{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6776071995764955,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0033880359978824773,
      "grad_norm": 0.04680836945772171,
      "learning_rate": 7.499999999999999e-06,
      "loss": 10.3766,
      "step": 1
    },
    {
      "epoch": 0.0033880359978824773,
      "eval_loss": 10.376468658447266,
      "eval_runtime": 3.878,
      "eval_samples_per_second": 256.575,
      "eval_steps_per_second": 128.416,
      "step": 1
    },
    {
      "epoch": 0.006776071995764955,
      "grad_norm": 0.04365997761487961,
      "learning_rate": 1.4999999999999999e-05,
      "loss": 10.3771,
      "step": 2
    },
    {
      "epoch": 0.010164107993647432,
      "grad_norm": 0.041304562240839005,
      "learning_rate": 2.2499999999999998e-05,
      "loss": 10.3758,
      "step": 3
    },
    {
      "epoch": 0.01355214399152991,
      "grad_norm": 0.043574266135692596,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 10.3764,
      "step": 4
    },
    {
      "epoch": 0.01694017998941239,
      "grad_norm": 0.045331861823797226,
      "learning_rate": 3.75e-05,
      "loss": 10.3757,
      "step": 5
    },
    {
      "epoch": 0.020328215987294864,
      "grad_norm": 0.04029256850481033,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 10.3764,
      "step": 6
    },
    {
      "epoch": 0.023716251985177343,
      "grad_norm": 0.046235088258981705,
      "learning_rate": 5.2499999999999995e-05,
      "loss": 10.3752,
      "step": 7
    },
    {
      "epoch": 0.02710428798305982,
      "grad_norm": 0.04704303666949272,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 10.3756,
      "step": 8
    },
    {
      "epoch": 0.030492323980942298,
      "grad_norm": 0.04604668170213699,
      "learning_rate": 6.75e-05,
      "loss": 10.3763,
      "step": 9
    },
    {
      "epoch": 0.03388035997882478,
      "grad_norm": 0.04410148411989212,
      "learning_rate": 7.5e-05,
      "loss": 10.3751,
      "step": 10
    },
    {
      "epoch": 0.03726839597670725,
      "grad_norm": 0.045992445200681686,
      "learning_rate": 8.25e-05,
      "loss": 10.3755,
      "step": 11
    },
    {
      "epoch": 0.04065643197458973,
      "grad_norm": 0.04755518212914467,
      "learning_rate": 8.999999999999999e-05,
      "loss": 10.374,
      "step": 12
    },
    {
      "epoch": 0.04404446797247221,
      "grad_norm": 0.0471210703253746,
      "learning_rate": 9.75e-05,
      "loss": 10.375,
      "step": 13
    },
    {
      "epoch": 0.047432503970354686,
      "grad_norm": 0.04655275121331215,
      "learning_rate": 0.00010499999999999999,
      "loss": 10.3753,
      "step": 14
    },
    {
      "epoch": 0.05082053996823716,
      "grad_norm": 0.04771905019879341,
      "learning_rate": 0.0001125,
      "loss": 10.3748,
      "step": 15
    },
    {
      "epoch": 0.05420857596611964,
      "grad_norm": 0.051401205360889435,
      "learning_rate": 0.00011999999999999999,
      "loss": 10.3749,
      "step": 16
    },
    {
      "epoch": 0.05759661196400212,
      "grad_norm": 0.045204389840364456,
      "learning_rate": 0.00012749999999999998,
      "loss": 10.3736,
      "step": 17
    },
    {
      "epoch": 0.060984647961884596,
      "grad_norm": 0.04979519173502922,
      "learning_rate": 0.000135,
      "loss": 10.3729,
      "step": 18
    },
    {
      "epoch": 0.06437268395976707,
      "grad_norm": 0.04958589747548103,
      "learning_rate": 0.0001425,
      "loss": 10.3735,
      "step": 19
    },
    {
      "epoch": 0.06776071995764955,
      "grad_norm": 0.054519593715667725,
      "learning_rate": 0.00015,
      "loss": 10.3723,
      "step": 20
    },
    {
      "epoch": 0.07114875595553202,
      "grad_norm": 0.060721371322870255,
      "learning_rate": 0.00014998857713672935,
      "loss": 10.372,
      "step": 21
    },
    {
      "epoch": 0.0745367919534145,
      "grad_norm": 0.06067592278122902,
      "learning_rate": 0.00014995431202643217,
      "loss": 10.3718,
      "step": 22
    },
    {
      "epoch": 0.07792482795129699,
      "grad_norm": 0.06362656503915787,
      "learning_rate": 0.000149897215106593,
      "loss": 10.3713,
      "step": 23
    },
    {
      "epoch": 0.08131286394917946,
      "grad_norm": 0.067110076546669,
      "learning_rate": 0.0001498173037694868,
      "loss": 10.3714,
      "step": 24
    },
    {
      "epoch": 0.08470089994706194,
      "grad_norm": 0.07370075583457947,
      "learning_rate": 0.0001497146023568809,
      "loss": 10.3712,
      "step": 25
    },
    {
      "epoch": 0.08808893594494442,
      "grad_norm": 0.0760367140173912,
      "learning_rate": 0.00014958914215262048,
      "loss": 10.371,
      "step": 26
    },
    {
      "epoch": 0.09147697194282689,
      "grad_norm": 0.08042097836732864,
      "learning_rate": 0.00014944096137309914,
      "loss": 10.37,
      "step": 27
    },
    {
      "epoch": 0.09486500794070937,
      "grad_norm": 0.08724083006381989,
      "learning_rate": 0.00014927010515561776,
      "loss": 10.3697,
      "step": 28
    },
    {
      "epoch": 0.09825304393859184,
      "grad_norm": 0.08779574185609818,
      "learning_rate": 0.00014907662554463532,
      "loss": 10.3689,
      "step": 29
    },
    {
      "epoch": 0.10164107993647432,
      "grad_norm": 0.09096319228410721,
      "learning_rate": 0.0001488605814759156,
      "loss": 10.3677,
      "step": 30
    },
    {
      "epoch": 0.1050291159343568,
      "grad_norm": 0.10570746660232544,
      "learning_rate": 0.00014862203875857477,
      "loss": 10.3666,
      "step": 31
    },
    {
      "epoch": 0.10841715193223928,
      "grad_norm": 0.1051798090338707,
      "learning_rate": 0.0001483610700550354,
      "loss": 10.3678,
      "step": 32
    },
    {
      "epoch": 0.11180518793012176,
      "grad_norm": 0.11076612770557404,
      "learning_rate": 0.00014807775485889264,
      "loss": 10.366,
      "step": 33
    },
    {
      "epoch": 0.11519322392800424,
      "grad_norm": 0.11073443293571472,
      "learning_rate": 0.0001477721794706997,
      "loss": 10.3658,
      "step": 34
    },
    {
      "epoch": 0.11858125992588671,
      "grad_norm": 0.11666611582040787,
      "learning_rate": 0.0001474444369716801,
      "loss": 10.3642,
      "step": 35
    },
    {
      "epoch": 0.12196929592376919,
      "grad_norm": 0.12058889120817184,
      "learning_rate": 0.0001470946271953739,
      "loss": 10.3624,
      "step": 36
    },
    {
      "epoch": 0.12535733192165166,
      "grad_norm": 0.13473331928253174,
      "learning_rate": 0.00014672285669722765,
      "loss": 10.3619,
      "step": 37
    },
    {
      "epoch": 0.12874536791953414,
      "grad_norm": 0.12408842891454697,
      "learning_rate": 0.00014632923872213652,
      "loss": 10.3616,
      "step": 38
    },
    {
      "epoch": 0.13213340391741663,
      "grad_norm": 0.12850341200828552,
      "learning_rate": 0.00014591389316994876,
      "loss": 10.3609,
      "step": 39
    },
    {
      "epoch": 0.1355214399152991,
      "grad_norm": 0.12435595691204071,
      "learning_rate": 0.0001454769465589431,
      "loss": 10.3597,
      "step": 40
    },
    {
      "epoch": 0.1389094759131816,
      "grad_norm": 0.11300837248563766,
      "learning_rate": 0.00014501853198729012,
      "loss": 10.3583,
      "step": 41
    },
    {
      "epoch": 0.14229751191106405,
      "grad_norm": 0.11374777555465698,
      "learning_rate": 0.00014453878909250904,
      "loss": 10.357,
      "step": 42
    },
    {
      "epoch": 0.14568554790894653,
      "grad_norm": 0.11273212730884552,
      "learning_rate": 0.00014403786400893302,
      "loss": 10.3559,
      "step": 43
    },
    {
      "epoch": 0.149073583906829,
      "grad_norm": 0.10369884222745895,
      "learning_rate": 0.00014351590932319504,
      "loss": 10.3545,
      "step": 44
    },
    {
      "epoch": 0.1524616199047115,
      "grad_norm": 0.09857185184955597,
      "learning_rate": 0.00014297308402774875,
      "loss": 10.3544,
      "step": 45
    },
    {
      "epoch": 0.15584965590259398,
      "grad_norm": 0.09635099023580551,
      "learning_rate": 0.0001424095534724375,
      "loss": 10.3537,
      "step": 46
    },
    {
      "epoch": 0.15923769190047643,
      "grad_norm": 0.08793843537569046,
      "learning_rate": 0.00014182548931412757,
      "loss": 10.3528,
      "step": 47
    },
    {
      "epoch": 0.1626257278983589,
      "grad_norm": 0.07799001038074493,
      "learning_rate": 0.0001412210694644195,
      "loss": 10.3516,
      "step": 48
    },
    {
      "epoch": 0.1660137638962414,
      "grad_norm": 0.07476358115673065,
      "learning_rate": 0.00014059647803545467,
      "loss": 10.3515,
      "step": 49
    },
    {
      "epoch": 0.16940179989412388,
      "grad_norm": 0.07342197000980377,
      "learning_rate": 0.0001399519052838329,
      "loss": 10.3523,
      "step": 50
    },
    {
      "epoch": 0.16940179989412388,
      "eval_loss": 10.351042747497559,
      "eval_runtime": 3.8684,
      "eval_samples_per_second": 257.211,
      "eval_steps_per_second": 128.735,
      "step": 50
    },
    {
      "epoch": 0.17278983589200636,
      "grad_norm": 0.06936267018318176,
      "learning_rate": 0.00013928754755265842,
      "loss": 10.3514,
      "step": 51
    },
    {
      "epoch": 0.17617787188988884,
      "grad_norm": 0.06112508103251457,
      "learning_rate": 0.00013860360721173193,
      "loss": 10.3511,
      "step": 52
    },
    {
      "epoch": 0.1795659078877713,
      "grad_norm": 0.06208924576640129,
      "learning_rate": 0.0001379002925959068,
      "loss": 10.3505,
      "step": 53
    },
    {
      "epoch": 0.18295394388565378,
      "grad_norm": 0.057701293379068375,
      "learning_rate": 0.0001371778179416281,
      "loss": 10.3505,
      "step": 54
    },
    {
      "epoch": 0.18634197988353626,
      "grad_norm": 0.050447553396224976,
      "learning_rate": 0.00013643640332167438,
      "loss": 10.349,
      "step": 55
    },
    {
      "epoch": 0.18973001588141875,
      "grad_norm": 0.05121852830052376,
      "learning_rate": 0.00013567627457812106,
      "loss": 10.3496,
      "step": 56
    },
    {
      "epoch": 0.19311805187930123,
      "grad_norm": 0.04376755282282829,
      "learning_rate": 0.00013489766325354695,
      "loss": 10.3488,
      "step": 57
    },
    {
      "epoch": 0.19650608787718368,
      "grad_norm": 0.04570882394909859,
      "learning_rate": 0.00013410080652050412,
      "loss": 10.3493,
      "step": 58
    },
    {
      "epoch": 0.19989412387506617,
      "grad_norm": 0.047347478568553925,
      "learning_rate": 0.0001332859471092728,
      "loss": 10.35,
      "step": 59
    },
    {
      "epoch": 0.20328215987294865,
      "grad_norm": 0.048713624477386475,
      "learning_rate": 0.00013245333323392333,
      "loss": 10.3484,
      "step": 60
    },
    {
      "epoch": 0.20667019587083113,
      "grad_norm": 0.04044219106435776,
      "learning_rate": 0.0001316032185167079,
      "loss": 10.3485,
      "step": 61
    },
    {
      "epoch": 0.2100582318687136,
      "grad_norm": 0.03352762386202812,
      "learning_rate": 0.00013073586191080457,
      "loss": 10.3494,
      "step": 62
    },
    {
      "epoch": 0.2134462678665961,
      "grad_norm": 0.03678755834698677,
      "learning_rate": 0.00012985152762143778,
      "loss": 10.3492,
      "step": 63
    },
    {
      "epoch": 0.21683430386447855,
      "grad_norm": 0.035951532423496246,
      "learning_rate": 0.00012895048502539882,
      "loss": 10.3475,
      "step": 64
    },
    {
      "epoch": 0.22022233986236103,
      "grad_norm": 0.04304710775613785,
      "learning_rate": 0.00012803300858899104,
      "loss": 10.349,
      "step": 65
    },
    {
      "epoch": 0.22361037586024352,
      "grad_norm": 0.035194698721170425,
      "learning_rate": 0.0001270993777844248,
      "loss": 10.3468,
      "step": 66
    },
    {
      "epoch": 0.226998411858126,
      "grad_norm": 0.029510466381907463,
      "learning_rate": 0.0001261498770046874,
      "loss": 10.3484,
      "step": 67
    },
    {
      "epoch": 0.23038644785600848,
      "grad_norm": 0.02603858895599842,
      "learning_rate": 0.00012518479547691435,
      "loss": 10.3485,
      "step": 68
    },
    {
      "epoch": 0.23377448385389094,
      "grad_norm": 0.028004931285977364,
      "learning_rate": 0.00012420442717428804,
      "loss": 10.3488,
      "step": 69
    },
    {
      "epoch": 0.23716251985177342,
      "grad_norm": 0.030328616499900818,
      "learning_rate": 0.00012320907072649044,
      "loss": 10.3479,
      "step": 70
    },
    {
      "epoch": 0.2405505558496559,
      "grad_norm": 0.027720727026462555,
      "learning_rate": 0.0001221990293287378,
      "loss": 10.3477,
      "step": 71
    },
    {
      "epoch": 0.24393859184753838,
      "grad_norm": 0.02903708443045616,
      "learning_rate": 0.00012117461064942435,
      "loss": 10.3479,
      "step": 72
    },
    {
      "epoch": 0.24732662784542087,
      "grad_norm": 0.026270205155014992,
      "learning_rate": 0.00012013612673640363,
      "loss": 10.3473,
      "step": 73
    },
    {
      "epoch": 0.2507146638433033,
      "grad_norm": 0.022023234516382217,
      "learning_rate": 0.00011908389392193547,
      "loss": 10.3462,
      "step": 74
    },
    {
      "epoch": 0.25410269984118583,
      "grad_norm": 0.018086234107613564,
      "learning_rate": 0.00011801823272632844,
      "loss": 10.3471,
      "step": 75
    },
    {
      "epoch": 0.2574907358390683,
      "grad_norm": 0.017115121707320213,
      "learning_rate": 0.00011693946776030599,
      "loss": 10.3481,
      "step": 76
    },
    {
      "epoch": 0.26087877183695074,
      "grad_norm": 0.022446399554610252,
      "learning_rate": 0.00011584792762612703,
      "loss": 10.3469,
      "step": 77
    },
    {
      "epoch": 0.26426680783483325,
      "grad_norm": 0.023726455867290497,
      "learning_rate": 0.00011474394481749035,
      "loss": 10.3475,
      "step": 78
    },
    {
      "epoch": 0.2676548438327157,
      "grad_norm": 0.02203121967613697,
      "learning_rate": 0.00011362785561825406,
      "loss": 10.3484,
      "step": 79
    },
    {
      "epoch": 0.2710428798305982,
      "grad_norm": 0.016930948942899704,
      "learning_rate": 0.0001125,
      "loss": 10.3476,
      "step": 80
    },
    {
      "epoch": 0.27443091582848067,
      "grad_norm": 0.017117898911237717,
      "learning_rate": 0.00011136072151847529,
      "loss": 10.3474,
      "step": 81
    },
    {
      "epoch": 0.2778189518263632,
      "grad_norm": 0.02053241617977619,
      "learning_rate": 0.00011021036720894179,
      "loss": 10.3467,
      "step": 82
    },
    {
      "epoch": 0.28120698782424564,
      "grad_norm": 0.022768596187233925,
      "learning_rate": 0.00010904928748046599,
      "loss": 10.3479,
      "step": 83
    },
    {
      "epoch": 0.2845950238221281,
      "grad_norm": 0.016698352992534637,
      "learning_rate": 0.0001078778360091808,
      "loss": 10.3468,
      "step": 84
    },
    {
      "epoch": 0.2879830598200106,
      "grad_norm": 0.020199725404381752,
      "learning_rate": 0.00010669636963055245,
      "loss": 10.3473,
      "step": 85
    },
    {
      "epoch": 0.29137109581789306,
      "grad_norm": 0.014243320561945438,
      "learning_rate": 0.00010550524823068502,
      "loss": 10.3472,
      "step": 86
    },
    {
      "epoch": 0.29475913181577557,
      "grad_norm": 0.019790155813097954,
      "learning_rate": 0.00010430483463669551,
      "loss": 10.3472,
      "step": 87
    },
    {
      "epoch": 0.298147167813658,
      "grad_norm": 0.01632939651608467,
      "learning_rate": 0.0001030954945061934,
      "loss": 10.3474,
      "step": 88
    },
    {
      "epoch": 0.3015352038115405,
      "grad_norm": 0.015530891716480255,
      "learning_rate": 0.0001018775962158975,
      "loss": 10.347,
      "step": 89
    },
    {
      "epoch": 0.304923239809423,
      "grad_norm": 0.015950841829180717,
      "learning_rate": 0.00010065151074942516,
      "loss": 10.3475,
      "step": 90
    },
    {
      "epoch": 0.30831127580730544,
      "grad_norm": 0.020643549039959908,
      "learning_rate": 9.941761158428674e-05,
      "loss": 10.347,
      "step": 91
    },
    {
      "epoch": 0.31169931180518795,
      "grad_norm": 0.019012747332453728,
      "learning_rate": 9.817627457812105e-05,
      "loss": 10.3465,
      "step": 92
    },
    {
      "epoch": 0.3150873478030704,
      "grad_norm": 0.014910330064594746,
      "learning_rate": 9.692787785420525e-05,
      "loss": 10.3482,
      "step": 93
    },
    {
      "epoch": 0.31847538380095286,
      "grad_norm": 0.01823591999709606,
      "learning_rate": 9.567280168627493e-05,
      "loss": 10.3467,
      "step": 94
    },
    {
      "epoch": 0.32186341979883537,
      "grad_norm": 0.01734175719320774,
      "learning_rate": 9.441142838268905e-05,
      "loss": 10.3468,
      "step": 95
    },
    {
      "epoch": 0.3252514557967178,
      "grad_norm": 0.021044116467237473,
      "learning_rate": 9.314414216997507e-05,
      "loss": 10.3477,
      "step": 96
    },
    {
      "epoch": 0.32863949179460034,
      "grad_norm": 0.01741754449903965,
      "learning_rate": 9.187132907578987e-05,
      "loss": 10.3468,
      "step": 97
    },
    {
      "epoch": 0.3320275277924828,
      "grad_norm": 0.018304290249943733,
      "learning_rate": 9.059337681133192e-05,
      "loss": 10.3482,
      "step": 98
    },
    {
      "epoch": 0.33541556379036525,
      "grad_norm": 0.017597520723938942,
      "learning_rate": 8.931067465324085e-05,
      "loss": 10.3468,
      "step": 99
    },
    {
      "epoch": 0.33880359978824776,
      "grad_norm": 0.01578284054994583,
      "learning_rate": 8.802361332501978e-05,
      "loss": 10.3476,
      "step": 100
    },
    {
      "epoch": 0.33880359978824776,
      "eval_loss": 10.34636116027832,
      "eval_runtime": 3.8912,
      "eval_samples_per_second": 255.704,
      "eval_steps_per_second": 127.981,
      "step": 100
    },
    {
      "epoch": 0.3421916357861302,
      "grad_norm": 0.02010318450629711,
      "learning_rate": 8.673258487801731e-05,
      "loss": 10.3469,
      "step": 101
    },
    {
      "epoch": 0.3455796717840127,
      "grad_norm": 0.02163493074476719,
      "learning_rate": 8.54379825720049e-05,
      "loss": 10.346,
      "step": 102
    },
    {
      "epoch": 0.3489677077818952,
      "grad_norm": 0.02064266800880432,
      "learning_rate": 8.414020075538605e-05,
      "loss": 10.3461,
      "step": 103
    },
    {
      "epoch": 0.3523557437797777,
      "grad_norm": 0.023022258654236794,
      "learning_rate": 8.2839634745074e-05,
      "loss": 10.3463,
      "step": 104
    },
    {
      "epoch": 0.35574377977766014,
      "grad_norm": 0.017432276159524918,
      "learning_rate": 8.153668070607437e-05,
      "loss": 10.3465,
      "step": 105
    },
    {
      "epoch": 0.3591318157755426,
      "grad_norm": 0.01911778748035431,
      "learning_rate": 8.023173553080938e-05,
      "loss": 10.3459,
      "step": 106
    },
    {
      "epoch": 0.3625198517734251,
      "grad_norm": 0.01831880584359169,
      "learning_rate": 7.89251967182208e-05,
      "loss": 10.3455,
      "step": 107
    },
    {
      "epoch": 0.36590788777130756,
      "grad_norm": 0.018690194934606552,
      "learning_rate": 7.761746225268758e-05,
      "loss": 10.3471,
      "step": 108
    },
    {
      "epoch": 0.36929592376919007,
      "grad_norm": 0.021015219390392303,
      "learning_rate": 7.630893048279627e-05,
      "loss": 10.3453,
      "step": 109
    },
    {
      "epoch": 0.3726839597670725,
      "grad_norm": 0.01983080990612507,
      "learning_rate": 7.5e-05,
      "loss": 10.3462,
      "step": 110
    },
    {
      "epoch": 0.376071995764955,
      "grad_norm": 0.021141625940799713,
      "learning_rate": 7.369106951720373e-05,
      "loss": 10.3457,
      "step": 111
    },
    {
      "epoch": 0.3794600317628375,
      "grad_norm": 0.021793803200125694,
      "learning_rate": 7.238253774731244e-05,
      "loss": 10.3457,
      "step": 112
    },
    {
      "epoch": 0.38284806776071995,
      "grad_norm": 0.019963612779974937,
      "learning_rate": 7.10748032817792e-05,
      "loss": 10.3463,
      "step": 113
    },
    {
      "epoch": 0.38623610375860246,
      "grad_norm": 0.020090965554118156,
      "learning_rate": 6.976826446919059e-05,
      "loss": 10.3458,
      "step": 114
    },
    {
      "epoch": 0.3896241397564849,
      "grad_norm": 0.02083776332437992,
      "learning_rate": 6.846331929392562e-05,
      "loss": 10.3469,
      "step": 115
    },
    {
      "epoch": 0.39301217575436737,
      "grad_norm": 0.01785002276301384,
      "learning_rate": 6.7160365254926e-05,
      "loss": 10.3465,
      "step": 116
    },
    {
      "epoch": 0.3964002117522499,
      "grad_norm": 0.02254386991262436,
      "learning_rate": 6.585979924461394e-05,
      "loss": 10.3452,
      "step": 117
    },
    {
      "epoch": 0.39978824775013233,
      "grad_norm": 0.023428700864315033,
      "learning_rate": 6.45620174279951e-05,
      "loss": 10.3475,
      "step": 118
    },
    {
      "epoch": 0.40317628374801484,
      "grad_norm": 0.01672559231519699,
      "learning_rate": 6.326741512198266e-05,
      "loss": 10.346,
      "step": 119
    },
    {
      "epoch": 0.4065643197458973,
      "grad_norm": 0.020479971542954445,
      "learning_rate": 6.197638667498022e-05,
      "loss": 10.3456,
      "step": 120
    },
    {
      "epoch": 0.40995235574377975,
      "grad_norm": 0.023177366703748703,
      "learning_rate": 6.068932534675913e-05,
      "loss": 10.3449,
      "step": 121
    },
    {
      "epoch": 0.41334039174166226,
      "grad_norm": 0.01870677061378956,
      "learning_rate": 5.9406623188668055e-05,
      "loss": 10.346,
      "step": 122
    },
    {
      "epoch": 0.4167284277395447,
      "grad_norm": 0.0195186547935009,
      "learning_rate": 5.812867092421013e-05,
      "loss": 10.3459,
      "step": 123
    },
    {
      "epoch": 0.4201164637374272,
      "grad_norm": 0.02066197618842125,
      "learning_rate": 5.685585783002493e-05,
      "loss": 10.3451,
      "step": 124
    },
    {
      "epoch": 0.4235044997353097,
      "grad_norm": 0.018614448606967926,
      "learning_rate": 5.558857161731093e-05,
      "loss": 10.3456,
      "step": 125
    },
    {
      "epoch": 0.4268925357331922,
      "grad_norm": 0.02485392615199089,
      "learning_rate": 5.4327198313725064e-05,
      "loss": 10.3456,
      "step": 126
    },
    {
      "epoch": 0.43028057173107465,
      "grad_norm": 0.019080353900790215,
      "learning_rate": 5.307212214579474e-05,
      "loss": 10.3463,
      "step": 127
    },
    {
      "epoch": 0.4336686077289571,
      "grad_norm": 0.02017894946038723,
      "learning_rate": 5.182372542187895e-05,
      "loss": 10.3456,
      "step": 128
    },
    {
      "epoch": 0.4370566437268396,
      "grad_norm": 0.02289474382996559,
      "learning_rate": 5.058238841571326e-05,
      "loss": 10.3443,
      "step": 129
    },
    {
      "epoch": 0.44044467972472207,
      "grad_norm": 0.02067600190639496,
      "learning_rate": 4.934848925057484e-05,
      "loss": 10.3459,
      "step": 130
    },
    {
      "epoch": 0.4438327157226046,
      "grad_norm": 0.02071257308125496,
      "learning_rate": 4.812240378410248e-05,
      "loss": 10.3452,
      "step": 131
    },
    {
      "epoch": 0.44722075172048703,
      "grad_norm": 0.02436411753296852,
      "learning_rate": 4.690450549380659e-05,
      "loss": 10.3449,
      "step": 132
    },
    {
      "epoch": 0.4506087877183695,
      "grad_norm": 0.0237566027790308,
      "learning_rate": 4.569516536330447e-05,
      "loss": 10.3462,
      "step": 133
    },
    {
      "epoch": 0.453996823716252,
      "grad_norm": 0.029039116576313972,
      "learning_rate": 4.449475176931499e-05,
      "loss": 10.3455,
      "step": 134
    },
    {
      "epoch": 0.45738485971413445,
      "grad_norm": 0.021290864795446396,
      "learning_rate": 4.3303630369447554e-05,
      "loss": 10.3446,
      "step": 135
    },
    {
      "epoch": 0.46077289571201696,
      "grad_norm": 0.01688864268362522,
      "learning_rate": 4.212216399081918e-05,
      "loss": 10.3439,
      "step": 136
    },
    {
      "epoch": 0.4641609317098994,
      "grad_norm": 0.026069054380059242,
      "learning_rate": 4.095071251953399e-05,
      "loss": 10.3461,
      "step": 137
    },
    {
      "epoch": 0.46754896770778187,
      "grad_norm": 0.020276112481951714,
      "learning_rate": 3.978963279105821e-05,
      "loss": 10.3445,
      "step": 138
    },
    {
      "epoch": 0.4709370037056644,
      "grad_norm": 0.021585950627923012,
      "learning_rate": 3.863927848152472e-05,
      "loss": 10.3442,
      "step": 139
    },
    {
      "epoch": 0.47432503970354684,
      "grad_norm": 0.025700606405735016,
      "learning_rate": 3.750000000000001e-05,
      "loss": 10.3458,
      "step": 140
    },
    {
      "epoch": 0.47771307570142935,
      "grad_norm": 0.020632240921258926,
      "learning_rate": 3.637214438174593e-05,
      "loss": 10.3446,
      "step": 141
    },
    {
      "epoch": 0.4811011116993118,
      "grad_norm": 0.020391074940562248,
      "learning_rate": 3.525605518250964e-05,
      "loss": 10.3442,
      "step": 142
    },
    {
      "epoch": 0.48448914769719426,
      "grad_norm": 0.021430406719446182,
      "learning_rate": 3.415207237387297e-05,
      "loss": 10.3444,
      "step": 143
    },
    {
      "epoch": 0.48787718369507677,
      "grad_norm": 0.01741032488644123,
      "learning_rate": 3.3060532239693994e-05,
      "loss": 10.3448,
      "step": 144
    },
    {
      "epoch": 0.4912652196929592,
      "grad_norm": 0.026816904544830322,
      "learning_rate": 3.198176727367156e-05,
      "loss": 10.3467,
      "step": 145
    },
    {
      "epoch": 0.49465325569084173,
      "grad_norm": 0.0245627723634243,
      "learning_rate": 3.091610607806452e-05,
      "loss": 10.3448,
      "step": 146
    },
    {
      "epoch": 0.4980412916887242,
      "grad_norm": 0.024026039987802505,
      "learning_rate": 2.986387326359637e-05,
      "loss": 10.3459,
      "step": 147
    },
    {
      "epoch": 0.5014293276866066,
      "grad_norm": 0.023174704983830452,
      "learning_rate": 2.8825389350575624e-05,
      "loss": 10.3454,
      "step": 148
    },
    {
      "epoch": 0.5048173636844892,
      "grad_norm": 0.029328398406505585,
      "learning_rate": 2.78009706712622e-05,
      "loss": 10.3446,
      "step": 149
    },
    {
      "epoch": 0.5082053996823717,
      "grad_norm": 0.021034657955169678,
      "learning_rate": 2.6790929273509545e-05,
      "loss": 10.344,
      "step": 150
    },
    {
      "epoch": 0.5082053996823717,
      "eval_loss": 10.344643592834473,
      "eval_runtime": 3.8713,
      "eval_samples_per_second": 257.02,
      "eval_steps_per_second": 128.639,
      "step": 150
    },
    {
      "epoch": 0.5115934356802541,
      "grad_norm": 0.02339405193924904,
      "learning_rate": 2.579557282571196e-05,
      "loss": 10.3449,
      "step": 151
    },
    {
      "epoch": 0.5149814716781366,
      "grad_norm": 0.02014802023768425,
      "learning_rate": 2.4815204523085654e-05,
      "loss": 10.3447,
      "step": 152
    },
    {
      "epoch": 0.5183695076760191,
      "grad_norm": 0.02366970293223858,
      "learning_rate": 2.385012299531262e-05,
      "loss": 10.3456,
      "step": 153
    },
    {
      "epoch": 0.5217575436739015,
      "grad_norm": 0.01631753146648407,
      "learning_rate": 2.2900622215575197e-05,
      "loss": 10.3453,
      "step": 154
    },
    {
      "epoch": 0.525145579671784,
      "grad_norm": 0.02035635896027088,
      "learning_rate": 2.1966991411008938e-05,
      "loss": 10.3455,
      "step": 155
    },
    {
      "epoch": 0.5285336156696665,
      "grad_norm": 0.02124161832034588,
      "learning_rate": 2.1049514974601175e-05,
      "loss": 10.3443,
      "step": 156
    },
    {
      "epoch": 0.531921651667549,
      "grad_norm": 0.020465832203626633,
      "learning_rate": 2.0148472378562215e-05,
      "loss": 10.3438,
      "step": 157
    },
    {
      "epoch": 0.5353096876654314,
      "grad_norm": 0.022870277985930443,
      "learning_rate": 1.926413808919542e-05,
      "loss": 10.3436,
      "step": 158
    },
    {
      "epoch": 0.5386977236633139,
      "grad_norm": 0.02524011954665184,
      "learning_rate": 1.8396781483292098e-05,
      "loss": 10.3448,
      "step": 159
    },
    {
      "epoch": 0.5420857596611964,
      "grad_norm": 0.019947601482272148,
      "learning_rate": 1.7546666766076655e-05,
      "loss": 10.3449,
      "step": 160
    },
    {
      "epoch": 0.5454737956590788,
      "grad_norm": 0.058847565203905106,
      "learning_rate": 1.671405289072718e-05,
      "loss": 10.3437,
      "step": 161
    },
    {
      "epoch": 0.5488618316569613,
      "grad_norm": 0.022570470348000526,
      "learning_rate": 1.5899193479495857e-05,
      "loss": 10.3451,
      "step": 162
    },
    {
      "epoch": 0.5522498676548439,
      "grad_norm": 0.019783953204751015,
      "learning_rate": 1.5102336746453053e-05,
      "loss": 10.3431,
      "step": 163
    },
    {
      "epoch": 0.5556379036527264,
      "grad_norm": 0.017986372113227844,
      "learning_rate": 1.4323725421878949e-05,
      "loss": 10.344,
      "step": 164
    },
    {
      "epoch": 0.5590259396506088,
      "grad_norm": 0.02159409038722515,
      "learning_rate": 1.3563596678325606e-05,
      "loss": 10.3442,
      "step": 165
    },
    {
      "epoch": 0.5624139756484913,
      "grad_norm": 0.020207397639751434,
      "learning_rate": 1.2822182058371878e-05,
      "loss": 10.344,
      "step": 166
    },
    {
      "epoch": 0.5658020116463738,
      "grad_norm": 0.02228572405874729,
      "learning_rate": 1.2099707404093203e-05,
      "loss": 10.343,
      "step": 167
    },
    {
      "epoch": 0.5691900476442562,
      "grad_norm": 0.02297716587781906,
      "learning_rate": 1.1396392788268052e-05,
      "loss": 10.3455,
      "step": 168
    },
    {
      "epoch": 0.5725780836421387,
      "grad_norm": 0.019231807440519333,
      "learning_rate": 1.0712452447341582e-05,
      "loss": 10.3439,
      "step": 169
    },
    {
      "epoch": 0.5759661196400212,
      "grad_norm": 0.02405407838523388,
      "learning_rate": 1.0048094716167095e-05,
      "loss": 10.344,
      "step": 170
    },
    {
      "epoch": 0.5793541556379036,
      "grad_norm": 0.02616795524954796,
      "learning_rate": 9.40352196454532e-06,
      "loss": 10.3444,
      "step": 171
    },
    {
      "epoch": 0.5827421916357861,
      "grad_norm": 0.01909734308719635,
      "learning_rate": 8.778930535580474e-06,
      "loss": 10.3453,
      "step": 172
    },
    {
      "epoch": 0.5861302276336686,
      "grad_norm": 0.0253478791564703,
      "learning_rate": 8.174510685872415e-06,
      "loss": 10.3448,
      "step": 173
    },
    {
      "epoch": 0.5895182636315511,
      "grad_norm": 0.020116323605179787,
      "learning_rate": 7.5904465275624884e-06,
      "loss": 10.3443,
      "step": 174
    },
    {
      "epoch": 0.5929062996294335,
      "grad_norm": 0.0158366896212101,
      "learning_rate": 7.026915972251254e-06,
      "loss": 10.3452,
      "step": 175
    },
    {
      "epoch": 0.596294335627316,
      "grad_norm": 0.020508933812379837,
      "learning_rate": 6.484090676804926e-06,
      "loss": 10.3454,
      "step": 176
    },
    {
      "epoch": 0.5996823716251986,
      "grad_norm": 0.020298492163419724,
      "learning_rate": 5.962135991066971e-06,
      "loss": 10.344,
      "step": 177
    },
    {
      "epoch": 0.603070407623081,
      "grad_norm": 0.01768598146736622,
      "learning_rate": 5.461210907490951e-06,
      "loss": 10.3442,
      "step": 178
    },
    {
      "epoch": 0.6064584436209635,
      "grad_norm": 0.02038932777941227,
      "learning_rate": 4.981468012709877e-06,
      "loss": 10.3456,
      "step": 179
    },
    {
      "epoch": 0.609846479618846,
      "grad_norm": 0.01764788292348385,
      "learning_rate": 4.523053441056876e-06,
      "loss": 10.3448,
      "step": 180
    },
    {
      "epoch": 0.6132345156167285,
      "grad_norm": 0.023541666567325592,
      "learning_rate": 4.086106830051236e-06,
      "loss": 10.3449,
      "step": 181
    },
    {
      "epoch": 0.6166225516146109,
      "grad_norm": 0.06664617359638214,
      "learning_rate": 3.670761277863485e-06,
      "loss": 10.3473,
      "step": 182
    },
    {
      "epoch": 0.6200105876124934,
      "grad_norm": 0.022008830681443214,
      "learning_rate": 3.277143302772342e-06,
      "loss": 10.345,
      "step": 183
    },
    {
      "epoch": 0.6233986236103759,
      "grad_norm": 0.020388372242450714,
      "learning_rate": 2.9053728046260825e-06,
      "loss": 10.3434,
      "step": 184
    },
    {
      "epoch": 0.6267866596082583,
      "grad_norm": 0.02203419804573059,
      "learning_rate": 2.555563028319885e-06,
      "loss": 10.3441,
      "step": 185
    },
    {
      "epoch": 0.6301746956061408,
      "grad_norm": 0.020321670919656754,
      "learning_rate": 2.227820529300264e-06,
      "loss": 10.3448,
      "step": 186
    },
    {
      "epoch": 0.6335627316040233,
      "grad_norm": 0.0204358771443367,
      "learning_rate": 1.9222451411073645e-06,
      "loss": 10.3445,
      "step": 187
    },
    {
      "epoch": 0.6369507676019057,
      "grad_norm": 0.02741316892206669,
      "learning_rate": 1.6389299449645733e-06,
      "loss": 10.3437,
      "step": 188
    },
    {
      "epoch": 0.6403388035997882,
      "grad_norm": 0.018788231536746025,
      "learning_rate": 1.3779612414252017e-06,
      "loss": 10.3452,
      "step": 189
    },
    {
      "epoch": 0.6437268395976707,
      "grad_norm": 0.020280800759792328,
      "learning_rate": 1.1394185240843983e-06,
      "loss": 10.3459,
      "step": 190
    },
    {
      "epoch": 0.6471148755955533,
      "grad_norm": 0.01888551376760006,
      "learning_rate": 9.233744553646754e-07,
      "loss": 10.3457,
      "step": 191
    },
    {
      "epoch": 0.6505029115934357,
      "grad_norm": 0.020312048494815826,
      "learning_rate": 7.298948443822228e-07,
      "loss": 10.3441,
      "step": 192
    },
    {
      "epoch": 0.6538909475913182,
      "grad_norm": 0.01959800161421299,
      "learning_rate": 5.590386269008512e-07,
      "loss": 10.3434,
      "step": 193
    },
    {
      "epoch": 0.6572789835892007,
      "grad_norm": 0.024537065997719765,
      "learning_rate": 4.108578473795032e-07,
      "loss": 10.3446,
      "step": 194
    },
    {
      "epoch": 0.6606670195870831,
      "grad_norm": 0.020832853391766548,
      "learning_rate": 2.8539764311908407e-07,
      "loss": 10.345,
      "step": 195
    },
    {
      "epoch": 0.6640550555849656,
      "grad_norm": 0.020389897748827934,
      "learning_rate": 1.8269623051318515e-07,
      "loss": 10.3452,
      "step": 196
    },
    {
      "epoch": 0.6674430915828481,
      "grad_norm": 0.018793173134326935,
      "learning_rate": 1.027848934069625e-07,
      "loss": 10.3462,
      "step": 197
    },
    {
      "epoch": 0.6708311275807305,
      "grad_norm": 0.03216562792658806,
      "learning_rate": 4.568797356781784e-08,
      "loss": 10.3447,
      "step": 198
    },
    {
      "epoch": 0.674219163578613,
      "grad_norm": 0.02798965945839882,
      "learning_rate": 1.142286327065478e-08,
      "loss": 10.3446,
      "step": 199
    },
    {
      "epoch": 0.6776071995764955,
      "grad_norm": 0.021245818585157394,
      "learning_rate": 0.0,
      "loss": 10.3461,
      "step": 200
    },
    {
      "epoch": 0.6776071995764955,
      "eval_loss": 10.3442964553833,
      "eval_runtime": 3.9275,
      "eval_samples_per_second": 253.34,
      "eval_steps_per_second": 126.797,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 17,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 85669769379840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}