{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.808664259927799,
  "eval_steps": 25,
  "global_step": 510,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.019253910950661854,
      "grad_norm": 65.07794952392578,
      "learning_rate": 2e-05,
      "loss": 10.0254,
      "step": 1
    },
    {
      "epoch": 0.03850782190132371,
      "grad_norm": 35.06503677368164,
      "learning_rate": 2e-05,
      "loss": 9.6326,
      "step": 2
    },
    {
      "epoch": 0.05776173285198556,
      "grad_norm": Infinity,
      "learning_rate": 2e-05,
      "loss": 9.7444,
      "step": 3
    },
    {
      "epoch": 0.07701564380264742,
      "grad_norm": 91.54127502441406,
      "learning_rate": 2e-05,
      "loss": 9.9694,
      "step": 4
    },
    {
      "epoch": 0.09626955475330927,
      "grad_norm": 48.64268493652344,
      "learning_rate": 2e-05,
      "loss": 9.777,
      "step": 5
    },
    {
      "epoch": 0.11552346570397112,
      "grad_norm": 45.61400604248047,
      "learning_rate": 2e-05,
      "loss": 9.6125,
      "step": 6
    },
    {
      "epoch": 0.13477737665463296,
      "grad_norm": 53.380062103271484,
      "learning_rate": 2e-05,
      "loss": 9.6476,
      "step": 7
    },
    {
      "epoch": 0.15403128760529483,
      "grad_norm": 48.681732177734375,
      "learning_rate": 2e-05,
      "loss": 9.5976,
      "step": 8
    },
    {
      "epoch": 0.17328519855595667,
      "grad_norm": 75.82644653320312,
      "learning_rate": 2e-05,
      "loss": 9.635,
      "step": 9
    },
    {
      "epoch": 0.19253910950661854,
      "grad_norm": 52.92415237426758,
      "learning_rate": 2e-05,
      "loss": 9.4741,
      "step": 10
    },
    {
      "epoch": 0.21179302045728038,
      "grad_norm": 45.76670455932617,
      "learning_rate": 2e-05,
      "loss": 9.4043,
      "step": 11
    },
    {
      "epoch": 0.23104693140794225,
      "grad_norm": 83.89037322998047,
      "learning_rate": 2e-05,
      "loss": 9.4551,
      "step": 12
    },
    {
      "epoch": 0.2503008423586041,
      "grad_norm": 63.491943359375,
      "learning_rate": 2e-05,
      "loss": 9.3453,
      "step": 13
    },
    {
      "epoch": 0.2695547533092659,
      "grad_norm": 51.0808219909668,
      "learning_rate": 2e-05,
      "loss": 9.2297,
      "step": 14
    },
    {
      "epoch": 0.2888086642599278,
      "grad_norm": 44.37099838256836,
      "learning_rate": 2e-05,
      "loss": 9.1875,
      "step": 15
    },
    {
      "epoch": 0.30806257521058966,
      "grad_norm": 67.27417755126953,
      "learning_rate": 2e-05,
      "loss": 9.1203,
      "step": 16
    },
    {
      "epoch": 0.32731648616125153,
      "grad_norm": 77.5335922241211,
      "learning_rate": 2e-05,
      "loss": 9.0269,
      "step": 17
    },
    {
      "epoch": 0.34657039711191334,
      "grad_norm": 83.21548461914062,
      "learning_rate": 2e-05,
      "loss": 9.0223,
      "step": 18
    },
    {
      "epoch": 0.3658243080625752,
      "grad_norm": 83.81153106689453,
      "learning_rate": 2e-05,
      "loss": 8.8856,
      "step": 19
    },
    {
      "epoch": 0.3850782190132371,
      "grad_norm": 70.34122467041016,
      "learning_rate": 2e-05,
      "loss": 8.7546,
      "step": 20
    },
    {
      "epoch": 0.4043321299638989,
      "grad_norm": 71.87590789794922,
      "learning_rate": 2e-05,
      "loss": 8.692,
      "step": 21
    },
    {
      "epoch": 0.42358604091456076,
      "grad_norm": 61.52598571777344,
      "learning_rate": 2e-05,
      "loss": 8.7245,
      "step": 22
    },
    {
      "epoch": 0.4428399518652226,
      "grad_norm": 81.4962158203125,
      "learning_rate": 2e-05,
      "loss": 8.4164,
      "step": 23
    },
    {
      "epoch": 0.4620938628158845,
      "grad_norm": 66.4041976928711,
      "learning_rate": 2e-05,
      "loss": 8.4377,
      "step": 24
    },
    {
      "epoch": 0.4813477737665463,
      "grad_norm": 74.9264144897461,
      "learning_rate": 2e-05,
      "loss": 8.305,
      "step": 25
    },
    {
      "epoch": 0.4813477737665463,
      "eval_clap": 0.2508222758769989,
      "eval_loss": 3.7162673473358154,
      "eval_runtime": 195.557,
      "eval_samples_per_second": 0.164,
      "eval_steps_per_second": 0.164,
      "step": 25
    },
    {
      "epoch": 0.5006016847172082,
      "grad_norm": 57.42286682128906,
      "learning_rate": 2e-05,
      "loss": 8.3213,
      "step": 26
    },
    {
      "epoch": 0.51985559566787,
      "grad_norm": 64.55001831054688,
      "learning_rate": 2e-05,
      "loss": 8.2368,
      "step": 27
    },
    {
      "epoch": 0.5391095066185319,
      "grad_norm": 51.85919952392578,
      "learning_rate": 2e-05,
      "loss": 8.2753,
      "step": 28
    },
    {
      "epoch": 0.5583634175691937,
      "grad_norm": 53.471458435058594,
      "learning_rate": 2e-05,
      "loss": 8.0826,
      "step": 29
    },
    {
      "epoch": 0.5776173285198556,
      "grad_norm": 49.86967849731445,
      "learning_rate": 2e-05,
      "loss": 7.9446,
      "step": 30
    },
    {
      "epoch": 0.5968712394705175,
      "grad_norm": 62.497581481933594,
      "learning_rate": 2e-05,
      "loss": 7.7911,
      "step": 31
    },
    {
      "epoch": 0.6161251504211793,
      "grad_norm": 46.13528823852539,
      "learning_rate": 2e-05,
      "loss": 7.7964,
      "step": 32
    },
    {
      "epoch": 0.6353790613718412,
      "grad_norm": 56.71400451660156,
      "learning_rate": 2e-05,
      "loss": 7.5232,
      "step": 33
    },
    {
      "epoch": 0.6546329723225031,
      "grad_norm": 43.25479507446289,
      "learning_rate": 2e-05,
      "loss": 7.7154,
      "step": 34
    },
    {
      "epoch": 0.6738868832731648,
      "grad_norm": 44.234336853027344,
      "learning_rate": 2e-05,
      "loss": 7.3668,
      "step": 35
    },
    {
      "epoch": 0.6931407942238267,
      "grad_norm": 43.533878326416016,
      "learning_rate": 2e-05,
      "loss": 7.8787,
      "step": 36
    },
    {
      "epoch": 0.7123947051744886,
      "grad_norm": 37.30876922607422,
      "learning_rate": 2e-05,
      "loss": 7.661,
      "step": 37
    },
    {
      "epoch": 0.7316486161251504,
      "grad_norm": 37.29338073730469,
      "learning_rate": 2e-05,
      "loss": 7.5059,
      "step": 38
    },
    {
      "epoch": 0.7509025270758123,
      "grad_norm": 39.37627410888672,
      "learning_rate": 2e-05,
      "loss": 7.6255,
      "step": 39
    },
    {
      "epoch": 0.7701564380264742,
      "grad_norm": 33.975730895996094,
      "learning_rate": 2e-05,
      "loss": 7.271,
      "step": 40
    },
    {
      "epoch": 0.789410348977136,
      "grad_norm": 43.57024002075195,
      "learning_rate": 2e-05,
      "loss": 7.6087,
      "step": 41
    },
    {
      "epoch": 0.8086642599277978,
      "grad_norm": 41.361568450927734,
      "learning_rate": 2e-05,
      "loss": 7.2042,
      "step": 42
    },
    {
      "epoch": 0.8279181708784596,
      "grad_norm": 41.087318420410156,
      "learning_rate": 2e-05,
      "loss": 7.188,
      "step": 43
    },
    {
      "epoch": 0.8471720818291215,
      "grad_norm": 39.903804779052734,
      "learning_rate": 2e-05,
      "loss": 7.0335,
      "step": 44
    },
    {
      "epoch": 0.8664259927797834,
      "grad_norm": 43.420780181884766,
      "learning_rate": 2e-05,
      "loss": 7.1334,
      "step": 45
    },
    {
      "epoch": 0.8856799037304453,
      "grad_norm": 38.208740234375,
      "learning_rate": 2e-05,
      "loss": 6.9014,
      "step": 46
    },
    {
      "epoch": 0.9049338146811071,
      "grad_norm": 34.4349250793457,
      "learning_rate": 2e-05,
      "loss": 6.9772,
      "step": 47
    },
    {
      "epoch": 0.924187725631769,
      "grad_norm": 42.55630874633789,
      "learning_rate": 2e-05,
      "loss": 7.3901,
      "step": 48
    },
    {
      "epoch": 0.9434416365824309,
      "grad_norm": 37.8997917175293,
      "learning_rate": 2e-05,
      "loss": 6.9604,
      "step": 49
    },
    {
      "epoch": 0.9626955475330926,
      "grad_norm": 27.6505184173584,
      "learning_rate": 2e-05,
      "loss": 6.9842,
      "step": 50
    },
    {
      "epoch": 0.9626955475330926,
      "eval_clap": 0.05512786656618118,
      "eval_loss": 4.608064651489258,
      "eval_runtime": 203.976,
      "eval_samples_per_second": 0.157,
      "eval_steps_per_second": 0.157,
      "step": 50
    },
    {
      "epoch": 0.9819494584837545,
      "grad_norm": 29.874601364135742,
      "learning_rate": 2e-05,
      "loss": 6.5285,
      "step": 51
    },
    {
      "epoch": 1.0,
      "grad_norm": 32.52230453491211,
      "learning_rate": 2e-05,
      "loss": 6.0624,
      "step": 52
    },
    {
      "epoch": 1.0192539109506618,
      "grad_norm": 25.571067810058594,
      "learning_rate": 2e-05,
      "loss": 6.965,
      "step": 53
    },
    {
      "epoch": 1.0385078219013237,
      "grad_norm": 24.804780960083008,
      "learning_rate": 2e-05,
      "loss": 6.6082,
      "step": 54
    },
    {
      "epoch": 1.0577617328519855,
      "grad_norm": 26.17034339904785,
      "learning_rate": 2e-05,
      "loss": 6.8646,
      "step": 55
    },
    {
      "epoch": 1.0770156438026475,
      "grad_norm": 26.33489990234375,
      "learning_rate": 2e-05,
      "loss": 7.0679,
      "step": 56
    },
    {
      "epoch": 1.0962695547533092,
      "grad_norm": 22.185443878173828,
      "learning_rate": 2e-05,
      "loss": 6.9692,
      "step": 57
    },
    {
      "epoch": 1.1155234657039712,
      "grad_norm": 24.1581974029541,
      "learning_rate": 2e-05,
      "loss": 6.7359,
      "step": 58
    },
    {
      "epoch": 1.134777376654633,
      "grad_norm": 19.098318099975586,
      "learning_rate": 2e-05,
      "loss": 6.8621,
      "step": 59
    },
    {
      "epoch": 1.154031287605295,
      "grad_norm": 18.446277618408203,
      "learning_rate": 2e-05,
      "loss": 6.9175,
      "step": 60
    },
    {
      "epoch": 1.1732851985559567,
      "grad_norm": 18.82305908203125,
      "learning_rate": 2e-05,
      "loss": 6.8505,
      "step": 61
    },
    {
      "epoch": 1.1925391095066185,
      "grad_norm": 23.049110412597656,
      "learning_rate": 2e-05,
      "loss": 6.4014,
      "step": 62
    },
    {
      "epoch": 1.2117930204572804,
      "grad_norm": 30.802398681640625,
      "learning_rate": 2e-05,
      "loss": 6.1833,
      "step": 63
    },
    {
      "epoch": 1.2310469314079422,
      "grad_norm": 31.79558563232422,
      "learning_rate": 2e-05,
      "loss": 6.3301,
      "step": 64
    },
    {
      "epoch": 1.2503008423586042,
      "grad_norm": 17.523427963256836,
      "learning_rate": 2e-05,
      "loss": 6.5382,
      "step": 65
    },
    {
      "epoch": 1.269554753309266,
      "grad_norm": 20.55564308166504,
      "learning_rate": 2e-05,
      "loss": 6.8307,
      "step": 66
    },
    {
      "epoch": 1.288808664259928,
      "grad_norm": 14.00365924835205,
      "learning_rate": 2e-05,
      "loss": 6.688,
      "step": 67
    },
    {
      "epoch": 1.3080625752105897,
      "grad_norm": 20.74002456665039,
      "learning_rate": 2e-05,
      "loss": 6.3775,
      "step": 68
    },
    {
      "epoch": 1.3273164861612514,
      "grad_norm": 13.387882232666016,
      "learning_rate": 2e-05,
      "loss": 6.4859,
      "step": 69
    },
    {
      "epoch": 1.3465703971119134,
      "grad_norm": 13.83588981628418,
      "learning_rate": 2e-05,
      "loss": 6.6777,
      "step": 70
    },
    {
      "epoch": 1.3658243080625752,
      "grad_norm": 18.38031005859375,
      "learning_rate": 2e-05,
      "loss": 6.712,
      "step": 71
    },
    {
      "epoch": 1.3850782190132371,
      "grad_norm": 15.858037948608398,
      "learning_rate": 2e-05,
      "loss": 6.7095,
      "step": 72
    },
    {
      "epoch": 1.404332129963899,
      "grad_norm": 14.21243667602539,
      "learning_rate": 2e-05,
      "loss": 6.6714,
      "step": 73
    },
    {
      "epoch": 1.4235860409145609,
      "grad_norm": 13.775053024291992,
      "learning_rate": 2e-05,
      "loss": 6.3512,
      "step": 74
    },
    {
      "epoch": 1.4428399518652226,
      "grad_norm": 18.616239547729492,
      "learning_rate": 2e-05,
      "loss": 6.9013,
      "step": 75
    },
    {
      "epoch": 1.4428399518652226,
      "eval_clap": 0.05818195268511772,
      "eval_loss": 5.64979362487793,
      "eval_runtime": 195.9522,
      "eval_samples_per_second": 0.163,
      "eval_steps_per_second": 0.163,
      "step": 75
    },
    {
      "epoch": 1.4620938628158844,
      "grad_norm": 27.710369110107422,
      "learning_rate": 2e-05,
      "loss": 6.0035,
      "step": 76
    },
    {
      "epoch": 1.4813477737665464,
      "grad_norm": 20.711942672729492,
      "learning_rate": 2e-05,
      "loss": 6.1597,
      "step": 77
    },
    {
      "epoch": 1.5006016847172083,
      "grad_norm": 11.78789234161377,
      "learning_rate": 2e-05,
      "loss": 6.4754,
      "step": 78
    },
    {
      "epoch": 1.5198555956678699,
      "grad_norm": 18.79988670349121,
      "learning_rate": 2e-05,
      "loss": 6.7886,
      "step": 79
    },
    {
      "epoch": 1.5391095066185319,
      "grad_norm": 9.708053588867188,
      "learning_rate": 2e-05,
      "loss": 6.4123,
      "step": 80
    },
    {
      "epoch": 1.5583634175691938,
      "grad_norm": 10.420573234558105,
      "learning_rate": 2e-05,
      "loss": 6.3586,
      "step": 81
    },
    {
      "epoch": 1.5776173285198556,
      "grad_norm": 12.453520774841309,
      "learning_rate": 2e-05,
      "loss": 6.2891,
      "step": 82
    },
    {
      "epoch": 1.5968712394705173,
      "grad_norm": 18.412593841552734,
      "learning_rate": 2e-05,
      "loss": 6.0656,
      "step": 83
    },
    {
      "epoch": 1.6161251504211793,
      "grad_norm": 15.798463821411133,
      "learning_rate": 2e-05,
      "loss": 6.5867,
      "step": 84
    },
    {
      "epoch": 1.6353790613718413,
      "grad_norm": 9.848593711853027,
      "learning_rate": 2e-05,
      "loss": 6.3659,
      "step": 85
    },
    {
      "epoch": 1.654632972322503,
      "grad_norm": 10.542499542236328,
      "learning_rate": 2e-05,
      "loss": 6.1898,
      "step": 86
    },
    {
      "epoch": 1.6738868832731648,
      "grad_norm": 10.715902328491211,
      "learning_rate": 2e-05,
      "loss": 6.2704,
      "step": 87
    },
    {
      "epoch": 1.6931407942238268,
      "grad_norm": 10.027088165283203,
      "learning_rate": 2e-05,
      "loss": 6.1835,
      "step": 88
    },
    {
      "epoch": 1.7123947051744886,
      "grad_norm": 17.48147964477539,
      "learning_rate": 2e-05,
      "loss": 6.0763,
      "step": 89
    },
    {
      "epoch": 1.7316486161251503,
      "grad_norm": 17.746797561645508,
      "learning_rate": 2e-05,
      "loss": 5.8703,
      "step": 90
    },
    {
      "epoch": 1.7509025270758123,
      "grad_norm": 28.819969177246094,
      "learning_rate": 2e-05,
      "loss": 6.8541,
      "step": 91
    },
    {
      "epoch": 1.7701564380264743,
      "grad_norm": 13.42017936706543,
      "learning_rate": 2e-05,
      "loss": 6.2243,
      "step": 92
    },
    {
      "epoch": 1.789410348977136,
      "grad_norm": 17.955583572387695,
      "learning_rate": 2e-05,
      "loss": 6.5344,
      "step": 93
    },
    {
      "epoch": 1.8086642599277978,
      "grad_norm": 22.70500946044922,
      "learning_rate": 2e-05,
      "loss": 6.6459,
      "step": 94
    },
    {
      "epoch": 1.8279181708784598,
      "grad_norm": 13.345677375793457,
      "learning_rate": 2e-05,
      "loss": 6.425,
      "step": 95
    },
    {
      "epoch": 1.8471720818291215,
      "grad_norm": 13.83546257019043,
      "learning_rate": 2e-05,
      "loss": 6.4378,
      "step": 96
    },
    {
      "epoch": 1.8664259927797833,
      "grad_norm": 23.364137649536133,
      "learning_rate": 2e-05,
      "loss": 5.854,
      "step": 97
    },
    {
      "epoch": 1.8856799037304453,
      "grad_norm": 8.366693496704102,
      "learning_rate": 2e-05,
      "loss": 6.2678,
      "step": 98
    },
    {
      "epoch": 1.9049338146811072,
      "grad_norm": 14.662858009338379,
      "learning_rate": 2e-05,
      "loss": 5.9462,
      "step": 99
    },
    {
      "epoch": 1.924187725631769,
      "grad_norm": 12.826397895812988,
      "learning_rate": 2e-05,
      "loss": 6.0195,
      "step": 100
    },
    {
      "epoch": 1.924187725631769,
      "eval_clap": 0.14504113793373108,
      "eval_loss": 5.763121604919434,
      "eval_runtime": 204.238,
      "eval_samples_per_second": 0.157,
      "eval_steps_per_second": 0.157,
      "step": 100
    },
    {
      "epoch": 1.9434416365824307,
      "grad_norm": 11.27551555633545,
      "learning_rate": 2e-05,
      "loss": 6.1058,
      "step": 101
    },
    {
      "epoch": 1.9626955475330927,
      "grad_norm": 16.934494018554688,
      "learning_rate": 2e-05,
      "loss": 6.6169,
      "step": 102
    },
    {
      "epoch": 1.9819494584837545,
      "grad_norm": 10.172548294067383,
      "learning_rate": 2e-05,
      "loss": 6.085,
      "step": 103
    },
    {
      "epoch": 2.0,
      "grad_norm": 21.66511344909668,
      "learning_rate": 2e-05,
      "loss": 6.374,
      "step": 104
    },
    {
      "epoch": 2.019253910950662,
      "grad_norm": 14.909863471984863,
      "learning_rate": 2e-05,
      "loss": 6.5841,
      "step": 105
    },
    {
      "epoch": 2.0385078219013235,
      "grad_norm": 13.277375221252441,
      "learning_rate": 2e-05,
      "loss": 6.0897,
      "step": 106
    },
    {
      "epoch": 2.0577617328519855,
      "grad_norm": 14.995245933532715,
      "learning_rate": 2e-05,
      "loss": 6.6047,
      "step": 107
    },
    {
      "epoch": 2.0770156438026475,
      "grad_norm": 8.810375213623047,
      "learning_rate": 2e-05,
      "loss": 6.4019,
      "step": 108
    },
    {
      "epoch": 2.0962695547533094,
      "grad_norm": 9.020201683044434,
      "learning_rate": 2e-05,
      "loss": 6.1859,
      "step": 109
    },
    {
      "epoch": 2.115523465703971,
      "grad_norm": 13.133101463317871,
      "learning_rate": 2e-05,
      "loss": 6.1151,
      "step": 110
    },
    {
      "epoch": 2.134777376654633,
      "grad_norm": 9.436896324157715,
      "learning_rate": 2e-05,
      "loss": 6.5699,
      "step": 111
    },
    {
      "epoch": 2.154031287605295,
      "grad_norm": 7.937966346740723,
      "learning_rate": 2e-05,
      "loss": 6.4376,
      "step": 112
    },
    {
      "epoch": 2.1732851985559565,
      "grad_norm": 9.059781074523926,
      "learning_rate": 2e-05,
      "loss": 6.514,
      "step": 113
    },
    {
      "epoch": 2.1925391095066185,
      "grad_norm": 6.838661193847656,
      "learning_rate": 2e-05,
      "loss": 6.4801,
      "step": 114
    },
    {
      "epoch": 2.2117930204572804,
      "grad_norm": 21.459503173828125,
      "learning_rate": 2e-05,
      "loss": 5.9983,
      "step": 115
    },
    {
      "epoch": 2.2310469314079424,
      "grad_norm": 10.961411476135254,
      "learning_rate": 2e-05,
      "loss": 6.257,
      "step": 116
    },
    {
      "epoch": 2.250300842358604,
      "grad_norm": 24.96747398376465,
      "learning_rate": 2e-05,
      "loss": 6.0786,
      "step": 117
    },
    {
      "epoch": 2.269554753309266,
      "grad_norm": 10.531516075134277,
      "learning_rate": 2e-05,
      "loss": 6.3389,
      "step": 118
    },
    {
      "epoch": 2.288808664259928,
      "grad_norm": 12.07296085357666,
      "learning_rate": 2e-05,
      "loss": 6.2715,
      "step": 119
    },
    {
      "epoch": 2.30806257521059,
      "grad_norm": 8.665770530700684,
      "learning_rate": 2e-05,
      "loss": 6.3378,
      "step": 120
    },
    {
      "epoch": 2.3273164861612514,
      "grad_norm": 11.358579635620117,
      "learning_rate": 2e-05,
      "loss": 6.2564,
      "step": 121
    },
    {
      "epoch": 2.3465703971119134,
      "grad_norm": 13.47236156463623,
      "learning_rate": 2e-05,
      "loss": 6.1455,
      "step": 122
    },
    {
      "epoch": 2.3658243080625754,
      "grad_norm": 6.947666168212891,
      "learning_rate": 2e-05,
      "loss": 6.3356,
      "step": 123
    },
    {
      "epoch": 2.385078219013237,
      "grad_norm": 13.422441482543945,
      "learning_rate": 2e-05,
      "loss": 6.5743,
      "step": 124
    },
    {
      "epoch": 2.404332129963899,
      "grad_norm": 8.865825653076172,
      "learning_rate": 2e-05,
      "loss": 6.447,
      "step": 125
    },
    {
      "epoch": 2.404332129963899,
      "eval_clap": 0.11870799958705902,
      "eval_loss": 5.7946672439575195,
      "eval_runtime": 196.002,
      "eval_samples_per_second": 0.163,
      "eval_steps_per_second": 0.163,
      "step": 125
    },
    {
      "epoch": 2.423586040914561,
      "grad_norm": 14.267729759216309,
      "learning_rate": 2e-05,
      "loss": 6.1854,
      "step": 126
    },
    {
      "epoch": 2.4428399518652224,
      "grad_norm": 11.992257118225098,
      "learning_rate": 2e-05,
      "loss": 6.4266,
      "step": 127
    },
    {
      "epoch": 2.4620938628158844,
      "grad_norm": 8.23071575164795,
      "learning_rate": 2e-05,
      "loss": 6.1821,
      "step": 128
    },
    {
      "epoch": 2.4813477737665464,
      "grad_norm": 14.663762092590332,
      "learning_rate": 2e-05,
      "loss": 5.8956,
      "step": 129
    },
    {
      "epoch": 2.5006016847172083,
      "grad_norm": 19.018505096435547,
      "learning_rate": 2e-05,
      "loss": 6.748,
      "step": 130
    },
    {
      "epoch": 2.51985559566787,
      "grad_norm": 15.996222496032715,
      "learning_rate": 2e-05,
      "loss": 6.6005,
      "step": 131
    },
    {
      "epoch": 2.539109506618532,
      "grad_norm": 15.696185111999512,
      "learning_rate": 2e-05,
      "loss": 5.94,
      "step": 132
    },
    {
      "epoch": 2.558363417569194,
      "grad_norm": 28.96451759338379,
      "learning_rate": 2e-05,
      "loss": 5.6643,
      "step": 133
    },
    {
      "epoch": 2.577617328519856,
      "grad_norm": 10.068239212036133,
      "learning_rate": 2e-05,
      "loss": 6.0527,
      "step": 134
    },
    {
      "epoch": 2.5968712394705173,
      "grad_norm": 20.770143508911133,
      "learning_rate": 2e-05,
      "loss": 5.8241,
      "step": 135
    },
    {
      "epoch": 2.6161251504211793,
      "grad_norm": 8.34460735321045,
      "learning_rate": 2e-05,
      "loss": 6.2976,
      "step": 136
    },
    {
      "epoch": 2.6353790613718413,
      "grad_norm": 7.031894683837891,
      "learning_rate": 2e-05,
      "loss": 6.1223,
      "step": 137
    },
    {
      "epoch": 2.654632972322503,
      "grad_norm": 13.371209144592285,
      "learning_rate": 2e-05,
      "loss": 6.4443,
      "step": 138
    },
    {
      "epoch": 2.673886883273165,
      "grad_norm": 13.32111930847168,
      "learning_rate": 2e-05,
      "loss": 6.0339,
      "step": 139
    },
    {
      "epoch": 2.693140794223827,
      "grad_norm": 12.334694862365723,
      "learning_rate": 2e-05,
      "loss": 6.1672,
      "step": 140
    },
    {
      "epoch": 2.7123947051744883,
      "grad_norm": 18.95940589904785,
      "learning_rate": 2e-05,
      "loss": 5.7344,
      "step": 141
    },
    {
      "epoch": 2.7316486161251503,
      "grad_norm": 16.167844772338867,
      "learning_rate": 2e-05,
      "loss": 5.8938,
      "step": 142
    },
    {
      "epoch": 2.7509025270758123,
      "grad_norm": 13.141815185546875,
      "learning_rate": 2e-05,
      "loss": 5.7477,
      "step": 143
    },
    {
      "epoch": 2.7701564380264743,
      "grad_norm": 9.945357322692871,
      "learning_rate": 2e-05,
      "loss": 6.0525,
      "step": 144
    },
    {
      "epoch": 2.7894103489771362,
      "grad_norm": 18.400161743164062,
      "learning_rate": 2e-05,
      "loss": 6.4865,
      "step": 145
    },
    {
      "epoch": 2.808664259927798,
      "grad_norm": 9.252588272094727,
      "learning_rate": 2e-05,
      "loss": 6.1021,
      "step": 146
    },
    {
      "epoch": 2.8279181708784598,
      "grad_norm": 9.42403793334961,
      "learning_rate": 2e-05,
      "loss": 5.9196,
      "step": 147
    },
    {
      "epoch": 2.8471720818291217,
      "grad_norm": 16.049497604370117,
      "learning_rate": 2e-05,
      "loss": 6.3472,
      "step": 148
    },
    {
      "epoch": 2.8664259927797833,
      "grad_norm": 16.170551300048828,
      "learning_rate": 2e-05,
      "loss": 6.4077,
      "step": 149
    },
    {
      "epoch": 2.8856799037304453,
      "grad_norm": 13.0892915725708,
      "learning_rate": 2e-05,
      "loss": 6.215,
      "step": 150
    },
    {
      "epoch": 2.8856799037304453,
      "eval_clap": 0.11637458205223083,
      "eval_loss": 5.839620590209961,
      "eval_runtime": 203.9479,
      "eval_samples_per_second": 0.157,
      "eval_steps_per_second": 0.157,
      "step": 150
    },
    {
      "epoch": 2.9049338146811072,
      "grad_norm": 11.786327362060547,
      "learning_rate": 2e-05,
      "loss": 6.3015,
      "step": 151
    },
    {
      "epoch": 2.9241877256317688,
      "grad_norm": 8.937137603759766,
      "learning_rate": 2e-05,
      "loss": 6.1963,
      "step": 152
    },
    {
      "epoch": 2.9434416365824307,
      "grad_norm": 15.840847969055176,
      "learning_rate": 2e-05,
      "loss": 6.4957,
      "step": 153
    },
    {
      "epoch": 2.9626955475330927,
      "grad_norm": 11.317403793334961,
      "learning_rate": 2e-05,
      "loss": 6.4699,
      "step": 154
    },
    {
      "epoch": 2.9819494584837543,
      "grad_norm": 11.2737398147583,
      "learning_rate": 2e-05,
      "loss": 6.0559,
      "step": 155
    },
    {
      "epoch": 3.0,
      "grad_norm": 15.351630210876465,
      "learning_rate": 2e-05,
      "loss": 5.5406,
      "step": 156
    },
    {
      "epoch": 3.019253910950662,
      "grad_norm": 10.597087860107422,
      "learning_rate": 2e-05,
      "loss": 6.5337,
      "step": 157
    },
    {
      "epoch": 3.0385078219013235,
      "grad_norm": 8.941291809082031,
      "learning_rate": 2e-05,
      "loss": 6.2708,
      "step": 158
    },
    {
      "epoch": 3.0577617328519855,
      "grad_norm": 15.444201469421387,
      "learning_rate": 2e-05,
      "loss": 6.1448,
      "step": 159
    },
    {
      "epoch": 3.0770156438026475,
      "grad_norm": 8.186105728149414,
      "learning_rate": 2e-05,
      "loss": 6.2508,
      "step": 160
    },
    {
      "epoch": 3.0962695547533094,
      "grad_norm": 25.041446685791016,
      "learning_rate": 2e-05,
      "loss": 5.9141,
      "step": 161
    },
    {
      "epoch": 3.115523465703971,
      "grad_norm": 25.764001846313477,
      "learning_rate": 2e-05,
      "loss": 5.7969,
      "step": 162
    },
    {
      "epoch": 3.134777376654633,
      "grad_norm": 8.077290534973145,
      "learning_rate": 2e-05,
      "loss": 6.485,
      "step": 163
    },
    {
      "epoch": 3.154031287605295,
      "grad_norm": 6.288991451263428,
      "learning_rate": 2e-05,
      "loss": 6.3003,
      "step": 164
    },
    {
      "epoch": 3.1732851985559565,
      "grad_norm": 7.810708522796631,
      "learning_rate": 2e-05,
      "loss": 6.191,
      "step": 165
    },
    {
      "epoch": 3.1925391095066185,
      "grad_norm": 12.891411781311035,
      "learning_rate": 2e-05,
      "loss": 5.9668,
      "step": 166
    },
    {
      "epoch": 3.2117930204572804,
      "grad_norm": 9.540118217468262,
      "learning_rate": 2e-05,
      "loss": 6.093,
      "step": 167
    },
    {
      "epoch": 3.2310469314079424,
      "grad_norm": 9.51327896118164,
      "learning_rate": 2e-05,
      "loss": 6.1793,
      "step": 168
    },
    {
      "epoch": 3.250300842358604,
      "grad_norm": 16.127683639526367,
      "learning_rate": 2e-05,
      "loss": 6.0557,
      "step": 169
    },
    {
      "epoch": 3.269554753309266,
      "grad_norm": 17.678020477294922,
      "learning_rate": 2e-05,
      "loss": 6.5721,
      "step": 170
    },
    {
      "epoch": 3.288808664259928,
      "grad_norm": 11.319859504699707,
      "learning_rate": 2e-05,
      "loss": 5.9967,
      "step": 171
    },
    {
      "epoch": 3.30806257521059,
      "grad_norm": 15.657870292663574,
      "learning_rate": 2e-05,
      "loss": 5.9343,
      "step": 172
    },
    {
      "epoch": 3.3273164861612514,
      "grad_norm": 15.364697456359863,
      "learning_rate": 2e-05,
      "loss": 6.2908,
      "step": 173
    },
    {
      "epoch": 3.3465703971119134,
      "grad_norm": 23.229448318481445,
      "learning_rate": 2e-05,
      "loss": 5.7732,
      "step": 174
    },
    {
      "epoch": 3.3658243080625754,
      "grad_norm": 13.746365547180176,
      "learning_rate": 2e-05,
      "loss": 6.4075,
      "step": 175
    },
    {
      "epoch": 3.3658243080625754,
      "eval_clap": 0.11743690818548203,
      "eval_loss": 5.836143493652344,
      "eval_runtime": 204.2948,
      "eval_samples_per_second": 0.157,
      "eval_steps_per_second": 0.157,
      "step": 175
    },
    {
      "epoch": 3.385078219013237,
      "grad_norm": 9.525516510009766,
      "learning_rate": 2e-05,
      "loss": 6.0857,
      "step": 176
    },
    {
      "epoch": 3.404332129963899,
      "grad_norm": 18.301898956298828,
      "learning_rate": 2e-05,
      "loss": 6.4325,
      "step": 177
    },
    {
      "epoch": 3.423586040914561,
      "grad_norm": 12.342935562133789,
      "learning_rate": 2e-05,
      "loss": 6.1896,
      "step": 178
    },
    {
      "epoch": 3.4428399518652224,
      "grad_norm": 12.635440826416016,
      "learning_rate": 2e-05,
      "loss": 6.2818,
      "step": 179
    },
    {
      "epoch": 3.4620938628158844,
      "grad_norm": 10.180573463439941,
      "learning_rate": 2e-05,
      "loss": 6.2591,
      "step": 180
    },
    {
      "epoch": 3.4813477737665464,
      "grad_norm": 9.508129119873047,
      "learning_rate": 2e-05,
      "loss": 6.2806,
      "step": 181
    },
    {
      "epoch": 3.5006016847172083,
      "grad_norm": 10.56059455871582,
      "learning_rate": 2e-05,
      "loss": 6.459,
      "step": 182
    },
    {
      "epoch": 3.51985559566787,
      "grad_norm": 10.22647762298584,
      "learning_rate": 2e-05,
      "loss": 6.0333,
      "step": 183
    },
    {
      "epoch": 3.539109506618532,
      "grad_norm": 8.610014915466309,
      "learning_rate": 2e-05,
      "loss": 6.4448,
      "step": 184
    },
    {
      "epoch": 3.558363417569194,
      "grad_norm": 12.473418235778809,
      "learning_rate": 2e-05,
      "loss": 6.0245,
      "step": 185
    },
    {
      "epoch": 3.577617328519856,
      "grad_norm": 15.734831809997559,
      "learning_rate": 2e-05,
      "loss": 5.9932,
      "step": 186
    },
    {
      "epoch": 3.5968712394705173,
      "grad_norm": 8.682183265686035,
      "learning_rate": 2e-05,
      "loss": 6.2845,
      "step": 187
    },
    {
      "epoch": 3.6161251504211793,
      "grad_norm": 21.06833839416504,
      "learning_rate": 2e-05,
      "loss": 5.8533,
      "step": 188
    },
    {
      "epoch": 3.6353790613718413,
      "grad_norm": 22.429513931274414,
      "learning_rate": 2e-05,
      "loss": 5.7251,
      "step": 189
    },
    {
      "epoch": 3.654632972322503,
      "grad_norm": 7.118320941925049,
      "learning_rate": 2e-05,
      "loss": 6.2949,
      "step": 190
    },
    {
      "epoch": 3.673886883273165,
      "grad_norm": 11.422521591186523,
      "learning_rate": 2e-05,
      "loss": 6.1418,
      "step": 191
    },
    {
      "epoch": 3.693140794223827,
      "grad_norm": 11.730757713317871,
      "learning_rate": 2e-05,
      "loss": 6.0665,
      "step": 192
    },
    {
      "epoch": 3.7123947051744883,
      "grad_norm": 7.965202331542969,
      "learning_rate": 2e-05,
      "loss": 6.3251,
      "step": 193
    },
    {
      "epoch": 3.7316486161251503,
      "grad_norm": 9.634132385253906,
      "learning_rate": 2e-05,
      "loss": 6.0327,
      "step": 194
    },
    {
      "epoch": 3.7509025270758123,
      "grad_norm": 12.675938606262207,
      "learning_rate": 2e-05,
      "loss": 6.4535,
      "step": 195
    },
    {
      "epoch": 3.7701564380264743,
      "grad_norm": 11.747628211975098,
      "learning_rate": 2e-05,
      "loss": 5.8515,
      "step": 196
    },
    {
      "epoch": 3.7894103489771362,
      "grad_norm": 9.878296852111816,
      "learning_rate": 2e-05,
      "loss": 6.3101,
      "step": 197
    },
    {
      "epoch": 3.808664259927798,
      "grad_norm": 8.255465507507324,
      "learning_rate": 2e-05,
      "loss": 6.1733,
      "step": 198
    },
    {
      "epoch": 3.8279181708784598,
      "grad_norm": 15.391761779785156,
      "learning_rate": 2e-05,
      "loss": 6.4827,
      "step": 199
    },
    {
      "epoch": 3.8471720818291217,
      "grad_norm": 16.02042579650879,
      "learning_rate": 2e-05,
      "loss": 5.797,
      "step": 200
    },
    {
      "epoch": 3.8471720818291217,
      "eval_clap": 0.10931383073329926,
      "eval_loss": 5.815006256103516,
      "eval_runtime": 204.8855,
      "eval_samples_per_second": 0.156,
      "eval_steps_per_second": 0.156,
      "step": 200
    },
    {
      "epoch": 3.8664259927797833,
      "grad_norm": 11.096480369567871,
      "learning_rate": 2e-05,
      "loss": 6.3396,
      "step": 201
    },
    {
      "epoch": 3.8856799037304453,
      "grad_norm": 17.267515182495117,
      "learning_rate": 2e-05,
      "loss": 5.7346,
      "step": 202
    },
    {
      "epoch": 3.9049338146811072,
      "grad_norm": 10.836710929870605,
      "learning_rate": 2e-05,
      "loss": 6.3001,
      "step": 203
    },
    {
      "epoch": 3.9241877256317688,
      "grad_norm": 6.178803443908691,
      "learning_rate": 2e-05,
      "loss": 6.1283,
      "step": 204
    },
    {
      "epoch": 3.9434416365824307,
      "grad_norm": 8.270339965820312,
      "learning_rate": 2e-05,
      "loss": 6.2692,
      "step": 205
    },
    {
      "epoch": 3.9626955475330927,
      "grad_norm": 8.276531219482422,
      "learning_rate": 2e-05,
      "loss": 6.2181,
      "step": 206
    },
    {
      "epoch": 3.9819494584837543,
      "grad_norm": 9.491342544555664,
      "learning_rate": 2e-05,
      "loss": 6.4109,
      "step": 207
    },
    {
      "epoch": 4.0,
      "grad_norm": 16.148122787475586,
      "learning_rate": 2e-05,
      "loss": 5.4716,
      "step": 208
    },
    {
      "epoch": 4.0192539109506615,
      "grad_norm": 5.439089298248291,
      "learning_rate": 2e-05,
      "loss": 6.1773,
      "step": 209
    },
    {
      "epoch": 4.038507821901324,
      "grad_norm": 8.583178520202637,
      "learning_rate": 2e-05,
      "loss": 6.097,
      "step": 210
    },
    {
      "epoch": 4.0577617328519855,
      "grad_norm": 5.862834453582764,
      "learning_rate": 2e-05,
      "loss": 6.2586,
      "step": 211
    },
    {
      "epoch": 4.077015643802647,
      "grad_norm": 19.868268966674805,
      "learning_rate": 2e-05,
      "loss": 5.7732,
      "step": 212
    },
    {
      "epoch": 4.0962695547533094,
      "grad_norm": 8.219894409179688,
      "learning_rate": 2e-05,
      "loss": 6.1416,
      "step": 213
    },
    {
      "epoch": 4.115523465703971,
      "grad_norm": 8.35651683807373,
      "learning_rate": 2e-05,
      "loss": 6.3144,
      "step": 214
    },
    {
      "epoch": 4.1347773766546325,
      "grad_norm": 9.109415054321289,
      "learning_rate": 2e-05,
      "loss": 6.1057,
      "step": 215
    },
    {
      "epoch": 4.154031287605295,
      "grad_norm": 7.91225004196167,
      "learning_rate": 2e-05,
      "loss": 6.3672,
      "step": 216
    },
    {
      "epoch": 4.1732851985559565,
      "grad_norm": 13.663270950317383,
      "learning_rate": 2e-05,
      "loss": 6.104,
      "step": 217
    },
    {
      "epoch": 4.192539109506619,
      "grad_norm": 7.140188694000244,
      "learning_rate": 2e-05,
      "loss": 6.214,
      "step": 218
    },
    {
      "epoch": 4.21179302045728,
      "grad_norm": 20.248258590698242,
      "learning_rate": 2e-05,
      "loss": 5.7409,
      "step": 219
    },
    {
      "epoch": 4.231046931407942,
      "grad_norm": 6.1542487144470215,
      "learning_rate": 2e-05,
      "loss": 6.1971,
      "step": 220
    },
    {
      "epoch": 4.250300842358604,
      "grad_norm": 16.50935935974121,
      "learning_rate": 2e-05,
      "loss": 5.7022,
      "step": 221
    },
    {
      "epoch": 4.269554753309266,
      "grad_norm": 6.602309226989746,
      "learning_rate": 2e-05,
      "loss": 6.0883,
      "step": 222
    },
    {
      "epoch": 4.2888086642599275,
      "grad_norm": 10.636795043945312,
      "learning_rate": 2e-05,
      "loss": 6.1146,
      "step": 223
    },
    {
      "epoch": 4.30806257521059,
      "grad_norm": 15.217754364013672,
      "learning_rate": 2e-05,
      "loss": 6.4887,
      "step": 224
    },
    {
      "epoch": 4.327316486161251,
      "grad_norm": 11.162585258483887,
      "learning_rate": 2e-05,
      "loss": 6.347,
      "step": 225
    },
    {
      "epoch": 4.327316486161251,
      "eval_clap": 0.10287218540906906,
      "eval_loss": 5.793514251708984,
      "eval_runtime": 195.2618,
      "eval_samples_per_second": 0.164,
      "eval_steps_per_second": 0.164,
      "step": 225
    },
    {
      "epoch": 4.346570397111913,
      "grad_norm": 6.50248908996582,
      "learning_rate": 2e-05,
      "loss": 6.128,
      "step": 226
    },
    {
      "epoch": 4.365824308062575,
      "grad_norm": 12.357426643371582,
      "learning_rate": 2e-05,
      "loss": 6.2944,
      "step": 227
    },
    {
      "epoch": 4.385078219013237,
      "grad_norm": 11.979768753051758,
      "learning_rate": 2e-05,
      "loss": 6.0331,
      "step": 228
    },
    {
      "epoch": 4.404332129963899,
      "grad_norm": 14.140297889709473,
      "learning_rate": 2e-05,
      "loss": 5.8348,
      "step": 229
    },
    {
      "epoch": 4.423586040914561,
      "grad_norm": 13.665949821472168,
      "learning_rate": 2e-05,
      "loss": 5.9629,
      "step": 230
    },
    {
      "epoch": 4.442839951865222,
      "grad_norm": 25.926544189453125,
      "learning_rate": 2e-05,
      "loss": 5.5899,
      "step": 231
    },
    {
      "epoch": 4.462093862815885,
      "grad_norm": 11.478584289550781,
      "learning_rate": 2e-05,
      "loss": 6.06,
      "step": 232
    },
    {
      "epoch": 4.481347773766546,
      "grad_norm": 7.444418907165527,
      "learning_rate": 2e-05,
      "loss": 6.0127,
      "step": 233
    },
    {
      "epoch": 4.500601684717208,
      "grad_norm": 11.302255630493164,
      "learning_rate": 2e-05,
      "loss": 6.3942,
      "step": 234
    },
    {
      "epoch": 4.51985559566787,
      "grad_norm": 12.104110717773438,
      "learning_rate": 2e-05,
      "loss": 6.0193,
      "step": 235
    },
    {
      "epoch": 4.539109506618532,
      "grad_norm": 11.314817428588867,
      "learning_rate": 2e-05,
      "loss": 5.8347,
      "step": 236
    },
    {
      "epoch": 4.558363417569193,
      "grad_norm": 9.530527114868164,
      "learning_rate": 2e-05,
      "loss": 5.9688,
      "step": 237
    },
    {
      "epoch": 4.577617328519856,
      "grad_norm": 14.764016151428223,
      "learning_rate": 2e-05,
      "loss": 6.4083,
      "step": 238
    },
    {
      "epoch": 4.596871239470517,
      "grad_norm": 12.319718360900879,
      "learning_rate": 2e-05,
      "loss": 6.2156,
      "step": 239
    },
    {
      "epoch": 4.61612515042118,
      "grad_norm": 14.426762580871582,
      "learning_rate": 2e-05,
      "loss": 6.3868,
      "step": 240
    },
    {
      "epoch": 4.635379061371841,
      "grad_norm": 11.573673248291016,
      "learning_rate": 2e-05,
      "loss": 6.2762,
      "step": 241
    },
    {
      "epoch": 4.654632972322503,
      "grad_norm": 6.983804702758789,
      "learning_rate": 2e-05,
      "loss": 6.0903,
      "step": 242
    },
    {
      "epoch": 4.673886883273164,
      "grad_norm": 8.895957946777344,
      "learning_rate": 2e-05,
      "loss": 6.3329,
      "step": 243
    },
    {
      "epoch": 4.693140794223827,
      "grad_norm": 11.459211349487305,
      "learning_rate": 2e-05,
      "loss": 6.532,
      "step": 244
    },
    {
      "epoch": 4.712394705174488,
      "grad_norm": 7.807408809661865,
      "learning_rate": 2e-05,
      "loss": 6.4127,
      "step": 245
    },
    {
      "epoch": 4.731648616125151,
      "grad_norm": 11.404520034790039,
      "learning_rate": 2e-05,
      "loss": 6.031,
      "step": 246
    },
    {
      "epoch": 4.750902527075812,
      "grad_norm": 5.500706672668457,
      "learning_rate": 2e-05,
      "loss": 6.3023,
      "step": 247
    },
    {
      "epoch": 4.770156438026474,
      "grad_norm": 12.774914741516113,
      "learning_rate": 2e-05,
      "loss": 6.1873,
      "step": 248
    },
    {
      "epoch": 4.789410348977136,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 6.1218,
      "step": 249
    },
    {
      "epoch": 4.808664259927798,
      "grad_norm": 37.46445083618164,
      "learning_rate": 2e-05,
      "loss": 5.3935,
      "step": 250
    },
    {
      "epoch": 4.808664259927798,
      "eval_clap": 0.10396266728639603,
      "eval_loss": 5.760514259338379,
      "eval_runtime": 196.0139,
      "eval_samples_per_second": 0.163,
      "eval_steps_per_second": 0.163,
      "step": 250
    },
    {
      "epoch": 4.827918170878459,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 6.6959,
      "step": 251
    },
    {
      "epoch": 4.847172081829122,
      "grad_norm": 19.07754135131836,
      "learning_rate": 2e-05,
      "loss": 5.9438,
      "step": 252
    },
    {
      "epoch": 4.866425992779783,
      "grad_norm": 7.950329780578613,
      "learning_rate": 2e-05,
      "loss": 6.2661,
      "step": 253
    },
    {
      "epoch": 4.885679903730445,
      "grad_norm": 6.870863437652588,
      "learning_rate": 2e-05,
      "loss": 6.3211,
      "step": 254
    },
    {
      "epoch": 4.904933814681107,
      "grad_norm": 24.65618133544922,
      "learning_rate": 2e-05,
      "loss": 5.755,
      "step": 255
    },
    {
      "epoch": 4.924187725631769,
      "grad_norm": 18.71941566467285,
      "learning_rate": 2e-05,
      "loss": 5.8712,
      "step": 256
    },
    {
      "epoch": 4.943441636582431,
      "grad_norm": 22.989364624023438,
      "learning_rate": 2e-05,
      "loss": 5.9747,
      "step": 257
    },
    {
      "epoch": 4.962695547533093,
      "grad_norm": 9.502798080444336,
      "learning_rate": 2e-05,
      "loss": 6.2862,
      "step": 258
    },
    {
      "epoch": 4.981949458483754,
      "grad_norm": 7.668398857116699,
      "learning_rate": 2e-05,
      "loss": 6.0501,
      "step": 259
    },
    {
      "epoch": 5.0,
      "grad_norm": 11.83493423461914,
      "learning_rate": 2e-05,
      "loss": 5.7551,
      "step": 260
    },
    {
      "epoch": 5.0192539109506615,
      "grad_norm": 10.512737274169922,
      "learning_rate": 2e-05,
      "loss": 6.1863,
      "step": 261
    },
    {
      "epoch": 5.038507821901324,
      "grad_norm": 11.778082847595215,
      "learning_rate": 2e-05,
      "loss": 6.2453,
      "step": 262
    },
    {
      "epoch": 5.0577617328519855,
      "grad_norm": 8.815237998962402,
      "learning_rate": 2e-05,
      "loss": 6.0878,
      "step": 263
    },
    {
      "epoch": 5.077015643802647,
      "grad_norm": 8.149435997009277,
      "learning_rate": 2e-05,
      "loss": 6.109,
      "step": 264
    },
    {
      "epoch": 5.0962695547533094,
      "grad_norm": 17.911197662353516,
      "learning_rate": 2e-05,
      "loss": 6.5584,
      "step": 265
    },
    {
      "epoch": 5.115523465703971,
      "grad_norm": 15.374232292175293,
      "learning_rate": 2e-05,
      "loss": 5.6938,
      "step": 266
    },
    {
      "epoch": 5.1347773766546325,
      "grad_norm": 14.54749870300293,
      "learning_rate": 2e-05,
      "loss": 6.0208,
      "step": 267
    },
    {
      "epoch": 5.154031287605295,
      "grad_norm": 22.222078323364258,
      "learning_rate": 2e-05,
      "loss": 6.6856,
      "step": 268
    },
    {
      "epoch": 5.1732851985559565,
      "grad_norm": 14.544611930847168,
      "learning_rate": 2e-05,
      "loss": 6.5379,
      "step": 269
    },
    {
      "epoch": 5.192539109506619,
      "grad_norm": 7.748518466949463,
      "learning_rate": 2e-05,
      "loss": 6.124,
      "step": 270
    },
    {
      "epoch": 5.21179302045728,
      "grad_norm": 38.051204681396484,
      "learning_rate": 2e-05,
      "loss": 5.5926,
      "step": 271
    },
    {
      "epoch": 5.231046931407942,
      "grad_norm": 8.9555025100708,
      "learning_rate": 2e-05,
      "loss": 6.2883,
      "step": 272
    },
    {
      "epoch": 5.250300842358604,
      "grad_norm": 8.490158081054688,
      "learning_rate": 2e-05,
      "loss": 6.1882,
      "step": 273
    },
    {
      "epoch": 5.269554753309266,
      "grad_norm": 23.794368743896484,
      "learning_rate": 2e-05,
      "loss": 5.7156,
      "step": 274
    },
    {
      "epoch": 5.2888086642599275,
      "grad_norm": 9.640610694885254,
      "learning_rate": 2e-05,
      "loss": 6.0328,
      "step": 275
    },
    {
      "epoch": 5.2888086642599275,
      "eval_clap": 0.10059554874897003,
      "eval_loss": 5.7012224197387695,
      "eval_runtime": 196.9351,
      "eval_samples_per_second": 0.162,
      "eval_steps_per_second": 0.162,
      "step": 275
    },
    {
      "epoch": 5.30806257521059,
      "grad_norm": 10.774741172790527,
      "learning_rate": 2e-05,
      "loss": 6.0371,
      "step": 276
    },
    {
      "epoch": 5.327316486161251,
      "grad_norm": 31.07454490661621,
      "learning_rate": 2e-05,
      "loss": 5.4832,
      "step": 277
    },
    {
      "epoch": 5.346570397111913,
      "grad_norm": 20.25762939453125,
      "learning_rate": 2e-05,
      "loss": 5.829,
      "step": 278
    },
    {
      "epoch": 5.365824308062575,
      "grad_norm": 14.205655097961426,
      "learning_rate": 2e-05,
      "loss": 5.8925,
      "step": 279
    },
    {
      "epoch": 5.385078219013237,
      "grad_norm": 10.45982551574707,
      "learning_rate": 2e-05,
      "loss": 5.9619,
      "step": 280
    },
    {
      "epoch": 5.404332129963899,
      "grad_norm": 10.787467956542969,
      "learning_rate": 2e-05,
      "loss": 6.2064,
      "step": 281
    },
    {
      "epoch": 5.423586040914561,
      "grad_norm": 14.345209121704102,
      "learning_rate": 2e-05,
      "loss": 6.4463,
      "step": 282
    },
    {
      "epoch": 5.442839951865222,
      "grad_norm": 11.769346237182617,
      "learning_rate": 2e-05,
      "loss": 6.2416,
      "step": 283
    },
    {
      "epoch": 5.462093862815885,
      "grad_norm": 10.520780563354492,
      "learning_rate": 2e-05,
      "loss": 5.9882,
      "step": 284
    },
    {
      "epoch": 5.481347773766546,
      "grad_norm": 9.365582466125488,
      "learning_rate": 2e-05,
      "loss": 6.1293,
      "step": 285
    },
    {
      "epoch": 5.500601684717208,
      "grad_norm": 11.546175003051758,
      "learning_rate": 2e-05,
      "loss": 6.1385,
      "step": 286
    },
    {
      "epoch": 5.51985559566787,
      "grad_norm": 8.784673690795898,
      "learning_rate": 2e-05,
      "loss": 5.9021,
      "step": 287
    },
    {
      "epoch": 5.539109506618532,
      "grad_norm": 14.96414566040039,
      "learning_rate": 2e-05,
      "loss": 5.7696,
      "step": 288
    },
    {
      "epoch": 5.558363417569193,
      "grad_norm": 10.28773307800293,
      "learning_rate": 2e-05,
      "loss": 5.8558,
      "step": 289
    },
    {
      "epoch": 5.577617328519856,
      "grad_norm": 8.956218719482422,
      "learning_rate": 2e-05,
      "loss": 6.1751,
      "step": 290
    },
    {
      "epoch": 5.596871239470517,
      "grad_norm": 8.992794036865234,
      "learning_rate": 2e-05,
      "loss": 5.9301,
      "step": 291
    },
    {
      "epoch": 5.61612515042118,
      "grad_norm": 15.411934852600098,
      "learning_rate": 2e-05,
      "loss": 5.7903,
      "step": 292
    },
    {
      "epoch": 5.635379061371841,
      "grad_norm": 17.23996925354004,
      "learning_rate": 2e-05,
      "loss": 5.7608,
      "step": 293
    },
    {
      "epoch": 5.654632972322503,
      "grad_norm": 9.80339241027832,
      "learning_rate": 2e-05,
      "loss": 5.9715,
      "step": 294
    },
    {
      "epoch": 5.673886883273164,
      "grad_norm": 9.020657539367676,
      "learning_rate": 2e-05,
      "loss": 5.9026,
      "step": 295
    },
    {
      "epoch": 5.693140794223827,
      "grad_norm": 10.856344223022461,
      "learning_rate": 2e-05,
      "loss": 5.9779,
      "step": 296
    },
    {
      "epoch": 5.712394705174488,
      "grad_norm": 8.707733154296875,
      "learning_rate": 2e-05,
      "loss": 6.1238,
      "step": 297
    },
    {
      "epoch": 5.731648616125151,
      "grad_norm": 14.64277172088623,
      "learning_rate": 2e-05,
      "loss": 6.0237,
      "step": 298
    },
    {
      "epoch": 5.750902527075812,
      "grad_norm": 11.925372123718262,
      "learning_rate": 2e-05,
      "loss": 6.393,
      "step": 299
    },
    {
      "epoch": 5.770156438026474,
      "grad_norm": 8.235823631286621,
      "learning_rate": 2e-05,
      "loss": 6.1476,
      "step": 300
    },
    {
      "epoch": 5.770156438026474,
      "eval_clap": 0.08804576098918915,
      "eval_loss": 5.670257568359375,
      "eval_runtime": 196.4571,
      "eval_samples_per_second": 0.163,
      "eval_steps_per_second": 0.163,
      "step": 300
    },
    {
      "epoch": 5.789410348977136,
      "grad_norm": 10.681437492370605,
      "learning_rate": 2e-05,
      "loss": 6.5,
      "step": 301
    },
    {
      "epoch": 5.808664259927798,
      "grad_norm": 7.725464820861816,
      "learning_rate": 2e-05,
      "loss": 6.3363,
      "step": 302
    },
    {
      "epoch": 5.827918170878459,
      "grad_norm": 23.754108428955078,
      "learning_rate": 2e-05,
      "loss": 5.4885,
      "step": 303
    },
    {
      "epoch": 5.847172081829122,
      "grad_norm": 16.799196243286133,
      "learning_rate": 2e-05,
      "loss": 5.8577,
      "step": 304
    },
    {
      "epoch": 5.866425992779783,
      "grad_norm": 18.410417556762695,
      "learning_rate": 2e-05,
      "loss": 5.7364,
      "step": 305
    },
    {
      "epoch": 5.885679903730445,
      "grad_norm": 13.101805686950684,
      "learning_rate": 2e-05,
      "loss": 6.1962,
      "step": 306
    },
    {
      "epoch": 5.904933814681107,
      "grad_norm": 20.438919067382812,
      "learning_rate": 2e-05,
      "loss": 5.6507,
      "step": 307
    },
    {
      "epoch": 5.924187725631769,
      "grad_norm": 16.583629608154297,
      "learning_rate": 2e-05,
      "loss": 5.6965,
      "step": 308
    },
    {
      "epoch": 5.943441636582431,
      "grad_norm": 12.213188171386719,
      "learning_rate": 2e-05,
      "loss": 5.9619,
      "step": 309
    },
    {
      "epoch": 5.962695547533093,
      "grad_norm": 10.092710494995117,
      "learning_rate": 2e-05,
      "loss": 5.9366,
      "step": 310
    },
    {
      "epoch": 5.981949458483754,
      "grad_norm": 11.882303237915039,
      "learning_rate": 2e-05,
      "loss": 5.653,
      "step": 311
    },
    {
      "epoch": 6.0,
      "grad_norm": 14.35622501373291,
      "learning_rate": 2e-05,
      "loss": 5.3527,
      "step": 312
    },
    {
      "epoch": 6.0192539109506615,
      "grad_norm": 15.661309242248535,
      "learning_rate": 2e-05,
      "loss": 5.9525,
      "step": 313
    },
    {
      "epoch": 6.038507821901324,
      "grad_norm": 20.924646377563477,
      "learning_rate": 2e-05,
      "loss": 6.5313,
      "step": 314
    },
    {
      "epoch": 6.0577617328519855,
      "grad_norm": 14.876949310302734,
      "learning_rate": 2e-05,
      "loss": 5.6237,
      "step": 315
    },
    {
      "epoch": 6.077015643802647,
      "grad_norm": 14.90765380859375,
      "learning_rate": 2e-05,
      "loss": 5.9514,
      "step": 316
    },
    {
      "epoch": 6.0962695547533094,
      "grad_norm": 11.085007667541504,
      "learning_rate": 2e-05,
      "loss": 6.3012,
      "step": 317
    },
    {
      "epoch": 6.115523465703971,
      "grad_norm": 7.102397918701172,
      "learning_rate": 2e-05,
      "loss": 6.2968,
      "step": 318
    },
    {
      "epoch": 6.1347773766546325,
      "grad_norm": 10.636114120483398,
      "learning_rate": 2e-05,
      "loss": 6.0036,
      "step": 319
    },
    {
      "epoch": 6.154031287605295,
      "grad_norm": 9.180078506469727,
      "learning_rate": 2e-05,
      "loss": 5.8668,
      "step": 320
    },
    {
      "epoch": 6.1732851985559565,
      "grad_norm": 8.283641815185547,
      "learning_rate": 2e-05,
      "loss": 5.9111,
      "step": 321
    },
    {
      "epoch": 6.192539109506619,
      "grad_norm": 16.489126205444336,
      "learning_rate": 2e-05,
      "loss": 5.7074,
      "step": 322
    },
    {
      "epoch": 6.21179302045728,
      "grad_norm": 8.536720275878906,
      "learning_rate": 2e-05,
      "loss": 6.0873,
      "step": 323
    },
    {
      "epoch": 6.231046931407942,
      "grad_norm": 19.378023147583008,
      "learning_rate": 2e-05,
      "loss": 5.7451,
      "step": 324
    },
    {
      "epoch": 6.250300842358604,
      "grad_norm": 8.368978500366211,
      "learning_rate": 2e-05,
      "loss": 5.9049,
      "step": 325
    },
    {
      "epoch": 6.250300842358604,
      "eval_clap": 0.12603802978992462,
      "eval_loss": 5.833277702331543,
      "eval_runtime": 196.2372,
      "eval_samples_per_second": 0.163,
      "eval_steps_per_second": 0.163,
      "step": 325
    },
    {
      "epoch": 6.269554753309266,
      "grad_norm": 9.310341835021973,
      "learning_rate": 2e-05,
      "loss": 5.9592,
      "step": 326
    },
    {
      "epoch": 6.2888086642599275,
      "grad_norm": 10.618816375732422,
      "learning_rate": 2e-05,
      "loss": 5.7331,
      "step": 327
    },
    {
      "epoch": 6.30806257521059,
      "grad_norm": 20.578750610351562,
      "learning_rate": 2e-05,
      "loss": 5.2624,
      "step": 328
    },
    {
      "epoch": 6.327316486161251,
      "grad_norm": 9.402525901794434,
      "learning_rate": 2e-05,
      "loss": 6.067,
      "step": 329
    },
    {
      "epoch": 6.346570397111913,
      "grad_norm": 9.60403060913086,
      "learning_rate": 2e-05,
      "loss": 6.214,
      "step": 330
    },
    {
      "epoch": 6.365824308062575,
      "grad_norm": 14.769834518432617,
      "learning_rate": 2e-05,
      "loss": 5.7947,
      "step": 331
    },
    {
      "epoch": 6.385078219013237,
      "grad_norm": 7.659432411193848,
      "learning_rate": 2e-05,
      "loss": 5.8996,
      "step": 332
    },
    {
      "epoch": 6.404332129963899,
      "grad_norm": 9.789624214172363,
      "learning_rate": 2e-05,
      "loss": 6.0822,
      "step": 333
    },
    {
      "epoch": 6.423586040914561,
      "grad_norm": 13.061244010925293,
      "learning_rate": 2e-05,
      "loss": 5.8736,
      "step": 334
    },
    {
      "epoch": 6.442839951865222,
      "grad_norm": 9.671375274658203,
      "learning_rate": 2e-05,
      "loss": 5.6454,
      "step": 335
    },
    {
      "epoch": 6.462093862815885,
      "grad_norm": 7.602629661560059,
      "learning_rate": 2e-05,
      "loss": 6.1014,
      "step": 336
    },
    {
      "epoch": 6.481347773766546,
      "grad_norm": 9.208328247070312,
      "learning_rate": 2e-05,
      "loss": 5.8553,
      "step": 337
    },
    {
      "epoch": 6.500601684717208,
      "grad_norm": 6.751482963562012,
      "learning_rate": 2e-05,
      "loss": 6.3873,
      "step": 338
    },
    {
      "epoch": 6.51985559566787,
      "grad_norm": 19.14604377746582,
      "learning_rate": 2e-05,
      "loss": 5.5979,
      "step": 339
    },
    {
      "epoch": 6.539109506618532,
      "grad_norm": 6.979920387268066,
      "learning_rate": 2e-05,
      "loss": 5.9776,
      "step": 340
    },
    {
      "epoch": 6.558363417569193,
      "grad_norm": 12.88497257232666,
      "learning_rate": 2e-05,
      "loss": 6.4447,
      "step": 341
    },
    {
      "epoch": 6.577617328519856,
      "grad_norm": 9.550447463989258,
      "learning_rate": 2e-05,
      "loss": 6.0607,
      "step": 342
    },
    {
      "epoch": 6.596871239470517,
      "grad_norm": 17.2004451751709,
      "learning_rate": 2e-05,
      "loss": 5.8465,
      "step": 343
    },
    {
      "epoch": 6.61612515042118,
      "grad_norm": 9.696534156799316,
      "learning_rate": 2e-05,
      "loss": 5.7955,
      "step": 344
    },
    {
      "epoch": 6.635379061371841,
      "grad_norm": 6.361357688903809,
      "learning_rate": 2e-05,
      "loss": 6.2663,
      "step": 345
    },
    {
      "epoch": 6.654632972322503,
      "grad_norm": 28.56427574157715,
      "learning_rate": 2e-05,
      "loss": 5.0443,
      "step": 346
    },
    {
      "epoch": 6.673886883273164,
      "grad_norm": 10.24687671661377,
      "learning_rate": 2e-05,
      "loss": 5.9321,
      "step": 347
    },
    {
      "epoch": 6.693140794223827,
      "grad_norm": 8.435123443603516,
      "learning_rate": 2e-05,
      "loss": 6.1062,
      "step": 348
    },
    {
      "epoch": 6.712394705174488,
      "grad_norm": 6.668614387512207,
      "learning_rate": 2e-05,
      "loss": 5.9755,
      "step": 349
    },
    {
      "epoch": 6.731648616125151,
      "grad_norm": 8.491061210632324,
      "learning_rate": 2e-05,
      "loss": 5.8547,
      "step": 350
    },
    {
      "epoch": 6.731648616125151,
      "eval_clap": 0.14147447049617767,
      "eval_loss": 5.917084693908691,
      "eval_runtime": 201.9514,
      "eval_samples_per_second": 0.158,
      "eval_steps_per_second": 0.158,
      "step": 350
    },
    {
      "epoch": 6.750902527075812,
      "grad_norm": 10.25600528717041,
      "learning_rate": 2e-05,
      "loss": 5.8823,
      "step": 351
    },
    {
      "epoch": 6.770156438026474,
      "grad_norm": 8.48415470123291,
      "learning_rate": 2e-05,
      "loss": 5.8709,
      "step": 352
    },
    {
      "epoch": 6.789410348977136,
      "grad_norm": 18.866851806640625,
      "learning_rate": 2e-05,
      "loss": 5.7262,
      "step": 353
    },
    {
      "epoch": 6.808664259927798,
      "grad_norm": 7.648865222930908,
      "learning_rate": 2e-05,
      "loss": 5.6922,
      "step": 354
    },
    {
      "epoch": 6.827918170878459,
      "grad_norm": 12.319436073303223,
      "learning_rate": 2e-05,
      "loss": 6.1132,
      "step": 355
    },
    {
      "epoch": 6.847172081829122,
      "grad_norm": 6.688267230987549,
      "learning_rate": 2e-05,
      "loss": 6.0394,
      "step": 356
    },
    {
      "epoch": 6.866425992779783,
      "grad_norm": 8.100188255310059,
      "learning_rate": 2e-05,
      "loss": 5.7567,
      "step": 357
    },
    {
      "epoch": 6.885679903730445,
      "grad_norm": 19.447267532348633,
      "learning_rate": 2e-05,
      "loss": 5.1313,
      "step": 358
    },
    {
      "epoch": 6.904933814681107,
      "grad_norm": 8.269752502441406,
      "learning_rate": 2e-05,
      "loss": 5.6813,
      "step": 359
    },
    {
      "epoch": 6.924187725631769,
      "grad_norm": 11.055656433105469,
      "learning_rate": 2e-05,
      "loss": 5.7952,
      "step": 360
    },
    {
      "epoch": 6.943441636582431,
      "grad_norm": 12.430220603942871,
      "learning_rate": 2e-05,
      "loss": 5.4678,
      "step": 361
    },
    {
      "epoch": 6.962695547533093,
      "grad_norm": 9.070528984069824,
      "learning_rate": 2e-05,
      "loss": 6.3099,
      "step": 362
    },
    {
      "epoch": 6.981949458483754,
      "grad_norm": 11.570778846740723,
      "learning_rate": 2e-05,
      "loss": 5.9188,
      "step": 363
    },
    {
      "epoch": 7.0,
      "grad_norm": 7.6774821281433105,
      "learning_rate": 2e-05,
      "loss": 5.7076,
      "step": 364
    },
    {
      "epoch": 7.0192539109506615,
      "grad_norm": 7.454392910003662,
      "learning_rate": 2e-05,
      "loss": 6.3174,
      "step": 365
    },
    {
      "epoch": 7.038507821901324,
      "grad_norm": 16.39904022216797,
      "learning_rate": 2e-05,
      "loss": 5.5487,
      "step": 366
    },
    {
      "epoch": 7.0577617328519855,
      "grad_norm": 8.567000389099121,
      "learning_rate": 2e-05,
      "loss": 5.8364,
      "step": 367
    },
    {
      "epoch": 7.077015643802647,
      "grad_norm": 11.228474617004395,
      "learning_rate": 2e-05,
      "loss": 6.1298,
      "step": 368
    },
    {
      "epoch": 7.0962695547533094,
      "grad_norm": 8.90956974029541,
      "learning_rate": 2e-05,
      "loss": 5.8714,
      "step": 369
    },
    {
      "epoch": 7.115523465703971,
      "grad_norm": 11.500467300415039,
      "learning_rate": 2e-05,
      "loss": 6.0238,
      "step": 370
    },
    {
      "epoch": 7.1347773766546325,
      "grad_norm": 9.86660099029541,
      "learning_rate": 2e-05,
      "loss": 5.4866,
      "step": 371
    },
    {
      "epoch": 7.154031287605295,
      "grad_norm": 15.263172149658203,
      "learning_rate": 2e-05,
      "loss": 5.6674,
      "step": 372
    },
    {
      "epoch": 7.1732851985559565,
      "grad_norm": 9.802757263183594,
      "learning_rate": 2e-05,
      "loss": 6.2604,
      "step": 373
    },
    {
      "epoch": 7.192539109506619,
      "grad_norm": 9.074177742004395,
      "learning_rate": 2e-05,
      "loss": 6.0723,
      "step": 374
    },
    {
      "epoch": 7.21179302045728,
      "grad_norm": 13.025900840759277,
      "learning_rate": 2e-05,
      "loss": 5.5151,
      "step": 375
    },
    {
      "epoch": 7.21179302045728,
      "eval_clap": 0.14877665042877197,
      "eval_loss": 6.030681610107422,
      "eval_runtime": 196.9659,
      "eval_samples_per_second": 0.162,
      "eval_steps_per_second": 0.162,
      "step": 375
    },
    {
      "epoch": 7.231046931407942,
      "grad_norm": 8.610788345336914,
      "learning_rate": 2e-05,
      "loss": 5.4889,
      "step": 376
    },
    {
      "epoch": 7.250300842358604,
      "grad_norm": 8.993633270263672,
      "learning_rate": 2e-05,
      "loss": 6.0395,
      "step": 377
    },
    {
      "epoch": 7.269554753309266,
      "grad_norm": 11.314407348632812,
      "learning_rate": 2e-05,
      "loss": 5.7346,
      "step": 378
    },
    {
      "epoch": 7.2888086642599275,
      "grad_norm": 6.467037677764893,
      "learning_rate": 2e-05,
      "loss": 5.7235,
      "step": 379
    },
    {
      "epoch": 7.30806257521059,
      "grad_norm": 8.104763984680176,
      "learning_rate": 2e-05,
      "loss": 5.9586,
      "step": 380
    },
    {
      "epoch": 7.327316486161251,
      "grad_norm": 7.068090915679932,
      "learning_rate": 2e-05,
      "loss": 5.9094,
      "step": 381
    },
    {
      "epoch": 7.346570397111913,
      "grad_norm": 12.21611213684082,
      "learning_rate": 2e-05,
      "loss": 5.4139,
      "step": 382
    },
    {
      "epoch": 7.365824308062575,
      "grad_norm": 7.650627136230469,
      "learning_rate": 2e-05,
      "loss": 5.9595,
      "step": 383
    },
    {
      "epoch": 7.385078219013237,
      "grad_norm": 9.73534107208252,
      "learning_rate": 2e-05,
      "loss": 5.6262,
      "step": 384
    },
    {
      "epoch": 7.404332129963899,
      "grad_norm": 4.8408989906311035,
      "learning_rate": 2e-05,
      "loss": 6.2293,
      "step": 385
    },
    {
      "epoch": 7.423586040914561,
      "grad_norm": 8.489951133728027,
      "learning_rate": 2e-05,
      "loss": 5.7281,
      "step": 386
    },
    {
      "epoch": 7.442839951865222,
      "grad_norm": 11.095331192016602,
      "learning_rate": 2e-05,
      "loss": 5.7553,
      "step": 387
    },
    {
      "epoch": 7.462093862815885,
      "grad_norm": 11.590924263000488,
      "learning_rate": 2e-05,
      "loss": 5.5951,
      "step": 388
    },
    {
      "epoch": 7.481347773766546,
      "grad_norm": 8.009002685546875,
      "learning_rate": 2e-05,
      "loss": 5.8574,
      "step": 389
    },
    {
      "epoch": 7.500601684717208,
      "grad_norm": 6.733258247375488,
      "learning_rate": 2e-05,
      "loss": 5.9511,
      "step": 390
    },
    {
      "epoch": 7.51985559566787,
      "grad_norm": 12.49974250793457,
      "learning_rate": 2e-05,
      "loss": 5.8766,
      "step": 391
    },
    {
      "epoch": 7.539109506618532,
      "grad_norm": 8.18664264678955,
      "learning_rate": 2e-05,
      "loss": 6.2401,
      "step": 392
    },
    {
      "epoch": 7.558363417569193,
      "grad_norm": 7.806461811065674,
      "learning_rate": 2e-05,
      "loss": 5.6931,
      "step": 393
    },
    {
      "epoch": 7.577617328519856,
      "grad_norm": 11.137080192565918,
      "learning_rate": 2e-05,
      "loss": 5.447,
      "step": 394
    },
    {
      "epoch": 7.596871239470517,
      "grad_norm": 7.18437385559082,
      "learning_rate": 2e-05,
      "loss": 5.8764,
      "step": 395
    },
    {
      "epoch": 7.61612515042118,
      "grad_norm": 7.777758598327637,
      "learning_rate": 2e-05,
      "loss": 5.9383,
      "step": 396
    },
    {
      "epoch": 7.635379061371841,
      "grad_norm": 10.361425399780273,
      "learning_rate": 2e-05,
      "loss": 5.8001,
      "step": 397
    },
    {
      "epoch": 7.654632972322503,
      "grad_norm": 6.713755130767822,
      "learning_rate": 2e-05,
      "loss": 6.1663,
      "step": 398
    },
    {
      "epoch": 7.673886883273164,
      "grad_norm": 10.869112014770508,
      "learning_rate": 2e-05,
      "loss": 5.9626,
      "step": 399
    },
    {
      "epoch": 7.693140794223827,
      "grad_norm": 7.977558135986328,
      "learning_rate": 2e-05,
      "loss": 6.0651,
      "step": 400
    },
    {
      "epoch": 7.693140794223827,
      "eval_clap": 0.15197913348674774,
      "eval_loss": 6.068316459655762,
      "eval_runtime": 198.5968,
      "eval_samples_per_second": 0.161,
      "eval_steps_per_second": 0.161,
      "step": 400
    },
    {
      "epoch": 7.712394705174488,
      "grad_norm": 9.780762672424316,
      "learning_rate": 2e-05,
      "loss": 5.5897,
      "step": 401
    },
    {
      "epoch": 7.731648616125151,
      "grad_norm": 6.951937198638916,
      "learning_rate": 2e-05,
      "loss": 6.2431,
      "step": 402
    },
    {
      "epoch": 7.750902527075812,
      "grad_norm": 9.692300796508789,
      "learning_rate": 2e-05,
      "loss": 5.4305,
      "step": 403
    },
    {
      "epoch": 7.770156438026474,
      "grad_norm": 7.418123245239258,
      "learning_rate": 2e-05,
      "loss": 5.8003,
      "step": 404
    },
    {
      "epoch": 7.789410348977136,
      "grad_norm": 6.651110649108887,
      "learning_rate": 2e-05,
      "loss": 5.7815,
      "step": 405
    },
    {
      "epoch": 7.808664259927798,
      "grad_norm": 6.156674861907959,
      "learning_rate": 2e-05,
      "loss": 6.4313,
      "step": 406
    },
    {
      "epoch": 7.827918170878459,
      "grad_norm": 8.222352981567383,
      "learning_rate": 2e-05,
      "loss": 6.2155,
      "step": 407
    },
    {
      "epoch": 7.847172081829122,
      "grad_norm": 16.708091735839844,
      "learning_rate": 2e-05,
      "loss": 5.5932,
      "step": 408
    },
    {
      "epoch": 7.866425992779783,
      "grad_norm": 7.200738906860352,
      "learning_rate": 2e-05,
      "loss": 5.7048,
      "step": 409
    },
    {
      "epoch": 7.885679903730445,
      "grad_norm": 7.8692450523376465,
      "learning_rate": 2e-05,
      "loss": 6.0216,
      "step": 410
    },
    {
      "epoch": 7.904933814681107,
      "grad_norm": 9.36465835571289,
      "learning_rate": 2e-05,
      "loss": 5.5713,
      "step": 411
    },
    {
      "epoch": 7.924187725631769,
      "grad_norm": 6.110987186431885,
      "learning_rate": 2e-05,
      "loss": 5.972,
      "step": 412
    },
    {
      "epoch": 7.943441636582431,
      "grad_norm": 10.555682182312012,
      "learning_rate": 2e-05,
      "loss": 5.1856,
      "step": 413
    },
    {
      "epoch": 7.962695547533093,
      "grad_norm": 8.164458274841309,
      "learning_rate": 2e-05,
      "loss": 5.9857,
      "step": 414
    },
    {
      "epoch": 7.981949458483754,
      "grad_norm": 6.370028018951416,
      "learning_rate": 2e-05,
      "loss": 6.2021,
      "step": 415
    },
    {
      "epoch": 8.0,
      "grad_norm": 7.894473552703857,
      "learning_rate": 2e-05,
      "loss": 5.1235,
      "step": 416
    },
    {
      "epoch": 8.019253910950662,
      "grad_norm": 8.825623512268066,
      "learning_rate": 2e-05,
      "loss": 5.7924,
      "step": 417
    },
    {
      "epoch": 8.038507821901323,
      "grad_norm": 10.459378242492676,
      "learning_rate": 2e-05,
      "loss": 5.8566,
      "step": 418
    },
    {
      "epoch": 8.057761732851986,
      "grad_norm": 7.0936713218688965,
      "learning_rate": 2e-05,
      "loss": 6.2791,
      "step": 419
    },
    {
      "epoch": 8.077015643802648,
      "grad_norm": 6.6698079109191895,
      "learning_rate": 2e-05,
      "loss": 6.1026,
      "step": 420
    },
    {
      "epoch": 8.09626955475331,
      "grad_norm": 12.212193489074707,
      "learning_rate": 2e-05,
      "loss": 5.4735,
      "step": 421
    },
    {
      "epoch": 8.115523465703971,
      "grad_norm": 10.958526611328125,
      "learning_rate": 2e-05,
      "loss": 5.3301,
      "step": 422
    },
    {
      "epoch": 8.134777376654633,
      "grad_norm": 9.644707679748535,
      "learning_rate": 2e-05,
      "loss": 6.2481,
      "step": 423
    },
    {
      "epoch": 8.154031287605294,
      "grad_norm": 7.314677715301514,
      "learning_rate": 2e-05,
      "loss": 5.6373,
      "step": 424
    },
    {
      "epoch": 8.173285198555957,
      "grad_norm": 6.350398063659668,
      "learning_rate": 2e-05,
      "loss": 6.0339,
      "step": 425
    },
    {
      "epoch": 8.173285198555957,
      "eval_clap": 0.14958661794662476,
      "eval_loss": 6.165280342102051,
      "eval_runtime": 204.1039,
      "eval_samples_per_second": 0.157,
      "eval_steps_per_second": 0.157,
      "step": 425
    },
    {
      "epoch": 8.192539109506619,
      "grad_norm": 5.304975509643555,
      "learning_rate": 2e-05,
      "loss": 6.1317,
      "step": 426
    },
    {
      "epoch": 8.21179302045728,
      "grad_norm": 6.82647705078125,
      "learning_rate": 2e-05,
      "loss": 5.4539,
      "step": 427
    },
    {
      "epoch": 8.231046931407942,
      "grad_norm": 8.981968879699707,
      "learning_rate": 2e-05,
      "loss": 5.739,
      "step": 428
    },
    {
      "epoch": 8.250300842358604,
      "grad_norm": 9.646061897277832,
      "learning_rate": 2e-05,
      "loss": 5.737,
      "step": 429
    },
    {
      "epoch": 8.269554753309265,
      "grad_norm": 9.535126686096191,
      "learning_rate": 2e-05,
      "loss": 6.1408,
      "step": 430
    },
    {
      "epoch": 8.288808664259928,
      "grad_norm": 6.139739513397217,
      "learning_rate": 2e-05,
      "loss": 6.2988,
      "step": 431
    },
    {
      "epoch": 8.30806257521059,
      "grad_norm": 6.903513431549072,
      "learning_rate": 2e-05,
      "loss": 6.0573,
      "step": 432
    },
    {
      "epoch": 8.327316486161251,
      "grad_norm": 11.271062850952148,
      "learning_rate": 2e-05,
      "loss": 6.2397,
      "step": 433
    },
    {
      "epoch": 8.346570397111913,
      "grad_norm": 6.281597137451172,
      "learning_rate": 2e-05,
      "loss": 6.16,
      "step": 434
    },
    {
      "epoch": 8.365824308062574,
      "grad_norm": 7.392561912536621,
      "learning_rate": 2e-05,
      "loss": 6.0408,
      "step": 435
    },
    {
      "epoch": 8.385078219013238,
      "grad_norm": 13.390826225280762,
      "learning_rate": 2e-05,
      "loss": 5.5365,
      "step": 436
    },
    {
      "epoch": 8.4043321299639,
      "grad_norm": 6.831297397613525,
      "learning_rate": 2e-05,
      "loss": 5.9492,
      "step": 437
    },
    {
      "epoch": 8.42358604091456,
      "grad_norm": 8.311152458190918,
      "learning_rate": 2e-05,
      "loss": 6.0555,
      "step": 438
    },
    {
      "epoch": 8.442839951865222,
      "grad_norm": 5.671159267425537,
      "learning_rate": 2e-05,
      "loss": 6.1021,
      "step": 439
    },
    {
      "epoch": 8.462093862815884,
      "grad_norm": 12.393537521362305,
      "learning_rate": 2e-05,
      "loss": 5.3335,
      "step": 440
    },
    {
      "epoch": 8.481347773766545,
      "grad_norm": 7.936432361602783,
      "learning_rate": 2e-05,
      "loss": 5.537,
      "step": 441
    },
    {
      "epoch": 8.500601684717209,
      "grad_norm": 8.93083667755127,
      "learning_rate": 2e-05,
      "loss": 5.6945,
      "step": 442
    },
    {
      "epoch": 8.51985559566787,
      "grad_norm": 7.8789238929748535,
      "learning_rate": 2e-05,
      "loss": 6.4316,
      "step": 443
    },
    {
      "epoch": 8.539109506618532,
      "grad_norm": 7.957115650177002,
      "learning_rate": 2e-05,
      "loss": 5.4203,
      "step": 444
    },
    {
      "epoch": 8.558363417569193,
      "grad_norm": 6.194324016571045,
      "learning_rate": 2e-05,
      "loss": 5.8967,
      "step": 445
    },
    {
      "epoch": 8.577617328519855,
      "grad_norm": 9.573834419250488,
      "learning_rate": 2e-05,
      "loss": 5.7136,
      "step": 446
    },
    {
      "epoch": 8.596871239470518,
      "grad_norm": 8.004561424255371,
      "learning_rate": 2e-05,
      "loss": 5.5264,
      "step": 447
    },
    {
      "epoch": 8.61612515042118,
      "grad_norm": 6.711611747741699,
      "learning_rate": 2e-05,
      "loss": 6.0729,
      "step": 448
    },
    {
      "epoch": 8.635379061371841,
      "grad_norm": 8.102109909057617,
      "learning_rate": 2e-05,
      "loss": 5.3048,
      "step": 449
    },
    {
      "epoch": 8.654632972322503,
      "grad_norm": 11.3334379196167,
      "learning_rate": 2e-05,
      "loss": 5.5607,
      "step": 450
    },
    {
      "epoch": 8.654632972322503,
      "eval_clap": 0.1344371885061264,
      "eval_loss": 6.358816146850586,
      "eval_runtime": 205.1551,
      "eval_samples_per_second": 0.156,
      "eval_steps_per_second": 0.156,
      "step": 450
    },
    {
      "epoch": 8.673886883273164,
      "grad_norm": 7.845404148101807,
      "learning_rate": 2e-05,
      "loss": 5.6627,
      "step": 451
    },
    {
      "epoch": 8.693140794223826,
      "grad_norm": 5.972433090209961,
      "learning_rate": 2e-05,
      "loss": 6.3562,
      "step": 452
    },
    {
      "epoch": 8.71239470517449,
      "grad_norm": 9.84822940826416,
      "learning_rate": 2e-05,
      "loss": 5.4597,
      "step": 453
    },
    {
      "epoch": 8.73164861612515,
      "grad_norm": 9.735132217407227,
      "learning_rate": 2e-05,
      "loss": 5.9511,
      "step": 454
    },
    {
      "epoch": 8.750902527075812,
      "grad_norm": 8.289355278015137,
      "learning_rate": 2e-05,
      "loss": 5.7793,
      "step": 455
    },
    {
      "epoch": 8.770156438026474,
      "grad_norm": 10.302011489868164,
      "learning_rate": 2e-05,
      "loss": 5.7178,
      "step": 456
    },
    {
      "epoch": 8.789410348977135,
      "grad_norm": 12.201030731201172,
      "learning_rate": 2e-05,
      "loss": 5.4838,
      "step": 457
    },
    {
      "epoch": 8.808664259927799,
      "grad_norm": 8.123917579650879,
      "learning_rate": 2e-05,
      "loss": 5.6764,
      "step": 458
    },
    {
      "epoch": 8.82791817087846,
      "grad_norm": 7.225223064422607,
      "learning_rate": 2e-05,
      "loss": 5.7118,
      "step": 459
    },
    {
      "epoch": 8.847172081829122,
      "grad_norm": 10.377509117126465,
      "learning_rate": 2e-05,
      "loss": 5.6576,
      "step": 460
    },
    {
      "epoch": 8.866425992779783,
      "grad_norm": 7.475393772125244,
      "learning_rate": 2e-05,
      "loss": 5.3861,
      "step": 461
    },
    {
      "epoch": 8.885679903730445,
      "grad_norm": 11.457231521606445,
      "learning_rate": 2e-05,
      "loss": 5.8163,
      "step": 462
    },
    {
      "epoch": 8.904933814681106,
      "grad_norm": 5.9624199867248535,
      "learning_rate": 2e-05,
      "loss": 6.0883,
      "step": 463
    },
    {
      "epoch": 8.92418772563177,
      "grad_norm": 15.740527153015137,
      "learning_rate": 2e-05,
      "loss": 5.1762,
      "step": 464
    },
    {
      "epoch": 8.943441636582431,
      "grad_norm": 6.486323833465576,
      "learning_rate": 2e-05,
      "loss": 6.0539,
      "step": 465
    },
    {
      "epoch": 8.962695547533093,
      "grad_norm": 6.787285804748535,
      "learning_rate": 2e-05,
      "loss": 6.007,
      "step": 466
    },
    {
      "epoch": 8.981949458483754,
      "grad_norm": 9.911301612854004,
      "learning_rate": 2e-05,
      "loss": 5.0872,
      "step": 467
    },
    {
      "epoch": 9.0,
      "grad_norm": 7.354274749755859,
      "learning_rate": 2e-05,
      "loss": 5.5188,
      "step": 468
    },
    {
      "epoch": 9.019253910950662,
      "grad_norm": 7.0421881675720215,
      "learning_rate": 2e-05,
      "loss": 5.6728,
      "step": 469
    },
    {
      "epoch": 9.038507821901323,
      "grad_norm": 8.74863052368164,
      "learning_rate": 2e-05,
      "loss": 5.5255,
      "step": 470
    },
    {
      "epoch": 9.057761732851986,
      "grad_norm": 6.350273609161377,
      "learning_rate": 2e-05,
      "loss": 5.7792,
      "step": 471
    },
    {
      "epoch": 9.077015643802648,
      "grad_norm": 5.793376922607422,
      "learning_rate": 2e-05,
      "loss": 6.019,
      "step": 472
    },
    {
      "epoch": 9.09626955475331,
      "grad_norm": 7.126486778259277,
      "learning_rate": 2e-05,
      "loss": 5.5166,
      "step": 473
    },
    {
      "epoch": 9.115523465703971,
      "grad_norm": 7.304249286651611,
      "learning_rate": 2e-05,
      "loss": 6.2965,
      "step": 474
    },
    {
      "epoch": 9.134777376654633,
      "grad_norm": 6.9295172691345215,
      "learning_rate": 2e-05,
      "loss": 6.0312,
      "step": 475
    },
    {
      "epoch": 9.134777376654633,
      "eval_clap": 0.13584719598293304,
      "eval_loss": 6.450309753417969,
      "eval_runtime": 205.0145,
      "eval_samples_per_second": 0.156,
      "eval_steps_per_second": 0.156,
      "step": 475
    },
    {
      "epoch": 9.154031287605294,
      "grad_norm": 8.397627830505371,
      "learning_rate": 2e-05,
      "loss": 5.1701,
      "step": 476
    },
    {
      "epoch": 9.173285198555957,
      "grad_norm": 8.74401569366455,
      "learning_rate": 2e-05,
      "loss": 5.9924,
      "step": 477
    },
    {
      "epoch": 9.192539109506619,
      "grad_norm": 4.799812316894531,
      "learning_rate": 2e-05,
      "loss": 6.1081,
      "step": 478
    },
    {
      "epoch": 9.21179302045728,
      "grad_norm": 8.459375381469727,
      "learning_rate": 2e-05,
      "loss": 5.1495,
      "step": 479
    },
    {
      "epoch": 9.231046931407942,
      "grad_norm": 12.414017677307129,
      "learning_rate": 2e-05,
      "loss": 5.3805,
      "step": 480
    },
    {
      "epoch": 9.250300842358604,
      "grad_norm": 7.55842924118042,
      "learning_rate": 2e-05,
      "loss": 5.9,
      "step": 481
    },
    {
      "epoch": 9.269554753309265,
      "grad_norm": 7.019160270690918,
      "learning_rate": 2e-05,
      "loss": 6.0315,
      "step": 482
    },
    {
      "epoch": 9.288808664259928,
      "grad_norm": 6.8493852615356445,
      "learning_rate": 2e-05,
      "loss": 5.989,
      "step": 483
    },
    {
      "epoch": 9.30806257521059,
      "grad_norm": 6.040197372436523,
      "learning_rate": 2e-05,
      "loss": 6.1547,
      "step": 484
    },
    {
      "epoch": 9.327316486161251,
      "grad_norm": 6.4489006996154785,
      "learning_rate": 2e-05,
      "loss": 6.1476,
      "step": 485
    },
    {
      "epoch": 9.346570397111913,
      "grad_norm": 6.498973846435547,
      "learning_rate": 2e-05,
      "loss": 5.6649,
      "step": 486
    },
    {
      "epoch": 9.365824308062574,
      "grad_norm": 7.927713394165039,
      "learning_rate": 2e-05,
      "loss": 5.4862,
      "step": 487
    },
    {
      "epoch": 9.385078219013238,
      "grad_norm": 7.368226051330566,
      "learning_rate": 2e-05,
      "loss": 5.8106,
      "step": 488
    },
    {
      "epoch": 9.4043321299639,
      "grad_norm": 8.220806121826172,
      "learning_rate": 2e-05,
      "loss": 5.9079,
      "step": 489
    },
    {
      "epoch": 9.42358604091456,
      "grad_norm": 9.574630737304688,
      "learning_rate": 2e-05,
      "loss": 6.2155,
      "step": 490
    },
    {
      "epoch": 9.442839951865222,
      "grad_norm": 6.782036304473877,
      "learning_rate": 2e-05,
      "loss": 6.0144,
      "step": 491
    },
    {
      "epoch": 9.462093862815884,
      "grad_norm": 8.27569580078125,
      "learning_rate": 2e-05,
      "loss": 5.4657,
      "step": 492
    },
    {
      "epoch": 9.481347773766545,
      "grad_norm": 9.7858304977417,
      "learning_rate": 2e-05,
      "loss": 5.4273,
      "step": 493
    },
    {
      "epoch": 9.500601684717209,
      "grad_norm": 6.2194905281066895,
      "learning_rate": 2e-05,
      "loss": 6.0479,
      "step": 494
    },
    {
      "epoch": 9.51985559566787,
      "grad_norm": 8.673853874206543,
      "learning_rate": 2e-05,
      "loss": 5.8649,
      "step": 495
    },
    {
      "epoch": 9.539109506618532,
      "grad_norm": 7.277229309082031,
      "learning_rate": 2e-05,
      "loss": 5.4538,
      "step": 496
    },
    {
      "epoch": 9.558363417569193,
      "grad_norm": 7.213720798492432,
      "learning_rate": 2e-05,
      "loss": 5.9019,
      "step": 497
    },
    {
      "epoch": 9.577617328519855,
      "grad_norm": 6.2223896980285645,
      "learning_rate": 2e-05,
      "loss": 6.0874,
      "step": 498
    },
    {
      "epoch": 9.596871239470518,
      "grad_norm": 7.928698539733887,
      "learning_rate": 2e-05,
      "loss": 5.5944,
      "step": 499
    },
    {
      "epoch": 9.61612515042118,
      "grad_norm": 6.528334617614746,
      "learning_rate": 2e-05,
      "loss": 5.9084,
      "step": 500
    },
    {
      "epoch": 9.61612515042118,
      "eval_clap": 0.1080508604645729,
      "eval_loss": 6.520473003387451,
      "eval_runtime": 205.013,
      "eval_samples_per_second": 0.156,
      "eval_steps_per_second": 0.156,
      "step": 500
    },
    {
      "epoch": 9.635379061371841,
      "grad_norm": 5.430109024047852,
      "learning_rate": 2e-05,
      "loss": 6.1004,
      "step": 501
    },
    {
      "epoch": 9.654632972322503,
      "grad_norm": 5.635249614715576,
      "learning_rate": 2e-05,
      "loss": 6.0965,
      "step": 502
    },
    {
      "epoch": 9.673886883273164,
      "grad_norm": 11.477826118469238,
      "learning_rate": 2e-05,
      "loss": 5.257,
      "step": 503
    },
    {
      "epoch": 9.693140794223826,
      "grad_norm": 13.920645713806152,
      "learning_rate": 2e-05,
      "loss": 5.6852,
      "step": 504
    },
    {
      "epoch": 9.71239470517449,
      "grad_norm": 7.871194362640381,
      "learning_rate": 2e-05,
      "loss": 5.635,
      "step": 505
    },
    {
      "epoch": 9.73164861612515,
      "grad_norm": 12.229103088378906,
      "learning_rate": 2e-05,
      "loss": 5.6566,
      "step": 506
    },
    {
      "epoch": 9.750902527075812,
      "grad_norm": 6.054317474365234,
      "learning_rate": 2e-05,
      "loss": 6.1042,
      "step": 507
    },
    {
      "epoch": 9.770156438026474,
      "grad_norm": 7.183253288269043,
      "learning_rate": 2e-05,
      "loss": 5.8351,
      "step": 508
    },
    {
      "epoch": 9.789410348977135,
      "grad_norm": 11.31477165222168,
      "learning_rate": 2e-05,
      "loss": 5.8469,
      "step": 509
    },
    {
      "epoch": 9.808664259927799,
      "grad_norm": 8.236515045166016,
      "learning_rate": 2e-05,
      "loss": 5.3767,
      "step": 510
    },
    {
      "epoch": 9.808664259927799,
      "step": 510,
      "total_flos": 1697829404754480.0,
      "train_loss": 6.270190904654709,
      "train_runtime": 7324.9933,
      "train_samples_per_second": 1.134,
      "train_steps_per_second": 0.07
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 510,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1697829404754480.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}