{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08483363182203789,
  "eval_steps": 300,
  "global_step": 300,
  "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
    }
  ],
  "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": 1.0466845500899328e+18,
  "train_batch_size": 36,
  "trial_name": null,
  "trial_params": null
}