{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 20,
  "global_step": 1078,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0,
      "eval_accuracy": 0.738359201773836,
      "eval_f1": 0.23376623376623376,
      "eval_loss": 0.5994226336479187,
      "eval_precision": 0.6545454545454545,
      "eval_recall": 0.1422924901185771,
      "eval_runtime": 47.8594,
      "eval_samples_per_second": 5.767,
      "eval_steps_per_second": 0.188,
      "step": 0
    },
    {
      "epoch": 0.0009276437847866419,
      "grad_norm": 2.113847255706787,
      "learning_rate": 1.8518518518518518e-07,
      "loss": 0.6464,
      "step": 1
    },
    {
      "epoch": 0.0018552875695732839,
      "grad_norm": 2.337275505065918,
      "learning_rate": 3.7037037037037036e-07,
      "loss": 0.7325,
      "step": 2
    },
    {
      "epoch": 0.0027829313543599257,
      "grad_norm": 2.0731401443481445,
      "learning_rate": 5.555555555555555e-07,
      "loss": 0.6441,
      "step": 3
    },
    {
      "epoch": 0.0037105751391465678,
      "grad_norm": 2.075726270675659,
      "learning_rate": 7.407407407407407e-07,
      "loss": 0.6722,
      "step": 4
    },
    {
      "epoch": 0.00463821892393321,
      "grad_norm": 2.2193410396575928,
      "learning_rate": 9.259259259259259e-07,
      "loss": 0.6676,
      "step": 5
    },
    {
      "epoch": 0.0055658627087198514,
      "grad_norm": 2.2222299575805664,
      "learning_rate": 1.111111111111111e-06,
      "loss": 0.5932,
      "step": 6
    },
    {
      "epoch": 0.006493506493506494,
      "grad_norm": 2.5532214641571045,
      "learning_rate": 1.2962962962962962e-06,
      "loss": 0.6558,
      "step": 7
    },
    {
      "epoch": 0.0074211502782931356,
      "grad_norm": 1.7259494066238403,
      "learning_rate": 1.4814814814814815e-06,
      "loss": 0.5976,
      "step": 8
    },
    {
      "epoch": 0.008348794063079777,
      "grad_norm": 2.020770788192749,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 0.6576,
      "step": 9
    },
    {
      "epoch": 0.00927643784786642,
      "grad_norm": 2.5885586738586426,
      "learning_rate": 1.8518518518518519e-06,
      "loss": 0.6656,
      "step": 10
    },
    {
      "epoch": 0.01020408163265306,
      "grad_norm": 1.901673674583435,
      "learning_rate": 2.037037037037037e-06,
      "loss": 0.6293,
      "step": 11
    },
    {
      "epoch": 0.011131725417439703,
      "grad_norm": 1.867441177368164,
      "learning_rate": 2.222222222222222e-06,
      "loss": 0.5698,
      "step": 12
    },
    {
      "epoch": 0.012059369202226345,
      "grad_norm": 2.405125141143799,
      "learning_rate": 2.4074074074074075e-06,
      "loss": 0.5984,
      "step": 13
    },
    {
      "epoch": 0.012987012987012988,
      "grad_norm": 2.0719292163848877,
      "learning_rate": 2.5925925925925925e-06,
      "loss": 0.5933,
      "step": 14
    },
    {
      "epoch": 0.013914656771799629,
      "grad_norm": 2.2819459438323975,
      "learning_rate": 2.7777777777777783e-06,
      "loss": 0.6439,
      "step": 15
    },
    {
      "epoch": 0.014842300556586271,
      "grad_norm": 2.3114988803863525,
      "learning_rate": 2.962962962962963e-06,
      "loss": 0.6118,
      "step": 16
    },
    {
      "epoch": 0.015769944341372914,
      "grad_norm": 2.1615548133850098,
      "learning_rate": 3.1481481481481483e-06,
      "loss": 0.5185,
      "step": 17
    },
    {
      "epoch": 0.016697588126159554,
      "grad_norm": 2.3003029823303223,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.6267,
      "step": 18
    },
    {
      "epoch": 0.017625231910946195,
      "grad_norm": 2.284081220626831,
      "learning_rate": 3.5185185185185187e-06,
      "loss": 0.6659,
      "step": 19
    },
    {
      "epoch": 0.01855287569573284,
      "grad_norm": 1.8381303548812866,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 0.572,
      "step": 20
    },
    {
      "epoch": 0.01855287569573284,
      "eval_accuracy": 0.7394678492239468,
      "eval_f1": 0.22950819672131148,
      "eval_loss": 0.5945659279823303,
      "eval_precision": 0.6730769230769231,
      "eval_recall": 0.1383399209486166,
      "eval_runtime": 47.6156,
      "eval_samples_per_second": 5.796,
      "eval_steps_per_second": 0.189,
      "step": 20
    },
    {
      "epoch": 0.01948051948051948,
      "grad_norm": 2.036238670349121,
      "learning_rate": 3.88888888888889e-06,
      "loss": 0.6409,
      "step": 21
    },
    {
      "epoch": 0.02040816326530612,
      "grad_norm": 1.9110214710235596,
      "learning_rate": 4.074074074074074e-06,
      "loss": 0.6008,
      "step": 22
    },
    {
      "epoch": 0.021335807050092765,
      "grad_norm": 2.4081571102142334,
      "learning_rate": 4.2592592592592596e-06,
      "loss": 0.632,
      "step": 23
    },
    {
      "epoch": 0.022263450834879406,
      "grad_norm": 1.9782453775405884,
      "learning_rate": 4.444444444444444e-06,
      "loss": 0.6474,
      "step": 24
    },
    {
      "epoch": 0.023191094619666047,
      "grad_norm": 1.7934902906417847,
      "learning_rate": 4.62962962962963e-06,
      "loss": 0.5803,
      "step": 25
    },
    {
      "epoch": 0.02411873840445269,
      "grad_norm": 2.6915359497070312,
      "learning_rate": 4.814814814814815e-06,
      "loss": 0.6505,
      "step": 26
    },
    {
      "epoch": 0.02504638218923933,
      "grad_norm": 1.806140422821045,
      "learning_rate": 5e-06,
      "loss": 0.5283,
      "step": 27
    },
    {
      "epoch": 0.025974025974025976,
      "grad_norm": 1.7927738428115845,
      "learning_rate": 5.185185185185185e-06,
      "loss": 0.5696,
      "step": 28
    },
    {
      "epoch": 0.026901669758812616,
      "grad_norm": 1.7386640310287476,
      "learning_rate": 5.370370370370371e-06,
      "loss": 0.4902,
      "step": 29
    },
    {
      "epoch": 0.027829313543599257,
      "grad_norm": 2.015052318572998,
      "learning_rate": 5.555555555555557e-06,
      "loss": 0.6123,
      "step": 30
    },
    {
      "epoch": 0.0287569573283859,
      "grad_norm": 1.620802402496338,
      "learning_rate": 5.740740740740741e-06,
      "loss": 0.5611,
      "step": 31
    },
    {
      "epoch": 0.029684601113172542,
      "grad_norm": 1.8895862102508545,
      "learning_rate": 5.925925925925926e-06,
      "loss": 0.6024,
      "step": 32
    },
    {
      "epoch": 0.030612244897959183,
      "grad_norm": 2.030715227127075,
      "learning_rate": 6.111111111111112e-06,
      "loss": 0.6245,
      "step": 33
    },
    {
      "epoch": 0.03153988868274583,
      "grad_norm": 2.208017349243164,
      "learning_rate": 6.296296296296297e-06,
      "loss": 0.5331,
      "step": 34
    },
    {
      "epoch": 0.032467532467532464,
      "grad_norm": 2.373842239379883,
      "learning_rate": 6.481481481481482e-06,
      "loss": 0.638,
      "step": 35
    },
    {
      "epoch": 0.03339517625231911,
      "grad_norm": 2.170443296432495,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.563,
      "step": 36
    },
    {
      "epoch": 0.03432282003710575,
      "grad_norm": 1.4894213676452637,
      "learning_rate": 6.851851851851853e-06,
      "loss": 0.5338,
      "step": 37
    },
    {
      "epoch": 0.03525046382189239,
      "grad_norm": 1.9410276412963867,
      "learning_rate": 7.0370370370370375e-06,
      "loss": 0.5609,
      "step": 38
    },
    {
      "epoch": 0.036178107606679034,
      "grad_norm": 2.315661668777466,
      "learning_rate": 7.222222222222223e-06,
      "loss": 0.4866,
      "step": 39
    },
    {
      "epoch": 0.03710575139146568,
      "grad_norm": 1.8483999967575073,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 0.5829,
      "step": 40
    },
    {
      "epoch": 0.03710575139146568,
      "eval_accuracy": 0.7494456762749445,
      "eval_f1": 0.2848101265822785,
      "eval_loss": 0.5677995681762695,
      "eval_precision": 0.7142857142857143,
      "eval_recall": 0.17786561264822134,
      "eval_runtime": 46.6917,
      "eval_samples_per_second": 5.911,
      "eval_steps_per_second": 0.193,
      "step": 40
    },
    {
      "epoch": 0.038033395176252316,
      "grad_norm": 2.0759365558624268,
      "learning_rate": 7.592592592592594e-06,
      "loss": 0.5541,
      "step": 41
    },
    {
      "epoch": 0.03896103896103896,
      "grad_norm": 1.7480107545852661,
      "learning_rate": 7.77777777777778e-06,
      "loss": 0.5236,
      "step": 42
    },
    {
      "epoch": 0.039888682745825604,
      "grad_norm": 1.8141703605651855,
      "learning_rate": 7.962962962962963e-06,
      "loss": 0.519,
      "step": 43
    },
    {
      "epoch": 0.04081632653061224,
      "grad_norm": 1.8323687314987183,
      "learning_rate": 8.148148148148148e-06,
      "loss": 0.5472,
      "step": 44
    },
    {
      "epoch": 0.041743970315398886,
      "grad_norm": 1.6657449007034302,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.4735,
      "step": 45
    },
    {
      "epoch": 0.04267161410018553,
      "grad_norm": 2.900596857070923,
      "learning_rate": 8.518518518518519e-06,
      "loss": 0.5968,
      "step": 46
    },
    {
      "epoch": 0.04359925788497217,
      "grad_norm": 1.9013563394546509,
      "learning_rate": 8.703703703703705e-06,
      "loss": 0.5436,
      "step": 47
    },
    {
      "epoch": 0.04452690166975881,
      "grad_norm": 1.7270978689193726,
      "learning_rate": 8.888888888888888e-06,
      "loss": 0.4987,
      "step": 48
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 1.4679995775222778,
      "learning_rate": 9.074074074074075e-06,
      "loss": 0.4405,
      "step": 49
    },
    {
      "epoch": 0.04638218923933209,
      "grad_norm": 2.332545042037964,
      "learning_rate": 9.25925925925926e-06,
      "loss": 0.5181,
      "step": 50
    },
    {
      "epoch": 0.04730983302411874,
      "grad_norm": 2.0095181465148926,
      "learning_rate": 9.444444444444445e-06,
      "loss": 0.5561,
      "step": 51
    },
    {
      "epoch": 0.04823747680890538,
      "grad_norm": 2.628974199295044,
      "learning_rate": 9.62962962962963e-06,
      "loss": 0.5791,
      "step": 52
    },
    {
      "epoch": 0.04916512059369202,
      "grad_norm": 1.918746829032898,
      "learning_rate": 9.814814814814815e-06,
      "loss": 0.5171,
      "step": 53
    },
    {
      "epoch": 0.05009276437847866,
      "grad_norm": 1.907528281211853,
      "learning_rate": 1e-05,
      "loss": 0.5104,
      "step": 54
    },
    {
      "epoch": 0.05102040816326531,
      "grad_norm": 1.70274817943573,
      "learning_rate": 1.0185185185185186e-05,
      "loss": 0.5104,
      "step": 55
    },
    {
      "epoch": 0.05194805194805195,
      "grad_norm": 2.177898406982422,
      "learning_rate": 1.037037037037037e-05,
      "loss": 0.4683,
      "step": 56
    },
    {
      "epoch": 0.05287569573283859,
      "grad_norm": 2.1687746047973633,
      "learning_rate": 1.0555555555555557e-05,
      "loss": 0.4888,
      "step": 57
    },
    {
      "epoch": 0.05380333951762523,
      "grad_norm": 3.19343900680542,
      "learning_rate": 1.0740740740740742e-05,
      "loss": 0.5476,
      "step": 58
    },
    {
      "epoch": 0.05473098330241188,
      "grad_norm": 2.7876338958740234,
      "learning_rate": 1.0925925925925926e-05,
      "loss": 0.4876,
      "step": 59
    },
    {
      "epoch": 0.055658627087198514,
      "grad_norm": 2.028104066848755,
      "learning_rate": 1.1111111111111113e-05,
      "loss": 0.4808,
      "step": 60
    },
    {
      "epoch": 0.055658627087198514,
      "eval_accuracy": 0.7694013303769401,
      "eval_f1": 0.45549738219895286,
      "eval_loss": 0.512853741645813,
      "eval_precision": 0.6744186046511628,
      "eval_recall": 0.3438735177865613,
      "eval_runtime": 46.8717,
      "eval_samples_per_second": 5.888,
      "eval_steps_per_second": 0.192,
      "step": 60
    },
    {
      "epoch": 0.05658627087198516,
      "grad_norm": 2.1539430618286133,
      "learning_rate": 1.1296296296296297e-05,
      "loss": 0.5098,
      "step": 61
    },
    {
      "epoch": 0.0575139146567718,
      "grad_norm": 2.1614112854003906,
      "learning_rate": 1.1481481481481482e-05,
      "loss": 0.4424,
      "step": 62
    },
    {
      "epoch": 0.05844155844155844,
      "grad_norm": 2.3000025749206543,
      "learning_rate": 1.1666666666666668e-05,
      "loss": 0.4228,
      "step": 63
    },
    {
      "epoch": 0.059369202226345084,
      "grad_norm": 2.695854663848877,
      "learning_rate": 1.1851851851851852e-05,
      "loss": 0.4409,
      "step": 64
    },
    {
      "epoch": 0.06029684601113173,
      "grad_norm": 2.0516905784606934,
      "learning_rate": 1.2037037037037039e-05,
      "loss": 0.5061,
      "step": 65
    },
    {
      "epoch": 0.061224489795918366,
      "grad_norm": 2.1683146953582764,
      "learning_rate": 1.2222222222222224e-05,
      "loss": 0.4346,
      "step": 66
    },
    {
      "epoch": 0.06215213358070501,
      "grad_norm": 1.7861865758895874,
      "learning_rate": 1.2407407407407408e-05,
      "loss": 0.4451,
      "step": 67
    },
    {
      "epoch": 0.06307977736549165,
      "grad_norm": 2.505061626434326,
      "learning_rate": 1.2592592592592593e-05,
      "loss": 0.4545,
      "step": 68
    },
    {
      "epoch": 0.0640074211502783,
      "grad_norm": 2.663344621658325,
      "learning_rate": 1.2777777777777777e-05,
      "loss": 0.4741,
      "step": 69
    },
    {
      "epoch": 0.06493506493506493,
      "grad_norm": 2.4229860305786133,
      "learning_rate": 1.2962962962962964e-05,
      "loss": 0.4564,
      "step": 70
    },
    {
      "epoch": 0.06586270871985157,
      "grad_norm": 1.9748098850250244,
      "learning_rate": 1.314814814814815e-05,
      "loss": 0.4832,
      "step": 71
    },
    {
      "epoch": 0.06679035250463822,
      "grad_norm": 2.0413177013397217,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.4377,
      "step": 72
    },
    {
      "epoch": 0.06771799628942486,
      "grad_norm": 2.965312957763672,
      "learning_rate": 1.351851851851852e-05,
      "loss": 0.3847,
      "step": 73
    },
    {
      "epoch": 0.0686456400742115,
      "grad_norm": 3.3258345127105713,
      "learning_rate": 1.3703703703703706e-05,
      "loss": 0.441,
      "step": 74
    },
    {
      "epoch": 0.06957328385899815,
      "grad_norm": 4.911780834197998,
      "learning_rate": 1.388888888888889e-05,
      "loss": 0.5277,
      "step": 75
    },
    {
      "epoch": 0.07050092764378478,
      "grad_norm": 3.556264638900757,
      "learning_rate": 1.4074074074074075e-05,
      "loss": 0.5102,
      "step": 76
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 2.313514232635498,
      "learning_rate": 1.4259259259259259e-05,
      "loss": 0.3874,
      "step": 77
    },
    {
      "epoch": 0.07235621521335807,
      "grad_norm": 2.3410682678222656,
      "learning_rate": 1.4444444444444446e-05,
      "loss": 0.3794,
      "step": 78
    },
    {
      "epoch": 0.07328385899814471,
      "grad_norm": 1.974550724029541,
      "learning_rate": 1.4629629629629631e-05,
      "loss": 0.3691,
      "step": 79
    },
    {
      "epoch": 0.07421150278293136,
      "grad_norm": 3.7399516105651855,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 0.498,
      "step": 80
    },
    {
      "epoch": 0.07421150278293136,
      "eval_accuracy": 0.7804878048780488,
      "eval_f1": 0.5217391304347826,
      "eval_loss": 0.46577775478363037,
      "eval_precision": 0.6708074534161491,
      "eval_recall": 0.4268774703557312,
      "eval_runtime": 47.3211,
      "eval_samples_per_second": 5.832,
      "eval_steps_per_second": 0.19,
      "step": 80
    },
    {
      "epoch": 0.075139146567718,
      "grad_norm": 4.030659198760986,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.4012,
      "step": 81
    },
    {
      "epoch": 0.07606679035250463,
      "grad_norm": 4.128874778747559,
      "learning_rate": 1.5185185185185187e-05,
      "loss": 0.4411,
      "step": 82
    },
    {
      "epoch": 0.07699443413729128,
      "grad_norm": 5.405181884765625,
      "learning_rate": 1.537037037037037e-05,
      "loss": 0.3886,
      "step": 83
    },
    {
      "epoch": 0.07792207792207792,
      "grad_norm": 2.473198175430298,
      "learning_rate": 1.555555555555556e-05,
      "loss": 0.3348,
      "step": 84
    },
    {
      "epoch": 0.07884972170686456,
      "grad_norm": 3.9382104873657227,
      "learning_rate": 1.5740740740740744e-05,
      "loss": 0.3732,
      "step": 85
    },
    {
      "epoch": 0.07977736549165121,
      "grad_norm": 2.209444761276245,
      "learning_rate": 1.5925925925925926e-05,
      "loss": 0.3247,
      "step": 86
    },
    {
      "epoch": 0.08070500927643785,
      "grad_norm": 4.216385364532471,
      "learning_rate": 1.6111111111111115e-05,
      "loss": 0.4295,
      "step": 87
    },
    {
      "epoch": 0.08163265306122448,
      "grad_norm": 4.730212211608887,
      "learning_rate": 1.6296296296296297e-05,
      "loss": 0.3214,
      "step": 88
    },
    {
      "epoch": 0.08256029684601113,
      "grad_norm": 2.821192741394043,
      "learning_rate": 1.6481481481481482e-05,
      "loss": 0.3864,
      "step": 89
    },
    {
      "epoch": 0.08348794063079777,
      "grad_norm": 2.9178500175476074,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.3257,
      "step": 90
    },
    {
      "epoch": 0.08441558441558442,
      "grad_norm": 4.074183464050293,
      "learning_rate": 1.6851851851851853e-05,
      "loss": 0.3916,
      "step": 91
    },
    {
      "epoch": 0.08534322820037106,
      "grad_norm": 2.721669912338257,
      "learning_rate": 1.7037037037037038e-05,
      "loss": 0.3153,
      "step": 92
    },
    {
      "epoch": 0.0862708719851577,
      "grad_norm": 4.657402992248535,
      "learning_rate": 1.7222222222222224e-05,
      "loss": 0.4462,
      "step": 93
    },
    {
      "epoch": 0.08719851576994433,
      "grad_norm": 2.9709548950195312,
      "learning_rate": 1.740740740740741e-05,
      "loss": 0.3124,
      "step": 94
    },
    {
      "epoch": 0.08812615955473098,
      "grad_norm": 5.8010711669921875,
      "learning_rate": 1.7592592592592595e-05,
      "loss": 0.2713,
      "step": 95
    },
    {
      "epoch": 0.08905380333951762,
      "grad_norm": 3.4263553619384766,
      "learning_rate": 1.7777777777777777e-05,
      "loss": 0.3161,
      "step": 96
    },
    {
      "epoch": 0.08998144712430427,
      "grad_norm": 3.680510997772217,
      "learning_rate": 1.7962962962962965e-05,
      "loss": 0.3464,
      "step": 97
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 5.526573657989502,
      "learning_rate": 1.814814814814815e-05,
      "loss": 0.2899,
      "step": 98
    },
    {
      "epoch": 0.09183673469387756,
      "grad_norm": 3.2282707691192627,
      "learning_rate": 1.8333333333333333e-05,
      "loss": 0.2088,
      "step": 99
    },
    {
      "epoch": 0.09276437847866419,
      "grad_norm": 3.8928277492523193,
      "learning_rate": 1.851851851851852e-05,
      "loss": 0.2531,
      "step": 100
    },
    {
      "epoch": 0.09276437847866419,
      "eval_accuracy": 0.8015521064301552,
      "eval_f1": 0.5665859564164649,
      "eval_loss": 0.4834875166416168,
      "eval_precision": 0.73125,
      "eval_recall": 0.4624505928853755,
      "eval_runtime": 48.1977,
      "eval_samples_per_second": 5.726,
      "eval_steps_per_second": 0.187,
      "step": 100
    },
    {
      "epoch": 0.09369202226345083,
      "grad_norm": 4.2124924659729,
      "learning_rate": 1.8703703703703707e-05,
      "loss": 0.2609,
      "step": 101
    },
    {
      "epoch": 0.09461966604823747,
      "grad_norm": 5.753302097320557,
      "learning_rate": 1.888888888888889e-05,
      "loss": 0.3886,
      "step": 102
    },
    {
      "epoch": 0.09554730983302412,
      "grad_norm": 4.0034050941467285,
      "learning_rate": 1.9074074074074075e-05,
      "loss": 0.2714,
      "step": 103
    },
    {
      "epoch": 0.09647495361781076,
      "grad_norm": 7.041585922241211,
      "learning_rate": 1.925925925925926e-05,
      "loss": 0.3665,
      "step": 104
    },
    {
      "epoch": 0.09740259740259741,
      "grad_norm": 5.10760498046875,
      "learning_rate": 1.9444444444444445e-05,
      "loss": 0.3047,
      "step": 105
    },
    {
      "epoch": 0.09833024118738404,
      "grad_norm": 7.445008754730225,
      "learning_rate": 1.962962962962963e-05,
      "loss": 0.2991,
      "step": 106
    },
    {
      "epoch": 0.09925788497217068,
      "grad_norm": 5.59462833404541,
      "learning_rate": 1.9814814814814816e-05,
      "loss": 0.3124,
      "step": 107
    },
    {
      "epoch": 0.10018552875695733,
      "grad_norm": 4.407949447631836,
      "learning_rate": 2e-05,
      "loss": 0.2371,
      "step": 108
    },
    {
      "epoch": 0.10111317254174397,
      "grad_norm": 7.777821063995361,
      "learning_rate": 1.999994755236596e-05,
      "loss": 0.4208,
      "step": 109
    },
    {
      "epoch": 0.10204081632653061,
      "grad_norm": 9.282930374145508,
      "learning_rate": 1.999979021001399e-05,
      "loss": 0.2394,
      "step": 110
    },
    {
      "epoch": 0.10296846011131726,
      "grad_norm": 3.985445976257324,
      "learning_rate": 1.999952797459453e-05,
      "loss": 0.3059,
      "step": 111
    },
    {
      "epoch": 0.1038961038961039,
      "grad_norm": 8.832866668701172,
      "learning_rate": 1.999916084885832e-05,
      "loss": 0.2748,
      "step": 112
    },
    {
      "epoch": 0.10482374768089053,
      "grad_norm": 3.676673173904419,
      "learning_rate": 1.9998688836656322e-05,
      "loss": 0.2271,
      "step": 113
    },
    {
      "epoch": 0.10575139146567718,
      "grad_norm": 4.632993698120117,
      "learning_rate": 1.9998111942939727e-05,
      "loss": 0.292,
      "step": 114
    },
    {
      "epoch": 0.10667903525046382,
      "grad_norm": 4.095834732055664,
      "learning_rate": 1.9997430173759876e-05,
      "loss": 0.2222,
      "step": 115
    },
    {
      "epoch": 0.10760667903525047,
      "grad_norm": 5.404327392578125,
      "learning_rate": 1.9996643536268202e-05,
      "loss": 0.3083,
      "step": 116
    },
    {
      "epoch": 0.10853432282003711,
      "grad_norm": 5.261657238006592,
      "learning_rate": 1.9995752038716166e-05,
      "loss": 0.2628,
      "step": 117
    },
    {
      "epoch": 0.10946196660482375,
      "grad_norm": 5.081439018249512,
      "learning_rate": 1.9994755690455154e-05,
      "loss": 0.3403,
      "step": 118
    },
    {
      "epoch": 0.11038961038961038,
      "grad_norm": 8.73869800567627,
      "learning_rate": 1.999365450193638e-05,
      "loss": 0.2949,
      "step": 119
    },
    {
      "epoch": 0.11131725417439703,
      "grad_norm": 6.3659586906433105,
      "learning_rate": 1.99924484847108e-05,
      "loss": 0.2925,
      "step": 120
    },
    {
      "epoch": 0.11131725417439703,
      "eval_accuracy": 0.8015521064301552,
      "eval_f1": 0.5095890410958904,
      "eval_loss": 0.500335693359375,
      "eval_precision": 0.8303571428571429,
      "eval_recall": 0.3675889328063241,
      "eval_runtime": 48.0846,
      "eval_samples_per_second": 5.74,
      "eval_steps_per_second": 0.187,
      "step": 120
    },
    {
      "epoch": 0.11224489795918367,
      "grad_norm": 4.58190393447876,
      "learning_rate": 1.9991137651428957e-05,
      "loss": 0.2265,
      "step": 121
    },
    {
      "epoch": 0.11317254174397032,
      "grad_norm": 5.173889636993408,
      "learning_rate": 1.998972201584088e-05,
      "loss": 0.2239,
      "step": 122
    },
    {
      "epoch": 0.11410018552875696,
      "grad_norm": 4.783614158630371,
      "learning_rate": 1.998820159279591e-05,
      "loss": 0.2998,
      "step": 123
    },
    {
      "epoch": 0.1150278293135436,
      "grad_norm": 3.5412709712982178,
      "learning_rate": 1.9986576398242566e-05,
      "loss": 0.2021,
      "step": 124
    },
    {
      "epoch": 0.11595547309833024,
      "grad_norm": 3.692047119140625,
      "learning_rate": 1.998484644922837e-05,
      "loss": 0.2432,
      "step": 125
    },
    {
      "epoch": 0.11688311688311688,
      "grad_norm": 2.976855993270874,
      "learning_rate": 1.9983011763899674e-05,
      "loss": 0.2703,
      "step": 126
    },
    {
      "epoch": 0.11781076066790352,
      "grad_norm": 5.132311820983887,
      "learning_rate": 1.998107236150145e-05,
      "loss": 0.3625,
      "step": 127
    },
    {
      "epoch": 0.11873840445269017,
      "grad_norm": 5.332205772399902,
      "learning_rate": 1.997902826237712e-05,
      "loss": 0.3431,
      "step": 128
    },
    {
      "epoch": 0.11966604823747681,
      "grad_norm": 7.54325532913208,
      "learning_rate": 1.997687948796831e-05,
      "loss": 0.2762,
      "step": 129
    },
    {
      "epoch": 0.12059369202226346,
      "grad_norm": 4.39344596862793,
      "learning_rate": 1.997462606081465e-05,
      "loss": 0.2178,
      "step": 130
    },
    {
      "epoch": 0.12152133580705009,
      "grad_norm": 4.67897891998291,
      "learning_rate": 1.997226800455352e-05,
      "loss": 0.2575,
      "step": 131
    },
    {
      "epoch": 0.12244897959183673,
      "grad_norm": 2.7064077854156494,
      "learning_rate": 1.9969805343919822e-05,
      "loss": 0.1973,
      "step": 132
    },
    {
      "epoch": 0.12337662337662338,
      "grad_norm": 2.841456413269043,
      "learning_rate": 1.9967238104745695e-05,
      "loss": 0.186,
      "step": 133
    },
    {
      "epoch": 0.12430426716141002,
      "grad_norm": 5.078066349029541,
      "learning_rate": 1.9964566313960265e-05,
      "loss": 0.2899,
      "step": 134
    },
    {
      "epoch": 0.12523191094619665,
      "grad_norm": 3.5166287422180176,
      "learning_rate": 1.9961789999589357e-05,
      "loss": 0.2397,
      "step": 135
    },
    {
      "epoch": 0.1261595547309833,
      "grad_norm": 3.0311009883880615,
      "learning_rate": 1.995890919075519e-05,
      "loss": 0.2042,
      "step": 136
    },
    {
      "epoch": 0.12708719851576994,
      "grad_norm": 4.455051898956299,
      "learning_rate": 1.995592391767608e-05,
      "loss": 0.1938,
      "step": 137
    },
    {
      "epoch": 0.1280148423005566,
      "grad_norm": 3.05238676071167,
      "learning_rate": 1.995283421166614e-05,
      "loss": 0.2134,
      "step": 138
    },
    {
      "epoch": 0.12894248608534323,
      "grad_norm": 2.5545527935028076,
      "learning_rate": 1.994964010513492e-05,
      "loss": 0.1558,
      "step": 139
    },
    {
      "epoch": 0.12987012987012986,
      "grad_norm": 3.169755458831787,
      "learning_rate": 1.9946341631587086e-05,
      "loss": 0.1912,
      "step": 140
    },
    {
      "epoch": 0.12987012987012986,
      "eval_accuracy": 0.8004434589800443,
      "eval_f1": 0.5,
      "eval_loss": 0.45746758580207825,
      "eval_precision": 0.8411214953271028,
      "eval_recall": 0.3557312252964427,
      "eval_runtime": 48.503,
      "eval_samples_per_second": 5.69,
      "eval_steps_per_second": 0.186,
      "step": 140
    },
    {
      "epoch": 0.13079777365491652,
      "grad_norm": 5.176037788391113,
      "learning_rate": 1.9942938825622064e-05,
      "loss": 0.261,
      "step": 141
    },
    {
      "epoch": 0.13172541743970315,
      "grad_norm": 4.5571513175964355,
      "learning_rate": 1.9939431722933678e-05,
      "loss": 0.1861,
      "step": 142
    },
    {
      "epoch": 0.1326530612244898,
      "grad_norm": 4.165744304656982,
      "learning_rate": 1.993582036030978e-05,
      "loss": 0.252,
      "step": 143
    },
    {
      "epoch": 0.13358070500927643,
      "grad_norm": 3.6084752082824707,
      "learning_rate": 1.9932104775631847e-05,
      "loss": 0.2091,
      "step": 144
    },
    {
      "epoch": 0.1345083487940631,
      "grad_norm": 5.7025837898254395,
      "learning_rate": 1.992828500787461e-05,
      "loss": 0.2875,
      "step": 145
    },
    {
      "epoch": 0.13543599257884972,
      "grad_norm": 3.954706907272339,
      "learning_rate": 1.9924361097105624e-05,
      "loss": 0.147,
      "step": 146
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 3.246682643890381,
      "learning_rate": 1.992033308448486e-05,
      "loss": 0.1406,
      "step": 147
    },
    {
      "epoch": 0.137291280148423,
      "grad_norm": 7.386576175689697,
      "learning_rate": 1.9916201012264255e-05,
      "loss": 0.2637,
      "step": 148
    },
    {
      "epoch": 0.13821892393320964,
      "grad_norm": 11.797701835632324,
      "learning_rate": 1.9911964923787295e-05,
      "loss": 0.2989,
      "step": 149
    },
    {
      "epoch": 0.1391465677179963,
      "grad_norm": 4.424801349639893,
      "learning_rate": 1.990762486348855e-05,
      "loss": 0.2059,
      "step": 150
    },
    {
      "epoch": 0.14007421150278293,
      "grad_norm": 6.5464582443237305,
      "learning_rate": 1.9903180876893195e-05,
      "loss": 0.3335,
      "step": 151
    },
    {
      "epoch": 0.14100185528756956,
      "grad_norm": 6.232185363769531,
      "learning_rate": 1.989863301061654e-05,
      "loss": 0.1652,
      "step": 152
    },
    {
      "epoch": 0.14192949907235622,
      "grad_norm": 7.7785162925720215,
      "learning_rate": 1.9893981312363563e-05,
      "loss": 0.3246,
      "step": 153
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 4.034485340118408,
      "learning_rate": 1.9889225830928365e-05,
      "loss": 0.1639,
      "step": 154
    },
    {
      "epoch": 0.1437847866419295,
      "grad_norm": 4.565614223480225,
      "learning_rate": 1.9884366616193707e-05,
      "loss": 0.2567,
      "step": 155
    },
    {
      "epoch": 0.14471243042671614,
      "grad_norm": 4.671913146972656,
      "learning_rate": 1.987940371913044e-05,
      "loss": 0.2956,
      "step": 156
    },
    {
      "epoch": 0.1456400742115028,
      "grad_norm": 4.866475582122803,
      "learning_rate": 1.987433719179702e-05,
      "loss": 0.1732,
      "step": 157
    },
    {
      "epoch": 0.14656771799628943,
      "grad_norm": 7.748964786529541,
      "learning_rate": 1.9869167087338908e-05,
      "loss": 0.3068,
      "step": 158
    },
    {
      "epoch": 0.14749536178107606,
      "grad_norm": 3.243945837020874,
      "learning_rate": 1.986389345998806e-05,
      "loss": 0.2172,
      "step": 159
    },
    {
      "epoch": 0.14842300556586271,
      "grad_norm": 2.541400671005249,
      "learning_rate": 1.9858516365062334e-05,
      "loss": 0.1991,
      "step": 160
    },
    {
      "epoch": 0.14842300556586271,
      "eval_accuracy": 0.811529933481153,
      "eval_f1": 0.5478723404255319,
      "eval_loss": 0.4108695983886719,
      "eval_precision": 0.8373983739837398,
      "eval_recall": 0.40711462450592883,
      "eval_runtime": 49.0091,
      "eval_samples_per_second": 5.632,
      "eval_steps_per_second": 0.184,
      "step": 160
    },
    {
      "epoch": 0.14935064935064934,
      "grad_norm": 3.5915067195892334,
      "learning_rate": 1.9853035858964907e-05,
      "loss": 0.2252,
      "step": 161
    },
    {
      "epoch": 0.150278293135436,
      "grad_norm": 3.297874927520752,
      "learning_rate": 1.9847451999183692e-05,
      "loss": 0.2025,
      "step": 162
    },
    {
      "epoch": 0.15120593692022263,
      "grad_norm": 7.80188512802124,
      "learning_rate": 1.9841764844290744e-05,
      "loss": 0.3563,
      "step": 163
    },
    {
      "epoch": 0.15213358070500926,
      "grad_norm": 4.962357044219971,
      "learning_rate": 1.9835974453941623e-05,
      "loss": 0.2331,
      "step": 164
    },
    {
      "epoch": 0.15306122448979592,
      "grad_norm": 4.794024467468262,
      "learning_rate": 1.983008088887478e-05,
      "loss": 0.2759,
      "step": 165
    },
    {
      "epoch": 0.15398886827458255,
      "grad_norm": 5.007259368896484,
      "learning_rate": 1.9824084210910924e-05,
      "loss": 0.1732,
      "step": 166
    },
    {
      "epoch": 0.1549165120593692,
      "grad_norm": 4.154080390930176,
      "learning_rate": 1.9817984482952378e-05,
      "loss": 0.199,
      "step": 167
    },
    {
      "epoch": 0.15584415584415584,
      "grad_norm": 5.933828830718994,
      "learning_rate": 1.9811781768982392e-05,
      "loss": 0.3237,
      "step": 168
    },
    {
      "epoch": 0.1567717996289425,
      "grad_norm": 4.5709943771362305,
      "learning_rate": 1.980547613406451e-05,
      "loss": 0.2356,
      "step": 169
    },
    {
      "epoch": 0.15769944341372913,
      "grad_norm": 4.232250690460205,
      "learning_rate": 1.9799067644341844e-05,
      "loss": 0.2318,
      "step": 170
    },
    {
      "epoch": 0.15862708719851576,
      "grad_norm": 5.491664886474609,
      "learning_rate": 1.9792556367036432e-05,
      "loss": 0.2551,
      "step": 171
    },
    {
      "epoch": 0.15955473098330242,
      "grad_norm": 3.584186315536499,
      "learning_rate": 1.978594237044849e-05,
      "loss": 0.1733,
      "step": 172
    },
    {
      "epoch": 0.16048237476808905,
      "grad_norm": 2.8872857093811035,
      "learning_rate": 1.977922572395571e-05,
      "loss": 0.2076,
      "step": 173
    },
    {
      "epoch": 0.1614100185528757,
      "grad_norm": 4.199950695037842,
      "learning_rate": 1.977240649801253e-05,
      "loss": 0.2076,
      "step": 174
    },
    {
      "epoch": 0.16233766233766234,
      "grad_norm": 3.1421799659729004,
      "learning_rate": 1.9765484764149413e-05,
      "loss": 0.2281,
      "step": 175
    },
    {
      "epoch": 0.16326530612244897,
      "grad_norm": 4.832352638244629,
      "learning_rate": 1.9758460594972068e-05,
      "loss": 0.1834,
      "step": 176
    },
    {
      "epoch": 0.16419294990723562,
      "grad_norm": 2.8222384452819824,
      "learning_rate": 1.9751334064160708e-05,
      "loss": 0.1908,
      "step": 177
    },
    {
      "epoch": 0.16512059369202226,
      "grad_norm": 3.1630570888519287,
      "learning_rate": 1.9744105246469264e-05,
      "loss": 0.1962,
      "step": 178
    },
    {
      "epoch": 0.1660482374768089,
      "grad_norm": 3.811518669128418,
      "learning_rate": 1.9736774217724614e-05,
      "loss": 0.1786,
      "step": 179
    },
    {
      "epoch": 0.16697588126159554,
      "grad_norm": 4.223273754119873,
      "learning_rate": 1.9729341054825783e-05,
      "loss": 0.2153,
      "step": 180
    },
    {
      "epoch": 0.16697588126159554,
      "eval_accuracy": 0.8337028824833703,
      "eval_f1": 0.6268656716417911,
      "eval_loss": 0.37183114886283875,
      "eval_precision": 0.8456375838926175,
      "eval_recall": 0.4980237154150198,
      "eval_runtime": 48.5694,
      "eval_samples_per_second": 5.683,
      "eval_steps_per_second": 0.185,
      "step": 180
    },
    {
      "epoch": 0.1679035250463822,
      "grad_norm": 3.9425668716430664,
      "learning_rate": 1.972180583574313e-05,
      "loss": 0.1998,
      "step": 181
    },
    {
      "epoch": 0.16883116883116883,
      "grad_norm": 5.5068840980529785,
      "learning_rate": 1.9714168639517543e-05,
      "loss": 0.2466,
      "step": 182
    },
    {
      "epoch": 0.16975881261595546,
      "grad_norm": 6.162604808807373,
      "learning_rate": 1.9706429546259592e-05,
      "loss": 0.163,
      "step": 183
    },
    {
      "epoch": 0.17068645640074212,
      "grad_norm": 5.026734828948975,
      "learning_rate": 1.9698588637148705e-05,
      "loss": 0.275,
      "step": 184
    },
    {
      "epoch": 0.17161410018552875,
      "grad_norm": 6.298387050628662,
      "learning_rate": 1.9690645994432307e-05,
      "loss": 0.1692,
      "step": 185
    },
    {
      "epoch": 0.1725417439703154,
      "grad_norm": 5.307831287384033,
      "learning_rate": 1.9682601701424958e-05,
      "loss": 0.2499,
      "step": 186
    },
    {
      "epoch": 0.17346938775510204,
      "grad_norm": 6.9988203048706055,
      "learning_rate": 1.9674455842507494e-05,
      "loss": 0.2434,
      "step": 187
    },
    {
      "epoch": 0.17439703153988867,
      "grad_norm": 4.128062725067139,
      "learning_rate": 1.9666208503126115e-05,
      "loss": 0.1976,
      "step": 188
    },
    {
      "epoch": 0.17532467532467533,
      "grad_norm": 3.3845396041870117,
      "learning_rate": 1.9657859769791506e-05,
      "loss": 0.1355,
      "step": 189
    },
    {
      "epoch": 0.17625231910946196,
      "grad_norm": 3.59576416015625,
      "learning_rate": 1.9649409730077934e-05,
      "loss": 0.2027,
      "step": 190
    },
    {
      "epoch": 0.17717996289424862,
      "grad_norm": 3.110616683959961,
      "learning_rate": 1.9640858472622316e-05,
      "loss": 0.2039,
      "step": 191
    },
    {
      "epoch": 0.17810760667903525,
      "grad_norm": 3.8708298206329346,
      "learning_rate": 1.9632206087123296e-05,
      "loss": 0.2163,
      "step": 192
    },
    {
      "epoch": 0.1790352504638219,
      "grad_norm": 5.087402820587158,
      "learning_rate": 1.9623452664340305e-05,
      "loss": 0.2631,
      "step": 193
    },
    {
      "epoch": 0.17996289424860853,
      "grad_norm": 3.7053322792053223,
      "learning_rate": 1.9614598296092603e-05,
      "loss": 0.2034,
      "step": 194
    },
    {
      "epoch": 0.18089053803339517,
      "grad_norm": 4.846376419067383,
      "learning_rate": 1.9605643075258323e-05,
      "loss": 0.2071,
      "step": 195
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 3.7219040393829346,
      "learning_rate": 1.9596587095773496e-05,
      "loss": 0.2516,
      "step": 196
    },
    {
      "epoch": 0.18274582560296845,
      "grad_norm": 5.604904651641846,
      "learning_rate": 1.958743045263106e-05,
      "loss": 0.2076,
      "step": 197
    },
    {
      "epoch": 0.1836734693877551,
      "grad_norm": 2.9652745723724365,
      "learning_rate": 1.957817324187987e-05,
      "loss": 0.1752,
      "step": 198
    },
    {
      "epoch": 0.18460111317254174,
      "grad_norm": 4.468489646911621,
      "learning_rate": 1.956881556062369e-05,
      "loss": 0.2177,
      "step": 199
    },
    {
      "epoch": 0.18552875695732837,
      "grad_norm": 4.231448173522949,
      "learning_rate": 1.9559357507020163e-05,
      "loss": 0.1638,
      "step": 200
    },
    {
      "epoch": 0.18552875695732837,
      "eval_accuracy": 0.8237250554323725,
      "eval_f1": 0.5826771653543307,
      "eval_loss": 0.36573752760887146,
      "eval_precision": 0.8671875,
      "eval_recall": 0.43873517786561267,
      "eval_runtime": 49.5575,
      "eval_samples_per_second": 5.569,
      "eval_steps_per_second": 0.182,
      "step": 200
    },
    {
      "epoch": 0.18645640074211503,
      "grad_norm": 3.4353301525115967,
      "learning_rate": 1.9549799180279793e-05,
      "loss": 0.2293,
      "step": 201
    },
    {
      "epoch": 0.18738404452690166,
      "grad_norm": 3.4561715126037598,
      "learning_rate": 1.9540140680664915e-05,
      "loss": 0.1131,
      "step": 202
    },
    {
      "epoch": 0.18831168831168832,
      "grad_norm": 4.9482293128967285,
      "learning_rate": 1.953038210948861e-05,
      "loss": 0.2009,
      "step": 203
    },
    {
      "epoch": 0.18923933209647495,
      "grad_norm": 4.263972759246826,
      "learning_rate": 1.952052356911368e-05,
      "loss": 0.2624,
      "step": 204
    },
    {
      "epoch": 0.1901669758812616,
      "grad_norm": 4.766571044921875,
      "learning_rate": 1.9510565162951538e-05,
      "loss": 0.1823,
      "step": 205
    },
    {
      "epoch": 0.19109461966604824,
      "grad_norm": 5.494351387023926,
      "learning_rate": 1.950050699546116e-05,
      "loss": 0.2365,
      "step": 206
    },
    {
      "epoch": 0.19202226345083487,
      "grad_norm": 5.0484795570373535,
      "learning_rate": 1.9490349172147964e-05,
      "loss": 0.2197,
      "step": 207
    },
    {
      "epoch": 0.19294990723562153,
      "grad_norm": 4.198167324066162,
      "learning_rate": 1.9480091799562706e-05,
      "loss": 0.1825,
      "step": 208
    },
    {
      "epoch": 0.19387755102040816,
      "grad_norm": 4.7388105392456055,
      "learning_rate": 1.9469734985300373e-05,
      "loss": 0.2195,
      "step": 209
    },
    {
      "epoch": 0.19480519480519481,
      "grad_norm": 4.556212902069092,
      "learning_rate": 1.9459278837999048e-05,
      "loss": 0.2085,
      "step": 210
    },
    {
      "epoch": 0.19573283858998144,
      "grad_norm": 5.153113842010498,
      "learning_rate": 1.9448723467338765e-05,
      "loss": 0.2332,
      "step": 211
    },
    {
      "epoch": 0.19666048237476808,
      "grad_norm": 2.6720712184906006,
      "learning_rate": 1.9438068984040366e-05,
      "loss": 0.1761,
      "step": 212
    },
    {
      "epoch": 0.19758812615955473,
      "grad_norm": 2.9613466262817383,
      "learning_rate": 1.9427315499864345e-05,
      "loss": 0.1877,
      "step": 213
    },
    {
      "epoch": 0.19851576994434136,
      "grad_norm": 3.5731585025787354,
      "learning_rate": 1.9416463127609655e-05,
      "loss": 0.2018,
      "step": 214
    },
    {
      "epoch": 0.19944341372912802,
      "grad_norm": 4.205770015716553,
      "learning_rate": 1.9405511981112553e-05,
      "loss": 0.1952,
      "step": 215
    },
    {
      "epoch": 0.20037105751391465,
      "grad_norm": 4.905291557312012,
      "learning_rate": 1.9394462175245382e-05,
      "loss": 0.2482,
      "step": 216
    },
    {
      "epoch": 0.2012987012987013,
      "grad_norm": 6.575018405914307,
      "learning_rate": 1.9383313825915372e-05,
      "loss": 0.2007,
      "step": 217
    },
    {
      "epoch": 0.20222634508348794,
      "grad_norm": 4.795684814453125,
      "learning_rate": 1.937206705006344e-05,
      "loss": 0.1878,
      "step": 218
    },
    {
      "epoch": 0.20315398886827457,
      "grad_norm": 3.1328468322753906,
      "learning_rate": 1.9360721965662934e-05,
      "loss": 0.1864,
      "step": 219
    },
    {
      "epoch": 0.20408163265306123,
      "grad_norm": 3.297593355178833,
      "learning_rate": 1.9349278691718426e-05,
      "loss": 0.2033,
      "step": 220
    },
    {
      "epoch": 0.20408163265306123,
      "eval_accuracy": 0.8370288248337029,
      "eval_f1": 0.6423357664233577,
      "eval_loss": 0.34552833437919617,
      "eval_precision": 0.8354430379746836,
      "eval_recall": 0.5217391304347826,
      "eval_runtime": 48.9715,
      "eval_samples_per_second": 5.636,
      "eval_steps_per_second": 0.184,
      "step": 220
    },
    {
      "epoch": 0.20500927643784786,
      "grad_norm": 3.253046989440918,
      "learning_rate": 1.9337737348264448e-05,
      "loss": 0.2099,
      "step": 221
    },
    {
      "epoch": 0.20593692022263452,
      "grad_norm": 4.903271675109863,
      "learning_rate": 1.9326098056364224e-05,
      "loss": 0.2595,
      "step": 222
    },
    {
      "epoch": 0.20686456400742115,
      "grad_norm": 6.408766746520996,
      "learning_rate": 1.9314360938108427e-05,
      "loss": 0.2615,
      "step": 223
    },
    {
      "epoch": 0.2077922077922078,
      "grad_norm": 4.407992839813232,
      "learning_rate": 1.9302526116613863e-05,
      "loss": 0.1009,
      "step": 224
    },
    {
      "epoch": 0.20871985157699444,
      "grad_norm": 2.9286835193634033,
      "learning_rate": 1.9290593716022218e-05,
      "loss": 0.1412,
      "step": 225
    },
    {
      "epoch": 0.20964749536178107,
      "grad_norm": 3.6685068607330322,
      "learning_rate": 1.9278563861498726e-05,
      "loss": 0.221,
      "step": 226
    },
    {
      "epoch": 0.21057513914656772,
      "grad_norm": 4.300150394439697,
      "learning_rate": 1.9266436679230866e-05,
      "loss": 0.1645,
      "step": 227
    },
    {
      "epoch": 0.21150278293135436,
      "grad_norm": 4.307882308959961,
      "learning_rate": 1.9254212296427043e-05,
      "loss": 0.2284,
      "step": 228
    },
    {
      "epoch": 0.212430426716141,
      "grad_norm": 2.4391989707946777,
      "learning_rate": 1.924189084131525e-05,
      "loss": 0.118,
      "step": 229
    },
    {
      "epoch": 0.21335807050092764,
      "grad_norm": 5.997758388519287,
      "learning_rate": 1.922947244314172e-05,
      "loss": 0.2798,
      "step": 230
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 4.957704544067383,
      "learning_rate": 1.9216957232169567e-05,
      "loss": 0.1852,
      "step": 231
    },
    {
      "epoch": 0.21521335807050093,
      "grad_norm": 5.667599678039551,
      "learning_rate": 1.9204345339677442e-05,
      "loss": 0.2155,
      "step": 232
    },
    {
      "epoch": 0.21614100185528756,
      "grad_norm": 4.291685104370117,
      "learning_rate": 1.9191636897958123e-05,
      "loss": 0.2637,
      "step": 233
    },
    {
      "epoch": 0.21706864564007422,
      "grad_norm": 4.587561130523682,
      "learning_rate": 1.9178832040317153e-05,
      "loss": 0.2383,
      "step": 234
    },
    {
      "epoch": 0.21799628942486085,
      "grad_norm": 3.8426513671875,
      "learning_rate": 1.916593090107143e-05,
      "loss": 0.212,
      "step": 235
    },
    {
      "epoch": 0.2189239332096475,
      "grad_norm": 5.173671722412109,
      "learning_rate": 1.91529336155478e-05,
      "loss": 0.2054,
      "step": 236
    },
    {
      "epoch": 0.21985157699443414,
      "grad_norm": 4.827680587768555,
      "learning_rate": 1.913984032008163e-05,
      "loss": 0.2072,
      "step": 237
    },
    {
      "epoch": 0.22077922077922077,
      "grad_norm": 7.693399906158447,
      "learning_rate": 1.9126651152015404e-05,
      "loss": 0.2071,
      "step": 238
    },
    {
      "epoch": 0.22170686456400743,
      "grad_norm": 3.128953695297241,
      "learning_rate": 1.911336624969725e-05,
      "loss": 0.2271,
      "step": 239
    },
    {
      "epoch": 0.22263450834879406,
      "grad_norm": 6.966447353363037,
      "learning_rate": 1.9099985752479505e-05,
      "loss": 0.2448,
      "step": 240
    },
    {
      "epoch": 0.22263450834879406,
      "eval_accuracy": 0.8381374722838137,
      "eval_f1": 0.6403940886699507,
      "eval_loss": 0.34381967782974243,
      "eval_precision": 0.8496732026143791,
      "eval_recall": 0.5138339920948617,
      "eval_runtime": 48.6504,
      "eval_samples_per_second": 5.673,
      "eval_steps_per_second": 0.185,
      "step": 240
    },
    {
      "epoch": 0.22356215213358072,
      "grad_norm": 4.817497730255127,
      "learning_rate": 1.908650980071726e-05,
      "loss": 0.1878,
      "step": 241
    },
    {
      "epoch": 0.22448979591836735,
      "grad_norm": 3.612339973449707,
      "learning_rate": 1.9072938535766864e-05,
      "loss": 0.1226,
      "step": 242
    },
    {
      "epoch": 0.22541743970315398,
      "grad_norm": 4.005315780639648,
      "learning_rate": 1.905927209998447e-05,
      "loss": 0.2076,
      "step": 243
    },
    {
      "epoch": 0.22634508348794063,
      "grad_norm": 3.032423496246338,
      "learning_rate": 1.904551063672452e-05,
      "loss": 0.1511,
      "step": 244
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 3.060365676879883,
      "learning_rate": 1.9031654290338256e-05,
      "loss": 0.1954,
      "step": 245
    },
    {
      "epoch": 0.22820037105751392,
      "grad_norm": 5.271503448486328,
      "learning_rate": 1.9017703206172187e-05,
      "loss": 0.2244,
      "step": 246
    },
    {
      "epoch": 0.22912801484230055,
      "grad_norm": 2.923628568649292,
      "learning_rate": 1.900365753056659e-05,
      "loss": 0.1753,
      "step": 247
    },
    {
      "epoch": 0.2300556586270872,
      "grad_norm": 3.745664119720459,
      "learning_rate": 1.8989517410853956e-05,
      "loss": 0.188,
      "step": 248
    },
    {
      "epoch": 0.23098330241187384,
      "grad_norm": 3.7633256912231445,
      "learning_rate": 1.8975282995357448e-05,
      "loss": 0.201,
      "step": 249
    },
    {
      "epoch": 0.23191094619666047,
      "grad_norm": 3.29656720161438,
      "learning_rate": 1.896095443338935e-05,
      "loss": 0.1956,
      "step": 250
    },
    {
      "epoch": 0.23283858998144713,
      "grad_norm": 4.702951431274414,
      "learning_rate": 1.8946531875249496e-05,
      "loss": 0.2101,
      "step": 251
    },
    {
      "epoch": 0.23376623376623376,
      "grad_norm": 7.016535758972168,
      "learning_rate": 1.8932015472223692e-05,
      "loss": 0.2486,
      "step": 252
    },
    {
      "epoch": 0.23469387755102042,
      "grad_norm": 4.004672050476074,
      "learning_rate": 1.8917405376582144e-05,
      "loss": 0.239,
      "step": 253
    },
    {
      "epoch": 0.23562152133580705,
      "grad_norm": 4.382692337036133,
      "learning_rate": 1.8902701741577844e-05,
      "loss": 0.2308,
      "step": 254
    },
    {
      "epoch": 0.23654916512059368,
      "grad_norm": 4.72487735748291,
      "learning_rate": 1.8887904721444955e-05,
      "loss": 0.2098,
      "step": 255
    },
    {
      "epoch": 0.23747680890538034,
      "grad_norm": 3.4035651683807373,
      "learning_rate": 1.8873014471397225e-05,
      "loss": 0.101,
      "step": 256
    },
    {
      "epoch": 0.23840445269016697,
      "grad_norm": 7.383582592010498,
      "learning_rate": 1.8858031147626326e-05,
      "loss": 0.2499,
      "step": 257
    },
    {
      "epoch": 0.23933209647495363,
      "grad_norm": 4.3388895988464355,
      "learning_rate": 1.8842954907300236e-05,
      "loss": 0.1859,
      "step": 258
    },
    {
      "epoch": 0.24025974025974026,
      "grad_norm": 3.2572548389434814,
      "learning_rate": 1.8827785908561585e-05,
      "loss": 0.1833,
      "step": 259
    },
    {
      "epoch": 0.24118738404452691,
      "grad_norm": 7.2369561195373535,
      "learning_rate": 1.881252431052599e-05,
      "loss": 0.2337,
      "step": 260
    },
    {
      "epoch": 0.24118738404452691,
      "eval_accuracy": 0.8281596452328159,
      "eval_f1": 0.5931758530183727,
      "eval_loss": 0.3704891502857208,
      "eval_precision": 0.8828125,
      "eval_recall": 0.44664031620553357,
      "eval_runtime": 47.7821,
      "eval_samples_per_second": 5.776,
      "eval_steps_per_second": 0.188,
      "step": 260
    },
    {
      "epoch": 0.24211502782931354,
      "grad_norm": 6.052790641784668,
      "learning_rate": 1.879717027328039e-05,
      "loss": 0.2569,
      "step": 261
    },
    {
      "epoch": 0.24304267161410018,
      "grad_norm": 3.246156692504883,
      "learning_rate": 1.8781723957881374e-05,
      "loss": 0.1871,
      "step": 262
    },
    {
      "epoch": 0.24397031539888683,
      "grad_norm": 6.536667823791504,
      "learning_rate": 1.876618552635348e-05,
      "loss": 0.1425,
      "step": 263
    },
    {
      "epoch": 0.24489795918367346,
      "grad_norm": 5.4920830726623535,
      "learning_rate": 1.87505551416875e-05,
      "loss": 0.2275,
      "step": 264
    },
    {
      "epoch": 0.24582560296846012,
      "grad_norm": 7.879229545593262,
      "learning_rate": 1.8734832967838775e-05,
      "loss": 0.2852,
      "step": 265
    },
    {
      "epoch": 0.24675324675324675,
      "grad_norm": 3.7755329608917236,
      "learning_rate": 1.871901916972547e-05,
      "loss": 0.1967,
      "step": 266
    },
    {
      "epoch": 0.24768089053803338,
      "grad_norm": 4.236266136169434,
      "learning_rate": 1.8703113913226847e-05,
      "loss": 0.1302,
      "step": 267
    },
    {
      "epoch": 0.24860853432282004,
      "grad_norm": 5.8521599769592285,
      "learning_rate": 1.8687117365181514e-05,
      "loss": 0.2866,
      "step": 268
    },
    {
      "epoch": 0.24953617810760667,
      "grad_norm": 2.9448065757751465,
      "learning_rate": 1.867102969338569e-05,
      "loss": 0.171,
      "step": 269
    },
    {
      "epoch": 0.2504638218923933,
      "grad_norm": 4.411244869232178,
      "learning_rate": 1.865485106659145e-05,
      "loss": 0.1424,
      "step": 270
    },
    {
      "epoch": 0.25139146567717996,
      "grad_norm": 5.2516655921936035,
      "learning_rate": 1.863858165450492e-05,
      "loss": 0.2166,
      "step": 271
    },
    {
      "epoch": 0.2523191094619666,
      "grad_norm": 2.6857924461364746,
      "learning_rate": 1.862222162778454e-05,
      "loss": 0.1786,
      "step": 272
    },
    {
      "epoch": 0.2532467532467532,
      "grad_norm": 6.46083927154541,
      "learning_rate": 1.8605771158039253e-05,
      "loss": 0.1817,
      "step": 273
    },
    {
      "epoch": 0.2541743970315399,
      "grad_norm": 6.851802349090576,
      "learning_rate": 1.85892304178267e-05,
      "loss": 0.174,
      "step": 274
    },
    {
      "epoch": 0.25510204081632654,
      "grad_norm": 4.372910022735596,
      "learning_rate": 1.8572599580651415e-05,
      "loss": 0.211,
      "step": 275
    },
    {
      "epoch": 0.2560296846011132,
      "grad_norm": 8.214804649353027,
      "learning_rate": 1.8555878820963014e-05,
      "loss": 0.2295,
      "step": 276
    },
    {
      "epoch": 0.2569573283858998,
      "grad_norm": 3.299901247024536,
      "learning_rate": 1.8539068314154355e-05,
      "loss": 0.1784,
      "step": 277
    },
    {
      "epoch": 0.25788497217068646,
      "grad_norm": 3.1576666831970215,
      "learning_rate": 1.8522168236559693e-05,
      "loss": 0.1864,
      "step": 278
    },
    {
      "epoch": 0.2588126159554731,
      "grad_norm": 6.918071269989014,
      "learning_rate": 1.8505178765452853e-05,
      "loss": 0.2015,
      "step": 279
    },
    {
      "epoch": 0.2597402597402597,
      "grad_norm": 2.884896755218506,
      "learning_rate": 1.8488100079045345e-05,
      "loss": 0.1698,
      "step": 280
    },
    {
      "epoch": 0.2597402597402597,
      "eval_accuracy": 0.8215077605321508,
      "eval_f1": 0.5729442970822282,
      "eval_loss": 0.37236273288726807,
      "eval_precision": 0.8709677419354839,
      "eval_recall": 0.4268774703557312,
      "eval_runtime": 48.19,
      "eval_samples_per_second": 5.727,
      "eval_steps_per_second": 0.187,
      "step": 280
    },
    {
      "epoch": 0.2606679035250464,
      "grad_norm": 2.52854061126709,
      "learning_rate": 1.847093235648451e-05,
      "loss": 0.1427,
      "step": 281
    },
    {
      "epoch": 0.26159554730983303,
      "grad_norm": 3.8434646129608154,
      "learning_rate": 1.8453675777851627e-05,
      "loss": 0.2429,
      "step": 282
    },
    {
      "epoch": 0.2625231910946197,
      "grad_norm": 3.32183837890625,
      "learning_rate": 1.8436330524160048e-05,
      "loss": 0.1672,
      "step": 283
    },
    {
      "epoch": 0.2634508348794063,
      "grad_norm": 3.077954053878784,
      "learning_rate": 1.8418896777353272e-05,
      "loss": 0.1511,
      "step": 284
    },
    {
      "epoch": 0.26437847866419295,
      "grad_norm": 6.1399617195129395,
      "learning_rate": 1.8401374720303054e-05,
      "loss": 0.1989,
      "step": 285
    },
    {
      "epoch": 0.2653061224489796,
      "grad_norm": 4.476570129394531,
      "learning_rate": 1.8383764536807486e-05,
      "loss": 0.2204,
      "step": 286
    },
    {
      "epoch": 0.2662337662337662,
      "grad_norm": 3.3272931575775146,
      "learning_rate": 1.836606641158905e-05,
      "loss": 0.1733,
      "step": 287
    },
    {
      "epoch": 0.26716141001855287,
      "grad_norm": 3.8696646690368652,
      "learning_rate": 1.8348280530292712e-05,
      "loss": 0.2698,
      "step": 288
    },
    {
      "epoch": 0.2680890538033395,
      "grad_norm": 4.347325325012207,
      "learning_rate": 1.833040707948395e-05,
      "loss": 0.2098,
      "step": 289
    },
    {
      "epoch": 0.2690166975881262,
      "grad_norm": 3.8024332523345947,
      "learning_rate": 1.831244624664681e-05,
      "loss": 0.2092,
      "step": 290
    },
    {
      "epoch": 0.2699443413729128,
      "grad_norm": 3.742701768875122,
      "learning_rate": 1.829439822018192e-05,
      "loss": 0.1793,
      "step": 291
    },
    {
      "epoch": 0.27087198515769945,
      "grad_norm": 4.459840774536133,
      "learning_rate": 1.827626318940454e-05,
      "loss": 0.224,
      "step": 292
    },
    {
      "epoch": 0.2717996289424861,
      "grad_norm": 3.4559335708618164,
      "learning_rate": 1.8258041344542567e-05,
      "loss": 0.2342,
      "step": 293
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 4.520707607269287,
      "learning_rate": 1.8239732876734525e-05,
      "loss": 0.2899,
      "step": 294
    },
    {
      "epoch": 0.27365491651205937,
      "grad_norm": 3.844388246536255,
      "learning_rate": 1.822133797802758e-05,
      "loss": 0.172,
      "step": 295
    },
    {
      "epoch": 0.274582560296846,
      "grad_norm": 3.944843292236328,
      "learning_rate": 1.8202856841375517e-05,
      "loss": 0.1602,
      "step": 296
    },
    {
      "epoch": 0.2755102040816326,
      "grad_norm": 2.833136796951294,
      "learning_rate": 1.8184289660636715e-05,
      "loss": 0.1829,
      "step": 297
    },
    {
      "epoch": 0.2764378478664193,
      "grad_norm": 5.877793312072754,
      "learning_rate": 1.816563663057211e-05,
      "loss": 0.1776,
      "step": 298
    },
    {
      "epoch": 0.27736549165120594,
      "grad_norm": 7.863223552703857,
      "learning_rate": 1.8146897946843162e-05,
      "loss": 0.2734,
      "step": 299
    },
    {
      "epoch": 0.2782931354359926,
      "grad_norm": 3.5865793228149414,
      "learning_rate": 1.81280738060098e-05,
      "loss": 0.1607,
      "step": 300
    },
    {
      "epoch": 0.2782931354359926,
      "eval_accuracy": 0.8292682926829268,
      "eval_f1": 0.6010362694300518,
      "eval_loss": 0.34550240635871887,
      "eval_precision": 0.8721804511278195,
      "eval_recall": 0.45849802371541504,
      "eval_runtime": 47.9887,
      "eval_samples_per_second": 5.751,
      "eval_steps_per_second": 0.188,
      "step": 300
    },
    {
      "epoch": 0.2792207792207792,
      "grad_norm": 4.416810512542725,
      "learning_rate": 1.810916440552835e-05,
      "loss": 0.2122,
      "step": 301
    },
    {
      "epoch": 0.28014842300556586,
      "grad_norm": 4.608455657958984,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.1634,
      "step": 302
    },
    {
      "epoch": 0.2810760667903525,
      "grad_norm": 2.9112977981567383,
      "learning_rate": 1.8071090619916095e-05,
      "loss": 0.1863,
      "step": 303
    },
    {
      "epoch": 0.2820037105751391,
      "grad_norm": 4.165685176849365,
      "learning_rate": 1.8051926634161282e-05,
      "loss": 0.1607,
      "step": 304
    },
    {
      "epoch": 0.2829313543599258,
      "grad_norm": 3.188124895095825,
      "learning_rate": 1.8032678187506187e-05,
      "loss": 0.1379,
      "step": 305
    },
    {
      "epoch": 0.28385899814471244,
      "grad_norm": 4.277055740356445,
      "learning_rate": 1.8013345481857903e-05,
      "loss": 0.1945,
      "step": 306
    },
    {
      "epoch": 0.2847866419294991,
      "grad_norm": 4.259377956390381,
      "learning_rate": 1.799392872000736e-05,
      "loss": 0.2123,
      "step": 307
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 4.486137390136719,
      "learning_rate": 1.797442810562721e-05,
      "loss": 0.2004,
      "step": 308
    },
    {
      "epoch": 0.28664192949907236,
      "grad_norm": 6.125461578369141,
      "learning_rate": 1.7954843843269665e-05,
      "loss": 0.2124,
      "step": 309
    },
    {
      "epoch": 0.287569573283859,
      "grad_norm": 4.838400363922119,
      "learning_rate": 1.793517613836437e-05,
      "loss": 0.2112,
      "step": 310
    },
    {
      "epoch": 0.2884972170686456,
      "grad_norm": 3.1725666522979736,
      "learning_rate": 1.7915425197216246e-05,
      "loss": 0.1658,
      "step": 311
    },
    {
      "epoch": 0.2894248608534323,
      "grad_norm": 3.154855489730835,
      "learning_rate": 1.7895591227003316e-05,
      "loss": 0.2081,
      "step": 312
    },
    {
      "epoch": 0.29035250463821893,
      "grad_norm": 3.7664122581481934,
      "learning_rate": 1.7875674435774546e-05,
      "loss": 0.1628,
      "step": 313
    },
    {
      "epoch": 0.2912801484230056,
      "grad_norm": 5.876150131225586,
      "learning_rate": 1.7855675032447648e-05,
      "loss": 0.1882,
      "step": 314
    },
    {
      "epoch": 0.2922077922077922,
      "grad_norm": 2.4536941051483154,
      "learning_rate": 1.7835593226806902e-05,
      "loss": 0.1287,
      "step": 315
    },
    {
      "epoch": 0.29313543599257885,
      "grad_norm": 4.552228927612305,
      "learning_rate": 1.7815429229500946e-05,
      "loss": 0.2509,
      "step": 316
    },
    {
      "epoch": 0.2940630797773655,
      "grad_norm": 3.861381769180298,
      "learning_rate": 1.7795183252040568e-05,
      "loss": 0.1827,
      "step": 317
    },
    {
      "epoch": 0.2949907235621521,
      "grad_norm": 3.6626925468444824,
      "learning_rate": 1.7774855506796497e-05,
      "loss": 0.154,
      "step": 318
    },
    {
      "epoch": 0.29591836734693877,
      "grad_norm": 6.695428848266602,
      "learning_rate": 1.7754446206997152e-05,
      "loss": 0.2334,
      "step": 319
    },
    {
      "epoch": 0.29684601113172543,
      "grad_norm": 3.2786192893981934,
      "learning_rate": 1.7733955566726438e-05,
      "loss": 0.1671,
      "step": 320
    },
    {
      "epoch": 0.29684601113172543,
      "eval_accuracy": 0.8337028824833703,
      "eval_f1": 0.625,
      "eval_loss": 0.3371331989765167,
      "eval_precision": 0.8503401360544217,
      "eval_recall": 0.49407114624505927,
      "eval_runtime": 47.664,
      "eval_samples_per_second": 5.791,
      "eval_steps_per_second": 0.189,
      "step": 320
    },
    {
      "epoch": 0.29777365491651203,
      "grad_norm": 4.181811809539795,
      "learning_rate": 1.771338380092148e-05,
      "loss": 0.2198,
      "step": 321
    },
    {
      "epoch": 0.2987012987012987,
      "grad_norm": 4.808495998382568,
      "learning_rate": 1.7692731125370355e-05,
      "loss": 0.171,
      "step": 322
    },
    {
      "epoch": 0.29962894248608535,
      "grad_norm": 5.946144104003906,
      "learning_rate": 1.767199775670986e-05,
      "loss": 0.2176,
      "step": 323
    },
    {
      "epoch": 0.300556586270872,
      "grad_norm": 4.010025978088379,
      "learning_rate": 1.7651183912423228e-05,
      "loss": 0.2003,
      "step": 324
    },
    {
      "epoch": 0.3014842300556586,
      "grad_norm": 4.795968055725098,
      "learning_rate": 1.7630289810837836e-05,
      "loss": 0.165,
      "step": 325
    },
    {
      "epoch": 0.30241187384044527,
      "grad_norm": 2.9344944953918457,
      "learning_rate": 1.7609315671122912e-05,
      "loss": 0.1603,
      "step": 326
    },
    {
      "epoch": 0.3033395176252319,
      "grad_norm": 5.812965393066406,
      "learning_rate": 1.758826171328727e-05,
      "loss": 0.1458,
      "step": 327
    },
    {
      "epoch": 0.3042671614100185,
      "grad_norm": 4.66487979888916,
      "learning_rate": 1.7567128158176955e-05,
      "loss": 0.2155,
      "step": 328
    },
    {
      "epoch": 0.3051948051948052,
      "grad_norm": 3.436579942703247,
      "learning_rate": 1.7545915227472967e-05,
      "loss": 0.1699,
      "step": 329
    },
    {
      "epoch": 0.30612244897959184,
      "grad_norm": 4.022927284240723,
      "learning_rate": 1.7524623143688905e-05,
      "loss": 0.2037,
      "step": 330
    },
    {
      "epoch": 0.3070500927643785,
      "grad_norm": 3.154623031616211,
      "learning_rate": 1.7503252130168657e-05,
      "loss": 0.1627,
      "step": 331
    },
    {
      "epoch": 0.3079777365491651,
      "grad_norm": 2.7966222763061523,
      "learning_rate": 1.748180241108404e-05,
      "loss": 0.1439,
      "step": 332
    },
    {
      "epoch": 0.30890538033395176,
      "grad_norm": 3.8477606773376465,
      "learning_rate": 1.7460274211432463e-05,
      "loss": 0.135,
      "step": 333
    },
    {
      "epoch": 0.3098330241187384,
      "grad_norm": 3.51237416267395,
      "learning_rate": 1.7438667757034547e-05,
      "loss": 0.213,
      "step": 334
    },
    {
      "epoch": 0.310760667903525,
      "grad_norm": 4.482552528381348,
      "learning_rate": 1.7416983274531777e-05,
      "loss": 0.2018,
      "step": 335
    },
    {
      "epoch": 0.3116883116883117,
      "grad_norm": 3.7399659156799316,
      "learning_rate": 1.739522099138411e-05,
      "loss": 0.2196,
      "step": 336
    },
    {
      "epoch": 0.31261595547309834,
      "grad_norm": 3.4632811546325684,
      "learning_rate": 1.7373381135867605e-05,
      "loss": 0.1588,
      "step": 337
    },
    {
      "epoch": 0.313543599257885,
      "grad_norm": 5.400178909301758,
      "learning_rate": 1.7351463937072008e-05,
      "loss": 0.2455,
      "step": 338
    },
    {
      "epoch": 0.3144712430426716,
      "grad_norm": 4.754225730895996,
      "learning_rate": 1.732946962489836e-05,
      "loss": 0.2067,
      "step": 339
    },
    {
      "epoch": 0.31539888682745826,
      "grad_norm": 3.6749982833862305,
      "learning_rate": 1.7307398430056595e-05,
      "loss": 0.1809,
      "step": 340
    },
    {
      "epoch": 0.31539888682745826,
      "eval_accuracy": 0.8514412416851441,
      "eval_f1": 0.6912442396313364,
      "eval_loss": 0.34059056639671326,
      "eval_precision": 0.8287292817679558,
      "eval_recall": 0.5928853754940712,
      "eval_runtime": 47.764,
      "eval_samples_per_second": 5.778,
      "eval_steps_per_second": 0.188,
      "step": 340
    },
    {
      "epoch": 0.3163265306122449,
      "grad_norm": 5.549361705780029,
      "learning_rate": 1.72852505840631e-05,
      "loss": 0.1656,
      "step": 341
    },
    {
      "epoch": 0.3172541743970315,
      "grad_norm": 7.491882801055908,
      "learning_rate": 1.72630263192383e-05,
      "loss": 0.2493,
      "step": 342
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 5.225057125091553,
      "learning_rate": 1.7240725868704218e-05,
      "loss": 0.2031,
      "step": 343
    },
    {
      "epoch": 0.31910946196660483,
      "grad_norm": 7.436551094055176,
      "learning_rate": 1.7218349466382024e-05,
      "loss": 0.2245,
      "step": 344
    },
    {
      "epoch": 0.3200371057513915,
      "grad_norm": 4.4297871589660645,
      "learning_rate": 1.719589734698959e-05,
      "loss": 0.2226,
      "step": 345
    },
    {
      "epoch": 0.3209647495361781,
      "grad_norm": 6.560292720794678,
      "learning_rate": 1.7173369746039026e-05,
      "loss": 0.2331,
      "step": 346
    },
    {
      "epoch": 0.32189239332096475,
      "grad_norm": 5.045467376708984,
      "learning_rate": 1.7150766899834205e-05,
      "loss": 0.2321,
      "step": 347
    },
    {
      "epoch": 0.3228200371057514,
      "grad_norm": 6.464671611785889,
      "learning_rate": 1.7128089045468294e-05,
      "loss": 0.19,
      "step": 348
    },
    {
      "epoch": 0.323747680890538,
      "grad_norm": 2.7538771629333496,
      "learning_rate": 1.7105336420821247e-05,
      "loss": 0.1642,
      "step": 349
    },
    {
      "epoch": 0.3246753246753247,
      "grad_norm": 4.287221431732178,
      "learning_rate": 1.7082509264557333e-05,
      "loss": 0.1556,
      "step": 350
    },
    {
      "epoch": 0.32560296846011133,
      "grad_norm": 3.1308867931365967,
      "learning_rate": 1.705960781612262e-05,
      "loss": 0.1583,
      "step": 351
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": 3.598468542098999,
      "learning_rate": 1.7036632315742464e-05,
      "loss": 0.1571,
      "step": 352
    },
    {
      "epoch": 0.3274582560296846,
      "grad_norm": 2.93074369430542,
      "learning_rate": 1.7013583004418994e-05,
      "loss": 0.1463,
      "step": 353
    },
    {
      "epoch": 0.32838589981447125,
      "grad_norm": 3.5115561485290527,
      "learning_rate": 1.6990460123928577e-05,
      "loss": 0.1522,
      "step": 354
    },
    {
      "epoch": 0.3293135435992579,
      "grad_norm": 2.3975048065185547,
      "learning_rate": 1.696726391681929e-05,
      "loss": 0.136,
      "step": 355
    },
    {
      "epoch": 0.3302411873840445,
      "grad_norm": 3.01874041557312,
      "learning_rate": 1.6943994626408365e-05,
      "loss": 0.1928,
      "step": 356
    },
    {
      "epoch": 0.33116883116883117,
      "grad_norm": 3.620572805404663,
      "learning_rate": 1.692065249677965e-05,
      "loss": 0.1964,
      "step": 357
    },
    {
      "epoch": 0.3320964749536178,
      "grad_norm": 3.1630985736846924,
      "learning_rate": 1.6897237772781046e-05,
      "loss": 0.1757,
      "step": 358
    },
    {
      "epoch": 0.33302411873840443,
      "grad_norm": 2.7404632568359375,
      "learning_rate": 1.6873750700021917e-05,
      "loss": 0.1391,
      "step": 359
    },
    {
      "epoch": 0.3339517625231911,
      "grad_norm": 3.915576696395874,
      "learning_rate": 1.6850191524870548e-05,
      "loss": 0.1672,
      "step": 360
    },
    {
      "epoch": 0.3339517625231911,
      "eval_accuracy": 0.8392461197339246,
      "eval_f1": 0.6365914786967418,
      "eval_loss": 0.3519636392593384,
      "eval_precision": 0.8698630136986302,
      "eval_recall": 0.5019762845849802,
      "eval_runtime": 48.8319,
      "eval_samples_per_second": 5.652,
      "eval_steps_per_second": 0.184,
      "step": 360
    },
    {
      "epoch": 0.33487940630797774,
      "grad_norm": 4.442441940307617,
      "learning_rate": 1.682656049445154e-05,
      "loss": 0.1695,
      "step": 361
    },
    {
      "epoch": 0.3358070500927644,
      "grad_norm": 3.9514217376708984,
      "learning_rate": 1.6802857856643214e-05,
      "loss": 0.1744,
      "step": 362
    },
    {
      "epoch": 0.336734693877551,
      "grad_norm": 5.170446395874023,
      "learning_rate": 1.6779083860075032e-05,
      "loss": 0.1198,
      "step": 363
    },
    {
      "epoch": 0.33766233766233766,
      "grad_norm": 7.009990215301514,
      "learning_rate": 1.6755238754124965e-05,
      "loss": 0.1708,
      "step": 364
    },
    {
      "epoch": 0.3385899814471243,
      "grad_norm": 7.845787048339844,
      "learning_rate": 1.6731322788916892e-05,
      "loss": 0.1723,
      "step": 365
    },
    {
      "epoch": 0.3395176252319109,
      "grad_norm": 3.684112071990967,
      "learning_rate": 1.6707336215317968e-05,
      "loss": 0.1136,
      "step": 366
    },
    {
      "epoch": 0.3404452690166976,
      "grad_norm": 6.165255069732666,
      "learning_rate": 1.6683279284936004e-05,
      "loss": 0.2895,
      "step": 367
    },
    {
      "epoch": 0.34137291280148424,
      "grad_norm": 5.1027326583862305,
      "learning_rate": 1.665915225011681e-05,
      "loss": 0.1915,
      "step": 368
    },
    {
      "epoch": 0.3423005565862709,
      "grad_norm": 4.702267646789551,
      "learning_rate": 1.6634955363941573e-05,
      "loss": 0.135,
      "step": 369
    },
    {
      "epoch": 0.3432282003710575,
      "grad_norm": 3.623323678970337,
      "learning_rate": 1.6610688880224178e-05,
      "loss": 0.1364,
      "step": 370
    },
    {
      "epoch": 0.34415584415584416,
      "grad_norm": 4.77068567276001,
      "learning_rate": 1.6586353053508548e-05,
      "loss": 0.2082,
      "step": 371
    },
    {
      "epoch": 0.3450834879406308,
      "grad_norm": 6.354672908782959,
      "learning_rate": 1.6561948139065997e-05,
      "loss": 0.2037,
      "step": 372
    },
    {
      "epoch": 0.3460111317254174,
      "grad_norm": 3.074613094329834,
      "learning_rate": 1.6537474392892527e-05,
      "loss": 0.1123,
      "step": 373
    },
    {
      "epoch": 0.3469387755102041,
      "grad_norm": 5.388340473175049,
      "learning_rate": 1.6512932071706153e-05,
      "loss": 0.2308,
      "step": 374
    },
    {
      "epoch": 0.34786641929499074,
      "grad_norm": 3.377591609954834,
      "learning_rate": 1.6488321432944218e-05,
      "loss": 0.1607,
      "step": 375
    },
    {
      "epoch": 0.34879406307977734,
      "grad_norm": 3.697253465652466,
      "learning_rate": 1.646364273476067e-05,
      "loss": 0.2064,
      "step": 376
    },
    {
      "epoch": 0.349721706864564,
      "grad_norm": 2.825587272644043,
      "learning_rate": 1.6438896236023374e-05,
      "loss": 0.1405,
      "step": 377
    },
    {
      "epoch": 0.35064935064935066,
      "grad_norm": 5.332752227783203,
      "learning_rate": 1.6414082196311402e-05,
      "loss": 0.1838,
      "step": 378
    },
    {
      "epoch": 0.3515769944341373,
      "grad_norm": 3.3014256954193115,
      "learning_rate": 1.638920087591228e-05,
      "loss": 0.1516,
      "step": 379
    },
    {
      "epoch": 0.3525046382189239,
      "grad_norm": 2.9438254833221436,
      "learning_rate": 1.6364252535819284e-05,
      "loss": 0.153,
      "step": 380
    },
    {
      "epoch": 0.3525046382189239,
      "eval_accuracy": 0.8458980044345898,
      "eval_f1": 0.6634382566585957,
      "eval_loss": 0.32734009623527527,
      "eval_precision": 0.85625,
      "eval_recall": 0.541501976284585,
      "eval_runtime": 47.3489,
      "eval_samples_per_second": 5.829,
      "eval_steps_per_second": 0.19,
      "step": 380
    },
    {
      "epoch": 0.3534322820037106,
      "grad_norm": 4.24219274520874,
      "learning_rate": 1.63392374377287e-05,
      "loss": 0.1265,
      "step": 381
    },
    {
      "epoch": 0.35435992578849723,
      "grad_norm": 3.8825278282165527,
      "learning_rate": 1.6314155844037074e-05,
      "loss": 0.173,
      "step": 382
    },
    {
      "epoch": 0.35528756957328383,
      "grad_norm": 4.059886455535889,
      "learning_rate": 1.6289008017838447e-05,
      "loss": 0.1639,
      "step": 383
    },
    {
      "epoch": 0.3562152133580705,
      "grad_norm": 5.13779878616333,
      "learning_rate": 1.626379422292162e-05,
      "loss": 0.1006,
      "step": 384
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 5.269052028656006,
      "learning_rate": 1.6238514723767372e-05,
      "loss": 0.2033,
      "step": 385
    },
    {
      "epoch": 0.3580705009276438,
      "grad_norm": 4.739077091217041,
      "learning_rate": 1.6213169785545688e-05,
      "loss": 0.2673,
      "step": 386
    },
    {
      "epoch": 0.3589981447124304,
      "grad_norm": 5.1900634765625,
      "learning_rate": 1.6187759674112972e-05,
      "loss": 0.2156,
      "step": 387
    },
    {
      "epoch": 0.35992578849721707,
      "grad_norm": 2.844031810760498,
      "learning_rate": 1.6162284656009276e-05,
      "loss": 0.0855,
      "step": 388
    },
    {
      "epoch": 0.3608534322820037,
      "grad_norm": 5.831792831420898,
      "learning_rate": 1.6136744998455477e-05,
      "loss": 0.2278,
      "step": 389
    },
    {
      "epoch": 0.36178107606679033,
      "grad_norm": 3.952970504760742,
      "learning_rate": 1.6111140969350504e-05,
      "loss": 0.1348,
      "step": 390
    },
    {
      "epoch": 0.362708719851577,
      "grad_norm": 3.9323179721832275,
      "learning_rate": 1.6085472837268504e-05,
      "loss": 0.1731,
      "step": 391
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 4.621875286102295,
      "learning_rate": 1.6059740871456035e-05,
      "loss": 0.2011,
      "step": 392
    },
    {
      "epoch": 0.3645640074211503,
      "grad_norm": 6.936546325683594,
      "learning_rate": 1.603394534182925e-05,
      "loss": 0.1766,
      "step": 393
    },
    {
      "epoch": 0.3654916512059369,
      "grad_norm": 4.287359237670898,
      "learning_rate": 1.6008086518971037e-05,
      "loss": 0.1939,
      "step": 394
    },
    {
      "epoch": 0.36641929499072357,
      "grad_norm": 3.0315101146698,
      "learning_rate": 1.598216467412822e-05,
      "loss": 0.1091,
      "step": 395
    },
    {
      "epoch": 0.3673469387755102,
      "grad_norm": 6.599478721618652,
      "learning_rate": 1.5956180079208684e-05,
      "loss": 0.232,
      "step": 396
    },
    {
      "epoch": 0.3682745825602968,
      "grad_norm": 4.763383388519287,
      "learning_rate": 1.593013300677853e-05,
      "loss": 0.1877,
      "step": 397
    },
    {
      "epoch": 0.3692022263450835,
      "grad_norm": 4.326437950134277,
      "learning_rate": 1.5904023730059227e-05,
      "loss": 0.1924,
      "step": 398
    },
    {
      "epoch": 0.37012987012987014,
      "grad_norm": 4.332076072692871,
      "learning_rate": 1.5877852522924733e-05,
      "loss": 0.201,
      "step": 399
    },
    {
      "epoch": 0.37105751391465674,
      "grad_norm": 4.557116985321045,
      "learning_rate": 1.5851619659898623e-05,
      "loss": 0.2,
      "step": 400
    },
    {
      "epoch": 0.37105751391465674,
      "eval_accuracy": 0.844789356984479,
      "eval_f1": 0.6585365853658537,
      "eval_loss": 0.33066147565841675,
      "eval_precision": 0.8598726114649682,
      "eval_recall": 0.5335968379446641,
      "eval_runtime": 47.9063,
      "eval_samples_per_second": 5.761,
      "eval_steps_per_second": 0.188,
      "step": 400
    },
    {
      "epoch": 0.3719851576994434,
      "grad_norm": 4.4434332847595215,
      "learning_rate": 1.582532541615122e-05,
      "loss": 0.1563,
      "step": 401
    },
    {
      "epoch": 0.37291280148423006,
      "grad_norm": 2.928924083709717,
      "learning_rate": 1.57989700674967e-05,
      "loss": 0.1211,
      "step": 402
    },
    {
      "epoch": 0.3738404452690167,
      "grad_norm": 3.329848527908325,
      "learning_rate": 1.5772553890390196e-05,
      "loss": 0.2248,
      "step": 403
    },
    {
      "epoch": 0.3747680890538033,
      "grad_norm": 4.852266311645508,
      "learning_rate": 1.5746077161924905e-05,
      "loss": 0.2121,
      "step": 404
    },
    {
      "epoch": 0.37569573283859,
      "grad_norm": 8.039565086364746,
      "learning_rate": 1.5719540159829185e-05,
      "loss": 0.1864,
      "step": 405
    },
    {
      "epoch": 0.37662337662337664,
      "grad_norm": 4.178286552429199,
      "learning_rate": 1.5692943162463628e-05,
      "loss": 0.1164,
      "step": 406
    },
    {
      "epoch": 0.37755102040816324,
      "grad_norm": 4.181092739105225,
      "learning_rate": 1.5666286448818152e-05,
      "loss": 0.136,
      "step": 407
    },
    {
      "epoch": 0.3784786641929499,
      "grad_norm": 4.847424030303955,
      "learning_rate": 1.5639570298509067e-05,
      "loss": 0.1692,
      "step": 408
    },
    {
      "epoch": 0.37940630797773656,
      "grad_norm": 5.589816570281982,
      "learning_rate": 1.5612794991776147e-05,
      "loss": 0.1375,
      "step": 409
    },
    {
      "epoch": 0.3803339517625232,
      "grad_norm": 3.174445629119873,
      "learning_rate": 1.5585960809479698e-05,
      "loss": 0.1683,
      "step": 410
    },
    {
      "epoch": 0.3812615955473098,
      "grad_norm": 7.2739739418029785,
      "learning_rate": 1.5559068033097583e-05,
      "loss": 0.2135,
      "step": 411
    },
    {
      "epoch": 0.3821892393320965,
      "grad_norm": 5.514982223510742,
      "learning_rate": 1.5532116944722308e-05,
      "loss": 0.2366,
      "step": 412
    },
    {
      "epoch": 0.38311688311688313,
      "grad_norm": 4.4258036613464355,
      "learning_rate": 1.5505107827058038e-05,
      "loss": 0.1667,
      "step": 413
    },
    {
      "epoch": 0.38404452690166974,
      "grad_norm": 4.089566230773926,
      "learning_rate": 1.547804096341763e-05,
      "loss": 0.1647,
      "step": 414
    },
    {
      "epoch": 0.3849721706864564,
      "grad_norm": 3.6559548377990723,
      "learning_rate": 1.5450916637719683e-05,
      "loss": 0.1705,
      "step": 415
    },
    {
      "epoch": 0.38589981447124305,
      "grad_norm": 4.045246124267578,
      "learning_rate": 1.5423735134485537e-05,
      "loss": 0.1915,
      "step": 416
    },
    {
      "epoch": 0.3868274582560297,
      "grad_norm": 3.6718714237213135,
      "learning_rate": 1.5396496738836292e-05,
      "loss": 0.1532,
      "step": 417
    },
    {
      "epoch": 0.3877551020408163,
      "grad_norm": 4.593350887298584,
      "learning_rate": 1.536920173648984e-05,
      "loss": 0.1815,
      "step": 418
    },
    {
      "epoch": 0.38868274582560297,
      "grad_norm": 3.913667917251587,
      "learning_rate": 1.5341850413757834e-05,
      "loss": 0.1448,
      "step": 419
    },
    {
      "epoch": 0.38961038961038963,
      "grad_norm": 4.148723125457764,
      "learning_rate": 1.5314443057542703e-05,
      "loss": 0.2082,
      "step": 420
    },
    {
      "epoch": 0.38961038961038963,
      "eval_accuracy": 0.8603104212860311,
      "eval_f1": 0.7136363636363636,
      "eval_loss": 0.31429344415664673,
      "eval_precision": 0.839572192513369,
      "eval_recall": 0.6205533596837944,
      "eval_runtime": 48.5179,
      "eval_samples_per_second": 5.689,
      "eval_steps_per_second": 0.185,
      "step": 420
    },
    {
      "epoch": 0.39053803339517623,
      "grad_norm": 4.14030122756958,
      "learning_rate": 1.5286979955334655e-05,
      "loss": 0.1749,
      "step": 421
    },
    {
      "epoch": 0.3914656771799629,
      "grad_norm": 3.4345805644989014,
      "learning_rate": 1.5259461395208628e-05,
      "loss": 0.1712,
      "step": 422
    },
    {
      "epoch": 0.39239332096474955,
      "grad_norm": 3.9379382133483887,
      "learning_rate": 1.52318876658213e-05,
      "loss": 0.1658,
      "step": 423
    },
    {
      "epoch": 0.39332096474953615,
      "grad_norm": 3.1555135250091553,
      "learning_rate": 1.5204259056408046e-05,
      "loss": 0.1537,
      "step": 424
    },
    {
      "epoch": 0.3942486085343228,
      "grad_norm": 3.893655776977539,
      "learning_rate": 1.5176575856779904e-05,
      "loss": 0.1509,
      "step": 425
    },
    {
      "epoch": 0.39517625231910947,
      "grad_norm": 4.423066139221191,
      "learning_rate": 1.5148838357320537e-05,
      "loss": 0.1501,
      "step": 426
    },
    {
      "epoch": 0.3961038961038961,
      "grad_norm": 5.078852653503418,
      "learning_rate": 1.512104684898319e-05,
      "loss": 0.2835,
      "step": 427
    },
    {
      "epoch": 0.3970315398886827,
      "grad_norm": 3.377333164215088,
      "learning_rate": 1.5093201623287631e-05,
      "loss": 0.1393,
      "step": 428
    },
    {
      "epoch": 0.3979591836734694,
      "grad_norm": 4.0545196533203125,
      "learning_rate": 1.5065302972317108e-05,
      "loss": 0.1567,
      "step": 429
    },
    {
      "epoch": 0.39888682745825604,
      "grad_norm": 6.253279685974121,
      "learning_rate": 1.5037351188715265e-05,
      "loss": 0.2155,
      "step": 430
    },
    {
      "epoch": 0.39981447124304265,
      "grad_norm": 2.698172092437744,
      "learning_rate": 1.5009346565683088e-05,
      "loss": 0.1102,
      "step": 431
    },
    {
      "epoch": 0.4007421150278293,
      "grad_norm": 4.845376014709473,
      "learning_rate": 1.4981289396975818e-05,
      "loss": 0.2186,
      "step": 432
    },
    {
      "epoch": 0.40166975881261596,
      "grad_norm": 2.9927968978881836,
      "learning_rate": 1.4953179976899878e-05,
      "loss": 0.1365,
      "step": 433
    },
    {
      "epoch": 0.4025974025974026,
      "grad_norm": 3.484133720397949,
      "learning_rate": 1.4925018600309784e-05,
      "loss": 0.18,
      "step": 434
    },
    {
      "epoch": 0.4035250463821892,
      "grad_norm": 2.8350846767425537,
      "learning_rate": 1.4896805562605052e-05,
      "loss": 0.1644,
      "step": 435
    },
    {
      "epoch": 0.4044526901669759,
      "grad_norm": 3.7044577598571777,
      "learning_rate": 1.4868541159727097e-05,
      "loss": 0.1758,
      "step": 436
    },
    {
      "epoch": 0.40538033395176254,
      "grad_norm": 3.7919528484344482,
      "learning_rate": 1.4840225688156132e-05,
      "loss": 0.1609,
      "step": 437
    },
    {
      "epoch": 0.40630797773654914,
      "grad_norm": 3.7263407707214355,
      "learning_rate": 1.4811859444908053e-05,
      "loss": 0.1674,
      "step": 438
    },
    {
      "epoch": 0.4072356215213358,
      "grad_norm": 3.5427684783935547,
      "learning_rate": 1.4783442727531328e-05,
      "loss": 0.212,
      "step": 439
    },
    {
      "epoch": 0.40816326530612246,
      "grad_norm": 5.29186487197876,
      "learning_rate": 1.4754975834103877e-05,
      "loss": 0.2051,
      "step": 440
    },
    {
      "epoch": 0.40816326530612246,
      "eval_accuracy": 0.8569844789356984,
      "eval_f1": 0.6978922716627635,
      "eval_loss": 0.3138832747936249,
      "eval_precision": 0.8563218390804598,
      "eval_recall": 0.5889328063241107,
      "eval_runtime": 48.1239,
      "eval_samples_per_second": 5.735,
      "eval_steps_per_second": 0.187,
      "step": 440
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 6.476135730743408,
      "learning_rate": 1.4726459063229946e-05,
      "loss": 0.1586,
      "step": 441
    },
    {
      "epoch": 0.4100185528756957,
      "grad_norm": 4.70169734954834,
      "learning_rate": 1.4697892714036959e-05,
      "loss": 0.1604,
      "step": 442
    },
    {
      "epoch": 0.4109461966604824,
      "grad_norm": 3.1262881755828857,
      "learning_rate": 1.4669277086172406e-05,
      "loss": 0.1282,
      "step": 443
    },
    {
      "epoch": 0.41187384044526903,
      "grad_norm": 3.5137503147125244,
      "learning_rate": 1.4640612479800686e-05,
      "loss": 0.179,
      "step": 444
    },
    {
      "epoch": 0.41280148423005564,
      "grad_norm": 5.388190269470215,
      "learning_rate": 1.4611899195599952e-05,
      "loss": 0.2404,
      "step": 445
    },
    {
      "epoch": 0.4137291280148423,
      "grad_norm": 4.668002128601074,
      "learning_rate": 1.4583137534758968e-05,
      "loss": 0.1781,
      "step": 446
    },
    {
      "epoch": 0.41465677179962895,
      "grad_norm": 4.363613128662109,
      "learning_rate": 1.455432779897395e-05,
      "loss": 0.1636,
      "step": 447
    },
    {
      "epoch": 0.4155844155844156,
      "grad_norm": 3.608628749847412,
      "learning_rate": 1.4525470290445392e-05,
      "loss": 0.1604,
      "step": 448
    },
    {
      "epoch": 0.4165120593692022,
      "grad_norm": 4.1195387840271,
      "learning_rate": 1.4496565311874902e-05,
      "loss": 0.1752,
      "step": 449
    },
    {
      "epoch": 0.4174397031539889,
      "grad_norm": 2.9940760135650635,
      "learning_rate": 1.4467613166462024e-05,
      "loss": 0.1579,
      "step": 450
    },
    {
      "epoch": 0.41836734693877553,
      "grad_norm": 3.3826465606689453,
      "learning_rate": 1.4438614157901073e-05,
      "loss": 0.1529,
      "step": 451
    },
    {
      "epoch": 0.41929499072356213,
      "grad_norm": 2.9892001152038574,
      "learning_rate": 1.4409568590377918e-05,
      "loss": 0.1435,
      "step": 452
    },
    {
      "epoch": 0.4202226345083488,
      "grad_norm": 3.4909090995788574,
      "learning_rate": 1.4380476768566825e-05,
      "loss": 0.1879,
      "step": 453
    },
    {
      "epoch": 0.42115027829313545,
      "grad_norm": 3.8178699016571045,
      "learning_rate": 1.4351338997627233e-05,
      "loss": 0.1693,
      "step": 454
    },
    {
      "epoch": 0.42207792207792205,
      "grad_norm": 3.101930618286133,
      "learning_rate": 1.4322155583200577e-05,
      "loss": 0.1315,
      "step": 455
    },
    {
      "epoch": 0.4230055658627087,
      "grad_norm": 3.344278335571289,
      "learning_rate": 1.429292683140706e-05,
      "loss": 0.1539,
      "step": 456
    },
    {
      "epoch": 0.42393320964749537,
      "grad_norm": 2.970942497253418,
      "learning_rate": 1.4263653048842461e-05,
      "loss": 0.1374,
      "step": 457
    },
    {
      "epoch": 0.424860853432282,
      "grad_norm": 3.1692464351654053,
      "learning_rate": 1.4234334542574906e-05,
      "loss": 0.2035,
      "step": 458
    },
    {
      "epoch": 0.42578849721706863,
      "grad_norm": 2.829171895980835,
      "learning_rate": 1.4204971620141648e-05,
      "loss": 0.1483,
      "step": 459
    },
    {
      "epoch": 0.4267161410018553,
      "grad_norm": 3.1080052852630615,
      "learning_rate": 1.4175564589545853e-05,
      "loss": 0.0959,
      "step": 460
    },
    {
      "epoch": 0.4267161410018553,
      "eval_accuracy": 0.8569844789356984,
      "eval_f1": 0.6993006993006993,
      "eval_loss": 0.3129526674747467,
      "eval_precision": 0.8522727272727273,
      "eval_recall": 0.5928853754940712,
      "eval_runtime": 48.0013,
      "eval_samples_per_second": 5.75,
      "eval_steps_per_second": 0.187,
      "step": 460
    },
    {
      "epoch": 0.42764378478664195,
      "grad_norm": 4.785598278045654,
      "learning_rate": 1.4146113759253362e-05,
      "loss": 0.1891,
      "step": 461
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 4.229030609130859,
      "learning_rate": 1.411661943818944e-05,
      "loss": 0.1546,
      "step": 462
    },
    {
      "epoch": 0.4294990723562152,
      "grad_norm": 4.43852424621582,
      "learning_rate": 1.4087081935735565e-05,
      "loss": 0.1769,
      "step": 463
    },
    {
      "epoch": 0.43042671614100186,
      "grad_norm": 4.6244049072265625,
      "learning_rate": 1.4057501561726157e-05,
      "loss": 0.2404,
      "step": 464
    },
    {
      "epoch": 0.4313543599257885,
      "grad_norm": 4.3941168785095215,
      "learning_rate": 1.4027878626445339e-05,
      "loss": 0.1781,
      "step": 465
    },
    {
      "epoch": 0.4322820037105751,
      "grad_norm": 6.995157718658447,
      "learning_rate": 1.3998213440623691e-05,
      "loss": 0.2318,
      "step": 466
    },
    {
      "epoch": 0.4332096474953618,
      "grad_norm": 2.781472682952881,
      "learning_rate": 1.3968506315434973e-05,
      "loss": 0.0949,
      "step": 467
    },
    {
      "epoch": 0.43413729128014844,
      "grad_norm": 2.9485185146331787,
      "learning_rate": 1.3938757562492873e-05,
      "loss": 0.1268,
      "step": 468
    },
    {
      "epoch": 0.43506493506493504,
      "grad_norm": 6.8653130531311035,
      "learning_rate": 1.390896749384773e-05,
      "loss": 0.2818,
      "step": 469
    },
    {
      "epoch": 0.4359925788497217,
      "grad_norm": 5.269331932067871,
      "learning_rate": 1.3879136421983265e-05,
      "loss": 0.1386,
      "step": 470
    },
    {
      "epoch": 0.43692022263450836,
      "grad_norm": 5.839674472808838,
      "learning_rate": 1.3849264659813314e-05,
      "loss": 0.1739,
      "step": 471
    },
    {
      "epoch": 0.437847866419295,
      "grad_norm": 4.306594371795654,
      "learning_rate": 1.3819352520678519e-05,
      "loss": 0.1562,
      "step": 472
    },
    {
      "epoch": 0.4387755102040816,
      "grad_norm": 4.80615234375,
      "learning_rate": 1.378940031834307e-05,
      "loss": 0.2049,
      "step": 473
    },
    {
      "epoch": 0.4397031539888683,
      "grad_norm": 4.824836730957031,
      "learning_rate": 1.3759408366991391e-05,
      "loss": 0.1667,
      "step": 474
    },
    {
      "epoch": 0.44063079777365494,
      "grad_norm": 4.227314472198486,
      "learning_rate": 1.3729376981224869e-05,
      "loss": 0.1783,
      "step": 475
    },
    {
      "epoch": 0.44155844155844154,
      "grad_norm": 4.170743942260742,
      "learning_rate": 1.3699306476058523e-05,
      "loss": 0.1724,
      "step": 476
    },
    {
      "epoch": 0.4424860853432282,
      "grad_norm": 6.098860263824463,
      "learning_rate": 1.3669197166917723e-05,
      "loss": 0.2301,
      "step": 477
    },
    {
      "epoch": 0.44341372912801486,
      "grad_norm": 3.2894742488861084,
      "learning_rate": 1.3639049369634878e-05,
      "loss": 0.1636,
      "step": 478
    },
    {
      "epoch": 0.44434137291280146,
      "grad_norm": 3.913362503051758,
      "learning_rate": 1.3608863400446113e-05,
      "loss": 0.1762,
      "step": 479
    },
    {
      "epoch": 0.4452690166975881,
      "grad_norm": 4.007498741149902,
      "learning_rate": 1.357863957598796e-05,
      "loss": 0.1955,
      "step": 480
    },
    {
      "epoch": 0.4452690166975881,
      "eval_accuracy": 0.8592017738359202,
      "eval_f1": 0.7080459770114943,
      "eval_loss": 0.3043546974658966,
      "eval_precision": 0.8461538461538461,
      "eval_recall": 0.6086956521739131,
      "eval_runtime": 48.2191,
      "eval_samples_per_second": 5.724,
      "eval_steps_per_second": 0.187,
      "step": 480
    },
    {
      "epoch": 0.4461966604823748,
      "grad_norm": 4.113521575927734,
      "learning_rate": 1.3548378213294042e-05,
      "loss": 0.1875,
      "step": 481
    },
    {
      "epoch": 0.44712430426716143,
      "grad_norm": 4.532953262329102,
      "learning_rate": 1.3518079629791725e-05,
      "loss": 0.1425,
      "step": 482
    },
    {
      "epoch": 0.44805194805194803,
      "grad_norm": 2.7280144691467285,
      "learning_rate": 1.3487744143298822e-05,
      "loss": 0.0783,
      "step": 483
    },
    {
      "epoch": 0.4489795918367347,
      "grad_norm": 3.562812566757202,
      "learning_rate": 1.345737207202023e-05,
      "loss": 0.1569,
      "step": 484
    },
    {
      "epoch": 0.44990723562152135,
      "grad_norm": 5.523044109344482,
      "learning_rate": 1.3426963734544601e-05,
      "loss": 0.2227,
      "step": 485
    },
    {
      "epoch": 0.45083487940630795,
      "grad_norm": 4.155531883239746,
      "learning_rate": 1.3396519449841006e-05,
      "loss": 0.2297,
      "step": 486
    },
    {
      "epoch": 0.4517625231910946,
      "grad_norm": 2.8421530723571777,
      "learning_rate": 1.3366039537255589e-05,
      "loss": 0.1699,
      "step": 487
    },
    {
      "epoch": 0.45269016697588127,
      "grad_norm": 3.845489263534546,
      "learning_rate": 1.3335524316508208e-05,
      "loss": 0.1773,
      "step": 488
    },
    {
      "epoch": 0.4536178107606679,
      "grad_norm": 3.0157673358917236,
      "learning_rate": 1.3304974107689088e-05,
      "loss": 0.1379,
      "step": 489
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 2.74364972114563,
      "learning_rate": 1.3274389231255466e-05,
      "loss": 0.1265,
      "step": 490
    },
    {
      "epoch": 0.4554730983302412,
      "grad_norm": 6.820478439331055,
      "learning_rate": 1.3243770008028225e-05,
      "loss": 0.1849,
      "step": 491
    },
    {
      "epoch": 0.45640074211502785,
      "grad_norm": 2.741809368133545,
      "learning_rate": 1.3213116759188525e-05,
      "loss": 0.1295,
      "step": 492
    },
    {
      "epoch": 0.45732838589981445,
      "grad_norm": 3.473961353302002,
      "learning_rate": 1.3182429806274442e-05,
      "loss": 0.099,
      "step": 493
    },
    {
      "epoch": 0.4582560296846011,
      "grad_norm": 5.271576881408691,
      "learning_rate": 1.3151709471177589e-05,
      "loss": 0.1753,
      "step": 494
    },
    {
      "epoch": 0.45918367346938777,
      "grad_norm": 6.4196577072143555,
      "learning_rate": 1.3120956076139746e-05,
      "loss": 0.2568,
      "step": 495
    },
    {
      "epoch": 0.4601113172541744,
      "grad_norm": 5.339606761932373,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 0.1535,
      "step": 496
    },
    {
      "epoch": 0.461038961038961,
      "grad_norm": 4.3615593910217285,
      "learning_rate": 1.305935139693874e-05,
      "loss": 0.1362,
      "step": 497
    },
    {
      "epoch": 0.4619666048237477,
      "grad_norm": 4.690557956695557,
      "learning_rate": 1.3028500758979507e-05,
      "loss": 0.1776,
      "step": 498
    },
    {
      "epoch": 0.46289424860853434,
      "grad_norm": 4.32938814163208,
      "learning_rate": 1.299761835348038e-05,
      "loss": 0.1429,
      "step": 499
    },
    {
      "epoch": 0.46382189239332094,
      "grad_norm": 3.8397958278656006,
      "learning_rate": 1.296670450438317e-05,
      "loss": 0.1904,
      "step": 500
    },
    {
      "epoch": 0.46382189239332094,
      "eval_accuracy": 0.8403547671840355,
      "eval_f1": 0.6381909547738693,
      "eval_loss": 0.3388740122318268,
      "eval_precision": 0.8758620689655172,
      "eval_recall": 0.5019762845849802,
      "eval_runtime": 48.3395,
      "eval_samples_per_second": 5.71,
      "eval_steps_per_second": 0.186,
      "step": 500
    },
    {
      "epoch": 0.4647495361781076,
      "grad_norm": 4.0140509605407715,
      "learning_rate": 1.2935759535959528e-05,
      "loss": 0.2093,
      "step": 501
    },
    {
      "epoch": 0.46567717996289426,
      "grad_norm": 2.7800872325897217,
      "learning_rate": 1.2904783772807534e-05,
      "loss": 0.1333,
      "step": 502
    },
    {
      "epoch": 0.46660482374768086,
      "grad_norm": 4.866140842437744,
      "learning_rate": 1.2873777539848284e-05,
      "loss": 0.2078,
      "step": 503
    },
    {
      "epoch": 0.4675324675324675,
      "grad_norm": 4.730177879333496,
      "learning_rate": 1.2842741162322487e-05,
      "loss": 0.1834,
      "step": 504
    },
    {
      "epoch": 0.4684601113172542,
      "grad_norm": 3.826939582824707,
      "learning_rate": 1.2811674965787058e-05,
      "loss": 0.1712,
      "step": 505
    },
    {
      "epoch": 0.46938775510204084,
      "grad_norm": 16.19306755065918,
      "learning_rate": 1.2780579276111702e-05,
      "loss": 0.2195,
      "step": 506
    },
    {
      "epoch": 0.47031539888682744,
      "grad_norm": 4.020465850830078,
      "learning_rate": 1.2749454419475486e-05,
      "loss": 0.1387,
      "step": 507
    },
    {
      "epoch": 0.4712430426716141,
      "grad_norm": 3.083519697189331,
      "learning_rate": 1.2718300722363431e-05,
      "loss": 0.1595,
      "step": 508
    },
    {
      "epoch": 0.47217068645640076,
      "grad_norm": 3.982968807220459,
      "learning_rate": 1.2687118511563075e-05,
      "loss": 0.1304,
      "step": 509
    },
    {
      "epoch": 0.47309833024118736,
      "grad_norm": 4.213962554931641,
      "learning_rate": 1.2655908114161053e-05,
      "loss": 0.1269,
      "step": 510
    },
    {
      "epoch": 0.474025974025974,
      "grad_norm": 3.9727156162261963,
      "learning_rate": 1.2624669857539669e-05,
      "loss": 0.1327,
      "step": 511
    },
    {
      "epoch": 0.4749536178107607,
      "grad_norm": 4.792732238769531,
      "learning_rate": 1.2593404069373452e-05,
      "loss": 0.1782,
      "step": 512
    },
    {
      "epoch": 0.47588126159554733,
      "grad_norm": 3.0668811798095703,
      "learning_rate": 1.2562111077625723e-05,
      "loss": 0.1568,
      "step": 513
    },
    {
      "epoch": 0.47680890538033394,
      "grad_norm": 4.204139709472656,
      "learning_rate": 1.2530791210545163e-05,
      "loss": 0.149,
      "step": 514
    },
    {
      "epoch": 0.4777365491651206,
      "grad_norm": 4.396578788757324,
      "learning_rate": 1.2499444796662354e-05,
      "loss": 0.1943,
      "step": 515
    },
    {
      "epoch": 0.47866419294990725,
      "grad_norm": 8.477376937866211,
      "learning_rate": 1.2468072164786342e-05,
      "loss": 0.3153,
      "step": 516
    },
    {
      "epoch": 0.47959183673469385,
      "grad_norm": 4.493762016296387,
      "learning_rate": 1.2436673644001196e-05,
      "loss": 0.2028,
      "step": 517
    },
    {
      "epoch": 0.4805194805194805,
      "grad_norm": 3.7687320709228516,
      "learning_rate": 1.2405249563662539e-05,
      "loss": 0.1834,
      "step": 518
    },
    {
      "epoch": 0.48144712430426717,
      "grad_norm": 5.828054428100586,
      "learning_rate": 1.23738002533941e-05,
      "loss": 0.1587,
      "step": 519
    },
    {
      "epoch": 0.48237476808905383,
      "grad_norm": 4.38277006149292,
      "learning_rate": 1.2342326043084268e-05,
      "loss": 0.1809,
      "step": 520
    },
    {
      "epoch": 0.48237476808905383,
      "eval_accuracy": 0.8458980044345898,
      "eval_f1": 0.6584766584766585,
      "eval_loss": 0.3318649232387543,
      "eval_precision": 0.8701298701298701,
      "eval_recall": 0.5296442687747036,
      "eval_runtime": 46.7049,
      "eval_samples_per_second": 5.909,
      "eval_steps_per_second": 0.193,
      "step": 520
    },
    {
      "epoch": 0.48330241187384043,
      "grad_norm": 4.514082908630371,
      "learning_rate": 1.2310827262882614e-05,
      "loss": 0.1759,
      "step": 521
    },
    {
      "epoch": 0.4842300556586271,
      "grad_norm": 3.4471170902252197,
      "learning_rate": 1.2279304243196438e-05,
      "loss": 0.1364,
      "step": 522
    },
    {
      "epoch": 0.48515769944341375,
      "grad_norm": 2.6771576404571533,
      "learning_rate": 1.2247757314687296e-05,
      "loss": 0.146,
      "step": 523
    },
    {
      "epoch": 0.48608534322820035,
      "grad_norm": 3.6538710594177246,
      "learning_rate": 1.2216186808267544e-05,
      "loss": 0.2009,
      "step": 524
    },
    {
      "epoch": 0.487012987012987,
      "grad_norm": 4.4636149406433105,
      "learning_rate": 1.2184593055096853e-05,
      "loss": 0.1474,
      "step": 525
    },
    {
      "epoch": 0.48794063079777367,
      "grad_norm": 5.249742031097412,
      "learning_rate": 1.215297638657875e-05,
      "loss": 0.1564,
      "step": 526
    },
    {
      "epoch": 0.48886827458256027,
      "grad_norm": 6.001680850982666,
      "learning_rate": 1.2121337134357121e-05,
      "loss": 0.1718,
      "step": 527
    },
    {
      "epoch": 0.4897959183673469,
      "grad_norm": 6.546911716461182,
      "learning_rate": 1.2089675630312755e-05,
      "loss": 0.2193,
      "step": 528
    },
    {
      "epoch": 0.4907235621521336,
      "grad_norm": 2.6112513542175293,
      "learning_rate": 1.2057992206559837e-05,
      "loss": 0.1295,
      "step": 529
    },
    {
      "epoch": 0.49165120593692024,
      "grad_norm": 3.9656717777252197,
      "learning_rate": 1.2026287195442503e-05,
      "loss": 0.1707,
      "step": 530
    },
    {
      "epoch": 0.49257884972170685,
      "grad_norm": 3.8426477909088135,
      "learning_rate": 1.199456092953131e-05,
      "loss": 0.1768,
      "step": 531
    },
    {
      "epoch": 0.4935064935064935,
      "grad_norm": 3.001831531524658,
      "learning_rate": 1.1962813741619777e-05,
      "loss": 0.1839,
      "step": 532
    },
    {
      "epoch": 0.49443413729128016,
      "grad_norm": 5.149347305297852,
      "learning_rate": 1.1931045964720882e-05,
      "loss": 0.2559,
      "step": 533
    },
    {
      "epoch": 0.49536178107606677,
      "grad_norm": 3.0468552112579346,
      "learning_rate": 1.189925793206357e-05,
      "loss": 0.1408,
      "step": 534
    },
    {
      "epoch": 0.4962894248608534,
      "grad_norm": 4.5860490798950195,
      "learning_rate": 1.1867449977089264e-05,
      "loss": 0.1945,
      "step": 535
    },
    {
      "epoch": 0.4972170686456401,
      "grad_norm": 3.8901429176330566,
      "learning_rate": 1.1835622433448361e-05,
      "loss": 0.2126,
      "step": 536
    },
    {
      "epoch": 0.49814471243042674,
      "grad_norm": 4.597271919250488,
      "learning_rate": 1.1803775634996735e-05,
      "loss": 0.1977,
      "step": 537
    },
    {
      "epoch": 0.49907235621521334,
      "grad_norm": 3.079770803451538,
      "learning_rate": 1.177190991579223e-05,
      "loss": 0.1758,
      "step": 538
    },
    {
      "epoch": 0.5,
      "grad_norm": 4.214216709136963,
      "learning_rate": 1.174002561009116e-05,
      "loss": 0.141,
      "step": 539
    },
    {
      "epoch": 0.5009276437847866,
      "grad_norm": 5.213557243347168,
      "learning_rate": 1.1708123052344803e-05,
      "loss": 0.1605,
      "step": 540
    },
    {
      "epoch": 0.5009276437847866,
      "eval_accuracy": 0.8614190687361419,
      "eval_f1": 0.7072599531615925,
      "eval_loss": 0.30164089798927307,
      "eval_precision": 0.867816091954023,
      "eval_recall": 0.5968379446640316,
      "eval_runtime": 47.208,
      "eval_samples_per_second": 5.846,
      "eval_steps_per_second": 0.191,
      "step": 540
    },
    {
      "epoch": 0.5018552875695733,
      "grad_norm": 2.1639671325683594,
      "learning_rate": 1.1676202577195901e-05,
      "loss": 0.0809,
      "step": 541
    },
    {
      "epoch": 0.5027829313543599,
      "grad_norm": 4.442990303039551,
      "learning_rate": 1.164426451947513e-05,
      "loss": 0.1677,
      "step": 542
    },
    {
      "epoch": 0.5037105751391465,
      "grad_norm": 3.968435049057007,
      "learning_rate": 1.1612309214197599e-05,
      "loss": 0.2114,
      "step": 543
    },
    {
      "epoch": 0.5046382189239332,
      "grad_norm": 9.67383098602295,
      "learning_rate": 1.1580336996559343e-05,
      "loss": 0.2159,
      "step": 544
    },
    {
      "epoch": 0.5055658627087198,
      "grad_norm": 3.427710771560669,
      "learning_rate": 1.1548348201933799e-05,
      "loss": 0.0846,
      "step": 545
    },
    {
      "epoch": 0.5064935064935064,
      "grad_norm": 3.03241229057312,
      "learning_rate": 1.151634316586828e-05,
      "loss": 0.1195,
      "step": 546
    },
    {
      "epoch": 0.5074211502782932,
      "grad_norm": 5.138626575469971,
      "learning_rate": 1.1484322224080474e-05,
      "loss": 0.1542,
      "step": 547
    },
    {
      "epoch": 0.5083487940630798,
      "grad_norm": 4.37513542175293,
      "learning_rate": 1.1452285712454905e-05,
      "loss": 0.2118,
      "step": 548
    },
    {
      "epoch": 0.5092764378478665,
      "grad_norm": 4.746356010437012,
      "learning_rate": 1.1420233967039423e-05,
      "loss": 0.1456,
      "step": 549
    },
    {
      "epoch": 0.5102040816326531,
      "grad_norm": 5.190648555755615,
      "learning_rate": 1.138816732404167e-05,
      "loss": 0.1921,
      "step": 550
    },
    {
      "epoch": 0.5111317254174397,
      "grad_norm": 3.955061197280884,
      "learning_rate": 1.1356086119825553e-05,
      "loss": 0.1964,
      "step": 551
    },
    {
      "epoch": 0.5120593692022264,
      "grad_norm": 7.773352146148682,
      "learning_rate": 1.1323990690907734e-05,
      "loss": 0.2178,
      "step": 552
    },
    {
      "epoch": 0.512987012987013,
      "grad_norm": 3.211651563644409,
      "learning_rate": 1.1291881373954066e-05,
      "loss": 0.1859,
      "step": 553
    },
    {
      "epoch": 0.5139146567717996,
      "grad_norm": 3.536742687225342,
      "learning_rate": 1.1259758505776092e-05,
      "loss": 0.1949,
      "step": 554
    },
    {
      "epoch": 0.5148423005565863,
      "grad_norm": 4.817080974578857,
      "learning_rate": 1.1227622423327501e-05,
      "loss": 0.2482,
      "step": 555
    },
    {
      "epoch": 0.5157699443413729,
      "grad_norm": 4.828971862792969,
      "learning_rate": 1.119547346370059e-05,
      "loss": 0.216,
      "step": 556
    },
    {
      "epoch": 0.5166975881261595,
      "grad_norm": 4.580413818359375,
      "learning_rate": 1.1163311964122733e-05,
      "loss": 0.2267,
      "step": 557
    },
    {
      "epoch": 0.5176252319109462,
      "grad_norm": 2.9997427463531494,
      "learning_rate": 1.1131138261952845e-05,
      "loss": 0.1556,
      "step": 558
    },
    {
      "epoch": 0.5185528756957328,
      "grad_norm": 2.876847982406616,
      "learning_rate": 1.109895269467783e-05,
      "loss": 0.1551,
      "step": 559
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 6.003294467926025,
      "learning_rate": 1.1066755599909065e-05,
      "loss": 0.2123,
      "step": 560
    },
    {
      "epoch": 0.5194805194805194,
      "eval_accuracy": 0.8603104212860311,
      "eval_f1": 0.7136363636363636,
      "eval_loss": 0.2982672452926636,
      "eval_precision": 0.839572192513369,
      "eval_recall": 0.6205533596837944,
      "eval_runtime": 48.6549,
      "eval_samples_per_second": 5.673,
      "eval_steps_per_second": 0.185,
      "step": 560
    },
    {
      "epoch": 0.5204081632653061,
      "grad_norm": 3.7513365745544434,
      "learning_rate": 1.1034547315378838e-05,
      "loss": 0.1808,
      "step": 561
    },
    {
      "epoch": 0.5213358070500927,
      "grad_norm": 2.755664110183716,
      "learning_rate": 1.1002328178936813e-05,
      "loss": 0.1272,
      "step": 562
    },
    {
      "epoch": 0.5222634508348795,
      "grad_norm": 6.458003520965576,
      "learning_rate": 1.0970098528546482e-05,
      "loss": 0.161,
      "step": 563
    },
    {
      "epoch": 0.5231910946196661,
      "grad_norm": 3.156869649887085,
      "learning_rate": 1.0937858702281631e-05,
      "loss": 0.1423,
      "step": 564
    },
    {
      "epoch": 0.5241187384044527,
      "grad_norm": 4.826041221618652,
      "learning_rate": 1.090560903832278e-05,
      "loss": 0.1717,
      "step": 565
    },
    {
      "epoch": 0.5250463821892394,
      "grad_norm": 2.8493692874908447,
      "learning_rate": 1.087334987495364e-05,
      "loss": 0.147,
      "step": 566
    },
    {
      "epoch": 0.525974025974026,
      "grad_norm": 3.3068854808807373,
      "learning_rate": 1.0841081550557577e-05,
      "loss": 0.1084,
      "step": 567
    },
    {
      "epoch": 0.5269016697588126,
      "grad_norm": 3.908871650695801,
      "learning_rate": 1.0808804403614044e-05,
      "loss": 0.1484,
      "step": 568
    },
    {
      "epoch": 0.5278293135435993,
      "grad_norm": 3.8984129428863525,
      "learning_rate": 1.0776518772695035e-05,
      "loss": 0.1883,
      "step": 569
    },
    {
      "epoch": 0.5287569573283859,
      "grad_norm": 3.58467960357666,
      "learning_rate": 1.0744224996461541e-05,
      "loss": 0.1238,
      "step": 570
    },
    {
      "epoch": 0.5296846011131725,
      "grad_norm": 5.206255912780762,
      "learning_rate": 1.0711923413659995e-05,
      "loss": 0.2008,
      "step": 571
    },
    {
      "epoch": 0.5306122448979592,
      "grad_norm": 2.4864425659179688,
      "learning_rate": 1.0679614363118718e-05,
      "loss": 0.1181,
      "step": 572
    },
    {
      "epoch": 0.5315398886827458,
      "grad_norm": 3.949312686920166,
      "learning_rate": 1.0647298183744359e-05,
      "loss": 0.1927,
      "step": 573
    },
    {
      "epoch": 0.5324675324675324,
      "grad_norm": 6.005074501037598,
      "learning_rate": 1.061497521451835e-05,
      "loss": 0.1936,
      "step": 574
    },
    {
      "epoch": 0.5333951762523191,
      "grad_norm": 4.429588317871094,
      "learning_rate": 1.0582645794493337e-05,
      "loss": 0.2031,
      "step": 575
    },
    {
      "epoch": 0.5343228200371057,
      "grad_norm": 4.36995792388916,
      "learning_rate": 1.055031026278965e-05,
      "loss": 0.1846,
      "step": 576
    },
    {
      "epoch": 0.5352504638218923,
      "grad_norm": 4.059164524078369,
      "learning_rate": 1.0517968958591705e-05,
      "loss": 0.1681,
      "step": 577
    },
    {
      "epoch": 0.536178107606679,
      "grad_norm": 4.211386203765869,
      "learning_rate": 1.0485622221144485e-05,
      "loss": 0.1296,
      "step": 578
    },
    {
      "epoch": 0.5371057513914657,
      "grad_norm": 4.114365100860596,
      "learning_rate": 1.0453270389749956e-05,
      "loss": 0.164,
      "step": 579
    },
    {
      "epoch": 0.5380333951762524,
      "grad_norm": 7.943957805633545,
      "learning_rate": 1.0420913803763522e-05,
      "loss": 0.2279,
      "step": 580
    },
    {
      "epoch": 0.5380333951762524,
      "eval_accuracy": 0.8558758314855875,
      "eval_f1": 0.7018348623853211,
      "eval_loss": 0.30458346009254456,
      "eval_precision": 0.8360655737704918,
      "eval_recall": 0.6047430830039525,
      "eval_runtime": 46.8877,
      "eval_samples_per_second": 5.886,
      "eval_steps_per_second": 0.192,
      "step": 580
    },
    {
      "epoch": 0.538961038961039,
      "grad_norm": 7.277109146118164,
      "learning_rate": 1.0388552802590461e-05,
      "loss": 0.0867,
      "step": 581
    },
    {
      "epoch": 0.5398886827458256,
      "grad_norm": 3.722276449203491,
      "learning_rate": 1.0356187725682359e-05,
      "loss": 0.1233,
      "step": 582
    },
    {
      "epoch": 0.5408163265306123,
      "grad_norm": 4.75911283493042,
      "learning_rate": 1.0323818912533561e-05,
      "loss": 0.2018,
      "step": 583
    },
    {
      "epoch": 0.5417439703153989,
      "grad_norm": 5.309391498565674,
      "learning_rate": 1.0291446702677598e-05,
      "loss": 0.1853,
      "step": 584
    },
    {
      "epoch": 0.5426716141001855,
      "grad_norm": 3.6361756324768066,
      "learning_rate": 1.0259071435683636e-05,
      "loss": 0.1594,
      "step": 585
    },
    {
      "epoch": 0.5435992578849722,
      "grad_norm": 8.379057884216309,
      "learning_rate": 1.02266934511529e-05,
      "loss": 0.1496,
      "step": 586
    },
    {
      "epoch": 0.5445269016697588,
      "grad_norm": 6.6115593910217285,
      "learning_rate": 1.0194313088715135e-05,
      "loss": 0.1887,
      "step": 587
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 3.5273900032043457,
      "learning_rate": 1.0161930688025018e-05,
      "loss": 0.1549,
      "step": 588
    },
    {
      "epoch": 0.5463821892393321,
      "grad_norm": 4.194179058074951,
      "learning_rate": 1.0129546588758605e-05,
      "loss": 0.1748,
      "step": 589
    },
    {
      "epoch": 0.5473098330241187,
      "grad_norm": 3.131457805633545,
      "learning_rate": 1.0097161130609774e-05,
      "loss": 0.1319,
      "step": 590
    },
    {
      "epoch": 0.5482374768089053,
      "grad_norm": 4.083921909332275,
      "learning_rate": 1.0064774653286662e-05,
      "loss": 0.1759,
      "step": 591
    },
    {
      "epoch": 0.549165120593692,
      "grad_norm": 3.384917736053467,
      "learning_rate": 1.003238749650809e-05,
      "loss": 0.1434,
      "step": 592
    },
    {
      "epoch": 0.5500927643784786,
      "grad_norm": 2.5680859088897705,
      "learning_rate": 1e-05,
      "loss": 0.1626,
      "step": 593
    },
    {
      "epoch": 0.5510204081632653,
      "grad_norm": 3.510484457015991,
      "learning_rate": 9.967612503491915e-06,
      "loss": 0.1701,
      "step": 594
    },
    {
      "epoch": 0.551948051948052,
      "grad_norm": 5.625200271606445,
      "learning_rate": 9.935225346713341e-06,
      "loss": 0.1486,
      "step": 595
    },
    {
      "epoch": 0.5528756957328386,
      "grad_norm": 5.352198123931885,
      "learning_rate": 9.90283886939023e-06,
      "loss": 0.1158,
      "step": 596
    },
    {
      "epoch": 0.5538033395176253,
      "grad_norm": 3.0487513542175293,
      "learning_rate": 9.870453411241399e-06,
      "loss": 0.1339,
      "step": 597
    },
    {
      "epoch": 0.5547309833024119,
      "grad_norm": 3.2191503047943115,
      "learning_rate": 9.838069311974986e-06,
      "loss": 0.1147,
      "step": 598
    },
    {
      "epoch": 0.5556586270871985,
      "grad_norm": 4.020503520965576,
      "learning_rate": 9.805686911284867e-06,
      "loss": 0.1163,
      "step": 599
    },
    {
      "epoch": 0.5565862708719852,
      "grad_norm": 6.643052101135254,
      "learning_rate": 9.773306548847102e-06,
      "loss": 0.2224,
      "step": 600
    },
    {
      "epoch": 0.5565862708719852,
      "eval_accuracy": 0.8381374722838137,
      "eval_f1": 0.6313131313131313,
      "eval_loss": 0.3394555449485779,
      "eval_precision": 0.8741258741258742,
      "eval_recall": 0.49407114624505927,
      "eval_runtime": 48.1127,
      "eval_samples_per_second": 5.737,
      "eval_steps_per_second": 0.187,
      "step": 600
    },
    {
      "epoch": 0.5575139146567718,
      "grad_norm": 4.177931308746338,
      "learning_rate": 9.740928564316369e-06,
      "loss": 0.1734,
      "step": 601
    },
    {
      "epoch": 0.5584415584415584,
      "grad_norm": 6.294393062591553,
      "learning_rate": 9.708553297322407e-06,
      "loss": 0.1923,
      "step": 602
    },
    {
      "epoch": 0.5593692022263451,
      "grad_norm": 3.275909662246704,
      "learning_rate": 9.676181087466444e-06,
      "loss": 0.1662,
      "step": 603
    },
    {
      "epoch": 0.5602968460111317,
      "grad_norm": 3.7851905822753906,
      "learning_rate": 9.643812274317644e-06,
      "loss": 0.1521,
      "step": 604
    },
    {
      "epoch": 0.5612244897959183,
      "grad_norm": 4.724743366241455,
      "learning_rate": 9.611447197409544e-06,
      "loss": 0.1713,
      "step": 605
    },
    {
      "epoch": 0.562152133580705,
      "grad_norm": 6.553765773773193,
      "learning_rate": 9.579086196236483e-06,
      "loss": 0.1596,
      "step": 606
    },
    {
      "epoch": 0.5630797773654916,
      "grad_norm": 3.5295910835266113,
      "learning_rate": 9.54672961025005e-06,
      "loss": 0.1436,
      "step": 607
    },
    {
      "epoch": 0.5640074211502782,
      "grad_norm": 4.828715801239014,
      "learning_rate": 9.514377778855521e-06,
      "loss": 0.2361,
      "step": 608
    },
    {
      "epoch": 0.564935064935065,
      "grad_norm": 6.0731072425842285,
      "learning_rate": 9.482031041408296e-06,
      "loss": 0.165,
      "step": 609
    },
    {
      "epoch": 0.5658627087198516,
      "grad_norm": 8.083799362182617,
      "learning_rate": 9.449689737210352e-06,
      "loss": 0.1995,
      "step": 610
    },
    {
      "epoch": 0.5667903525046383,
      "grad_norm": 3.7561042308807373,
      "learning_rate": 9.417354205506663e-06,
      "loss": 0.214,
      "step": 611
    },
    {
      "epoch": 0.5677179962894249,
      "grad_norm": 4.848057746887207,
      "learning_rate": 9.385024785481653e-06,
      "loss": 0.2019,
      "step": 612
    },
    {
      "epoch": 0.5686456400742115,
      "grad_norm": 5.188536167144775,
      "learning_rate": 9.352701816255643e-06,
      "loss": 0.1568,
      "step": 613
    },
    {
      "epoch": 0.5695732838589982,
      "grad_norm": 2.897571325302124,
      "learning_rate": 9.320385636881283e-06,
      "loss": 0.1241,
      "step": 614
    },
    {
      "epoch": 0.5705009276437848,
      "grad_norm": 5.466006278991699,
      "learning_rate": 9.288076586340005e-06,
      "loss": 0.195,
      "step": 615
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 3.484766960144043,
      "learning_rate": 9.255775003538462e-06,
      "loss": 0.1419,
      "step": 616
    },
    {
      "epoch": 0.5723562152133581,
      "grad_norm": 5.067159175872803,
      "learning_rate": 9.22348122730497e-06,
      "loss": 0.1938,
      "step": 617
    },
    {
      "epoch": 0.5732838589981447,
      "grad_norm": 4.161076545715332,
      "learning_rate": 9.19119559638596e-06,
      "loss": 0.1925,
      "step": 618
    },
    {
      "epoch": 0.5742115027829313,
      "grad_norm": 3.2418394088745117,
      "learning_rate": 9.158918449442425e-06,
      "loss": 0.1592,
      "step": 619
    },
    {
      "epoch": 0.575139146567718,
      "grad_norm": 5.799723148345947,
      "learning_rate": 9.126650125046361e-06,
      "loss": 0.1655,
      "step": 620
    },
    {
      "epoch": 0.575139146567718,
      "eval_accuracy": 0.835920177383592,
      "eval_f1": 0.6224489795918368,
      "eval_loss": 0.3387525677680969,
      "eval_precision": 0.8776978417266187,
      "eval_recall": 0.48221343873517786,
      "eval_runtime": 47.1826,
      "eval_samples_per_second": 5.85,
      "eval_steps_per_second": 0.191,
      "step": 620
    },
    {
      "epoch": 0.5760667903525046,
      "grad_norm": 4.049962997436523,
      "learning_rate": 9.094390961677223e-06,
      "loss": 0.1364,
      "step": 621
    },
    {
      "epoch": 0.5769944341372912,
      "grad_norm": 3.7945103645324707,
      "learning_rate": 9.062141297718372e-06,
      "loss": 0.18,
      "step": 622
    },
    {
      "epoch": 0.577922077922078,
      "grad_norm": 3.9919049739837646,
      "learning_rate": 9.02990147145352e-06,
      "loss": 0.1833,
      "step": 623
    },
    {
      "epoch": 0.5788497217068646,
      "grad_norm": 2.300546407699585,
      "learning_rate": 8.99767182106319e-06,
      "loss": 0.0625,
      "step": 624
    },
    {
      "epoch": 0.5797773654916512,
      "grad_norm": 4.982729911804199,
      "learning_rate": 8.965452684621164e-06,
      "loss": 0.1884,
      "step": 625
    },
    {
      "epoch": 0.5807050092764379,
      "grad_norm": 4.047850131988525,
      "learning_rate": 8.933244400090937e-06,
      "loss": 0.1206,
      "step": 626
    },
    {
      "epoch": 0.5816326530612245,
      "grad_norm": 4.123579978942871,
      "learning_rate": 8.901047305322172e-06,
      "loss": 0.1503,
      "step": 627
    },
    {
      "epoch": 0.5825602968460112,
      "grad_norm": 4.2010273933410645,
      "learning_rate": 8.868861738047158e-06,
      "loss": 0.1311,
      "step": 628
    },
    {
      "epoch": 0.5834879406307978,
      "grad_norm": 4.511427402496338,
      "learning_rate": 8.836688035877268e-06,
      "loss": 0.1521,
      "step": 629
    },
    {
      "epoch": 0.5844155844155844,
      "grad_norm": 5.0462775230407715,
      "learning_rate": 8.804526536299413e-06,
      "loss": 0.1746,
      "step": 630
    },
    {
      "epoch": 0.5853432282003711,
      "grad_norm": 6.308788299560547,
      "learning_rate": 8.772377576672502e-06,
      "loss": 0.2369,
      "step": 631
    },
    {
      "epoch": 0.5862708719851577,
      "grad_norm": 4.165151596069336,
      "learning_rate": 8.740241494223911e-06,
      "loss": 0.2034,
      "step": 632
    },
    {
      "epoch": 0.5871985157699443,
      "grad_norm": 4.502403259277344,
      "learning_rate": 8.708118626045939e-06,
      "loss": 0.1893,
      "step": 633
    },
    {
      "epoch": 0.588126159554731,
      "grad_norm": 3.4875142574310303,
      "learning_rate": 8.676009309092273e-06,
      "loss": 0.1328,
      "step": 634
    },
    {
      "epoch": 0.5890538033395176,
      "grad_norm": 4.179616928100586,
      "learning_rate": 8.643913880174449e-06,
      "loss": 0.1466,
      "step": 635
    },
    {
      "epoch": 0.5899814471243042,
      "grad_norm": 3.073174476623535,
      "learning_rate": 8.611832675958335e-06,
      "loss": 0.1269,
      "step": 636
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 3.9491851329803467,
      "learning_rate": 8.579766032960582e-06,
      "loss": 0.1247,
      "step": 637
    },
    {
      "epoch": 0.5918367346938775,
      "grad_norm": 3.502418041229248,
      "learning_rate": 8.5477142875451e-06,
      "loss": 0.1536,
      "step": 638
    },
    {
      "epoch": 0.5927643784786641,
      "grad_norm": 5.294571876525879,
      "learning_rate": 8.515677775919528e-06,
      "loss": 0.213,
      "step": 639
    },
    {
      "epoch": 0.5936920222634509,
      "grad_norm": 3.3282008171081543,
      "learning_rate": 8.48365683413172e-06,
      "loss": 0.1468,
      "step": 640
    },
    {
      "epoch": 0.5936920222634509,
      "eval_accuracy": 0.8592017738359202,
      "eval_f1": 0.7093821510297483,
      "eval_loss": 0.3021511137485504,
      "eval_precision": 0.842391304347826,
      "eval_recall": 0.6126482213438735,
      "eval_runtime": 46.8153,
      "eval_samples_per_second": 5.896,
      "eval_steps_per_second": 0.192,
      "step": 640
    },
    {
      "epoch": 0.5946196660482375,
      "grad_norm": 5.158597946166992,
      "learning_rate": 8.451651798066203e-06,
      "loss": 0.2459,
      "step": 641
    },
    {
      "epoch": 0.5955473098330241,
      "grad_norm": 7.210265159606934,
      "learning_rate": 8.419663003440657e-06,
      "loss": 0.1745,
      "step": 642
    },
    {
      "epoch": 0.5964749536178108,
      "grad_norm": 4.469946384429932,
      "learning_rate": 8.387690785802403e-06,
      "loss": 0.1879,
      "step": 643
    },
    {
      "epoch": 0.5974025974025974,
      "grad_norm": 3.5130228996276855,
      "learning_rate": 8.355735480524874e-06,
      "loss": 0.1453,
      "step": 644
    },
    {
      "epoch": 0.5983302411873841,
      "grad_norm": 3.8892977237701416,
      "learning_rate": 8.3237974228041e-06,
      "loss": 0.1852,
      "step": 645
    },
    {
      "epoch": 0.5992578849721707,
      "grad_norm": 4.912310600280762,
      "learning_rate": 8.291876947655197e-06,
      "loss": 0.1595,
      "step": 646
    },
    {
      "epoch": 0.6001855287569573,
      "grad_norm": 3.8313469886779785,
      "learning_rate": 8.259974389908842e-06,
      "loss": 0.1207,
      "step": 647
    },
    {
      "epoch": 0.601113172541744,
      "grad_norm": 4.376918792724609,
      "learning_rate": 8.228090084207773e-06,
      "loss": 0.2188,
      "step": 648
    },
    {
      "epoch": 0.6020408163265306,
      "grad_norm": 4.086894989013672,
      "learning_rate": 8.196224365003267e-06,
      "loss": 0.1806,
      "step": 649
    },
    {
      "epoch": 0.6029684601113172,
      "grad_norm": 2.9185261726379395,
      "learning_rate": 8.16437756655164e-06,
      "loss": 0.1301,
      "step": 650
    },
    {
      "epoch": 0.6038961038961039,
      "grad_norm": 5.638646125793457,
      "learning_rate": 8.132550022910737e-06,
      "loss": 0.2069,
      "step": 651
    },
    {
      "epoch": 0.6048237476808905,
      "grad_norm": 6.044648170471191,
      "learning_rate": 8.100742067936432e-06,
      "loss": 0.2543,
      "step": 652
    },
    {
      "epoch": 0.6057513914656771,
      "grad_norm": 5.261450290679932,
      "learning_rate": 8.068954035279121e-06,
      "loss": 0.1861,
      "step": 653
    },
    {
      "epoch": 0.6066790352504638,
      "grad_norm": 2.6060245037078857,
      "learning_rate": 8.037186258380226e-06,
      "loss": 0.1102,
      "step": 654
    },
    {
      "epoch": 0.6076066790352505,
      "grad_norm": 5.192462921142578,
      "learning_rate": 8.005439070468692e-06,
      "loss": 0.1196,
      "step": 655
    },
    {
      "epoch": 0.608534322820037,
      "grad_norm": 4.267360210418701,
      "learning_rate": 7.9737128045575e-06,
      "loss": 0.1549,
      "step": 656
    },
    {
      "epoch": 0.6094619666048238,
      "grad_norm": 2.9216721057891846,
      "learning_rate": 7.942007793440165e-06,
      "loss": 0.1326,
      "step": 657
    },
    {
      "epoch": 0.6103896103896104,
      "grad_norm": 3.592209577560425,
      "learning_rate": 7.91032436968725e-06,
      "loss": 0.1399,
      "step": 658
    },
    {
      "epoch": 0.6113172541743971,
      "grad_norm": 3.6594440937042236,
      "learning_rate": 7.87866286564288e-06,
      "loss": 0.1223,
      "step": 659
    },
    {
      "epoch": 0.6122448979591837,
      "grad_norm": 6.019983291625977,
      "learning_rate": 7.847023613421251e-06,
      "loss": 0.1421,
      "step": 660
    },
    {
      "epoch": 0.6122448979591837,
      "eval_accuracy": 0.843680709534368,
      "eval_f1": 0.6483790523690773,
      "eval_loss": 0.3296959400177002,
      "eval_precision": 0.8783783783783784,
      "eval_recall": 0.5138339920948617,
      "eval_runtime": 47.6918,
      "eval_samples_per_second": 5.787,
      "eval_steps_per_second": 0.189,
      "step": 660
    },
    {
      "epoch": 0.6131725417439703,
      "grad_norm": 3.82082462310791,
      "learning_rate": 7.815406944903148e-06,
      "loss": 0.1369,
      "step": 661
    },
    {
      "epoch": 0.614100185528757,
      "grad_norm": 3.763209819793701,
      "learning_rate": 7.78381319173246e-06,
      "loss": 0.1345,
      "step": 662
    },
    {
      "epoch": 0.6150278293135436,
      "grad_norm": 5.018528938293457,
      "learning_rate": 7.752242685312709e-06,
      "loss": 0.1762,
      "step": 663
    },
    {
      "epoch": 0.6159554730983302,
      "grad_norm": 3.500230073928833,
      "learning_rate": 7.720695756803569e-06,
      "loss": 0.0632,
      "step": 664
    },
    {
      "epoch": 0.6168831168831169,
      "grad_norm": 4.73206090927124,
      "learning_rate": 7.689172737117389e-06,
      "loss": 0.1771,
      "step": 665
    },
    {
      "epoch": 0.6178107606679035,
      "grad_norm": 5.639405250549316,
      "learning_rate": 7.657673956915735e-06,
      "loss": 0.2544,
      "step": 666
    },
    {
      "epoch": 0.6187384044526901,
      "grad_norm": 4.007811546325684,
      "learning_rate": 7.6261997466059035e-06,
      "loss": 0.1547,
      "step": 667
    },
    {
      "epoch": 0.6196660482374768,
      "grad_norm": 4.930268287658691,
      "learning_rate": 7.594750436337467e-06,
      "loss": 0.1426,
      "step": 668
    },
    {
      "epoch": 0.6205936920222634,
      "grad_norm": 5.008491516113281,
      "learning_rate": 7.5633263559988035e-06,
      "loss": 0.1129,
      "step": 669
    },
    {
      "epoch": 0.62152133580705,
      "grad_norm": 3.0749435424804688,
      "learning_rate": 7.531927835213657e-06,
      "loss": 0.1166,
      "step": 670
    },
    {
      "epoch": 0.6224489795918368,
      "grad_norm": 5.739880084991455,
      "learning_rate": 7.500555203337647e-06,
      "loss": 0.1634,
      "step": 671
    },
    {
      "epoch": 0.6233766233766234,
      "grad_norm": 3.3177554607391357,
      "learning_rate": 7.469208789454838e-06,
      "loss": 0.1388,
      "step": 672
    },
    {
      "epoch": 0.62430426716141,
      "grad_norm": 4.005073070526123,
      "learning_rate": 7.4378889223742766e-06,
      "loss": 0.1429,
      "step": 673
    },
    {
      "epoch": 0.6252319109461967,
      "grad_norm": 4.268346786499023,
      "learning_rate": 7.40659593062655e-06,
      "loss": 0.187,
      "step": 674
    },
    {
      "epoch": 0.6261595547309833,
      "grad_norm": 6.763199329376221,
      "learning_rate": 7.375330142460331e-06,
      "loss": 0.2241,
      "step": 675
    },
    {
      "epoch": 0.62708719851577,
      "grad_norm": 3.3440911769866943,
      "learning_rate": 7.344091885838949e-06,
      "loss": 0.1407,
      "step": 676
    },
    {
      "epoch": 0.6280148423005566,
      "grad_norm": 5.204977035522461,
      "learning_rate": 7.312881488436928e-06,
      "loss": 0.2322,
      "step": 677
    },
    {
      "epoch": 0.6289424860853432,
      "grad_norm": 4.433789253234863,
      "learning_rate": 7.2816992776365714e-06,
      "loss": 0.1657,
      "step": 678
    },
    {
      "epoch": 0.6298701298701299,
      "grad_norm": 4.035289287567139,
      "learning_rate": 7.250545580524515e-06,
      "loss": 0.1994,
      "step": 679
    },
    {
      "epoch": 0.6307977736549165,
      "grad_norm": 4.986621856689453,
      "learning_rate": 7.219420723888301e-06,
      "loss": 0.2483,
      "step": 680
    },
    {
      "epoch": 0.6307977736549165,
      "eval_accuracy": 0.852549889135255,
      "eval_f1": 0.6855791962174941,
      "eval_loss": 0.30598554015159607,
      "eval_precision": 0.8529411764705882,
      "eval_recall": 0.5731225296442688,
      "eval_runtime": 46.8299,
      "eval_samples_per_second": 5.894,
      "eval_steps_per_second": 0.192,
      "step": 680
    },
    {
      "epoch": 0.6317254174397031,
      "grad_norm": 5.635754108428955,
      "learning_rate": 7.188325034212944e-06,
      "loss": 0.2133,
      "step": 681
    },
    {
      "epoch": 0.6326530612244898,
      "grad_norm": 6.280815601348877,
      "learning_rate": 7.157258837677514e-06,
      "loss": 0.2312,
      "step": 682
    },
    {
      "epoch": 0.6335807050092764,
      "grad_norm": 2.508446455001831,
      "learning_rate": 7.126222460151719e-06,
      "loss": 0.1189,
      "step": 683
    },
    {
      "epoch": 0.634508348794063,
      "grad_norm": 3.8485682010650635,
      "learning_rate": 7.095216227192467e-06,
      "loss": 0.1505,
      "step": 684
    },
    {
      "epoch": 0.6354359925788498,
      "grad_norm": 3.7377712726593018,
      "learning_rate": 7.064240464040472e-06,
      "loss": 0.129,
      "step": 685
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 3.6466944217681885,
      "learning_rate": 7.033295495616834e-06,
      "loss": 0.1457,
      "step": 686
    },
    {
      "epoch": 0.637291280148423,
      "grad_norm": 4.0310564041137695,
      "learning_rate": 7.002381646519625e-06,
      "loss": 0.1739,
      "step": 687
    },
    {
      "epoch": 0.6382189239332097,
      "grad_norm": 6.287572860717773,
      "learning_rate": 6.971499241020495e-06,
      "loss": 0.1513,
      "step": 688
    },
    {
      "epoch": 0.6391465677179963,
      "grad_norm": 5.086080551147461,
      "learning_rate": 6.940648603061263e-06,
      "loss": 0.2203,
      "step": 689
    },
    {
      "epoch": 0.640074211502783,
      "grad_norm": 3.155775785446167,
      "learning_rate": 6.909830056250527e-06,
      "loss": 0.1288,
      "step": 690
    },
    {
      "epoch": 0.6410018552875696,
      "grad_norm": 4.002538204193115,
      "learning_rate": 6.8790439238602576e-06,
      "loss": 0.1526,
      "step": 691
    },
    {
      "epoch": 0.6419294990723562,
      "grad_norm": 5.535161972045898,
      "learning_rate": 6.848290528822417e-06,
      "loss": 0.2223,
      "step": 692
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 4.103289604187012,
      "learning_rate": 6.8175701937255645e-06,
      "loss": 0.1831,
      "step": 693
    },
    {
      "epoch": 0.6437847866419295,
      "grad_norm": 4.057906150817871,
      "learning_rate": 6.786883240811479e-06,
      "loss": 0.1619,
      "step": 694
    },
    {
      "epoch": 0.6447124304267161,
      "grad_norm": 2.6124215126037598,
      "learning_rate": 6.756229991971779e-06,
      "loss": 0.0988,
      "step": 695
    },
    {
      "epoch": 0.6456400742115028,
      "grad_norm": 3.484631061553955,
      "learning_rate": 6.725610768744535e-06,
      "loss": 0.1127,
      "step": 696
    },
    {
      "epoch": 0.6465677179962894,
      "grad_norm": 3.0936501026153564,
      "learning_rate": 6.695025892310913e-06,
      "loss": 0.1455,
      "step": 697
    },
    {
      "epoch": 0.647495361781076,
      "grad_norm": 3.7610599994659424,
      "learning_rate": 6.664475683491797e-06,
      "loss": 0.1725,
      "step": 698
    },
    {
      "epoch": 0.6484230055658627,
      "grad_norm": 3.537524700164795,
      "learning_rate": 6.633960462744415e-06,
      "loss": 0.1971,
      "step": 699
    },
    {
      "epoch": 0.6493506493506493,
      "grad_norm": 4.47899055480957,
      "learning_rate": 6.603480550158995e-06,
      "loss": 0.1411,
      "step": 700
    },
    {
      "epoch": 0.6493506493506493,
      "eval_accuracy": 0.8481152993348116,
      "eval_f1": 0.6714628297362111,
      "eval_loss": 0.31714314222335815,
      "eval_precision": 0.8536585365853658,
      "eval_recall": 0.5533596837944664,
      "eval_runtime": 47.2966,
      "eval_samples_per_second": 5.836,
      "eval_steps_per_second": 0.19,
      "step": 700
    },
    {
      "epoch": 0.650278293135436,
      "grad_norm": 5.3951334953308105,
      "learning_rate": 6.5730362654554015e-06,
      "loss": 0.2149,
      "step": 701
    },
    {
      "epoch": 0.6512059369202227,
      "grad_norm": 4.401817798614502,
      "learning_rate": 6.542627927979772e-06,
      "loss": 0.2215,
      "step": 702
    },
    {
      "epoch": 0.6521335807050093,
      "grad_norm": 3.9779934883117676,
      "learning_rate": 6.5122558567011775e-06,
      "loss": 0.1763,
      "step": 703
    },
    {
      "epoch": 0.6530612244897959,
      "grad_norm": 3.7413315773010254,
      "learning_rate": 6.481920370208274e-06,
      "loss": 0.1176,
      "step": 704
    },
    {
      "epoch": 0.6539888682745826,
      "grad_norm": 6.082540988922119,
      "learning_rate": 6.4516217867059615e-06,
      "loss": 0.2444,
      "step": 705
    },
    {
      "epoch": 0.6549165120593692,
      "grad_norm": 7.003627300262451,
      "learning_rate": 6.421360424012039e-06,
      "loss": 0.1389,
      "step": 706
    },
    {
      "epoch": 0.6558441558441559,
      "grad_norm": 4.237902641296387,
      "learning_rate": 6.39113659955389e-06,
      "loss": 0.1767,
      "step": 707
    },
    {
      "epoch": 0.6567717996289425,
      "grad_norm": 3.1200437545776367,
      "learning_rate": 6.360950630365126e-06,
      "loss": 0.1127,
      "step": 708
    },
    {
      "epoch": 0.6576994434137291,
      "grad_norm": 4.659437656402588,
      "learning_rate": 6.33080283308228e-06,
      "loss": 0.1292,
      "step": 709
    },
    {
      "epoch": 0.6586270871985158,
      "grad_norm": 7.017888069152832,
      "learning_rate": 6.300693523941481e-06,
      "loss": 0.201,
      "step": 710
    },
    {
      "epoch": 0.6595547309833024,
      "grad_norm": 4.794656276702881,
      "learning_rate": 6.270623018775135e-06,
      "loss": 0.1835,
      "step": 711
    },
    {
      "epoch": 0.660482374768089,
      "grad_norm": 4.382326602935791,
      "learning_rate": 6.2405916330086106e-06,
      "loss": 0.1703,
      "step": 712
    },
    {
      "epoch": 0.6614100185528757,
      "grad_norm": 6.628244876861572,
      "learning_rate": 6.210599681656933e-06,
      "loss": 0.2367,
      "step": 713
    },
    {
      "epoch": 0.6623376623376623,
      "grad_norm": 4.854303359985352,
      "learning_rate": 6.180647479321484e-06,
      "loss": 0.1874,
      "step": 714
    },
    {
      "epoch": 0.6632653061224489,
      "grad_norm": 2.9809422492980957,
      "learning_rate": 6.1507353401866896e-06,
      "loss": 0.1429,
      "step": 715
    },
    {
      "epoch": 0.6641929499072357,
      "grad_norm": 3.899773359298706,
      "learning_rate": 6.120863578016736e-06,
      "loss": 0.1745,
      "step": 716
    },
    {
      "epoch": 0.6651205936920223,
      "grad_norm": 5.175771713256836,
      "learning_rate": 6.091032506152274e-06,
      "loss": 0.162,
      "step": 717
    },
    {
      "epoch": 0.6660482374768089,
      "grad_norm": 4.2920002937316895,
      "learning_rate": 6.061242437507131e-06,
      "loss": 0.1806,
      "step": 718
    },
    {
      "epoch": 0.6669758812615956,
      "grad_norm": 4.961828708648682,
      "learning_rate": 6.0314936845650296e-06,
      "loss": 0.1259,
      "step": 719
    },
    {
      "epoch": 0.6679035250463822,
      "grad_norm": 4.258510589599609,
      "learning_rate": 6.00178655937631e-06,
      "loss": 0.2015,
      "step": 720
    },
    {
      "epoch": 0.6679035250463822,
      "eval_accuracy": 0.852549889135255,
      "eval_f1": 0.6825775656324582,
      "eval_loss": 0.31203413009643555,
      "eval_precision": 0.8614457831325302,
      "eval_recall": 0.5652173913043478,
      "eval_runtime": 47.6328,
      "eval_samples_per_second": 5.794,
      "eval_steps_per_second": 0.189,
      "step": 720
    },
    {
      "epoch": 0.6688311688311688,
      "grad_norm": 4.69655179977417,
      "learning_rate": 5.972121373554665e-06,
      "loss": 0.1334,
      "step": 721
    },
    {
      "epoch": 0.6697588126159555,
      "grad_norm": 4.1556806564331055,
      "learning_rate": 5.942498438273849e-06,
      "loss": 0.159,
      "step": 722
    },
    {
      "epoch": 0.6706864564007421,
      "grad_norm": 4.261734485626221,
      "learning_rate": 5.912918064264441e-06,
      "loss": 0.14,
      "step": 723
    },
    {
      "epoch": 0.6716141001855288,
      "grad_norm": 5.172565460205078,
      "learning_rate": 5.8833805618105635e-06,
      "loss": 0.2259,
      "step": 724
    },
    {
      "epoch": 0.6725417439703154,
      "grad_norm": 5.771614074707031,
      "learning_rate": 5.853886240746643e-06,
      "loss": 0.1806,
      "step": 725
    },
    {
      "epoch": 0.673469387755102,
      "grad_norm": 3.933560371398926,
      "learning_rate": 5.82443541045415e-06,
      "loss": 0.1874,
      "step": 726
    },
    {
      "epoch": 0.6743970315398887,
      "grad_norm": 4.140106201171875,
      "learning_rate": 5.795028379858355e-06,
      "loss": 0.1252,
      "step": 727
    },
    {
      "epoch": 0.6753246753246753,
      "grad_norm": 4.954802513122559,
      "learning_rate": 5.765665457425102e-06,
      "loss": 0.2296,
      "step": 728
    },
    {
      "epoch": 0.6762523191094619,
      "grad_norm": 3.336763620376587,
      "learning_rate": 5.736346951157544e-06,
      "loss": 0.1571,
      "step": 729
    },
    {
      "epoch": 0.6771799628942486,
      "grad_norm": 6.951479434967041,
      "learning_rate": 5.707073168592943e-06,
      "loss": 0.227,
      "step": 730
    },
    {
      "epoch": 0.6781076066790352,
      "grad_norm": 6.168885231018066,
      "learning_rate": 5.677844416799424e-06,
      "loss": 0.1793,
      "step": 731
    },
    {
      "epoch": 0.6790352504638218,
      "grad_norm": 4.202786445617676,
      "learning_rate": 5.648661002372769e-06,
      "loss": 0.1307,
      "step": 732
    },
    {
      "epoch": 0.6799628942486086,
      "grad_norm": 5.333949565887451,
      "learning_rate": 5.619523231433177e-06,
      "loss": 0.1435,
      "step": 733
    },
    {
      "epoch": 0.6808905380333952,
      "grad_norm": 3.218813896179199,
      "learning_rate": 5.590431409622081e-06,
      "loss": 0.152,
      "step": 734
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 3.0740416049957275,
      "learning_rate": 5.56138584209893e-06,
      "loss": 0.1625,
      "step": 735
    },
    {
      "epoch": 0.6827458256029685,
      "grad_norm": 3.7008039951324463,
      "learning_rate": 5.5323868335379775e-06,
      "loss": 0.1361,
      "step": 736
    },
    {
      "epoch": 0.6836734693877551,
      "grad_norm": 3.482449769973755,
      "learning_rate": 5.503434688125104e-06,
      "loss": 0.1539,
      "step": 737
    },
    {
      "epoch": 0.6846011131725418,
      "grad_norm": 3.1356945037841797,
      "learning_rate": 5.4745297095546125e-06,
      "loss": 0.116,
      "step": 738
    },
    {
      "epoch": 0.6855287569573284,
      "grad_norm": 3.0260050296783447,
      "learning_rate": 5.445672201026054e-06,
      "loss": 0.1491,
      "step": 739
    },
    {
      "epoch": 0.686456400742115,
      "grad_norm": 6.386862754821777,
      "learning_rate": 5.416862465241033e-06,
      "loss": 0.2216,
      "step": 740
    },
    {
      "epoch": 0.686456400742115,
      "eval_accuracy": 0.8503325942350333,
      "eval_f1": 0.6762589928057554,
      "eval_loss": 0.30298492312431335,
      "eval_precision": 0.8597560975609756,
      "eval_recall": 0.5573122529644269,
      "eval_runtime": 47.363,
      "eval_samples_per_second": 5.827,
      "eval_steps_per_second": 0.19,
      "step": 740
    },
    {
      "epoch": 0.6873840445269017,
      "grad_norm": 2.5552661418914795,
      "learning_rate": 5.3881008044000495e-06,
      "loss": 0.113,
      "step": 741
    },
    {
      "epoch": 0.6883116883116883,
      "grad_norm": 3.5924112796783447,
      "learning_rate": 5.359387520199317e-06,
      "loss": 0.0896,
      "step": 742
    },
    {
      "epoch": 0.6892393320964749,
      "grad_norm": 3.5902557373046875,
      "learning_rate": 5.330722913827594e-06,
      "loss": 0.2078,
      "step": 743
    },
    {
      "epoch": 0.6901669758812616,
      "grad_norm": 3.3769776821136475,
      "learning_rate": 5.302107285963045e-06,
      "loss": 0.1311,
      "step": 744
    },
    {
      "epoch": 0.6910946196660482,
      "grad_norm": 4.20431661605835,
      "learning_rate": 5.273540936770059e-06,
      "loss": 0.1694,
      "step": 745
    },
    {
      "epoch": 0.6920222634508348,
      "grad_norm": 3.680614948272705,
      "learning_rate": 5.245024165896126e-06,
      "loss": 0.168,
      "step": 746
    },
    {
      "epoch": 0.6929499072356216,
      "grad_norm": 4.88540506362915,
      "learning_rate": 5.216557272468675e-06,
      "loss": 0.2021,
      "step": 747
    },
    {
      "epoch": 0.6938775510204082,
      "grad_norm": 3.159914016723633,
      "learning_rate": 5.18814055509195e-06,
      "loss": 0.1696,
      "step": 748
    },
    {
      "epoch": 0.6948051948051948,
      "grad_norm": 5.163516044616699,
      "learning_rate": 5.1597743118438725e-06,
      "loss": 0.1485,
      "step": 749
    },
    {
      "epoch": 0.6957328385899815,
      "grad_norm": 6.143499851226807,
      "learning_rate": 5.131458840272905e-06,
      "loss": 0.1769,
      "step": 750
    },
    {
      "epoch": 0.6966604823747681,
      "grad_norm": 3.032066822052002,
      "learning_rate": 5.103194437394952e-06,
      "loss": 0.1202,
      "step": 751
    },
    {
      "epoch": 0.6975881261595547,
      "grad_norm": 4.9984965324401855,
      "learning_rate": 5.074981399690219e-06,
      "loss": 0.2292,
      "step": 752
    },
    {
      "epoch": 0.6985157699443414,
      "grad_norm": 2.7881083488464355,
      "learning_rate": 5.046820023100129e-06,
      "loss": 0.0989,
      "step": 753
    },
    {
      "epoch": 0.699443413729128,
      "grad_norm": 4.462379455566406,
      "learning_rate": 5.018710603024187e-06,
      "loss": 0.1788,
      "step": 754
    },
    {
      "epoch": 0.7003710575139147,
      "grad_norm": 5.801154613494873,
      "learning_rate": 4.990653434316915e-06,
      "loss": 0.1807,
      "step": 755
    },
    {
      "epoch": 0.7012987012987013,
      "grad_norm": 4.452095031738281,
      "learning_rate": 4.9626488112847384e-06,
      "loss": 0.1348,
      "step": 756
    },
    {
      "epoch": 0.7022263450834879,
      "grad_norm": 4.256060600280762,
      "learning_rate": 4.934697027682894e-06,
      "loss": 0.1618,
      "step": 757
    },
    {
      "epoch": 0.7031539888682746,
      "grad_norm": 2.893348217010498,
      "learning_rate": 4.9067983767123736e-06,
      "loss": 0.114,
      "step": 758
    },
    {
      "epoch": 0.7040816326530612,
      "grad_norm": 2.409883737564087,
      "learning_rate": 4.878953151016816e-06,
      "loss": 0.0739,
      "step": 759
    },
    {
      "epoch": 0.7050092764378478,
      "grad_norm": 4.646303176879883,
      "learning_rate": 4.851161642679466e-06,
      "loss": 0.1936,
      "step": 760
    },
    {
      "epoch": 0.7050092764378478,
      "eval_accuracy": 0.8503325942350333,
      "eval_f1": 0.6762589928057554,
      "eval_loss": 0.30913296341896057,
      "eval_precision": 0.8597560975609756,
      "eval_recall": 0.5573122529644269,
      "eval_runtime": 47.2588,
      "eval_samples_per_second": 5.84,
      "eval_steps_per_second": 0.19,
      "step": 760
    },
    {
      "epoch": 0.7059369202226345,
      "grad_norm": 3.7548396587371826,
      "learning_rate": 4.823424143220097e-06,
      "loss": 0.1332,
      "step": 761
    },
    {
      "epoch": 0.7068645640074211,
      "grad_norm": 4.519832611083984,
      "learning_rate": 4.795740943591955e-06,
      "loss": 0.1508,
      "step": 762
    },
    {
      "epoch": 0.7077922077922078,
      "grad_norm": 4.223718643188477,
      "learning_rate": 4.7681123341787e-06,
      "loss": 0.2027,
      "step": 763
    },
    {
      "epoch": 0.7087198515769945,
      "grad_norm": 4.345351219177246,
      "learning_rate": 4.740538604791371e-06,
      "loss": 0.1641,
      "step": 764
    },
    {
      "epoch": 0.7096474953617811,
      "grad_norm": 6.437448024749756,
      "learning_rate": 4.713020044665348e-06,
      "loss": 0.1839,
      "step": 765
    },
    {
      "epoch": 0.7105751391465677,
      "grad_norm": 5.154228687286377,
      "learning_rate": 4.685556942457296e-06,
      "loss": 0.1696,
      "step": 766
    },
    {
      "epoch": 0.7115027829313544,
      "grad_norm": 4.437908172607422,
      "learning_rate": 4.65814958624217e-06,
      "loss": 0.1199,
      "step": 767
    },
    {
      "epoch": 0.712430426716141,
      "grad_norm": 4.337602615356445,
      "learning_rate": 4.630798263510162e-06,
      "loss": 0.166,
      "step": 768
    },
    {
      "epoch": 0.7133580705009277,
      "grad_norm": 4.633522987365723,
      "learning_rate": 4.60350326116371e-06,
      "loss": 0.1667,
      "step": 769
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 4.564393997192383,
      "learning_rate": 4.576264865514467e-06,
      "loss": 0.1996,
      "step": 770
    },
    {
      "epoch": 0.7152133580705009,
      "grad_norm": 5.6954803466796875,
      "learning_rate": 4.549083362280318e-06,
      "loss": 0.1227,
      "step": 771
    },
    {
      "epoch": 0.7161410018552876,
      "grad_norm": 2.704313278198242,
      "learning_rate": 4.521959036582372e-06,
      "loss": 0.1118,
      "step": 772
    },
    {
      "epoch": 0.7170686456400742,
      "grad_norm": 3.529452085494995,
      "learning_rate": 4.494892172941965e-06,
      "loss": 0.1595,
      "step": 773
    },
    {
      "epoch": 0.7179962894248608,
      "grad_norm": 4.921022415161133,
      "learning_rate": 4.467883055277696e-06,
      "loss": 0.1755,
      "step": 774
    },
    {
      "epoch": 0.7189239332096475,
      "grad_norm": 3.468756675720215,
      "learning_rate": 4.440931966902419e-06,
      "loss": 0.1198,
      "step": 775
    },
    {
      "epoch": 0.7198515769944341,
      "grad_norm": 3.8362793922424316,
      "learning_rate": 4.414039190520308e-06,
      "loss": 0.162,
      "step": 776
    },
    {
      "epoch": 0.7207792207792207,
      "grad_norm": 3.9787826538085938,
      "learning_rate": 4.3872050082238535e-06,
      "loss": 0.1539,
      "step": 777
    },
    {
      "epoch": 0.7217068645640075,
      "grad_norm": 4.675662517547607,
      "learning_rate": 4.360429701490935e-06,
      "loss": 0.1961,
      "step": 778
    },
    {
      "epoch": 0.7226345083487941,
      "grad_norm": 3.907136917114258,
      "learning_rate": 4.3337135511818514e-06,
      "loss": 0.1566,
      "step": 779
    },
    {
      "epoch": 0.7235621521335807,
      "grad_norm": 4.647920608520508,
      "learning_rate": 4.307056837536373e-06,
      "loss": 0.135,
      "step": 780
    },
    {
      "epoch": 0.7235621521335807,
      "eval_accuracy": 0.852549889135255,
      "eval_f1": 0.6855791962174941,
      "eval_loss": 0.30233433842658997,
      "eval_precision": 0.8529411764705882,
      "eval_recall": 0.5731225296442688,
      "eval_runtime": 49.2875,
      "eval_samples_per_second": 5.6,
      "eval_steps_per_second": 0.183,
      "step": 780
    },
    {
      "epoch": 0.7244897959183674,
      "grad_norm": 4.066539287567139,
      "learning_rate": 4.280459840170818e-06,
      "loss": 0.098,
      "step": 781
    },
    {
      "epoch": 0.725417439703154,
      "grad_norm": 4.152294635772705,
      "learning_rate": 4.2539228380750955e-06,
      "loss": 0.1492,
      "step": 782
    },
    {
      "epoch": 0.7263450834879406,
      "grad_norm": 4.5321831703186035,
      "learning_rate": 4.2274461096098085e-06,
      "loss": 0.1727,
      "step": 783
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 4.524892807006836,
      "learning_rate": 4.201029932503303e-06,
      "loss": 0.1529,
      "step": 784
    },
    {
      "epoch": 0.7282003710575139,
      "grad_norm": 6.373286724090576,
      "learning_rate": 4.17467458384878e-06,
      "loss": 0.1686,
      "step": 785
    },
    {
      "epoch": 0.7291280148423006,
      "grad_norm": 3.8836734294891357,
      "learning_rate": 4.14838034010138e-06,
      "loss": 0.1148,
      "step": 786
    },
    {
      "epoch": 0.7300556586270872,
      "grad_norm": 4.612453937530518,
      "learning_rate": 4.12214747707527e-06,
      "loss": 0.1585,
      "step": 787
    },
    {
      "epoch": 0.7309833024118738,
      "grad_norm": 3.490913152694702,
      "learning_rate": 4.095976269940777e-06,
      "loss": 0.1045,
      "step": 788
    },
    {
      "epoch": 0.7319109461966605,
      "grad_norm": 4.676249027252197,
      "learning_rate": 4.069866993221473e-06,
      "loss": 0.2105,
      "step": 789
    },
    {
      "epoch": 0.7328385899814471,
      "grad_norm": 4.428783416748047,
      "learning_rate": 4.043819920791322e-06,
      "loss": 0.1764,
      "step": 790
    },
    {
      "epoch": 0.7337662337662337,
      "grad_norm": 4.41617488861084,
      "learning_rate": 4.017835325871781e-06,
      "loss": 0.1616,
      "step": 791
    },
    {
      "epoch": 0.7346938775510204,
      "grad_norm": 3.8224010467529297,
      "learning_rate": 3.991913481028965e-06,
      "loss": 0.2009,
      "step": 792
    },
    {
      "epoch": 0.735621521335807,
      "grad_norm": 4.631185531616211,
      "learning_rate": 3.966054658170754e-06,
      "loss": 0.1481,
      "step": 793
    },
    {
      "epoch": 0.7365491651205937,
      "grad_norm": 4.32712984085083,
      "learning_rate": 3.940259128543967e-06,
      "loss": 0.1977,
      "step": 794
    },
    {
      "epoch": 0.7374768089053804,
      "grad_norm": 2.936823606491089,
      "learning_rate": 3.914527162731498e-06,
      "loss": 0.1197,
      "step": 795
    },
    {
      "epoch": 0.738404452690167,
      "grad_norm": 6.375387191772461,
      "learning_rate": 3.888859030649498e-06,
      "loss": 0.2587,
      "step": 796
    },
    {
      "epoch": 0.7393320964749536,
      "grad_norm": 5.587421894073486,
      "learning_rate": 3.863255001544526e-06,
      "loss": 0.2271,
      "step": 797
    },
    {
      "epoch": 0.7402597402597403,
      "grad_norm": 5.898324966430664,
      "learning_rate": 3.837715343990727e-06,
      "loss": 0.2026,
      "step": 798
    },
    {
      "epoch": 0.7411873840445269,
      "grad_norm": 6.89965295791626,
      "learning_rate": 3.81224032588703e-06,
      "loss": 0.222,
      "step": 799
    },
    {
      "epoch": 0.7421150278293135,
      "grad_norm": 4.845470428466797,
      "learning_rate": 3.7868302144543146e-06,
      "loss": 0.1332,
      "step": 800
    },
    {
      "epoch": 0.7421150278293135,
      "eval_accuracy": 0.843680709534368,
      "eval_f1": 0.6466165413533834,
      "eval_loss": 0.32069557905197144,
      "eval_precision": 0.8835616438356164,
      "eval_recall": 0.5098814229249012,
      "eval_runtime": 47.5467,
      "eval_samples_per_second": 5.805,
      "eval_steps_per_second": 0.189,
      "step": 800
    },
    {
      "epoch": 0.7430426716141002,
      "grad_norm": 3.8346760272979736,
      "learning_rate": 3.7614852762326303e-06,
      "loss": 0.1511,
      "step": 801
    },
    {
      "epoch": 0.7439703153988868,
      "grad_norm": 3.3582327365875244,
      "learning_rate": 3.736205777078381e-06,
      "loss": 0.099,
      "step": 802
    },
    {
      "epoch": 0.7448979591836735,
      "grad_norm": 4.043883323669434,
      "learning_rate": 3.7109919821615546e-06,
      "loss": 0.1684,
      "step": 803
    },
    {
      "epoch": 0.7458256029684601,
      "grad_norm": 4.061108112335205,
      "learning_rate": 3.685844155962931e-06,
      "loss": 0.1874,
      "step": 804
    },
    {
      "epoch": 0.7467532467532467,
      "grad_norm": 2.596107244491577,
      "learning_rate": 3.6607625622713005e-06,
      "loss": 0.1146,
      "step": 805
    },
    {
      "epoch": 0.7476808905380334,
      "grad_norm": 3.7484891414642334,
      "learning_rate": 3.63574746418072e-06,
      "loss": 0.1027,
      "step": 806
    },
    {
      "epoch": 0.74860853432282,
      "grad_norm": 4.787120342254639,
      "learning_rate": 3.610799124087725e-06,
      "loss": 0.2284,
      "step": 807
    },
    {
      "epoch": 0.7495361781076066,
      "grad_norm": 3.2740108966827393,
      "learning_rate": 3.585917803688603e-06,
      "loss": 0.126,
      "step": 808
    },
    {
      "epoch": 0.7504638218923934,
      "grad_norm": 3.000568389892578,
      "learning_rate": 3.5611037639766267e-06,
      "loss": 0.1258,
      "step": 809
    },
    {
      "epoch": 0.75139146567718,
      "grad_norm": 3.994319200515747,
      "learning_rate": 3.536357265239333e-06,
      "loss": 0.2042,
      "step": 810
    },
    {
      "epoch": 0.7523191094619666,
      "grad_norm": 3.8152012825012207,
      "learning_rate": 3.511678567055786e-06,
      "loss": 0.147,
      "step": 811
    },
    {
      "epoch": 0.7532467532467533,
      "grad_norm": 3.8970158100128174,
      "learning_rate": 3.487067928293848e-06,
      "loss": 0.142,
      "step": 812
    },
    {
      "epoch": 0.7541743970315399,
      "grad_norm": 4.383775234222412,
      "learning_rate": 3.4625256071074776e-06,
      "loss": 0.1752,
      "step": 813
    },
    {
      "epoch": 0.7551020408163265,
      "grad_norm": 3.43391489982605,
      "learning_rate": 3.4380518609340076e-06,
      "loss": 0.1207,
      "step": 814
    },
    {
      "epoch": 0.7560296846011132,
      "grad_norm": 3.767289161682129,
      "learning_rate": 3.413646946491458e-06,
      "loss": 0.1301,
      "step": 815
    },
    {
      "epoch": 0.7569573283858998,
      "grad_norm": 3.6454761028289795,
      "learning_rate": 3.3893111197758276e-06,
      "loss": 0.1729,
      "step": 816
    },
    {
      "epoch": 0.7578849721706865,
      "grad_norm": 4.36724328994751,
      "learning_rate": 3.3650446360584276e-06,
      "loss": 0.1707,
      "step": 817
    },
    {
      "epoch": 0.7588126159554731,
      "grad_norm": 2.9927897453308105,
      "learning_rate": 3.3408477498831917e-06,
      "loss": 0.112,
      "step": 818
    },
    {
      "epoch": 0.7597402597402597,
      "grad_norm": 4.448176860809326,
      "learning_rate": 3.3167207150640003e-06,
      "loss": 0.1064,
      "step": 819
    },
    {
      "epoch": 0.7606679035250464,
      "grad_norm": 6.467900276184082,
      "learning_rate": 3.2926637846820366e-06,
      "loss": 0.249,
      "step": 820
    },
    {
      "epoch": 0.7606679035250464,
      "eval_accuracy": 0.8592017738359202,
      "eval_f1": 0.6997635933806147,
      "eval_loss": 0.3030702769756317,
      "eval_precision": 0.8705882352941177,
      "eval_recall": 0.5849802371541502,
      "eval_runtime": 47.6515,
      "eval_samples_per_second": 5.792,
      "eval_steps_per_second": 0.189,
      "step": 820
    },
    {
      "epoch": 0.761595547309833,
      "grad_norm": 3.21474027633667,
      "learning_rate": 3.268677211083109e-06,
      "loss": 0.1103,
      "step": 821
    },
    {
      "epoch": 0.7625231910946196,
      "grad_norm": 3.8230926990509033,
      "learning_rate": 3.2447612458750365e-06,
      "loss": 0.1608,
      "step": 822
    },
    {
      "epoch": 0.7634508348794063,
      "grad_norm": 4.736266136169434,
      "learning_rate": 3.2209161399249677e-06,
      "loss": 0.1549,
      "step": 823
    },
    {
      "epoch": 0.764378478664193,
      "grad_norm": 5.4161481857299805,
      "learning_rate": 3.197142143356787e-06,
      "loss": 0.1905,
      "step": 824
    },
    {
      "epoch": 0.7653061224489796,
      "grad_norm": 3.857360601425171,
      "learning_rate": 3.1734395055484623e-06,
      "loss": 0.1287,
      "step": 825
    },
    {
      "epoch": 0.7662337662337663,
      "grad_norm": 4.246245861053467,
      "learning_rate": 3.1498084751294523e-06,
      "loss": 0.1751,
      "step": 826
    },
    {
      "epoch": 0.7671614100185529,
      "grad_norm": 4.21674108505249,
      "learning_rate": 3.126249299978086e-06,
      "loss": 0.1593,
      "step": 827
    },
    {
      "epoch": 0.7680890538033395,
      "grad_norm": 3.7095324993133545,
      "learning_rate": 3.1027622272189572e-06,
      "loss": 0.1384,
      "step": 828
    },
    {
      "epoch": 0.7690166975881262,
      "grad_norm": 6.3794965744018555,
      "learning_rate": 3.0793475032203513e-06,
      "loss": 0.1583,
      "step": 829
    },
    {
      "epoch": 0.7699443413729128,
      "grad_norm": 3.0277578830718994,
      "learning_rate": 3.0560053735916372e-06,
      "loss": 0.1043,
      "step": 830
    },
    {
      "epoch": 0.7708719851576994,
      "grad_norm": 5.117831707000732,
      "learning_rate": 3.032736083180716e-06,
      "loss": 0.15,
      "step": 831
    },
    {
      "epoch": 0.7717996289424861,
      "grad_norm": 2.76505184173584,
      "learning_rate": 3.009539876071427e-06,
      "loss": 0.0558,
      "step": 832
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 4.057276725769043,
      "learning_rate": 2.9864169955810085e-06,
      "loss": 0.1391,
      "step": 833
    },
    {
      "epoch": 0.7736549165120594,
      "grad_norm": 3.700852870941162,
      "learning_rate": 2.9633676842575386e-06,
      "loss": 0.1721,
      "step": 834
    },
    {
      "epoch": 0.774582560296846,
      "grad_norm": 4.1468939781188965,
      "learning_rate": 2.940392183877382e-06,
      "loss": 0.1866,
      "step": 835
    },
    {
      "epoch": 0.7755102040816326,
      "grad_norm": 3.1190547943115234,
      "learning_rate": 2.9174907354426696e-06,
      "loss": 0.1292,
      "step": 836
    },
    {
      "epoch": 0.7764378478664193,
      "grad_norm": 3.0235095024108887,
      "learning_rate": 2.8946635791787546e-06,
      "loss": 0.0629,
      "step": 837
    },
    {
      "epoch": 0.7773654916512059,
      "grad_norm": 3.435035467147827,
      "learning_rate": 2.8719109545317102e-06,
      "loss": 0.1064,
      "step": 838
    },
    {
      "epoch": 0.7782931354359925,
      "grad_norm": 5.368072986602783,
      "learning_rate": 2.849233100165795e-06,
      "loss": 0.1662,
      "step": 839
    },
    {
      "epoch": 0.7792207792207793,
      "grad_norm": 4.488304615020752,
      "learning_rate": 2.8266302539609747e-06,
      "loss": 0.2033,
      "step": 840
    },
    {
      "epoch": 0.7792207792207793,
      "eval_accuracy": 0.8592017738359202,
      "eval_f1": 0.6983372921615202,
      "eval_loss": 0.30760514736175537,
      "eval_precision": 0.875,
      "eval_recall": 0.5810276679841897,
      "eval_runtime": 47.6262,
      "eval_samples_per_second": 5.795,
      "eval_steps_per_second": 0.189,
      "step": 840
    },
    {
      "epoch": 0.7801484230055659,
      "grad_norm": 4.42378044128418,
      "learning_rate": 2.8041026530104144e-06,
      "loss": 0.1223,
      "step": 841
    },
    {
      "epoch": 0.7810760667903525,
      "grad_norm": 3.143146514892578,
      "learning_rate": 2.78165053361798e-06,
      "loss": 0.1408,
      "step": 842
    },
    {
      "epoch": 0.7820037105751392,
      "grad_norm": 3.8427817821502686,
      "learning_rate": 2.759274131295787e-06,
      "loss": 0.0995,
      "step": 843
    },
    {
      "epoch": 0.7829313543599258,
      "grad_norm": 4.896306991577148,
      "learning_rate": 2.736973680761702e-06,
      "loss": 0.1621,
      "step": 844
    },
    {
      "epoch": 0.7838589981447124,
      "grad_norm": 5.344152450561523,
      "learning_rate": 2.714749415936904e-06,
      "loss": 0.1749,
      "step": 845
    },
    {
      "epoch": 0.7847866419294991,
      "grad_norm": 4.093927383422852,
      "learning_rate": 2.692601569943407e-06,
      "loss": 0.1716,
      "step": 846
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 3.3568267822265625,
      "learning_rate": 2.670530375101641e-06,
      "loss": 0.1658,
      "step": 847
    },
    {
      "epoch": 0.7866419294990723,
      "grad_norm": 3.3225290775299072,
      "learning_rate": 2.648536062927999e-06,
      "loss": 0.1358,
      "step": 848
    },
    {
      "epoch": 0.787569573283859,
      "grad_norm": 4.490353584289551,
      "learning_rate": 2.6266188641324e-06,
      "loss": 0.1178,
      "step": 849
    },
    {
      "epoch": 0.7884972170686456,
      "grad_norm": 3.4706945419311523,
      "learning_rate": 2.604779008615895e-06,
      "loss": 0.0946,
      "step": 850
    },
    {
      "epoch": 0.7894248608534323,
      "grad_norm": 5.027894020080566,
      "learning_rate": 2.583016725468226e-06,
      "loss": 0.1434,
      "step": 851
    },
    {
      "epoch": 0.7903525046382189,
      "grad_norm": 4.010559558868408,
      "learning_rate": 2.5613322429654573e-06,
      "loss": 0.158,
      "step": 852
    },
    {
      "epoch": 0.7912801484230055,
      "grad_norm": 6.057810306549072,
      "learning_rate": 2.5397257885675396e-06,
      "loss": 0.1912,
      "step": 853
    },
    {
      "epoch": 0.7922077922077922,
      "grad_norm": 5.5663371086120605,
      "learning_rate": 2.5181975889159615e-06,
      "loss": 0.2398,
      "step": 854
    },
    {
      "epoch": 0.7931354359925789,
      "grad_norm": 2.8672025203704834,
      "learning_rate": 2.496747869831345e-06,
      "loss": 0.0944,
      "step": 855
    },
    {
      "epoch": 0.7940630797773655,
      "grad_norm": 4.048581123352051,
      "learning_rate": 2.475376856311097e-06,
      "loss": 0.1603,
      "step": 856
    },
    {
      "epoch": 0.7949907235621522,
      "grad_norm": 5.737659931182861,
      "learning_rate": 2.4540847725270376e-06,
      "loss": 0.1366,
      "step": 857
    },
    {
      "epoch": 0.7959183673469388,
      "grad_norm": 4.4261155128479,
      "learning_rate": 2.432871841823047e-06,
      "loss": 0.1939,
      "step": 858
    },
    {
      "epoch": 0.7968460111317254,
      "grad_norm": 5.629834175109863,
      "learning_rate": 2.411738286712735e-06,
      "loss": 0.2281,
      "step": 859
    },
    {
      "epoch": 0.7977736549165121,
      "grad_norm": 3.919034004211426,
      "learning_rate": 2.390684328877089e-06,
      "loss": 0.1418,
      "step": 860
    },
    {
      "epoch": 0.7977736549165121,
      "eval_accuracy": 0.8614190687361419,
      "eval_f1": 0.7072599531615925,
      "eval_loss": 0.29977986216545105,
      "eval_precision": 0.867816091954023,
      "eval_recall": 0.5968379446640316,
      "eval_runtime": 47.4113,
      "eval_samples_per_second": 5.821,
      "eval_steps_per_second": 0.19,
      "step": 860
    },
    {
      "epoch": 0.7987012987012987,
      "grad_norm": 7.607851982116699,
      "learning_rate": 2.36971018916217e-06,
      "loss": 0.187,
      "step": 861
    },
    {
      "epoch": 0.7996289424860853,
      "grad_norm": 3.1179118156433105,
      "learning_rate": 2.3488160875767717e-06,
      "loss": 0.1326,
      "step": 862
    },
    {
      "epoch": 0.800556586270872,
      "grad_norm": 3.8754749298095703,
      "learning_rate": 2.328002243290138e-06,
      "loss": 0.1497,
      "step": 863
    },
    {
      "epoch": 0.8014842300556586,
      "grad_norm": 4.216552734375,
      "learning_rate": 2.307268874629649e-06,
      "loss": 0.1259,
      "step": 864
    },
    {
      "epoch": 0.8024118738404453,
      "grad_norm": 5.980984210968018,
      "learning_rate": 2.2866161990785228e-06,
      "loss": 0.1778,
      "step": 865
    },
    {
      "epoch": 0.8033395176252319,
      "grad_norm": 4.638891220092773,
      "learning_rate": 2.266044433273562e-06,
      "loss": 0.2258,
      "step": 866
    },
    {
      "epoch": 0.8042671614100185,
      "grad_norm": 3.3244616985321045,
      "learning_rate": 2.245553793002849e-06,
      "loss": 0.1215,
      "step": 867
    },
    {
      "epoch": 0.8051948051948052,
      "grad_norm": 6.757506370544434,
      "learning_rate": 2.2251444932035094e-06,
      "loss": 0.159,
      "step": 868
    },
    {
      "epoch": 0.8061224489795918,
      "grad_norm": 5.527317523956299,
      "learning_rate": 2.204816747959434e-06,
      "loss": 0.1025,
      "step": 869
    },
    {
      "epoch": 0.8070500927643784,
      "grad_norm": 3.5259664058685303,
      "learning_rate": 2.184570770499056e-06,
      "loss": 0.1522,
      "step": 870
    },
    {
      "epoch": 0.8079777365491652,
      "grad_norm": 4.936224937438965,
      "learning_rate": 2.1644067731931005e-06,
      "loss": 0.1679,
      "step": 871
    },
    {
      "epoch": 0.8089053803339518,
      "grad_norm": 4.338299751281738,
      "learning_rate": 2.1443249675523536e-06,
      "loss": 0.1705,
      "step": 872
    },
    {
      "epoch": 0.8098330241187384,
      "grad_norm": 3.631812334060669,
      "learning_rate": 2.124325564225458e-06,
      "loss": 0.1034,
      "step": 873
    },
    {
      "epoch": 0.8107606679035251,
      "grad_norm": 3.276409864425659,
      "learning_rate": 2.1044087729966856e-06,
      "loss": 0.1486,
      "step": 874
    },
    {
      "epoch": 0.8116883116883117,
      "grad_norm": 5.677032947540283,
      "learning_rate": 2.0845748027837585e-06,
      "loss": 0.2155,
      "step": 875
    },
    {
      "epoch": 0.8126159554730983,
      "grad_norm": 6.064774036407471,
      "learning_rate": 2.064823861635633e-06,
      "loss": 0.1773,
      "step": 876
    },
    {
      "epoch": 0.813543599257885,
      "grad_norm": 3.783052444458008,
      "learning_rate": 2.0451561567303378e-06,
      "loss": 0.1696,
      "step": 877
    },
    {
      "epoch": 0.8144712430426716,
      "grad_norm": 3.9778928756713867,
      "learning_rate": 2.025571894372794e-06,
      "loss": 0.0916,
      "step": 878
    },
    {
      "epoch": 0.8153988868274582,
      "grad_norm": 3.2632224559783936,
      "learning_rate": 2.0060712799926407e-06,
      "loss": 0.1004,
      "step": 879
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 5.624824047088623,
      "learning_rate": 1.9866545181421016e-06,
      "loss": 0.1826,
      "step": 880
    },
    {
      "epoch": 0.8163265306122449,
      "eval_accuracy": 0.8625277161862528,
      "eval_f1": 0.7089201877934272,
      "eval_loss": 0.30142825841903687,
      "eval_precision": 0.8728323699421965,
      "eval_recall": 0.5968379446640316,
      "eval_runtime": 47.5017,
      "eval_samples_per_second": 5.81,
      "eval_steps_per_second": 0.189,
      "step": 880
    },
    {
      "epoch": 0.8172541743970315,
      "grad_norm": 5.620955944061279,
      "learning_rate": 1.967321812493813e-06,
      "loss": 0.159,
      "step": 881
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 3.5917294025421143,
      "learning_rate": 1.9480733658387175e-06,
      "loss": 0.1544,
      "step": 882
    },
    {
      "epoch": 0.8191094619666048,
      "grad_norm": 4.478516101837158,
      "learning_rate": 1.9289093800839067e-06,
      "loss": 0.1835,
      "step": 883
    },
    {
      "epoch": 0.8200371057513914,
      "grad_norm": 5.72329044342041,
      "learning_rate": 1.9098300562505266e-06,
      "loss": 0.181,
      "step": 884
    },
    {
      "epoch": 0.8209647495361782,
      "grad_norm": 4.014090538024902,
      "learning_rate": 1.8908355944716516e-06,
      "loss": 0.123,
      "step": 885
    },
    {
      "epoch": 0.8218923933209648,
      "grad_norm": 3.9502549171447754,
      "learning_rate": 1.8719261939902023e-06,
      "loss": 0.1675,
      "step": 886
    },
    {
      "epoch": 0.8228200371057514,
      "grad_norm": 3.701931953430176,
      "learning_rate": 1.8531020531568377e-06,
      "loss": 0.1297,
      "step": 887
    },
    {
      "epoch": 0.8237476808905381,
      "grad_norm": 4.026066303253174,
      "learning_rate": 1.8343633694278895e-06,
      "loss": 0.1366,
      "step": 888
    },
    {
      "epoch": 0.8246753246753247,
      "grad_norm": 4.122823715209961,
      "learning_rate": 1.8157103393632869e-06,
      "loss": 0.1819,
      "step": 889
    },
    {
      "epoch": 0.8256029684601113,
      "grad_norm": 4.512097358703613,
      "learning_rate": 1.7971431586244814e-06,
      "loss": 0.2281,
      "step": 890
    },
    {
      "epoch": 0.826530612244898,
      "grad_norm": 3.6927201747894287,
      "learning_rate": 1.7786620219724205e-06,
      "loss": 0.0749,
      "step": 891
    },
    {
      "epoch": 0.8274582560296846,
      "grad_norm": 5.3355207443237305,
      "learning_rate": 1.7602671232654755e-06,
      "loss": 0.1781,
      "step": 892
    },
    {
      "epoch": 0.8283858998144712,
      "grad_norm": 3.310504674911499,
      "learning_rate": 1.7419586554574364e-06,
      "loss": 0.0927,
      "step": 893
    },
    {
      "epoch": 0.8293135435992579,
      "grad_norm": 3.6718716621398926,
      "learning_rate": 1.723736810595461e-06,
      "loss": 0.159,
      "step": 894
    },
    {
      "epoch": 0.8302411873840445,
      "grad_norm": 4.083915710449219,
      "learning_rate": 1.7056017798180824e-06,
      "loss": 0.1516,
      "step": 895
    },
    {
      "epoch": 0.8311688311688312,
      "grad_norm": 8.39147663116455,
      "learning_rate": 1.687553753353195e-06,
      "loss": 0.1548,
      "step": 896
    },
    {
      "epoch": 0.8320964749536178,
      "grad_norm": 3.83030366897583,
      "learning_rate": 1.669592920516049e-06,
      "loss": 0.1613,
      "step": 897
    },
    {
      "epoch": 0.8330241187384044,
      "grad_norm": 3.559238910675049,
      "learning_rate": 1.6517194697072903e-06,
      "loss": 0.1193,
      "step": 898
    },
    {
      "epoch": 0.8339517625231911,
      "grad_norm": 4.015861511230469,
      "learning_rate": 1.633933588410952e-06,
      "loss": 0.1383,
      "step": 899
    },
    {
      "epoch": 0.8348794063079777,
      "grad_norm": 4.48312520980835,
      "learning_rate": 1.6162354631925203e-06,
      "loss": 0.1538,
      "step": 900
    },
    {
      "epoch": 0.8348794063079777,
      "eval_accuracy": 0.8614190687361419,
      "eval_f1": 0.7016706443914081,
      "eval_loss": 0.3091951012611389,
      "eval_precision": 0.8855421686746988,
      "eval_recall": 0.5810276679841897,
      "eval_runtime": 47.4361,
      "eval_samples_per_second": 5.818,
      "eval_steps_per_second": 0.19,
      "step": 900
    },
    {
      "epoch": 0.8358070500927643,
      "grad_norm": 3.852740526199341,
      "learning_rate": 1.5986252796969482e-06,
      "loss": 0.1165,
      "step": 901
    },
    {
      "epoch": 0.8367346938775511,
      "grad_norm": 5.131833076477051,
      "learning_rate": 1.5811032226467304e-06,
      "loss": 0.198,
      "step": 902
    },
    {
      "epoch": 0.8376623376623377,
      "grad_norm": 4.975651741027832,
      "learning_rate": 1.5636694758399563e-06,
      "loss": 0.1891,
      "step": 903
    },
    {
      "epoch": 0.8385899814471243,
      "grad_norm": 3.24419903755188,
      "learning_rate": 1.5463242221483742e-06,
      "loss": 0.0935,
      "step": 904
    },
    {
      "epoch": 0.839517625231911,
      "grad_norm": 3.5641651153564453,
      "learning_rate": 1.5290676435154949e-06,
      "loss": 0.1533,
      "step": 905
    },
    {
      "epoch": 0.8404452690166976,
      "grad_norm": 3.872134208679199,
      "learning_rate": 1.511899920954656e-06,
      "loss": 0.1545,
      "step": 906
    },
    {
      "epoch": 0.8413729128014842,
      "grad_norm": 6.075543403625488,
      "learning_rate": 1.4948212345471492e-06,
      "loss": 0.2032,
      "step": 907
    },
    {
      "epoch": 0.8423005565862709,
      "grad_norm": 2.9056954383850098,
      "learning_rate": 1.4778317634403082e-06,
      "loss": 0.0986,
      "step": 908
    },
    {
      "epoch": 0.8432282003710575,
      "grad_norm": 5.516162872314453,
      "learning_rate": 1.460931685845649e-06,
      "loss": 0.1868,
      "step": 909
    },
    {
      "epoch": 0.8441558441558441,
      "grad_norm": 2.8610849380493164,
      "learning_rate": 1.4441211790369892e-06,
      "loss": 0.0923,
      "step": 910
    },
    {
      "epoch": 0.8450834879406308,
      "grad_norm": 3.700863838195801,
      "learning_rate": 1.427400419348588e-06,
      "loss": 0.1291,
      "step": 911
    },
    {
      "epoch": 0.8460111317254174,
      "grad_norm": 4.772455215454102,
      "learning_rate": 1.4107695821733026e-06,
      "loss": 0.1352,
      "step": 912
    },
    {
      "epoch": 0.8469387755102041,
      "grad_norm": 3.5742745399475098,
      "learning_rate": 1.3942288419607476e-06,
      "loss": 0.1824,
      "step": 913
    },
    {
      "epoch": 0.8478664192949907,
      "grad_norm": 8.259415626525879,
      "learning_rate": 1.3777783722154603e-06,
      "loss": 0.2448,
      "step": 914
    },
    {
      "epoch": 0.8487940630797773,
      "grad_norm": 3.900238513946533,
      "learning_rate": 1.3614183454950824e-06,
      "loss": 0.1273,
      "step": 915
    },
    {
      "epoch": 0.849721706864564,
      "grad_norm": 2.9773433208465576,
      "learning_rate": 1.3451489334085555e-06,
      "loss": 0.1522,
      "step": 916
    },
    {
      "epoch": 0.8506493506493507,
      "grad_norm": 3.071232318878174,
      "learning_rate": 1.3289703066143112e-06,
      "loss": 0.1256,
      "step": 917
    },
    {
      "epoch": 0.8515769944341373,
      "grad_norm": 3.8165667057037354,
      "learning_rate": 1.3128826348184886e-06,
      "loss": 0.1111,
      "step": 918
    },
    {
      "epoch": 0.852504638218924,
      "grad_norm": 3.7821688652038574,
      "learning_rate": 1.296886086773157e-06,
      "loss": 0.2091,
      "step": 919
    },
    {
      "epoch": 0.8534322820037106,
      "grad_norm": 4.833895206451416,
      "learning_rate": 1.2809808302745298e-06,
      "loss": 0.1762,
      "step": 920
    },
    {
      "epoch": 0.8534322820037106,
      "eval_accuracy": 0.8603104212860311,
      "eval_f1": 0.704225352112676,
      "eval_loss": 0.30113720893859863,
      "eval_precision": 0.8670520231213873,
      "eval_recall": 0.5928853754940712,
      "eval_runtime": 47.313,
      "eval_samples_per_second": 5.833,
      "eval_steps_per_second": 0.19,
      "step": 920
    },
    {
      "epoch": 0.8543599257884972,
      "grad_norm": 3.3207972049713135,
      "learning_rate": 1.2651670321612264e-06,
      "loss": 0.1367,
      "step": 921
    },
    {
      "epoch": 0.8552875695732839,
      "grad_norm": 3.202796697616577,
      "learning_rate": 1.249444858312502e-06,
      "loss": 0.1379,
      "step": 922
    },
    {
      "epoch": 0.8562152133580705,
      "grad_norm": 6.188356876373291,
      "learning_rate": 1.233814473646524e-06,
      "loss": 0.2627,
      "step": 923
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 3.4624321460723877,
      "learning_rate": 1.218276042118629e-06,
      "loss": 0.1318,
      "step": 924
    },
    {
      "epoch": 0.8580705009276438,
      "grad_norm": 3.288809061050415,
      "learning_rate": 1.202829726719611e-06,
      "loss": 0.1188,
      "step": 925
    },
    {
      "epoch": 0.8589981447124304,
      "grad_norm": 2.691675901412964,
      "learning_rate": 1.1874756894740137e-06,
      "loss": 0.1252,
      "step": 926
    },
    {
      "epoch": 0.859925788497217,
      "grad_norm": 3.750600576400757,
      "learning_rate": 1.1722140914384162e-06,
      "loss": 0.1644,
      "step": 927
    },
    {
      "epoch": 0.8608534322820037,
      "grad_norm": 3.1353397369384766,
      "learning_rate": 1.1570450926997657e-06,
      "loss": 0.1461,
      "step": 928
    },
    {
      "epoch": 0.8617810760667903,
      "grad_norm": 5.295469760894775,
      "learning_rate": 1.1419688523736761e-06,
      "loss": 0.1967,
      "step": 929
    },
    {
      "epoch": 0.862708719851577,
      "grad_norm": 3.461599349975586,
      "learning_rate": 1.1269855286027798e-06,
      "loss": 0.1426,
      "step": 930
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 6.9660420417785645,
      "learning_rate": 1.1120952785550477e-06,
      "loss": 0.2015,
      "step": 931
    },
    {
      "epoch": 0.8645640074211502,
      "grad_norm": 2.989213705062866,
      "learning_rate": 1.0972982584221592e-06,
      "loss": 0.1204,
      "step": 932
    },
    {
      "epoch": 0.865491651205937,
      "grad_norm": 4.492414474487305,
      "learning_rate": 1.0825946234178575e-06,
      "loss": 0.1579,
      "step": 933
    },
    {
      "epoch": 0.8664192949907236,
      "grad_norm": 4.693439960479736,
      "learning_rate": 1.067984527776309e-06,
      "loss": 0.1959,
      "step": 934
    },
    {
      "epoch": 0.8673469387755102,
      "grad_norm": 5.462426662445068,
      "learning_rate": 1.0534681247505107e-06,
      "loss": 0.1435,
      "step": 935
    },
    {
      "epoch": 0.8682745825602969,
      "grad_norm": 2.594604730606079,
      "learning_rate": 1.0390455666106547e-06,
      "loss": 0.115,
      "step": 936
    },
    {
      "epoch": 0.8692022263450835,
      "grad_norm": 5.900606155395508,
      "learning_rate": 1.024717004642557e-06,
      "loss": 0.1749,
      "step": 937
    },
    {
      "epoch": 0.8701298701298701,
      "grad_norm": 5.774359226226807,
      "learning_rate": 1.010482589146048e-06,
      "loss": 0.1802,
      "step": 938
    },
    {
      "epoch": 0.8710575139146568,
      "grad_norm": 4.002913951873779,
      "learning_rate": 9.963424694334122e-07,
      "loss": 0.1277,
      "step": 939
    },
    {
      "epoch": 0.8719851576994434,
      "grad_norm": 3.6173672676086426,
      "learning_rate": 9.822967938278172e-07,
      "loss": 0.1561,
      "step": 940
    },
    {
      "epoch": 0.8719851576994434,
      "eval_accuracy": 0.8603104212860311,
      "eval_f1": 0.704225352112676,
      "eval_loss": 0.29984721541404724,
      "eval_precision": 0.8670520231213873,
      "eval_recall": 0.5928853754940712,
      "eval_runtime": 48.0345,
      "eval_samples_per_second": 5.746,
      "eval_steps_per_second": 0.187,
      "step": 940
    },
    {
      "epoch": 0.87291280148423,
      "grad_norm": 5.298496723175049,
      "learning_rate": 9.683457096617487e-07,
      "loss": 0.1343,
      "step": 941
    },
    {
      "epoch": 0.8738404452690167,
      "grad_norm": 4.087591648101807,
      "learning_rate": 9.544893632754816e-07,
      "loss": 0.1342,
      "step": 942
    },
    {
      "epoch": 0.8747680890538033,
      "grad_norm": 3.6953861713409424,
      "learning_rate": 9.407279000155311e-07,
      "loss": 0.1125,
      "step": 943
    },
    {
      "epoch": 0.87569573283859,
      "grad_norm": 5.693349838256836,
      "learning_rate": 9.270614642331377e-07,
      "loss": 0.2285,
      "step": 944
    },
    {
      "epoch": 0.8766233766233766,
      "grad_norm": 4.321276664733887,
      "learning_rate": 9.134901992827427e-07,
      "loss": 0.2169,
      "step": 945
    },
    {
      "epoch": 0.8775510204081632,
      "grad_norm": 5.951560020446777,
      "learning_rate": 9.000142475204965e-07,
      "loss": 0.2039,
      "step": 946
    },
    {
      "epoch": 0.87847866419295,
      "grad_norm": 5.382765293121338,
      "learning_rate": 8.866337503027523e-07,
      "loss": 0.1347,
      "step": 947
    },
    {
      "epoch": 0.8794063079777366,
      "grad_norm": 4.566171646118164,
      "learning_rate": 8.733488479845997e-07,
      "loss": 0.1929,
      "step": 948
    },
    {
      "epoch": 0.8803339517625232,
      "grad_norm": 4.413459300994873,
      "learning_rate": 8.60159679918372e-07,
      "loss": 0.1463,
      "step": 949
    },
    {
      "epoch": 0.8812615955473099,
      "grad_norm": 3.8674092292785645,
      "learning_rate": 8.470663844522053e-07,
      "loss": 0.1523,
      "step": 950
    },
    {
      "epoch": 0.8821892393320965,
      "grad_norm": 3.844576597213745,
      "learning_rate": 8.340690989285727e-07,
      "loss": 0.1248,
      "step": 951
    },
    {
      "epoch": 0.8831168831168831,
      "grad_norm": 4.541808605194092,
      "learning_rate": 8.211679596828481e-07,
      "loss": 0.1571,
      "step": 952
    },
    {
      "epoch": 0.8840445269016698,
      "grad_norm": 3.0702145099639893,
      "learning_rate": 8.083631020418792e-07,
      "loss": 0.157,
      "step": 953
    },
    {
      "epoch": 0.8849721706864564,
      "grad_norm": 3.5125439167022705,
      "learning_rate": 7.956546603225601e-07,
      "loss": 0.1011,
      "step": 954
    },
    {
      "epoch": 0.885899814471243,
      "grad_norm": 4.256104469299316,
      "learning_rate": 7.830427678304353e-07,
      "loss": 0.1411,
      "step": 955
    },
    {
      "epoch": 0.8868274582560297,
      "grad_norm": 4.931686878204346,
      "learning_rate": 7.705275568582848e-07,
      "loss": 0.1953,
      "step": 956
    },
    {
      "epoch": 0.8877551020408163,
      "grad_norm": 5.233354091644287,
      "learning_rate": 7.581091586847522e-07,
      "loss": 0.2095,
      "step": 957
    },
    {
      "epoch": 0.8886827458256029,
      "grad_norm": 6.383068084716797,
      "learning_rate": 7.457877035729588e-07,
      "loss": 0.2274,
      "step": 958
    },
    {
      "epoch": 0.8896103896103896,
      "grad_norm": 2.8475682735443115,
      "learning_rate": 7.335633207691362e-07,
      "loss": 0.1336,
      "step": 959
    },
    {
      "epoch": 0.8905380333951762,
      "grad_norm": 3.393915891647339,
      "learning_rate": 7.21436138501278e-07,
      "loss": 0.1633,
      "step": 960
    },
    {
      "epoch": 0.8905380333951762,
      "eval_accuracy": 0.8569844789356984,
      "eval_f1": 0.6935866983372921,
      "eval_loss": 0.3064272701740265,
      "eval_precision": 0.8690476190476191,
      "eval_recall": 0.5770750988142292,
      "eval_runtime": 48.2701,
      "eval_samples_per_second": 5.718,
      "eval_steps_per_second": 0.186,
      "step": 960
    },
    {
      "epoch": 0.891465677179963,
      "grad_norm": 4.68550968170166,
      "learning_rate": 7.094062839777838e-07,
      "loss": 0.1854,
      "step": 961
    },
    {
      "epoch": 0.8923933209647495,
      "grad_norm": 5.072958946228027,
      "learning_rate": 6.974738833861383e-07,
      "loss": 0.1762,
      "step": 962
    },
    {
      "epoch": 0.8933209647495362,
      "grad_norm": 4.519327640533447,
      "learning_rate": 6.856390618915775e-07,
      "loss": 0.182,
      "step": 963
    },
    {
      "epoch": 0.8942486085343229,
      "grad_norm": 5.558988094329834,
      "learning_rate": 6.739019436357774e-07,
      "loss": 0.1665,
      "step": 964
    },
    {
      "epoch": 0.8951762523191095,
      "grad_norm": 2.263278007507324,
      "learning_rate": 6.622626517355557e-07,
      "loss": 0.1112,
      "step": 965
    },
    {
      "epoch": 0.8961038961038961,
      "grad_norm": 5.888603687286377,
      "learning_rate": 6.507213082815745e-07,
      "loss": 0.1455,
      "step": 966
    },
    {
      "epoch": 0.8970315398886828,
      "grad_norm": 5.091086387634277,
      "learning_rate": 6.392780343370686e-07,
      "loss": 0.1812,
      "step": 967
    },
    {
      "epoch": 0.8979591836734694,
      "grad_norm": 6.290548324584961,
      "learning_rate": 6.279329499365649e-07,
      "loss": 0.1527,
      "step": 968
    },
    {
      "epoch": 0.898886827458256,
      "grad_norm": 6.533473014831543,
      "learning_rate": 6.166861740846297e-07,
      "loss": 0.2105,
      "step": 969
    },
    {
      "epoch": 0.8998144712430427,
      "grad_norm": 3.4495279788970947,
      "learning_rate": 6.055378247546217e-07,
      "loss": 0.1222,
      "step": 970
    },
    {
      "epoch": 0.9007421150278293,
      "grad_norm": 5.290384769439697,
      "learning_rate": 5.94488018887448e-07,
      "loss": 0.2046,
      "step": 971
    },
    {
      "epoch": 0.9016697588126159,
      "grad_norm": 6.091614723205566,
      "learning_rate": 5.835368723903456e-07,
      "loss": 0.2643,
      "step": 972
    },
    {
      "epoch": 0.9025974025974026,
      "grad_norm": 4.488548278808594,
      "learning_rate": 5.726845001356573e-07,
      "loss": 0.1263,
      "step": 973
    },
    {
      "epoch": 0.9035250463821892,
      "grad_norm": 2.7875099182128906,
      "learning_rate": 5.619310159596358e-07,
      "loss": 0.0922,
      "step": 974
    },
    {
      "epoch": 0.9044526901669759,
      "grad_norm": 5.558516025543213,
      "learning_rate": 5.51276532661238e-07,
      "loss": 0.2045,
      "step": 975
    },
    {
      "epoch": 0.9053803339517625,
      "grad_norm": 5.901011943817139,
      "learning_rate": 5.407211620009545e-07,
      "loss": 0.1743,
      "step": 976
    },
    {
      "epoch": 0.9063079777365491,
      "grad_norm": 3.838674783706665,
      "learning_rate": 5.30265014699628e-07,
      "loss": 0.1728,
      "step": 977
    },
    {
      "epoch": 0.9072356215213359,
      "grad_norm": 3.811453104019165,
      "learning_rate": 5.199082004372958e-07,
      "loss": 0.153,
      "step": 978
    },
    {
      "epoch": 0.9081632653061225,
      "grad_norm": 5.14892578125,
      "learning_rate": 5.096508278520385e-07,
      "loss": 0.1991,
      "step": 979
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 3.6292712688446045,
      "learning_rate": 4.994930045388414e-07,
      "loss": 0.1452,
      "step": 980
    },
    {
      "epoch": 0.9090909090909091,
      "eval_accuracy": 0.8603104212860311,
      "eval_f1": 0.7028301886792453,
      "eval_loss": 0.3034472167491913,
      "eval_precision": 0.8713450292397661,
      "eval_recall": 0.5889328063241107,
      "eval_runtime": 48.7572,
      "eval_samples_per_second": 5.661,
      "eval_steps_per_second": 0.185,
      "step": 980
    },
    {
      "epoch": 0.9100185528756958,
      "grad_norm": 3.438109874725342,
      "learning_rate": 4.894348370484648e-07,
      "loss": 0.1054,
      "step": 981
    },
    {
      "epoch": 0.9109461966604824,
      "grad_norm": 5.481462478637695,
      "learning_rate": 4.794764308863242e-07,
      "loss": 0.1463,
      "step": 982
    },
    {
      "epoch": 0.911873840445269,
      "grad_norm": 6.784456253051758,
      "learning_rate": 4.696178905113913e-07,
      "loss": 0.1634,
      "step": 983
    },
    {
      "epoch": 0.9128014842300557,
      "grad_norm": 3.902355194091797,
      "learning_rate": 4.5985931933508757e-07,
      "loss": 0.1689,
      "step": 984
    },
    {
      "epoch": 0.9137291280148423,
      "grad_norm": 4.524623394012451,
      "learning_rate": 4.502008197202068e-07,
      "loss": 0.1428,
      "step": 985
    },
    {
      "epoch": 0.9146567717996289,
      "grad_norm": 3.976349353790283,
      "learning_rate": 4.406424929798403e-07,
      "loss": 0.1864,
      "step": 986
    },
    {
      "epoch": 0.9155844155844156,
      "grad_norm": 3.3905527591705322,
      "learning_rate": 4.3118443937631094e-07,
      "loss": 0.1719,
      "step": 987
    },
    {
      "epoch": 0.9165120593692022,
      "grad_norm": 4.1316938400268555,
      "learning_rate": 4.218267581201296e-07,
      "loss": 0.1124,
      "step": 988
    },
    {
      "epoch": 0.9174397031539888,
      "grad_norm": 5.6381754875183105,
      "learning_rate": 4.125695473689406e-07,
      "loss": 0.1994,
      "step": 989
    },
    {
      "epoch": 0.9183673469387755,
      "grad_norm": 7.625948905944824,
      "learning_rate": 4.034129042265067e-07,
      "loss": 0.2211,
      "step": 990
    },
    {
      "epoch": 0.9192949907235621,
      "grad_norm": 3.567246437072754,
      "learning_rate": 3.943569247416801e-07,
      "loss": 0.1359,
      "step": 991
    },
    {
      "epoch": 0.9202226345083488,
      "grad_norm": 4.336119174957275,
      "learning_rate": 3.8540170390740097e-07,
      "loss": 0.1519,
      "step": 992
    },
    {
      "epoch": 0.9211502782931354,
      "grad_norm": 4.9389848709106445,
      "learning_rate": 3.7654733565969826e-07,
      "loss": 0.1874,
      "step": 993
    },
    {
      "epoch": 0.922077922077922,
      "grad_norm": 3.25769305229187,
      "learning_rate": 3.67793912876705e-07,
      "loss": 0.1191,
      "step": 994
    },
    {
      "epoch": 0.9230055658627088,
      "grad_norm": 3.4334826469421387,
      "learning_rate": 3.591415273776855e-07,
      "loss": 0.1012,
      "step": 995
    },
    {
      "epoch": 0.9239332096474954,
      "grad_norm": 3.1981468200683594,
      "learning_rate": 3.5059026992206645e-07,
      "loss": 0.0812,
      "step": 996
    },
    {
      "epoch": 0.924860853432282,
      "grad_norm": 5.118222236633301,
      "learning_rate": 3.421402302084953e-07,
      "loss": 0.1293,
      "step": 997
    },
    {
      "epoch": 0.9257884972170687,
      "grad_norm": 4.047184944152832,
      "learning_rate": 3.3379149687388866e-07,
      "loss": 0.1723,
      "step": 998
    },
    {
      "epoch": 0.9267161410018553,
      "grad_norm": 7.083133220672607,
      "learning_rate": 3.255441574925089e-07,
      "loss": 0.2061,
      "step": 999
    },
    {
      "epoch": 0.9276437847866419,
      "grad_norm": 2.8097355365753174,
      "learning_rate": 3.1739829857504235e-07,
      "loss": 0.086,
      "step": 1000
    },
    {
      "epoch": 0.9276437847866419,
      "eval_accuracy": 0.8580931263858093,
      "eval_f1": 0.6966824644549763,
      "eval_loss": 0.30505669116973877,
      "eval_precision": 0.8698224852071006,
      "eval_recall": 0.5810276679841897,
      "eval_runtime": 47.8654,
      "eval_samples_per_second": 5.766,
      "eval_steps_per_second": 0.188,
      "step": 1000
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 6.499805927276611,
      "learning_rate": 3.093540055676958e-07,
      "loss": 0.2015,
      "step": 1001
    },
    {
      "epoch": 0.9294990723562152,
      "grad_norm": 4.742324352264404,
      "learning_rate": 3.0141136285129825e-07,
      "loss": 0.1585,
      "step": 1002
    },
    {
      "epoch": 0.9304267161410018,
      "grad_norm": 4.395940780639648,
      "learning_rate": 2.935704537404083e-07,
      "loss": 0.1249,
      "step": 1003
    },
    {
      "epoch": 0.9313543599257885,
      "grad_norm": 3.036573886871338,
      "learning_rate": 2.8583136048245697e-07,
      "loss": 0.1331,
      "step": 1004
    },
    {
      "epoch": 0.9322820037105751,
      "grad_norm": 4.401485919952393,
      "learning_rate": 2.781941642568686e-07,
      "loss": 0.2138,
      "step": 1005
    },
    {
      "epoch": 0.9332096474953617,
      "grad_norm": 4.973133087158203,
      "learning_rate": 2.706589451742181e-07,
      "loss": 0.2253,
      "step": 1006
    },
    {
      "epoch": 0.9341372912801484,
      "grad_norm": 6.711733818054199,
      "learning_rate": 2.632257822753881e-07,
      "loss": 0.2465,
      "step": 1007
    },
    {
      "epoch": 0.935064935064935,
      "grad_norm": 3.2245848178863525,
      "learning_rate": 2.5589475353073987e-07,
      "loss": 0.1524,
      "step": 1008
    },
    {
      "epoch": 0.9359925788497218,
      "grad_norm": 3.8495306968688965,
      "learning_rate": 2.486659358392951e-07,
      "loss": 0.1646,
      "step": 1009
    },
    {
      "epoch": 0.9369202226345084,
      "grad_norm": 5.713381290435791,
      "learning_rate": 2.4153940502793185e-07,
      "loss": 0.2161,
      "step": 1010
    },
    {
      "epoch": 0.937847866419295,
      "grad_norm": 3.7789957523345947,
      "learning_rate": 2.3451523585058756e-07,
      "loss": 0.1509,
      "step": 1011
    },
    {
      "epoch": 0.9387755102040817,
      "grad_norm": 4.0073652267456055,
      "learning_rate": 2.2759350198746978e-07,
      "loss": 0.1402,
      "step": 1012
    },
    {
      "epoch": 0.9397031539888683,
      "grad_norm": 3.3210415840148926,
      "learning_rate": 2.2077427604429435e-07,
      "loss": 0.1431,
      "step": 1013
    },
    {
      "epoch": 0.9406307977736549,
      "grad_norm": 5.2902750968933105,
      "learning_rate": 2.1405762955151178e-07,
      "loss": 0.1239,
      "step": 1014
    },
    {
      "epoch": 0.9415584415584416,
      "grad_norm": 5.931840419769287,
      "learning_rate": 2.0744363296356872e-07,
      "loss": 0.1965,
      "step": 1015
    },
    {
      "epoch": 0.9424860853432282,
      "grad_norm": 3.9065020084381104,
      "learning_rate": 2.009323556581566e-07,
      "loss": 0.1344,
      "step": 1016
    },
    {
      "epoch": 0.9434137291280148,
      "grad_norm": 3.194225311279297,
      "learning_rate": 1.9452386593549534e-07,
      "loss": 0.0979,
      "step": 1017
    },
    {
      "epoch": 0.9443413729128015,
      "grad_norm": 3.794304847717285,
      "learning_rate": 1.8821823101760949e-07,
      "loss": 0.2038,
      "step": 1018
    },
    {
      "epoch": 0.9452690166975881,
      "grad_norm": 3.638219118118286,
      "learning_rate": 1.8201551704762453e-07,
      "loss": 0.1254,
      "step": 1019
    },
    {
      "epoch": 0.9461966604823747,
      "grad_norm": 4.820856094360352,
      "learning_rate": 1.7591578908907724e-07,
      "loss": 0.1909,
      "step": 1020
    },
    {
      "epoch": 0.9461966604823747,
      "eval_accuracy": 0.8580931263858093,
      "eval_f1": 0.6966824644549763,
      "eval_loss": 0.3055438697338104,
      "eval_precision": 0.8698224852071006,
      "eval_recall": 0.5810276679841897,
      "eval_runtime": 47.7431,
      "eval_samples_per_second": 5.781,
      "eval_steps_per_second": 0.189,
      "step": 1020
    },
    {
      "epoch": 0.9471243042671614,
      "grad_norm": 3.5032293796539307,
      "learning_rate": 1.699191111252241e-07,
      "loss": 0.077,
      "step": 1021
    },
    {
      "epoch": 0.948051948051948,
      "grad_norm": 3.7761011123657227,
      "learning_rate": 1.6402554605838173e-07,
      "loss": 0.1564,
      "step": 1022
    },
    {
      "epoch": 0.9489795918367347,
      "grad_norm": 5.951882839202881,
      "learning_rate": 1.5823515570925763e-07,
      "loss": 0.2323,
      "step": 1023
    },
    {
      "epoch": 0.9499072356215214,
      "grad_norm": 4.935650825500488,
      "learning_rate": 1.5254800081630828e-07,
      "loss": 0.2172,
      "step": 1024
    },
    {
      "epoch": 0.950834879406308,
      "grad_norm": 5.279281139373779,
      "learning_rate": 1.469641410350964e-07,
      "loss": 0.1845,
      "step": 1025
    },
    {
      "epoch": 0.9517625231910947,
      "grad_norm": 5.034005641937256,
      "learning_rate": 1.4148363493766803e-07,
      "loss": 0.174,
      "step": 1026
    },
    {
      "epoch": 0.9526901669758813,
      "grad_norm": 3.964360237121582,
      "learning_rate": 1.361065400119399e-07,
      "loss": 0.0888,
      "step": 1027
    },
    {
      "epoch": 0.9536178107606679,
      "grad_norm": 4.862616062164307,
      "learning_rate": 1.30832912661093e-07,
      "loss": 0.2007,
      "step": 1028
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 4.140252590179443,
      "learning_rate": 1.2566280820298427e-07,
      "loss": 0.13,
      "step": 1029
    },
    {
      "epoch": 0.9554730983302412,
      "grad_norm": 5.299205780029297,
      "learning_rate": 1.2059628086956044e-07,
      "loss": 0.1795,
      "step": 1030
    },
    {
      "epoch": 0.9564007421150278,
      "grad_norm": 5.694372653961182,
      "learning_rate": 1.1563338380629618e-07,
      "loss": 0.2278,
      "step": 1031
    },
    {
      "epoch": 0.9573283858998145,
      "grad_norm": 4.10621452331543,
      "learning_rate": 1.1077416907163573e-07,
      "loss": 0.1832,
      "step": 1032
    },
    {
      "epoch": 0.9582560296846011,
      "grad_norm": 3.0105836391448975,
      "learning_rate": 1.0601868763643997e-07,
      "loss": 0.1126,
      "step": 1033
    },
    {
      "epoch": 0.9591836734693877,
      "grad_norm": 5.412391185760498,
      "learning_rate": 1.0136698938346012e-07,
      "loss": 0.1996,
      "step": 1034
    },
    {
      "epoch": 0.9601113172541744,
      "grad_norm": 3.507596492767334,
      "learning_rate": 9.68191231068083e-08,
      "loss": 0.1647,
      "step": 1035
    },
    {
      "epoch": 0.961038961038961,
      "grad_norm": 4.733442783355713,
      "learning_rate": 9.237513651145224e-08,
      "loss": 0.102,
      "step": 1036
    },
    {
      "epoch": 0.9619666048237476,
      "grad_norm": 6.855641841888428,
      "learning_rate": 8.80350762127058e-08,
      "loss": 0.1197,
      "step": 1037
    },
    {
      "epoch": 0.9628942486085343,
      "grad_norm": 3.809262275695801,
      "learning_rate": 8.379898773574924e-08,
      "loss": 0.1287,
      "step": 1038
    },
    {
      "epoch": 0.963821892393321,
      "grad_norm": 3.4764761924743652,
      "learning_rate": 7.966691551514527e-08,
      "loss": 0.1106,
      "step": 1039
    },
    {
      "epoch": 0.9647495361781077,
      "grad_norm": 5.395627021789551,
      "learning_rate": 7.563890289437825e-08,
      "loss": 0.2017,
      "step": 1040
    },
    {
      "epoch": 0.9647495361781077,
      "eval_accuracy": 0.8580931263858093,
      "eval_f1": 0.6952380952380952,
      "eval_loss": 0.30581432580947876,
      "eval_precision": 0.874251497005988,
      "eval_recall": 0.5770750988142292,
      "eval_runtime": 48.746,
      "eval_samples_per_second": 5.662,
      "eval_steps_per_second": 0.185,
      "step": 1040
    },
    {
      "epoch": 0.9656771799628943,
      "grad_norm": 3.9932026863098145,
      "learning_rate": 7.171499212539124e-08,
      "loss": 0.1513,
      "step": 1041
    },
    {
      "epoch": 0.9666048237476809,
      "grad_norm": 5.8107075691223145,
      "learning_rate": 6.78952243681541e-08,
      "loss": 0.172,
      "step": 1042
    },
    {
      "epoch": 0.9675324675324676,
      "grad_norm": 3.7357017993927,
      "learning_rate": 6.417963969022389e-08,
      "loss": 0.1422,
      "step": 1043
    },
    {
      "epoch": 0.9684601113172542,
      "grad_norm": 3.854876756668091,
      "learning_rate": 6.056827706632185e-08,
      "loss": 0.1587,
      "step": 1044
    },
    {
      "epoch": 0.9693877551020408,
      "grad_norm": 6.006348133087158,
      "learning_rate": 5.7061174377937015e-08,
      "loss": 0.2244,
      "step": 1045
    },
    {
      "epoch": 0.9703153988868275,
      "grad_norm": 4.745636463165283,
      "learning_rate": 5.365836841291439e-08,
      "loss": 0.1803,
      "step": 1046
    },
    {
      "epoch": 0.9712430426716141,
      "grad_norm": 3.8510711193084717,
      "learning_rate": 5.035989486508075e-08,
      "loss": 0.1635,
      "step": 1047
    },
    {
      "epoch": 0.9721706864564007,
      "grad_norm": 5.504276752471924,
      "learning_rate": 4.716578833386054e-08,
      "loss": 0.1517,
      "step": 1048
    },
    {
      "epoch": 0.9730983302411874,
      "grad_norm": 3.3400299549102783,
      "learning_rate": 4.4076082323920576e-08,
      "loss": 0.1494,
      "step": 1049
    },
    {
      "epoch": 0.974025974025974,
      "grad_norm": 5.584471225738525,
      "learning_rate": 4.109080924481479e-08,
      "loss": 0.1781,
      "step": 1050
    },
    {
      "epoch": 0.9749536178107606,
      "grad_norm": 4.575666904449463,
      "learning_rate": 3.82100004106456e-08,
      "loss": 0.1298,
      "step": 1051
    },
    {
      "epoch": 0.9758812615955473,
      "grad_norm": 3.4456560611724854,
      "learning_rate": 3.543368603973529e-08,
      "loss": 0.1292,
      "step": 1052
    },
    {
      "epoch": 0.9768089053803339,
      "grad_norm": 2.841853618621826,
      "learning_rate": 3.2761895254306285e-08,
      "loss": 0.076,
      "step": 1053
    },
    {
      "epoch": 0.9777365491651205,
      "grad_norm": 4.662397384643555,
      "learning_rate": 3.019465608018024e-08,
      "loss": 0.2181,
      "step": 1054
    },
    {
      "epoch": 0.9786641929499073,
      "grad_norm": 3.259526014328003,
      "learning_rate": 2.773199544648164e-08,
      "loss": 0.108,
      "step": 1055
    },
    {
      "epoch": 0.9795918367346939,
      "grad_norm": 4.32330322265625,
      "learning_rate": 2.537393918535358e-08,
      "loss": 0.2068,
      "step": 1056
    },
    {
      "epoch": 0.9805194805194806,
      "grad_norm": 4.7618536949157715,
      "learning_rate": 2.312051203169352e-08,
      "loss": 0.1936,
      "step": 1057
    },
    {
      "epoch": 0.9814471243042672,
      "grad_norm": 4.779612064361572,
      "learning_rate": 2.0971737622883515e-08,
      "loss": 0.1007,
      "step": 1058
    },
    {
      "epoch": 0.9823747680890538,
      "grad_norm": 4.346301078796387,
      "learning_rate": 1.8927638498551502e-08,
      "loss": 0.1594,
      "step": 1059
    },
    {
      "epoch": 0.9833024118738405,
      "grad_norm": 4.017016410827637,
      "learning_rate": 1.698823610032929e-08,
      "loss": 0.1828,
      "step": 1060
    },
    {
      "epoch": 0.9833024118738405,
      "eval_accuracy": 0.8603104212860311,
      "eval_f1": 0.7028301886792453,
      "eval_loss": 0.306577205657959,
      "eval_precision": 0.8713450292397661,
      "eval_recall": 0.5889328063241107,
      "eval_runtime": 47.7001,
      "eval_samples_per_second": 5.786,
      "eval_steps_per_second": 0.189,
      "step": 1060
    },
    {
      "epoch": 0.9842300556586271,
      "grad_norm": 5.6250505447387695,
      "learning_rate": 1.5153550771630498e-08,
      "loss": 0.17,
      "step": 1061
    },
    {
      "epoch": 0.9851576994434137,
      "grad_norm": 5.426425933837891,
      "learning_rate": 1.3423601757436289e-08,
      "loss": 0.2122,
      "step": 1062
    },
    {
      "epoch": 0.9860853432282004,
      "grad_norm": 4.71135950088501,
      "learning_rate": 1.179840720409331e-08,
      "loss": 0.1715,
      "step": 1063
    },
    {
      "epoch": 0.987012987012987,
      "grad_norm": 4.350978851318359,
      "learning_rate": 1.0277984159122734e-08,
      "loss": 0.1704,
      "step": 1064
    },
    {
      "epoch": 0.9879406307977736,
      "grad_norm": 5.211360931396484,
      "learning_rate": 8.862348571043733e-09,
      "loss": 0.166,
      "step": 1065
    },
    {
      "epoch": 0.9888682745825603,
      "grad_norm": 4.015779495239258,
      "learning_rate": 7.551515289203615e-09,
      "loss": 0.1616,
      "step": 1066
    },
    {
      "epoch": 0.9897959183673469,
      "grad_norm": 4.356948375701904,
      "learning_rate": 6.345498063622391e-09,
      "loss": 0.1961,
      "step": 1067
    },
    {
      "epoch": 0.9907235621521335,
      "grad_norm": 6.508297920227051,
      "learning_rate": 5.2443095448506674e-09,
      "loss": 0.1935,
      "step": 1068
    },
    {
      "epoch": 0.9916512059369202,
      "grad_norm": 4.595229625701904,
      "learning_rate": 4.247961283835311e-09,
      "loss": 0.2116,
      "step": 1069
    },
    {
      "epoch": 0.9925788497217068,
      "grad_norm": 4.39501428604126,
      "learning_rate": 3.3564637317984318e-09,
      "loss": 0.1568,
      "step": 1070
    },
    {
      "epoch": 0.9935064935064936,
      "grad_norm": 4.391909599304199,
      "learning_rate": 2.5698262401263607e-09,
      "loss": 0.1553,
      "step": 1071
    },
    {
      "epoch": 0.9944341372912802,
      "grad_norm": 3.195699453353882,
      "learning_rate": 1.888057060274173e-09,
      "loss": 0.1469,
      "step": 1072
    },
    {
      "epoch": 0.9953617810760668,
      "grad_norm": 5.479938507080078,
      "learning_rate": 1.3111633436779792e-09,
      "loss": 0.1662,
      "step": 1073
    },
    {
      "epoch": 0.9962894248608535,
      "grad_norm": 4.181588172912598,
      "learning_rate": 8.391511416816489e-10,
      "loss": 0.1746,
      "step": 1074
    },
    {
      "epoch": 0.9972170686456401,
      "grad_norm": 4.144800662994385,
      "learning_rate": 4.720254054679796e-10,
      "loss": 0.1624,
      "step": 1075
    },
    {
      "epoch": 0.9981447124304267,
      "grad_norm": 3.857682228088379,
      "learning_rate": 2.0978998601206558e-10,
      "loss": 0.1293,
      "step": 1076
    },
    {
      "epoch": 0.9990723562152134,
      "grad_norm": 5.734769344329834,
      "learning_rate": 5.244763404133046e-11,
      "loss": 0.1897,
      "step": 1077
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.7049508094787598,
      "learning_rate": 0.0,
      "loss": 0.1706,
      "step": 1078
    }
  ],
  "logging_steps": 1,
  "max_steps": 1078,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.4499307937307034e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}