938271605,
      "loss": 0.5454,
      "step": 692
    },
    {
      "epoch": 1.5395723410163842,
      "grad_norm": 0.0030316906049847603,
      "learning_rate": 0.0016246913580246912,
      "loss": 0.5372,
      "step": 693
    },
    {
      "epoch": 1.5417939461260761,
      "grad_norm": 0.005995257291942835,
      "learning_rate": 0.0016222222222222222,
      "loss": 0.6709,
      "step": 694
    },
    {
      "epoch": 1.5440155512357678,
      "grad_norm": 0.003808059263974428,
      "learning_rate": 0.0016197530864197533,
      "loss": 0.5844,
      "step": 695
    },
    {
      "epoch": 1.5462371563454596,
      "grad_norm": 0.011298948898911476,
      "learning_rate": 0.0016172839506172839,
      "loss": 0.4954,
      "step": 696
    },
    {
      "epoch": 1.5484587614551515,
      "grad_norm": 0.0028677433729171753,
      "learning_rate": 0.001614814814814815,
      "loss": 0.6268,
      "step": 697
    },
    {
      "epoch": 1.5506803665648432,
      "grad_norm": 0.0030779889784753323,
      "learning_rate": 0.0016123456790123455,
      "loss": 0.6099,
      "step": 698
    },
    {
      "epoch": 1.552901971674535,
      "grad_norm": 0.00362383178435266,
      "learning_rate": 0.0016098765432098767,
      "loss": 0.3287,
      "step": 699
    },
    {
      "epoch": 1.5551235767842266,
      "grad_norm": 0.0034677220974117517,
      "learning_rate": 0.0016074074074074072,
      "loss": 0.4904,
      "step": 700
    },
    {
      "epoch": 1.5573451818939184,
      "grad_norm": 0.002137311501428485,
      "learning_rate": 0.0016049382716049384,
      "loss": 0.5541,
      "step": 701
    },
    {
      "epoch": 1.55956678700361,
      "grad_norm": 0.005134223494678736,
      "learning_rate": 0.0016024691358024693,
      "loss": 0.4853,
      "step": 702
    },
    {
      "epoch": 1.5617883921133018,
      "grad_norm": 0.003064094576984644,
      "learning_rate": 0.0016,
      "loss": 0.4526,
      "step": 703
    },
    {
      "epoch": 1.5640099972229935,
      "grad_norm": 0.005116754211485386,
      "learning_rate": 0.001597530864197531,
      "loss": 0.659,
      "step": 704
    },
    {
      "epoch": 1.5662316023326852,
      "grad_norm": 0.0022850583773106337,
      "learning_rate": 0.0015950617283950618,
      "loss": 0.6389,
      "step": 705
    },
    {
      "epoch": 1.5684532074423772,
      "grad_norm": 0.007098461501300335,
      "learning_rate": 0.0015925925925925927,
      "loss": 0.8021,
      "step": 706
    },
    {
      "epoch": 1.5706748125520689,
      "grad_norm": 0.00476048281416297,
      "learning_rate": 0.0015901234567901234,
      "loss": 0.6475,
      "step": 707
    },
    {
      "epoch": 1.5728964176617606,
      "grad_norm": 0.003650781698524952,
      "learning_rate": 0.0015876543209876544,
      "loss": 0.5739,
      "step": 708
    },
    {
      "epoch": 1.5751180227714525,
      "grad_norm": 0.007543939631432295,
      "learning_rate": 0.0015851851851851851,
      "loss": 0.5423,
      "step": 709
    },
    {
      "epoch": 1.5773396278811442,
      "grad_norm": 0.002252609934657812,
      "learning_rate": 0.001582716049382716,
      "loss": 0.5449,
      "step": 710
    },
    {
      "epoch": 1.579561232990836,
      "grad_norm": 0.003283283207565546,
      "learning_rate": 0.001580246913580247,
      "loss": 0.6492,
      "step": 711
    },
    {
      "epoch": 1.5817828381005277,
      "grad_norm": 0.005788418930023909,
      "learning_rate": 0.0015777777777777778,
      "loss": 0.5985,
      "step": 712
    },
    {
      "epoch": 1.5840044432102194,
      "grad_norm": 0.0032692374661564827,
      "learning_rate": 0.0015753086419753087,
      "loss": 0.5648,
      "step": 713
    },
    {
      "epoch": 1.586226048319911,
      "grad_norm": 0.0020325537770986557,
      "learning_rate": 0.0015728395061728395,
      "loss": 0.6423,
      "step": 714
    },
    {
      "epoch": 1.5884476534296028,
      "grad_norm": 0.004419246688485146,
      "learning_rate": 0.0015703703703703704,
      "loss": 0.5961,
      "step": 715
    },
    {
      "epoch": 1.5906692585392945,
      "grad_norm": 0.00279060285538435,
      "learning_rate": 0.0015679012345679011,
      "loss": 0.5713,
      "step": 716
    },
    {
      "epoch": 1.5928908636489862,
      "grad_norm": 0.002780338516458869,
      "learning_rate": 0.001565432098765432,
      "loss": 0.5692,
      "step": 717
    },
    {
      "epoch": 1.5951124687586782,
      "grad_norm": 0.0040886979550123215,
      "learning_rate": 0.001562962962962963,
      "loss": 0.7251,
      "step": 718
    },
    {
      "epoch": 1.59733407386837,
      "grad_norm": 0.0029384142253547907,
      "learning_rate": 0.0015604938271604938,
      "loss": 0.5374,
      "step": 719
    },
    {
      "epoch": 1.5995556789780616,
      "grad_norm": 0.004719528369605541,
      "learning_rate": 0.0015580246913580247,
      "loss": 0.6144,
      "step": 720
    },
    {
      "epoch": 1.6017772840877536,
      "grad_norm": 0.004983996041119099,
      "learning_rate": 0.0015555555555555555,
      "loss": 0.5503,
      "step": 721
    },
    {
      "epoch": 1.6039988891974453,
      "grad_norm": 0.0032239570282399654,
      "learning_rate": 0.0015530864197530864,
      "loss": 0.4954,
      "step": 722
    },
    {
      "epoch": 1.606220494307137,
      "grad_norm": 0.003059024689719081,
      "learning_rate": 0.0015506172839506172,
      "loss": 0.6519,
      "step": 723
    },
    {
      "epoch": 1.6084420994168287,
      "grad_norm": 0.003872303757816553,
      "learning_rate": 0.001548148148148148,
      "loss": 0.6012,
      "step": 724
    },
    {
      "epoch": 1.6106637045265204,
      "grad_norm": 0.002675506751984358,
      "learning_rate": 0.0015456790123456793,
      "loss": 0.5477,
      "step": 725
    },
    {
      "epoch": 1.6128853096362121,
      "grad_norm": 0.0026655576657503843,
      "learning_rate": 0.0015432098765432098,
      "loss": 0.4555,
      "step": 726
    },
    {
      "epoch": 1.6151069147459038,
      "grad_norm": 0.0024202964268624783,
      "learning_rate": 0.001540740740740741,
      "loss": 0.5497,
      "step": 727
    },
    {
      "epoch": 1.6173285198555956,
      "grad_norm": 0.0026473121251910925,
      "learning_rate": 0.0015382716049382715,
      "loss": 0.5244,
      "step": 728
    },
    {
      "epoch": 1.6195501249652873,
      "grad_norm": 0.0023546661250293255,
      "learning_rate": 0.0015358024691358026,
      "loss": 0.5198,
      "step": 729
    },
    {
      "epoch": 1.6217717300749792,
      "grad_norm": 0.005462705623358488,
      "learning_rate": 0.0015333333333333332,
      "loss": 0.6265,
      "step": 730
    },
    {
      "epoch": 1.623993335184671,
      "grad_norm": 0.0027786572463810444,
      "learning_rate": 0.0015308641975308643,
      "loss": 0.4646,
      "step": 731
    },
    {
      "epoch": 1.6262149402943626,
      "grad_norm": 0.0028380712028592825,
      "learning_rate": 0.0015283950617283948,
      "loss": 0.565,
      "step": 732
    },
    {
      "epoch": 1.6284365454040546,
      "grad_norm": 0.003053019754588604,
      "learning_rate": 0.001525925925925926,
      "loss": 0.7553,
      "step": 733
    },
    {
      "epoch": 1.6306581505137463,
      "grad_norm": 0.003874375019222498,
      "learning_rate": 0.001523456790123457,
      "loss": 0.6461,
      "step": 734
    },
    {
      "epoch": 1.632879755623438,
      "grad_norm": 0.0028247684240341187,
      "learning_rate": 0.0015209876543209877,
      "loss": 0.5023,
      "step": 735
    },
    {
      "epoch": 1.6351013607331297,
      "grad_norm": 0.002465775702148676,
      "learning_rate": 0.0015185185185185187,
      "loss": 0.5531,
      "step": 736
    },
    {
      "epoch": 1.6373229658428214,
      "grad_norm": 0.004178790375590324,
      "learning_rate": 0.0015160493827160494,
      "loss": 0.6716,
      "step": 737
    },
    {
      "epoch": 1.6395445709525132,
      "grad_norm": 0.002611462725326419,
      "learning_rate": 0.0015135802469135803,
      "loss": 0.6135,
      "step": 738
    },
    {
      "epoch": 1.6417661760622049,
      "grad_norm": 0.002397043164819479,
      "learning_rate": 0.001511111111111111,
      "loss": 0.569,
      "step": 739
    },
    {
      "epoch": 1.6439877811718966,
      "grad_norm": 0.002325512235984206,
      "learning_rate": 0.001508641975308642,
      "loss": 0.503,
      "step": 740
    },
    {
      "epoch": 1.6462093862815883,
      "grad_norm": 0.0030543282628059387,
      "learning_rate": 0.001506172839506173,
      "loss": 0.6359,
      "step": 741
    },
    {
      "epoch": 1.6484309913912802,
      "grad_norm": 0.0028390754014253616,
      "learning_rate": 0.0015037037037037037,
      "loss": 0.4931,
      "step": 742
    },
    {
      "epoch": 1.650652596500972,
      "grad_norm": 0.002786872675642371,
      "learning_rate": 0.0015012345679012347,
      "loss": 0.476,
      "step": 743
    },
    {
      "epoch": 1.6528742016106637,
      "grad_norm": 0.0036699699703603983,
      "learning_rate": 0.0014987654320987656,
      "loss": 0.6503,
      "step": 744
    },
    {
      "epoch": 1.6550958067203556,
      "grad_norm": 0.0026146643795073032,
      "learning_rate": 0.0014962962962962963,
      "loss": 0.5942,
      "step": 745
    },
    {
      "epoch": 1.6573174118300473,
      "grad_norm": 0.0027851243503391743,
      "learning_rate": 0.0014938271604938273,
      "loss": 0.4666,
      "step": 746
    },
    {
      "epoch": 1.659539016939739,
      "grad_norm": 0.0027679656632244587,
      "learning_rate": 0.001491358024691358,
      "loss": 0.4465,
      "step": 747
    },
    {
      "epoch": 1.6617606220494308,
      "grad_norm": 0.0025281680282205343,
      "learning_rate": 0.001488888888888889,
      "loss": 0.5175,
      "step": 748
    },
    {
      "epoch": 1.6639822271591225,
      "grad_norm": 0.0025729681365191936,
      "learning_rate": 0.0014864197530864197,
      "loss": 0.4341,
      "step": 749
    },
    {
      "epoch": 1.6662038322688142,
      "grad_norm": 0.0047666034661233425,
      "learning_rate": 0.0014839506172839507,
      "loss": 0.5477,
      "step": 750
    },
    {
      "epoch": 1.668425437378506,
      "grad_norm": 0.003271319903433323,
      "learning_rate": 0.0014814814814814814,
      "loss": 0.58,
      "step": 751
    },
    {
      "epoch": 1.6706470424881976,
      "grad_norm": 0.0022829915396869183,
      "learning_rate": 0.0014790123456790124,
      "loss": 0.5517,
      "step": 752
    },
    {
      "epoch": 1.6728686475978893,
      "grad_norm": 0.017747538164258003,
      "learning_rate": 0.0014765432098765433,
      "loss": 0.8429,
      "step": 753
    },
    {
      "epoch": 1.6750902527075813,
      "grad_norm": 0.001992157194763422,
      "learning_rate": 0.001474074074074074,
      "loss": 0.7384,
      "step": 754
    },
    {
      "epoch": 1.677311857817273,
      "grad_norm": 0.003742379369214177,
      "learning_rate": 0.001471604938271605,
      "loss": 0.5096,
      "step": 755
    },
    {
      "epoch": 1.6795334629269647,
      "grad_norm": 0.0029558995738625526,
      "learning_rate": 0.0014691358024691357,
      "loss": 0.5372,
      "step": 756
    },
    {
      "epoch": 1.6817550680366566,
      "grad_norm": 0.004147657193243504,
      "learning_rate": 0.0014666666666666667,
      "loss": 0.5812,
      "step": 757
    },
    {
      "epoch": 1.6839766731463484,
      "grad_norm": 0.003808134002611041,
      "learning_rate": 0.0014641975308641974,
      "loss": 0.4782,
      "step": 758
    },
    {
      "epoch": 1.68619827825604,
      "grad_norm": 0.0029203954618424177,
      "learning_rate": 0.0014617283950617286,
      "loss": 0.5484,
      "step": 759
    },
    {
      "epoch": 1.6884198833657318,
      "grad_norm": 0.00273098424077034,
      "learning_rate": 0.0014592592592592593,
      "loss": 0.6331,
      "step": 760
    },
    {
      "epoch": 1.6906414884754235,
      "grad_norm": 0.0043821679428219795,
      "learning_rate": 0.0014567901234567903,
      "loss": 0.553,
      "step": 761
    },
    {
      "epoch": 1.6928630935851152,
      "grad_norm": 0.006967128254473209,
      "learning_rate": 0.001454320987654321,
      "loss": 0.5257,
      "step": 762
    },
    {
      "epoch": 1.695084698694807,
      "grad_norm": 0.003911661449819803,
      "learning_rate": 0.001451851851851852,
      "loss": 0.5607,
      "step": 763
    },
    {
      "epoch": 1.6973063038044987,
      "grad_norm": 0.0030148366931825876,
      "learning_rate": 0.0014493827160493827,
      "loss": 0.7029,
      "step": 764
    },
    {
      "epoch": 1.6995279089141904,
      "grad_norm": 0.00347959459759295,
      "learning_rate": 0.0014469135802469136,
      "loss": 0.5572,
      "step": 765
    },
    {
      "epoch": 1.7017495140238823,
      "grad_norm": 0.002361173741519451,
      "learning_rate": 0.0014444444444444444,
      "loss": 0.6018,
      "step": 766
    },
    {
      "epoch": 1.703971119133574,
      "grad_norm": 0.0032668791245669127,
      "learning_rate": 0.0014419753086419753,
      "loss": 0.4671,
      "step": 767
    },
    {
      "epoch": 1.7061927242432657,
      "grad_norm": 0.003675680374726653,
      "learning_rate": 0.0014395061728395063,
      "loss": 0.4676,
      "step": 768
    },
    {
      "epoch": 1.7084143293529577,
      "grad_norm": 0.008208445273339748,
      "learning_rate": 0.001437037037037037,
      "loss": 0.6771,
      "step": 769
    },
    {
      "epoch": 1.7106359344626494,
      "grad_norm": 0.0033595936838537455,
      "learning_rate": 0.001434567901234568,
      "loss": 0.5334,
      "step": 770
    },
    {
      "epoch": 1.712857539572341,
      "grad_norm": 0.006078768987208605,
      "learning_rate": 0.0014320987654320987,
      "loss": 0.4963,
      "step": 771
    },
    {
      "epoch": 1.7150791446820328,
      "grad_norm": 0.003778295125812292,
      "learning_rate": 0.0014296296296296297,
      "loss": 0.6502,
      "step": 772
    },
    {
      "epoch": 1.7173007497917245,
      "grad_norm": 0.0029222946614027023,
      "learning_rate": 0.0014271604938271604,
      "loss": 0.566,
      "step": 773
    },
    {
      "epoch": 1.7195223549014163,
      "grad_norm": 0.0029675152618438005,
      "learning_rate": 0.0014246913580246916,
      "loss": 0.5897,
      "step": 774
    },
    {
      "epoch": 1.721743960011108,
      "grad_norm": 0.004698608536273241,
      "learning_rate": 0.0014222222222222223,
      "loss": 0.5154,
      "step": 775
    },
    {
      "epoch": 1.7239655651207997,
      "grad_norm": 0.0036145735066384077,
      "learning_rate": 0.0014197530864197532,
      "loss": 0.4653,
      "step": 776
    },
    {
      "epoch": 1.7261871702304914,
      "grad_norm": 0.004345126915723085,
      "learning_rate": 0.001417283950617284,
      "loss": 0.5234,
      "step": 777
    },
    {
      "epoch": 1.7284087753401833,
      "grad_norm": 0.003433341858908534,
      "learning_rate": 0.001414814814814815,
      "loss": 0.5059,
      "step": 778
    },
    {
      "epoch": 1.730630380449875,
      "grad_norm": 0.0028149851132184267,
      "learning_rate": 0.0014123456790123457,
      "loss": 0.4714,
      "step": 779
    },
    {
      "epoch": 1.7328519855595668,
      "grad_norm": 0.0035309260711073875,
      "learning_rate": 0.0014098765432098766,
      "loss": 0.564,
      "step": 780
    },
    {
      "epoch": 1.7350735906692587,
      "grad_norm": 0.0024095147382467985,
      "learning_rate": 0.0014074074074074073,
      "loss": 0.5296,
      "step": 781
    },
    {
      "epoch": 1.7372951957789504,
      "grad_norm": 0.0036908118054270744,
      "learning_rate": 0.0014049382716049383,
      "loss": 0.6492,
      "step": 782
    },
    {
      "epoch": 1.7395168008886421,
      "grad_norm": 0.003246041014790535,
      "learning_rate": 0.0014024691358024693,
      "loss": 0.5894,
      "step": 783
    },
    {
      "epoch": 1.7417384059983338,
      "grad_norm": 0.00329392752610147,
      "learning_rate": 0.0014,
      "loss": 0.4149,
      "step": 784
    },
    {
      "epoch": 1.7439600111080256,
      "grad_norm": 0.0035899202339351177,
      "learning_rate": 0.001397530864197531,
      "loss": 0.5695,
      "step": 785
    },
    {
      "epoch": 1.7461816162177173,
      "grad_norm": 0.0034819571301341057,
      "learning_rate": 0.0013950617283950617,
      "loss": 0.5442,
      "step": 786
    },
    {
      "epoch": 1.748403221327409,
      "grad_norm": 0.004988197702914476,
      "learning_rate": 0.0013925925925925926,
      "loss": 0.5689,
      "step": 787
    },
    {
      "epoch": 1.7506248264371007,
      "grad_norm": 0.0034855392295867205,
      "learning_rate": 0.0013901234567901234,
      "loss": 0.6102,
      "step": 788
    },
    {
      "epoch": 1.7528464315467924,
      "grad_norm": 0.0026496578939259052,
      "learning_rate": 0.0013876543209876545,
      "loss": 0.6409,
      "step": 789
    },
    {
      "epoch": 1.7550680366564844,
      "grad_norm": 0.0031368425115942955,
      "learning_rate": 0.0013851851851851853,
      "loss": 0.6088,
      "step": 790
    },
    {
      "epoch": 1.757289641766176,
      "grad_norm": 0.004890915006399155,
      "learning_rate": 0.0013827160493827162,
      "loss": 0.7336,
      "step": 791
    },
    {
      "epoch": 1.7595112468758678,
      "grad_norm": 0.0027104285545647144,
      "learning_rate": 0.001380246913580247,
      "loss": 0.6273,
      "step": 792
    },
    {
      "epoch": 1.7617328519855595,
      "grad_norm": 0.0035991212353110313,
      "learning_rate": 0.001377777777777778,
      "loss": 0.6898,
      "step": 793
    },
    {
      "epoch": 1.7639544570952514,
      "grad_norm": 0.0032256029080599546,
      "learning_rate": 0.0013753086419753086,
      "loss": 0.6599,
      "step": 794
    },
    {
      "epoch": 1.7661760622049432,
      "grad_norm": 0.003426952753216028,
      "learning_rate": 0.0013728395061728396,
      "loss": 0.7319,
      "step": 795
    },
    {
      "epoch": 1.7683976673146349,
      "grad_norm": 0.002788130659610033,
      "learning_rate": 0.0013703703703703703,
      "loss": 0.483,
      "step": 796
    },
    {
      "epoch": 1.7706192724243266,
      "grad_norm": 0.011121896095573902,
      "learning_rate": 0.0013679012345679013,
      "loss": 0.512,
      "step": 797
    },
    {
      "epoch": 1.7728408775340183,
      "grad_norm": 0.0021587309893220663,
      "learning_rate": 0.0013654320987654322,
      "loss": 0.641,
      "step": 798
    },
    {
      "epoch": 1.77506248264371,
      "grad_norm": 0.002482533687725663,
      "learning_rate": 0.001362962962962963,
      "loss": 0.5022,
      "step": 799
    },
    {
      "epoch": 1.7772840877534017,
      "grad_norm": 0.0024441415444016457,
      "learning_rate": 0.001360493827160494,
      "loss": 0.6722,
      "step": 800
    },
    {
      "epoch": 1.7795056928630935,
      "grad_norm": 0.0027782402466982603,
      "learning_rate": 0.0013580246913580246,
      "loss": 0.582,
      "step": 801
    },
    {
      "epoch": 1.7817272979727852,
      "grad_norm": 0.0028855646960437298,
      "learning_rate": 0.0013555555555555556,
      "loss": 0.4304,
      "step": 802
    },
    {
      "epoch": 1.783948903082477,
      "grad_norm": 0.006873362231999636,
      "learning_rate": 0.0013530864197530863,
      "loss": 0.7037,
      "step": 803
    },
    {
      "epoch": 1.7861705081921688,
      "grad_norm": 0.0031411319505423307,
      "learning_rate": 0.0013506172839506175,
      "loss": 0.7455,
      "step": 804
    },
    {
      "epoch": 1.7883921133018605,
      "grad_norm": 0.005225402768701315,
      "learning_rate": 0.0013481481481481482,
      "loss": 0.4395,
      "step": 805
    },
    {
      "epoch": 1.7906137184115525,
      "grad_norm": 0.0035771653056144714,
      "learning_rate": 0.0013456790123456792,
      "loss": 0.7324,
      "step": 806
    },
    {
      "epoch": 1.7928353235212442,
      "grad_norm": 0.0027949302457273006,
      "learning_rate": 0.00134320987654321,
      "loss": 0.831,
      "step": 807
    },
    {
      "epoch": 1.795056928630936,
      "grad_norm": 0.0043035815469920635,
      "learning_rate": 0.0013407407407407409,
      "loss": 0.7116,
      "step": 808
    },
    {
      "epoch": 1.7972785337406276,
      "grad_norm": 0.0025215493515133858,
      "learning_rate": 0.0013382716049382716,
      "loss": 0.6202,
      "step": 809
    },
    {
      "epoch": 1.7995001388503193,
      "grad_norm": 0.003835323266685009,
      "learning_rate": 0.0013358024691358023,
      "loss": 0.8188,
      "step": 810
    },
    {
      "epoch": 1.801721743960011,
      "grad_norm": 0.002193405758589506,
      "learning_rate": 0.0013333333333333333,
      "loss": 0.5497,
      "step": 811
    },
    {
      "epoch": 1.8039433490697028,
      "grad_norm": 0.003946555312722921,
      "learning_rate": 0.0013308641975308642,
      "loss": 0.6345,
      "step": 812
    },
    {
      "epoch": 1.8061649541793945,
      "grad_norm": 0.0034872544929385185,
      "learning_rate": 0.0013283950617283952,
      "loss": 0.615,
      "step": 813
    },
    {
      "epoch": 1.8083865592890862,
      "grad_norm": 0.0031431701499968767,
      "learning_rate": 0.001325925925925926,
      "loss": 0.5983,
      "step": 814
    },
    {
      "epoch": 1.8106081643987781,
      "grad_norm": 0.0040554506704211235,
      "learning_rate": 0.0013234567901234569,
      "loss": 0.4915,
      "step": 815
    },
    {
      "epoch": 1.8128297695084699,
      "grad_norm": 0.003248132998123765,
      "learning_rate": 0.0013209876543209876,
      "loss": 0.5397,
      "step": 816
    },
    {
      "epoch": 1.8150513746181616,
      "grad_norm": 0.0054314411245286465,
      "learning_rate": 0.0013185185185185186,
      "loss": 0.6909,
      "step": 817
    },
    {
      "epoch": 1.8172729797278535,
      "grad_norm": 0.0028211737517267466,
      "learning_rate": 0.0013160493827160493,
      "loss": 0.4895,
      "step": 818
    },
    {
      "epoch": 1.8194945848375452,
      "grad_norm": 0.004534921608865261,
      "learning_rate": 0.0013135802469135802,
      "loss": 0.5644,
      "step": 819
    },
    {
      "epoch": 1.821716189947237,
      "grad_norm": 0.0021549463272094727,
      "learning_rate": 0.0013111111111111112,
      "loss": 0.5457,
      "step": 820
    },
    {
      "epoch": 1.8239377950569287,
      "grad_norm": 0.002857828978449106,
      "learning_rate": 0.001308641975308642,
      "loss": 0.5026,
      "step": 821
    },
    {
      "epoch": 1.8261594001666204,
      "grad_norm": 0.00304958107881248,
      "learning_rate": 0.0013061728395061729,
      "loss": 0.5401,
      "step": 822
    },
    {
      "epoch": 1.828381005276312,
      "grad_norm": 0.0022149235010147095,
      "learning_rate": 0.0013037037037037036,
      "loss": 0.5181,
      "step": 823
    },
    {
      "epoch": 1.8306026103860038,
      "grad_norm": 0.004668918903917074,
      "learning_rate": 0.0013012345679012346,
      "loss": 0.751,
      "step": 824
    },
    {
      "epoch": 1.8328242154956955,
      "grad_norm": 0.004631809890270233,
      "learning_rate": 0.0012987654320987653,
      "loss": 0.4988,
      "step": 825
    },
    {
      "epoch": 1.8350458206053872,
      "grad_norm": 0.0024211418349295855,
      "learning_rate": 0.0012962962962962963,
      "loss": 0.6242,
      "step": 826
    },
    {
      "epoch": 1.8372674257150792,
      "grad_norm": 0.00401139073073864,
      "learning_rate": 0.0012938271604938272,
      "loss": 0.7337,
      "step": 827
    },
    {
      "epoch": 1.8394890308247709,
      "grad_norm": 0.004702482372522354,
      "learning_rate": 0.0012913580246913582,
      "loss": 0.4629,
      "step": 828
    },
    {
      "epoch": 1.8417106359344626,
      "grad_norm": 0.004868146497756243,
      "learning_rate": 0.001288888888888889,
      "loss": 0.4775,
      "step": 829
    },
    {
      "epoch": 1.8439322410441545,
      "grad_norm": 0.0038116569630801678,
      "learning_rate": 0.0012864197530864198,
      "loss": 0.4549,
      "step": 830
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.00293547916226089,
      "learning_rate": 0.0012839506172839506,
      "loss": 0.5516,
      "step": 831
    },
    {
      "epoch": 1.848375451263538,
      "grad_norm": 0.004145658574998379,
      "learning_rate": 0.0012814814814814815,
      "loss": 0.5789,
      "step": 832
    },
    {
      "epoch": 1.8505970563732297,
      "grad_norm": 0.004254059866070747,
      "learning_rate": 0.0012790123456790123,
      "loss": 0.4993,
      "step": 833
    },
    {
      "epoch": 1.8528186614829214,
      "grad_norm": 0.002749624429270625,
      "learning_rate": 0.0012765432098765432,
      "loss": 0.6233,
      "step": 834
    },
    {
      "epoch": 1.8550402665926131,
      "grad_norm": 0.0027774199843406677,
      "learning_rate": 0.0012740740740740742,
      "loss": 0.5444,
      "step": 835
    },
    {
      "epoch": 1.8572618717023048,
      "grad_norm": 0.003853573463857174,
      "learning_rate": 0.001271604938271605,
      "loss": 0.6018,
      "step": 836
    },
    {
      "epoch": 1.8594834768119965,
      "grad_norm": 0.0038579183164983988,
      "learning_rate": 0.0012691358024691359,
      "loss": 0.5005,
      "step": 837
    },
    {
      "epoch": 1.8617050819216883,
      "grad_norm": 0.0033002146519720554,
      "learning_rate": 0.0012666666666666666,
      "loss": 0.5519,
      "step": 838
    },
    {
      "epoch": 1.8639266870313802,
      "grad_norm": 0.002311147516593337,
      "learning_rate": 0.0012641975308641975,
      "loss": 0.5059,
      "step": 839
    },
    {
      "epoch": 1.866148292141072,
      "grad_norm": 0.003047521458938718,
      "learning_rate": 0.0012617283950617283,
      "loss": 0.4934,
      "step": 840
    },
    {
      "epoch": 1.8683698972507636,
      "grad_norm": 0.0018599721370264888,
      "learning_rate": 0.0012592592592592592,
      "loss": 0.5947,
      "step": 841
    },
    {
      "epoch": 1.8705915023604556,
      "grad_norm": 0.00537974014878273,
      "learning_rate": 0.0012567901234567902,
      "loss": 0.5727,
      "step": 842
    },
    {
      "epoch": 1.8728131074701473,
      "grad_norm": 0.002149309730157256,
      "learning_rate": 0.0012543209876543211,
      "loss": 0.4621,
      "step": 843
    },
    {
      "epoch": 1.875034712579839,
      "grad_norm": 0.004313463345170021,
      "learning_rate": 0.0012518518518518519,
      "loss": 0.5645,
      "step": 844
    },
    {
      "epoch": 1.8772563176895307,
      "grad_norm": 0.0028063429053872824,
      "learning_rate": 0.0012493827160493828,
      "loss": 0.604,
      "step": 845
    },
    {
      "epoch": 1.8794779227992224,
      "grad_norm": 0.0033968379721045494,
      "learning_rate": 0.0012469135802469136,
      "loss": 0.5508,
      "step": 846
    },
    {
      "epoch": 1.8816995279089141,
      "grad_norm": 0.003952283877879381,
      "learning_rate": 0.0012444444444444445,
      "loss": 0.6968,
      "step": 847
    },
    {
      "epoch": 1.8839211330186059,
      "grad_norm": 0.0025829654186964035,
      "learning_rate": 0.0012419753086419752,
      "loss": 0.5558,
      "step": 848
    },
    {
      "epoch": 1.8861427381282976,
      "grad_norm": 0.005058688577264547,
      "learning_rate": 0.0012395061728395062,
      "loss": 0.626,
      "step": 849
    },
    {
      "epoch": 1.8883643432379893,
      "grad_norm": 0.0024038597475737333,
      "learning_rate": 0.0012370370370370371,
      "loss": 0.4763,
      "step": 850
    },
    {
      "epoch": 1.8905859483476812,
      "grad_norm": 0.003360903589054942,
      "learning_rate": 0.0012345679012345679,
      "loss": 0.7703,
      "step": 851
    },
    {
      "epoch": 1.892807553457373,
      "grad_norm": 0.0023337923921644688,
      "learning_rate": 0.0012320987654320988,
      "loss": 0.4288,
      "step": 852
    },
    {
      "epoch": 1.8950291585670647,
      "grad_norm": 0.0043142749927937984,
      "learning_rate": 0.0012296296296296296,
      "loss": 0.5582,
      "step": 853
    },
    {
      "epoch": 1.8972507636767566,
      "grad_norm": 0.0049232495948672295,
      "learning_rate": 0.0012271604938271605,
      "loss": 0.6853,
      "step": 854
    },
    {
      "epoch": 1.8994723687864483,
      "grad_norm": 0.003679855726659298,
      "learning_rate": 0.0012246913580246912,
      "loss": 0.5373,
      "step": 855
    },
    {
      "epoch": 1.90169397389614,
      "grad_norm": 0.0029625846073031425,
      "learning_rate": 0.0012222222222222222,
      "loss": 0.5378,
      "step": 856
    },
    {
      "epoch": 1.9039155790058317,
      "grad_norm": 0.004192112945020199,
      "learning_rate": 0.0012197530864197532,
      "loss": 0.7442,
      "step": 857
    },
    {
      "epoch": 1.9061371841155235,
      "grad_norm": 0.003077823668718338,
      "learning_rate": 0.001217283950617284,
      "loss": 0.5761,
      "step": 858
    },
    {
      "epoch": 1.9083587892252152,
      "grad_norm": 0.0023701803293079138,
      "learning_rate": 0.0012148148148148148,
      "loss": 0.4808,
      "step": 859
    },
    {
      "epoch": 1.910580394334907,
      "grad_norm": 0.004746532067656517,
      "learning_rate": 0.0012123456790123458,
      "loss": 0.5794,
      "step": 860
    },
    {
      "epoch": 1.9128019994445986,
      "grad_norm": 0.003315276000648737,
      "learning_rate": 0.0012098765432098765,
      "loss": 0.5283,
      "step": 861
    },
    {
      "epoch": 1.9150236045542903,
      "grad_norm": 0.0036441627889871597,
      "learning_rate": 0.0012074074074074075,
      "loss": 0.4374,
      "step": 862
    },
    {
      "epoch": 1.9172452096639823,
      "grad_norm": 0.003225019434466958,
      "learning_rate": 0.0012049382716049382,
      "loss": 0.5463,
      "step": 863
    },
    {
      "epoch": 1.919466814773674,
      "grad_norm": 0.003116652835160494,
      "learning_rate": 0.0012024691358024692,
      "loss": 0.5431,
      "step": 864
    },
    {
      "epoch": 1.9216884198833657,
      "grad_norm": 0.0038938429206609726,
      "learning_rate": 0.0012000000000000001,
      "loss": 0.5612,
      "step": 865
    },
    {
      "epoch": 1.9239100249930576,
      "grad_norm": 0.004084984306246042,
      "learning_rate": 0.0011975308641975308,
      "loss": 0.6515,
      "step": 866
    },
    {
      "epoch": 1.9261316301027493,
      "grad_norm": 0.0033745935652405024,
      "learning_rate": 0.0011950617283950618,
      "loss": 0.8171,
      "step": 867
    },
    {
      "epoch": 1.928353235212441,
      "grad_norm": 0.004159669391810894,
      "learning_rate": 0.0011925925925925925,
      "loss": 0.6611,
      "step": 868
    },
    {
      "epoch": 1.9305748403221328,
      "grad_norm": 0.002937123877927661,
      "learning_rate": 0.0011901234567901235,
      "loss": 0.9107,
      "step": 869
    },
    {
      "epoch": 1.9327964454318245,
      "grad_norm": 0.005026680883020163,
      "learning_rate": 0.0011876543209876542,
      "loss": 0.5438,
      "step": 870
    },
    {
      "epoch": 1.9350180505415162,
      "grad_norm": 0.003714249935001135,
      "learning_rate": 0.0011851851851851852,
      "loss": 0.5313,
      "step": 871
    },
    {
      "epoch": 1.937239655651208,
      "grad_norm": 0.0030297571793198586,
      "learning_rate": 0.0011827160493827161,
      "loss": 0.5847,
      "step": 872
    },
    {
      "epoch": 1.9394612607608996,
      "grad_norm": 0.003413270227611065,
      "learning_rate": 0.001180246913580247,
      "loss": 0.4856,
      "step": 873
    },
    {
      "epoch": 1.9416828658705914,
      "grad_norm": 0.0021302655804902315,
      "learning_rate": 0.0011777777777777778,
      "loss": 0.3875,
      "step": 874
    },
    {
      "epoch": 1.9439044709802833,
      "grad_norm": 0.004350871313363314,
      "learning_rate": 0.0011753086419753088,
      "loss": 0.736,
      "step": 875
    },
    {
      "epoch": 1.946126076089975,
      "grad_norm": 0.004902921617031097,
      "learning_rate": 0.0011728395061728395,
      "loss": 0.8231,
      "step": 876
    },
    {
      "epoch": 1.9483476811996667,
      "grad_norm": 0.007053270936012268,
      "learning_rate": 0.0011703703703703704,
      "loss": 0.5124,
      "step": 877
    },
    {
      "epoch": 1.9505692863093587,
      "grad_norm": 0.010358642786741257,
      "learning_rate": 0.0011679012345679012,
      "loss": 0.4956,
      "step": 878
    },
    {
      "epoch": 1.9527908914190504,
      "grad_norm": 0.003492894349619746,
      "learning_rate": 0.0011654320987654321,
      "loss": 0.5751,
      "step": 879
    },
    {
      "epoch": 1.955012496528742,
      "grad_norm": 0.004429376684129238,
      "learning_rate": 0.001162962962962963,
      "loss": 0.6184,
      "step": 880
    },
    {
      "epoch": 1.9572341016384338,
      "grad_norm": 0.003521913895383477,
      "learning_rate": 0.0011604938271604938,
      "loss": 0.723,
      "step": 881
    },
    {
      "epoch": 1.9594557067481255,
      "grad_norm": 0.002686472609639168,
      "learning_rate": 0.0011580246913580248,
      "loss": 0.6462,
      "step": 882
    },
    {
      "epoch": 1.9616773118578172,
      "grad_norm": 0.004554643761366606,
      "learning_rate": 0.0011555555555555555,
      "loss": 0.6709,
      "step": 883
    },
    {
      "epoch": 1.963898916967509,
      "grad_norm": 0.004862558096647263,
      "learning_rate": 0.0011530864197530865,
      "loss": 0.6733,
      "step": 884
    },
    {
      "epoch": 1.9661205220772007,
      "grad_norm": 0.005469104740768671,
      "learning_rate": 0.0011506172839506172,
      "loss": 0.5257,
      "step": 885
    },
    {
      "epoch": 1.9683421271868924,
      "grad_norm": 0.0030248200055211782,
      "learning_rate": 0.0011481481481481481,
      "loss": 0.5843,
      "step": 886
    },
    {
      "epoch": 1.9705637322965843,
      "grad_norm": 0.004950486123561859,
      "learning_rate": 0.001145679012345679,
      "loss": 0.6141,
      "step": 887
    },
    {
      "epoch": 1.972785337406276,
      "grad_norm": 0.002904703374952078,
      "learning_rate": 0.00114320987654321,
      "loss": 0.5761,
      "step": 888
    },
    {
      "epoch": 1.9750069425159678,
      "grad_norm": 0.004664995241910219,
      "learning_rate": 0.0011407407407407408,
      "loss": 0.5301,
      "step": 889
    },
    {
      "epoch": 1.9772285476256597,
      "grad_norm": 0.003233542200177908,
      "learning_rate": 0.0011382716049382717,
      "loss": 0.5926,
      "step": 890
    },
    {
      "epoch": 1.9794501527353514,
      "grad_norm": 0.0027818542439490557,
      "learning_rate": 0.0011358024691358025,
      "loss": 0.5411,
      "step": 891
    },
    {
      "epoch": 1.9816717578450431,
      "grad_norm": 0.0033229857217520475,
      "learning_rate": 0.0011333333333333334,
      "loss": 0.5764,
      "step": 892
    },
    {
      "epoch": 1.9838933629547348,
      "grad_norm": 0.002867978299036622,
      "learning_rate": 0.0011308641975308641,
      "loss": 0.7052,
      "step": 893
    },
    {
      "epoch": 1.9861149680644266,
      "grad_norm": 0.004475011490285397,
      "learning_rate": 0.001128395061728395,
      "loss": 0.6588,
      "step": 894
    },
    {
      "epoch": 1.9883365731741183,
      "grad_norm": 0.002667571185156703,
      "learning_rate": 0.001125925925925926,
      "loss": 0.7128,
      "step": 895
    },
    {
      "epoch": 1.99055817828381,
      "grad_norm": 0.0024032574146986008,
      "learning_rate": 0.0011234567901234568,
      "loss": 0.5392,
      "step": 896
    },
    {
      "epoch": 1.9927797833935017,
      "grad_norm": 0.003127054776996374,
      "learning_rate": 0.0011209876543209877,
      "loss": 0.6177,
      "step": 897
    },
    {
      "epoch": 1.9950013885031934,
      "grad_norm": 0.0033272269647568464,
      "learning_rate": 0.0011185185185185185,
      "loss": 0.538,
      "step": 898
    },
    {
      "epoch": 1.9972229936128854,
      "grad_norm": 0.005829309578984976,
      "learning_rate": 0.0011160493827160494,
      "loss": 0.6241,
      "step": 899
    },
    {
      "epoch": 1.999444598722577,
      "grad_norm": 0.003134448081254959,
      "learning_rate": 0.0011135802469135802,
      "loss": 0.5829,
      "step": 900
    },
    {
      "epoch": 2.001666203832269,
      "grad_norm": 0.005726494826376438,
      "learning_rate": 0.0011111111111111111,
      "loss": 0.8312,
      "step": 901
    },
    {
      "epoch": 2.0038878089419607,
      "grad_norm": 0.006034851539880037,
      "learning_rate": 0.001108641975308642,
      "loss": 0.6504,
      "step": 902
    },
    {
      "epoch": 2.0061094140516524,
      "grad_norm": 0.0043348087929189205,
      "learning_rate": 0.001106172839506173,
      "loss": 0.5744,
      "step": 903
    },
    {
      "epoch": 2.008331019161344,
      "grad_norm": 0.002852479461580515,
      "learning_rate": 0.0011037037037037037,
      "loss": 0.6126,
      "step": 904
    },
    {
      "epoch": 2.010552624271036,
      "grad_norm": 0.003809214336797595,
      "learning_rate": 0.0011012345679012347,
      "loss": 0.5645,
      "step": 905
    },
    {
      "epoch": 2.0127742293807276,
      "grad_norm": 0.002835030434653163,
      "learning_rate": 0.0010987654320987654,
      "loss": 0.7222,
      "step": 906
    },
    {
      "epoch": 2.0149958344904193,
      "grad_norm": 0.0031501781195402145,
      "learning_rate": 0.0010962962962962964,
      "loss": 0.503,
      "step": 907
    },
    {
      "epoch": 2.017217439600111,
      "grad_norm": 0.0020767690148204565,
      "learning_rate": 0.0010938271604938271,
      "loss": 0.5213,
      "step": 908
    },
    {
      "epoch": 2.0194390447098027,
      "grad_norm": 0.005374135449528694,
      "learning_rate": 0.001091358024691358,
      "loss": 0.511,
      "step": 909
    },
    {
      "epoch": 2.0216606498194944,
      "grad_norm": 0.0024446737952530384,
      "learning_rate": 0.001088888888888889,
      "loss": 0.5695,
      "step": 910
    },
    {
      "epoch": 2.023882254929186,
      "grad_norm": 0.0037711448967456818,
      "learning_rate": 0.0010864197530864198,
      "loss": 0.6868,
      "step": 911
    },
    {
      "epoch": 2.026103860038878,
      "grad_norm": 0.003181366017088294,
      "learning_rate": 0.0010839506172839507,
      "loss": 0.6471,
      "step": 912
    },
    {
      "epoch": 2.02832546514857,
      "grad_norm": 0.003707725554704666,
      "learning_rate": 0.0010814814814814814,
      "loss": 0.6463,
      "step": 913
    },
    {
      "epoch": 2.0305470702582618,
      "grad_norm": 0.005613626912236214,
      "learning_rate": 0.0010790123456790124,
      "loss": 0.5502,
      "step": 914
    },
    {
      "epoch": 2.0327686753679535,
      "grad_norm": 0.0028704151045531034,
      "learning_rate": 0.0010765432098765431,
      "loss": 0.4868,
      "step": 915
    },
    {
      "epoch": 2.034990280477645,
      "grad_norm": 0.0031033153645694256,
      "learning_rate": 0.001074074074074074,
      "loss": 0.4847,
      "step": 916
    },
    {
      "epoch": 2.037211885587337,
      "grad_norm": 0.009834744967520237,
      "learning_rate": 0.0010716049382716048,
      "loss": 0.6895,
      "step": 917
    },
    {
      "epoch": 2.0394334906970286,
      "grad_norm": 0.0026071355678141117,
      "learning_rate": 0.001069135802469136,
      "loss": 0.4661,
      "step": 918
    },
    {
      "epoch": 2.0416550958067203,
      "grad_norm": 0.002305686706677079,
      "learning_rate": 0.0010666666666666667,
      "loss": 0.5058,
      "step": 919
    },
    {
      "epoch": 2.043876700916412,
      "grad_norm": 0.0027897008694708347,
      "learning_rate": 0.0010641975308641977,
      "loss": 0.4986,
      "step": 920
    },
    {
      "epoch": 2.0460983060261038,
      "grad_norm": 0.003080989234149456,
      "learning_rate": 0.0010617283950617284,
      "loss": 0.6066,
      "step": 921
    },
    {
      "epoch": 2.0483199111357955,
      "grad_norm": 0.0035790393594652414,
      "learning_rate": 0.0010592592592592594,
      "loss": 0.4724,
      "step": 922
    },
    {
      "epoch": 2.050541516245487,
      "grad_norm": 0.00642067426815629,
      "learning_rate": 0.00105679012345679,
      "loss": 0.5943,
      "step": 923
    },
    {
      "epoch": 2.052763121355179,
      "grad_norm": 0.002329667564481497,
      "learning_rate": 0.001054320987654321,
      "loss": 0.7673,
      "step": 924
    },
    {
      "epoch": 2.054984726464871,
      "grad_norm": 0.0023226335179060698,
      "learning_rate": 0.001051851851851852,
      "loss": 0.4616,
      "step": 925
    },
    {
      "epoch": 2.057206331574563,
      "grad_norm": 0.002876643091440201,
      "learning_rate": 0.0010493827160493827,
      "loss": 0.4811,
      "step": 926
    },
    {
      "epoch": 2.0594279366842545,
      "grad_norm": 0.0042649186216294765,
      "learning_rate": 0.0010469135802469137,
      "loss": 0.5468,
      "step": 927
    },
    {
      "epoch": 2.061649541793946,
      "grad_norm": 0.0031739561818540096,
      "learning_rate": 0.0010444444444444444,
      "loss": 0.5715,
      "step": 928
    },
    {
      "epoch": 2.063871146903638,
      "grad_norm": 0.0024899898562580347,
      "learning_rate": 0.0010419753086419754,
      "loss": 0.4128,
      "step": 929
    },
    {
      "epoch": 2.0660927520133296,
      "grad_norm": 0.004804682917892933,
      "learning_rate": 0.001039506172839506,
      "loss": 0.6968,
      "step": 930
    },
    {
      "epoch": 2.0683143571230214,
      "grad_norm": 0.0025492811109870672,
      "learning_rate": 0.001037037037037037,
      "loss": 0.6023,
      "step": 931
    },
    {
      "epoch": 2.070535962232713,
      "grad_norm": 0.002714942442253232,
      "learning_rate": 0.0010345679012345678,
      "loss": 0.5751,
      "step": 932
    },
    {
      "epoch": 2.072757567342405,
      "grad_norm": 0.0028560515493154526,
      "learning_rate": 0.001032098765432099,
      "loss": 0.5003,
      "step": 933
    },
    {
      "epoch": 2.0749791724520965,
      "grad_norm": 0.0036102875601500273,
      "learning_rate": 0.0010296296296296297,
      "loss": 0.5057,
      "step": 934
    },
    {
      "epoch": 2.0772007775617882,
      "grad_norm": 0.0032866063993424177,
      "learning_rate": 0.0010271604938271606,
      "loss": 0.6955,
      "step": 935
    },
    {
      "epoch": 2.07942238267148,
      "grad_norm": 0.0031991819851100445,
      "learning_rate": 0.0010246913580246914,
      "loss": 0.4787,
      "step": 936
    },
    {
      "epoch": 2.081643987781172,
      "grad_norm": 0.003320596180856228,
      "learning_rate": 0.0010222222222222223,
      "loss": 0.5585,
      "step": 937
    },
    {
      "epoch": 2.083865592890864,
      "grad_norm": 0.0029568076133728027,
      "learning_rate": 0.001019753086419753,
      "loss": 0.5728,
      "step": 938
    },
    {
      "epoch": 2.0860871980005555,
      "grad_norm": 0.003186257090419531,
      "learning_rate": 0.001017283950617284,
      "loss": 0.6485,
      "step": 939
    },
    {
      "epoch": 2.0883088031102472,
      "grad_norm": 0.0029728305526077747,
      "learning_rate": 0.001014814814814815,
      "loss": 0.5389,
      "step": 940
    },
    {
      "epoch": 2.090530408219939,
      "grad_norm": 0.003383141476660967,
      "learning_rate": 0.0010123456790123457,
      "loss": 0.6484,
      "step": 941
    },
    {
      "epoch": 2.0927520133296307,
      "grad_norm": 0.0021532620303332806,
      "learning_rate": 0.0010098765432098766,
      "loss": 0.4437,
      "step": 942
    },
    {
      "epoch": 2.0949736184393224,
      "grad_norm": 0.0036302912048995495,
      "learning_rate": 0.0010074074074074074,
      "loss": 0.4678,
      "step": 943
    },
    {
      "epoch": 2.097195223549014,
      "grad_norm": 0.0027362217660993338,
      "learning_rate": 0.0010049382716049383,
      "loss": 0.6783,
      "step": 944
    },
    {
      "epoch": 2.099416828658706,
      "grad_norm": 0.003980798646807671,
      "learning_rate": 0.001002469135802469,
      "loss": 0.4243,
      "step": 945
    },
    {
      "epoch": 2.1016384337683975,
      "grad_norm": 0.003117599757388234,
      "learning_rate": 0.001,
      "loss": 0.6358,
      "step": 946
    },
    {
      "epoch": 2.1038600388780893,
      "grad_norm": 0.002921710954979062,
      "learning_rate": 0.0009975308641975308,
      "loss": 0.5536,
      "step": 947
    },
    {
      "epoch": 2.106081643987781,
      "grad_norm": 0.002694458467885852,
      "learning_rate": 0.000995061728395062,
      "loss": 0.5176,
      "step": 948
    },
    {
      "epoch": 2.108303249097473,
      "grad_norm": 0.0024422232527285814,
      "learning_rate": 0.0009925925925925927,
      "loss": 0.4896,
      "step": 949
    },
    {
      "epoch": 2.110524854207165,
      "grad_norm": 0.0038264193572103977,
      "learning_rate": 0.0009901234567901234,
      "loss": 0.5917,
      "step": 950
    },
    {
      "epoch": 2.1127464593168566,
      "grad_norm": 0.003285654354840517,
      "learning_rate": 0.0009876543209876543,
      "loss": 0.5477,
      "step": 951
    },
    {
      "epoch": 2.1149680644265483,
      "grad_norm": 0.0052144345827400684,
      "learning_rate": 0.000985185185185185,
      "loss": 0.6782,
      "step": 952
    },
    {
      "epoch": 2.11718966953624,
      "grad_norm": 0.0023586968891322613,
      "learning_rate": 0.000982716049382716,
      "loss": 0.6897,
      "step": 953
    },
    {
      "epoch": 2.1194112746459317,
      "grad_norm": 0.003020720323547721,
      "learning_rate": 0.0009802469135802468,
      "loss": 0.3999,
      "step": 954
    },
    {
      "epoch": 2.1216328797556234,
      "grad_norm": 0.001899965456686914,
      "learning_rate": 0.000977777777777778,
      "loss": 0.6384,
      "step": 955
    },
    {
      "epoch": 2.123854484865315,
      "grad_norm": 0.004147064406424761,
      "learning_rate": 0.0009753086419753087,
      "loss": 0.6325,
      "step": 956
    },
    {
      "epoch": 2.126076089975007,
      "grad_norm": 0.002664576517418027,
      "learning_rate": 0.0009728395061728395,
      "loss": 0.5964,
      "step": 957
    },
    {
      "epoch": 2.1282976950846986,
      "grad_norm": 0.0025310623459517956,
      "learning_rate": 0.0009703703703703704,
      "loss": 0.5945,
      "step": 958
    },
    {
      "epoch": 2.1305193001943903,
      "grad_norm": 0.00503195496276021,
      "learning_rate": 0.0009679012345679012,
      "loss": 0.593,
      "step": 959
    },
    {
      "epoch": 2.132740905304082,
      "grad_norm": 0.00486906198784709,
      "learning_rate": 0.000965432098765432,
      "loss": 0.5602,
      "step": 960
    },
    {
      "epoch": 2.134962510413774,
      "grad_norm": 0.0024207246024161577,
      "learning_rate": 0.0009629629629629629,
      "loss": 0.4595,
      "step": 961
    },
    {
      "epoch": 2.137184115523466,
      "grad_norm": 0.0028605612460523844,
      "learning_rate": 0.0009604938271604937,
      "loss": 0.5915,
      "step": 962
    },
    {
      "epoch": 2.1394057206331576,
      "grad_norm": 0.0030085062608122826,
      "learning_rate": 0.0009580246913580248,
      "loss": 0.5204,
      "step": 963
    },
    {
      "epoch": 2.1416273257428493,
      "grad_norm": 0.0030539585277438164,
      "learning_rate": 0.0009555555555555556,
      "loss": 0.5966,
      "step": 964
    },
    {
      "epoch": 2.143848930852541,
      "grad_norm": 0.004271404352039099,
      "learning_rate": 0.0009530864197530865,
      "loss": 0.5244,
      "step": 965
    },
    {
      "epoch": 2.1460705359622327,
      "grad_norm": 0.0030084841419011354,
      "learning_rate": 0.0009506172839506173,
      "loss": 0.7287,
      "step": 966
    },
    {
      "epoch": 2.1482921410719245,
      "grad_norm": 0.0035079021472483873,
      "learning_rate": 0.0009481481481481482,
      "loss": 0.6869,
      "step": 967
    },
    {
      "epoch": 2.150513746181616,
      "grad_norm": 0.0022759109269827604,
      "learning_rate": 0.000945679012345679,
      "loss": 0.536,
      "step": 968
    },
    {
      "epoch": 2.152735351291308,
      "grad_norm": 0.00978132151067257,
      "learning_rate": 0.0009432098765432098,
      "loss": 0.7213,
      "step": 969
    },
    {
      "epoch": 2.1549569564009996,
      "grad_norm": 0.003520718775689602,
      "learning_rate": 0.0009407407407407408,
      "loss": 0.5426,
      "step": 970
    },
    {
      "epoch": 2.1571785615106913,
      "grad_norm": 0.003189661307260394,
      "learning_rate": 0.0009382716049382716,
      "loss": 0.5682,
      "step": 971
    },
    {
      "epoch": 2.159400166620383,
      "grad_norm": 0.004090138245373964,
      "learning_rate": 0.0009358024691358025,
      "loss": 0.5585,
      "step": 972
    },
    {
      "epoch": 2.1616217717300747,
      "grad_norm": 0.002348746173083782,
      "learning_rate": 0.0009333333333333333,
      "loss": 0.5744,
      "step": 973
    },
    {
      "epoch": 2.163843376839767,
      "grad_norm": 0.0030610274989157915,
      "learning_rate": 0.0009308641975308642,
      "loss": 0.5157,
      "step": 974
    },
    {
      "epoch": 2.1660649819494586,
      "grad_norm": 0.004090711008757353,
      "learning_rate": 0.000928395061728395,
      "loss": 0.5026,
      "step": 975
    },
    {
      "epoch": 2.1682865870591503,
      "grad_norm": 0.005956096574664116,
      "learning_rate": 0.0009259259259259259,
      "loss": 0.5018,
      "step": 976
    },
    {
      "epoch": 2.170508192168842,
      "grad_norm": 0.003179134801030159,
      "learning_rate": 0.0009234567901234567,
      "loss": 0.6329,
      "step": 977
    },
    {
      "epoch": 2.1727297972785338,
      "grad_norm": 0.004298276733607054,
      "learning_rate": 0.0009209876543209878,
      "loss": 0.5353,
      "step": 978
    },
    {
      "epoch": 2.1749514023882255,
      "grad_norm": 0.003176155500113964,
      "learning_rate": 0.0009185185185185186,
      "loss": 0.6158,
      "step": 979
    },
    {
      "epoch": 2.177173007497917,
      "grad_norm": 0.0038320133462548256,
      "learning_rate": 0.0009160493827160494,
      "loss": 0.6133,
      "step": 980
    },
    {
      "epoch": 2.179394612607609,
      "grad_norm": 0.002970824483782053,
      "learning_rate": 0.0009135802469135803,
      "loss": 0.5616,
      "step": 981
    },
    {
      "epoch": 2.1816162177173006,
      "grad_norm": 0.0038941886741667986,
      "learning_rate": 0.0009111111111111111,
      "loss": 0.5171,
      "step": 982
    },
    {
      "epoch": 2.1838378228269923,
      "grad_norm": 0.0038700338918715715,
      "learning_rate": 0.000908641975308642,
      "loss": 0.5789,
      "step": 983
    },
    {
      "epoch": 2.186059427936684,
      "grad_norm": 0.0026391134597361088,
      "learning_rate": 0.0009061728395061728,
      "loss": 0.6502,
      "step": 984
    },
    {
      "epoch": 2.1882810330463762,
      "grad_norm": 0.0023232395760715008,
      "learning_rate": 0.0009037037037037038,
      "loss": 0.5188,
      "step": 985
    },
    {
      "epoch": 2.190502638156068,
      "grad_norm": 0.003235009266063571,
      "learning_rate": 0.0009012345679012346,
      "loss": 0.5062,
      "step": 986
    },
    {
      "epoch": 2.1927242432657597,
      "grad_norm": 0.002925153123214841,
      "learning_rate": 0.0008987654320987655,
      "loss": 0.544,
      "step": 987
    },
    {
      "epoch": 2.1949458483754514,
      "grad_norm": 0.002652216237038374,
      "learning_rate": 0.0008962962962962963,
      "loss": 0.5938,
      "step": 988
    },
    {
      "epoch": 2.197167453485143,
      "grad_norm": 0.0038400006014853716,
      "learning_rate": 0.0008938271604938271,
      "loss": 0.4818,
      "step": 989
    },
    {
      "epoch": 2.199389058594835,
      "grad_norm": 0.003454734105616808,
      "learning_rate": 0.000891358024691358,
      "loss": 0.5117,
      "step": 990
    },
    {
      "epoch": 2.2016106637045265,
      "grad_norm": 0.003155773039907217,
      "learning_rate": 0.0008888888888888888,
      "loss": 0.6079,
      "step": 991
    },
    {
      "epoch": 2.2038322688142182,
      "grad_norm": 0.007587943226099014,
      "learning_rate": 0.0008864197530864197,
      "loss": 0.5854,
      "step": 992
    },
    {
      "epoch": 2.20605387392391,
      "grad_norm": 0.0024301139637827873,
      "learning_rate": 0.0008839506172839507,
      "loss": 0.484,
      "step": 993
    },
    {
      "epoch": 2.2082754790336017,
      "grad_norm": 0.006092358380556107,
      "learning_rate": 0.0008814814814814816,
      "loss": 0.5864,
      "step": 994
    },
    {
      "epoch": 2.2104970841432934,
      "grad_norm": 0.002938348799943924,
      "learning_rate": 0.0008790123456790124,
      "loss": 0.5164,
      "step": 995
    },
    {
      "epoch": 2.212718689252985,
      "grad_norm": 0.0024373226333409548,
      "learning_rate": 0.0008765432098765433,
      "loss": 0.5449,
      "step": 996
    },
    {
      "epoch": 2.214940294362677,
      "grad_norm": 0.0031108020339161158,
      "learning_rate": 0.0008740740740740741,
      "loss": 0.4239,
      "step": 997
    },
    {
      "epoch": 2.217161899472369,
      "grad_norm": 0.005813131108880043,
      "learning_rate": 0.0008716049382716049,
      "loss": 0.5485,
      "step": 998
    },
    {
      "epoch": 2.2193835045820607,
      "grad_norm": 0.0029320288449525833,
      "learning_rate": 0.0008691358024691358,
      "loss": 0.5638,
      "step": 999
    },
    {
      "epoch": 2.2216051096917524,
      "grad_norm": 0.0034687980078160763,
      "learning_rate": 0.0008666666666666666,
      "loss": 0.6191,
      "step": 1000
    },
    {
      "epoch": 2.223826714801444,
      "grad_norm": 0.004658684600144625,
      "learning_rate": 0.0008641975308641976,
      "loss": 0.5282,
      "step": 1001
    },
    {
      "epoch": 2.226048319911136,
      "grad_norm": 0.003695260500535369,
      "learning_rate": 0.0008617283950617284,
      "loss": 0.6722,
      "step": 1002
    },
    {
      "epoch": 2.2282699250208275,
      "grad_norm": 0.00335449050180614,
      "learning_rate": 0.0008592592592592593,
      "loss": 0.6853,
      "step": 1003
    },
    {
      "epoch": 2.2304915301305193,
      "grad_norm": 0.0034760725684463978,
      "learning_rate": 0.0008567901234567901,
      "loss": 0.4872,
      "step": 1004
    },
    {
      "epoch": 2.232713135240211,
      "grad_norm": 0.00436612032353878,
      "learning_rate": 0.000854320987654321,
      "loss": 0.6294,
      "step": 1005
    },
    {
      "epoch": 2.2349347403499027,
      "grad_norm": 0.005213717930018902,
      "learning_rate": 0.0008518518518518518,
      "loss": 0.5129,
      "step": 1006
    },
    {
      "epoch": 2.2371563454595944,
      "grad_norm": 0.003134811297059059,
      "learning_rate": 0.0008493827160493826,
      "loss": 0.5639,
      "step": 1007
    },
    {
      "epoch": 2.239377950569286,
      "grad_norm": 0.003105428535491228,
      "learning_rate": 0.0008469135802469137,
      "loss": 0.6618,
      "step": 1008
    },
    {
      "epoch": 2.2415995556789783,
      "grad_norm": 0.004108819179236889,
      "learning_rate": 0.0008444444444444445,
      "loss": 0.5644,
      "step": 1009
    },
    {
      "epoch": 2.24382116078867,
      "grad_norm": 0.0030806276481598616,
      "learning_rate": 0.0008419753086419754,
      "loss": 0.467,
      "step": 1010
    },
    {
      "epoch": 2.2460427658983617,
      "grad_norm": 0.003562948666512966,
      "learning_rate": 0.0008395061728395062,
      "loss": 0.5842,
      "step": 1011
    },
    {
      "epoch": 2.2482643710080534,
      "grad_norm": 0.0057414439506828785,
      "learning_rate": 0.0008370370370370371,
      "loss": 0.5443,
      "step": 1012
    },
    {
      "epoch": 2.250485976117745,
      "grad_norm": 0.003909396473318338,
      "learning_rate": 0.0008345679012345679,
      "loss": 0.5694,
      "step": 1013
    },
    {
      "epoch": 2.252707581227437,
      "grad_norm": 0.006677468307316303,
      "learning_rate": 0.0008320987654320988,
      "loss": 0.6676,
      "step": 1014
    },
    {
      "epoch": 2.2549291863371286,
      "grad_norm": 0.005053333006799221,
      "learning_rate": 0.0008296296296296296,
      "loss": 0.5625,
      "step": 1015
    },
    {
      "epoch": 2.2571507914468203,
      "grad_norm": 0.004885704722255468,
      "learning_rate": 0.0008271604938271605,
      "loss": 0.4741,
      "step": 1016
    },
    {
      "epoch": 2.259372396556512,
      "grad_norm": 0.003592871828004718,
      "learning_rate": 0.0008246913580246914,
      "loss": 0.5534,
      "step": 1017
    },
    {
      "epoch": 2.2615940016662037,
      "grad_norm": 0.003084664000198245,
      "learning_rate": 0.0008222222222222222,
      "loss": 0.6343,
      "step": 1018
    },
    {
      "epoch": 2.2638156067758954,
      "grad_norm": 0.0027031810022890568,
      "learning_rate": 0.0008197530864197531,
      "loss": 0.6111,
      "step": 1019
    },
    {
      "epoch": 2.266037211885587,
      "grad_norm": 0.0039059389382600784,
      "learning_rate": 0.0008172839506172839,
      "loss": 0.5344,
      "step": 1020
    },
    {
      "epoch": 2.268258816995279,
      "grad_norm": 0.0038647891487926245,
      "learning_rate": 0.0008148148148148148,
      "loss": 0.5565,
      "step": 1021
    },
    {
      "epoch": 2.270480422104971,
      "grad_norm": 0.00459673535078764,
      "learning_rate": 0.0008123456790123456,
      "loss": 0.5623,
      "step": 1022
    },
    {
      "epoch": 2.2727020272146627,
      "grad_norm": 0.005373631604015827,
      "learning_rate": 0.0008098765432098767,
      "loss": 0.6348,
      "step": 1023
    },
    {
      "epoch": 2.2749236323243545,
      "grad_norm": 0.004298051353543997,
      "learning_rate": 0.0008074074074074075,
      "loss": 0.5197,
      "step": 1024
    },
    {
      "epoch": 2.277145237434046,
      "grad_norm": 0.00378704653121531,
      "learning_rate": 0.0008049382716049384,
      "loss": 0.5934,
      "step": 1025
    },
    {
      "epoch": 2.279366842543738,
      "grad_norm": 0.004439651500433683,
      "learning_rate": 0.0008024691358024692,
      "loss": 0.7252,
      "step": 1026
    },
    {
      "epoch": 2.2815884476534296,
      "grad_norm": 0.0030909578781574965,
      "learning_rate": 0.0008,
      "loss": 0.6597,
      "step": 1027
    },
    {
      "epoch": 2.2838100527631213,
      "grad_norm": 0.00279823481105268,
      "learning_rate": 0.0007975308641975309,
      "loss": 0.5536,
      "step": 1028
    },
    {
      "epoch": 2.286031657872813,
      "grad_norm": 0.007109540980309248,
      "learning_rate": 0.0007950617283950617,
      "loss": 0.6379,
      "step": 1029
    },
    {
      "epoch": 2.2882532629825048,
      "grad_norm": 0.0029051511082798243,
      "learning_rate": 0.0007925925925925926,
      "loss": 0.5066,
      "step": 1030
    },
    {
      "epoch": 2.2904748680921965,
      "grad_norm": 0.0025258744135499,
      "learning_rate": 0.0007901234567901235,
      "loss": 0.7498,
      "step": 1031
    },
    {
      "epoch": 2.292696473201888,
      "grad_norm": 0.0031271756161004305,
      "learning_rate": 0.0007876543209876544,
      "loss": 0.6633,
      "step": 1032
    },
    {
      "epoch": 2.2949180783115803,
      "grad_norm": 0.003749959636479616,
      "learning_rate": 0.0007851851851851852,
      "loss": 0.5935,
      "step": 1033
    },
    {
      "epoch": 2.297139683421272,
      "grad_norm": 0.018562858924269676,
      "learning_rate": 0.000782716049382716,
      "loss": 0.6668,
      "step": 1034
    },
    {
      "epoch": 2.2993612885309638,
      "grad_norm": 0.0034211401361972094,
      "learning_rate": 0.0007802469135802469,
      "loss": 0.5198,
      "step": 1035
    },
    {
      "epoch": 2.3015828936406555,
      "grad_norm": 0.007033830508589745,
      "learning_rate": 0.0007777777777777777,
      "loss": 0.6454,
      "step": 1036
    },
    {
      "epoch": 2.303804498750347,
      "grad_norm": 0.004096447490155697,
      "learning_rate": 0.0007753086419753086,
      "loss": 0.4284,
      "step": 1037
    },
    {
      "epoch": 2.306026103860039,
      "grad_norm": 0.0033222660422325134,
      "learning_rate": 0.0007728395061728396,
      "loss": 0.7389,
      "step": 1038
    },
    {
      "epoch": 2.3082477089697306,
      "grad_norm": 0.003214897122234106,
      "learning_rate": 0.0007703703703703705,
      "loss": 0.4918,
      "step": 1039
    },
    {
      "epoch": 2.3104693140794224,
      "grad_norm": 0.003940572030842304,
      "learning_rate": 0.0007679012345679013,
      "loss": 0.6554,
      "step": 1040
    },
    {
      "epoch": 2.312690919189114,
      "grad_norm": 0.0031553073786199093,
      "learning_rate": 0.0007654320987654322,
      "loss": 0.562,
      "step": 1041
    },
    {
      "epoch": 2.314912524298806,
      "grad_norm": 0.0022206681314855814,
      "learning_rate": 0.000762962962962963,
      "loss": 0.516,
      "step": 1042
    },
    {
      "epoch": 2.3171341294084975,
      "grad_norm": 0.002873531309887767,
      "learning_rate": 0.0007604938271604939,
      "loss": 0.4869,
      "step": 1043
    },
    {
      "epoch": 2.319355734518189,
      "grad_norm": 0.002862492110580206,
      "learning_rate": 0.0007580246913580247,
      "loss": 0.6987,
      "step": 1044
    },
    {
      "epoch": 2.321577339627881,
      "grad_norm": 0.0036229663528501987,
      "learning_rate": 0.0007555555555555555,
      "loss": 0.5343,
      "step": 1045
    },
    {
      "epoch": 2.3237989447375726,
      "grad_norm": 0.0054009584710001945,
      "learning_rate": 0.0007530864197530865,
      "loss": 0.8101,
      "step": 1046
    },
    {
      "epoch": 2.326020549847265,
      "grad_norm": 0.005098678171634674,
      "learning_rate": 0.0007506172839506173,
      "loss": 0.6813,
      "step": 1047
    },
    {
      "epoch": 2.3282421549569565,
      "grad_norm": 0.003056863322854042,
      "learning_rate": 0.0007481481481481482,
      "loss": 0.4675,
      "step": 1048
    },
    {
      "epoch": 2.3304637600666482,
      "grad_norm": 0.003354548942297697,
      "learning_rate": 0.000745679012345679,
      "loss": 0.5348,
      "step": 1049
    },
    {
      "epoch": 2.33268536517634,
      "grad_norm": 0.004473726265132427,
      "learning_rate": 0.0007432098765432099,
      "loss": 0.629,
      "step": 1050
    },
    {
      "epoch": 2.3349069702860317,
      "grad_norm": 0.0039171804673969746,
      "learning_rate": 0.0007407407407407407,
      "loss": 0.5336,
      "step": 1051
    },
    {
      "epoch": 2.3371285753957234,
      "grad_norm": 0.004147024359554052,
      "learning_rate": 0.0007382716049382717,
      "loss": 0.5684,
      "step": 1052
    },
    {
      "epoch": 2.339350180505415,
      "grad_norm": 0.0027169683016836643,
      "learning_rate": 0.0007358024691358025,
      "loss": 0.5648,
      "step": 1053
    },
    {
      "epoch": 2.341571785615107,
      "grad_norm": 0.003304773010313511,
      "learning_rate": 0.0007333333333333333,
      "loss": 0.5302,
      "step": 1054
    },
    {
      "epoch": 2.3437933907247985,
      "grad_norm": 0.0029916686471551657,
      "learning_rate": 0.0007308641975308643,
      "loss": 0.5553,
      "step": 1055
    },
    {
      "epoch": 2.3460149958344902,
      "grad_norm": 0.003973797429352999,
      "learning_rate": 0.0007283950617283951,
      "loss": 0.5325,
      "step": 1056
    },
    {
      "epoch": 2.3482366009441824,
      "grad_norm": 0.0018603012431412935,
      "learning_rate": 0.000725925925925926,
      "loss": 0.4591,
      "step": 1057
    },
    {
      "epoch": 2.350458206053874,
      "grad_norm": 0.002701596822589636,
      "learning_rate": 0.0007234567901234568,
      "loss": 0.5483,
      "step": 1058
    },
    {
      "epoch": 2.352679811163566,
      "grad_norm": 0.003739901352673769,
      "learning_rate": 0.0007209876543209877,
      "loss": 0.5299,
      "step": 1059
    },
    {
      "epoch": 2.3549014162732576,
      "grad_norm": 0.004963619168847799,
      "learning_rate": 0.0007185185185185185,
      "loss": 0.6273,
      "step": 1060
    },
    {
      "epoch": 2.3571230213829493,
      "grad_norm": 0.0027527539059519768,
      "learning_rate": 0.0007160493827160494,
      "loss": 0.4585,
      "step": 1061
    },
    {
      "epoch": 2.359344626492641,
      "grad_norm": 0.003659699810668826,
      "learning_rate": 0.0007135802469135802,
      "loss": 0.5179,
      "step": 1062
    },
    {
      "epoch": 2.3615662316023327,
      "grad_norm": 0.004066236782819033,
      "learning_rate": 0.0007111111111111111,
      "loss": 0.5565,
      "step": 1063
    },
    {
      "epoch": 2.3637878367120244,
      "grad_norm": 0.0036002537235617638,
      "learning_rate": 0.000708641975308642,
      "loss": 0.4883,
      "step": 1064
    },
    {
      "epoch": 2.366009441821716,
      "grad_norm": 0.0032738163135945797,
      "learning_rate": 0.0007061728395061728,
      "loss": 0.5275,
      "step": 1065
    },
    {
      "epoch": 2.368231046931408,
      "grad_norm": 0.0037834448739886284,
      "learning_rate": 0.0007037037037037037,
      "loss": 0.6872,
      "step": 1066
    },
    {
      "epoch": 2.3704526520410996,
      "grad_norm": 0.0036043571308255196,
      "learning_rate": 0.0007012345679012346,
      "loss": 0.5326,
      "step": 1067
    },
    {
      "epoch": 2.3726742571507913,
      "grad_norm": 0.0025616211351007223,
      "learning_rate": 0.0006987654320987655,
      "loss": 0.5362,
      "step": 1068
    },
    {
      "epoch": 2.374895862260483,
      "grad_norm": 0.02127094380557537,
      "learning_rate": 0.0006962962962962963,
      "loss": 0.522,
      "step": 1069
    },
    {
      "epoch": 2.3771174673701747,
      "grad_norm": 0.003062931587919593,
      "learning_rate": 0.0006938271604938273,
      "loss": 0.6184,
      "step": 1070
    },
    {
      "epoch": 2.379339072479867,
      "grad_norm": 0.0035400697961449623,
      "learning_rate": 0.0006913580246913581,
      "loss": 0.5067,
      "step": 1071
    },
    {
      "epoch": 2.3815606775895586,
      "grad_norm": 0.0039336830377578735,
      "learning_rate": 0.000688888888888889,
      "loss": 0.6399,
      "step": 1072
    },
    {
      "epoch": 2.3837822826992503,
      "grad_norm": 0.003443269059062004,
      "learning_rate": 0.0006864197530864198,
      "loss": 0.4827,
      "step": 1073
    },
    {
      "epoch": 2.386003887808942,
      "grad_norm": 0.003925650846213102,
      "learning_rate": 0.0006839506172839506,
      "loss": 0.5119,
      "step": 1074
    },
    {
      "epoch": 2.3882254929186337,
      "grad_norm": 0.0021815653890371323,
      "learning_rate": 0.0006814814814814815,
      "loss": 0.6329,
      "step": 1075
    },
    {
      "epoch": 2.3904470980283254,
      "grad_norm": 0.0022753621451556683,
      "learning_rate": 0.0006790123456790123,
      "loss": 0.5293,
      "step": 1076
    },
    {
      "epoch": 2.392668703138017,
      "grad_norm": 0.006638281513005495,
      "learning_rate": 0.0006765432098765432,
      "loss": 0.5449,
      "step": 1077
    },
    {
      "epoch": 2.394890308247709,
      "grad_norm": 0.003063911572098732,
      "learning_rate": 0.0006740740740740741,
      "loss": 0.5938,
      "step": 1078
    },
    {
      "epoch": 2.3971119133574006,
      "grad_norm": 0.0031239197123795748,
      "learning_rate": 0.000671604938271605,
      "loss": 0.4162,
      "step": 1079
    },
    {
      "epoch": 2.3993335184670923,
      "grad_norm": 0.002710064873099327,
      "learning_rate": 0.0006691358024691358,
      "loss": 0.4449,
      "step": 1080
    },
    {
      "epoch": 2.4015551235767845,
      "grad_norm": 0.003996432293206453,
      "learning_rate": 0.0006666666666666666,
      "loss": 0.6663,
      "step": 1081
    },
    {
      "epoch": 2.403776728686476,
      "grad_norm": 0.004136720672249794,
      "learning_rate": 0.0006641975308641976,
      "loss": 0.5533,
      "step": 1082
    },
    {
      "epoch": 2.405998333796168,
      "grad_norm": 0.003114722203463316,
      "learning_rate": 0.0006617283950617284,
      "loss": 0.4705,
      "step": 1083
    },
    {
      "epoch": 2.4082199389058596,
      "grad_norm": 0.0034891797695308924,
      "learning_rate": 0.0006592592592592593,
      "loss": 0.6902,
      "step": 1084
    },
    {
      "epoch": 2.4104415440155513,
      "grad_norm": 0.0045388005673885345,
      "learning_rate": 0.0006567901234567901,
      "loss": 0.5728,
      "step": 1085
    },
    {
      "epoch": 2.412663149125243,
      "grad_norm": 0.003884939244017005,
      "learning_rate": 0.000654320987654321,
      "loss": 0.4668,
      "step": 1086
    },
    {
      "epoch": 2.4148847542349348,
      "grad_norm": 0.003789950627833605,
      "learning_rate": 0.0006518518518518518,
      "loss": 0.5495,
      "step": 1087
    },
    {
      "epoch": 2.4171063593446265,
      "grad_norm": 0.0027637809980660677,
      "learning_rate": 0.0006493827160493827,
      "loss": 0.5626,
      "step": 1088
    },
    {
      "epoch": 2.419327964454318,
      "grad_norm": 0.0039571127854287624,
      "learning_rate": 0.0006469135802469136,
      "loss": 0.5258,
      "step": 1089
    },
    {
      "epoch": 2.42154956956401,
      "grad_norm": 0.004000820219516754,
      "learning_rate": 0.0006444444444444444,
      "loss": 0.4894,
      "step": 1090
    },
    {
      "epoch": 2.4237711746737016,
      "grad_norm": 0.0066573964431881905,
      "learning_rate": 0.0006419753086419753,
      "loss": 0.5473,
      "step": 1091
    },
    {
      "epoch": 2.4259927797833933,
      "grad_norm": 0.0024974343832582235,
      "learning_rate": 0.0006395061728395061,
      "loss": 0.525,
      "step": 1092
    },
    {
      "epoch": 2.428214384893085,
      "grad_norm": 0.0035255502443760633,
      "learning_rate": 0.0006370370370370371,
      "loss": 0.535,
      "step": 1093
    },
    {
      "epoch": 2.4304359900027768,
      "grad_norm": 0.00428081164136529,
      "learning_rate": 0.0006345679012345679,
      "loss": 0.5378,
      "step": 1094
    },
    {
      "epoch": 2.432657595112469,
      "grad_norm": 0.0036717208568006754,
      "learning_rate": 0.0006320987654320988,
      "loss": 0.5462,
      "step": 1095
    },
    {
      "epoch": 2.4348792002221606,
      "grad_norm": 0.006416546646505594,
      "learning_rate": 0.0006296296296296296,
      "loss": 0.6657,
      "step": 1096
    },
    {
      "epoch": 2.4371008053318524,
      "grad_norm": 0.004640530329197645,
      "learning_rate": 0.0006271604938271606,
      "loss": 0.6332,
      "step": 1097
    },
    {
      "epoch": 2.439322410441544,
      "grad_norm": 0.004433172754943371,
      "learning_rate": 0.0006246913580246914,
      "loss": 0.5313,
      "step": 1098
    },
    {
      "epoch": 2.441544015551236,
      "grad_norm": 0.0037143733352422714,
      "learning_rate": 0.0006222222222222223,
      "loss": 0.6797,
      "step": 1099
    },
    {
      "epoch": 2.4437656206609275,
      "grad_norm": 0.0037918142043054104,
      "learning_rate": 0.0006197530864197531,
      "loss": 0.5052,
      "step": 1100
    },
    {
      "epoch": 2.4459872257706192,
      "grad_norm": 0.004170644097030163,
      "learning_rate": 0.0006172839506172839,
      "loss": 0.5218,
      "step": 1101
    },
    {
      "epoch": 2.448208830880311,
      "grad_norm": 0.006858695298433304,
      "learning_rate": 0.0006148148148148148,
      "loss": 0.7513,
      "step": 1102
    },
    {
      "epoch": 2.4504304359900027,
      "grad_norm": 0.0030471975915133953,
      "learning_rate": 0.0006123456790123456,
      "loss": 0.4431,
      "step": 1103
    },
    {
      "epoch": 2.4526520410996944,
      "grad_norm": 0.0025605515111237764,
      "learning_rate": 0.0006098765432098766,
      "loss": 0.5324,
      "step": 1104
    },
    {
      "epoch": 2.4548736462093865,
      "grad_norm": 0.002681012498214841,
      "learning_rate": 0.0006074074074074074,
      "loss": 0.5425,
      "step": 1105
    },
    {
      "epoch": 2.4570952513190782,
      "grad_norm": 0.003387799486517906,
      "learning_rate": 0.0006049382716049383,
      "loss": 0.5723,
      "step": 1106
    },
    {
      "epoch": 2.45931685642877,
      "grad_norm": 0.004109434317797422,
      "learning_rate": 0.0006024691358024691,
      "loss": 0.6352,
      "step": 1107
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.0024278839118778706,
      "learning_rate": 0.0006000000000000001,
      "loss": 0.6173,
      "step": 1108
    },
    {
      "epoch": 2.4637600666481534,
      "grad_norm": 0.004283036105334759,
      "learning_rate": 0.0005975308641975309,
      "loss": 0.4519,
      "step": 1109
    },
    {
      "epoch": 2.465981671757845,
      "grad_norm": 0.0027808351442217827,
      "learning_rate": 0.0005950617283950617,
      "loss": 0.5603,
      "step": 1110
    },
    {
      "epoch": 2.468203276867537,
      "grad_norm": 0.005799554288387299,
      "learning_rate": 0.0005925925925925926,
      "loss": 0.4953,
      "step": 1111
    },
    {
      "epoch": 2.4704248819772285,
      "grad_norm": 0.003943710122257471,
      "learning_rate": 0.0005901234567901235,
      "loss": 0.6436,
      "step": 1112
    },
    {
      "epoch": 2.4726464870869203,
      "grad_norm": 0.0031780507415533066,
      "learning_rate": 0.0005876543209876544,
      "loss": 0.8561,
      "step": 1113
    },
    {
      "epoch": 2.474868092196612,
      "grad_norm": 0.0029456582851707935,
      "learning_rate": 0.0005851851851851852,
      "loss": 0.7947,
      "step": 1114
    },
    {
      "epoch": 2.4770896973063037,
      "grad_norm": 0.004234964959323406,
      "learning_rate": 0.0005827160493827161,
      "loss": 0.6216,
      "step": 1115
    },
    {
      "epoch": 2.4793113024159954,
      "grad_norm": 0.002773207612335682,
      "learning_rate": 0.0005802469135802469,
      "loss": 0.4893,
      "step": 1116
    },
    {
      "epoch": 2.481532907525687,
      "grad_norm": 0.0036813535261899233,
      "learning_rate": 0.0005777777777777778,
      "loss": 0.5087,
      "step": 1117
    },
    {
      "epoch": 2.483754512635379,
      "grad_norm": 0.004553146194666624,
      "learning_rate": 0.0005753086419753086,
      "loss": 0.6018,
      "step": 1118
    },
    {
      "epoch": 2.485976117745071,
      "grad_norm": 0.003832323709502816,
      "learning_rate": 0.0005728395061728395,
      "loss": 0.5061,
      "step": 1119
    },
    {
      "epoch": 2.4881977228547627,
      "grad_norm": 0.0032602003775537014,
      "learning_rate": 0.0005703703703703704,
      "loss": 0.5801,
      "step": 1120
    },
    {
      "epoch": 2.4904193279644544,
      "grad_norm": 0.003078698879107833,
      "learning_rate": 0.0005679012345679012,
      "loss": 0.5464,
      "step": 1121
    },
    {
      "epoch": 2.492640933074146,
      "grad_norm": 0.0034781810827553272,
      "learning_rate": 0.0005654320987654321,
      "loss": 0.5988,
      "step": 1122
    },
    {
      "epoch": 2.494862538183838,
      "grad_norm": 0.004380400758236647,
      "learning_rate": 0.000562962962962963,
      "loss": 0.7865,
      "step": 1123
    },
    {
      "epoch": 2.4970841432935296,
      "grad_norm": 0.0039103650487959385,
      "learning_rate": 0.0005604938271604939,
      "loss": 0.6177,
      "step": 1124
    },
    {
      "epoch": 2.4993057484032213,
      "grad_norm": 0.0022219792008399963,
      "learning_rate": 0.0005580246913580247,
      "loss": 0.5995,
      "step": 1125
    },
    {
      "epoch": 2.501527353512913,
      "grad_norm": 0.0030277410987764597,
      "learning_rate": 0.0005555555555555556,
      "loss": 0.6282,
      "step": 1126
    },
    {
      "epoch": 2.5037489586226047,
      "grad_norm": 0.00469292514026165,
      "learning_rate": 0.0005530864197530865,
      "loss": 0.5087,
      "step": 1127
    },
    {
      "epoch": 2.5059705637322964,
      "grad_norm": 0.0040251887403428555,
      "learning_rate": 0.0005506172839506173,
      "loss": 0.4887,
      "step": 1128
    },
    {
      "epoch": 2.5081921688419886,
      "grad_norm": 0.0035228501074016094,
      "learning_rate": 0.0005481481481481482,
      "loss": 0.4532,
      "step": 1129
    },
    {
      "epoch": 2.5104137739516803,
      "grad_norm": 0.0039059482514858246,
      "learning_rate": 0.000545679012345679,
      "loss": 0.5497,
      "step": 1130
    },
    {
      "epoch": 2.512635379061372,
      "grad_norm": 0.0033773144241422415,
      "learning_rate": 0.0005432098765432099,
      "loss": 0.5005,
      "step": 1131
    },
    {
      "epoch": 2.5148569841710637,
      "grad_norm": 0.003276864066720009,
      "learning_rate": 0.0005407407407407407,
      "loss": 0.6146,
      "step": 1132
    },
    {
      "epoch": 2.5170785892807555,
      "grad_norm": 0.004736774135380983,
      "learning_rate": 0.0005382716049382716,
      "loss": 0.6555,
      "step": 1133
    },
    {
      "epoch": 2.519300194390447,
      "grad_norm": 0.003248099237680435,
      "learning_rate": 0.0005358024691358024,
      "loss": 0.5267,
      "step": 1134
    },
    {
      "epoch": 2.521521799500139,
      "grad_norm": 0.0030893636867403984,
      "learning_rate": 0.0005333333333333334,
      "loss": 0.5392,
      "step": 1135
    },
    {
      "epoch": 2.5237434046098306,
      "grad_norm": 0.0039703804068267345,
      "learning_rate": 0.0005308641975308642,
      "loss": 0.5964,
      "step": 1136
    },
    {
      "epoch": 2.5259650097195223,
      "grad_norm": 0.0026025359984487295,
      "learning_rate": 0.000528395061728395,
      "loss": 0.424,
      "step": 1137
    },
    {
      "epoch": 2.528186614829214,
      "grad_norm": 0.002934755990281701,
      "learning_rate": 0.000525925925925926,
      "loss": 0.5888,
      "step": 1138
    },
    {
      "epoch": 2.5304082199389057,
      "grad_norm": 0.004901326727122068,
      "learning_rate": 0.0005234567901234568,
      "loss": 0.6006,
      "step": 1139
    },
    {
      "epoch": 2.5326298250485975,
      "grad_norm": 0.00381462718360126,
      "learning_rate": 0.0005209876543209877,
      "loss": 0.5134,
      "step": 1140
    },
    {
      "epoch": 2.534851430158289,
      "grad_norm": 0.00261781201697886,
      "learning_rate": 0.0005185185185185185,
      "loss": 0.606,
      "step": 1141
    },
    {
      "epoch": 2.537073035267981,
      "grad_norm": 0.0029276409186422825,
      "learning_rate": 0.0005160493827160495,
      "loss": 0.5911,
      "step": 1142
    },
    {
      "epoch": 2.5392946403776726,
      "grad_norm": 0.0036239551845937967,
      "learning_rate": 0.0005135802469135803,
      "loss": 0.6584,
      "step": 1143
    },
    {
      "epoch": 2.5415162454873648,
      "grad_norm": 0.0035461464431136847,
      "learning_rate": 0.0005111111111111112,
      "loss": 0.4826,
      "step": 1144
    },
    {
      "epoch": 2.5437378505970565,
      "grad_norm": 0.0031179594807326794,
      "learning_rate": 0.000508641975308642,
      "loss": 0.6802,
      "step": 1145
    },
    {
      "epoch": 2.545959455706748,
      "grad_norm": 0.004939055535942316,
      "learning_rate": 0.0005061728395061728,
      "loss": 0.6728,
      "step": 1146
    },
    {
      "epoch": 2.54818106081644,
      "grad_norm": 0.0032385385129600763,
      "learning_rate": 0.0005037037037037037,
      "loss": 0.5022,
      "step": 1147
    },
    {
      "epoch": 2.5504026659261316,
      "grad_norm": 0.0034658366348594427,
      "learning_rate": 0.0005012345679012345,
      "loss": 0.6337,
      "step": 1148
    },
    {
      "epoch": 2.5526242710358233,
      "grad_norm": 0.003818860510364175,
      "learning_rate": 0.0004987654320987654,
      "loss": 0.5069,
      "step": 1149
    },
    {
      "epoch": 2.554845876145515,
      "grad_norm": 0.0030890421476215124,
      "learning_rate": 0.0004962962962962963,
      "loss": 0.5816,
      "step": 1150
    },
    {
      "epoch": 2.5570674812552068,
      "grad_norm": 0.004149436019361019,
      "learning_rate": 0.0004938271604938272,
      "loss": 0.6642,
      "step": 1151
    },
    {
      "epoch": 2.5592890863648985,
      "grad_norm": 0.00414425740018487,
      "learning_rate": 0.000491358024691358,
      "loss": 0.6913,
      "step": 1152
    },
    {
      "epoch": 2.5615106914745907,
      "grad_norm": 0.003239423269405961,
      "learning_rate": 0.000488888888888889,
      "loss": 0.5676,
      "step": 1153
    },
    {
      "epoch": 2.5637322965842824,
      "grad_norm": 0.003647661069408059,
      "learning_rate": 0.00048641975308641976,
      "loss": 0.4489,
      "step": 1154
    },
    {
      "epoch": 2.565953901693974,
      "grad_norm": 0.006356607656925917,
      "learning_rate": 0.0004839506172839506,
      "loss": 0.4973,
      "step": 1155
    },
    {
      "epoch": 2.568175506803666,
      "grad_norm": 0.0033991627860814333,
      "learning_rate": 0.00048148148148148144,
      "loss": 0.8475,
      "step": 1156
    },
    {
      "epoch": 2.5703971119133575,
      "grad_norm": 0.00468791788443923,
      "learning_rate": 0.0004790123456790124,
      "loss": 0.6448,
      "step": 1157
    },
    {
      "epoch": 2.5726187170230492,
      "grad_norm": 0.0044874101877212524,
      "learning_rate": 0.00047654320987654324,
      "loss": 0.5421,
      "step": 1158
    },
    {
      "epoch": 2.574840322132741,
      "grad_norm": 0.0032975287176668644,
      "learning_rate": 0.0004740740740740741,
      "loss": 0.5827,
      "step": 1159
    },
    {
      "epoch": 2.5770619272424327,
      "grad_norm": 0.003136139363050461,
      "learning_rate": 0.0004716049382716049,
      "loss": 0.5586,
      "step": 1160
    },
    {
      "epoch": 2.5792835323521244,
      "grad_norm": 0.002414422109723091,
      "learning_rate": 0.0004691358024691358,
      "loss": 0.8068,
      "step": 1161
    },
    {
      "epoch": 2.581505137461816,
      "grad_norm": 0.003160569118335843,
      "learning_rate": 0.00046666666666666666,
      "loss": 0.6286,
      "step": 1162
    },
    {
      "epoch": 2.583726742571508,
      "grad_norm": 0.0029906497802585363,
      "learning_rate": 0.0004641975308641975,
      "loss": 0.644,
      "step": 1163
    },
    {
      "epoch": 2.5859483476811995,
      "grad_norm": 0.0037106021773070097,
      "learning_rate": 0.00046172839506172835,
      "loss": 0.712,
      "step": 1164
    },
    {
      "epoch": 2.5881699527908912,
      "grad_norm": 0.004012922756373882,
      "learning_rate": 0.0004592592592592593,
      "loss": 0.4536,
      "step": 1165
    },
    {
      "epoch": 2.590391557900583,
      "grad_norm": 0.0037863117177039385,
      "learning_rate": 0.00045679012345679014,
      "loss": 0.6261,
      "step": 1166
    },
    {
      "epoch": 2.5926131630102747,
      "grad_norm": 0.003073723753914237,
      "learning_rate": 0.000454320987654321,
      "loss": 0.7629,
      "step": 1167
    },
    {
      "epoch": 2.594834768119967,
      "grad_norm": 0.002828410593792796,
      "learning_rate": 0.0004518518518518519,
      "loss": 0.64,
      "step": 1168
    },
    {
      "epoch": 2.5970563732296585,
      "grad_norm": 0.0034212307073175907,
      "learning_rate": 0.0004493827160493827,
      "loss": 0.6729,
      "step": 1169
    },
    {
      "epoch": 2.5992779783393503,
      "grad_norm": 0.004914992954581976,
      "learning_rate": 0.00044691358024691357,
      "loss": 0.5882,
      "step": 1170
    },
    {
      "epoch": 2.601499583449042,
      "grad_norm": 0.003478400409221649,
      "learning_rate": 0.0004444444444444444,
      "loss": 0.5794,
      "step": 1171
    },
    {
      "epoch": 2.6037211885587337,
      "grad_norm": 0.002796370768919587,
      "learning_rate": 0.00044197530864197536,
      "loss": 0.7561,
      "step": 1172
    },
    {
      "epoch": 2.6059427936684254,
      "grad_norm": 0.004800213035196066,
      "learning_rate": 0.0004395061728395062,
      "loss": 0.5332,
      "step": 1173
    },
    {
      "epoch": 2.608164398778117,
      "grad_norm": 0.003488753689453006,
      "learning_rate": 0.00043703703703703705,
      "loss": 0.6473,
      "step": 1174
    },
    {
      "epoch": 2.610386003887809,
      "grad_norm": 0.0034767366014420986,
      "learning_rate": 0.0004345679012345679,
      "loss": 0.5521,
      "step": 1175
    },
    {
      "epoch": 2.6126076089975006,
      "grad_norm": 0.004232069011777639,
      "learning_rate": 0.0004320987654320988,
      "loss": 0.4903,
      "step": 1176
    },
    {
      "epoch": 2.6148292141071927,
      "grad_norm": 0.00912979245185852,
      "learning_rate": 0.00042962962962962963,
      "loss": 0.6654,
      "step": 1177
    },
    {
      "epoch": 2.6170508192168844,
      "grad_norm": 0.0028827181085944176,
      "learning_rate": 0.0004271604938271605,
      "loss": 0.4747,
      "step": 1178
    },
    {
      "epoch": 2.619272424326576,
      "grad_norm": 0.003413770580664277,
      "learning_rate": 0.0004246913580246913,
      "loss": 0.6909,
      "step": 1179
    },
    {
      "epoch": 2.621494029436268,
      "grad_norm": 0.002472649561241269,
      "learning_rate": 0.00042222222222222227,
      "loss": 0.6341,
      "step": 1180
    },
    {
      "epoch": 2.6237156345459596,
      "grad_norm": 0.00421160738915205,
      "learning_rate": 0.0004197530864197531,
      "loss": 0.5952,
      "step": 1181
    },
    {
      "epoch": 2.6259372396556513,
      "grad_norm": 0.00468397606164217,
      "learning_rate": 0.00041728395061728396,
      "loss": 0.5865,
      "step": 1182
    },
    {
      "epoch": 2.628158844765343,
      "grad_norm": 0.003892808686941862,
      "learning_rate": 0.0004148148148148148,
      "loss": 0.6862,
      "step": 1183
    },
    {
      "epoch": 2.6303804498750347,
      "grad_norm": 0.0030200849287211895,
      "learning_rate": 0.0004123456790123457,
      "loss": 0.3986,
      "step": 1184
    },
    {
      "epoch": 2.6326020549847264,
      "grad_norm": 0.0042160493321716785,
      "learning_rate": 0.00040987654320987654,
      "loss": 0.5801,
      "step": 1185
    },
    {
      "epoch": 2.634823660094418,
      "grad_norm": 0.006309780292212963,
      "learning_rate": 0.0004074074074074074,
      "loss": 0.5234,
      "step": 1186
    },
    {
      "epoch": 2.63704526520411,
      "grad_norm": 0.0029553258791565895,
      "learning_rate": 0.00040493827160493833,
      "loss": 0.5774,
      "step": 1187
    },
    {
      "epoch": 2.6392668703138016,
      "grad_norm": 0.005045739468187094,
      "learning_rate": 0.0004024691358024692,
      "loss": 0.6001,
      "step": 1188
    },
    {
      "epoch": 2.6414884754234933,
      "grad_norm": 0.0071875047869980335,
      "learning_rate": 0.0004,
      "loss": 0.6371,
      "step": 1189
    },
    {
      "epoch": 2.643710080533185,
      "grad_norm": 0.003521390026435256,
      "learning_rate": 0.00039753086419753086,
      "loss": 0.6738,
      "step": 1190
    },
    {
      "epoch": 2.6459316856428767,
      "grad_norm": 0.0030773284379392862,
      "learning_rate": 0.00039506172839506176,
      "loss": 0.5635,
      "step": 1191
    },
    {
      "epoch": 2.648153290752569,
      "grad_norm": 0.00331405783072114,
      "learning_rate": 0.0003925925925925926,
      "loss": 0.6265,
      "step": 1192
    },
    {
      "epoch": 2.6503748958622606,
      "grad_norm": 0.004428196232765913,
      "learning_rate": 0.00039012345679012345,
      "loss": 0.6565,
      "step": 1193
    },
    {
      "epoch": 2.6525965009719523,
      "grad_norm": 0.0028734297957271338,
      "learning_rate": 0.0003876543209876543,
      "loss": 0.4557,
      "step": 1194
    },
    {
      "epoch": 2.654818106081644,
      "grad_norm": 0.0032686248887330294,
      "learning_rate": 0.00038518518518518524,
      "loss": 0.5205,
      "step": 1195
    },
    {
      "epoch": 2.6570397111913358,
      "grad_norm": 0.0034671644680202007,
      "learning_rate": 0.0003827160493827161,
      "loss": 0.7389,
      "step": 1196
    },
    {
      "epoch": 2.6592613163010275,
      "grad_norm": 0.0034542689099907875,
      "learning_rate": 0.0003802469135802469,
      "loss": 0.7012,
      "step": 1197
    },
    {
      "epoch": 2.661482921410719,
      "grad_norm": 0.00446385657414794,
      "learning_rate": 0.00037777777777777777,
      "loss": 0.6022,
      "step": 1198
    },
    {
      "epoch": 2.663704526520411,
      "grad_norm": 0.0034254337660968304,
      "learning_rate": 0.00037530864197530867,
      "loss": 0.6535,
      "step": 1199
    },
    {
      "epoch": 2.6659261316301026,
      "grad_norm": 0.003482289845123887,
      "learning_rate": 0.0003728395061728395,
      "loss": 0.4263,
      "step": 1200
    },
    {
      "epoch": 2.6681477367397948,
      "grad_norm": 0.010489952750504017,
      "learning_rate": 0.00037037037037037035,
      "loss": 0.6682,
      "step": 1201
    },
    {
      "epoch": 2.6703693418494865,
      "grad_norm": 0.008210372179746628,
      "learning_rate": 0.00036790123456790125,
      "loss": 0.4274,
      "step": 1202
    },
    {
      "epoch": 2.672590946959178,
      "grad_norm": 0.003869694657623768,
      "learning_rate": 0.00036543209876543215,
      "loss": 0.5503,
      "step": 1203
    },
    {
      "epoch": 2.67481255206887,
      "grad_norm": 0.00279775052331388,
      "learning_rate": 0.000362962962962963,
      "loss": 0.5255,
      "step": 1204
    },
    {
      "epoch": 2.6770341571785616,
      "grad_norm": 0.00240530539304018,
      "learning_rate": 0.00036049382716049383,
      "loss": 0.5576,
      "step": 1205
    },
    {
      "epoch": 2.6792557622882534,
      "grad_norm": 0.003824488027021289,
      "learning_rate": 0.0003580246913580247,
      "loss": 0.6877,
      "step": 1206
    },
    {
      "epoch": 2.681477367397945,
      "grad_norm": 0.003564296755939722,
      "learning_rate": 0.00035555555555555557,
      "loss": 0.6427,
      "step": 1207
    },
    {
      "epoch": 2.683698972507637,
      "grad_norm": 0.003400566754862666,
      "learning_rate": 0.0003530864197530864,
      "loss": 0.5636,
      "step": 1208
    },
    {
      "epoch": 2.6859205776173285,
      "grad_norm": 0.005312902387231588,
      "learning_rate": 0.0003506172839506173,
      "loss": 0.7443,
      "step": 1209
    },
    {
      "epoch": 2.68814218272702,
      "grad_norm": 0.003194639924913645,
      "learning_rate": 0.00034814814814814816,
      "loss": 0.5213,
      "step": 1210
    },
    {
      "epoch": 2.690363787836712,
      "grad_norm": 0.003232366871088743,
      "learning_rate": 0.00034567901234567905,
      "loss": 0.558,
      "step": 1211
    },
    {
      "epoch": 2.6925853929464036,
      "grad_norm": 0.0031920920591801405,
      "learning_rate": 0.0003432098765432099,
      "loss": 0.545,
      "step": 1212
    },
    {
      "epoch": 2.6948069980560954,
      "grad_norm": 0.011023471131920815,
      "learning_rate": 0.00034074074074074074,
      "loss": 0.6454,
      "step": 1213
    },
    {
      "epoch": 2.697028603165787,
      "grad_norm": 0.0028811749070882797,
      "learning_rate": 0.0003382716049382716,
      "loss": 0.5344,
      "step": 1214
    },
    {
      "epoch": 2.699250208275479,
      "grad_norm": 0.0036712063010782003,
      "learning_rate": 0.0003358024691358025,
      "loss": 0.6927,
      "step": 1215
    },
    {
      "epoch": 2.701471813385171,
      "grad_norm": 0.0031385060865432024,
      "learning_rate": 0.0003333333333333333,
      "loss": 0.5934,
      "step": 1216
    },
    {
      "epoch": 2.7036934184948627,
      "grad_norm": 0.0062264325097203255,
      "learning_rate": 0.0003308641975308642,
      "loss": 0.5604,
      "step": 1217
    },
    {
      "epoch": 2.7059150236045544,
      "grad_norm": 0.007265784312039614,
      "learning_rate": 0.00032839506172839506,
      "loss": 0.6847,
      "step": 1218
    },
    {
      "epoch": 2.708136628714246,
      "grad_norm": 0.003674163017421961,
      "learning_rate": 0.0003259259259259259,
      "loss": 0.6359,
      "step": 1219
    },
    {
      "epoch": 2.710358233823938,
      "grad_norm": 0.003143347566947341,
      "learning_rate": 0.0003234567901234568,
      "loss": 0.6139,
      "step": 1220
    },
    {
      "epoch": 2.7125798389336295,
      "grad_norm": 0.0036580993328243494,
      "learning_rate": 0.00032098765432098765,
      "loss": 0.5035,
      "step": 1221
    },
    {
      "epoch": 2.7148014440433212,
      "grad_norm": 0.0032888823188841343,
      "learning_rate": 0.00031851851851851854,
      "loss": 0.6166,
      "step": 1222
    },
    {
      "epoch": 2.717023049153013,
      "grad_norm": 0.0031141925137490034,
      "learning_rate": 0.0003160493827160494,
      "loss": 0.6041,
      "step": 1223
    },
    {
      "epoch": 2.7192446542627047,
      "grad_norm": 0.003442190820351243,
      "learning_rate": 0.0003135802469135803,
      "loss": 0.5397,
      "step": 1224
    },
    {
      "epoch": 2.7214662593723964,
      "grad_norm": 0.004747328814119101,
      "learning_rate": 0.0003111111111111111,
      "loss": 0.5768,
      "step": 1225
    },
    {
      "epoch": 2.7236878644820885,
      "grad_norm": 0.0025287456810474396,
      "learning_rate": 0.00030864197530864197,
      "loss": 0.5381,
      "step": 1226
    },
    {
      "epoch": 2.7259094695917803,
      "grad_norm": 0.007512194570153952,
      "learning_rate": 0.0003061728395061728,
      "loss": 0.628,
      "step": 1227
    },
    {
      "epoch": 2.728131074701472,
      "grad_norm": 0.004234898369759321,
      "learning_rate": 0.0003037037037037037,
      "loss": 0.5636,
      "step": 1228
    },
    {
      "epoch": 2.7303526798111637,
      "grad_norm": 0.003465744899585843,
      "learning_rate": 0.00030123456790123455,
      "loss": 0.5558,
      "step": 1229
    },
    {
      "epoch": 2.7325742849208554,
      "grad_norm": 0.014260316267609596,
      "learning_rate": 0.00029876543209876545,
      "loss": 0.6407,
      "step": 1230
    },
    {
      "epoch": 2.734795890030547,
      "grad_norm": 0.0033130717929452658,
      "learning_rate": 0.0002962962962962963,
      "loss": 0.6253,
      "step": 1231
    },
    {
      "epoch": 2.737017495140239,
      "grad_norm": 0.010730063542723656,
      "learning_rate": 0.0002938271604938272,
      "loss": 0.5129,
      "step": 1232
    },
    {
      "epoch": 2.7392391002499306,
      "grad_norm": 0.0033962007146328688,
      "learning_rate": 0.00029135802469135803,
      "loss": 0.4089,
      "step": 1233
    },
    {
      "epoch": 2.7414607053596223,
      "grad_norm": 0.0028743180446326733,
      "learning_rate": 0.0002888888888888889,
      "loss": 0.6482,
      "step": 1234
    },
    {
      "epoch": 2.743682310469314,
      "grad_norm": 0.0036041648127138615,
      "learning_rate": 0.00028641975308641977,
      "loss": 0.4847,
      "step": 1235
    },
    {
      "epoch": 2.7459039155790057,
      "grad_norm": 0.0035236182156950235,
      "learning_rate": 0.0002839506172839506,
      "loss": 0.5779,
      "step": 1236
    },
    {
      "epoch": 2.7481255206886974,
      "grad_norm": 0.0027155387215316296,
      "learning_rate": 0.0002814814814814815,
      "loss": 0.6672,
      "step": 1237
    },
    {
      "epoch": 2.750347125798389,
      "grad_norm": 0.003950577694922686,
      "learning_rate": 0.00027901234567901236,
      "loss": 0.5514,
      "step": 1238
    },
    {
      "epoch": 2.752568730908081,
      "grad_norm": 0.0031434199772775173,
      "learning_rate": 0.00027654320987654325,
      "loss": 0.4795,
      "step": 1239
    },
    {
      "epoch": 2.7547903360177726,
      "grad_norm": 0.01073761098086834,
      "learning_rate": 0.0002740740740740741,
      "loss": 0.5087,
      "step": 1240
    },
    {
      "epoch": 2.7570119411274647,
      "grad_norm": 0.0029550394974648952,
      "learning_rate": 0.00027160493827160494,
      "loss": 0.7197,
      "step": 1241
    },
    {
      "epoch": 2.7592335462371564,
      "grad_norm": 0.002490705344825983,
      "learning_rate": 0.0002691358024691358,
      "loss": 0.5334,
      "step": 1242
    },
    {
      "epoch": 2.761455151346848,
      "grad_norm": 0.0038245634641498327,
      "learning_rate": 0.0002666666666666667,
      "loss": 0.6461,
      "step": 1243
    },
    {
      "epoch": 2.76367675645654,
      "grad_norm": 0.0034504050854593515,
      "learning_rate": 0.0002641975308641975,
      "loss": 0.5505,
      "step": 1244
    },
    {
      "epoch": 2.7658983615662316,
      "grad_norm": 0.003910180181264877,
      "learning_rate": 0.0002617283950617284,
      "loss": 0.4494,
      "step": 1245
    },
    {
      "epoch": 2.7681199666759233,
      "grad_norm": 0.00400611711665988,
      "learning_rate": 0.00025925925925925926,
      "loss": 0.4137,
      "step": 1246
    },
    {
      "epoch": 2.770341571785615,
      "grad_norm": 0.004063760861754417,
      "learning_rate": 0.00025679012345679016,
      "loss": 0.5035,
      "step": 1247
    },
    {
      "epoch": 2.7725631768953067,
      "grad_norm": 0.003407078795135021,
      "learning_rate": 0.000254320987654321,
      "loss": 0.7291,
      "step": 1248
    },
    {
      "epoch": 2.7747847820049985,
      "grad_norm": 0.006849862169474363,
      "learning_rate": 0.00025185185185185185,
      "loss": 0.6297,
      "step": 1249
    },
    {
      "epoch": 2.7770063871146906,
      "grad_norm": 0.0041533177718520164,
      "learning_rate": 0.0002493827160493827,
      "loss": 0.6171,
      "step": 1250
    },
    {
      "epoch": 2.7792279922243823,
      "grad_norm": 0.003316490212455392,
      "learning_rate": 0.0002469135802469136,
      "loss": 0.6766,
      "step": 1251
    },
    {
      "epoch": 2.781449597334074,
      "grad_norm": 0.002814968815073371,
      "learning_rate": 0.0002444444444444445,
      "loss": 0.6536,
      "step": 1252
    },
    {
      "epoch": 2.7836712024437658,
      "grad_norm": 0.003848499385640025,
      "learning_rate": 0.0002419753086419753,
      "loss": 0.6443,
      "step": 1253
    },
    {
      "epoch": 2.7858928075534575,
      "grad_norm": 0.003510064445436001,
      "learning_rate": 0.0002395061728395062,
      "loss": 0.6888,
      "step": 1254
    },
    {
      "epoch": 2.788114412663149,
      "grad_norm": 0.00316590815782547,
      "learning_rate": 0.00023703703703703704,
      "loss": 0.5631,
      "step": 1255
    },
    {
      "epoch": 2.790336017772841,
      "grad_norm": 0.004097390919923782,
      "learning_rate": 0.0002345679012345679,
      "loss": 0.5161,
      "step": 1256
    },
    {
      "epoch": 2.7925576228825326,
      "grad_norm": 0.005050000734627247,
      "learning_rate": 0.00023209876543209875,
      "loss": 0.5353,
      "step": 1257
    },
    {
      "epoch": 2.7947792279922243,
      "grad_norm": 0.002930557122454047,
      "learning_rate": 0.00022962962962962965,
      "loss": 0.516,
      "step": 1258
    },
    {
      "epoch": 2.797000833101916,
      "grad_norm": 0.0038380646146833897,
      "learning_rate": 0.0002271604938271605,
      "loss": 0.6113,
      "step": 1259
    },
    {
      "epoch": 2.7992224382116078,
      "grad_norm": 0.004944332875311375,
      "learning_rate": 0.00022469135802469136,
      "loss": 0.6723,
      "step": 1260
    },
    {
      "epoch": 2.8014440433212995,
      "grad_norm": 0.00393567094579339,
      "learning_rate": 0.0002222222222222222,
      "loss": 0.616,
      "step": 1261
    },
    {
      "epoch": 2.803665648430991,
      "grad_norm": 0.0032372584100812674,
      "learning_rate": 0.0002197530864197531,
      "loss": 0.6801,
      "step": 1262
    },
    {
      "epoch": 2.805887253540683,
      "grad_norm": 0.005238884594291449,
      "learning_rate": 0.00021728395061728395,
      "loss": 0.5011,
      "step": 1263
    },
    {
      "epoch": 2.8081088586503746,
      "grad_norm": 0.002907345537096262,
      "learning_rate": 0.00021481481481481482,
      "loss": 0.7613,
      "step": 1264
    },
    {
      "epoch": 2.810330463760067,
      "grad_norm": 0.004339124076068401,
      "learning_rate": 0.00021234567901234566,
      "loss": 0.6434,
      "step": 1265
    },
    {
      "epoch": 2.8125520688697585,
      "grad_norm": 0.005125504918396473,
      "learning_rate": 0.00020987654320987656,
      "loss": 0.6791,
      "step": 1266
    },
    {
      "epoch": 2.81477367397945,
      "grad_norm": 0.0028487134259194136,
      "learning_rate": 0.0002074074074074074,
      "loss": 0.6477,
      "step": 1267
    },
    {
      "epoch": 2.816995279089142,
      "grad_norm": 0.0031643547117710114,
      "learning_rate": 0.00020493827160493827,
      "loss": 0.5613,
      "step": 1268
    },
    {
      "epoch": 2.8192168841988337,
      "grad_norm": 0.005931346211582422,
      "learning_rate": 0.00020246913580246917,
      "loss": 0.7626,
      "step": 1269
    },
    {
      "epoch": 2.8214384893085254,
      "grad_norm": 0.004396750126034021,
      "learning_rate": 0.0002,
      "loss": 0.5373,
      "step": 1270
    },
    {
      "epoch": 2.823660094418217,
      "grad_norm": 0.002597388345748186,
      "learning_rate": 0.00019753086419753088,
      "loss": 0.6037,
      "step": 1271
    },
    {
      "epoch": 2.825881699527909,
      "grad_norm": 0.0033694864250719547,
      "learning_rate": 0.00019506172839506172,
      "loss": 0.4563,
      "step": 1272
    },
    {
      "epoch": 2.8281033046376005,
      "grad_norm": 0.0034194274339824915,
      "learning_rate": 0.00019259259259259262,
      "loss": 0.5773,
      "step": 1273
    },
    {
      "epoch": 2.8303249097472927,
      "grad_norm": 0.003407923271879554,
      "learning_rate": 0.00019012345679012346,
      "loss": 0.4458,
      "step": 1274
    },
    {
      "epoch": 2.8325465148569844,
      "grad_norm": 0.002831199672073126,
      "learning_rate": 0.00018765432098765433,
      "loss": 0.5024,
      "step": 1275
    },
    {
      "epoch": 2.834768119966676,
      "grad_norm": 0.00448482995852828,
      "learning_rate": 0.00018518518518518518,
      "loss": 0.534,
      "step": 1276
    },
    {
      "epoch": 2.836989725076368,
      "grad_norm": 0.003159653628244996,
      "learning_rate": 0.00018271604938271607,
      "loss": 0.6053,
      "step": 1277
    },
    {
      "epoch": 2.8392113301860595,
      "grad_norm": 0.003079737536609173,
      "learning_rate": 0.00018024691358024692,
      "loss": 0.7034,
      "step": 1278
    },
    {
      "epoch": 2.8414329352957512,
      "grad_norm": 0.003197902347892523,
      "learning_rate": 0.00017777777777777779,
      "loss": 0.4896,
      "step": 1279
    },
    {
      "epoch": 2.843654540405443,
      "grad_norm": 0.0034542051143944263,
      "learning_rate": 0.00017530864197530866,
      "loss": 0.5431,
      "step": 1280
    },
    {
      "epoch": 2.8458761455151347,
      "grad_norm": 0.0029420393984764814,
      "learning_rate": 0.00017283950617283953,
      "loss": 0.6649,
      "step": 1281
    },
    {
      "epoch": 2.8480977506248264,
      "grad_norm": 0.004599207080900669,
      "learning_rate": 0.00017037037037037037,
      "loss": 0.4534,
      "step": 1282
    },
    {
      "epoch": 2.850319355734518,
      "grad_norm": 0.0031824030447751284,
      "learning_rate": 0.00016790123456790124,
      "loss": 0.4879,
      "step": 1283
    },
    {
      "epoch": 2.85254096084421,
      "grad_norm": 0.005857157986611128,
      "learning_rate": 0.0001654320987654321,
      "loss": 0.5966,
      "step": 1284
    },
    {
      "epoch": 2.8547625659539015,
      "grad_norm": 0.004492443520575762,
      "learning_rate": 0.00016296296296296295,
      "loss": 0.5266,
      "step": 1285
    },
    {
      "epoch": 2.8569841710635933,
      "grad_norm": 0.004190143197774887,
      "learning_rate": 0.00016049382716049382,
      "loss": 0.6263,
      "step": 1286
    },
    {
      "epoch": 2.859205776173285,
      "grad_norm": 0.004138167481869459,
      "learning_rate": 0.0001580246913580247,
      "loss": 0.6236,
      "step": 1287
    },
    {
      "epoch": 2.8614273812829767,
      "grad_norm": 0.002312315395101905,
      "learning_rate": 0.00015555555555555556,
      "loss": 0.6016,
      "step": 1288
    },
    {
      "epoch": 2.863648986392669,
      "grad_norm": 0.003110610879957676,
      "learning_rate": 0.0001530864197530864,
      "loss": 0.6744,
      "step": 1289
    },
    {
      "epoch": 2.8658705915023606,
      "grad_norm": 0.0033535826951265335,
      "learning_rate": 0.00015061728395061728,
      "loss": 0.5006,
      "step": 1290
    },
    {
      "epoch": 2.8680921966120523,
      "grad_norm": 0.0042699831537902355,
      "learning_rate": 0.00014814814814814815,
      "loss": 0.5889,
      "step": 1291
    },
    {
      "epoch": 2.870313801721744,
      "grad_norm": 0.0033779111690819263,
      "learning_rate": 0.00014567901234567902,
      "loss": 0.6792,
      "step": 1292
    },
    {
      "epoch": 2.8725354068314357,
      "grad_norm": 0.0031225201673805714,
      "learning_rate": 0.00014320987654320989,
      "loss": 0.7333,
      "step": 1293
    },
    {
      "epoch": 2.8747570119411274,
      "grad_norm": 0.005412708502262831,
      "learning_rate": 0.00014074074074074076,
      "loss": 0.8419,
      "step": 1294
    },
    {
      "epoch": 2.876978617050819,
      "grad_norm": 0.003851811634376645,
      "learning_rate": 0.00013827160493827163,
      "loss": 0.5996,
      "step": 1295
    },
    {
      "epoch": 2.879200222160511,
      "grad_norm": 0.0034581879153847694,
      "learning_rate": 0.00013580246913580247,
      "loss": 0.4841,
      "step": 1296
    },
    {
      "epoch": 2.8814218272702026,
      "grad_norm": 0.003359030233696103,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.5553,
      "step": 1297
    },
    {
      "epoch": 2.8836434323798947,
      "grad_norm": 0.0034187238197773695,
      "learning_rate": 0.0001308641975308642,
      "loss": 0.5145,
      "step": 1298
    },
    {
      "epoch": 2.8858650374895864,
      "grad_norm": 0.004329441115260124,
      "learning_rate": 0.00012839506172839508,
      "loss": 0.5466,
      "step": 1299
    },
    {
      "epoch": 2.888086642599278,
      "grad_norm": 0.002967827720567584,
      "learning_rate": 0.00012592592592592592,
      "loss": 0.5053,
      "step": 1300
    },
    {
      "epoch": 2.89030824770897,
      "grad_norm": 0.004363194573670626,
      "learning_rate": 0.0001234567901234568,
      "loss": 0.8809,
      "step": 1301
    },
    {
      "epoch": 2.8925298528186616,
      "grad_norm": 0.0066121588461101055,
      "learning_rate": 0.00012098765432098765,
      "loss": 0.5158,
      "step": 1302
    },
    {
      "epoch": 2.8947514579283533,
      "grad_norm": 0.0031841997988522053,
      "learning_rate": 0.00011851851851851852,
      "loss": 0.4624,
      "step": 1303
    },
    {
      "epoch": 2.896973063038045,
      "grad_norm": 0.002588280476629734,
      "learning_rate": 0.00011604938271604938,
      "loss": 0.4071,
      "step": 1304
    },
    {
      "epoch": 2.8991946681477367,
      "grad_norm": 0.003058835631236434,
      "learning_rate": 0.00011358024691358025,
      "loss": 0.5446,
      "step": 1305
    },
    {
      "epoch": 2.9014162732574285,
      "grad_norm": 0.004084974527359009,
      "learning_rate": 0.0001111111111111111,
      "loss": 0.5341,
      "step": 1306
    },
    {
      "epoch": 2.90363787836712,
      "grad_norm": 0.002559412270784378,
      "learning_rate": 0.00010864197530864197,
      "loss": 0.5326,
      "step": 1307
    },
    {
      "epoch": 2.905859483476812,
      "grad_norm": 0.004436027258634567,
      "learning_rate": 0.00010617283950617283,
      "loss": 0.6186,
      "step": 1308
    },
    {
      "epoch": 2.9080810885865036,
      "grad_norm": 0.005317239556461573,
      "learning_rate": 0.0001037037037037037,
      "loss": 0.6755,
      "step": 1309
    },
    {
      "epoch": 2.9103026936961953,
      "grad_norm": 0.002583589870482683,
      "learning_rate": 0.00010123456790123458,
      "loss": 0.5533,
      "step": 1310
    },
    {
      "epoch": 2.912524298805887,
      "grad_norm": 0.0035740782041102648,
      "learning_rate": 9.876543209876544e-05,
      "loss": 0.4858,
      "step": 1311
    },
    {
      "epoch": 2.9147459039155788,
      "grad_norm": 0.002853245474398136,
      "learning_rate": 9.629629629629631e-05,
      "loss": 0.5962,
      "step": 1312
    },
    {
      "epoch": 2.916967509025271,
      "grad_norm": 0.0054124994203448296,
      "learning_rate": 9.382716049382717e-05,
      "loss": 0.6357,
      "step": 1313
    },
    {
      "epoch": 2.9191891141349626,
      "grad_norm": 0.003988190088421106,
      "learning_rate": 9.135802469135804e-05,
      "loss": 0.758,
      "step": 1314
    },
    {
      "epoch": 2.9214107192446543,
      "grad_norm": 0.008741138502955437,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.5623,
      "step": 1315
    },
    {
      "epoch": 2.923632324354346,
      "grad_norm": 0.003952341619879007,
      "learning_rate": 8.641975308641976e-05,
      "loss": 0.4589,
      "step": 1316
    },
    {
      "epoch": 2.9258539294640378,
      "grad_norm": 0.0029261866584420204,
      "learning_rate": 8.395061728395062e-05,
      "loss": 0.5325,
      "step": 1317
    },
    {
      "epoch": 2.9280755345737295,
      "grad_norm": 0.0040866415947675705,
      "learning_rate": 8.148148148148148e-05,
      "loss": 0.6314,
      "step": 1318
    },
    {
      "epoch": 2.930297139683421,
      "grad_norm": 0.003230329370126128,
      "learning_rate": 7.901234567901235e-05,
      "loss": 0.6039,
      "step": 1319
    },
    {
      "epoch": 2.932518744793113,
      "grad_norm": 0.002752997912466526,
      "learning_rate": 7.65432098765432e-05,
      "loss": 0.5133,
      "step": 1320
    },
    {
      "epoch": 2.9347403499028046,
      "grad_norm": 0.003844594117254019,
      "learning_rate": 7.407407407407407e-05,
      "loss": 0.591,
      "step": 1321
    },
    {
      "epoch": 2.936961955012497,
      "grad_norm": 0.0021649012342095375,
      "learning_rate": 7.160493827160494e-05,
      "loss": 0.4656,
      "step": 1322
    },
    {
      "epoch": 2.9391835601221885,
      "grad_norm": 0.004816529806703329,
      "learning_rate": 6.913580246913581e-05,
      "loss": 0.5848,
      "step": 1323
    },
    {
      "epoch": 2.9414051652318802,
      "grad_norm": 0.0032435518223792315,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.49,
      "step": 1324
    },
    {
      "epoch": 2.943626770341572,
      "grad_norm": 0.004449759144335985,
      "learning_rate": 6.419753086419754e-05,
      "loss": 0.6067,
      "step": 1325
    },
    {
      "epoch": 2.9458483754512637,
      "grad_norm": 0.004610596224665642,
      "learning_rate": 6.17283950617284e-05,
      "loss": 0.6566,
      "step": 1326
    },
    {
      "epoch": 2.9480699805609554,
      "grad_norm": 0.004660632461309433,
      "learning_rate": 5.925925925925926e-05,
      "loss": 0.5043,
      "step": 1327
    },
    {
      "epoch": 2.950291585670647,
      "grad_norm": 0.002484169788658619,
      "learning_rate": 5.679012345679012e-05,
      "loss": 0.5333,
      "step": 1328
    },
    {
      "epoch": 2.952513190780339,
      "grad_norm": 0.004068448208272457,
      "learning_rate": 5.4320987654320986e-05,
      "loss": 0.6013,
      "step": 1329
    },
    {
      "epoch": 2.9547347958900305,
      "grad_norm": 0.004336718935519457,
      "learning_rate": 5.185185185185185e-05,
      "loss": 0.482,
      "step": 1330
    },
    {
      "epoch": 2.9569564009997222,
      "grad_norm": 0.0036426191218197346,
      "learning_rate": 4.938271604938272e-05,
      "loss": 0.6332,
      "step": 1331
    },
    {
      "epoch": 2.959178006109414,
      "grad_norm": 0.0028451422695070505,
      "learning_rate": 4.691358024691358e-05,
      "loss": 0.6019,
      "step": 1332
    },
    {
      "epoch": 2.9613996112191057,
      "grad_norm": 0.0033803503029048443,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.6632,
      "step": 1333
    },
    {
      "epoch": 2.9636212163287974,
      "grad_norm": 0.0022810918744653463,
      "learning_rate": 4.197530864197531e-05,
      "loss": 0.6522,
      "step": 1334
    },
    {
      "epoch": 2.965842821438489,
      "grad_norm": 0.0038658741395920515,
      "learning_rate": 3.950617283950617e-05,
      "loss": 0.5008,
      "step": 1335
    },
    {
      "epoch": 2.968064426548181,
      "grad_norm": 0.002063379855826497,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 0.4754,
      "step": 1336
    },
    {
      "epoch": 2.970286031657873,
      "grad_norm": 0.003890747670084238,
      "learning_rate": 3.456790123456791e-05,
      "loss": 0.4873,
      "step": 1337
    },
    {
      "epoch": 2.9725076367675647,
      "grad_norm": 0.0032711054664105177,
      "learning_rate": 3.209876543209877e-05,
      "loss": 0.5427,
      "step": 1338
    },
    {
      "epoch": 2.9747292418772564,
      "grad_norm": 0.0045552970841526985,
      "learning_rate": 2.962962962962963e-05,
      "loss": 0.6243,
      "step": 1339
    },
    {
      "epoch": 2.976950846986948,
      "grad_norm": 0.0027161447796970606,
      "learning_rate": 2.7160493827160493e-05,
      "loss": 0.5946,
      "step": 1340
    },
    {
      "epoch": 2.97917245209664,
      "grad_norm": 0.002958644414320588,
      "learning_rate": 2.469135802469136e-05,
      "loss": 0.517,
      "step": 1341
    },
    {
      "epoch": 2.9813940572063315,
      "grad_norm": 0.0031449785456061363,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.6588,
      "step": 1342
    },
    {
      "epoch": 2.9836156623160233,
      "grad_norm": 0.004473565611988306,
      "learning_rate": 1.9753086419753087e-05,
      "loss": 0.6024,
      "step": 1343
    },
    {
      "epoch": 2.985837267425715,
      "grad_norm": 0.002840437227860093,
      "learning_rate": 1.7283950617283953e-05,
      "loss": 0.638,
      "step": 1344
    },
    {
      "epoch": 2.9880588725354067,
      "grad_norm": 0.00275403936393559,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 0.5455,
      "step": 1345
    },
    {
      "epoch": 2.990280477645099,
      "grad_norm": 0.0028612022288143635,
      "learning_rate": 1.234567901234568e-05,
      "loss": 0.5602,
      "step": 1346
    },
    {
      "epoch": 2.9925020827547906,
      "grad_norm": 0.003987766336649656,
      "learning_rate": 9.876543209876543e-06,
      "loss": 0.5018,
      "step": 1347
    },
    {
      "epoch": 2.9947236878644823,
      "grad_norm": 0.003095380263403058,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 0.4335,
      "step": 1348
    },
    {
      "epoch": 2.996945292974174,
      "grad_norm": 0.002762428717687726,
      "learning_rate": 4.938271604938272e-06,
      "loss": 0.5598,
      "step": 1349
    },
    {
      "epoch": 2.9991668980838657,
      "grad_norm": 0.0024110933300107718,
      "learning_rate": 2.469135802469136e-06,
      "loss": 0.5225,
      "step": 1350
    },
    {
      "epoch": 2.9991668980838657,
      "step": 1350,
      "total_flos": 1.1970136381168026e+18,
      "train_loss": 0.5906960194199173,
      "train_runtime": 7334.375,
      "train_samples_per_second": 2.946,
      "train_steps_per_second": 0.184
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 1350,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1970136381168026e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}