{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.74247491638796,
  "eval_steps": 200,
  "global_step": 20500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013377926421404682,
      "grad_norm": 0.9171162843704224,
      "learning_rate": 7.05e-06,
      "loss": 2.16,
      "step": 100
    },
    {
      "epoch": 0.026755852842809364,
      "grad_norm": 0.4195552170276642,
      "learning_rate": 1.41e-05,
      "loss": 1.7242,
      "step": 200
    },
    {
      "epoch": 0.04013377926421405,
      "grad_norm": 0.40102216601371765,
      "learning_rate": 1.4036557930258718e-05,
      "loss": 1.2567,
      "step": 300
    },
    {
      "epoch": 0.05351170568561873,
      "grad_norm": 0.5191290378570557,
      "learning_rate": 1.3973115860517437e-05,
      "loss": 1.0338,
      "step": 400
    },
    {
      "epoch": 0.06688963210702341,
      "grad_norm": 0.356404185295105,
      "learning_rate": 1.3909673790776152e-05,
      "loss": 0.8353,
      "step": 500
    },
    {
      "epoch": 0.0802675585284281,
      "grad_norm": 0.4750893712043762,
      "learning_rate": 1.3846231721034871e-05,
      "loss": 0.7277,
      "step": 600
    },
    {
      "epoch": 0.09364548494983277,
      "grad_norm": 0.27046123147010803,
      "learning_rate": 1.3782789651293589e-05,
      "loss": 0.6938,
      "step": 700
    },
    {
      "epoch": 0.10702341137123746,
      "grad_norm": 0.22247174382209778,
      "learning_rate": 1.3719347581552308e-05,
      "loss": 0.6622,
      "step": 800
    },
    {
      "epoch": 0.12040133779264214,
      "grad_norm": 0.2817244827747345,
      "learning_rate": 1.3655905511811023e-05,
      "loss": 0.639,
      "step": 900
    },
    {
      "epoch": 0.13377926421404682,
      "grad_norm": 0.31701573729515076,
      "learning_rate": 1.3592463442069742e-05,
      "loss": 0.6269,
      "step": 1000
    },
    {
      "epoch": 0.14715719063545152,
      "grad_norm": 0.2620750367641449,
      "learning_rate": 1.352902137232846e-05,
      "loss": 0.6095,
      "step": 1100
    },
    {
      "epoch": 0.1605351170568562,
      "grad_norm": 0.31606021523475647,
      "learning_rate": 1.3465579302587177e-05,
      "loss": 0.6336,
      "step": 1200
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 0.2545430362224579,
      "learning_rate": 1.3402137232845896e-05,
      "loss": 0.6061,
      "step": 1300
    },
    {
      "epoch": 0.18729096989966554,
      "grad_norm": 0.1961711347103119,
      "learning_rate": 1.3338695163104611e-05,
      "loss": 0.6155,
      "step": 1400
    },
    {
      "epoch": 0.20066889632107024,
      "grad_norm": 0.3367158770561218,
      "learning_rate": 1.327525309336333e-05,
      "loss": 0.6045,
      "step": 1500
    },
    {
      "epoch": 0.2140468227424749,
      "grad_norm": 0.23051577806472778,
      "learning_rate": 1.3211811023622048e-05,
      "loss": 0.5899,
      "step": 1600
    },
    {
      "epoch": 0.22742474916387959,
      "grad_norm": 0.198777973651886,
      "learning_rate": 1.3148368953880767e-05,
      "loss": 0.5787,
      "step": 1700
    },
    {
      "epoch": 0.2408026755852843,
      "grad_norm": 0.20267942547798157,
      "learning_rate": 1.3084926884139484e-05,
      "loss": 0.5825,
      "step": 1800
    },
    {
      "epoch": 0.25418060200668896,
      "grad_norm": 0.19377346336841583,
      "learning_rate": 1.30214848143982e-05,
      "loss": 0.5571,
      "step": 1900
    },
    {
      "epoch": 0.26755852842809363,
      "grad_norm": 0.2121889889240265,
      "learning_rate": 1.2958042744656918e-05,
      "loss": 0.5843,
      "step": 2000
    },
    {
      "epoch": 0.2809364548494983,
      "grad_norm": 0.28105607628822327,
      "learning_rate": 1.2894600674915636e-05,
      "loss": 0.5766,
      "step": 2100
    },
    {
      "epoch": 0.29431438127090304,
      "grad_norm": 0.22681908309459686,
      "learning_rate": 1.2831158605174355e-05,
      "loss": 0.6059,
      "step": 2200
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.21604150533676147,
      "learning_rate": 1.276771653543307e-05,
      "loss": 0.5724,
      "step": 2300
    },
    {
      "epoch": 0.3210702341137124,
      "grad_norm": 0.24839992821216583,
      "learning_rate": 1.270427446569179e-05,
      "loss": 0.5921,
      "step": 2400
    },
    {
      "epoch": 0.33444816053511706,
      "grad_norm": 0.1966131031513214,
      "learning_rate": 1.2640832395950507e-05,
      "loss": 0.553,
      "step": 2500
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 0.21823905408382416,
      "learning_rate": 1.2577390326209224e-05,
      "loss": 0.5772,
      "step": 2600
    },
    {
      "epoch": 0.3612040133779264,
      "grad_norm": 0.19366396963596344,
      "learning_rate": 1.2513948256467943e-05,
      "loss": 0.574,
      "step": 2700
    },
    {
      "epoch": 0.3745819397993311,
      "grad_norm": 0.2325657606124878,
      "learning_rate": 1.2450506186726658e-05,
      "loss": 0.5573,
      "step": 2800
    },
    {
      "epoch": 0.3879598662207358,
      "grad_norm": 0.1978592425584793,
      "learning_rate": 1.2387064116985377e-05,
      "loss": 0.5728,
      "step": 2900
    },
    {
      "epoch": 0.4013377926421405,
      "grad_norm": 0.25745445489883423,
      "learning_rate": 1.2323622047244095e-05,
      "loss": 0.5659,
      "step": 3000
    },
    {
      "epoch": 0.41471571906354515,
      "grad_norm": 0.25649788975715637,
      "learning_rate": 1.2260179977502814e-05,
      "loss": 0.5573,
      "step": 3100
    },
    {
      "epoch": 0.4280936454849498,
      "grad_norm": 0.2513531744480133,
      "learning_rate": 1.2196737907761531e-05,
      "loss": 0.5505,
      "step": 3200
    },
    {
      "epoch": 0.4414715719063545,
      "grad_norm": 0.3094983398914337,
      "learning_rate": 1.2133295838020248e-05,
      "loss": 0.5708,
      "step": 3300
    },
    {
      "epoch": 0.45484949832775917,
      "grad_norm": 0.2737010717391968,
      "learning_rate": 1.2069853768278965e-05,
      "loss": 0.5586,
      "step": 3400
    },
    {
      "epoch": 0.4682274247491639,
      "grad_norm": 0.23205673694610596,
      "learning_rate": 1.2006411698537683e-05,
      "loss": 0.5509,
      "step": 3500
    },
    {
      "epoch": 0.4816053511705686,
      "grad_norm": 0.23067252337932587,
      "learning_rate": 1.1942969628796402e-05,
      "loss": 0.5622,
      "step": 3600
    },
    {
      "epoch": 0.49498327759197325,
      "grad_norm": 0.25091397762298584,
      "learning_rate": 1.1879527559055117e-05,
      "loss": 0.5468,
      "step": 3700
    },
    {
      "epoch": 0.5083612040133779,
      "grad_norm": 0.20600271224975586,
      "learning_rate": 1.1816085489313836e-05,
      "loss": 0.5649,
      "step": 3800
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 0.26764076948165894,
      "learning_rate": 1.1752643419572554e-05,
      "loss": 0.5713,
      "step": 3900
    },
    {
      "epoch": 0.5351170568561873,
      "grad_norm": 0.22692909836769104,
      "learning_rate": 1.1689201349831273e-05,
      "loss": 0.5495,
      "step": 4000
    },
    {
      "epoch": 0.5484949832775919,
      "grad_norm": 0.2563936710357666,
      "learning_rate": 1.162575928008999e-05,
      "loss": 0.5557,
      "step": 4100
    },
    {
      "epoch": 0.5618729096989966,
      "grad_norm": 0.23220312595367432,
      "learning_rate": 1.1562317210348705e-05,
      "loss": 0.542,
      "step": 4200
    },
    {
      "epoch": 0.5752508361204013,
      "grad_norm": 0.19552694261074066,
      "learning_rate": 1.1498875140607424e-05,
      "loss": 0.5645,
      "step": 4300
    },
    {
      "epoch": 0.5886287625418061,
      "grad_norm": 0.27880212664604187,
      "learning_rate": 1.1435433070866142e-05,
      "loss": 0.538,
      "step": 4400
    },
    {
      "epoch": 0.6020066889632107,
      "grad_norm": 0.2759273052215576,
      "learning_rate": 1.137199100112486e-05,
      "loss": 0.554,
      "step": 4500
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.21541567146778107,
      "learning_rate": 1.1308548931383578e-05,
      "loss": 0.5598,
      "step": 4600
    },
    {
      "epoch": 0.6287625418060201,
      "grad_norm": 0.2586516737937927,
      "learning_rate": 1.1245106861642295e-05,
      "loss": 0.5558,
      "step": 4700
    },
    {
      "epoch": 0.6421404682274248,
      "grad_norm": 0.355333149433136,
      "learning_rate": 1.1181664791901013e-05,
      "loss": 0.5529,
      "step": 4800
    },
    {
      "epoch": 0.6555183946488294,
      "grad_norm": 0.2383916974067688,
      "learning_rate": 1.111822272215973e-05,
      "loss": 0.5409,
      "step": 4900
    },
    {
      "epoch": 0.6688963210702341,
      "grad_norm": 0.24805516004562378,
      "learning_rate": 1.1054780652418449e-05,
      "loss": 0.5546,
      "step": 5000
    },
    {
      "epoch": 0.6822742474916388,
      "grad_norm": 0.25741276144981384,
      "learning_rate": 1.0991338582677164e-05,
      "loss": 0.5393,
      "step": 5100
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.2695322334766388,
      "learning_rate": 1.0927896512935883e-05,
      "loss": 0.5526,
      "step": 5200
    },
    {
      "epoch": 0.7090301003344481,
      "grad_norm": 0.3145568072795868,
      "learning_rate": 1.08644544431946e-05,
      "loss": 0.541,
      "step": 5300
    },
    {
      "epoch": 0.7224080267558528,
      "grad_norm": 0.2946968972682953,
      "learning_rate": 1.080101237345332e-05,
      "loss": 0.5463,
      "step": 5400
    },
    {
      "epoch": 0.7357859531772575,
      "grad_norm": 0.24955065548419952,
      "learning_rate": 1.0737570303712037e-05,
      "loss": 0.5423,
      "step": 5500
    },
    {
      "epoch": 0.7491638795986622,
      "grad_norm": 0.24316702783107758,
      "learning_rate": 1.0674128233970754e-05,
      "loss": 0.5445,
      "step": 5600
    },
    {
      "epoch": 0.7625418060200669,
      "grad_norm": 0.25755423307418823,
      "learning_rate": 1.0610686164229471e-05,
      "loss": 0.5396,
      "step": 5700
    },
    {
      "epoch": 0.7759197324414716,
      "grad_norm": 0.25169652700424194,
      "learning_rate": 1.0547244094488189e-05,
      "loss": 0.5416,
      "step": 5800
    },
    {
      "epoch": 0.7892976588628763,
      "grad_norm": 0.27045324444770813,
      "learning_rate": 1.0483802024746908e-05,
      "loss": 0.5358,
      "step": 5900
    },
    {
      "epoch": 0.802675585284281,
      "grad_norm": 0.24991023540496826,
      "learning_rate": 1.0420359955005625e-05,
      "loss": 0.5346,
      "step": 6000
    },
    {
      "epoch": 0.8160535117056856,
      "grad_norm": 0.26907652616500854,
      "learning_rate": 1.0356917885264342e-05,
      "loss": 0.5435,
      "step": 6100
    },
    {
      "epoch": 0.8294314381270903,
      "grad_norm": 0.23370976746082306,
      "learning_rate": 1.029347581552306e-05,
      "loss": 0.5465,
      "step": 6200
    },
    {
      "epoch": 0.842809364548495,
      "grad_norm": 0.2467469573020935,
      "learning_rate": 1.0230033745781779e-05,
      "loss": 0.5321,
      "step": 6300
    },
    {
      "epoch": 0.8561872909698997,
      "grad_norm": 0.2975829839706421,
      "learning_rate": 1.0166591676040496e-05,
      "loss": 0.5454,
      "step": 6400
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.2862960398197174,
      "learning_rate": 1.0103149606299211e-05,
      "loss": 0.5364,
      "step": 6500
    },
    {
      "epoch": 0.882943143812709,
      "grad_norm": 0.2974550724029541,
      "learning_rate": 1.003970753655793e-05,
      "loss": 0.5551,
      "step": 6600
    },
    {
      "epoch": 0.8963210702341137,
      "grad_norm": 0.3028159737586975,
      "learning_rate": 9.976265466816648e-06,
      "loss": 0.545,
      "step": 6700
    },
    {
      "epoch": 0.9096989966555183,
      "grad_norm": 0.2919917404651642,
      "learning_rate": 9.912823397075367e-06,
      "loss": 0.5321,
      "step": 6800
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.2511245012283325,
      "learning_rate": 9.849381327334084e-06,
      "loss": 0.5437,
      "step": 6900
    },
    {
      "epoch": 0.9364548494983278,
      "grad_norm": 0.2747950553894043,
      "learning_rate": 9.785939257592801e-06,
      "loss": 0.5515,
      "step": 7000
    },
    {
      "epoch": 0.9498327759197325,
      "grad_norm": 0.28584617376327515,
      "learning_rate": 9.722497187851519e-06,
      "loss": 0.5372,
      "step": 7100
    },
    {
      "epoch": 0.9632107023411371,
      "grad_norm": 0.3047812283039093,
      "learning_rate": 9.659055118110236e-06,
      "loss": 0.5497,
      "step": 7200
    },
    {
      "epoch": 0.9765886287625418,
      "grad_norm": 0.27929434180259705,
      "learning_rate": 9.595613048368955e-06,
      "loss": 0.5343,
      "step": 7300
    },
    {
      "epoch": 0.9899665551839465,
      "grad_norm": 0.26125389337539673,
      "learning_rate": 9.532170978627672e-06,
      "loss": 0.5345,
      "step": 7400
    },
    {
      "epoch": 1.0033444816053512,
      "grad_norm": 0.26159632205963135,
      "learning_rate": 9.46872890888639e-06,
      "loss": 0.5367,
      "step": 7500
    },
    {
      "epoch": 1.0167224080267558,
      "grad_norm": 0.2183777093887329,
      "learning_rate": 9.405286839145107e-06,
      "loss": 0.5299,
      "step": 7600
    },
    {
      "epoch": 1.0301003344481605,
      "grad_norm": 0.29552075266838074,
      "learning_rate": 9.341844769403826e-06,
      "loss": 0.5233,
      "step": 7700
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 0.30615565180778503,
      "learning_rate": 9.278402699662543e-06,
      "loss": 0.556,
      "step": 7800
    },
    {
      "epoch": 1.0568561872909699,
      "grad_norm": 0.27595141530036926,
      "learning_rate": 9.21496062992126e-06,
      "loss": 0.5394,
      "step": 7900
    },
    {
      "epoch": 1.0702341137123745,
      "grad_norm": 0.3372192978858948,
      "learning_rate": 9.151518560179978e-06,
      "loss": 0.5228,
      "step": 8000
    },
    {
      "epoch": 1.0836120401337792,
      "grad_norm": 0.25586509704589844,
      "learning_rate": 9.088076490438695e-06,
      "loss": 0.5441,
      "step": 8100
    },
    {
      "epoch": 1.0969899665551839,
      "grad_norm": 0.2440231442451477,
      "learning_rate": 9.024634420697414e-06,
      "loss": 0.5469,
      "step": 8200
    },
    {
      "epoch": 1.1103678929765886,
      "grad_norm": 0.21979352831840515,
      "learning_rate": 8.961192350956131e-06,
      "loss": 0.5295,
      "step": 8300
    },
    {
      "epoch": 1.1237458193979932,
      "grad_norm": 0.3029584586620331,
      "learning_rate": 8.897750281214848e-06,
      "loss": 0.5334,
      "step": 8400
    },
    {
      "epoch": 1.137123745819398,
      "grad_norm": 0.2796266973018646,
      "learning_rate": 8.834308211473566e-06,
      "loss": 0.5346,
      "step": 8500
    },
    {
      "epoch": 1.1505016722408028,
      "grad_norm": 0.2513901889324188,
      "learning_rate": 8.770866141732285e-06,
      "loss": 0.5271,
      "step": 8600
    },
    {
      "epoch": 1.1638795986622075,
      "grad_norm": 0.32265734672546387,
      "learning_rate": 8.707424071991002e-06,
      "loss": 0.5426,
      "step": 8700
    },
    {
      "epoch": 1.1772575250836121,
      "grad_norm": 0.26003068685531616,
      "learning_rate": 8.64398200224972e-06,
      "loss": 0.5484,
      "step": 8800
    },
    {
      "epoch": 1.1906354515050168,
      "grad_norm": 0.28756487369537354,
      "learning_rate": 8.580539932508436e-06,
      "loss": 0.5459,
      "step": 8900
    },
    {
      "epoch": 1.2040133779264215,
      "grad_norm": 0.2572449743747711,
      "learning_rate": 8.517097862767154e-06,
      "loss": 0.5371,
      "step": 9000
    },
    {
      "epoch": 1.2173913043478262,
      "grad_norm": 0.3304179012775421,
      "learning_rate": 8.453655793025873e-06,
      "loss": 0.5319,
      "step": 9100
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.30001091957092285,
      "learning_rate": 8.39021372328459e-06,
      "loss": 0.5441,
      "step": 9200
    },
    {
      "epoch": 1.2441471571906355,
      "grad_norm": 0.29723092913627625,
      "learning_rate": 8.326771653543307e-06,
      "loss": 0.5252,
      "step": 9300
    },
    {
      "epoch": 1.2575250836120402,
      "grad_norm": 0.3556860685348511,
      "learning_rate": 8.263329583802025e-06,
      "loss": 0.5369,
      "step": 9400
    },
    {
      "epoch": 1.2709030100334449,
      "grad_norm": 0.3591911792755127,
      "learning_rate": 8.199887514060742e-06,
      "loss": 0.5352,
      "step": 9500
    },
    {
      "epoch": 1.2842809364548495,
      "grad_norm": 0.3007011115550995,
      "learning_rate": 8.13644544431946e-06,
      "loss": 0.5418,
      "step": 9600
    },
    {
      "epoch": 1.2976588628762542,
      "grad_norm": 0.2747509479522705,
      "learning_rate": 8.073003374578178e-06,
      "loss": 0.5377,
      "step": 9700
    },
    {
      "epoch": 1.3110367892976589,
      "grad_norm": 0.32818782329559326,
      "learning_rate": 8.009561304836895e-06,
      "loss": 0.5226,
      "step": 9800
    },
    {
      "epoch": 1.3244147157190636,
      "grad_norm": 0.33487051725387573,
      "learning_rate": 7.946119235095613e-06,
      "loss": 0.5314,
      "step": 9900
    },
    {
      "epoch": 1.3377926421404682,
      "grad_norm": 0.25218817591667175,
      "learning_rate": 7.882677165354332e-06,
      "loss": 0.5329,
      "step": 10000
    },
    {
      "epoch": 1.351170568561873,
      "grad_norm": 0.3178349733352661,
      "learning_rate": 7.819235095613049e-06,
      "loss": 0.5278,
      "step": 10100
    },
    {
      "epoch": 1.3645484949832776,
      "grad_norm": 0.2949560284614563,
      "learning_rate": 7.755793025871766e-06,
      "loss": 0.5453,
      "step": 10200
    },
    {
      "epoch": 1.3779264214046822,
      "grad_norm": 0.3159886300563812,
      "learning_rate": 7.692350956130484e-06,
      "loss": 0.5382,
      "step": 10300
    },
    {
      "epoch": 1.391304347826087,
      "grad_norm": 0.32193896174430847,
      "learning_rate": 7.628908886389202e-06,
      "loss": 0.5365,
      "step": 10400
    },
    {
      "epoch": 1.4046822742474916,
      "grad_norm": 0.27942079305648804,
      "learning_rate": 7.56546681664792e-06,
      "loss": 0.5276,
      "step": 10500
    },
    {
      "epoch": 1.4180602006688963,
      "grad_norm": 0.28040722012519836,
      "learning_rate": 7.502024746906637e-06,
      "loss": 0.5281,
      "step": 10600
    },
    {
      "epoch": 1.431438127090301,
      "grad_norm": 0.3048112094402313,
      "learning_rate": 7.4385826771653535e-06,
      "loss": 0.5347,
      "step": 10700
    },
    {
      "epoch": 1.4448160535117056,
      "grad_norm": 0.3182535767555237,
      "learning_rate": 7.375140607424072e-06,
      "loss": 0.5444,
      "step": 10800
    },
    {
      "epoch": 1.4581939799331103,
      "grad_norm": 0.6139577031135559,
      "learning_rate": 7.31169853768279e-06,
      "loss": 0.5292,
      "step": 10900
    },
    {
      "epoch": 1.471571906354515,
      "grad_norm": 0.26481977105140686,
      "learning_rate": 7.248256467941508e-06,
      "loss": 0.5409,
      "step": 11000
    },
    {
      "epoch": 1.4849498327759196,
      "grad_norm": 0.2902706265449524,
      "learning_rate": 7.184814398200226e-06,
      "loss": 0.5525,
      "step": 11100
    },
    {
      "epoch": 1.4983277591973243,
      "grad_norm": 0.3402746021747589,
      "learning_rate": 7.1213723284589425e-06,
      "loss": 0.5267,
      "step": 11200
    },
    {
      "epoch": 1.511705685618729,
      "grad_norm": 0.2799215018749237,
      "learning_rate": 7.057930258717661e-06,
      "loss": 0.5247,
      "step": 11300
    },
    {
      "epoch": 1.5250836120401337,
      "grad_norm": 0.38291794061660767,
      "learning_rate": 6.994488188976379e-06,
      "loss": 0.5376,
      "step": 11400
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.28172844648361206,
      "learning_rate": 6.931046119235095e-06,
      "loss": 0.5279,
      "step": 11500
    },
    {
      "epoch": 1.551839464882943,
      "grad_norm": 0.42768093943595886,
      "learning_rate": 6.867604049493813e-06,
      "loss": 0.5189,
      "step": 11600
    },
    {
      "epoch": 1.5652173913043477,
      "grad_norm": 0.2789342701435089,
      "learning_rate": 6.8041619797525314e-06,
      "loss": 0.528,
      "step": 11700
    },
    {
      "epoch": 1.5785953177257523,
      "grad_norm": 0.30609387159347534,
      "learning_rate": 6.740719910011249e-06,
      "loss": 0.5381,
      "step": 11800
    },
    {
      "epoch": 1.5919732441471572,
      "grad_norm": 0.3225257098674774,
      "learning_rate": 6.677277840269967e-06,
      "loss": 0.5472,
      "step": 11900
    },
    {
      "epoch": 1.605351170568562,
      "grad_norm": 0.3523938059806824,
      "learning_rate": 6.613835770528684e-06,
      "loss": 0.5269,
      "step": 12000
    },
    {
      "epoch": 1.6187290969899666,
      "grad_norm": 0.31391632556915283,
      "learning_rate": 6.550393700787402e-06,
      "loss": 0.539,
      "step": 12100
    },
    {
      "epoch": 1.6321070234113713,
      "grad_norm": 0.3466421365737915,
      "learning_rate": 6.4869516310461196e-06,
      "loss": 0.5228,
      "step": 12200
    },
    {
      "epoch": 1.645484949832776,
      "grad_norm": 0.31395405530929565,
      "learning_rate": 6.423509561304837e-06,
      "loss": 0.5199,
      "step": 12300
    },
    {
      "epoch": 1.6588628762541806,
      "grad_norm": 0.2847534120082855,
      "learning_rate": 6.360067491563555e-06,
      "loss": 0.5233,
      "step": 12400
    },
    {
      "epoch": 1.6722408026755853,
      "grad_norm": 0.28372418880462646,
      "learning_rate": 6.296625421822272e-06,
      "loss": 0.5287,
      "step": 12500
    },
    {
      "epoch": 1.68561872909699,
      "grad_norm": 0.30443572998046875,
      "learning_rate": 6.23318335208099e-06,
      "loss": 0.5307,
      "step": 12600
    },
    {
      "epoch": 1.6989966555183946,
      "grad_norm": 0.2609320878982544,
      "learning_rate": 6.169741282339708e-06,
      "loss": 0.5342,
      "step": 12700
    },
    {
      "epoch": 1.7123745819397993,
      "grad_norm": 0.33631429076194763,
      "learning_rate": 6.106299212598426e-06,
      "loss": 0.5276,
      "step": 12800
    },
    {
      "epoch": 1.725752508361204,
      "grad_norm": 0.3686012923717499,
      "learning_rate": 6.042857142857143e-06,
      "loss": 0.5469,
      "step": 12900
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 0.31965962052345276,
      "learning_rate": 5.97941507311586e-06,
      "loss": 0.5225,
      "step": 13000
    },
    {
      "epoch": 1.7525083612040135,
      "grad_norm": 0.3114967346191406,
      "learning_rate": 5.9159730033745785e-06,
      "loss": 0.5284,
      "step": 13100
    },
    {
      "epoch": 1.7658862876254182,
      "grad_norm": 0.2994590997695923,
      "learning_rate": 5.852530933633296e-06,
      "loss": 0.522,
      "step": 13200
    },
    {
      "epoch": 1.779264214046823,
      "grad_norm": 0.2821991443634033,
      "learning_rate": 5.789088863892014e-06,
      "loss": 0.5331,
      "step": 13300
    },
    {
      "epoch": 1.7926421404682276,
      "grad_norm": 0.3011917769908905,
      "learning_rate": 5.725646794150731e-06,
      "loss": 0.53,
      "step": 13400
    },
    {
      "epoch": 1.8060200668896322,
      "grad_norm": 0.35369744896888733,
      "learning_rate": 5.662204724409449e-06,
      "loss": 0.5214,
      "step": 13500
    },
    {
      "epoch": 1.819397993311037,
      "grad_norm": 0.4051268696784973,
      "learning_rate": 5.598762654668167e-06,
      "loss": 0.523,
      "step": 13600
    },
    {
      "epoch": 1.8327759197324416,
      "grad_norm": 0.291557252407074,
      "learning_rate": 5.535320584926885e-06,
      "loss": 0.5168,
      "step": 13700
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.3216087222099304,
      "learning_rate": 5.471878515185602e-06,
      "loss": 0.5173,
      "step": 13800
    },
    {
      "epoch": 1.859531772575251,
      "grad_norm": 0.30401530861854553,
      "learning_rate": 5.408436445444319e-06,
      "loss": 0.53,
      "step": 13900
    },
    {
      "epoch": 1.8729096989966556,
      "grad_norm": 0.317964106798172,
      "learning_rate": 5.3449943757030374e-06,
      "loss": 0.5338,
      "step": 14000
    },
    {
      "epoch": 1.8862876254180603,
      "grad_norm": 0.29879599809646606,
      "learning_rate": 5.281552305961755e-06,
      "loss": 0.5167,
      "step": 14100
    },
    {
      "epoch": 1.899665551839465,
      "grad_norm": 0.32501399517059326,
      "learning_rate": 5.218110236220473e-06,
      "loss": 0.5403,
      "step": 14200
    },
    {
      "epoch": 1.9130434782608696,
      "grad_norm": 0.3261101543903351,
      "learning_rate": 5.15466816647919e-06,
      "loss": 0.5393,
      "step": 14300
    },
    {
      "epoch": 1.9264214046822743,
      "grad_norm": 0.3254980742931366,
      "learning_rate": 5.091226096737908e-06,
      "loss": 0.532,
      "step": 14400
    },
    {
      "epoch": 1.939799331103679,
      "grad_norm": 0.3090830445289612,
      "learning_rate": 5.0277840269966256e-06,
      "loss": 0.523,
      "step": 14500
    },
    {
      "epoch": 1.9531772575250836,
      "grad_norm": 0.3061154782772064,
      "learning_rate": 4.964341957255343e-06,
      "loss": 0.543,
      "step": 14600
    },
    {
      "epoch": 1.9665551839464883,
      "grad_norm": 0.3317748010158539,
      "learning_rate": 4.900899887514061e-06,
      "loss": 0.5294,
      "step": 14700
    },
    {
      "epoch": 1.979933110367893,
      "grad_norm": 0.31979861855506897,
      "learning_rate": 4.837457817772778e-06,
      "loss": 0.5267,
      "step": 14800
    },
    {
      "epoch": 1.9933110367892977,
      "grad_norm": 0.3413035571575165,
      "learning_rate": 4.774015748031496e-06,
      "loss": 0.5249,
      "step": 14900
    },
    {
      "epoch": 2.0066889632107023,
      "grad_norm": 0.3047432601451874,
      "learning_rate": 4.710573678290214e-06,
      "loss": 0.5245,
      "step": 15000
    },
    {
      "epoch": 2.020066889632107,
      "grad_norm": 0.41027894616127014,
      "learning_rate": 4.647131608548932e-06,
      "loss": 0.5254,
      "step": 15100
    },
    {
      "epoch": 2.0334448160535117,
      "grad_norm": 0.32369574904441833,
      "learning_rate": 4.58368953880765e-06,
      "loss": 0.5129,
      "step": 15200
    },
    {
      "epoch": 2.0468227424749164,
      "grad_norm": 0.35738885402679443,
      "learning_rate": 4.520247469066366e-06,
      "loss": 0.5297,
      "step": 15300
    },
    {
      "epoch": 2.060200668896321,
      "grad_norm": 0.3717624545097351,
      "learning_rate": 4.4568053993250845e-06,
      "loss": 0.523,
      "step": 15400
    },
    {
      "epoch": 2.0735785953177257,
      "grad_norm": 0.4179551601409912,
      "learning_rate": 4.393363329583802e-06,
      "loss": 0.5262,
      "step": 15500
    },
    {
      "epoch": 2.0869565217391304,
      "grad_norm": 0.28650280833244324,
      "learning_rate": 4.32992125984252e-06,
      "loss": 0.5173,
      "step": 15600
    },
    {
      "epoch": 2.100334448160535,
      "grad_norm": 0.3133101463317871,
      "learning_rate": 4.266479190101237e-06,
      "loss": 0.5371,
      "step": 15700
    },
    {
      "epoch": 2.1137123745819397,
      "grad_norm": 0.28342047333717346,
      "learning_rate": 4.203037120359955e-06,
      "loss": 0.5305,
      "step": 15800
    },
    {
      "epoch": 2.1270903010033444,
      "grad_norm": 0.3236102759838104,
      "learning_rate": 4.1395950506186735e-06,
      "loss": 0.5365,
      "step": 15900
    },
    {
      "epoch": 2.140468227424749,
      "grad_norm": 0.2886063754558563,
      "learning_rate": 4.076152980877391e-06,
      "loss": 0.5264,
      "step": 16000
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.32379692792892456,
      "learning_rate": 4.012710911136108e-06,
      "loss": 0.5311,
      "step": 16100
    },
    {
      "epoch": 2.1672240802675584,
      "grad_norm": 0.33309829235076904,
      "learning_rate": 3.949268841394825e-06,
      "loss": 0.5253,
      "step": 16200
    },
    {
      "epoch": 2.180602006688963,
      "grad_norm": 0.4101524353027344,
      "learning_rate": 3.8858267716535435e-06,
      "loss": 0.5302,
      "step": 16300
    },
    {
      "epoch": 2.1939799331103678,
      "grad_norm": 0.3807373344898224,
      "learning_rate": 3.822384701912261e-06,
      "loss": 0.5178,
      "step": 16400
    },
    {
      "epoch": 2.2073578595317724,
      "grad_norm": 0.32313257455825806,
      "learning_rate": 3.758942632170979e-06,
      "loss": 0.5158,
      "step": 16500
    },
    {
      "epoch": 2.220735785953177,
      "grad_norm": 0.26424798369407654,
      "learning_rate": 3.6955005624296966e-06,
      "loss": 0.519,
      "step": 16600
    },
    {
      "epoch": 2.234113712374582,
      "grad_norm": 0.4011124074459076,
      "learning_rate": 3.632058492688414e-06,
      "loss": 0.5195,
      "step": 16700
    },
    {
      "epoch": 2.2474916387959865,
      "grad_norm": 0.3362158238887787,
      "learning_rate": 3.568616422947132e-06,
      "loss": 0.5373,
      "step": 16800
    },
    {
      "epoch": 2.260869565217391,
      "grad_norm": 0.3145718276500702,
      "learning_rate": 3.5051743532058493e-06,
      "loss": 0.5405,
      "step": 16900
    },
    {
      "epoch": 2.274247491638796,
      "grad_norm": 0.3200240731239319,
      "learning_rate": 3.4417322834645674e-06,
      "loss": 0.5299,
      "step": 17000
    },
    {
      "epoch": 2.2876254180602005,
      "grad_norm": 0.37791967391967773,
      "learning_rate": 3.3782902137232847e-06,
      "loss": 0.5237,
      "step": 17100
    },
    {
      "epoch": 2.3010033444816056,
      "grad_norm": 0.3673136532306671,
      "learning_rate": 3.3148481439820024e-06,
      "loss": 0.5324,
      "step": 17200
    },
    {
      "epoch": 2.3143812709030103,
      "grad_norm": 0.39470499753952026,
      "learning_rate": 3.25140607424072e-06,
      "loss": 0.541,
      "step": 17300
    },
    {
      "epoch": 2.327759197324415,
      "grad_norm": 0.3546443283557892,
      "learning_rate": 3.187964004499438e-06,
      "loss": 0.5279,
      "step": 17400
    },
    {
      "epoch": 2.3411371237458196,
      "grad_norm": 0.5016634464263916,
      "learning_rate": 3.124521934758155e-06,
      "loss": 0.5353,
      "step": 17500
    },
    {
      "epoch": 2.3545150501672243,
      "grad_norm": 0.40390917658805847,
      "learning_rate": 3.061079865016873e-06,
      "loss": 0.5304,
      "step": 17600
    },
    {
      "epoch": 2.367892976588629,
      "grad_norm": 0.28355857729911804,
      "learning_rate": 2.997637795275591e-06,
      "loss": 0.5407,
      "step": 17700
    },
    {
      "epoch": 2.3812709030100336,
      "grad_norm": 0.3010845482349396,
      "learning_rate": 2.9341957255343082e-06,
      "loss": 0.5195,
      "step": 17800
    },
    {
      "epoch": 2.3946488294314383,
      "grad_norm": 0.2997265160083771,
      "learning_rate": 2.870753655793026e-06,
      "loss": 0.5132,
      "step": 17900
    },
    {
      "epoch": 2.408026755852843,
      "grad_norm": 0.2978328466415405,
      "learning_rate": 2.8073115860517436e-06,
      "loss": 0.5138,
      "step": 18000
    },
    {
      "epoch": 2.4214046822742477,
      "grad_norm": 0.45286494493484497,
      "learning_rate": 2.7438695163104614e-06,
      "loss": 0.525,
      "step": 18100
    },
    {
      "epoch": 2.4347826086956523,
      "grad_norm": 0.3671605885028839,
      "learning_rate": 2.6804274465691786e-06,
      "loss": 0.5116,
      "step": 18200
    },
    {
      "epoch": 2.448160535117057,
      "grad_norm": 0.38759517669677734,
      "learning_rate": 2.6169853768278963e-06,
      "loss": 0.5252,
      "step": 18300
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.34254246950149536,
      "learning_rate": 2.5535433070866145e-06,
      "loss": 0.533,
      "step": 18400
    },
    {
      "epoch": 2.4749163879598663,
      "grad_norm": 0.4010314345359802,
      "learning_rate": 2.490101237345332e-06,
      "loss": 0.5378,
      "step": 18500
    },
    {
      "epoch": 2.488294314381271,
      "grad_norm": 0.37069615721702576,
      "learning_rate": 2.4266591676040495e-06,
      "loss": 0.5377,
      "step": 18600
    },
    {
      "epoch": 2.5016722408026757,
      "grad_norm": 0.3937046229839325,
      "learning_rate": 2.363217097862767e-06,
      "loss": 0.5195,
      "step": 18700
    },
    {
      "epoch": 2.5150501672240804,
      "grad_norm": 0.29711517691612244,
      "learning_rate": 2.299775028121485e-06,
      "loss": 0.5227,
      "step": 18800
    },
    {
      "epoch": 2.528428093645485,
      "grad_norm": 0.4100757837295532,
      "learning_rate": 2.2363329583802026e-06,
      "loss": 0.5354,
      "step": 18900
    },
    {
      "epoch": 2.5418060200668897,
      "grad_norm": 0.37300094962120056,
      "learning_rate": 2.17289088863892e-06,
      "loss": 0.5084,
      "step": 19000
    },
    {
      "epoch": 2.5551839464882944,
      "grad_norm": 0.42899075150489807,
      "learning_rate": 2.109448818897638e-06,
      "loss": 0.5302,
      "step": 19100
    },
    {
      "epoch": 2.568561872909699,
      "grad_norm": 0.35038477182388306,
      "learning_rate": 2.0460067491563557e-06,
      "loss": 0.5193,
      "step": 19200
    },
    {
      "epoch": 2.5819397993311037,
      "grad_norm": 0.42968684434890747,
      "learning_rate": 1.9825646794150734e-06,
      "loss": 0.5342,
      "step": 19300
    },
    {
      "epoch": 2.5953177257525084,
      "grad_norm": 0.33188048005104065,
      "learning_rate": 1.9191226096737907e-06,
      "loss": 0.5129,
      "step": 19400
    },
    {
      "epoch": 2.608695652173913,
      "grad_norm": 0.341915100812912,
      "learning_rate": 1.8556805399325084e-06,
      "loss": 0.5236,
      "step": 19500
    },
    {
      "epoch": 2.6220735785953178,
      "grad_norm": 0.3550443649291992,
      "learning_rate": 1.7922384701912261e-06,
      "loss": 0.5349,
      "step": 19600
    },
    {
      "epoch": 2.6354515050167224,
      "grad_norm": 0.3079615533351898,
      "learning_rate": 1.7287964004499438e-06,
      "loss": 0.5153,
      "step": 19700
    },
    {
      "epoch": 2.648829431438127,
      "grad_norm": 0.43465080857276917,
      "learning_rate": 1.6653543307086615e-06,
      "loss": 0.5324,
      "step": 19800
    },
    {
      "epoch": 2.6622073578595318,
      "grad_norm": 0.2985840439796448,
      "learning_rate": 1.601912260967379e-06,
      "loss": 0.5228,
      "step": 19900
    },
    {
      "epoch": 2.6755852842809364,
      "grad_norm": 0.3450627624988556,
      "learning_rate": 1.538470191226097e-06,
      "loss": 0.5205,
      "step": 20000
    },
    {
      "epoch": 2.688963210702341,
      "grad_norm": 0.3443169593811035,
      "learning_rate": 1.4750281214848145e-06,
      "loss": 0.5292,
      "step": 20100
    },
    {
      "epoch": 2.702341137123746,
      "grad_norm": 0.3672339618206024,
      "learning_rate": 1.4115860517435322e-06,
      "loss": 0.5193,
      "step": 20200
    },
    {
      "epoch": 2.7157190635451505,
      "grad_norm": 0.40497252345085144,
      "learning_rate": 1.3481439820022499e-06,
      "loss": 0.5132,
      "step": 20300
    },
    {
      "epoch": 2.729096989966555,
      "grad_norm": 0.32014942169189453,
      "learning_rate": 1.2847019122609674e-06,
      "loss": 0.551,
      "step": 20400
    },
    {
      "epoch": 2.74247491638796,
      "grad_norm": 0.3468855619430542,
      "learning_rate": 1.221259842519685e-06,
      "loss": 0.5245,
      "step": 20500
    }
  ],
  "logging_steps": 100,
  "max_steps": 22425,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.524970641256612e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}