{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 122720,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04074315514993481,
      "grad_norm": 1.2286359071731567,
      "learning_rate": 0.0002987777053455019,
      "loss": 1.0833,
      "step": 500
    },
    {
      "epoch": 0.08148631029986962,
      "grad_norm": 1.5809699296951294,
      "learning_rate": 0.0002975554106910039,
      "loss": 0.8691,
      "step": 1000
    },
    {
      "epoch": 0.12222946544980444,
      "grad_norm": 3.2468457221984863,
      "learning_rate": 0.00029633311603650584,
      "loss": 0.7727,
      "step": 1500
    },
    {
      "epoch": 0.16297262059973924,
      "grad_norm": 2.7406773567199707,
      "learning_rate": 0.0002951108213820078,
      "loss": 0.7164,
      "step": 2000
    },
    {
      "epoch": 0.20371577574967406,
      "grad_norm": 2.737673759460449,
      "learning_rate": 0.00029388852672750977,
      "loss": 0.6845,
      "step": 2500
    },
    {
      "epoch": 0.24445893089960888,
      "grad_norm": 2.072187900543213,
      "learning_rate": 0.0002926662320730117,
      "loss": 0.6582,
      "step": 3000
    },
    {
      "epoch": 0.28520208604954367,
      "grad_norm": 2.475517749786377,
      "learning_rate": 0.00029144393741851364,
      "loss": 0.6504,
      "step": 3500
    },
    {
      "epoch": 0.3259452411994785,
      "grad_norm": 2.9354279041290283,
      "learning_rate": 0.0002902216427640156,
      "loss": 0.6288,
      "step": 4000
    },
    {
      "epoch": 0.3666883963494133,
      "grad_norm": 3.1031923294067383,
      "learning_rate": 0.0002889993481095176,
      "loss": 0.6368,
      "step": 4500
    },
    {
      "epoch": 0.4074315514993481,
      "grad_norm": 1.9472472667694092,
      "learning_rate": 0.00028777705345501956,
      "loss": 0.6164,
      "step": 5000
    },
    {
      "epoch": 0.44817470664928294,
      "grad_norm": 2.2042434215545654,
      "learning_rate": 0.0002865547588005215,
      "loss": 0.6072,
      "step": 5500
    },
    {
      "epoch": 0.48891786179921776,
      "grad_norm": 1.8782039880752563,
      "learning_rate": 0.00028533246414602344,
      "loss": 0.6,
      "step": 6000
    },
    {
      "epoch": 0.5296610169491526,
      "grad_norm": 1.4596766233444214,
      "learning_rate": 0.00028411016949152543,
      "loss": 0.6029,
      "step": 6500
    },
    {
      "epoch": 0.5704041720990873,
      "grad_norm": 2.1240434646606445,
      "learning_rate": 0.00028288787483702737,
      "loss": 0.586,
      "step": 7000
    },
    {
      "epoch": 0.6111473272490222,
      "grad_norm": 2.826650857925415,
      "learning_rate": 0.0002816655801825293,
      "loss": 0.5824,
      "step": 7500
    },
    {
      "epoch": 0.651890482398957,
      "grad_norm": 1.699205994606018,
      "learning_rate": 0.00028044328552803124,
      "loss": 0.5854,
      "step": 8000
    },
    {
      "epoch": 0.6926336375488917,
      "grad_norm": 1.7933754920959473,
      "learning_rate": 0.00027922099087353323,
      "loss": 0.5845,
      "step": 8500
    },
    {
      "epoch": 0.7333767926988266,
      "grad_norm": 1.97022545337677,
      "learning_rate": 0.00027799869621903517,
      "loss": 0.5756,
      "step": 9000
    },
    {
      "epoch": 0.7741199478487614,
      "grad_norm": 2.521186351776123,
      "learning_rate": 0.0002767764015645371,
      "loss": 0.572,
      "step": 9500
    },
    {
      "epoch": 0.8148631029986962,
      "grad_norm": 2.8268449306488037,
      "learning_rate": 0.0002755541069100391,
      "loss": 0.5568,
      "step": 10000
    },
    {
      "epoch": 0.855606258148631,
      "grad_norm": 2.6119906902313232,
      "learning_rate": 0.00027433181225554104,
      "loss": 0.5648,
      "step": 10500
    },
    {
      "epoch": 0.8963494132985659,
      "grad_norm": 1.7407381534576416,
      "learning_rate": 0.000273109517601043,
      "loss": 0.5665,
      "step": 11000
    },
    {
      "epoch": 0.9370925684485006,
      "grad_norm": 2.3571789264678955,
      "learning_rate": 0.00027188722294654497,
      "loss": 0.5603,
      "step": 11500
    },
    {
      "epoch": 0.9778357235984355,
      "grad_norm": 1.8720216751098633,
      "learning_rate": 0.0002706649282920469,
      "loss": 0.5524,
      "step": 12000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7979919910430908,
      "eval_loss": 0.510469913482666,
      "eval_runtime": 1.8901,
      "eval_samples_per_second": 1317.363,
      "eval_steps_per_second": 165.067,
      "step": 12272
    },
    {
      "epoch": 1.0185788787483703,
      "grad_norm": 1.6880804300308228,
      "learning_rate": 0.00026944263363754884,
      "loss": 0.5529,
      "step": 12500
    },
    {
      "epoch": 1.0593220338983051,
      "grad_norm": 2.5561161041259766,
      "learning_rate": 0.00026822033898305083,
      "loss": 0.5401,
      "step": 13000
    },
    {
      "epoch": 1.1000651890482398,
      "grad_norm": 2.007246732711792,
      "learning_rate": 0.00026699804432855277,
      "loss": 0.5433,
      "step": 13500
    },
    {
      "epoch": 1.1408083441981747,
      "grad_norm": 1.4851559400558472,
      "learning_rate": 0.00026577574967405476,
      "loss": 0.5424,
      "step": 14000
    },
    {
      "epoch": 1.1815514993481095,
      "grad_norm": 1.755630373954773,
      "learning_rate": 0.0002645534550195567,
      "loss": 0.5454,
      "step": 14500
    },
    {
      "epoch": 1.2222946544980444,
      "grad_norm": 2.556314468383789,
      "learning_rate": 0.00026333116036505864,
      "loss": 0.5344,
      "step": 15000
    },
    {
      "epoch": 1.263037809647979,
      "grad_norm": 2.2163028717041016,
      "learning_rate": 0.00026210886571056063,
      "loss": 0.5396,
      "step": 15500
    },
    {
      "epoch": 1.303780964797914,
      "grad_norm": 3.3935835361480713,
      "learning_rate": 0.00026088657105606257,
      "loss": 0.5308,
      "step": 16000
    },
    {
      "epoch": 1.3445241199478488,
      "grad_norm": 1.7446889877319336,
      "learning_rate": 0.0002596642764015645,
      "loss": 0.536,
      "step": 16500
    },
    {
      "epoch": 1.3852672750977835,
      "grad_norm": 3.142510414123535,
      "learning_rate": 0.0002584419817470665,
      "loss": 0.5405,
      "step": 17000
    },
    {
      "epoch": 1.4260104302477183,
      "grad_norm": 1.8411943912506104,
      "learning_rate": 0.00025721968709256843,
      "loss": 0.5298,
      "step": 17500
    },
    {
      "epoch": 1.4667535853976532,
      "grad_norm": 1.9463316202163696,
      "learning_rate": 0.00025599739243807037,
      "loss": 0.5249,
      "step": 18000
    },
    {
      "epoch": 1.5074967405475879,
      "grad_norm": 2.070413112640381,
      "learning_rate": 0.0002547750977835723,
      "loss": 0.526,
      "step": 18500
    },
    {
      "epoch": 1.548239895697523,
      "grad_norm": 2.2457096576690674,
      "learning_rate": 0.0002535528031290743,
      "loss": 0.5175,
      "step": 19000
    },
    {
      "epoch": 1.5889830508474576,
      "grad_norm": 2.3023736476898193,
      "learning_rate": 0.00025233050847457624,
      "loss": 0.5269,
      "step": 19500
    },
    {
      "epoch": 1.6297262059973925,
      "grad_norm": 1.1311193704605103,
      "learning_rate": 0.0002511082138200782,
      "loss": 0.5261,
      "step": 20000
    },
    {
      "epoch": 1.6704693611473274,
      "grad_norm": 2.1254351139068604,
      "learning_rate": 0.00024988591916558017,
      "loss": 0.5236,
      "step": 20500
    },
    {
      "epoch": 1.711212516297262,
      "grad_norm": 2.908379316329956,
      "learning_rate": 0.0002486636245110821,
      "loss": 0.5208,
      "step": 21000
    },
    {
      "epoch": 1.7519556714471969,
      "grad_norm": 2.5445449352264404,
      "learning_rate": 0.00024744132985658404,
      "loss": 0.5125,
      "step": 21500
    },
    {
      "epoch": 1.7926988265971318,
      "grad_norm": 1.4653292894363403,
      "learning_rate": 0.00024621903520208603,
      "loss": 0.5147,
      "step": 22000
    },
    {
      "epoch": 1.8334419817470664,
      "grad_norm": 3.521878719329834,
      "learning_rate": 0.000244996740547588,
      "loss": 0.5264,
      "step": 22500
    },
    {
      "epoch": 1.8741851368970013,
      "grad_norm": 2.296907901763916,
      "learning_rate": 0.00024377444589308996,
      "loss": 0.5097,
      "step": 23000
    },
    {
      "epoch": 1.9149282920469362,
      "grad_norm": 1.7283244132995605,
      "learning_rate": 0.0002425521512385919,
      "loss": 0.5191,
      "step": 23500
    },
    {
      "epoch": 1.9556714471968708,
      "grad_norm": 2.8024685382843018,
      "learning_rate": 0.00024132985658409386,
      "loss": 0.5158,
      "step": 24000
    },
    {
      "epoch": 1.996414602346806,
      "grad_norm": 1.581881046295166,
      "learning_rate": 0.00024010756192959583,
      "loss": 0.5069,
      "step": 24500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8152610659599304,
      "eval_loss": 0.479065477848053,
      "eval_runtime": 1.8655,
      "eval_samples_per_second": 1334.774,
      "eval_steps_per_second": 167.249,
      "step": 24544
    },
    {
      "epoch": 2.0371577574967406,
      "grad_norm": 2.120530128479004,
      "learning_rate": 0.00023888526727509777,
      "loss": 0.5044,
      "step": 25000
    },
    {
      "epoch": 2.077900912646675,
      "grad_norm": 1.6350152492523193,
      "learning_rate": 0.00023766297262059973,
      "loss": 0.5013,
      "step": 25500
    },
    {
      "epoch": 2.1186440677966103,
      "grad_norm": 1.545474886894226,
      "learning_rate": 0.00023644067796610167,
      "loss": 0.5069,
      "step": 26000
    },
    {
      "epoch": 2.159387222946545,
      "grad_norm": 1.6649187803268433,
      "learning_rate": 0.00023521838331160363,
      "loss": 0.5006,
      "step": 26500
    },
    {
      "epoch": 2.2001303780964796,
      "grad_norm": 1.4398220777511597,
      "learning_rate": 0.0002339960886571056,
      "loss": 0.5042,
      "step": 27000
    },
    {
      "epoch": 2.2408735332464147,
      "grad_norm": 2.4021449089050293,
      "learning_rate": 0.00023277379400260753,
      "loss": 0.497,
      "step": 27500
    },
    {
      "epoch": 2.2816166883963493,
      "grad_norm": 1.679760217666626,
      "learning_rate": 0.0002315514993481095,
      "loss": 0.5037,
      "step": 28000
    },
    {
      "epoch": 2.322359843546284,
      "grad_norm": 1.7519738674163818,
      "learning_rate": 0.00023032920469361144,
      "loss": 0.4828,
      "step": 28500
    },
    {
      "epoch": 2.363102998696219,
      "grad_norm": 2.2004222869873047,
      "learning_rate": 0.0002291069100391134,
      "loss": 0.4969,
      "step": 29000
    },
    {
      "epoch": 2.4038461538461537,
      "grad_norm": 4.179736614227295,
      "learning_rate": 0.00022788461538461537,
      "loss": 0.4974,
      "step": 29500
    },
    {
      "epoch": 2.444589308996089,
      "grad_norm": 2.7707066535949707,
      "learning_rate": 0.0002266623207301173,
      "loss": 0.5013,
      "step": 30000
    },
    {
      "epoch": 2.4853324641460235,
      "grad_norm": 2.4455089569091797,
      "learning_rate": 0.00022544002607561927,
      "loss": 0.5016,
      "step": 30500
    },
    {
      "epoch": 2.526075619295958,
      "grad_norm": 2.344694137573242,
      "learning_rate": 0.0002242177314211212,
      "loss": 0.5054,
      "step": 31000
    },
    {
      "epoch": 2.5668187744458932,
      "grad_norm": 3.2276628017425537,
      "learning_rate": 0.0002229954367666232,
      "loss": 0.5024,
      "step": 31500
    },
    {
      "epoch": 2.607561929595828,
      "grad_norm": 1.8482904434204102,
      "learning_rate": 0.00022177314211212516,
      "loss": 0.4885,
      "step": 32000
    },
    {
      "epoch": 2.648305084745763,
      "grad_norm": 1.7066946029663086,
      "learning_rate": 0.0002205508474576271,
      "loss": 0.4961,
      "step": 32500
    },
    {
      "epoch": 2.6890482398956976,
      "grad_norm": 2.765458822250366,
      "learning_rate": 0.00021932855280312906,
      "loss": 0.4957,
      "step": 33000
    },
    {
      "epoch": 2.7297913950456323,
      "grad_norm": 1.5319150686264038,
      "learning_rate": 0.00021810625814863103,
      "loss": 0.4942,
      "step": 33500
    },
    {
      "epoch": 2.770534550195567,
      "grad_norm": 1.3999781608581543,
      "learning_rate": 0.00021688396349413296,
      "loss": 0.5003,
      "step": 34000
    },
    {
      "epoch": 2.811277705345502,
      "grad_norm": 2.038933277130127,
      "learning_rate": 0.00021566166883963493,
      "loss": 0.4986,
      "step": 34500
    },
    {
      "epoch": 2.8520208604954367,
      "grad_norm": 1.5663559436798096,
      "learning_rate": 0.0002144393741851369,
      "loss": 0.4817,
      "step": 35000
    },
    {
      "epoch": 2.8927640156453718,
      "grad_norm": 2.1904823780059814,
      "learning_rate": 0.00021321707953063883,
      "loss": 0.4843,
      "step": 35500
    },
    {
      "epoch": 2.9335071707953064,
      "grad_norm": 2.08329701423645,
      "learning_rate": 0.0002119947848761408,
      "loss": 0.4952,
      "step": 36000
    },
    {
      "epoch": 2.974250325945241,
      "grad_norm": 2.4121880531311035,
      "learning_rate": 0.00021077249022164273,
      "loss": 0.484,
      "step": 36500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.800000011920929,
      "eval_loss": 0.507464587688446,
      "eval_runtime": 1.8775,
      "eval_samples_per_second": 1326.218,
      "eval_steps_per_second": 166.177,
      "step": 36816
    },
    {
      "epoch": 3.014993481095176,
      "grad_norm": 1.707140564918518,
      "learning_rate": 0.0002095501955671447,
      "loss": 0.4885,
      "step": 37000
    },
    {
      "epoch": 3.055736636245111,
      "grad_norm": 1.6870657205581665,
      "learning_rate": 0.00020832790091264666,
      "loss": 0.4798,
      "step": 37500
    },
    {
      "epoch": 3.0964797913950455,
      "grad_norm": 2.7480688095092773,
      "learning_rate": 0.0002071056062581486,
      "loss": 0.4749,
      "step": 38000
    },
    {
      "epoch": 3.1372229465449806,
      "grad_norm": 3.1180686950683594,
      "learning_rate": 0.00020588331160365056,
      "loss": 0.4782,
      "step": 38500
    },
    {
      "epoch": 3.1779661016949152,
      "grad_norm": 2.0525007247924805,
      "learning_rate": 0.0002046610169491525,
      "loss": 0.4761,
      "step": 39000
    },
    {
      "epoch": 3.21870925684485,
      "grad_norm": 2.5591986179351807,
      "learning_rate": 0.00020343872229465447,
      "loss": 0.4741,
      "step": 39500
    },
    {
      "epoch": 3.259452411994785,
      "grad_norm": 3.1262454986572266,
      "learning_rate": 0.00020221642764015643,
      "loss": 0.4868,
      "step": 40000
    },
    {
      "epoch": 3.3001955671447196,
      "grad_norm": 1.468479037284851,
      "learning_rate": 0.0002009941329856584,
      "loss": 0.476,
      "step": 40500
    },
    {
      "epoch": 3.3409387222946547,
      "grad_norm": 1.5937858819961548,
      "learning_rate": 0.00019977183833116036,
      "loss": 0.4741,
      "step": 41000
    },
    {
      "epoch": 3.3816818774445894,
      "grad_norm": 1.9121133089065552,
      "learning_rate": 0.00019854954367666232,
      "loss": 0.4833,
      "step": 41500
    },
    {
      "epoch": 3.422425032594524,
      "grad_norm": 1.7851836681365967,
      "learning_rate": 0.00019732724902216426,
      "loss": 0.4659,
      "step": 42000
    },
    {
      "epoch": 3.463168187744459,
      "grad_norm": 1.5859330892562866,
      "learning_rate": 0.00019610495436766623,
      "loss": 0.4796,
      "step": 42500
    },
    {
      "epoch": 3.5039113428943938,
      "grad_norm": 2.265151023864746,
      "learning_rate": 0.00019488265971316816,
      "loss": 0.4838,
      "step": 43000
    },
    {
      "epoch": 3.5446544980443284,
      "grad_norm": 2.09751558303833,
      "learning_rate": 0.00019366036505867013,
      "loss": 0.4783,
      "step": 43500
    },
    {
      "epoch": 3.5853976531942635,
      "grad_norm": 2.5252413749694824,
      "learning_rate": 0.0001924380704041721,
      "loss": 0.4699,
      "step": 44000
    },
    {
      "epoch": 3.626140808344198,
      "grad_norm": 4.366662979125977,
      "learning_rate": 0.00019121577574967403,
      "loss": 0.4708,
      "step": 44500
    },
    {
      "epoch": 3.666883963494133,
      "grad_norm": 3.9609336853027344,
      "learning_rate": 0.000189993481095176,
      "loss": 0.4822,
      "step": 45000
    },
    {
      "epoch": 3.707627118644068,
      "grad_norm": 3.021212577819824,
      "learning_rate": 0.00018877118644067796,
      "loss": 0.4775,
      "step": 45500
    },
    {
      "epoch": 3.7483702737940026,
      "grad_norm": 2.1417489051818848,
      "learning_rate": 0.0001875488917861799,
      "loss": 0.4703,
      "step": 46000
    },
    {
      "epoch": 3.7891134289439377,
      "grad_norm": 2.012929677963257,
      "learning_rate": 0.00018632659713168186,
      "loss": 0.4612,
      "step": 46500
    },
    {
      "epoch": 3.8298565840938723,
      "grad_norm": 2.7424936294555664,
      "learning_rate": 0.0001851043024771838,
      "loss": 0.4793,
      "step": 47000
    },
    {
      "epoch": 3.870599739243807,
      "grad_norm": 1.7710371017456055,
      "learning_rate": 0.00018388200782268576,
      "loss": 0.4758,
      "step": 47500
    },
    {
      "epoch": 3.9113428943937416,
      "grad_norm": 2.0552587509155273,
      "learning_rate": 0.00018265971316818773,
      "loss": 0.4874,
      "step": 48000
    },
    {
      "epoch": 3.9520860495436767,
      "grad_norm": 1.4387139081954956,
      "learning_rate": 0.00018143741851368966,
      "loss": 0.4599,
      "step": 48500
    },
    {
      "epoch": 3.9928292046936114,
      "grad_norm": 1.992775559425354,
      "learning_rate": 0.00018021512385919163,
      "loss": 0.4782,
      "step": 49000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8248996138572693,
      "eval_loss": 0.4452807903289795,
      "eval_runtime": 1.8761,
      "eval_samples_per_second": 1327.188,
      "eval_steps_per_second": 166.298,
      "step": 49088
    },
    {
      "epoch": 4.0335723598435465,
      "grad_norm": 2.6025853157043457,
      "learning_rate": 0.00017899282920469362,
      "loss": 0.4656,
      "step": 49500
    },
    {
      "epoch": 4.074315514993481,
      "grad_norm": 3.0864315032958984,
      "learning_rate": 0.00017777053455019556,
      "loss": 0.4553,
      "step": 50000
    },
    {
      "epoch": 4.115058670143416,
      "grad_norm": 2.274549961090088,
      "learning_rate": 0.00017654823989569752,
      "loss": 0.4566,
      "step": 50500
    },
    {
      "epoch": 4.15580182529335,
      "grad_norm": 2.5139005184173584,
      "learning_rate": 0.00017532594524119946,
      "loss": 0.4562,
      "step": 51000
    },
    {
      "epoch": 4.196544980443286,
      "grad_norm": 2.4532859325408936,
      "learning_rate": 0.00017410365058670142,
      "loss": 0.4547,
      "step": 51500
    },
    {
      "epoch": 4.237288135593221,
      "grad_norm": 2.213334321975708,
      "learning_rate": 0.0001728813559322034,
      "loss": 0.4623,
      "step": 52000
    },
    {
      "epoch": 4.278031290743155,
      "grad_norm": 2.893470525741577,
      "learning_rate": 0.00017165906127770533,
      "loss": 0.461,
      "step": 52500
    },
    {
      "epoch": 4.31877444589309,
      "grad_norm": 2.628871440887451,
      "learning_rate": 0.0001704367666232073,
      "loss": 0.4674,
      "step": 53000
    },
    {
      "epoch": 4.3595176010430245,
      "grad_norm": 2.02699613571167,
      "learning_rate": 0.00016921447196870926,
      "loss": 0.4622,
      "step": 53500
    },
    {
      "epoch": 4.400260756192959,
      "grad_norm": 1.5286389589309692,
      "learning_rate": 0.0001679921773142112,
      "loss": 0.4655,
      "step": 54000
    },
    {
      "epoch": 4.441003911342895,
      "grad_norm": 1.5373179912567139,
      "learning_rate": 0.00016676988265971316,
      "loss": 0.4618,
      "step": 54500
    },
    {
      "epoch": 4.481747066492829,
      "grad_norm": 1.6187845468521118,
      "learning_rate": 0.0001655475880052151,
      "loss": 0.4582,
      "step": 55000
    },
    {
      "epoch": 4.522490221642764,
      "grad_norm": 2.48063588142395,
      "learning_rate": 0.00016432529335071706,
      "loss": 0.4548,
      "step": 55500
    },
    {
      "epoch": 4.563233376792699,
      "grad_norm": 1.8845105171203613,
      "learning_rate": 0.00016310299869621902,
      "loss": 0.4588,
      "step": 56000
    },
    {
      "epoch": 4.603976531942633,
      "grad_norm": 1.609021782875061,
      "learning_rate": 0.00016188070404172096,
      "loss": 0.4607,
      "step": 56500
    },
    {
      "epoch": 4.644719687092568,
      "grad_norm": 2.585796356201172,
      "learning_rate": 0.00016065840938722293,
      "loss": 0.4696,
      "step": 57000
    },
    {
      "epoch": 4.6854628422425035,
      "grad_norm": 1.7783458232879639,
      "learning_rate": 0.00015943611473272486,
      "loss": 0.4629,
      "step": 57500
    },
    {
      "epoch": 4.726205997392438,
      "grad_norm": 2.618834972381592,
      "learning_rate": 0.00015821382007822685,
      "loss": 0.4581,
      "step": 58000
    },
    {
      "epoch": 4.766949152542373,
      "grad_norm": 3.300272226333618,
      "learning_rate": 0.00015699152542372882,
      "loss": 0.464,
      "step": 58500
    },
    {
      "epoch": 4.8076923076923075,
      "grad_norm": 1.469986915588379,
      "learning_rate": 0.00015576923076923076,
      "loss": 0.475,
      "step": 59000
    },
    {
      "epoch": 4.848435462842242,
      "grad_norm": 1.9230191707611084,
      "learning_rate": 0.00015454693611473272,
      "loss": 0.4546,
      "step": 59500
    },
    {
      "epoch": 4.889178617992178,
      "grad_norm": 2.021245241165161,
      "learning_rate": 0.00015332464146023469,
      "loss": 0.4593,
      "step": 60000
    },
    {
      "epoch": 4.929921773142112,
      "grad_norm": 3.770566940307617,
      "learning_rate": 0.00015210234680573662,
      "loss": 0.4638,
      "step": 60500
    },
    {
      "epoch": 4.970664928292047,
      "grad_norm": 2.287729501724243,
      "learning_rate": 0.0001508800521512386,
      "loss": 0.4577,
      "step": 61000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8305220603942871,
      "eval_loss": 0.4432857930660248,
      "eval_runtime": 1.8884,
      "eval_samples_per_second": 1318.548,
      "eval_steps_per_second": 165.216,
      "step": 61360
    },
    {
      "epoch": 5.011408083441982,
      "grad_norm": 3.241933584213257,
      "learning_rate": 0.00014965775749674052,
      "loss": 0.4639,
      "step": 61500
    },
    {
      "epoch": 5.052151238591916,
      "grad_norm": 2.545016288757324,
      "learning_rate": 0.0001484354628422425,
      "loss": 0.4527,
      "step": 62000
    },
    {
      "epoch": 5.092894393741851,
      "grad_norm": 2.6042070388793945,
      "learning_rate": 0.00014721316818774445,
      "loss": 0.4397,
      "step": 62500
    },
    {
      "epoch": 5.1336375488917865,
      "grad_norm": 1.4144200086593628,
      "learning_rate": 0.0001459908735332464,
      "loss": 0.4486,
      "step": 63000
    },
    {
      "epoch": 5.174380704041721,
      "grad_norm": 3.1483497619628906,
      "learning_rate": 0.00014476857887874836,
      "loss": 0.4498,
      "step": 63500
    },
    {
      "epoch": 5.215123859191656,
      "grad_norm": 1.670169711112976,
      "learning_rate": 0.00014354628422425032,
      "loss": 0.4375,
      "step": 64000
    },
    {
      "epoch": 5.25586701434159,
      "grad_norm": 2.3249220848083496,
      "learning_rate": 0.00014232398956975226,
      "loss": 0.4524,
      "step": 64500
    },
    {
      "epoch": 5.296610169491525,
      "grad_norm": 1.7436152696609497,
      "learning_rate": 0.00014110169491525422,
      "loss": 0.4483,
      "step": 65000
    },
    {
      "epoch": 5.337353324641461,
      "grad_norm": 1.9936621189117432,
      "learning_rate": 0.0001398794002607562,
      "loss": 0.4516,
      "step": 65500
    },
    {
      "epoch": 5.378096479791395,
      "grad_norm": 1.7099202871322632,
      "learning_rate": 0.00013865710560625815,
      "loss": 0.45,
      "step": 66000
    },
    {
      "epoch": 5.41883963494133,
      "grad_norm": 2.8098649978637695,
      "learning_rate": 0.0001374348109517601,
      "loss": 0.443,
      "step": 66500
    },
    {
      "epoch": 5.459582790091265,
      "grad_norm": 2.907409191131592,
      "learning_rate": 0.00013621251629726205,
      "loss": 0.4582,
      "step": 67000
    },
    {
      "epoch": 5.500325945241199,
      "grad_norm": 1.900261640548706,
      "learning_rate": 0.000134990221642764,
      "loss": 0.4551,
      "step": 67500
    },
    {
      "epoch": 5.541069100391134,
      "grad_norm": 1.8006491661071777,
      "learning_rate": 0.00013376792698826596,
      "loss": 0.4526,
      "step": 68000
    },
    {
      "epoch": 5.581812255541069,
      "grad_norm": 2.5919241905212402,
      "learning_rate": 0.00013254563233376792,
      "loss": 0.4481,
      "step": 68500
    },
    {
      "epoch": 5.622555410691004,
      "grad_norm": 3.156646966934204,
      "learning_rate": 0.00013132333767926986,
      "loss": 0.4468,
      "step": 69000
    },
    {
      "epoch": 5.663298565840939,
      "grad_norm": 1.866025686264038,
      "learning_rate": 0.00013010104302477182,
      "loss": 0.4417,
      "step": 69500
    },
    {
      "epoch": 5.704041720990873,
      "grad_norm": 2.51347017288208,
      "learning_rate": 0.00012887874837027379,
      "loss": 0.4465,
      "step": 70000
    },
    {
      "epoch": 5.744784876140808,
      "grad_norm": 1.674730896949768,
      "learning_rate": 0.00012765645371577575,
      "loss": 0.4529,
      "step": 70500
    },
    {
      "epoch": 5.7855280312907436,
      "grad_norm": 1.6664891242980957,
      "learning_rate": 0.0001264341590612777,
      "loss": 0.4504,
      "step": 71000
    },
    {
      "epoch": 5.826271186440678,
      "grad_norm": 1.9357300996780396,
      "learning_rate": 0.00012521186440677965,
      "loss": 0.4533,
      "step": 71500
    },
    {
      "epoch": 5.867014341590613,
      "grad_norm": 3.9650068283081055,
      "learning_rate": 0.0001239895697522816,
      "loss": 0.4427,
      "step": 72000
    },
    {
      "epoch": 5.9077574967405475,
      "grad_norm": 3.934169292449951,
      "learning_rate": 0.00012276727509778355,
      "loss": 0.4466,
      "step": 72500
    },
    {
      "epoch": 5.948500651890482,
      "grad_norm": 3.175135612487793,
      "learning_rate": 0.0001215449804432855,
      "loss": 0.4457,
      "step": 73000
    },
    {
      "epoch": 5.989243807040417,
      "grad_norm": 2.4715468883514404,
      "learning_rate": 0.00012032268578878747,
      "loss": 0.448,
      "step": 73500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8277108669281006,
      "eval_loss": 0.43607163429260254,
      "eval_runtime": 1.8958,
      "eval_samples_per_second": 1313.425,
      "eval_steps_per_second": 164.574,
      "step": 73632
    },
    {
      "epoch": 6.029986962190352,
      "grad_norm": 1.9677677154541016,
      "learning_rate": 0.00011910039113428943,
      "loss": 0.4381,
      "step": 74000
    },
    {
      "epoch": 6.070730117340287,
      "grad_norm": 1.6302155256271362,
      "learning_rate": 0.00011787809647979139,
      "loss": 0.4413,
      "step": 74500
    },
    {
      "epoch": 6.111473272490222,
      "grad_norm": 1.828708529472351,
      "learning_rate": 0.00011665580182529335,
      "loss": 0.434,
      "step": 75000
    },
    {
      "epoch": 6.152216427640156,
      "grad_norm": 2.035036563873291,
      "learning_rate": 0.0001154335071707953,
      "loss": 0.4393,
      "step": 75500
    },
    {
      "epoch": 6.192959582790091,
      "grad_norm": 3.3159615993499756,
      "learning_rate": 0.00011421121251629725,
      "loss": 0.4366,
      "step": 76000
    },
    {
      "epoch": 6.2337027379400265,
      "grad_norm": 1.8185631036758423,
      "learning_rate": 0.0001129889178617992,
      "loss": 0.4448,
      "step": 76500
    },
    {
      "epoch": 6.274445893089961,
      "grad_norm": 2.4315009117126465,
      "learning_rate": 0.00011176662320730115,
      "loss": 0.4429,
      "step": 77000
    },
    {
      "epoch": 6.315189048239896,
      "grad_norm": 2.994472026824951,
      "learning_rate": 0.00011054432855280312,
      "loss": 0.4297,
      "step": 77500
    },
    {
      "epoch": 6.3559322033898304,
      "grad_norm": 4.0591535568237305,
      "learning_rate": 0.00010932203389830507,
      "loss": 0.44,
      "step": 78000
    },
    {
      "epoch": 6.396675358539765,
      "grad_norm": 2.4489145278930664,
      "learning_rate": 0.00010809973924380703,
      "loss": 0.4486,
      "step": 78500
    },
    {
      "epoch": 6.4374185136897,
      "grad_norm": 2.0163211822509766,
      "learning_rate": 0.00010687744458930898,
      "loss": 0.4335,
      "step": 79000
    },
    {
      "epoch": 6.478161668839635,
      "grad_norm": 2.3287277221679688,
      "learning_rate": 0.00010565514993481095,
      "loss": 0.4404,
      "step": 79500
    },
    {
      "epoch": 6.51890482398957,
      "grad_norm": 2.65160870552063,
      "learning_rate": 0.0001044328552803129,
      "loss": 0.4332,
      "step": 80000
    },
    {
      "epoch": 6.559647979139505,
      "grad_norm": 1.8823881149291992,
      "learning_rate": 0.00010321056062581485,
      "loss": 0.4411,
      "step": 80500
    },
    {
      "epoch": 6.600391134289439,
      "grad_norm": 3.4502170085906982,
      "learning_rate": 0.0001019882659713168,
      "loss": 0.4369,
      "step": 81000
    },
    {
      "epoch": 6.641134289439374,
      "grad_norm": 2.612377643585205,
      "learning_rate": 0.00010076597131681877,
      "loss": 0.4426,
      "step": 81500
    },
    {
      "epoch": 6.681877444589309,
      "grad_norm": 2.040041208267212,
      "learning_rate": 9.954367666232072e-05,
      "loss": 0.4366,
      "step": 82000
    },
    {
      "epoch": 6.722620599739244,
      "grad_norm": 2.8943679332733154,
      "learning_rate": 9.832138200782268e-05,
      "loss": 0.4359,
      "step": 82500
    },
    {
      "epoch": 6.763363754889179,
      "grad_norm": 2.6226155757904053,
      "learning_rate": 9.709908735332463e-05,
      "loss": 0.4312,
      "step": 83000
    },
    {
      "epoch": 6.804106910039113,
      "grad_norm": 1.850989818572998,
      "learning_rate": 9.58767926988266e-05,
      "loss": 0.4413,
      "step": 83500
    },
    {
      "epoch": 6.844850065189048,
      "grad_norm": 2.610006809234619,
      "learning_rate": 9.465449804432855e-05,
      "loss": 0.4279,
      "step": 84000
    },
    {
      "epoch": 6.885593220338983,
      "grad_norm": 1.603615164756775,
      "learning_rate": 9.34322033898305e-05,
      "loss": 0.4294,
      "step": 84500
    },
    {
      "epoch": 6.926336375488918,
      "grad_norm": 2.0891976356506348,
      "learning_rate": 9.220990873533245e-05,
      "loss": 0.431,
      "step": 85000
    },
    {
      "epoch": 6.967079530638853,
      "grad_norm": 2.503952980041504,
      "learning_rate": 9.098761408083442e-05,
      "loss": 0.4223,
      "step": 85500
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8261044025421143,
      "eval_loss": 0.437867134809494,
      "eval_runtime": 1.8713,
      "eval_samples_per_second": 1330.637,
      "eval_steps_per_second": 166.73,
      "step": 85904
    },
    {
      "epoch": 7.0078226857887875,
      "grad_norm": 2.344571590423584,
      "learning_rate": 8.976531942633637e-05,
      "loss": 0.4353,
      "step": 86000
    },
    {
      "epoch": 7.048565840938722,
      "grad_norm": 2.651838779449463,
      "learning_rate": 8.854302477183832e-05,
      "loss": 0.4198,
      "step": 86500
    },
    {
      "epoch": 7.089308996088657,
      "grad_norm": 2.481079339981079,
      "learning_rate": 8.732073011734028e-05,
      "loss": 0.4244,
      "step": 87000
    },
    {
      "epoch": 7.130052151238592,
      "grad_norm": 2.060640573501587,
      "learning_rate": 8.609843546284225e-05,
      "loss": 0.423,
      "step": 87500
    },
    {
      "epoch": 7.170795306388527,
      "grad_norm": 2.1923210620880127,
      "learning_rate": 8.48761408083442e-05,
      "loss": 0.4279,
      "step": 88000
    },
    {
      "epoch": 7.211538461538462,
      "grad_norm": 2.073127031326294,
      "learning_rate": 8.365384615384615e-05,
      "loss": 0.4318,
      "step": 88500
    },
    {
      "epoch": 7.252281616688396,
      "grad_norm": 2.4381213188171387,
      "learning_rate": 8.24315514993481e-05,
      "loss": 0.4245,
      "step": 89000
    },
    {
      "epoch": 7.293024771838331,
      "grad_norm": 3.0839269161224365,
      "learning_rate": 8.120925684485006e-05,
      "loss": 0.4339,
      "step": 89500
    },
    {
      "epoch": 7.333767926988266,
      "grad_norm": 1.9257709980010986,
      "learning_rate": 7.998696219035201e-05,
      "loss": 0.4295,
      "step": 90000
    },
    {
      "epoch": 7.374511082138201,
      "grad_norm": 2.7651491165161133,
      "learning_rate": 7.876466753585397e-05,
      "loss": 0.4312,
      "step": 90500
    },
    {
      "epoch": 7.415254237288136,
      "grad_norm": 2.7670464515686035,
      "learning_rate": 7.754237288135592e-05,
      "loss": 0.4202,
      "step": 91000
    },
    {
      "epoch": 7.4559973924380705,
      "grad_norm": 3.2333455085754395,
      "learning_rate": 7.63200782268579e-05,
      "loss": 0.4283,
      "step": 91500
    },
    {
      "epoch": 7.496740547588005,
      "grad_norm": 1.5139400959014893,
      "learning_rate": 7.509778357235985e-05,
      "loss": 0.4286,
      "step": 92000
    },
    {
      "epoch": 7.53748370273794,
      "grad_norm": 2.027017831802368,
      "learning_rate": 7.387548891786178e-05,
      "loss": 0.4273,
      "step": 92500
    },
    {
      "epoch": 7.578226857887875,
      "grad_norm": 2.0233519077301025,
      "learning_rate": 7.265319426336375e-05,
      "loss": 0.43,
      "step": 93000
    },
    {
      "epoch": 7.61897001303781,
      "grad_norm": 1.8519268035888672,
      "learning_rate": 7.14308996088657e-05,
      "loss": 0.4335,
      "step": 93500
    },
    {
      "epoch": 7.659713168187745,
      "grad_norm": 3.348663806915283,
      "learning_rate": 7.020860495436766e-05,
      "loss": 0.4218,
      "step": 94000
    },
    {
      "epoch": 7.700456323337679,
      "grad_norm": 2.584179162979126,
      "learning_rate": 6.898631029986961e-05,
      "loss": 0.4353,
      "step": 94500
    },
    {
      "epoch": 7.741199478487614,
      "grad_norm": 1.8661848306655884,
      "learning_rate": 6.776401564537158e-05,
      "loss": 0.4391,
      "step": 95000
    },
    {
      "epoch": 7.781942633637549,
      "grad_norm": 2.880671977996826,
      "learning_rate": 6.654172099087353e-05,
      "loss": 0.4271,
      "step": 95500
    },
    {
      "epoch": 7.822685788787483,
      "grad_norm": 3.3717212677001953,
      "learning_rate": 6.531942633637548e-05,
      "loss": 0.4229,
      "step": 96000
    },
    {
      "epoch": 7.863428943937419,
      "grad_norm": 2.9987239837646484,
      "learning_rate": 6.409713168187743e-05,
      "loss": 0.4292,
      "step": 96500
    },
    {
      "epoch": 7.904172099087353,
      "grad_norm": 3.033198118209839,
      "learning_rate": 6.28748370273794e-05,
      "loss": 0.4218,
      "step": 97000
    },
    {
      "epoch": 7.944915254237288,
      "grad_norm": 2.786151647567749,
      "learning_rate": 6.165254237288135e-05,
      "loss": 0.4287,
      "step": 97500
    },
    {
      "epoch": 7.985658409387223,
      "grad_norm": 1.6547356843948364,
      "learning_rate": 6.0430247718383304e-05,
      "loss": 0.428,
      "step": 98000
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8361445665359497,
      "eval_loss": 0.4338319003582001,
      "eval_runtime": 1.8867,
      "eval_samples_per_second": 1319.775,
      "eval_steps_per_second": 165.369,
      "step": 98176
    },
    {
      "epoch": 8.026401564537158,
      "grad_norm": 2.6882944107055664,
      "learning_rate": 5.920795306388526e-05,
      "loss": 0.4242,
      "step": 98500
    },
    {
      "epoch": 8.067144719687093,
      "grad_norm": 2.8945088386535645,
      "learning_rate": 5.798565840938721e-05,
      "loss": 0.4133,
      "step": 99000
    },
    {
      "epoch": 8.107887874837028,
      "grad_norm": 3.313706636428833,
      "learning_rate": 5.676336375488918e-05,
      "loss": 0.4171,
      "step": 99500
    },
    {
      "epoch": 8.148631029986962,
      "grad_norm": 2.4790937900543213,
      "learning_rate": 5.554106910039113e-05,
      "loss": 0.431,
      "step": 100000
    },
    {
      "epoch": 8.189374185136897,
      "grad_norm": 4.389292240142822,
      "learning_rate": 5.4318774445893086e-05,
      "loss": 0.4179,
      "step": 100500
    },
    {
      "epoch": 8.230117340286832,
      "grad_norm": 2.9039342403411865,
      "learning_rate": 5.309647979139504e-05,
      "loss": 0.4209,
      "step": 101000
    },
    {
      "epoch": 8.270860495436766,
      "grad_norm": 2.5934033393859863,
      "learning_rate": 5.1874185136897e-05,
      "loss": 0.4272,
      "step": 101500
    },
    {
      "epoch": 8.3116036505867,
      "grad_norm": 1.9648871421813965,
      "learning_rate": 5.065189048239895e-05,
      "loss": 0.4125,
      "step": 102000
    },
    {
      "epoch": 8.352346805736635,
      "grad_norm": 1.7102642059326172,
      "learning_rate": 4.942959582790091e-05,
      "loss": 0.4173,
      "step": 102500
    },
    {
      "epoch": 8.393089960886572,
      "grad_norm": 1.927245855331421,
      "learning_rate": 4.820730117340286e-05,
      "loss": 0.4291,
      "step": 103000
    },
    {
      "epoch": 8.433833116036507,
      "grad_norm": 3.463087320327759,
      "learning_rate": 4.698500651890482e-05,
      "loss": 0.4217,
      "step": 103500
    },
    {
      "epoch": 8.474576271186441,
      "grad_norm": 2.2184531688690186,
      "learning_rate": 4.576271186440678e-05,
      "loss": 0.4198,
      "step": 104000
    },
    {
      "epoch": 8.515319426336376,
      "grad_norm": 2.0366404056549072,
      "learning_rate": 4.4540417209908735e-05,
      "loss": 0.4253,
      "step": 104500
    },
    {
      "epoch": 8.55606258148631,
      "grad_norm": 3.1242620944976807,
      "learning_rate": 4.3318122555410686e-05,
      "loss": 0.4227,
      "step": 105000
    },
    {
      "epoch": 8.596805736636245,
      "grad_norm": 2.4676053524017334,
      "learning_rate": 4.2095827900912643e-05,
      "loss": 0.4156,
      "step": 105500
    },
    {
      "epoch": 8.63754889178618,
      "grad_norm": 2.298691987991333,
      "learning_rate": 4.08735332464146e-05,
      "loss": 0.4177,
      "step": 106000
    },
    {
      "epoch": 8.678292046936114,
      "grad_norm": 2.6490094661712646,
      "learning_rate": 3.965123859191656e-05,
      "loss": 0.4311,
      "step": 106500
    },
    {
      "epoch": 8.719035202086049,
      "grad_norm": 2.1568782329559326,
      "learning_rate": 3.842894393741851e-05,
      "loss": 0.4256,
      "step": 107000
    },
    {
      "epoch": 8.759778357235984,
      "grad_norm": 2.9031362533569336,
      "learning_rate": 3.720664928292047e-05,
      "loss": 0.4139,
      "step": 107500
    },
    {
      "epoch": 8.800521512385918,
      "grad_norm": 1.819143533706665,
      "learning_rate": 3.5984354628422425e-05,
      "loss": 0.4232,
      "step": 108000
    },
    {
      "epoch": 8.841264667535853,
      "grad_norm": 1.8355783224105835,
      "learning_rate": 3.4762059973924376e-05,
      "loss": 0.4139,
      "step": 108500
    },
    {
      "epoch": 8.88200782268579,
      "grad_norm": 2.947263717651367,
      "learning_rate": 3.3539765319426334e-05,
      "loss": 0.4185,
      "step": 109000
    },
    {
      "epoch": 8.922750977835724,
      "grad_norm": 2.3757164478302,
      "learning_rate": 3.2317470664928285e-05,
      "loss": 0.4258,
      "step": 109500
    },
    {
      "epoch": 8.963494132985659,
      "grad_norm": 2.6306991577148438,
      "learning_rate": 3.109517601043025e-05,
      "loss": 0.4224,
      "step": 110000
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8353413939476013,
      "eval_loss": 0.43368807435035706,
      "eval_runtime": 1.8659,
      "eval_samples_per_second": 1334.501,
      "eval_steps_per_second": 167.215,
      "step": 110448
    },
    {
      "epoch": 9.004237288135593,
      "grad_norm": 1.9450658559799194,
      "learning_rate": 2.98728813559322e-05,
      "loss": 0.4133,
      "step": 110500
    },
    {
      "epoch": 9.044980443285528,
      "grad_norm": 2.0696680545806885,
      "learning_rate": 2.8650586701434158e-05,
      "loss": 0.4187,
      "step": 111000
    },
    {
      "epoch": 9.085723598435463,
      "grad_norm": 3.4499661922454834,
      "learning_rate": 2.7428292046936113e-05,
      "loss": 0.4057,
      "step": 111500
    },
    {
      "epoch": 9.126466753585397,
      "grad_norm": 2.0059680938720703,
      "learning_rate": 2.6205997392438067e-05,
      "loss": 0.4216,
      "step": 112000
    },
    {
      "epoch": 9.167209908735332,
      "grad_norm": 2.050560235977173,
      "learning_rate": 2.4983702737940025e-05,
      "loss": 0.4188,
      "step": 112500
    },
    {
      "epoch": 9.207953063885267,
      "grad_norm": 2.1449713706970215,
      "learning_rate": 2.376140808344198e-05,
      "loss": 0.4145,
      "step": 113000
    },
    {
      "epoch": 9.248696219035201,
      "grad_norm": 3.1341099739074707,
      "learning_rate": 2.2539113428943937e-05,
      "loss": 0.4126,
      "step": 113500
    },
    {
      "epoch": 9.289439374185136,
      "grad_norm": 2.521050214767456,
      "learning_rate": 2.131681877444589e-05,
      "loss": 0.418,
      "step": 114000
    },
    {
      "epoch": 9.330182529335072,
      "grad_norm": 1.99147367477417,
      "learning_rate": 2.009452411994785e-05,
      "loss": 0.4236,
      "step": 114500
    },
    {
      "epoch": 9.370925684485007,
      "grad_norm": 1.857513666152954,
      "learning_rate": 1.8872229465449803e-05,
      "loss": 0.4158,
      "step": 115000
    },
    {
      "epoch": 9.411668839634942,
      "grad_norm": 2.5369625091552734,
      "learning_rate": 1.7649934810951758e-05,
      "loss": 0.412,
      "step": 115500
    },
    {
      "epoch": 9.452411994784876,
      "grad_norm": 1.3735275268554688,
      "learning_rate": 1.6427640156453715e-05,
      "loss": 0.418,
      "step": 116000
    },
    {
      "epoch": 9.493155149934811,
      "grad_norm": 2.476191759109497,
      "learning_rate": 1.520534550195567e-05,
      "loss": 0.4267,
      "step": 116500
    },
    {
      "epoch": 9.533898305084746,
      "grad_norm": 2.943235158920288,
      "learning_rate": 1.3983050847457626e-05,
      "loss": 0.4207,
      "step": 117000
    },
    {
      "epoch": 9.57464146023468,
      "grad_norm": 2.901339530944824,
      "learning_rate": 1.2760756192959582e-05,
      "loss": 0.4075,
      "step": 117500
    },
    {
      "epoch": 9.615384615384615,
      "grad_norm": 1.8358930349349976,
      "learning_rate": 1.1538461538461538e-05,
      "loss": 0.4087,
      "step": 118000
    },
    {
      "epoch": 9.65612777053455,
      "grad_norm": 3.4656617641448975,
      "learning_rate": 1.0316166883963494e-05,
      "loss": 0.4085,
      "step": 118500
    },
    {
      "epoch": 9.696870925684484,
      "grad_norm": 2.3369274139404297,
      "learning_rate": 9.093872229465448e-06,
      "loss": 0.4207,
      "step": 119000
    },
    {
      "epoch": 9.737614080834419,
      "grad_norm": 2.220635175704956,
      "learning_rate": 7.871577574967404e-06,
      "loss": 0.4174,
      "step": 119500
    },
    {
      "epoch": 9.778357235984355,
      "grad_norm": 2.155561685562134,
      "learning_rate": 6.649282920469361e-06,
      "loss": 0.4059,
      "step": 120000
    },
    {
      "epoch": 9.81910039113429,
      "grad_norm": 1.8922115564346313,
      "learning_rate": 5.426988265971316e-06,
      "loss": 0.4129,
      "step": 120500
    },
    {
      "epoch": 9.859843546284225,
      "grad_norm": 2.2895336151123047,
      "learning_rate": 4.2046936114732716e-06,
      "loss": 0.4211,
      "step": 121000
    },
    {
      "epoch": 9.90058670143416,
      "grad_norm": 2.634411334991455,
      "learning_rate": 2.982398956975228e-06,
      "loss": 0.4157,
      "step": 121500
    },
    {
      "epoch": 9.941329856584094,
      "grad_norm": 3.487070083618164,
      "learning_rate": 1.7601043024771837e-06,
      "loss": 0.4114,
      "step": 122000
    },
    {
      "epoch": 9.982073011734029,
      "grad_norm": 2.2430856227874756,
      "learning_rate": 5.378096479791394e-07,
      "loss": 0.4105,
      "step": 122500
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.8317269086837769,
      "eval_loss": 0.4328731894493103,
      "eval_runtime": 1.8695,
      "eval_samples_per_second": 1331.893,
      "eval_steps_per_second": 166.888,
      "step": 122720
    },
    {
      "epoch": 10.0,
      "step": 122720,
      "total_flos": 2.6143616931499008e+17,
      "train_loss": 0.47506770621378075,
      "train_runtime": 4149.7744,
      "train_samples_per_second": 946.321,
      "train_steps_per_second": 29.573
    }
  ],
  "logging_steps": 500,
  "max_steps": 122720,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.6143616931499008e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}