{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.11311150909605053,
  "eval_steps": 300,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002827787727401263,
      "grad_norm": 0.80859375,
      "learning_rate": 2.5e-06,
      "loss": 2.7268,
      "step": 1
    },
    {
      "epoch": 0.0005655575454802526,
      "grad_norm": 0.7890625,
      "learning_rate": 5e-06,
      "loss": 2.718,
      "step": 2
    },
    {
      "epoch": 0.000848336318220379,
      "grad_norm": 0.77734375,
      "learning_rate": 7.5e-06,
      "loss": 2.6908,
      "step": 3
    },
    {
      "epoch": 0.0011311150909605052,
      "grad_norm": 0.796875,
      "learning_rate": 1e-05,
      "loss": 2.8856,
      "step": 4
    },
    {
      "epoch": 0.0014138938637006315,
      "grad_norm": 0.78125,
      "learning_rate": 1.25e-05,
      "loss": 2.7944,
      "step": 5
    },
    {
      "epoch": 0.001696672636440758,
      "grad_norm": 0.76171875,
      "learning_rate": 1.5e-05,
      "loss": 2.8203,
      "step": 6
    },
    {
      "epoch": 0.001979451409180884,
      "grad_norm": 0.76953125,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 2.6714,
      "step": 7
    },
    {
      "epoch": 0.0022622301819210104,
      "grad_norm": 0.8203125,
      "learning_rate": 2e-05,
      "loss": 2.6746,
      "step": 8
    },
    {
      "epoch": 0.0025450089546611367,
      "grad_norm": 0.74609375,
      "learning_rate": 2.2499999999999998e-05,
      "loss": 2.7972,
      "step": 9
    },
    {
      "epoch": 0.002827787727401263,
      "grad_norm": 0.8046875,
      "learning_rate": 2.5e-05,
      "loss": 2.8224,
      "step": 10
    },
    {
      "epoch": 0.003110566500141389,
      "grad_norm": 0.80078125,
      "learning_rate": 2.75e-05,
      "loss": 2.7473,
      "step": 11
    },
    {
      "epoch": 0.003393345272881516,
      "grad_norm": 0.83203125,
      "learning_rate": 3e-05,
      "loss": 2.7134,
      "step": 12
    },
    {
      "epoch": 0.003676124045621642,
      "grad_norm": 0.81640625,
      "learning_rate": 3.2500000000000004e-05,
      "loss": 2.7946,
      "step": 13
    },
    {
      "epoch": 0.003958902818361768,
      "grad_norm": 0.73828125,
      "learning_rate": 3.5000000000000004e-05,
      "loss": 2.8185,
      "step": 14
    },
    {
      "epoch": 0.004241681591101895,
      "grad_norm": 0.76171875,
      "learning_rate": 3.75e-05,
      "loss": 2.7015,
      "step": 15
    },
    {
      "epoch": 0.004524460363842021,
      "grad_norm": 0.73828125,
      "learning_rate": 4e-05,
      "loss": 2.7398,
      "step": 16
    },
    {
      "epoch": 0.004807239136582147,
      "grad_norm": 0.74609375,
      "learning_rate": 4.25e-05,
      "loss": 2.6954,
      "step": 17
    },
    {
      "epoch": 0.005090017909322273,
      "grad_norm": 0.79296875,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 2.7737,
      "step": 18
    },
    {
      "epoch": 0.0053727966820624,
      "grad_norm": 0.78515625,
      "learning_rate": 4.75e-05,
      "loss": 2.7532,
      "step": 19
    },
    {
      "epoch": 0.005655575454802526,
      "grad_norm": 0.7734375,
      "learning_rate": 5e-05,
      "loss": 2.7254,
      "step": 20
    },
    {
      "epoch": 0.005938354227542652,
      "grad_norm": 0.7890625,
      "learning_rate": 5.25e-05,
      "loss": 2.8117,
      "step": 21
    },
    {
      "epoch": 0.006221133000282778,
      "grad_norm": 0.76171875,
      "learning_rate": 5.5e-05,
      "loss": 2.7023,
      "step": 22
    },
    {
      "epoch": 0.0065039117730229055,
      "grad_norm": 0.796875,
      "learning_rate": 5.75e-05,
      "loss": 2.7226,
      "step": 23
    },
    {
      "epoch": 0.006786690545763032,
      "grad_norm": 0.75,
      "learning_rate": 6e-05,
      "loss": 2.7699,
      "step": 24
    },
    {
      "epoch": 0.007069469318503158,
      "grad_norm": 0.75390625,
      "learning_rate": 6.25e-05,
      "loss": 2.8024,
      "step": 25
    },
    {
      "epoch": 0.007352248091243284,
      "grad_norm": 0.69921875,
      "learning_rate": 6.500000000000001e-05,
      "loss": 2.8438,
      "step": 26
    },
    {
      "epoch": 0.0076350268639834105,
      "grad_norm": 0.69921875,
      "learning_rate": 6.75e-05,
      "loss": 2.7921,
      "step": 27
    },
    {
      "epoch": 0.007917805636723537,
      "grad_norm": 0.69140625,
      "learning_rate": 7.000000000000001e-05,
      "loss": 2.6334,
      "step": 28
    },
    {
      "epoch": 0.008200584409463663,
      "grad_norm": 0.7421875,
      "learning_rate": 7.25e-05,
      "loss": 2.7756,
      "step": 29
    },
    {
      "epoch": 0.00848336318220379,
      "grad_norm": 0.7421875,
      "learning_rate": 7.5e-05,
      "loss": 2.7423,
      "step": 30
    },
    {
      "epoch": 0.008766141954943915,
      "grad_norm": 0.65234375,
      "learning_rate": 7.75e-05,
      "loss": 2.8511,
      "step": 31
    },
    {
      "epoch": 0.009048920727684042,
      "grad_norm": 0.625,
      "learning_rate": 8e-05,
      "loss": 2.7675,
      "step": 32
    },
    {
      "epoch": 0.009331699500424168,
      "grad_norm": 0.65234375,
      "learning_rate": 8.25e-05,
      "loss": 2.7701,
      "step": 33
    },
    {
      "epoch": 0.009614478273164294,
      "grad_norm": 0.609375,
      "learning_rate": 8.5e-05,
      "loss": 2.855,
      "step": 34
    },
    {
      "epoch": 0.00989725704590442,
      "grad_norm": 0.6328125,
      "learning_rate": 8.75e-05,
      "loss": 2.8302,
      "step": 35
    },
    {
      "epoch": 0.010180035818644547,
      "grad_norm": 0.59375,
      "learning_rate": 8.999999999999999e-05,
      "loss": 2.8412,
      "step": 36
    },
    {
      "epoch": 0.010462814591384673,
      "grad_norm": 0.609375,
      "learning_rate": 9.25e-05,
      "loss": 2.8331,
      "step": 37
    },
    {
      "epoch": 0.0107455933641248,
      "grad_norm": 0.61328125,
      "learning_rate": 9.5e-05,
      "loss": 2.7374,
      "step": 38
    },
    {
      "epoch": 0.011028372136864925,
      "grad_norm": 0.57421875,
      "learning_rate": 9.750000000000001e-05,
      "loss": 2.7886,
      "step": 39
    },
    {
      "epoch": 0.011311150909605052,
      "grad_norm": 0.5859375,
      "learning_rate": 0.0001,
      "loss": 2.7014,
      "step": 40
    },
    {
      "epoch": 0.011593929682345178,
      "grad_norm": 0.609375,
      "learning_rate": 0.0001025,
      "loss": 2.7952,
      "step": 41
    },
    {
      "epoch": 0.011876708455085304,
      "grad_norm": 0.53515625,
      "learning_rate": 0.000105,
      "loss": 2.7336,
      "step": 42
    },
    {
      "epoch": 0.01215948722782543,
      "grad_norm": 0.56640625,
      "learning_rate": 0.0001075,
      "loss": 2.7843,
      "step": 43
    },
    {
      "epoch": 0.012442266000565557,
      "grad_norm": 0.5625,
      "learning_rate": 0.00011,
      "loss": 2.6144,
      "step": 44
    },
    {
      "epoch": 0.012725044773305685,
      "grad_norm": 0.5078125,
      "learning_rate": 0.00011250000000000001,
      "loss": 2.7719,
      "step": 45
    },
    {
      "epoch": 0.013007823546045811,
      "grad_norm": 0.54296875,
      "learning_rate": 0.000115,
      "loss": 2.7298,
      "step": 46
    },
    {
      "epoch": 0.013290602318785937,
      "grad_norm": 0.51953125,
      "learning_rate": 0.0001175,
      "loss": 2.8204,
      "step": 47
    },
    {
      "epoch": 0.013573381091526063,
      "grad_norm": 0.51953125,
      "learning_rate": 0.00012,
      "loss": 2.793,
      "step": 48
    },
    {
      "epoch": 0.01385615986426619,
      "grad_norm": 0.51171875,
      "learning_rate": 0.0001225,
      "loss": 2.7587,
      "step": 49
    },
    {
      "epoch": 0.014138938637006316,
      "grad_norm": 0.47265625,
      "learning_rate": 0.000125,
      "loss": 2.6685,
      "step": 50
    },
    {
      "epoch": 0.014421717409746442,
      "grad_norm": 0.46875,
      "learning_rate": 0.0001275,
      "loss": 2.7757,
      "step": 51
    },
    {
      "epoch": 0.014704496182486568,
      "grad_norm": 0.44921875,
      "learning_rate": 0.00013000000000000002,
      "loss": 2.7917,
      "step": 52
    },
    {
      "epoch": 0.014987274955226695,
      "grad_norm": 0.4765625,
      "learning_rate": 0.00013250000000000002,
      "loss": 2.7146,
      "step": 53
    },
    {
      "epoch": 0.015270053727966821,
      "grad_norm": 0.470703125,
      "learning_rate": 0.000135,
      "loss": 2.775,
      "step": 54
    },
    {
      "epoch": 0.015552832500706947,
      "grad_norm": 0.435546875,
      "learning_rate": 0.0001375,
      "loss": 2.7716,
      "step": 55
    },
    {
      "epoch": 0.015835611273447073,
      "grad_norm": 0.390625,
      "learning_rate": 0.00014000000000000001,
      "loss": 2.7673,
      "step": 56
    },
    {
      "epoch": 0.0161183900461872,
      "grad_norm": 0.40625,
      "learning_rate": 0.0001425,
      "loss": 2.7578,
      "step": 57
    },
    {
      "epoch": 0.016401168818927326,
      "grad_norm": 0.40234375,
      "learning_rate": 0.000145,
      "loss": 2.7354,
      "step": 58
    },
    {
      "epoch": 0.016683947591667452,
      "grad_norm": 0.37109375,
      "learning_rate": 0.0001475,
      "loss": 2.8292,
      "step": 59
    },
    {
      "epoch": 0.01696672636440758,
      "grad_norm": 0.39453125,
      "learning_rate": 0.00015,
      "loss": 2.7623,
      "step": 60
    },
    {
      "epoch": 0.017249505137147705,
      "grad_norm": 0.353515625,
      "learning_rate": 0.0001525,
      "loss": 2.7563,
      "step": 61
    },
    {
      "epoch": 0.01753228390988783,
      "grad_norm": 0.361328125,
      "learning_rate": 0.000155,
      "loss": 2.7535,
      "step": 62
    },
    {
      "epoch": 0.017815062682627957,
      "grad_norm": 0.3671875,
      "learning_rate": 0.0001575,
      "loss": 2.7041,
      "step": 63
    },
    {
      "epoch": 0.018097841455368083,
      "grad_norm": 0.34375,
      "learning_rate": 0.00016,
      "loss": 2.7757,
      "step": 64
    },
    {
      "epoch": 0.01838062022810821,
      "grad_norm": 0.353515625,
      "learning_rate": 0.00016250000000000002,
      "loss": 2.8202,
      "step": 65
    },
    {
      "epoch": 0.018663399000848336,
      "grad_norm": 0.345703125,
      "learning_rate": 0.000165,
      "loss": 2.7248,
      "step": 66
    },
    {
      "epoch": 0.018946177773588462,
      "grad_norm": 0.341796875,
      "learning_rate": 0.0001675,
      "loss": 2.7991,
      "step": 67
    },
    {
      "epoch": 0.01922895654632859,
      "grad_norm": 0.33984375,
      "learning_rate": 0.00017,
      "loss": 2.7269,
      "step": 68
    },
    {
      "epoch": 0.019511735319068715,
      "grad_norm": 0.3359375,
      "learning_rate": 0.0001725,
      "loss": 2.7502,
      "step": 69
    },
    {
      "epoch": 0.01979451409180884,
      "grad_norm": 0.34375,
      "learning_rate": 0.000175,
      "loss": 2.7022,
      "step": 70
    },
    {
      "epoch": 0.020077292864548967,
      "grad_norm": 0.3203125,
      "learning_rate": 0.0001775,
      "loss": 2.7533,
      "step": 71
    },
    {
      "epoch": 0.020360071637289093,
      "grad_norm": 0.326171875,
      "learning_rate": 0.00017999999999999998,
      "loss": 2.8295,
      "step": 72
    },
    {
      "epoch": 0.02064285041002922,
      "grad_norm": 0.322265625,
      "learning_rate": 0.0001825,
      "loss": 2.8412,
      "step": 73
    },
    {
      "epoch": 0.020925629182769346,
      "grad_norm": 0.328125,
      "learning_rate": 0.000185,
      "loss": 2.8365,
      "step": 74
    },
    {
      "epoch": 0.021208407955509472,
      "grad_norm": 0.32421875,
      "learning_rate": 0.0001875,
      "loss": 2.7001,
      "step": 75
    },
    {
      "epoch": 0.0214911867282496,
      "grad_norm": 0.353515625,
      "learning_rate": 0.00019,
      "loss": 2.7443,
      "step": 76
    },
    {
      "epoch": 0.021773965500989725,
      "grad_norm": 0.326171875,
      "learning_rate": 0.00019250000000000002,
      "loss": 2.7344,
      "step": 77
    },
    {
      "epoch": 0.02205674427372985,
      "grad_norm": 0.326171875,
      "learning_rate": 0.00019500000000000002,
      "loss": 2.7879,
      "step": 78
    },
    {
      "epoch": 0.022339523046469977,
      "grad_norm": 0.322265625,
      "learning_rate": 0.0001975,
      "loss": 2.7279,
      "step": 79
    },
    {
      "epoch": 0.022622301819210103,
      "grad_norm": 0.326171875,
      "learning_rate": 0.0002,
      "loss": 2.7011,
      "step": 80
    },
    {
      "epoch": 0.02290508059195023,
      "grad_norm": 0.3203125,
      "learning_rate": 0.00020250000000000002,
      "loss": 2.8249,
      "step": 81
    },
    {
      "epoch": 0.023187859364690356,
      "grad_norm": 0.328125,
      "learning_rate": 0.000205,
      "loss": 2.6382,
      "step": 82
    },
    {
      "epoch": 0.023470638137430482,
      "grad_norm": 0.302734375,
      "learning_rate": 0.0002075,
      "loss": 2.7064,
      "step": 83
    },
    {
      "epoch": 0.02375341691017061,
      "grad_norm": 0.314453125,
      "learning_rate": 0.00021,
      "loss": 2.6595,
      "step": 84
    },
    {
      "epoch": 0.024036195682910735,
      "grad_norm": 0.3046875,
      "learning_rate": 0.0002125,
      "loss": 2.7486,
      "step": 85
    },
    {
      "epoch": 0.02431897445565086,
      "grad_norm": 0.322265625,
      "learning_rate": 0.000215,
      "loss": 2.7189,
      "step": 86
    },
    {
      "epoch": 0.024601753228390987,
      "grad_norm": 0.33203125,
      "learning_rate": 0.0002175,
      "loss": 2.641,
      "step": 87
    },
    {
      "epoch": 0.024884532001131113,
      "grad_norm": 0.302734375,
      "learning_rate": 0.00022,
      "loss": 2.7538,
      "step": 88
    },
    {
      "epoch": 0.02516731077387124,
      "grad_norm": 0.3046875,
      "learning_rate": 0.00022250000000000001,
      "loss": 2.7962,
      "step": 89
    },
    {
      "epoch": 0.02545008954661137,
      "grad_norm": 0.294921875,
      "learning_rate": 0.00022500000000000002,
      "loss": 2.6709,
      "step": 90
    },
    {
      "epoch": 0.025732868319351496,
      "grad_norm": 0.294921875,
      "learning_rate": 0.0002275,
      "loss": 2.7583,
      "step": 91
    },
    {
      "epoch": 0.026015647092091622,
      "grad_norm": 0.296875,
      "learning_rate": 0.00023,
      "loss": 2.7533,
      "step": 92
    },
    {
      "epoch": 0.026298425864831748,
      "grad_norm": 0.291015625,
      "learning_rate": 0.0002325,
      "loss": 2.7713,
      "step": 93
    },
    {
      "epoch": 0.026581204637571874,
      "grad_norm": 0.279296875,
      "learning_rate": 0.000235,
      "loss": 2.7538,
      "step": 94
    },
    {
      "epoch": 0.026863983410312,
      "grad_norm": 0.294921875,
      "learning_rate": 0.0002375,
      "loss": 2.6667,
      "step": 95
    },
    {
      "epoch": 0.027146762183052127,
      "grad_norm": 0.30078125,
      "learning_rate": 0.00024,
      "loss": 2.629,
      "step": 96
    },
    {
      "epoch": 0.027429540955792253,
      "grad_norm": 0.294921875,
      "learning_rate": 0.00024249999999999999,
      "loss": 2.6954,
      "step": 97
    },
    {
      "epoch": 0.02771231972853238,
      "grad_norm": 0.294921875,
      "learning_rate": 0.000245,
      "loss": 2.6587,
      "step": 98
    },
    {
      "epoch": 0.027995098501272506,
      "grad_norm": 0.291015625,
      "learning_rate": 0.0002475,
      "loss": 2.7655,
      "step": 99
    },
    {
      "epoch": 0.028277877274012632,
      "grad_norm": 0.30859375,
      "learning_rate": 0.00025,
      "loss": 2.7836,
      "step": 100
    },
    {
      "epoch": 0.028560656046752758,
      "grad_norm": 0.2890625,
      "learning_rate": 0.0002525,
      "loss": 2.7529,
      "step": 101
    },
    {
      "epoch": 0.028843434819492884,
      "grad_norm": 0.326171875,
      "learning_rate": 0.000255,
      "loss": 2.6644,
      "step": 102
    },
    {
      "epoch": 0.02912621359223301,
      "grad_norm": 0.322265625,
      "learning_rate": 0.0002575,
      "loss": 2.705,
      "step": 103
    },
    {
      "epoch": 0.029408992364973137,
      "grad_norm": 0.31640625,
      "learning_rate": 0.00026000000000000003,
      "loss": 2.7109,
      "step": 104
    },
    {
      "epoch": 0.029691771137713263,
      "grad_norm": 0.279296875,
      "learning_rate": 0.00026250000000000004,
      "loss": 2.7592,
      "step": 105
    },
    {
      "epoch": 0.02997454991045339,
      "grad_norm": 0.30078125,
      "learning_rate": 0.00026500000000000004,
      "loss": 2.747,
      "step": 106
    },
    {
      "epoch": 0.030257328683193516,
      "grad_norm": 0.2890625,
      "learning_rate": 0.0002675,
      "loss": 2.7356,
      "step": 107
    },
    {
      "epoch": 0.030540107455933642,
      "grad_norm": 0.283203125,
      "learning_rate": 0.00027,
      "loss": 2.7167,
      "step": 108
    },
    {
      "epoch": 0.030822886228673768,
      "grad_norm": 0.283203125,
      "learning_rate": 0.0002725,
      "loss": 2.6863,
      "step": 109
    },
    {
      "epoch": 0.031105665001413894,
      "grad_norm": 0.275390625,
      "learning_rate": 0.000275,
      "loss": 2.6439,
      "step": 110
    },
    {
      "epoch": 0.03138844377415402,
      "grad_norm": 0.30859375,
      "learning_rate": 0.0002775,
      "loss": 2.6536,
      "step": 111
    },
    {
      "epoch": 0.03167122254689415,
      "grad_norm": 0.29296875,
      "learning_rate": 0.00028000000000000003,
      "loss": 2.7481,
      "step": 112
    },
    {
      "epoch": 0.03195400131963427,
      "grad_norm": 0.32421875,
      "learning_rate": 0.0002825,
      "loss": 2.6734,
      "step": 113
    },
    {
      "epoch": 0.0322367800923744,
      "grad_norm": 0.28515625,
      "learning_rate": 0.000285,
      "loss": 2.7453,
      "step": 114
    },
    {
      "epoch": 0.032519558865114526,
      "grad_norm": 0.326171875,
      "learning_rate": 0.0002875,
      "loss": 2.8891,
      "step": 115
    },
    {
      "epoch": 0.03280233763785465,
      "grad_norm": 0.287109375,
      "learning_rate": 0.00029,
      "loss": 2.7235,
      "step": 116
    },
    {
      "epoch": 0.03308511641059478,
      "grad_norm": 0.28515625,
      "learning_rate": 0.0002925,
      "loss": 2.6824,
      "step": 117
    },
    {
      "epoch": 0.033367895183334904,
      "grad_norm": 0.28125,
      "learning_rate": 0.000295,
      "loss": 2.7092,
      "step": 118
    },
    {
      "epoch": 0.03365067395607503,
      "grad_norm": 0.279296875,
      "learning_rate": 0.00029749999999999997,
      "loss": 2.7626,
      "step": 119
    },
    {
      "epoch": 0.03393345272881516,
      "grad_norm": 0.28515625,
      "learning_rate": 0.0003,
      "loss": 2.6733,
      "step": 120
    },
    {
      "epoch": 0.03421623150155528,
      "grad_norm": 0.287109375,
      "learning_rate": 0.0003025,
      "loss": 2.6709,
      "step": 121
    },
    {
      "epoch": 0.03449901027429541,
      "grad_norm": 0.291015625,
      "learning_rate": 0.000305,
      "loss": 2.7311,
      "step": 122
    },
    {
      "epoch": 0.034781789047035536,
      "grad_norm": 0.27734375,
      "learning_rate": 0.0003075,
      "loss": 2.6115,
      "step": 123
    },
    {
      "epoch": 0.03506456781977566,
      "grad_norm": 0.275390625,
      "learning_rate": 0.00031,
      "loss": 2.7095,
      "step": 124
    },
    {
      "epoch": 0.03534734659251579,
      "grad_norm": 0.28125,
      "learning_rate": 0.0003125,
      "loss": 2.6627,
      "step": 125
    },
    {
      "epoch": 0.035630125365255914,
      "grad_norm": 0.279296875,
      "learning_rate": 0.000315,
      "loss": 2.8735,
      "step": 126
    },
    {
      "epoch": 0.03591290413799604,
      "grad_norm": 0.28125,
      "learning_rate": 0.0003175,
      "loss": 2.7889,
      "step": 127
    },
    {
      "epoch": 0.03619568291073617,
      "grad_norm": 0.287109375,
      "learning_rate": 0.00032,
      "loss": 2.6057,
      "step": 128
    },
    {
      "epoch": 0.03647846168347629,
      "grad_norm": 0.28515625,
      "learning_rate": 0.00032250000000000003,
      "loss": 2.6387,
      "step": 129
    },
    {
      "epoch": 0.03676124045621642,
      "grad_norm": 0.28125,
      "learning_rate": 0.00032500000000000004,
      "loss": 2.6529,
      "step": 130
    },
    {
      "epoch": 0.037044019228956546,
      "grad_norm": 0.28125,
      "learning_rate": 0.00032750000000000005,
      "loss": 2.795,
      "step": 131
    },
    {
      "epoch": 0.03732679800169667,
      "grad_norm": 0.2734375,
      "learning_rate": 0.00033,
      "loss": 2.685,
      "step": 132
    },
    {
      "epoch": 0.0376095767744368,
      "grad_norm": 0.294921875,
      "learning_rate": 0.0003325,
      "loss": 2.6728,
      "step": 133
    },
    {
      "epoch": 0.037892355547176924,
      "grad_norm": 0.283203125,
      "learning_rate": 0.000335,
      "loss": 2.6906,
      "step": 134
    },
    {
      "epoch": 0.03817513431991705,
      "grad_norm": 0.2734375,
      "learning_rate": 0.0003375,
      "loss": 2.6905,
      "step": 135
    },
    {
      "epoch": 0.03845791309265718,
      "grad_norm": 0.2890625,
      "learning_rate": 0.00034,
      "loss": 2.8113,
      "step": 136
    },
    {
      "epoch": 0.0387406918653973,
      "grad_norm": 0.279296875,
      "learning_rate": 0.00034250000000000003,
      "loss": 2.7053,
      "step": 137
    },
    {
      "epoch": 0.03902347063813743,
      "grad_norm": 0.27734375,
      "learning_rate": 0.000345,
      "loss": 2.7589,
      "step": 138
    },
    {
      "epoch": 0.039306249410877556,
      "grad_norm": 0.2890625,
      "learning_rate": 0.0003475,
      "loss": 2.7462,
      "step": 139
    },
    {
      "epoch": 0.03958902818361768,
      "grad_norm": 0.279296875,
      "learning_rate": 0.00035,
      "loss": 2.801,
      "step": 140
    },
    {
      "epoch": 0.03987180695635781,
      "grad_norm": 0.27734375,
      "learning_rate": 0.0003525,
      "loss": 2.7696,
      "step": 141
    },
    {
      "epoch": 0.040154585729097934,
      "grad_norm": 0.267578125,
      "learning_rate": 0.000355,
      "loss": 2.7535,
      "step": 142
    },
    {
      "epoch": 0.04043736450183806,
      "grad_norm": 0.27734375,
      "learning_rate": 0.0003575,
      "loss": 2.6457,
      "step": 143
    },
    {
      "epoch": 0.04072014327457819,
      "grad_norm": 0.29296875,
      "learning_rate": 0.00035999999999999997,
      "loss": 2.6899,
      "step": 144
    },
    {
      "epoch": 0.04100292204731831,
      "grad_norm": 0.29296875,
      "learning_rate": 0.0003625,
      "loss": 2.7357,
      "step": 145
    },
    {
      "epoch": 0.04128570082005844,
      "grad_norm": 0.279296875,
      "learning_rate": 0.000365,
      "loss": 2.7567,
      "step": 146
    },
    {
      "epoch": 0.041568479592798566,
      "grad_norm": 0.27734375,
      "learning_rate": 0.0003675,
      "loss": 2.7435,
      "step": 147
    },
    {
      "epoch": 0.04185125836553869,
      "grad_norm": 0.2890625,
      "learning_rate": 0.00037,
      "loss": 2.719,
      "step": 148
    },
    {
      "epoch": 0.04213403713827882,
      "grad_norm": 0.283203125,
      "learning_rate": 0.0003725,
      "loss": 2.7422,
      "step": 149
    },
    {
      "epoch": 0.042416815911018944,
      "grad_norm": 0.283203125,
      "learning_rate": 0.000375,
      "loss": 2.6422,
      "step": 150
    },
    {
      "epoch": 0.04269959468375907,
      "grad_norm": 0.27734375,
      "learning_rate": 0.0003775,
      "loss": 2.6201,
      "step": 151
    },
    {
      "epoch": 0.0429823734564992,
      "grad_norm": 0.2734375,
      "learning_rate": 0.00038,
      "loss": 2.7534,
      "step": 152
    },
    {
      "epoch": 0.04326515222923932,
      "grad_norm": 0.294921875,
      "learning_rate": 0.00038250000000000003,
      "loss": 2.7279,
      "step": 153
    },
    {
      "epoch": 0.04354793100197945,
      "grad_norm": 0.28515625,
      "learning_rate": 0.00038500000000000003,
      "loss": 2.6537,
      "step": 154
    },
    {
      "epoch": 0.043830709774719576,
      "grad_norm": 0.275390625,
      "learning_rate": 0.00038750000000000004,
      "loss": 2.657,
      "step": 155
    },
    {
      "epoch": 0.0441134885474597,
      "grad_norm": 0.279296875,
      "learning_rate": 0.00039000000000000005,
      "loss": 2.6733,
      "step": 156
    },
    {
      "epoch": 0.04439626732019983,
      "grad_norm": 0.291015625,
      "learning_rate": 0.0003925,
      "loss": 2.6964,
      "step": 157
    },
    {
      "epoch": 0.044679046092939954,
      "grad_norm": 0.28125,
      "learning_rate": 0.000395,
      "loss": 2.7566,
      "step": 158
    },
    {
      "epoch": 0.04496182486568008,
      "grad_norm": 0.28125,
      "learning_rate": 0.0003975,
      "loss": 2.729,
      "step": 159
    },
    {
      "epoch": 0.04524460363842021,
      "grad_norm": 0.322265625,
      "learning_rate": 0.0004,
      "loss": 2.6093,
      "step": 160
    },
    {
      "epoch": 0.04552738241116033,
      "grad_norm": 0.296875,
      "learning_rate": 0.0004025,
      "loss": 2.7484,
      "step": 161
    },
    {
      "epoch": 0.04581016118390046,
      "grad_norm": 0.287109375,
      "learning_rate": 0.00040500000000000003,
      "loss": 2.7072,
      "step": 162
    },
    {
      "epoch": 0.046092939956640586,
      "grad_norm": 0.3046875,
      "learning_rate": 0.0004075,
      "loss": 2.7066,
      "step": 163
    },
    {
      "epoch": 0.04637571872938071,
      "grad_norm": 0.298828125,
      "learning_rate": 0.00041,
      "loss": 2.6637,
      "step": 164
    },
    {
      "epoch": 0.04665849750212084,
      "grad_norm": 0.302734375,
      "learning_rate": 0.0004125,
      "loss": 2.7463,
      "step": 165
    },
    {
      "epoch": 0.046941276274860964,
      "grad_norm": 0.28515625,
      "learning_rate": 0.000415,
      "loss": 2.6977,
      "step": 166
    },
    {
      "epoch": 0.04722405504760109,
      "grad_norm": 0.26171875,
      "learning_rate": 0.0004175,
      "loss": 2.6522,
      "step": 167
    },
    {
      "epoch": 0.04750683382034122,
      "grad_norm": 0.279296875,
      "learning_rate": 0.00042,
      "loss": 2.728,
      "step": 168
    },
    {
      "epoch": 0.04778961259308134,
      "grad_norm": 0.28515625,
      "learning_rate": 0.00042249999999999997,
      "loss": 2.8141,
      "step": 169
    },
    {
      "epoch": 0.04807239136582147,
      "grad_norm": 0.267578125,
      "learning_rate": 0.000425,
      "loss": 2.7782,
      "step": 170
    },
    {
      "epoch": 0.048355170138561596,
      "grad_norm": 0.28125,
      "learning_rate": 0.0004275,
      "loss": 2.6818,
      "step": 171
    },
    {
      "epoch": 0.04863794891130172,
      "grad_norm": 0.275390625,
      "learning_rate": 0.00043,
      "loss": 2.7362,
      "step": 172
    },
    {
      "epoch": 0.04892072768404185,
      "grad_norm": 0.271484375,
      "learning_rate": 0.0004325,
      "loss": 2.7075,
      "step": 173
    },
    {
      "epoch": 0.049203506456781974,
      "grad_norm": 0.2734375,
      "learning_rate": 0.000435,
      "loss": 2.8147,
      "step": 174
    },
    {
      "epoch": 0.0494862852295221,
      "grad_norm": 0.287109375,
      "learning_rate": 0.0004375,
      "loss": 2.5834,
      "step": 175
    },
    {
      "epoch": 0.04976906400226223,
      "grad_norm": 0.28125,
      "learning_rate": 0.00044,
      "loss": 2.5964,
      "step": 176
    },
    {
      "epoch": 0.05005184277500235,
      "grad_norm": 0.298828125,
      "learning_rate": 0.0004425,
      "loss": 2.7753,
      "step": 177
    },
    {
      "epoch": 0.05033462154774248,
      "grad_norm": 0.265625,
      "learning_rate": 0.00044500000000000003,
      "loss": 2.5962,
      "step": 178
    },
    {
      "epoch": 0.05061740032048261,
      "grad_norm": 0.279296875,
      "learning_rate": 0.00044750000000000004,
      "loss": 2.7144,
      "step": 179
    },
    {
      "epoch": 0.05090017909322274,
      "grad_norm": 0.283203125,
      "learning_rate": 0.00045000000000000004,
      "loss": 2.6035,
      "step": 180
    },
    {
      "epoch": 0.051182957865962865,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00045250000000000005,
      "loss": 2.7479,
      "step": 181
    },
    {
      "epoch": 0.05146573663870299,
      "grad_norm": 0.27734375,
      "learning_rate": 0.000455,
      "loss": 2.7137,
      "step": 182
    },
    {
      "epoch": 0.05174851541144312,
      "grad_norm": 0.27734375,
      "learning_rate": 0.0004575,
      "loss": 2.8017,
      "step": 183
    },
    {
      "epoch": 0.052031294184183244,
      "grad_norm": 0.287109375,
      "learning_rate": 0.00046,
      "loss": 2.7057,
      "step": 184
    },
    {
      "epoch": 0.05231407295692337,
      "grad_norm": 0.296875,
      "learning_rate": 0.0004625,
      "loss": 2.6357,
      "step": 185
    },
    {
      "epoch": 0.052596851729663496,
      "grad_norm": 0.306640625,
      "learning_rate": 0.000465,
      "loss": 2.7985,
      "step": 186
    },
    {
      "epoch": 0.05287963050240362,
      "grad_norm": 0.2734375,
      "learning_rate": 0.00046750000000000003,
      "loss": 2.7495,
      "step": 187
    },
    {
      "epoch": 0.05316240927514375,
      "grad_norm": 0.26953125,
      "learning_rate": 0.00047,
      "loss": 2.8081,
      "step": 188
    },
    {
      "epoch": 0.053445188047883875,
      "grad_norm": 0.275390625,
      "learning_rate": 0.0004725,
      "loss": 2.6571,
      "step": 189
    },
    {
      "epoch": 0.053727966820624,
      "grad_norm": 0.287109375,
      "learning_rate": 0.000475,
      "loss": 2.6884,
      "step": 190
    },
    {
      "epoch": 0.05401074559336413,
      "grad_norm": 0.3046875,
      "learning_rate": 0.0004775,
      "loss": 2.5996,
      "step": 191
    },
    {
      "epoch": 0.054293524366104254,
      "grad_norm": 0.2890625,
      "learning_rate": 0.00048,
      "loss": 2.7077,
      "step": 192
    },
    {
      "epoch": 0.05457630313884438,
      "grad_norm": 0.2890625,
      "learning_rate": 0.0004825,
      "loss": 2.5899,
      "step": 193
    },
    {
      "epoch": 0.054859081911584506,
      "grad_norm": 0.26953125,
      "learning_rate": 0.00048499999999999997,
      "loss": 2.6607,
      "step": 194
    },
    {
      "epoch": 0.05514186068432463,
      "grad_norm": 0.2890625,
      "learning_rate": 0.0004875,
      "loss": 2.6953,
      "step": 195
    },
    {
      "epoch": 0.05542463945706476,
      "grad_norm": 0.32421875,
      "learning_rate": 0.00049,
      "loss": 2.7074,
      "step": 196
    },
    {
      "epoch": 0.055707418229804885,
      "grad_norm": 0.28515625,
      "learning_rate": 0.0004925,
      "loss": 2.7335,
      "step": 197
    },
    {
      "epoch": 0.05599019700254501,
      "grad_norm": 0.306640625,
      "learning_rate": 0.000495,
      "loss": 2.6951,
      "step": 198
    },
    {
      "epoch": 0.05627297577528514,
      "grad_norm": 0.27734375,
      "learning_rate": 0.0004975,
      "loss": 2.6671,
      "step": 199
    },
    {
      "epoch": 0.056555754548025264,
      "grad_norm": 0.275390625,
      "learning_rate": 0.0005,
      "loss": 2.6488,
      "step": 200
    },
    {
      "epoch": 0.05683853332076539,
      "grad_norm": 0.2890625,
      "learning_rate": 0.0005024999999999999,
      "loss": 2.6969,
      "step": 201
    },
    {
      "epoch": 0.057121312093505516,
      "grad_norm": 0.296875,
      "learning_rate": 0.000505,
      "loss": 2.7266,
      "step": 202
    },
    {
      "epoch": 0.05740409086624564,
      "grad_norm": 0.291015625,
      "learning_rate": 0.0005074999999999999,
      "loss": 2.7185,
      "step": 203
    },
    {
      "epoch": 0.05768686963898577,
      "grad_norm": 0.29296875,
      "learning_rate": 0.00051,
      "loss": 2.6981,
      "step": 204
    },
    {
      "epoch": 0.057969648411725895,
      "grad_norm": 0.275390625,
      "learning_rate": 0.0005124999999999999,
      "loss": 2.7895,
      "step": 205
    },
    {
      "epoch": 0.05825242718446602,
      "grad_norm": 0.2734375,
      "learning_rate": 0.000515,
      "loss": 2.6501,
      "step": 206
    },
    {
      "epoch": 0.05853520595720615,
      "grad_norm": 0.2890625,
      "learning_rate": 0.0005175,
      "loss": 2.7063,
      "step": 207
    },
    {
      "epoch": 0.058817984729946274,
      "grad_norm": 0.3046875,
      "learning_rate": 0.0005200000000000001,
      "loss": 2.6494,
      "step": 208
    },
    {
      "epoch": 0.0591007635026864,
      "grad_norm": 0.29296875,
      "learning_rate": 0.0005225,
      "loss": 2.7103,
      "step": 209
    },
    {
      "epoch": 0.059383542275426526,
      "grad_norm": 0.28515625,
      "learning_rate": 0.0005250000000000001,
      "loss": 2.737,
      "step": 210
    },
    {
      "epoch": 0.05966632104816665,
      "grad_norm": 0.27734375,
      "learning_rate": 0.0005275,
      "loss": 2.767,
      "step": 211
    },
    {
      "epoch": 0.05994909982090678,
      "grad_norm": 0.283203125,
      "learning_rate": 0.0005300000000000001,
      "loss": 2.7649,
      "step": 212
    },
    {
      "epoch": 0.060231878593646905,
      "grad_norm": 0.283203125,
      "learning_rate": 0.0005325,
      "loss": 2.7723,
      "step": 213
    },
    {
      "epoch": 0.06051465736638703,
      "grad_norm": 0.27734375,
      "learning_rate": 0.000535,
      "loss": 2.7049,
      "step": 214
    },
    {
      "epoch": 0.06079743613912716,
      "grad_norm": 0.28125,
      "learning_rate": 0.0005375,
      "loss": 2.718,
      "step": 215
    },
    {
      "epoch": 0.061080214911867284,
      "grad_norm": 0.271484375,
      "learning_rate": 0.00054,
      "loss": 2.7322,
      "step": 216
    },
    {
      "epoch": 0.06136299368460741,
      "grad_norm": 0.279296875,
      "learning_rate": 0.0005425,
      "loss": 2.8249,
      "step": 217
    },
    {
      "epoch": 0.061645772457347536,
      "grad_norm": 0.287109375,
      "learning_rate": 0.000545,
      "loss": 2.597,
      "step": 218
    },
    {
      "epoch": 0.06192855123008766,
      "grad_norm": 0.283203125,
      "learning_rate": 0.0005475,
      "loss": 2.6562,
      "step": 219
    },
    {
      "epoch": 0.06221133000282779,
      "grad_norm": 0.265625,
      "learning_rate": 0.00055,
      "loss": 2.6592,
      "step": 220
    },
    {
      "epoch": 0.062494108775567915,
      "grad_norm": 0.294921875,
      "learning_rate": 0.0005525,
      "loss": 2.6218,
      "step": 221
    },
    {
      "epoch": 0.06277688754830804,
      "grad_norm": 0.275390625,
      "learning_rate": 0.000555,
      "loss": 2.7255,
      "step": 222
    },
    {
      "epoch": 0.06305966632104816,
      "grad_norm": 0.271484375,
      "learning_rate": 0.0005575,
      "loss": 2.8204,
      "step": 223
    },
    {
      "epoch": 0.0633424450937883,
      "grad_norm": 0.287109375,
      "learning_rate": 0.0005600000000000001,
      "loss": 2.7503,
      "step": 224
    },
    {
      "epoch": 0.06362522386652841,
      "grad_norm": 0.298828125,
      "learning_rate": 0.0005625000000000001,
      "loss": 2.659,
      "step": 225
    },
    {
      "epoch": 0.06390800263926855,
      "grad_norm": 0.2890625,
      "learning_rate": 0.000565,
      "loss": 2.8152,
      "step": 226
    },
    {
      "epoch": 0.06419078141200867,
      "grad_norm": 0.27734375,
      "learning_rate": 0.0005675,
      "loss": 2.7683,
      "step": 227
    },
    {
      "epoch": 0.0644735601847488,
      "grad_norm": 0.275390625,
      "learning_rate": 0.00057,
      "loss": 2.6908,
      "step": 228
    },
    {
      "epoch": 0.06475633895748892,
      "grad_norm": 0.302734375,
      "learning_rate": 0.0005725,
      "loss": 2.7206,
      "step": 229
    },
    {
      "epoch": 0.06503911773022905,
      "grad_norm": 0.28125,
      "learning_rate": 0.000575,
      "loss": 2.6713,
      "step": 230
    },
    {
      "epoch": 0.06532189650296917,
      "grad_norm": 0.296875,
      "learning_rate": 0.0005775,
      "loss": 2.5687,
      "step": 231
    },
    {
      "epoch": 0.0656046752757093,
      "grad_norm": 0.275390625,
      "learning_rate": 0.00058,
      "loss": 2.7068,
      "step": 232
    },
    {
      "epoch": 0.06588745404844942,
      "grad_norm": 0.29296875,
      "learning_rate": 0.0005825,
      "loss": 2.7664,
      "step": 233
    },
    {
      "epoch": 0.06617023282118956,
      "grad_norm": 0.306640625,
      "learning_rate": 0.000585,
      "loss": 2.7705,
      "step": 234
    },
    {
      "epoch": 0.06645301159392968,
      "grad_norm": 0.32421875,
      "learning_rate": 0.0005875,
      "loss": 2.6366,
      "step": 235
    },
    {
      "epoch": 0.06673579036666981,
      "grad_norm": 0.310546875,
      "learning_rate": 0.00059,
      "loss": 2.6913,
      "step": 236
    },
    {
      "epoch": 0.06701856913940993,
      "grad_norm": 0.2890625,
      "learning_rate": 0.0005925,
      "loss": 2.6292,
      "step": 237
    },
    {
      "epoch": 0.06730134791215006,
      "grad_norm": 0.275390625,
      "learning_rate": 0.0005949999999999999,
      "loss": 2.6452,
      "step": 238
    },
    {
      "epoch": 0.0675841266848902,
      "grad_norm": 0.279296875,
      "learning_rate": 0.0005975,
      "loss": 2.5264,
      "step": 239
    },
    {
      "epoch": 0.06786690545763031,
      "grad_norm": 0.2890625,
      "learning_rate": 0.0006,
      "loss": 2.7456,
      "step": 240
    },
    {
      "epoch": 0.06814968423037045,
      "grad_norm": 0.283203125,
      "learning_rate": 0.0006025000000000001,
      "loss": 2.6951,
      "step": 241
    },
    {
      "epoch": 0.06843246300311057,
      "grad_norm": 0.33203125,
      "learning_rate": 0.000605,
      "loss": 2.7262,
      "step": 242
    },
    {
      "epoch": 0.0687152417758507,
      "grad_norm": 0.294921875,
      "learning_rate": 0.0006075000000000001,
      "loss": 2.7282,
      "step": 243
    },
    {
      "epoch": 0.06899802054859082,
      "grad_norm": 0.291015625,
      "learning_rate": 0.00061,
      "loss": 2.7134,
      "step": 244
    },
    {
      "epoch": 0.06928079932133095,
      "grad_norm": 0.28515625,
      "learning_rate": 0.0006125000000000001,
      "loss": 2.6794,
      "step": 245
    },
    {
      "epoch": 0.06956357809407107,
      "grad_norm": 0.298828125,
      "learning_rate": 0.000615,
      "loss": 2.7105,
      "step": 246
    },
    {
      "epoch": 0.0698463568668112,
      "grad_norm": 0.3046875,
      "learning_rate": 0.0006175000000000001,
      "loss": 2.6656,
      "step": 247
    },
    {
      "epoch": 0.07012913563955132,
      "grad_norm": 0.271484375,
      "learning_rate": 0.00062,
      "loss": 2.669,
      "step": 248
    },
    {
      "epoch": 0.07041191441229146,
      "grad_norm": 0.294921875,
      "learning_rate": 0.0006225000000000001,
      "loss": 2.7143,
      "step": 249
    },
    {
      "epoch": 0.07069469318503158,
      "grad_norm": 0.28515625,
      "learning_rate": 0.000625,
      "loss": 2.7088,
      "step": 250
    },
    {
      "epoch": 0.07097747195777171,
      "grad_norm": 0.3125,
      "learning_rate": 0.0006274999999999999,
      "loss": 2.6446,
      "step": 251
    },
    {
      "epoch": 0.07126025073051183,
      "grad_norm": 0.30078125,
      "learning_rate": 0.00063,
      "loss": 2.6527,
      "step": 252
    },
    {
      "epoch": 0.07154302950325196,
      "grad_norm": 0.279296875,
      "learning_rate": 0.0006324999999999999,
      "loss": 2.7882,
      "step": 253
    },
    {
      "epoch": 0.07182580827599208,
      "grad_norm": 0.2734375,
      "learning_rate": 0.000635,
      "loss": 2.711,
      "step": 254
    },
    {
      "epoch": 0.07210858704873221,
      "grad_norm": 0.29296875,
      "learning_rate": 0.0006374999999999999,
      "loss": 2.733,
      "step": 255
    },
    {
      "epoch": 0.07239136582147233,
      "grad_norm": 0.283203125,
      "learning_rate": 0.00064,
      "loss": 2.5823,
      "step": 256
    },
    {
      "epoch": 0.07267414459421247,
      "grad_norm": 0.33203125,
      "learning_rate": 0.0006425,
      "loss": 2.6286,
      "step": 257
    },
    {
      "epoch": 0.07295692336695259,
      "grad_norm": 0.302734375,
      "learning_rate": 0.0006450000000000001,
      "loss": 2.6986,
      "step": 258
    },
    {
      "epoch": 0.07323970213969272,
      "grad_norm": 0.27734375,
      "learning_rate": 0.0006475,
      "loss": 2.7071,
      "step": 259
    },
    {
      "epoch": 0.07352248091243284,
      "grad_norm": 0.275390625,
      "learning_rate": 0.0006500000000000001,
      "loss": 2.6763,
      "step": 260
    },
    {
      "epoch": 0.07380525968517297,
      "grad_norm": 0.328125,
      "learning_rate": 0.0006525,
      "loss": 2.759,
      "step": 261
    },
    {
      "epoch": 0.07408803845791309,
      "grad_norm": 0.2890625,
      "learning_rate": 0.0006550000000000001,
      "loss": 2.735,
      "step": 262
    },
    {
      "epoch": 0.07437081723065322,
      "grad_norm": 0.296875,
      "learning_rate": 0.0006575,
      "loss": 2.7129,
      "step": 263
    },
    {
      "epoch": 0.07465359600339334,
      "grad_norm": 0.283203125,
      "learning_rate": 0.00066,
      "loss": 2.7521,
      "step": 264
    },
    {
      "epoch": 0.07493637477613348,
      "grad_norm": 0.2734375,
      "learning_rate": 0.0006625,
      "loss": 2.6918,
      "step": 265
    },
    {
      "epoch": 0.0752191535488736,
      "grad_norm": 0.28125,
      "learning_rate": 0.000665,
      "loss": 2.6264,
      "step": 266
    },
    {
      "epoch": 0.07550193232161373,
      "grad_norm": 0.298828125,
      "learning_rate": 0.0006675,
      "loss": 2.7115,
      "step": 267
    },
    {
      "epoch": 0.07578471109435385,
      "grad_norm": 0.298828125,
      "learning_rate": 0.00067,
      "loss": 2.7494,
      "step": 268
    },
    {
      "epoch": 0.07606748986709398,
      "grad_norm": 0.283203125,
      "learning_rate": 0.0006725,
      "loss": 2.6134,
      "step": 269
    },
    {
      "epoch": 0.0763502686398341,
      "grad_norm": 0.298828125,
      "learning_rate": 0.000675,
      "loss": 2.6015,
      "step": 270
    },
    {
      "epoch": 0.07663304741257423,
      "grad_norm": 0.31640625,
      "learning_rate": 0.0006775,
      "loss": 2.6864,
      "step": 271
    },
    {
      "epoch": 0.07691582618531435,
      "grad_norm": 0.2890625,
      "learning_rate": 0.00068,
      "loss": 2.6564,
      "step": 272
    },
    {
      "epoch": 0.07719860495805449,
      "grad_norm": 0.275390625,
      "learning_rate": 0.0006825000000000001,
      "loss": 2.6775,
      "step": 273
    },
    {
      "epoch": 0.0774813837307946,
      "grad_norm": 0.29296875,
      "learning_rate": 0.0006850000000000001,
      "loss": 2.6788,
      "step": 274
    },
    {
      "epoch": 0.07776416250353474,
      "grad_norm": 0.283203125,
      "learning_rate": 0.0006875,
      "loss": 2.6712,
      "step": 275
    },
    {
      "epoch": 0.07804694127627486,
      "grad_norm": 0.28125,
      "learning_rate": 0.00069,
      "loss": 2.7014,
      "step": 276
    },
    {
      "epoch": 0.07832972004901499,
      "grad_norm": 0.2734375,
      "learning_rate": 0.0006925,
      "loss": 2.6744,
      "step": 277
    },
    {
      "epoch": 0.07861249882175511,
      "grad_norm": 0.28125,
      "learning_rate": 0.000695,
      "loss": 2.7591,
      "step": 278
    },
    {
      "epoch": 0.07889527759449524,
      "grad_norm": 0.3203125,
      "learning_rate": 0.0006975,
      "loss": 2.7315,
      "step": 279
    },
    {
      "epoch": 0.07917805636723536,
      "grad_norm": 0.291015625,
      "learning_rate": 0.0007,
      "loss": 2.6955,
      "step": 280
    },
    {
      "epoch": 0.0794608351399755,
      "grad_norm": 0.29296875,
      "learning_rate": 0.0007025,
      "loss": 2.6846,
      "step": 281
    },
    {
      "epoch": 0.07974361391271562,
      "grad_norm": 0.2890625,
      "learning_rate": 0.000705,
      "loss": 2.5973,
      "step": 282
    },
    {
      "epoch": 0.08002639268545575,
      "grad_norm": 0.27734375,
      "learning_rate": 0.0007075,
      "loss": 2.671,
      "step": 283
    },
    {
      "epoch": 0.08030917145819587,
      "grad_norm": 0.29296875,
      "learning_rate": 0.00071,
      "loss": 2.7698,
      "step": 284
    },
    {
      "epoch": 0.080591950230936,
      "grad_norm": 0.29296875,
      "learning_rate": 0.0007125,
      "loss": 2.6023,
      "step": 285
    },
    {
      "epoch": 0.08087472900367612,
      "grad_norm": 0.26953125,
      "learning_rate": 0.000715,
      "loss": 2.5578,
      "step": 286
    },
    {
      "epoch": 0.08115750777641625,
      "grad_norm": 0.30078125,
      "learning_rate": 0.0007175,
      "loss": 2.7082,
      "step": 287
    },
    {
      "epoch": 0.08144028654915637,
      "grad_norm": 0.287109375,
      "learning_rate": 0.0007199999999999999,
      "loss": 2.6585,
      "step": 288
    },
    {
      "epoch": 0.08172306532189651,
      "grad_norm": 0.296875,
      "learning_rate": 0.0007225,
      "loss": 2.6401,
      "step": 289
    },
    {
      "epoch": 0.08200584409463663,
      "grad_norm": 0.296875,
      "learning_rate": 0.000725,
      "loss": 2.6788,
      "step": 290
    },
    {
      "epoch": 0.08228862286737676,
      "grad_norm": 0.26953125,
      "learning_rate": 0.0007275000000000001,
      "loss": 2.681,
      "step": 291
    },
    {
      "epoch": 0.08257140164011688,
      "grad_norm": 0.302734375,
      "learning_rate": 0.00073,
      "loss": 2.7276,
      "step": 292
    },
    {
      "epoch": 0.08285418041285701,
      "grad_norm": 0.28515625,
      "learning_rate": 0.0007325000000000001,
      "loss": 2.6946,
      "step": 293
    },
    {
      "epoch": 0.08313695918559713,
      "grad_norm": 0.283203125,
      "learning_rate": 0.000735,
      "loss": 2.6882,
      "step": 294
    },
    {
      "epoch": 0.08341973795833726,
      "grad_norm": 0.291015625,
      "learning_rate": 0.0007375000000000001,
      "loss": 2.6571,
      "step": 295
    },
    {
      "epoch": 0.08370251673107738,
      "grad_norm": 0.27734375,
      "learning_rate": 0.00074,
      "loss": 2.7716,
      "step": 296
    },
    {
      "epoch": 0.08398529550381752,
      "grad_norm": 0.3125,
      "learning_rate": 0.0007425000000000001,
      "loss": 2.7189,
      "step": 297
    },
    {
      "epoch": 0.08426807427655764,
      "grad_norm": 0.294921875,
      "learning_rate": 0.000745,
      "loss": 2.6868,
      "step": 298
    },
    {
      "epoch": 0.08455085304929777,
      "grad_norm": 0.28515625,
      "learning_rate": 0.0007475000000000001,
      "loss": 2.6705,
      "step": 299
    },
    {
      "epoch": 0.08483363182203789,
      "grad_norm": 0.28125,
      "learning_rate": 0.00075,
      "loss": 2.7242,
      "step": 300
    },
    {
      "epoch": 0.08483363182203789,
      "eval_loss": 1.8609898090362549,
      "eval_runtime": 74.934,
      "eval_samples_per_second": 13.665,
      "eval_steps_per_second": 0.427,
      "step": 300
    },
    {
      "epoch": 0.08483363182203789,
      "eval/hellaswag_acc": 0.37572196773551086,
      "eval/hellaswag_acc_norm": 0.4715196176060546,
      "eval_hellaswag_elapsed_time": 331.94735646247864,
      "step": 300
    },
    {
      "epoch": 0.028560656046752758,
      "grad_norm": 0.30078125,
      "learning_rate": 0.0007524999999999999,
      "loss": 2.6969,
      "step": 301
    },
    {
      "epoch": 0.028843434819492884,
      "grad_norm": 0.29296875,
      "learning_rate": 0.000755,
      "loss": 2.6047,
      "step": 302
    },
    {
      "epoch": 0.02912621359223301,
      "grad_norm": 0.294921875,
      "learning_rate": 0.0007574999999999999,
      "loss": 2.6485,
      "step": 303
    },
    {
      "epoch": 0.029408992364973137,
      "grad_norm": 0.27734375,
      "learning_rate": 0.00076,
      "loss": 2.6501,
      "step": 304
    },
    {
      "epoch": 0.029691771137713263,
      "grad_norm": 0.283203125,
      "learning_rate": 0.0007624999999999999,
      "loss": 2.7025,
      "step": 305
    },
    {
      "epoch": 0.02997454991045339,
      "grad_norm": 0.28125,
      "learning_rate": 0.0007650000000000001,
      "loss": 2.6906,
      "step": 306
    },
    {
      "epoch": 0.030257328683193516,
      "grad_norm": 0.279296875,
      "learning_rate": 0.0007675,
      "loss": 2.6791,
      "step": 307
    },
    {
      "epoch": 0.030540107455933642,
      "grad_norm": 0.29296875,
      "learning_rate": 0.0007700000000000001,
      "loss": 2.6582,
      "step": 308
    },
    {
      "epoch": 0.030822886228673768,
      "grad_norm": 0.275390625,
      "learning_rate": 0.0007725,
      "loss": 2.6284,
      "step": 309
    },
    {
      "epoch": 0.031105665001413894,
      "grad_norm": 0.283203125,
      "learning_rate": 0.0007750000000000001,
      "loss": 2.5862,
      "step": 310
    },
    {
      "epoch": 0.03138844377415402,
      "grad_norm": 0.294921875,
      "learning_rate": 0.0007775,
      "loss": 2.5938,
      "step": 311
    },
    {
      "epoch": 0.03167122254689415,
      "grad_norm": 0.337890625,
      "learning_rate": 0.0007800000000000001,
      "loss": 2.6905,
      "step": 312
    },
    {
      "epoch": 0.03195400131963427,
      "grad_norm": 0.3203125,
      "learning_rate": 0.0007825,
      "loss": 2.616,
      "step": 313
    },
    {
      "epoch": 0.0322367800923744,
      "grad_norm": 0.27734375,
      "learning_rate": 0.000785,
      "loss": 2.69,
      "step": 314
    },
    {
      "epoch": 0.032519558865114526,
      "grad_norm": 0.34765625,
      "learning_rate": 0.0007875,
      "loss": 2.8319,
      "step": 315
    },
    {
      "epoch": 0.03280233763785465,
      "grad_norm": 0.306640625,
      "learning_rate": 0.00079,
      "loss": 2.6675,
      "step": 316
    },
    {
      "epoch": 0.03308511641059478,
      "grad_norm": 0.283203125,
      "learning_rate": 0.0007925,
      "loss": 2.6262,
      "step": 317
    },
    {
      "epoch": 0.033367895183334904,
      "grad_norm": 0.29296875,
      "learning_rate": 0.000795,
      "loss": 2.6528,
      "step": 318
    },
    {
      "epoch": 0.03365067395607503,
      "grad_norm": 0.283203125,
      "learning_rate": 0.0007975,
      "loss": 2.7038,
      "step": 319
    },
    {
      "epoch": 0.03393345272881516,
      "grad_norm": 0.31640625,
      "learning_rate": 0.0008,
      "loss": 2.6198,
      "step": 320
    },
    {
      "epoch": 0.03421623150155528,
      "grad_norm": 0.3046875,
      "learning_rate": 0.0008025,
      "loss": 2.6152,
      "step": 321
    },
    {
      "epoch": 0.03449901027429541,
      "grad_norm": 0.296875,
      "learning_rate": 0.000805,
      "loss": 2.6731,
      "step": 322
    },
    {
      "epoch": 0.034781789047035536,
      "grad_norm": 0.287109375,
      "learning_rate": 0.0008075000000000001,
      "loss": 2.5537,
      "step": 323
    },
    {
      "epoch": 0.03506456781977566,
      "grad_norm": 0.28515625,
      "learning_rate": 0.0008100000000000001,
      "loss": 2.6532,
      "step": 324
    },
    {
      "epoch": 0.03534734659251579,
      "grad_norm": 0.306640625,
      "learning_rate": 0.0008125000000000001,
      "loss": 2.6131,
      "step": 325
    },
    {
      "epoch": 0.035630125365255914,
      "grad_norm": 0.298828125,
      "learning_rate": 0.000815,
      "loss": 2.8196,
      "step": 326
    },
    {
      "epoch": 0.03591290413799604,
      "grad_norm": 0.296875,
      "learning_rate": 0.0008175,
      "loss": 2.7387,
      "step": 327
    },
    {
      "epoch": 0.03619568291073617,
      "grad_norm": 0.28125,
      "learning_rate": 0.00082,
      "loss": 2.5512,
      "step": 328
    },
    {
      "epoch": 0.03647846168347629,
      "grad_norm": 0.306640625,
      "learning_rate": 0.0008225,
      "loss": 2.5846,
      "step": 329
    },
    {
      "epoch": 0.03676124045621642,
      "grad_norm": 0.298828125,
      "learning_rate": 0.000825,
      "loss": 2.5956,
      "step": 330
    },
    {
      "epoch": 0.037044019228956546,
      "grad_norm": 0.294921875,
      "learning_rate": 0.0008275,
      "loss": 2.7389,
      "step": 331
    },
    {
      "epoch": 0.03732679800169667,
      "grad_norm": 0.298828125,
      "learning_rate": 0.00083,
      "loss": 2.6311,
      "step": 332
    },
    {
      "epoch": 0.0376095767744368,
      "grad_norm": 0.326171875,
      "learning_rate": 0.0008325,
      "loss": 2.6184,
      "step": 333
    },
    {
      "epoch": 0.037892355547176924,
      "grad_norm": 0.283203125,
      "learning_rate": 0.000835,
      "loss": 2.636,
      "step": 334
    },
    {
      "epoch": 0.03817513431991705,
      "grad_norm": 0.287109375,
      "learning_rate": 0.0008375,
      "loss": 2.6349,
      "step": 335
    },
    {
      "epoch": 0.03845791309265718,
      "grad_norm": 0.294921875,
      "learning_rate": 0.00084,
      "loss": 2.7591,
      "step": 336
    },
    {
      "epoch": 0.0387406918653973,
      "grad_norm": 0.306640625,
      "learning_rate": 0.0008425,
      "loss": 2.6488,
      "step": 337
    },
    {
      "epoch": 0.03902347063813743,
      "grad_norm": 0.296875,
      "learning_rate": 0.0008449999999999999,
      "loss": 2.7071,
      "step": 338
    },
    {
      "epoch": 0.039306249410877556,
      "grad_norm": 0.294921875,
      "learning_rate": 0.0008475000000000001,
      "loss": 2.6898,
      "step": 339
    },
    {
      "epoch": 0.03958902818361768,
      "grad_norm": 0.291015625,
      "learning_rate": 0.00085,
      "loss": 2.7495,
      "step": 340
    },
    {
      "epoch": 0.03987180695635781,
      "grad_norm": 0.291015625,
      "learning_rate": 0.0008525000000000001,
      "loss": 2.7161,
      "step": 341
    },
    {
      "epoch": 0.040154585729097934,
      "grad_norm": 0.294921875,
      "learning_rate": 0.000855,
      "loss": 2.7001,
      "step": 342
    },
    {
      "epoch": 0.04043736450183806,
      "grad_norm": 0.291015625,
      "learning_rate": 0.0008575000000000001,
      "loss": 2.5912,
      "step": 343
    },
    {
      "epoch": 0.04072014327457819,
      "grad_norm": 0.306640625,
      "learning_rate": 0.00086,
      "loss": 2.6331,
      "step": 344
    },
    {
      "epoch": 0.04100292204731831,
      "grad_norm": 0.30078125,
      "learning_rate": 0.0008625000000000001,
      "loss": 2.6789,
      "step": 345
    },
    {
      "epoch": 0.04128570082005844,
      "grad_norm": 0.3046875,
      "learning_rate": 0.000865,
      "loss": 2.7028,
      "step": 346
    },
    {
      "epoch": 0.041568479592798566,
      "grad_norm": 0.30859375,
      "learning_rate": 0.0008675000000000001,
      "loss": 2.6873,
      "step": 347
    },
    {
      "epoch": 0.04185125836553869,
      "grad_norm": 0.3046875,
      "learning_rate": 0.00087,
      "loss": 2.665,
      "step": 348
    },
    {
      "epoch": 0.04213403713827882,
      "grad_norm": 0.287109375,
      "learning_rate": 0.0008725000000000001,
      "loss": 2.6889,
      "step": 349
    },
    {
      "epoch": 0.042416815911018944,
      "grad_norm": 0.294921875,
      "learning_rate": 0.000875,
      "loss": 2.5852,
      "step": 350
    },
    {
      "epoch": 0.04269959468375907,
      "grad_norm": 0.306640625,
      "learning_rate": 0.0008774999999999999,
      "loss": 2.5664,
      "step": 351
    },
    {
      "epoch": 0.0429823734564992,
      "grad_norm": 0.310546875,
      "learning_rate": 0.00088,
      "loss": 2.6956,
      "step": 352
    },
    {
      "epoch": 0.04326515222923932,
      "grad_norm": 0.3125,
      "learning_rate": 0.0008824999999999999,
      "loss": 2.6734,
      "step": 353
    },
    {
      "epoch": 0.04354793100197945,
      "grad_norm": 0.294921875,
      "learning_rate": 0.000885,
      "loss": 2.6,
      "step": 354
    },
    {
      "epoch": 0.043830709774719576,
      "grad_norm": 0.318359375,
      "learning_rate": 0.0008874999999999999,
      "loss": 2.6017,
      "step": 355
    },
    {
      "epoch": 0.0441134885474597,
      "grad_norm": 0.3125,
      "learning_rate": 0.0008900000000000001,
      "loss": 2.6188,
      "step": 356
    },
    {
      "epoch": 0.04439626732019983,
      "grad_norm": 0.291015625,
      "learning_rate": 0.0008925,
      "loss": 2.6405,
      "step": 357
    },
    {
      "epoch": 0.044679046092939954,
      "grad_norm": 0.2890625,
      "learning_rate": 0.0008950000000000001,
      "loss": 2.7035,
      "step": 358
    },
    {
      "epoch": 0.04496182486568008,
      "grad_norm": 0.279296875,
      "learning_rate": 0.0008975,
      "loss": 2.676,
      "step": 359
    },
    {
      "epoch": 0.04524460363842021,
      "grad_norm": 0.275390625,
      "learning_rate": 0.0009000000000000001,
      "loss": 2.553,
      "step": 360
    },
    {
      "epoch": 0.04552738241116033,
      "grad_norm": 0.29296875,
      "learning_rate": 0.0009025,
      "loss": 2.6944,
      "step": 361
    },
    {
      "epoch": 0.04581016118390046,
      "grad_norm": 0.3203125,
      "learning_rate": 0.0009050000000000001,
      "loss": 2.6527,
      "step": 362
    },
    {
      "epoch": 0.046092939956640586,
      "grad_norm": 0.287109375,
      "learning_rate": 0.0009075,
      "loss": 2.6531,
      "step": 363
    },
    {
      "epoch": 0.04637571872938071,
      "grad_norm": 0.291015625,
      "learning_rate": 0.00091,
      "loss": 2.6106,
      "step": 364
    },
    {
      "epoch": 0.04665849750212084,
      "grad_norm": 0.333984375,
      "learning_rate": 0.0009125,
      "loss": 2.6929,
      "step": 365
    },
    {
      "epoch": 0.046941276274860964,
      "grad_norm": 0.287109375,
      "learning_rate": 0.000915,
      "loss": 2.6441,
      "step": 366
    },
    {
      "epoch": 0.04722405504760109,
      "grad_norm": 0.28515625,
      "learning_rate": 0.0009175,
      "loss": 2.5974,
      "step": 367
    },
    {
      "epoch": 0.04750683382034122,
      "grad_norm": 0.302734375,
      "learning_rate": 0.00092,
      "loss": 2.676,
      "step": 368
    },
    {
      "epoch": 0.04778961259308134,
      "grad_norm": 0.298828125,
      "learning_rate": 0.0009225,
      "loss": 2.7611,
      "step": 369
    },
    {
      "epoch": 0.04807239136582147,
      "grad_norm": 0.296875,
      "learning_rate": 0.000925,
      "loss": 2.7243,
      "step": 370
    },
    {
      "epoch": 0.048355170138561596,
      "grad_norm": 0.275390625,
      "learning_rate": 0.0009275,
      "loss": 2.6278,
      "step": 371
    },
    {
      "epoch": 0.04863794891130172,
      "grad_norm": 0.298828125,
      "learning_rate": 0.00093,
      "loss": 2.681,
      "step": 372
    },
    {
      "epoch": 0.04892072768404185,
      "grad_norm": 0.310546875,
      "learning_rate": 0.0009325000000000001,
      "loss": 2.6493,
      "step": 373
    },
    {
      "epoch": 0.049203506456781974,
      "grad_norm": 0.30078125,
      "learning_rate": 0.0009350000000000001,
      "loss": 2.7624,
      "step": 374
    },
    {
      "epoch": 0.0494862852295221,
      "grad_norm": 0.30078125,
      "learning_rate": 0.0009375,
      "loss": 2.5307,
      "step": 375
    },
    {
      "epoch": 0.04976906400226223,
      "grad_norm": 0.30859375,
      "learning_rate": 0.00094,
      "loss": 2.5402,
      "step": 376
    },
    {
      "epoch": 0.05005184277500235,
      "grad_norm": 0.326171875,
      "learning_rate": 0.0009425,
      "loss": 2.7203,
      "step": 377
    },
    {
      "epoch": 0.05033462154774248,
      "grad_norm": 0.314453125,
      "learning_rate": 0.000945,
      "loss": 2.5387,
      "step": 378
    },
    {
      "epoch": 0.05061740032048261,
      "grad_norm": 0.326171875,
      "learning_rate": 0.0009475,
      "loss": 2.6619,
      "step": 379
    },
    {
      "epoch": 0.05090017909322274,
      "grad_norm": 0.322265625,
      "learning_rate": 0.00095,
      "loss": 2.5482,
      "step": 380
    },
    {
      "epoch": 0.051182957865962865,
      "grad_norm": 0.29296875,
      "learning_rate": 0.0009525,
      "loss": 2.6923,
      "step": 381
    },
    {
      "epoch": 0.05146573663870299,
      "grad_norm": 0.29296875,
      "learning_rate": 0.000955,
      "loss": 2.6563,
      "step": 382
    },
    {
      "epoch": 0.05174851541144312,
      "grad_norm": 0.30859375,
      "learning_rate": 0.0009575,
      "loss": 2.7508,
      "step": 383
    },
    {
      "epoch": 0.052031294184183244,
      "grad_norm": 0.306640625,
      "learning_rate": 0.00096,
      "loss": 2.6503,
      "step": 384
    },
    {
      "epoch": 0.05231407295692337,
      "grad_norm": 0.322265625,
      "learning_rate": 0.0009625,
      "loss": 2.5799,
      "step": 385
    },
    {
      "epoch": 0.052596851729663496,
      "grad_norm": 0.296875,
      "learning_rate": 0.000965,
      "loss": 2.7459,
      "step": 386
    },
    {
      "epoch": 0.05287963050240362,
      "grad_norm": 0.322265625,
      "learning_rate": 0.0009675,
      "loss": 2.693,
      "step": 387
    },
    {
      "epoch": 0.05316240927514375,
      "grad_norm": 0.30859375,
      "learning_rate": 0.0009699999999999999,
      "loss": 2.7552,
      "step": 388
    },
    {
      "epoch": 0.053445188047883875,
      "grad_norm": 0.29296875,
      "learning_rate": 0.0009725000000000001,
      "loss": 2.6024,
      "step": 389
    },
    {
      "epoch": 0.053727966820624,
      "grad_norm": 0.28125,
      "learning_rate": 0.000975,
      "loss": 2.6334,
      "step": 390
    },
    {
      "epoch": 0.05401074559336413,
      "grad_norm": 0.287109375,
      "learning_rate": 0.0009775,
      "loss": 2.5455,
      "step": 391
    },
    {
      "epoch": 0.054293524366104254,
      "grad_norm": 0.3046875,
      "learning_rate": 0.00098,
      "loss": 2.6543,
      "step": 392
    },
    {
      "epoch": 0.05457630313884438,
      "grad_norm": 0.287109375,
      "learning_rate": 0.0009825,
      "loss": 2.5376,
      "step": 393
    },
    {
      "epoch": 0.054859081911584506,
      "grad_norm": 0.287109375,
      "learning_rate": 0.000985,
      "loss": 2.606,
      "step": 394
    },
    {
      "epoch": 0.05514186068432463,
      "grad_norm": 0.3046875,
      "learning_rate": 0.0009875,
      "loss": 2.6413,
      "step": 395
    },
    {
      "epoch": 0.05542463945706476,
      "grad_norm": 0.283203125,
      "learning_rate": 0.00099,
      "loss": 2.6523,
      "step": 396
    },
    {
      "epoch": 0.055707418229804885,
      "grad_norm": 0.30078125,
      "learning_rate": 0.0009925000000000001,
      "loss": 2.6786,
      "step": 397
    },
    {
      "epoch": 0.05599019700254501,
      "grad_norm": 0.29296875,
      "learning_rate": 0.000995,
      "loss": 2.64,
      "step": 398
    },
    {
      "epoch": 0.05627297577528514,
      "grad_norm": 0.29296875,
      "learning_rate": 0.0009975000000000001,
      "loss": 2.6132,
      "step": 399
    },
    {
      "epoch": 0.056555754548025264,
      "grad_norm": 0.296875,
      "learning_rate": 0.001,
      "loss": 2.5936,
      "step": 400
    },
    {
      "epoch": 0.05683853332076539,
      "grad_norm": 0.27734375,
      "learning_rate": 0.001,
      "loss": 2.6395,
      "step": 401
    },
    {
      "epoch": 0.057121312093505516,
      "grad_norm": 0.298828125,
      "learning_rate": 0.001,
      "loss": 2.6744,
      "step": 402
    },
    {
      "epoch": 0.05740409086624564,
      "grad_norm": 0.3046875,
      "learning_rate": 0.001,
      "loss": 2.663,
      "step": 403
    },
    {
      "epoch": 0.05768686963898577,
      "grad_norm": 0.28125,
      "learning_rate": 0.001,
      "loss": 2.6422,
      "step": 404
    },
    {
      "epoch": 0.057969648411725895,
      "grad_norm": 0.283203125,
      "learning_rate": 0.001,
      "loss": 2.735,
      "step": 405
    },
    {
      "epoch": 0.05825242718446602,
      "grad_norm": 0.30859375,
      "learning_rate": 0.001,
      "loss": 2.5944,
      "step": 406
    },
    {
      "epoch": 0.05853520595720615,
      "grad_norm": 0.30078125,
      "learning_rate": 0.001,
      "loss": 2.6505,
      "step": 407
    },
    {
      "epoch": 0.058817984729946274,
      "grad_norm": 0.298828125,
      "learning_rate": 0.001,
      "loss": 2.59,
      "step": 408
    },
    {
      "epoch": 0.0591007635026864,
      "grad_norm": 0.3125,
      "learning_rate": 0.001,
      "loss": 2.6562,
      "step": 409
    },
    {
      "epoch": 0.059383542275426526,
      "grad_norm": 0.3671875,
      "learning_rate": 0.001,
      "loss": 2.6832,
      "step": 410
    },
    {
      "epoch": 0.05966632104816665,
      "grad_norm": 0.30859375,
      "learning_rate": 0.001,
      "loss": 2.7133,
      "step": 411
    },
    {
      "epoch": 0.05994909982090678,
      "grad_norm": 0.31640625,
      "learning_rate": 0.001,
      "loss": 2.7096,
      "step": 412
    },
    {
      "epoch": 0.060231878593646905,
      "grad_norm": 0.376953125,
      "learning_rate": 0.001,
      "loss": 2.7192,
      "step": 413
    },
    {
      "epoch": 0.06051465736638703,
      "grad_norm": 0.296875,
      "learning_rate": 0.001,
      "loss": 2.6494,
      "step": 414
    },
    {
      "epoch": 0.06079743613912716,
      "grad_norm": 0.30859375,
      "learning_rate": 0.001,
      "loss": 2.6594,
      "step": 415
    },
    {
      "epoch": 0.061080214911867284,
      "grad_norm": 0.296875,
      "learning_rate": 0.001,
      "loss": 2.6792,
      "step": 416
    },
    {
      "epoch": 0.06136299368460741,
      "grad_norm": 0.33984375,
      "learning_rate": 0.001,
      "loss": 2.771,
      "step": 417
    },
    {
      "epoch": 0.061645772457347536,
      "grad_norm": 0.29296875,
      "learning_rate": 0.001,
      "loss": 2.5395,
      "step": 418
    },
    {
      "epoch": 0.06192855123008766,
      "grad_norm": 0.28515625,
      "learning_rate": 0.001,
      "loss": 2.6015,
      "step": 419
    },
    {
      "epoch": 0.06221133000282779,
      "grad_norm": 0.302734375,
      "learning_rate": 0.001,
      "loss": 2.6022,
      "step": 420
    },
    {
      "epoch": 0.062494108775567915,
      "grad_norm": 0.3125,
      "learning_rate": 0.001,
      "loss": 2.5649,
      "step": 421
    },
    {
      "epoch": 0.06277688754830804,
      "grad_norm": 0.326171875,
      "learning_rate": 0.001,
      "loss": 2.6679,
      "step": 422
    },
    {
      "epoch": 0.06305966632104816,
      "grad_norm": 0.287109375,
      "learning_rate": 0.001,
      "loss": 2.7649,
      "step": 423
    },
    {
      "epoch": 0.0633424450937883,
      "grad_norm": 0.314453125,
      "learning_rate": 0.001,
      "loss": 2.6937,
      "step": 424
    },
    {
      "epoch": 0.06362522386652841,
      "grad_norm": 0.30859375,
      "learning_rate": 0.001,
      "loss": 2.6019,
      "step": 425
    },
    {
      "epoch": 0.06390800263926855,
      "grad_norm": 0.314453125,
      "learning_rate": 0.001,
      "loss": 2.7555,
      "step": 426
    },
    {
      "epoch": 0.06419078141200867,
      "grad_norm": 0.28515625,
      "learning_rate": 0.001,
      "loss": 2.712,
      "step": 427
    },
    {
      "epoch": 0.0644735601847488,
      "grad_norm": 0.3125,
      "learning_rate": 0.001,
      "loss": 2.6345,
      "step": 428
    },
    {
      "epoch": 0.06475633895748892,
      "grad_norm": 0.341796875,
      "learning_rate": 0.001,
      "loss": 2.6637,
      "step": 429
    },
    {
      "epoch": 0.06503911773022905,
      "grad_norm": 0.310546875,
      "learning_rate": 0.001,
      "loss": 2.6133,
      "step": 430
    },
    {
      "epoch": 0.06532189650296917,
      "grad_norm": 0.296875,
      "learning_rate": 0.001,
      "loss": 2.5122,
      "step": 431
    },
    {
      "epoch": 0.0656046752757093,
      "grad_norm": 0.306640625,
      "learning_rate": 0.001,
      "loss": 2.6504,
      "step": 432
    },
    {
      "epoch": 0.06588745404844942,
      "grad_norm": 0.314453125,
      "learning_rate": 0.001,
      "loss": 2.7061,
      "step": 433
    },
    {
      "epoch": 0.06617023282118956,
      "grad_norm": 0.322265625,
      "learning_rate": 0.001,
      "loss": 2.709,
      "step": 434
    },
    {
      "epoch": 0.06645301159392968,
      "grad_norm": 0.318359375,
      "learning_rate": 0.001,
      "loss": 2.5793,
      "step": 435
    },
    {
      "epoch": 0.06673579036666981,
      "grad_norm": 0.310546875,
      "learning_rate": 0.001,
      "loss": 2.6329,
      "step": 436
    },
    {
      "epoch": 0.06701856913940993,
      "grad_norm": 0.353515625,
      "learning_rate": 0.001,
      "loss": 2.5715,
      "step": 437
    },
    {
      "epoch": 0.06730134791215006,
      "grad_norm": 0.3125,
      "learning_rate": 0.001,
      "loss": 2.5859,
      "step": 438
    },
    {
      "epoch": 0.0675841266848902,
      "grad_norm": 0.3046875,
      "learning_rate": 0.001,
      "loss": 2.4683,
      "step": 439
    },
    {
      "epoch": 0.06786690545763031,
      "grad_norm": 0.30859375,
      "learning_rate": 0.001,
      "loss": 2.6868,
      "step": 440
    },
    {
      "epoch": 0.06814968423037045,
      "grad_norm": 0.29296875,
      "learning_rate": 0.001,
      "loss": 2.6378,
      "step": 441
    },
    {
      "epoch": 0.06843246300311057,
      "grad_norm": 0.306640625,
      "learning_rate": 0.001,
      "loss": 2.6701,
      "step": 442
    },
    {
      "epoch": 0.0687152417758507,
      "grad_norm": 0.296875,
      "learning_rate": 0.001,
      "loss": 2.6694,
      "step": 443
    },
    {
      "epoch": 0.06899802054859082,
      "grad_norm": 0.275390625,
      "learning_rate": 0.001,
      "loss": 2.6567,
      "step": 444
    },
    {
      "epoch": 0.06928079932133095,
      "grad_norm": 0.30078125,
      "learning_rate": 0.001,
      "loss": 2.6177,
      "step": 445
    },
    {
      "epoch": 0.06956357809407107,
      "grad_norm": 0.2890625,
      "learning_rate": 0.001,
      "loss": 2.6484,
      "step": 446
    },
    {
      "epoch": 0.0698463568668112,
      "grad_norm": 0.296875,
      "learning_rate": 0.001,
      "loss": 2.607,
      "step": 447
    },
    {
      "epoch": 0.07012913563955132,
      "grad_norm": 0.28515625,
      "learning_rate": 0.001,
      "loss": 2.6091,
      "step": 448
    },
    {
      "epoch": 0.07041191441229146,
      "grad_norm": 0.27734375,
      "learning_rate": 0.001,
      "loss": 2.6542,
      "step": 449
    },
    {
      "epoch": 0.07069469318503158,
      "grad_norm": 0.3046875,
      "learning_rate": 0.001,
      "loss": 2.6491,
      "step": 450
    },
    {
      "epoch": 0.07097747195777171,
      "grad_norm": 0.310546875,
      "learning_rate": 0.001,
      "loss": 2.5871,
      "step": 451
    },
    {
      "epoch": 0.07126025073051183,
      "grad_norm": 0.294921875,
      "learning_rate": 0.001,
      "loss": 2.5926,
      "step": 452
    },
    {
      "epoch": 0.07154302950325196,
      "grad_norm": 0.291015625,
      "learning_rate": 0.001,
      "loss": 2.729,
      "step": 453
    },
    {
      "epoch": 0.07182580827599208,
      "grad_norm": 0.29296875,
      "learning_rate": 0.001,
      "loss": 2.6517,
      "step": 454
    },
    {
      "epoch": 0.07210858704873221,
      "grad_norm": 0.283203125,
      "learning_rate": 0.001,
      "loss": 2.6714,
      "step": 455
    },
    {
      "epoch": 0.07239136582147233,
      "grad_norm": 0.275390625,
      "learning_rate": 0.001,
      "loss": 2.5205,
      "step": 456
    },
    {
      "epoch": 0.07267414459421247,
      "grad_norm": 0.322265625,
      "learning_rate": 0.001,
      "loss": 2.5694,
      "step": 457
    },
    {
      "epoch": 0.07295692336695259,
      "grad_norm": 0.306640625,
      "learning_rate": 0.001,
      "loss": 2.6391,
      "step": 458
    },
    {
      "epoch": 0.07323970213969272,
      "grad_norm": 0.2890625,
      "learning_rate": 0.001,
      "loss": 2.6492,
      "step": 459
    },
    {
      "epoch": 0.07352248091243284,
      "grad_norm": 0.29296875,
      "learning_rate": 0.001,
      "loss": 2.6153,
      "step": 460
    },
    {
      "epoch": 0.07380525968517297,
      "grad_norm": 0.318359375,
      "learning_rate": 0.001,
      "loss": 2.6975,
      "step": 461
    },
    {
      "epoch": 0.07408803845791309,
      "grad_norm": 0.322265625,
      "learning_rate": 0.001,
      "loss": 2.6751,
      "step": 462
    },
    {
      "epoch": 0.07437081723065322,
      "grad_norm": 0.3203125,
      "learning_rate": 0.001,
      "loss": 2.6519,
      "step": 463
    },
    {
      "epoch": 0.07465359600339334,
      "grad_norm": 0.3046875,
      "learning_rate": 0.001,
      "loss": 2.6895,
      "step": 464
    },
    {
      "epoch": 0.07493637477613348,
      "grad_norm": 0.287109375,
      "learning_rate": 0.001,
      "loss": 2.631,
      "step": 465
    },
    {
      "epoch": 0.0752191535488736,
      "grad_norm": 0.287109375,
      "learning_rate": 0.001,
      "loss": 2.5676,
      "step": 466
    },
    {
      "epoch": 0.07550193232161373,
      "grad_norm": 0.31640625,
      "learning_rate": 0.001,
      "loss": 2.6513,
      "step": 467
    },
    {
      "epoch": 0.07578471109435385,
      "grad_norm": 0.29296875,
      "learning_rate": 0.001,
      "loss": 2.6894,
      "step": 468
    },
    {
      "epoch": 0.07606748986709398,
      "grad_norm": 0.271484375,
      "learning_rate": 0.001,
      "loss": 2.552,
      "step": 469
    },
    {
      "epoch": 0.0763502686398341,
      "grad_norm": 0.29296875,
      "learning_rate": 0.001,
      "loss": 2.5399,
      "step": 470
    },
    {
      "epoch": 0.07663304741257423,
      "grad_norm": 0.29296875,
      "learning_rate": 0.001,
      "loss": 2.6246,
      "step": 471
    },
    {
      "epoch": 0.07691582618531435,
      "grad_norm": 0.296875,
      "learning_rate": 0.001,
      "loss": 2.5947,
      "step": 472
    },
    {
      "epoch": 0.07719860495805449,
      "grad_norm": 0.29296875,
      "learning_rate": 0.001,
      "loss": 2.6156,
      "step": 473
    },
    {
      "epoch": 0.0774813837307946,
      "grad_norm": 0.30078125,
      "learning_rate": 0.001,
      "loss": 2.6151,
      "step": 474
    },
    {
      "epoch": 0.07776416250353474,
      "grad_norm": 0.306640625,
      "learning_rate": 0.001,
      "loss": 2.6091,
      "step": 475
    },
    {
      "epoch": 0.07804694127627486,
      "grad_norm": 0.2890625,
      "learning_rate": 0.001,
      "loss": 2.6397,
      "step": 476
    },
    {
      "epoch": 0.07832972004901499,
      "grad_norm": 0.283203125,
      "learning_rate": 0.001,
      "loss": 2.6125,
      "step": 477
    },
    {
      "epoch": 0.07861249882175511,
      "grad_norm": 0.32421875,
      "learning_rate": 0.001,
      "loss": 2.6975,
      "step": 478
    },
    {
      "epoch": 0.07889527759449524,
      "grad_norm": 0.30859375,
      "learning_rate": 0.001,
      "loss": 2.6668,
      "step": 479
    },
    {
      "epoch": 0.07917805636723536,
      "grad_norm": 0.27734375,
      "learning_rate": 0.001,
      "loss": 2.6315,
      "step": 480
    },
    {
      "epoch": 0.0794608351399755,
      "grad_norm": 0.291015625,
      "learning_rate": 0.001,
      "loss": 2.6247,
      "step": 481
    },
    {
      "epoch": 0.07974361391271562,
      "grad_norm": 0.29296875,
      "learning_rate": 0.001,
      "loss": 2.5352,
      "step": 482
    },
    {
      "epoch": 0.08002639268545575,
      "grad_norm": 0.2890625,
      "learning_rate": 0.001,
      "loss": 2.6061,
      "step": 483
    },
    {
      "epoch": 0.08030917145819587,
      "grad_norm": 0.296875,
      "learning_rate": 0.001,
      "loss": 2.7082,
      "step": 484
    },
    {
      "epoch": 0.080591950230936,
      "grad_norm": 0.283203125,
      "learning_rate": 0.001,
      "loss": 2.5379,
      "step": 485
    },
    {
      "epoch": 0.08087472900367612,
      "grad_norm": 0.27734375,
      "learning_rate": 0.001,
      "loss": 2.4968,
      "step": 486
    },
    {
      "epoch": 0.08115750777641625,
      "grad_norm": 0.30859375,
      "learning_rate": 0.001,
      "loss": 2.6454,
      "step": 487
    },
    {
      "epoch": 0.08144028654915637,
      "grad_norm": 0.296875,
      "learning_rate": 0.001,
      "loss": 2.5961,
      "step": 488
    },
    {
      "epoch": 0.08172306532189651,
      "grad_norm": 0.296875,
      "learning_rate": 0.001,
      "loss": 2.5747,
      "step": 489
    },
    {
      "epoch": 0.08200584409463663,
      "grad_norm": 0.28125,
      "learning_rate": 0.001,
      "loss": 2.6152,
      "step": 490
    },
    {
      "epoch": 0.08228862286737676,
      "grad_norm": 0.28515625,
      "learning_rate": 0.001,
      "loss": 2.6164,
      "step": 491
    },
    {
      "epoch": 0.08257140164011688,
      "grad_norm": 0.283203125,
      "learning_rate": 0.001,
      "loss": 2.6652,
      "step": 492
    },
    {
      "epoch": 0.08285418041285701,
      "grad_norm": 0.28515625,
      "learning_rate": 0.001,
      "loss": 2.6285,
      "step": 493
    },
    {
      "epoch": 0.08313695918559713,
      "grad_norm": 0.2734375,
      "learning_rate": 0.001,
      "loss": 2.6251,
      "step": 494
    },
    {
      "epoch": 0.08341973795833726,
      "grad_norm": 0.283203125,
      "learning_rate": 0.001,
      "loss": 2.59,
      "step": 495
    },
    {
      "epoch": 0.08370251673107738,
      "grad_norm": 0.2734375,
      "learning_rate": 0.001,
      "loss": 2.7047,
      "step": 496
    },
    {
      "epoch": 0.08398529550381752,
      "grad_norm": 0.3046875,
      "learning_rate": 0.001,
      "loss": 2.6543,
      "step": 497
    },
    {
      "epoch": 0.08426807427655764,
      "grad_norm": 0.294921875,
      "learning_rate": 0.001,
      "loss": 2.621,
      "step": 498
    },
    {
      "epoch": 0.08455085304929777,
      "grad_norm": 0.287109375,
      "learning_rate": 0.001,
      "loss": 2.6055,
      "step": 499
    },
    {
      "epoch": 0.08483363182203789,
      "grad_norm": 0.283203125,
      "learning_rate": 0.001,
      "loss": 2.6596,
      "step": 500
    },
    {
      "epoch": 0.08511641059477802,
      "grad_norm": 0.291015625,
      "learning_rate": 0.001,
      "loss": 2.6667,
      "step": 501
    },
    {
      "epoch": 0.08539918936751814,
      "grad_norm": 0.291015625,
      "learning_rate": 0.001,
      "loss": 2.635,
      "step": 502
    },
    {
      "epoch": 0.08568196814025827,
      "grad_norm": 0.30078125,
      "learning_rate": 0.001,
      "loss": 2.6392,
      "step": 503
    },
    {
      "epoch": 0.0859647469129984,
      "grad_norm": 0.3046875,
      "learning_rate": 0.001,
      "loss": 2.7342,
      "step": 504
    },
    {
      "epoch": 0.08624752568573853,
      "grad_norm": 0.302734375,
      "learning_rate": 0.001,
      "loss": 2.713,
      "step": 505
    },
    {
      "epoch": 0.08653030445847865,
      "grad_norm": 0.32421875,
      "learning_rate": 0.001,
      "loss": 2.574,
      "step": 506
    },
    {
      "epoch": 0.08681308323121878,
      "grad_norm": 0.291015625,
      "learning_rate": 0.001,
      "loss": 2.69,
      "step": 507
    },
    {
      "epoch": 0.0870958620039589,
      "grad_norm": 0.298828125,
      "learning_rate": 0.001,
      "loss": 2.6181,
      "step": 508
    },
    {
      "epoch": 0.08737864077669903,
      "grad_norm": 0.3046875,
      "learning_rate": 0.001,
      "loss": 2.6711,
      "step": 509
    },
    {
      "epoch": 0.08766141954943915,
      "grad_norm": 0.279296875,
      "learning_rate": 0.001,
      "loss": 2.727,
      "step": 510
    },
    {
      "epoch": 0.08794419832217928,
      "grad_norm": 0.376953125,
      "learning_rate": 0.001,
      "loss": 2.6604,
      "step": 511
    },
    {
      "epoch": 0.0882269770949194,
      "grad_norm": 0.3203125,
      "learning_rate": 0.001,
      "loss": 2.7977,
      "step": 512
    },
    {
      "epoch": 0.08850975586765954,
      "grad_norm": 0.318359375,
      "learning_rate": 0.001,
      "loss": 2.6014,
      "step": 513
    },
    {
      "epoch": 0.08879253464039966,
      "grad_norm": 0.30078125,
      "learning_rate": 0.001,
      "loss": 2.6596,
      "step": 514
    },
    {
      "epoch": 0.08907531341313979,
      "grad_norm": 0.296875,
      "learning_rate": 0.001,
      "loss": 2.7032,
      "step": 515
    },
    {
      "epoch": 0.08935809218587991,
      "grad_norm": 0.310546875,
      "learning_rate": 0.001,
      "loss": 2.6362,
      "step": 516
    },
    {
      "epoch": 0.08964087095862004,
      "grad_norm": 0.322265625,
      "learning_rate": 0.001,
      "loss": 2.6397,
      "step": 517
    },
    {
      "epoch": 0.08992364973136016,
      "grad_norm": 0.296875,
      "learning_rate": 0.001,
      "loss": 2.7293,
      "step": 518
    },
    {
      "epoch": 0.0902064285041003,
      "grad_norm": 0.3125,
      "learning_rate": 0.001,
      "loss": 2.6345,
      "step": 519
    },
    {
      "epoch": 0.09048920727684041,
      "grad_norm": 0.310546875,
      "learning_rate": 0.001,
      "loss": 2.6847,
      "step": 520
    },
    {
      "epoch": 0.09077198604958055,
      "grad_norm": 0.298828125,
      "learning_rate": 0.001,
      "loss": 2.564,
      "step": 521
    },
    {
      "epoch": 0.09105476482232067,
      "grad_norm": 0.3125,
      "learning_rate": 0.001,
      "loss": 2.6334,
      "step": 522
    },
    {
      "epoch": 0.0913375435950608,
      "grad_norm": 0.27734375,
      "learning_rate": 0.001,
      "loss": 2.5749,
      "step": 523
    },
    {
      "epoch": 0.09162032236780092,
      "grad_norm": 0.314453125,
      "learning_rate": 0.001,
      "loss": 2.6195,
      "step": 524
    },
    {
      "epoch": 0.09190310114054105,
      "grad_norm": 0.314453125,
      "learning_rate": 0.001,
      "loss": 2.6638,
      "step": 525
    },
    {
      "epoch": 0.09218587991328117,
      "grad_norm": 0.2890625,
      "learning_rate": 0.001,
      "loss": 2.7185,
      "step": 526
    },
    {
      "epoch": 0.0924686586860213,
      "grad_norm": 0.64453125,
      "learning_rate": 0.001,
      "loss": 2.5877,
      "step": 527
    },
    {
      "epoch": 0.09275143745876142,
      "grad_norm": 0.298828125,
      "learning_rate": 0.001,
      "loss": 2.6217,
      "step": 528
    },
    {
      "epoch": 0.09303421623150156,
      "grad_norm": 0.294921875,
      "learning_rate": 0.001,
      "loss": 2.6648,
      "step": 529
    },
    {
      "epoch": 0.09331699500424168,
      "grad_norm": 0.302734375,
      "learning_rate": 0.001,
      "loss": 2.7246,
      "step": 530
    },
    {
      "epoch": 0.09359977377698181,
      "grad_norm": 0.287109375,
      "learning_rate": 0.001,
      "loss": 2.5819,
      "step": 531
    },
    {
      "epoch": 0.09388255254972193,
      "grad_norm": 0.283203125,
      "learning_rate": 0.001,
      "loss": 2.7524,
      "step": 532
    },
    {
      "epoch": 0.09416533132246206,
      "grad_norm": 0.28125,
      "learning_rate": 0.001,
      "loss": 2.6425,
      "step": 533
    },
    {
      "epoch": 0.09444811009520218,
      "grad_norm": 0.2890625,
      "learning_rate": 0.001,
      "loss": 2.6648,
      "step": 534
    },
    {
      "epoch": 0.09473088886794231,
      "grad_norm": 0.298828125,
      "learning_rate": 0.001,
      "loss": 2.6728,
      "step": 535
    },
    {
      "epoch": 0.09501366764068243,
      "grad_norm": 0.328125,
      "learning_rate": 0.001,
      "loss": 2.774,
      "step": 536
    },
    {
      "epoch": 0.09529644641342257,
      "grad_norm": 0.3125,
      "learning_rate": 0.001,
      "loss": 2.5793,
      "step": 537
    },
    {
      "epoch": 0.09557922518616269,
      "grad_norm": 0.279296875,
      "learning_rate": 0.001,
      "loss": 2.6956,
      "step": 538
    },
    {
      "epoch": 0.09586200395890282,
      "grad_norm": 0.294921875,
      "learning_rate": 0.001,
      "loss": 2.7181,
      "step": 539
    },
    {
      "epoch": 0.09614478273164294,
      "grad_norm": 0.3203125,
      "learning_rate": 0.001,
      "loss": 2.5904,
      "step": 540
    },
    {
      "epoch": 0.09642756150438307,
      "grad_norm": 0.30078125,
      "learning_rate": 0.001,
      "loss": 2.6337,
      "step": 541
    },
    {
      "epoch": 0.09671034027712319,
      "grad_norm": 0.3046875,
      "learning_rate": 0.001,
      "loss": 2.7056,
      "step": 542
    },
    {
      "epoch": 0.09699311904986332,
      "grad_norm": 0.296875,
      "learning_rate": 0.001,
      "loss": 2.6911,
      "step": 543
    },
    {
      "epoch": 0.09727589782260344,
      "grad_norm": 0.3046875,
      "learning_rate": 0.001,
      "loss": 2.5719,
      "step": 544
    },
    {
      "epoch": 0.09755867659534358,
      "grad_norm": 0.29296875,
      "learning_rate": 0.001,
      "loss": 2.7003,
      "step": 545
    },
    {
      "epoch": 0.0978414553680837,
      "grad_norm": 0.333984375,
      "learning_rate": 0.001,
      "loss": 2.6589,
      "step": 546
    },
    {
      "epoch": 0.09812423414082383,
      "grad_norm": 0.2890625,
      "learning_rate": 0.001,
      "loss": 2.6169,
      "step": 547
    },
    {
      "epoch": 0.09840701291356395,
      "grad_norm": 0.296875,
      "learning_rate": 0.001,
      "loss": 2.7062,
      "step": 548
    },
    {
      "epoch": 0.09868979168630408,
      "grad_norm": 0.3203125,
      "learning_rate": 0.001,
      "loss": 2.6251,
      "step": 549
    },
    {
      "epoch": 0.0989725704590442,
      "grad_norm": 0.302734375,
      "learning_rate": 0.001,
      "loss": 2.6212,
      "step": 550
    },
    {
      "epoch": 0.09925534923178433,
      "grad_norm": 0.3046875,
      "learning_rate": 0.001,
      "loss": 2.6516,
      "step": 551
    },
    {
      "epoch": 0.09953812800452445,
      "grad_norm": 0.294921875,
      "learning_rate": 0.001,
      "loss": 2.6951,
      "step": 552
    },
    {
      "epoch": 0.09982090677726459,
      "grad_norm": 0.302734375,
      "learning_rate": 0.001,
      "loss": 2.609,
      "step": 553
    },
    {
      "epoch": 0.1001036855500047,
      "grad_norm": 0.296875,
      "learning_rate": 0.001,
      "loss": 2.5634,
      "step": 554
    },
    {
      "epoch": 0.10038646432274484,
      "grad_norm": 0.3046875,
      "learning_rate": 0.001,
      "loss": 2.7114,
      "step": 555
    },
    {
      "epoch": 0.10066924309548496,
      "grad_norm": 0.283203125,
      "learning_rate": 0.001,
      "loss": 2.7047,
      "step": 556
    },
    {
      "epoch": 0.10095202186822509,
      "grad_norm": 0.296875,
      "learning_rate": 0.001,
      "loss": 2.6757,
      "step": 557
    },
    {
      "epoch": 0.10123480064096523,
      "grad_norm": 0.33984375,
      "learning_rate": 0.001,
      "loss": 2.6441,
      "step": 558
    },
    {
      "epoch": 0.10151757941370534,
      "grad_norm": 0.3046875,
      "learning_rate": 0.001,
      "loss": 2.6233,
      "step": 559
    },
    {
      "epoch": 0.10180035818644548,
      "grad_norm": 0.2890625,
      "learning_rate": 0.001,
      "loss": 2.608,
      "step": 560
    },
    {
      "epoch": 0.1020831369591856,
      "grad_norm": 0.2734375,
      "learning_rate": 0.001,
      "loss": 2.6825,
      "step": 561
    },
    {
      "epoch": 0.10236591573192573,
      "grad_norm": 0.298828125,
      "learning_rate": 0.001,
      "loss": 2.6709,
      "step": 562
    },
    {
      "epoch": 0.10264869450466585,
      "grad_norm": 0.333984375,
      "learning_rate": 0.001,
      "loss": 2.6721,
      "step": 563
    },
    {
      "epoch": 0.10293147327740598,
      "grad_norm": 0.291015625,
      "learning_rate": 0.001,
      "loss": 2.6968,
      "step": 564
    },
    {
      "epoch": 0.1032142520501461,
      "grad_norm": 0.291015625,
      "learning_rate": 0.001,
      "loss": 2.6053,
      "step": 565
    },
    {
      "epoch": 0.10349703082288624,
      "grad_norm": 0.2890625,
      "learning_rate": 0.001,
      "loss": 2.661,
      "step": 566
    },
    {
      "epoch": 0.10377980959562635,
      "grad_norm": 0.298828125,
      "learning_rate": 0.001,
      "loss": 2.7619,
      "step": 567
    },
    {
      "epoch": 0.10406258836836649,
      "grad_norm": 0.310546875,
      "learning_rate": 0.001,
      "loss": 2.7159,
      "step": 568
    },
    {
      "epoch": 0.1043453671411066,
      "grad_norm": 0.30078125,
      "learning_rate": 0.001,
      "loss": 2.6082,
      "step": 569
    },
    {
      "epoch": 0.10462814591384674,
      "grad_norm": 0.302734375,
      "learning_rate": 0.001,
      "loss": 2.5665,
      "step": 570
    },
    {
      "epoch": 0.10491092468658686,
      "grad_norm": 0.28125,
      "learning_rate": 0.001,
      "loss": 2.6323,
      "step": 571
    },
    {
      "epoch": 0.10519370345932699,
      "grad_norm": 0.2734375,
      "learning_rate": 0.001,
      "loss": 2.5845,
      "step": 572
    },
    {
      "epoch": 0.10547648223206711,
      "grad_norm": 0.33984375,
      "learning_rate": 0.001,
      "loss": 2.6217,
      "step": 573
    },
    {
      "epoch": 0.10575926100480725,
      "grad_norm": 0.3125,
      "learning_rate": 0.001,
      "loss": 2.6912,
      "step": 574
    },
    {
      "epoch": 0.10604203977754736,
      "grad_norm": 0.30859375,
      "learning_rate": 0.001,
      "loss": 2.7181,
      "step": 575
    },
    {
      "epoch": 0.1063248185502875,
      "grad_norm": 0.29296875,
      "learning_rate": 0.001,
      "loss": 2.7315,
      "step": 576
    },
    {
      "epoch": 0.10660759732302762,
      "grad_norm": 0.3125,
      "learning_rate": 0.001,
      "loss": 2.6777,
      "step": 577
    },
    {
      "epoch": 0.10689037609576775,
      "grad_norm": 0.330078125,
      "learning_rate": 0.001,
      "loss": 2.6848,
      "step": 578
    },
    {
      "epoch": 0.10717315486850787,
      "grad_norm": 0.333984375,
      "learning_rate": 0.001,
      "loss": 2.6643,
      "step": 579
    },
    {
      "epoch": 0.107455933641248,
      "grad_norm": 0.318359375,
      "learning_rate": 0.001,
      "loss": 2.6628,
      "step": 580
    },
    {
      "epoch": 0.10773871241398812,
      "grad_norm": 0.310546875,
      "learning_rate": 0.001,
      "loss": 2.6079,
      "step": 581
    },
    {
      "epoch": 0.10802149118672826,
      "grad_norm": 0.328125,
      "learning_rate": 0.001,
      "loss": 2.6305,
      "step": 582
    },
    {
      "epoch": 0.10830426995946837,
      "grad_norm": 0.30078125,
      "learning_rate": 0.001,
      "loss": 2.6973,
      "step": 583
    },
    {
      "epoch": 0.10858704873220851,
      "grad_norm": 0.275390625,
      "learning_rate": 0.001,
      "loss": 2.5784,
      "step": 584
    },
    {
      "epoch": 0.10886982750494863,
      "grad_norm": 0.29296875,
      "learning_rate": 0.001,
      "loss": 2.603,
      "step": 585
    },
    {
      "epoch": 0.10915260627768876,
      "grad_norm": 0.33984375,
      "learning_rate": 0.001,
      "loss": 2.6049,
      "step": 586
    },
    {
      "epoch": 0.10943538505042888,
      "grad_norm": 0.291015625,
      "learning_rate": 0.001,
      "loss": 2.6915,
      "step": 587
    },
    {
      "epoch": 0.10971816382316901,
      "grad_norm": 0.2734375,
      "learning_rate": 0.001,
      "loss": 2.6749,
      "step": 588
    },
    {
      "epoch": 0.11000094259590913,
      "grad_norm": 0.283203125,
      "learning_rate": 0.001,
      "loss": 2.659,
      "step": 589
    },
    {
      "epoch": 0.11028372136864927,
      "grad_norm": 0.294921875,
      "learning_rate": 0.001,
      "loss": 2.7775,
      "step": 590
    },
    {
      "epoch": 0.11056650014138938,
      "grad_norm": 0.28515625,
      "learning_rate": 0.001,
      "loss": 2.609,
      "step": 591
    },
    {
      "epoch": 0.11084927891412952,
      "grad_norm": 0.279296875,
      "learning_rate": 0.001,
      "loss": 2.7279,
      "step": 592
    },
    {
      "epoch": 0.11113205768686964,
      "grad_norm": 0.283203125,
      "learning_rate": 0.001,
      "loss": 2.6605,
      "step": 593
    },
    {
      "epoch": 0.11141483645960977,
      "grad_norm": 0.28515625,
      "learning_rate": 0.001,
      "loss": 2.5454,
      "step": 594
    },
    {
      "epoch": 0.11169761523234989,
      "grad_norm": 0.287109375,
      "learning_rate": 0.001,
      "loss": 2.7252,
      "step": 595
    },
    {
      "epoch": 0.11198039400509002,
      "grad_norm": 0.275390625,
      "learning_rate": 0.001,
      "loss": 2.706,
      "step": 596
    },
    {
      "epoch": 0.11226317277783014,
      "grad_norm": 0.27734375,
      "learning_rate": 0.001,
      "loss": 2.797,
      "step": 597
    },
    {
      "epoch": 0.11254595155057028,
      "grad_norm": 0.296875,
      "learning_rate": 0.001,
      "loss": 2.7828,
      "step": 598
    },
    {
      "epoch": 0.1128287303233104,
      "grad_norm": 0.298828125,
      "learning_rate": 0.001,
      "loss": 2.6853,
      "step": 599
    },
    {
      "epoch": 0.11311150909605053,
      "grad_norm": 0.2734375,
      "learning_rate": 0.001,
      "loss": 2.7337,
      "step": 600
    },
    {
      "epoch": 0.11311150909605053,
      "eval_loss": 1.8316214084625244,
      "eval_runtime": 35.2615,
      "eval_samples_per_second": 29.04,
      "eval_steps_per_second": 0.908,
      "step": 600
    },
    {
      "epoch": 0.11311150909605053,
      "eval/hellaswag_acc": 0.3759211312487552,
      "eval/hellaswag_acc_norm": 0.47301334395538736,
      "eval_hellaswag_elapsed_time": 170.16831135749817,
      "step": 600
    }
  ],
  "logging_steps": 1,
  "max_steps": 3536,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.0933691001798656e+18,
  "train_batch_size": 36,
  "trial_name": null,
  "trial_params": null
}