{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 176,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011363636363636364,
      "grad_norm": 0.04888428873089485,
      "learning_rate": 2.777777777777778e-06,
      "loss": 0.9533,
      "step": 1
    },
    {
      "epoch": 0.022727272727272728,
      "grad_norm": 0.04118674609403888,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.8187,
      "step": 2
    },
    {
      "epoch": 0.03409090909090909,
      "grad_norm": 0.036867673437168666,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.7078,
      "step": 3
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 0.04847692066919062,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.987,
      "step": 4
    },
    {
      "epoch": 0.056818181818181816,
      "grad_norm": 0.05003862080856868,
      "learning_rate": 1.388888888888889e-05,
      "loss": 0.9577,
      "step": 5
    },
    {
      "epoch": 0.06818181818181818,
      "grad_norm": 0.04493399553279938,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.9205,
      "step": 6
    },
    {
      "epoch": 0.07954545454545454,
      "grad_norm": 0.044174232851205655,
      "learning_rate": 1.9444444444444445e-05,
      "loss": 0.7971,
      "step": 7
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 0.0537270325545959,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.875,
      "step": 8
    },
    {
      "epoch": 0.10227272727272728,
      "grad_norm": 0.047274651714941,
      "learning_rate": 2.5e-05,
      "loss": 0.7865,
      "step": 9
    },
    {
      "epoch": 0.11363636363636363,
      "grad_norm": 0.047438139846740904,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.7949,
      "step": 10
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.0486064821581454,
      "learning_rate": 3.055555555555556e-05,
      "loss": 0.9187,
      "step": 11
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 0.049768338512046005,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.927,
      "step": 12
    },
    {
      "epoch": 0.14772727272727273,
      "grad_norm": 0.050752786859426545,
      "learning_rate": 3.611111111111111e-05,
      "loss": 0.882,
      "step": 13
    },
    {
      "epoch": 0.1590909090909091,
      "grad_norm": 0.04238163918748248,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.8273,
      "step": 14
    },
    {
      "epoch": 0.17045454545454544,
      "grad_norm": 0.03389553366668896,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.801,
      "step": 15
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.03219935695711762,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.8313,
      "step": 16
    },
    {
      "epoch": 0.19318181818181818,
      "grad_norm": 0.027821411081551388,
      "learning_rate": 4.722222222222222e-05,
      "loss": 0.6832,
      "step": 17
    },
    {
      "epoch": 0.20454545454545456,
      "grad_norm": 0.028125631584449494,
      "learning_rate": 5e-05,
      "loss": 0.724,
      "step": 18
    },
    {
      "epoch": 0.2159090909090909,
      "grad_norm": 0.03372930491801512,
      "learning_rate": 4.9995058244251644e-05,
      "loss": 0.765,
      "step": 19
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 0.03207593160425088,
      "learning_rate": 4.9980234930682546e-05,
      "loss": 0.8319,
      "step": 20
    },
    {
      "epoch": 0.23863636363636365,
      "grad_norm": 0.04392253595539216,
      "learning_rate": 4.995553591954832e-05,
      "loss": 0.8572,
      "step": 21
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.043837015398686424,
      "learning_rate": 4.99209709753674e-05,
      "loss": 0.7994,
      "step": 22
    },
    {
      "epoch": 0.26136363636363635,
      "grad_norm": 0.038660838245880964,
      "learning_rate": 4.9876553763060684e-05,
      "loss": 0.7595,
      "step": 23
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.03958181928823714,
      "learning_rate": 4.982230184254933e-05,
      "loss": 0.7524,
      "step": 24
    },
    {
      "epoch": 0.2840909090909091,
      "grad_norm": 0.04692096023674341,
      "learning_rate": 4.975823666181255e-05,
      "loss": 0.7565,
      "step": 25
    },
    {
      "epoch": 0.29545454545454547,
      "grad_norm": 0.039034963022689224,
      "learning_rate": 4.968438354840834e-05,
      "loss": 0.8968,
      "step": 26
    },
    {
      "epoch": 0.3068181818181818,
      "grad_norm": 0.03472677387974209,
      "learning_rate": 4.960077169946052e-05,
      "loss": 0.7522,
      "step": 27
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 0.031244118470989204,
      "learning_rate": 4.950743417011591e-05,
      "loss": 0.7937,
      "step": 28
    },
    {
      "epoch": 0.32954545454545453,
      "grad_norm": 0.029092500515729473,
      "learning_rate": 4.940440786047628e-05,
      "loss": 0.667,
      "step": 29
    },
    {
      "epoch": 0.3409090909090909,
      "grad_norm": 0.028474671621308404,
      "learning_rate": 4.929173350101025e-05,
      "loss": 0.7255,
      "step": 30
    },
    {
      "epoch": 0.3522727272727273,
      "grad_norm": 0.021514453472108053,
      "learning_rate": 4.9169455636450935e-05,
      "loss": 0.7683,
      "step": 31
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.01979063211912252,
      "learning_rate": 4.903762260818551e-05,
      "loss": 0.7236,
      "step": 32
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.019373274784309575,
      "learning_rate": 4.889628653514402e-05,
      "loss": 0.6894,
      "step": 33
    },
    {
      "epoch": 0.38636363636363635,
      "grad_norm": 0.01807357066294673,
      "learning_rate": 4.874550329319457e-05,
      "loss": 0.7558,
      "step": 34
    },
    {
      "epoch": 0.3977272727272727,
      "grad_norm": 0.01770418827474799,
      "learning_rate": 4.8585332493053364e-05,
      "loss": 0.6813,
      "step": 35
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 0.01675836399147525,
      "learning_rate": 4.84158374567182e-05,
      "loss": 0.7559,
      "step": 36
    },
    {
      "epoch": 0.42045454545454547,
      "grad_norm": 0.021175097986321438,
      "learning_rate": 4.8237085192434676e-05,
      "loss": 0.8176,
      "step": 37
    },
    {
      "epoch": 0.4318181818181818,
      "grad_norm": 0.017100608642967,
      "learning_rate": 4.804914636820517e-05,
      "loss": 0.7112,
      "step": 38
    },
    {
      "epoch": 0.4431818181818182,
      "grad_norm": 0.01683117973292665,
      "learning_rate": 4.7852095283850866e-05,
      "loss": 0.7345,
      "step": 39
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.019570606734413423,
      "learning_rate": 4.764600984163808e-05,
      "loss": 0.8125,
      "step": 40
    },
    {
      "epoch": 0.4659090909090909,
      "grad_norm": 0.015675238814520476,
      "learning_rate": 4.743097151548031e-05,
      "loss": 0.6994,
      "step": 41
    },
    {
      "epoch": 0.4772727272727273,
      "grad_norm": 0.019792988850059114,
      "learning_rate": 4.72070653187283e-05,
      "loss": 0.7837,
      "step": 42
    },
    {
      "epoch": 0.48863636363636365,
      "grad_norm": 0.015785852432543244,
      "learning_rate": 4.6974379770560846e-05,
      "loss": 0.6608,
      "step": 43
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.015533678745760247,
      "learning_rate": 4.673300686098957e-05,
      "loss": 0.7031,
      "step": 44
    },
    {
      "epoch": 0.5113636363636364,
      "grad_norm": 0.01921291960352695,
      "learning_rate": 4.648304201449153e-05,
      "loss": 0.8267,
      "step": 45
    },
    {
      "epoch": 0.5227272727272727,
      "grad_norm": 0.01614254754588724,
      "learning_rate": 4.6224584052284106e-05,
      "loss": 0.7058,
      "step": 46
    },
    {
      "epoch": 0.5340909090909091,
      "grad_norm": 0.019677063872610357,
      "learning_rate": 4.5957735153256915e-05,
      "loss": 0.6621,
      "step": 47
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.013519303189431392,
      "learning_rate": 4.5682600813576435e-05,
      "loss": 0.7478,
      "step": 48
    },
    {
      "epoch": 0.5568181818181818,
      "grad_norm": 0.013215293773761478,
      "learning_rate": 4.539928980497903e-05,
      "loss": 0.7034,
      "step": 49
    },
    {
      "epoch": 0.5681818181818182,
      "grad_norm": 0.013694552146445563,
      "learning_rate": 4.510791413176912e-05,
      "loss": 0.7448,
      "step": 50
    },
    {
      "epoch": 0.5795454545454546,
      "grad_norm": 0.016162877179262552,
      "learning_rate": 4.480858898653936e-05,
      "loss": 0.6728,
      "step": 51
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 0.017056245721837348,
      "learning_rate": 4.4501432704630305e-05,
      "loss": 0.6714,
      "step": 52
    },
    {
      "epoch": 0.6022727272727273,
      "grad_norm": 0.01602874080265432,
      "learning_rate": 4.41865667173477e-05,
      "loss": 0.7667,
      "step": 53
    },
    {
      "epoch": 0.6136363636363636,
      "grad_norm": 0.01556595840862479,
      "learning_rate": 4.386411550395576e-05,
      "loss": 0.6934,
      "step": 54
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.014885950964239066,
      "learning_rate": 4.353420654246546e-05,
      "loss": 0.6909,
      "step": 55
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 0.01399086114921709,
      "learning_rate": 4.319697025923736e-05,
      "loss": 0.6817,
      "step": 56
    },
    {
      "epoch": 0.6477272727272727,
      "grad_norm": 0.016980372482516305,
      "learning_rate": 4.285253997741875e-05,
      "loss": 0.7485,
      "step": 57
    },
    {
      "epoch": 0.6590909090909091,
      "grad_norm": 0.01370669813419946,
      "learning_rate": 4.2501051864235636e-05,
      "loss": 0.5524,
      "step": 58
    },
    {
      "epoch": 0.6704545454545454,
      "grad_norm": 0.0161962614922305,
      "learning_rate": 4.214264487716033e-05,
      "loss": 0.7145,
      "step": 59
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 0.01432616251653496,
      "learning_rate": 4.177746070897592e-05,
      "loss": 0.7263,
      "step": 60
    },
    {
      "epoch": 0.6931818181818182,
      "grad_norm": 0.01515485647301396,
      "learning_rate": 4.140564373175939e-05,
      "loss": 0.6531,
      "step": 61
    },
    {
      "epoch": 0.7045454545454546,
      "grad_norm": 0.014400704458474281,
      "learning_rate": 4.10273409398055e-05,
      "loss": 0.7696,
      "step": 62
    },
    {
      "epoch": 0.7159090909090909,
      "grad_norm": 0.015458672360864132,
      "learning_rate": 4.0642701891514e-05,
      "loss": 0.7081,
      "step": 63
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.015263330526513203,
      "learning_rate": 4.025187865026311e-05,
      "loss": 0.725,
      "step": 64
    },
    {
      "epoch": 0.7386363636363636,
      "grad_norm": 0.015125337784791405,
      "learning_rate": 3.985502572429276e-05,
      "loss": 0.7111,
      "step": 65
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.013985325014602094,
      "learning_rate": 3.945230000562121e-05,
      "loss": 0.7249,
      "step": 66
    },
    {
      "epoch": 0.7613636363636364,
      "grad_norm": 0.0155589237978013,
      "learning_rate": 3.9043860708019273e-05,
      "loss": 0.6881,
      "step": 67
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 0.01882918883166355,
      "learning_rate": 3.862986930406669e-05,
      "loss": 0.8102,
      "step": 68
    },
    {
      "epoch": 0.7840909090909091,
      "grad_norm": 0.015308078133970605,
      "learning_rate": 3.821048946131549e-05,
      "loss": 0.6919,
      "step": 69
    },
    {
      "epoch": 0.7954545454545454,
      "grad_norm": 0.01630125314346408,
      "learning_rate": 3.778588697758556e-05,
      "loss": 0.6464,
      "step": 70
    },
    {
      "epoch": 0.8068181818181818,
      "grad_norm": 0.015050157672318546,
      "learning_rate": 3.7356229715418074e-05,
      "loss": 0.7114,
      "step": 71
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.015186905856860966,
      "learning_rate": 3.6921687535712656e-05,
      "loss": 0.719,
      "step": 72
    },
    {
      "epoch": 0.8295454545454546,
      "grad_norm": 0.01935797435359767,
      "learning_rate": 3.6482432230574446e-05,
      "loss": 0.7255,
      "step": 73
    },
    {
      "epoch": 0.8409090909090909,
      "grad_norm": 0.016661093988049422,
      "learning_rate": 3.60386374553978e-05,
      "loss": 0.6642,
      "step": 74
    },
    {
      "epoch": 0.8522727272727273,
      "grad_norm": 0.017167771916012636,
      "learning_rate": 3.5590478660213214e-05,
      "loss": 0.677,
      "step": 75
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 0.015022481447368145,
      "learning_rate": 3.5138133020324845e-05,
      "loss": 0.7307,
      "step": 76
    },
    {
      "epoch": 0.875,
      "grad_norm": 0.01785502395194187,
      "learning_rate": 3.468177936626603e-05,
      "loss": 0.789,
      "step": 77
    },
    {
      "epoch": 0.8863636363636364,
      "grad_norm": 0.01864810858161923,
      "learning_rate": 3.4221598113100195e-05,
      "loss": 0.7059,
      "step": 78
    },
    {
      "epoch": 0.8977272727272727,
      "grad_norm": 0.016575657529251383,
      "learning_rate": 3.375777118909561e-05,
      "loss": 0.7456,
      "step": 79
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.016188984904551812,
      "learning_rate": 3.32904819638017e-05,
      "loss": 0.683,
      "step": 80
    },
    {
      "epoch": 0.9204545454545454,
      "grad_norm": 0.016436588560373562,
      "learning_rate": 3.2819915175555684e-05,
      "loss": 0.6475,
      "step": 81
    },
    {
      "epoch": 0.9318181818181818,
      "grad_norm": 0.017564054129248746,
      "learning_rate": 3.234625685844803e-05,
      "loss": 0.622,
      "step": 82
    },
    {
      "epoch": 0.9431818181818182,
      "grad_norm": 0.019239130214828547,
      "learning_rate": 3.186969426877563e-05,
      "loss": 0.638,
      "step": 83
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 0.01778558528784305,
      "learning_rate": 3.139041581101187e-05,
      "loss": 0.5941,
      "step": 84
    },
    {
      "epoch": 0.9659090909090909,
      "grad_norm": 0.03326719961885704,
      "learning_rate": 3.090861096332263e-05,
      "loss": 0.6721,
      "step": 85
    },
    {
      "epoch": 0.9772727272727273,
      "grad_norm": 0.017697778364759945,
      "learning_rate": 3.042447020265795e-05,
      "loss": 0.663,
      "step": 86
    },
    {
      "epoch": 0.9886363636363636,
      "grad_norm": 0.015032572277755535,
      "learning_rate": 2.993818492944882e-05,
      "loss": 0.6462,
      "step": 87
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.01697573905444168,
      "learning_rate": 2.9449947391938766e-05,
      "loss": 0.6957,
      "step": 88
    },
    {
      "epoch": 1.0113636363636365,
      "grad_norm": 0.01629821245832795,
      "learning_rate": 2.8959950610180374e-05,
      "loss": 0.6629,
      "step": 89
    },
    {
      "epoch": 1.0227272727272727,
      "grad_norm": 0.015172985524910379,
      "learning_rate": 2.8468388299726712e-05,
      "loss": 0.6602,
      "step": 90
    },
    {
      "epoch": 1.0340909090909092,
      "grad_norm": 0.015577909780648352,
      "learning_rate": 2.7975454795047622e-05,
      "loss": 0.796,
      "step": 91
    },
    {
      "epoch": 1.0454545454545454,
      "grad_norm": 0.017309986409190056,
      "learning_rate": 2.7481344972701545e-05,
      "loss": 0.6618,
      "step": 92
    },
    {
      "epoch": 1.0568181818181819,
      "grad_norm": 0.01661621611638882,
      "learning_rate": 2.6986254174292862e-05,
      "loss": 0.7065,
      "step": 93
    },
    {
      "epoch": 1.0681818181818181,
      "grad_norm": 0.016737287474769654,
      "learning_rate": 2.6490378129245498e-05,
      "loss": 0.6457,
      "step": 94
    },
    {
      "epoch": 1.0795454545454546,
      "grad_norm": 0.016921442525318752,
      "learning_rate": 2.599391287742315e-05,
      "loss": 0.7422,
      "step": 95
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.01644141496345415,
      "learning_rate": 2.5497054691626753e-05,
      "loss": 0.7125,
      "step": 96
    },
    {
      "epoch": 1.1022727272727273,
      "grad_norm": 0.01566715623525306,
      "learning_rate": 2.5e-05,
      "loss": 0.7015,
      "step": 97
    },
    {
      "epoch": 1.1136363636363635,
      "grad_norm": 0.016042962886209804,
      "learning_rate": 2.4502945308373246e-05,
      "loss": 0.6911,
      "step": 98
    },
    {
      "epoch": 1.125,
      "grad_norm": 0.014451142623462782,
      "learning_rate": 2.4006087122576863e-05,
      "loss": 0.6499,
      "step": 99
    },
    {
      "epoch": 1.1363636363636362,
      "grad_norm": 0.016365537745248963,
      "learning_rate": 2.3509621870754505e-05,
      "loss": 0.6564,
      "step": 100
    },
    {
      "epoch": 1.1477272727272727,
      "grad_norm": 0.015223080653847816,
      "learning_rate": 2.301374582570714e-05,
      "loss": 0.6767,
      "step": 101
    },
    {
      "epoch": 1.1590909090909092,
      "grad_norm": 0.017013122218294784,
      "learning_rate": 2.2518655027298464e-05,
      "loss": 0.6712,
      "step": 102
    },
    {
      "epoch": 1.1704545454545454,
      "grad_norm": 0.017431829042961085,
      "learning_rate": 2.2024545204952383e-05,
      "loss": 0.6363,
      "step": 103
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 0.01638659813387577,
      "learning_rate": 2.1531611700273297e-05,
      "loss": 0.7341,
      "step": 104
    },
    {
      "epoch": 1.1931818181818181,
      "grad_norm": 0.015883920910595706,
      "learning_rate": 2.104004938981963e-05,
      "loss": 0.7503,
      "step": 105
    },
    {
      "epoch": 1.2045454545454546,
      "grad_norm": 0.016308759795444855,
      "learning_rate": 2.055005260806125e-05,
      "loss": 0.7494,
      "step": 106
    },
    {
      "epoch": 1.2159090909090908,
      "grad_norm": 0.01653825796554113,
      "learning_rate": 2.0061815070551186e-05,
      "loss": 0.584,
      "step": 107
    },
    {
      "epoch": 1.2272727272727273,
      "grad_norm": 0.015995947052341933,
      "learning_rate": 1.957552979734205e-05,
      "loss": 0.7943,
      "step": 108
    },
    {
      "epoch": 1.2386363636363638,
      "grad_norm": 0.018158719978620477,
      "learning_rate": 1.9091389036677382e-05,
      "loss": 0.7001,
      "step": 109
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.015286756025554763,
      "learning_rate": 1.8609584188988136e-05,
      "loss": 0.6132,
      "step": 110
    },
    {
      "epoch": 1.2613636363636362,
      "grad_norm": 0.014766283231039113,
      "learning_rate": 1.813030573122437e-05,
      "loss": 0.6789,
      "step": 111
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.018163850190524557,
      "learning_rate": 1.7653743141551983e-05,
      "loss": 0.6641,
      "step": 112
    },
    {
      "epoch": 1.2840909090909092,
      "grad_norm": 0.015499094565043982,
      "learning_rate": 1.7180084824444325e-05,
      "loss": 0.7034,
      "step": 113
    },
    {
      "epoch": 1.2954545454545454,
      "grad_norm": 0.01666315009242263,
      "learning_rate": 1.6709518036198308e-05,
      "loss": 0.6644,
      "step": 114
    },
    {
      "epoch": 1.3068181818181819,
      "grad_norm": 0.018550049211631166,
      "learning_rate": 1.6242228810904392e-05,
      "loss": 0.6314,
      "step": 115
    },
    {
      "epoch": 1.3181818181818181,
      "grad_norm": 0.016414228273475284,
      "learning_rate": 1.5778401886899807e-05,
      "loss": 0.7085,
      "step": 116
    },
    {
      "epoch": 1.3295454545454546,
      "grad_norm": 0.016629484072509887,
      "learning_rate": 1.5318220633733978e-05,
      "loss": 0.6328,
      "step": 117
    },
    {
      "epoch": 1.3409090909090908,
      "grad_norm": 0.01735441033712776,
      "learning_rate": 1.4861866979675154e-05,
      "loss": 0.6987,
      "step": 118
    },
    {
      "epoch": 1.3522727272727273,
      "grad_norm": 0.01653379311481811,
      "learning_rate": 1.4409521339786808e-05,
      "loss": 0.7689,
      "step": 119
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.017109513908993915,
      "learning_rate": 1.3961362544602213e-05,
      "loss": 0.852,
      "step": 120
    },
    {
      "epoch": 1.375,
      "grad_norm": 0.015606168185551323,
      "learning_rate": 1.3517567769425548e-05,
      "loss": 0.6131,
      "step": 121
    },
    {
      "epoch": 1.3863636363636362,
      "grad_norm": 0.016954213866876906,
      "learning_rate": 1.3078312464287353e-05,
      "loss": 0.7262,
      "step": 122
    },
    {
      "epoch": 1.3977272727272727,
      "grad_norm": 0.019722191608232728,
      "learning_rate": 1.2643770284581929e-05,
      "loss": 0.6411,
      "step": 123
    },
    {
      "epoch": 1.4090909090909092,
      "grad_norm": 0.016754592315893345,
      "learning_rate": 1.2214113022414448e-05,
      "loss": 0.7406,
      "step": 124
    },
    {
      "epoch": 1.4204545454545454,
      "grad_norm": 0.01811366422363491,
      "learning_rate": 1.1789510538684523e-05,
      "loss": 0.6915,
      "step": 125
    },
    {
      "epoch": 1.4318181818181819,
      "grad_norm": 0.015117191146405742,
      "learning_rate": 1.1370130695933318e-05,
      "loss": 0.7914,
      "step": 126
    },
    {
      "epoch": 1.4431818181818181,
      "grad_norm": 0.019162871723577116,
      "learning_rate": 1.0956139291980727e-05,
      "loss": 0.7924,
      "step": 127
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.017257641671438298,
      "learning_rate": 1.0547699994378787e-05,
      "loss": 0.6671,
      "step": 128
    },
    {
      "epoch": 1.4659090909090908,
      "grad_norm": 0.018952048140386035,
      "learning_rate": 1.0144974275707241e-05,
      "loss": 0.7046,
      "step": 129
    },
    {
      "epoch": 1.4772727272727273,
      "grad_norm": 0.02016982804986924,
      "learning_rate": 9.748121349736892e-06,
      "loss": 0.7542,
      "step": 130
    },
    {
      "epoch": 1.4886363636363638,
      "grad_norm": 0.015861465051683968,
      "learning_rate": 9.357298108486003e-06,
      "loss": 0.6563,
      "step": 131
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.016677424892624696,
      "learning_rate": 8.972659060194506e-06,
      "loss": 0.6743,
      "step": 132
    },
    {
      "epoch": 1.5113636363636362,
      "grad_norm": 0.017220590202846452,
      "learning_rate": 8.594356268240616e-06,
      "loss": 0.5913,
      "step": 133
    },
    {
      "epoch": 1.5227272727272727,
      "grad_norm": 0.017476835977041916,
      "learning_rate": 8.222539291024078e-06,
      "loss": 0.6184,
      "step": 134
    },
    {
      "epoch": 1.5340909090909092,
      "grad_norm": 0.01852744989540818,
      "learning_rate": 7.857355122839675e-06,
      "loss": 0.8003,
      "step": 135
    },
    {
      "epoch": 1.5454545454545454,
      "grad_norm": 0.017724119693348375,
      "learning_rate": 7.4989481357643694e-06,
      "loss": 0.7319,
      "step": 136
    },
    {
      "epoch": 1.5568181818181817,
      "grad_norm": 0.01827897532047109,
      "learning_rate": 7.147460022581257e-06,
      "loss": 0.7496,
      "step": 137
    },
    {
      "epoch": 1.5681818181818183,
      "grad_norm": 0.017356487062778,
      "learning_rate": 6.803029740762648e-06,
      "loss": 0.6998,
      "step": 138
    },
    {
      "epoch": 1.5795454545454546,
      "grad_norm": 0.01850857557468877,
      "learning_rate": 6.465793457534553e-06,
      "loss": 0.6103,
      "step": 139
    },
    {
      "epoch": 1.5909090909090908,
      "grad_norm": 0.018299658199403747,
      "learning_rate": 6.135884496044244e-06,
      "loss": 0.6448,
      "step": 140
    },
    {
      "epoch": 1.6022727272727273,
      "grad_norm": 0.018388053763702464,
      "learning_rate": 5.813433282652298e-06,
      "loss": 0.6399,
      "step": 141
    },
    {
      "epoch": 1.6136363636363638,
      "grad_norm": 0.02080237717937431,
      "learning_rate": 5.4985672953697e-06,
      "loss": 0.6313,
      "step": 142
    },
    {
      "epoch": 1.625,
      "grad_norm": 0.01796260664782129,
      "learning_rate": 5.191411013460645e-06,
      "loss": 0.6843,
      "step": 143
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.02056859413635753,
      "learning_rate": 4.892085868230881e-06,
      "loss": 0.7157,
      "step": 144
    },
    {
      "epoch": 1.6477272727272727,
      "grad_norm": 0.016274442923538548,
      "learning_rate": 4.600710195020982e-06,
      "loss": 0.7276,
      "step": 145
    },
    {
      "epoch": 1.6590909090909092,
      "grad_norm": 0.01815637927898507,
      "learning_rate": 4.317399186423574e-06,
      "loss": 0.6305,
      "step": 146
    },
    {
      "epoch": 1.6704545454545454,
      "grad_norm": 0.01897651128017473,
      "learning_rate": 4.042264846743085e-06,
      "loss": 0.675,
      "step": 147
    },
    {
      "epoch": 1.6818181818181817,
      "grad_norm": 0.018136754953765325,
      "learning_rate": 3.775415947715899e-06,
      "loss": 0.7152,
      "step": 148
    },
    {
      "epoch": 1.6931818181818183,
      "grad_norm": 0.018312167884684892,
      "learning_rate": 3.516957985508476e-06,
      "loss": 0.6128,
      "step": 149
    },
    {
      "epoch": 1.7045454545454546,
      "grad_norm": 0.01872198284953679,
      "learning_rate": 3.266993139010438e-06,
      "loss": 0.7636,
      "step": 150
    },
    {
      "epoch": 1.7159090909090908,
      "grad_norm": 0.019247219050936033,
      "learning_rate": 3.0256202294391577e-06,
      "loss": 0.7763,
      "step": 151
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 0.01747541840805843,
      "learning_rate": 2.792934681271708e-06,
      "loss": 0.718,
      "step": 152
    },
    {
      "epoch": 1.7386363636363638,
      "grad_norm": 0.016543357188300384,
      "learning_rate": 2.5690284845196923e-06,
      "loss": 0.7503,
      "step": 153
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.017777133602865168,
      "learning_rate": 2.3539901583619185e-06,
      "loss": 0.6796,
      "step": 154
    },
    {
      "epoch": 1.7613636363636362,
      "grad_norm": 0.017730228650558268,
      "learning_rate": 2.147904716149135e-06,
      "loss": 0.7887,
      "step": 155
    },
    {
      "epoch": 1.7727272727272727,
      "grad_norm": 0.016904387380041325,
      "learning_rate": 1.9508536317948357e-06,
      "loss": 0.7028,
      "step": 156
    },
    {
      "epoch": 1.7840909090909092,
      "grad_norm": 0.017048389518616498,
      "learning_rate": 1.7629148075653245e-06,
      "loss": 0.6987,
      "step": 157
    },
    {
      "epoch": 1.7954545454545454,
      "grad_norm": 0.019231086359691812,
      "learning_rate": 1.5841625432818057e-06,
      "loss": 0.7262,
      "step": 158
    },
    {
      "epoch": 1.8068181818181817,
      "grad_norm": 0.018406406662889105,
      "learning_rate": 1.4146675069466403e-06,
      "loss": 0.6232,
      "step": 159
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.01859904836356649,
      "learning_rate": 1.2544967068054332e-06,
      "loss": 0.7216,
      "step": 160
    },
    {
      "epoch": 1.8295454545454546,
      "grad_norm": 0.017748264732114775,
      "learning_rate": 1.1037134648559794e-06,
      "loss": 0.66,
      "step": 161
    },
    {
      "epoch": 1.8409090909090908,
      "grad_norm": 0.019172670841775385,
      "learning_rate": 9.623773918144897e-07,
      "loss": 0.6719,
      "step": 162
    },
    {
      "epoch": 1.8522727272727273,
      "grad_norm": 0.017201032284762996,
      "learning_rate": 8.305443635490711e-07,
      "loss": 0.6841,
      "step": 163
    },
    {
      "epoch": 1.8636363636363638,
      "grad_norm": 0.017602592399586683,
      "learning_rate": 7.082664989897487e-07,
      "loss": 0.759,
      "step": 164
    },
    {
      "epoch": 1.875,
      "grad_norm": 0.01737274402951971,
      "learning_rate": 5.955921395237318e-07,
      "loss": 0.6251,
      "step": 165
    },
    {
      "epoch": 1.8863636363636362,
      "grad_norm": 0.018381873767541995,
      "learning_rate": 4.925658298840979e-07,
      "loss": 0.7006,
      "step": 166
    },
    {
      "epoch": 1.8977272727272727,
      "grad_norm": 0.017002639935913035,
      "learning_rate": 3.992283005394837e-07,
      "loss": 0.5917,
      "step": 167
    },
    {
      "epoch": 1.9090909090909092,
      "grad_norm": 0.017463979654969486,
      "learning_rate": 3.1561645159166597e-07,
      "loss": 0.6757,
      "step": 168
    },
    {
      "epoch": 1.9204545454545454,
      "grad_norm": 0.018406237369712176,
      "learning_rate": 2.417633381874534e-07,
      "loss": 0.7824,
      "step": 169
    },
    {
      "epoch": 1.9318181818181817,
      "grad_norm": 0.017967868873337563,
      "learning_rate": 1.7769815745066475e-07,
      "loss": 0.7394,
      "step": 170
    },
    {
      "epoch": 1.9431818181818183,
      "grad_norm": 0.01623825702144127,
      "learning_rate": 1.234462369393147e-07,
      "loss": 0.7684,
      "step": 171
    },
    {
      "epoch": 1.9545454545454546,
      "grad_norm": 0.017608033119901965,
      "learning_rate": 7.90290246326042e-08,
      "loss": 0.7831,
      "step": 172
    },
    {
      "epoch": 1.9659090909090908,
      "grad_norm": 0.017319359934865306,
      "learning_rate": 4.4464080451675494e-08,
      "loss": 0.6974,
      "step": 173
    },
    {
      "epoch": 1.9772727272727273,
      "grad_norm": 0.017475580158119938,
      "learning_rate": 1.976506931745392e-08,
      "loss": 0.7574,
      "step": 174
    },
    {
      "epoch": 1.9886363636363638,
      "grad_norm": 0.017048411256850495,
      "learning_rate": 4.941755748361088e-09,
      "loss": 0.6594,
      "step": 175
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.018638627651477082,
      "learning_rate": 0.0,
      "loss": 0.7388,
      "step": 176
    },
    {
      "epoch": 2.0,
      "step": 176,
      "total_flos": 3054747482324992.0,
      "train_loss": 0.7215218588032506,
      "train_runtime": 3666.1508,
      "train_samples_per_second": 1.53,
      "train_steps_per_second": 0.048
    }
  ],
  "logging_steps": 1,
  "max_steps": 176,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3054747482324992.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}