{
  "best_global_step": null,
  "best_metric": 0.4038073718547821,
  "best_model_checkpoint": null,
  "epoch": 3.899815440331511,
  "eval_steps": 500,
  "global_step": 14000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002785806316815823,
      "grad_norm": 0.4645193815231323,
      "learning_rate": 0.0,
      "loss": 2.3986,
      "step": 1
    },
    {
      "epoch": 0.027858063168158233,
      "grad_norm": 0.3897116482257843,
      "learning_rate": 1.9800000000000004e-05,
      "loss": 2.4541,
      "step": 100
    },
    {
      "epoch": 0.055716126336316465,
      "grad_norm": 0.9093355536460876,
      "learning_rate": 3.9800000000000005e-05,
      "loss": 1.4843,
      "step": 200
    },
    {
      "epoch": 0.0835741895044747,
      "grad_norm": 1.0977619886398315,
      "learning_rate": 4.9826364280652023e-05,
      "loss": 0.9759,
      "step": 300
    },
    {
      "epoch": 0.11143225267263293,
      "grad_norm": 1.0786027908325195,
      "learning_rate": 4.9472005669737774e-05,
      "loss": 0.8439,
      "step": 400
    },
    {
      "epoch": 0.13929031584079116,
      "grad_norm": 1.2702925205230713,
      "learning_rate": 4.911764705882353e-05,
      "loss": 0.7883,
      "step": 500
    },
    {
      "epoch": 0.13929031584079116,
      "eval_loss": 0.65428227186203,
      "eval_runtime": 591.887,
      "eval_samples_per_second": 48.518,
      "eval_steps_per_second": 3.033,
      "step": 500
    },
    {
      "epoch": 0.1671483790089494,
      "grad_norm": 1.3737353086471558,
      "learning_rate": 4.876328844790929e-05,
      "loss": 0.746,
      "step": 600
    },
    {
      "epoch": 0.19500644217710764,
      "grad_norm": 1.3053338527679443,
      "learning_rate": 4.840892983699504e-05,
      "loss": 0.7122,
      "step": 700
    },
    {
      "epoch": 0.22286450534526586,
      "grad_norm": 1.814271092414856,
      "learning_rate": 4.80545712260808e-05,
      "loss": 0.6914,
      "step": 800
    },
    {
      "epoch": 0.2507225685134241,
      "grad_norm": 1.3019365072250366,
      "learning_rate": 4.770021261516655e-05,
      "loss": 0.6831,
      "step": 900
    },
    {
      "epoch": 0.2785806316815823,
      "grad_norm": 1.2910503149032593,
      "learning_rate": 4.7345854004252306e-05,
      "loss": 0.6714,
      "step": 1000
    },
    {
      "epoch": 0.2785806316815823,
      "eval_loss": 0.5705545544624329,
      "eval_runtime": 592.3805,
      "eval_samples_per_second": 48.477,
      "eval_steps_per_second": 3.03,
      "step": 1000
    },
    {
      "epoch": 0.30643869484974057,
      "grad_norm": 1.4649542570114136,
      "learning_rate": 4.699149539333806e-05,
      "loss": 0.6487,
      "step": 1100
    },
    {
      "epoch": 0.3342967580178988,
      "grad_norm": 1.7467780113220215,
      "learning_rate": 4.6637136782423815e-05,
      "loss": 0.6456,
      "step": 1200
    },
    {
      "epoch": 0.362154821186057,
      "grad_norm": 1.33451247215271,
      "learning_rate": 4.628277817150957e-05,
      "loss": 0.637,
      "step": 1300
    },
    {
      "epoch": 0.3900128843542153,
      "grad_norm": 1.7314374446868896,
      "learning_rate": 4.592841956059532e-05,
      "loss": 0.6295,
      "step": 1400
    },
    {
      "epoch": 0.4178709475223735,
      "grad_norm": 1.344909906387329,
      "learning_rate": 4.557406094968108e-05,
      "loss": 0.621,
      "step": 1500
    },
    {
      "epoch": 0.4178709475223735,
      "eval_loss": 0.5306675434112549,
      "eval_runtime": 592.5408,
      "eval_samples_per_second": 48.464,
      "eval_steps_per_second": 3.029,
      "step": 1500
    },
    {
      "epoch": 0.4457290106905317,
      "grad_norm": 1.3075149059295654,
      "learning_rate": 4.521970233876683e-05,
      "loss": 0.6229,
      "step": 1600
    },
    {
      "epoch": 0.47358707385869,
      "grad_norm": 1.4076815843582153,
      "learning_rate": 4.486534372785259e-05,
      "loss": 0.6109,
      "step": 1700
    },
    {
      "epoch": 0.5014451370268482,
      "grad_norm": 1.3399609327316284,
      "learning_rate": 4.451098511693834e-05,
      "loss": 0.6024,
      "step": 1800
    },
    {
      "epoch": 0.5293032001950064,
      "grad_norm": 1.3271087408065796,
      "learning_rate": 4.41566265060241e-05,
      "loss": 0.5997,
      "step": 1900
    },
    {
      "epoch": 0.5571612633631646,
      "grad_norm": 1.412111520767212,
      "learning_rate": 4.3802267895109855e-05,
      "loss": 0.5839,
      "step": 2000
    },
    {
      "epoch": 0.5571612633631646,
      "eval_loss": 0.5096445679664612,
      "eval_runtime": 594.5376,
      "eval_samples_per_second": 48.301,
      "eval_steps_per_second": 3.019,
      "step": 2000
    },
    {
      "epoch": 0.5850193265313229,
      "grad_norm": 1.2040321826934814,
      "learning_rate": 4.3447909284195606e-05,
      "loss": 0.5789,
      "step": 2100
    },
    {
      "epoch": 0.6128773896994811,
      "grad_norm": 1.2207297086715698,
      "learning_rate": 4.3093550673281363e-05,
      "loss": 0.5761,
      "step": 2200
    },
    {
      "epoch": 0.6407354528676393,
      "grad_norm": 1.205450177192688,
      "learning_rate": 4.2739192062367114e-05,
      "loss": 0.5709,
      "step": 2300
    },
    {
      "epoch": 0.6685935160357976,
      "grad_norm": 1.3946952819824219,
      "learning_rate": 4.238483345145287e-05,
      "loss": 0.5696,
      "step": 2400
    },
    {
      "epoch": 0.6964515792039558,
      "grad_norm": 1.1846948862075806,
      "learning_rate": 4.203047484053862e-05,
      "loss": 0.5552,
      "step": 2500
    },
    {
      "epoch": 0.6964515792039558,
      "eval_loss": 0.4957100749015808,
      "eval_runtime": 593.2402,
      "eval_samples_per_second": 48.407,
      "eval_steps_per_second": 3.026,
      "step": 2500
    },
    {
      "epoch": 0.724309642372114,
      "grad_norm": 1.2646228075027466,
      "learning_rate": 4.167611622962439e-05,
      "loss": 0.5573,
      "step": 2600
    },
    {
      "epoch": 0.7521677055402723,
      "grad_norm": 1.2027941942214966,
      "learning_rate": 4.132175761871014e-05,
      "loss": 0.5568,
      "step": 2700
    },
    {
      "epoch": 0.7800257687084305,
      "grad_norm": 1.2179590463638306,
      "learning_rate": 4.0967399007795895e-05,
      "loss": 0.5579,
      "step": 2800
    },
    {
      "epoch": 0.8078838318765887,
      "grad_norm": 1.2543010711669922,
      "learning_rate": 4.0613040396881646e-05,
      "loss": 0.5632,
      "step": 2900
    },
    {
      "epoch": 0.835741895044747,
      "grad_norm": 1.2597264051437378,
      "learning_rate": 4.02586817859674e-05,
      "loss": 0.545,
      "step": 3000
    },
    {
      "epoch": 0.835741895044747,
      "eval_loss": 0.4792587161064148,
      "eval_runtime": 592.7585,
      "eval_samples_per_second": 48.446,
      "eval_steps_per_second": 3.028,
      "step": 3000
    },
    {
      "epoch": 0.8635999582129052,
      "grad_norm": 1.3292843103408813,
      "learning_rate": 3.9904323175053155e-05,
      "loss": 0.5571,
      "step": 3100
    },
    {
      "epoch": 0.8914580213810634,
      "grad_norm": 1.3142098188400269,
      "learning_rate": 3.9549964564138906e-05,
      "loss": 0.5397,
      "step": 3200
    },
    {
      "epoch": 0.9193160845492218,
      "grad_norm": 1.389565348625183,
      "learning_rate": 3.919560595322467e-05,
      "loss": 0.5478,
      "step": 3300
    },
    {
      "epoch": 0.94717414771738,
      "grad_norm": 1.1616095304489136,
      "learning_rate": 3.884124734231042e-05,
      "loss": 0.5396,
      "step": 3400
    },
    {
      "epoch": 0.9750322108855382,
      "grad_norm": 1.24950110912323,
      "learning_rate": 3.848688873139618e-05,
      "loss": 0.5337,
      "step": 3500
    },
    {
      "epoch": 0.9750322108855382,
      "eval_loss": 0.4686237871646881,
      "eval_runtime": 593.0319,
      "eval_samples_per_second": 48.424,
      "eval_steps_per_second": 3.027,
      "step": 3500
    },
    {
      "epoch": 1.0027858063168158,
      "grad_norm": 1.3192429542541504,
      "learning_rate": 3.813253012048193e-05,
      "loss": 0.5301,
      "step": 3600
    },
    {
      "epoch": 1.030643869484974,
      "grad_norm": 1.465832233428955,
      "learning_rate": 3.777817150956769e-05,
      "loss": 0.5272,
      "step": 3700
    },
    {
      "epoch": 1.0585019326531322,
      "grad_norm": 1.4403393268585205,
      "learning_rate": 3.742381289865344e-05,
      "loss": 0.5236,
      "step": 3800
    },
    {
      "epoch": 1.0863599958212906,
      "grad_norm": 1.3801666498184204,
      "learning_rate": 3.706945428773919e-05,
      "loss": 0.5242,
      "step": 3900
    },
    {
      "epoch": 1.1142180589894488,
      "grad_norm": 1.076539397239685,
      "learning_rate": 3.671509567682495e-05,
      "loss": 0.5224,
      "step": 4000
    },
    {
      "epoch": 1.1142180589894488,
      "eval_loss": 0.46663618087768555,
      "eval_runtime": 592.8183,
      "eval_samples_per_second": 48.441,
      "eval_steps_per_second": 3.028,
      "step": 4000
    },
    {
      "epoch": 1.142076122157607,
      "grad_norm": 1.3829838037490845,
      "learning_rate": 3.6360737065910704e-05,
      "loss": 0.5217,
      "step": 4100
    },
    {
      "epoch": 1.1699341853257652,
      "grad_norm": 1.098763108253479,
      "learning_rate": 3.600637845499646e-05,
      "loss": 0.5169,
      "step": 4200
    },
    {
      "epoch": 1.1977922484939234,
      "grad_norm": 1.260761022567749,
      "learning_rate": 3.565201984408221e-05,
      "loss": 0.5116,
      "step": 4300
    },
    {
      "epoch": 1.2256503116620816,
      "grad_norm": 1.3205015659332275,
      "learning_rate": 3.529766123316797e-05,
      "loss": 0.518,
      "step": 4400
    },
    {
      "epoch": 1.2535083748302398,
      "grad_norm": 1.3871066570281982,
      "learning_rate": 3.494330262225372e-05,
      "loss": 0.5181,
      "step": 4500
    },
    {
      "epoch": 1.2535083748302398,
      "eval_loss": 0.45501282811164856,
      "eval_runtime": 592.8496,
      "eval_samples_per_second": 48.439,
      "eval_steps_per_second": 3.028,
      "step": 4500
    },
    {
      "epoch": 1.2813664379983982,
      "grad_norm": 1.1054390668869019,
      "learning_rate": 3.458894401133948e-05,
      "loss": 0.5148,
      "step": 4600
    },
    {
      "epoch": 1.3092245011665564,
      "grad_norm": 1.0034719705581665,
      "learning_rate": 3.4234585400425235e-05,
      "loss": 0.5109,
      "step": 4700
    },
    {
      "epoch": 1.3370825643347146,
      "grad_norm": 1.417938232421875,
      "learning_rate": 3.3880226789510986e-05,
      "loss": 0.5104,
      "step": 4800
    },
    {
      "epoch": 1.3649406275028728,
      "grad_norm": 1.243116855621338,
      "learning_rate": 3.3525868178596744e-05,
      "loss": 0.4988,
      "step": 4900
    },
    {
      "epoch": 1.392798690671031,
      "grad_norm": 1.1632623672485352,
      "learning_rate": 3.3171509567682495e-05,
      "loss": 0.5072,
      "step": 5000
    },
    {
      "epoch": 1.392798690671031,
      "eval_loss": 0.45067891478538513,
      "eval_runtime": 593.6193,
      "eval_samples_per_second": 48.376,
      "eval_steps_per_second": 3.024,
      "step": 5000
    },
    {
      "epoch": 1.4206567538391894,
      "grad_norm": 1.3165979385375977,
      "learning_rate": 3.281715095676825e-05,
      "loss": 0.4934,
      "step": 5100
    },
    {
      "epoch": 1.4485148170073476,
      "grad_norm": 1.3166348934173584,
      "learning_rate": 3.2462792345854e-05,
      "loss": 0.51,
      "step": 5200
    },
    {
      "epoch": 1.4763728801755058,
      "grad_norm": 1.737769365310669,
      "learning_rate": 3.210843373493976e-05,
      "loss": 0.5079,
      "step": 5300
    },
    {
      "epoch": 1.504230943343664,
      "grad_norm": 1.0135122537612915,
      "learning_rate": 3.175407512402552e-05,
      "loss": 0.4915,
      "step": 5400
    },
    {
      "epoch": 1.5320890065118222,
      "grad_norm": 1.161383032798767,
      "learning_rate": 3.139971651311127e-05,
      "loss": 0.4972,
      "step": 5500
    },
    {
      "epoch": 1.5320890065118222,
      "eval_loss": 0.4426087737083435,
      "eval_runtime": 592.4939,
      "eval_samples_per_second": 48.468,
      "eval_steps_per_second": 3.03,
      "step": 5500
    },
    {
      "epoch": 1.5599470696799806,
      "grad_norm": 1.2716448307037354,
      "learning_rate": 3.104535790219703e-05,
      "loss": 0.4904,
      "step": 5600
    },
    {
      "epoch": 1.5878051328481386,
      "grad_norm": 1.2625107765197754,
      "learning_rate": 3.069099929128278e-05,
      "loss": 0.4943,
      "step": 5700
    },
    {
      "epoch": 1.615663196016297,
      "grad_norm": 1.2053842544555664,
      "learning_rate": 3.0336640680368532e-05,
      "loss": 0.5028,
      "step": 5800
    },
    {
      "epoch": 1.6435212591844552,
      "grad_norm": 1.1495795249938965,
      "learning_rate": 2.9982282069454286e-05,
      "loss": 0.4929,
      "step": 5900
    },
    {
      "epoch": 1.6713793223526134,
      "grad_norm": 1.1481202840805054,
      "learning_rate": 2.9627923458540047e-05,
      "loss": 0.4926,
      "step": 6000
    },
    {
      "epoch": 1.6713793223526134,
      "eval_loss": 0.444801926612854,
      "eval_runtime": 592.9633,
      "eval_samples_per_second": 48.43,
      "eval_steps_per_second": 3.027,
      "step": 6000
    },
    {
      "epoch": 1.6992373855207716,
      "grad_norm": 1.3731409311294556,
      "learning_rate": 2.92735648476258e-05,
      "loss": 0.5006,
      "step": 6100
    },
    {
      "epoch": 1.7270954486889298,
      "grad_norm": 1.0181461572647095,
      "learning_rate": 2.8919206236711555e-05,
      "loss": 0.4855,
      "step": 6200
    },
    {
      "epoch": 1.7549535118570883,
      "grad_norm": 1.5491364002227783,
      "learning_rate": 2.856484762579731e-05,
      "loss": 0.4994,
      "step": 6300
    },
    {
      "epoch": 1.7828115750252462,
      "grad_norm": 1.149021029472351,
      "learning_rate": 2.8210489014883064e-05,
      "loss": 0.4918,
      "step": 6400
    },
    {
      "epoch": 1.8106696381934047,
      "grad_norm": 1.0654308795928955,
      "learning_rate": 2.7856130403968818e-05,
      "loss": 0.487,
      "step": 6500
    },
    {
      "epoch": 1.8106696381934047,
      "eval_loss": 0.4356010854244232,
      "eval_runtime": 593.5091,
      "eval_samples_per_second": 48.385,
      "eval_steps_per_second": 3.024,
      "step": 6500
    },
    {
      "epoch": 1.8385277013615628,
      "grad_norm": 1.2700181007385254,
      "learning_rate": 2.750177179305457e-05,
      "loss": 0.4869,
      "step": 6600
    },
    {
      "epoch": 1.866385764529721,
      "grad_norm": 1.0347015857696533,
      "learning_rate": 2.714741318214033e-05,
      "loss": 0.4861,
      "step": 6700
    },
    {
      "epoch": 1.8942438276978795,
      "grad_norm": 1.08585786819458,
      "learning_rate": 2.6793054571226084e-05,
      "loss": 0.4884,
      "step": 6800
    },
    {
      "epoch": 1.9221018908660374,
      "grad_norm": 1.2477092742919922,
      "learning_rate": 2.6438695960311838e-05,
      "loss": 0.478,
      "step": 6900
    },
    {
      "epoch": 1.9499599540341959,
      "grad_norm": 1.1088532209396362,
      "learning_rate": 2.6084337349397592e-05,
      "loss": 0.4919,
      "step": 7000
    },
    {
      "epoch": 1.9499599540341959,
      "eval_loss": 0.43220457434654236,
      "eval_runtime": 593.2416,
      "eval_samples_per_second": 48.407,
      "eval_steps_per_second": 3.026,
      "step": 7000
    },
    {
      "epoch": 1.977818017202354,
      "grad_norm": 1.0134484767913818,
      "learning_rate": 2.5729978738483347e-05,
      "loss": 0.4861,
      "step": 7100
    },
    {
      "epoch": 2.0055716126336316,
      "grad_norm": 1.185179591178894,
      "learning_rate": 2.53756201275691e-05,
      "loss": 0.4805,
      "step": 7200
    },
    {
      "epoch": 2.03342967580179,
      "grad_norm": 1.2651209831237793,
      "learning_rate": 2.5021261516654855e-05,
      "loss": 0.4785,
      "step": 7300
    },
    {
      "epoch": 2.061287738969948,
      "grad_norm": 1.0275731086730957,
      "learning_rate": 2.466690290574061e-05,
      "loss": 0.4767,
      "step": 7400
    },
    {
      "epoch": 2.0891458021381064,
      "grad_norm": 1.0938606262207031,
      "learning_rate": 2.4312544294826363e-05,
      "loss": 0.4682,
      "step": 7500
    },
    {
      "epoch": 2.0891458021381064,
      "eval_loss": 0.4292644262313843,
      "eval_runtime": 592.5766,
      "eval_samples_per_second": 48.461,
      "eval_steps_per_second": 3.029,
      "step": 7500
    },
    {
      "epoch": 2.1170038653062644,
      "grad_norm": 1.1097854375839233,
      "learning_rate": 2.395818568391212e-05,
      "loss": 0.4703,
      "step": 7600
    },
    {
      "epoch": 2.144861928474423,
      "grad_norm": 1.3471382856369019,
      "learning_rate": 2.3603827072997875e-05,
      "loss": 0.4843,
      "step": 7700
    },
    {
      "epoch": 2.1727199916425812,
      "grad_norm": 1.351805329322815,
      "learning_rate": 2.324946846208363e-05,
      "loss": 0.4776,
      "step": 7800
    },
    {
      "epoch": 2.200578054810739,
      "grad_norm": 1.1416364908218384,
      "learning_rate": 2.2895109851169387e-05,
      "loss": 0.4714,
      "step": 7900
    },
    {
      "epoch": 2.2284361179788976,
      "grad_norm": 1.1691741943359375,
      "learning_rate": 2.254075124025514e-05,
      "loss": 0.4734,
      "step": 8000
    },
    {
      "epoch": 2.2284361179788976,
      "eval_loss": 0.4240116477012634,
      "eval_runtime": 594.3246,
      "eval_samples_per_second": 48.319,
      "eval_steps_per_second": 3.02,
      "step": 8000
    },
    {
      "epoch": 2.2562941811470556,
      "grad_norm": 1.0872358083724976,
      "learning_rate": 2.2186392629340892e-05,
      "loss": 0.4711,
      "step": 8100
    },
    {
      "epoch": 2.284152244315214,
      "grad_norm": 1.166755199432373,
      "learning_rate": 2.1832034018426646e-05,
      "loss": 0.4674,
      "step": 8200
    },
    {
      "epoch": 2.312010307483372,
      "grad_norm": 1.397355556488037,
      "learning_rate": 2.1477675407512404e-05,
      "loss": 0.4741,
      "step": 8300
    },
    {
      "epoch": 2.3398683706515304,
      "grad_norm": 1.0663005113601685,
      "learning_rate": 2.1123316796598158e-05,
      "loss": 0.4741,
      "step": 8400
    },
    {
      "epoch": 2.367726433819689,
      "grad_norm": 1.2197699546813965,
      "learning_rate": 2.0768958185683912e-05,
      "loss": 0.4691,
      "step": 8500
    },
    {
      "epoch": 2.367726433819689,
      "eval_loss": 0.4226415753364563,
      "eval_runtime": 592.9032,
      "eval_samples_per_second": 48.435,
      "eval_steps_per_second": 3.027,
      "step": 8500
    },
    {
      "epoch": 2.395584496987847,
      "grad_norm": 1.4034844636917114,
      "learning_rate": 2.041459957476967e-05,
      "loss": 0.4749,
      "step": 8600
    },
    {
      "epoch": 2.4234425601560052,
      "grad_norm": 1.2953102588653564,
      "learning_rate": 2.0060240963855424e-05,
      "loss": 0.4757,
      "step": 8700
    },
    {
      "epoch": 2.451300623324163,
      "grad_norm": 1.3071800470352173,
      "learning_rate": 1.9705882352941178e-05,
      "loss": 0.4668,
      "step": 8800
    },
    {
      "epoch": 2.4791586864923216,
      "grad_norm": 1.1789804697036743,
      "learning_rate": 1.9351523742026932e-05,
      "loss": 0.4729,
      "step": 8900
    },
    {
      "epoch": 2.5070167496604796,
      "grad_norm": 1.2676748037338257,
      "learning_rate": 1.8997165131112687e-05,
      "loss": 0.4679,
      "step": 9000
    },
    {
      "epoch": 2.5070167496604796,
      "eval_loss": 0.4187828004360199,
      "eval_runtime": 592.1014,
      "eval_samples_per_second": 48.5,
      "eval_steps_per_second": 3.032,
      "step": 9000
    },
    {
      "epoch": 2.534874812828638,
      "grad_norm": 1.3900854587554932,
      "learning_rate": 1.864280652019844e-05,
      "loss": 0.4677,
      "step": 9100
    },
    {
      "epoch": 2.5627328759967964,
      "grad_norm": 1.2864222526550293,
      "learning_rate": 1.8288447909284195e-05,
      "loss": 0.4584,
      "step": 9200
    },
    {
      "epoch": 2.5905909391649544,
      "grad_norm": 1.0441097021102905,
      "learning_rate": 1.7934089298369953e-05,
      "loss": 0.4654,
      "step": 9300
    },
    {
      "epoch": 2.618449002333113,
      "grad_norm": 1.1249713897705078,
      "learning_rate": 1.7579730687455707e-05,
      "loss": 0.4674,
      "step": 9400
    },
    {
      "epoch": 2.6463070655012713,
      "grad_norm": 1.2885221242904663,
      "learning_rate": 1.722537207654146e-05,
      "loss": 0.4694,
      "step": 9500
    },
    {
      "epoch": 2.6463070655012713,
      "eval_loss": 0.4162205457687378,
      "eval_runtime": 593.1028,
      "eval_samples_per_second": 48.418,
      "eval_steps_per_second": 3.026,
      "step": 9500
    },
    {
      "epoch": 2.6741651286694292,
      "grad_norm": 1.1028586626052856,
      "learning_rate": 1.6871013465627215e-05,
      "loss": 0.4573,
      "step": 9600
    },
    {
      "epoch": 2.7020231918375877,
      "grad_norm": 1.3248066902160645,
      "learning_rate": 1.651665485471297e-05,
      "loss": 0.4609,
      "step": 9700
    },
    {
      "epoch": 2.7298812550057456,
      "grad_norm": 1.073268175125122,
      "learning_rate": 1.6162296243798724e-05,
      "loss": 0.4543,
      "step": 9800
    },
    {
      "epoch": 2.757739318173904,
      "grad_norm": 1.0753856897354126,
      "learning_rate": 1.5807937632884478e-05,
      "loss": 0.4667,
      "step": 9900
    },
    {
      "epoch": 2.785597381342062,
      "grad_norm": 1.2315281629562378,
      "learning_rate": 1.5453579021970235e-05,
      "loss": 0.4573,
      "step": 10000
    },
    {
      "epoch": 2.785597381342062,
      "eval_loss": 0.41505932807922363,
      "eval_runtime": 592.7426,
      "eval_samples_per_second": 48.448,
      "eval_steps_per_second": 3.028,
      "step": 10000
    },
    {
      "epoch": 2.8134554445102204,
      "grad_norm": 1.1854623556137085,
      "learning_rate": 1.509922041105599e-05,
      "loss": 0.4579,
      "step": 10100
    },
    {
      "epoch": 2.841313507678379,
      "grad_norm": 1.1797943115234375,
      "learning_rate": 1.4744861800141744e-05,
      "loss": 0.4512,
      "step": 10200
    },
    {
      "epoch": 2.869171570846537,
      "grad_norm": 1.2852693796157837,
      "learning_rate": 1.43905031892275e-05,
      "loss": 0.4657,
      "step": 10300
    },
    {
      "epoch": 2.8970296340146953,
      "grad_norm": 1.4903700351715088,
      "learning_rate": 1.4036144578313254e-05,
      "loss": 0.4565,
      "step": 10400
    },
    {
      "epoch": 2.9248876971828532,
      "grad_norm": 1.1999119520187378,
      "learning_rate": 1.3681785967399008e-05,
      "loss": 0.4505,
      "step": 10500
    },
    {
      "epoch": 2.9248876971828532,
      "eval_loss": 0.41494467854499817,
      "eval_runtime": 594.0624,
      "eval_samples_per_second": 48.34,
      "eval_steps_per_second": 3.022,
      "step": 10500
    },
    {
      "epoch": 2.9527457603510117,
      "grad_norm": 1.1072437763214111,
      "learning_rate": 1.3327427356484764e-05,
      "loss": 0.4636,
      "step": 10600
    },
    {
      "epoch": 2.9806038235191696,
      "grad_norm": 1.0771669149398804,
      "learning_rate": 1.2973068745570518e-05,
      "loss": 0.4666,
      "step": 10700
    },
    {
      "epoch": 3.0083574189504474,
      "grad_norm": 1.1003024578094482,
      "learning_rate": 1.2618710134656272e-05,
      "loss": 0.4456,
      "step": 10800
    },
    {
      "epoch": 3.036215482118606,
      "grad_norm": 1.417353630065918,
      "learning_rate": 1.2264351523742028e-05,
      "loss": 0.4594,
      "step": 10900
    },
    {
      "epoch": 3.064073545286764,
      "grad_norm": 1.1961385011672974,
      "learning_rate": 1.1909992912827782e-05,
      "loss": 0.4478,
      "step": 11000
    },
    {
      "epoch": 3.064073545286764,
      "eval_loss": 0.4131682813167572,
      "eval_runtime": 592.6765,
      "eval_samples_per_second": 48.453,
      "eval_steps_per_second": 3.029,
      "step": 11000
    },
    {
      "epoch": 3.091931608454922,
      "grad_norm": 1.3566352128982544,
      "learning_rate": 1.1555634301913537e-05,
      "loss": 0.4416,
      "step": 11100
    },
    {
      "epoch": 3.1197896716230806,
      "grad_norm": 1.3073431253433228,
      "learning_rate": 1.1201275690999293e-05,
      "loss": 0.4509,
      "step": 11200
    },
    {
      "epoch": 3.1476477347912386,
      "grad_norm": 1.3190025091171265,
      "learning_rate": 1.0846917080085047e-05,
      "loss": 0.4513,
      "step": 11300
    },
    {
      "epoch": 3.175505797959397,
      "grad_norm": 1.3781085014343262,
      "learning_rate": 1.0492558469170801e-05,
      "loss": 0.4437,
      "step": 11400
    },
    {
      "epoch": 3.203363861127555,
      "grad_norm": 1.306618332862854,
      "learning_rate": 1.0138199858256555e-05,
      "loss": 0.4454,
      "step": 11500
    },
    {
      "epoch": 3.203363861127555,
      "eval_loss": 0.4108191132545471,
      "eval_runtime": 593.9192,
      "eval_samples_per_second": 48.352,
      "eval_steps_per_second": 3.022,
      "step": 11500
    },
    {
      "epoch": 3.2312219242957134,
      "grad_norm": 1.4700162410736084,
      "learning_rate": 9.783841247342311e-06,
      "loss": 0.4471,
      "step": 11600
    },
    {
      "epoch": 3.2590799874638714,
      "grad_norm": 1.1304278373718262,
      "learning_rate": 9.429482636428065e-06,
      "loss": 0.4536,
      "step": 11700
    },
    {
      "epoch": 3.28693805063203,
      "grad_norm": 1.4289369583129883,
      "learning_rate": 9.075124025513821e-06,
      "loss": 0.4474,
      "step": 11800
    },
    {
      "epoch": 3.3147961138001882,
      "grad_norm": 1.3017057180404663,
      "learning_rate": 8.720765414599575e-06,
      "loss": 0.4449,
      "step": 11900
    },
    {
      "epoch": 3.342654176968346,
      "grad_norm": 1.4927443265914917,
      "learning_rate": 8.36640680368533e-06,
      "loss": 0.4557,
      "step": 12000
    },
    {
      "epoch": 3.342654176968346,
      "eval_loss": 0.4085528552532196,
      "eval_runtime": 592.2863,
      "eval_samples_per_second": 48.485,
      "eval_steps_per_second": 3.031,
      "step": 12000
    },
    {
      "epoch": 3.3705122401365046,
      "grad_norm": 1.4530751705169678,
      "learning_rate": 8.012048192771085e-06,
      "loss": 0.455,
      "step": 12100
    },
    {
      "epoch": 3.3983703033046626,
      "grad_norm": 1.4134407043457031,
      "learning_rate": 7.65768958185684e-06,
      "loss": 0.4504,
      "step": 12200
    },
    {
      "epoch": 3.426228366472821,
      "grad_norm": 1.2031890153884888,
      "learning_rate": 7.303330970942594e-06,
      "loss": 0.4473,
      "step": 12300
    },
    {
      "epoch": 3.454086429640979,
      "grad_norm": 1.3506805896759033,
      "learning_rate": 6.94897236002835e-06,
      "loss": 0.4452,
      "step": 12400
    },
    {
      "epoch": 3.4819444928091374,
      "grad_norm": 1.6460970640182495,
      "learning_rate": 6.594613749114104e-06,
      "loss": 0.4475,
      "step": 12500
    },
    {
      "epoch": 3.4819444928091374,
      "eval_loss": 0.40733858942985535,
      "eval_runtime": 593.8096,
      "eval_samples_per_second": 48.361,
      "eval_steps_per_second": 3.023,
      "step": 12500
    },
    {
      "epoch": 3.509802555977296,
      "grad_norm": 1.34632408618927,
      "learning_rate": 6.240255138199858e-06,
      "loss": 0.4472,
      "step": 12600
    },
    {
      "epoch": 3.537660619145454,
      "grad_norm": 1.1388472318649292,
      "learning_rate": 5.885896527285613e-06,
      "loss": 0.4504,
      "step": 12700
    },
    {
      "epoch": 3.5655186823136122,
      "grad_norm": 1.3838173151016235,
      "learning_rate": 5.531537916371368e-06,
      "loss": 0.4509,
      "step": 12800
    },
    {
      "epoch": 3.59337674548177,
      "grad_norm": 1.2048169374465942,
      "learning_rate": 5.1771793054571225e-06,
      "loss": 0.4484,
      "step": 12900
    },
    {
      "epoch": 3.6212348086499286,
      "grad_norm": 1.337014079093933,
      "learning_rate": 4.8228206945428775e-06,
      "loss": 0.4514,
      "step": 13000
    },
    {
      "epoch": 3.6212348086499286,
      "eval_loss": 0.40576237440109253,
      "eval_runtime": 592.3205,
      "eval_samples_per_second": 48.482,
      "eval_steps_per_second": 3.03,
      "step": 13000
    },
    {
      "epoch": 3.6490928718180866,
      "grad_norm": 1.2974600791931152,
      "learning_rate": 4.4684620836286326e-06,
      "loss": 0.4449,
      "step": 13100
    },
    {
      "epoch": 3.676950934986245,
      "grad_norm": 1.1322963237762451,
      "learning_rate": 4.114103472714388e-06,
      "loss": 0.4514,
      "step": 13200
    },
    {
      "epoch": 3.7048089981544035,
      "grad_norm": 1.2485069036483765,
      "learning_rate": 3.7597448618001422e-06,
      "loss": 0.441,
      "step": 13300
    },
    {
      "epoch": 3.7326670613225614,
      "grad_norm": 1.3043463230133057,
      "learning_rate": 3.405386250885897e-06,
      "loss": 0.4429,
      "step": 13400
    },
    {
      "epoch": 3.76052512449072,
      "grad_norm": 1.22727632522583,
      "learning_rate": 3.0510276399716515e-06,
      "loss": 0.4461,
      "step": 13500
    },
    {
      "epoch": 3.76052512449072,
      "eval_loss": 0.40465712547302246,
      "eval_runtime": 593.0804,
      "eval_samples_per_second": 48.42,
      "eval_steps_per_second": 3.027,
      "step": 13500
    },
    {
      "epoch": 3.7883831876588783,
      "grad_norm": 1.322852611541748,
      "learning_rate": 2.696669029057406e-06,
      "loss": 0.4495,
      "step": 13600
    },
    {
      "epoch": 3.8162412508270362,
      "grad_norm": 1.18853759765625,
      "learning_rate": 2.342310418143161e-06,
      "loss": 0.4363,
      "step": 13700
    },
    {
      "epoch": 3.8440993139951942,
      "grad_norm": 1.22146475315094,
      "learning_rate": 1.987951807228916e-06,
      "loss": 0.4393,
      "step": 13800
    },
    {
      "epoch": 3.8719573771633526,
      "grad_norm": 1.3995431661605835,
      "learning_rate": 1.6335931963146704e-06,
      "loss": 0.4475,
      "step": 13900
    },
    {
      "epoch": 3.899815440331511,
      "grad_norm": 1.402491807937622,
      "learning_rate": 1.2792345854004253e-06,
      "loss": 0.445,
      "step": 14000
    },
    {
      "epoch": 3.899815440331511,
      "eval_loss": 0.4038073718547821,
      "eval_runtime": 594.2622,
      "eval_samples_per_second": 48.324,
      "eval_steps_per_second": 3.021,
      "step": 14000
    }
  ],
  "logging_steps": 100,
  "max_steps": 14360,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 4.932896695826283e+21,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}