{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.44145873320537427,
  "eval_steps": 500,
  "global_step": 460,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0047984644913627635,
      "grad_norm": 32.591251373291016,
      "learning_rate": 8.401166180758017e-06,
      "loss": 1.152,
      "mean_token_accuracy": 0.730931556224823,
      "num_tokens": 799294.0,
      "step": 5
    },
    {
      "epoch": 0.009596928982725527,
      "grad_norm": 3.1753504276275635,
      "learning_rate": 1.8902623906705538e-05,
      "loss": 0.5765,
      "mean_token_accuracy": 0.8255371809005737,
      "num_tokens": 1589820.0,
      "step": 10
    },
    {
      "epoch": 0.014395393474088292,
      "grad_norm": 2.811250686645508,
      "learning_rate": 2.9404081632653062e-05,
      "loss": 0.4173,
      "mean_token_accuracy": 0.8512514710426331,
      "num_tokens": 2378183.0,
      "step": 15
    },
    {
      "epoch": 0.019193857965451054,
      "grad_norm": 2.1911630630493164,
      "learning_rate": 3.990553935860058e-05,
      "loss": 0.3916,
      "mean_token_accuracy": 0.8533002972602844,
      "num_tokens": 3183115.0,
      "step": 20
    },
    {
      "epoch": 0.02399232245681382,
      "grad_norm": 3.374872922897339,
      "learning_rate": 5.0406997084548104e-05,
      "loss": 0.3496,
      "mean_token_accuracy": 0.8802085399627686,
      "num_tokens": 3991639.0,
      "step": 25
    },
    {
      "epoch": 0.028790786948176585,
      "grad_norm": 2.2735555171966553,
      "learning_rate": 6.090845481049563e-05,
      "loss": 0.3253,
      "mean_token_accuracy": 0.8847130298614502,
      "num_tokens": 4786386.0,
      "step": 30
    },
    {
      "epoch": 0.03358925143953935,
      "grad_norm": 1.5320895910263062,
      "learning_rate": 7.140991253644314e-05,
      "loss": 0.2999,
      "mean_token_accuracy": 0.8903302311897278,
      "num_tokens": 5575841.0,
      "step": 35
    },
    {
      "epoch": 0.03838771593090211,
      "grad_norm": 2.4821479320526123,
      "learning_rate": 7.350805771429152e-05,
      "loss": 0.3198,
      "mean_token_accuracy": 0.8918884038925171,
      "num_tokens": 6351291.0,
      "step": 40
    },
    {
      "epoch": 0.04318618042226487,
      "grad_norm": 1.3984349966049194,
      "learning_rate": 7.349933866980902e-05,
      "loss": 0.2805,
      "mean_token_accuracy": 0.8992334485054017,
      "num_tokens": 7127815.0,
      "step": 45
    },
    {
      "epoch": 0.04798464491362764,
      "grad_norm": 0.9826128482818604,
      "learning_rate": 7.348391492008383e-05,
      "loss": 0.2894,
      "mean_token_accuracy": 0.8915998458862304,
      "num_tokens": 7928844.0,
      "step": 50
    },
    {
      "epoch": 0.052783109404990404,
      "grad_norm": 1.3426622152328491,
      "learning_rate": 7.34617902179726e-05,
      "loss": 0.2652,
      "mean_token_accuracy": 0.9018174767494201,
      "num_tokens": 8725094.0,
      "step": 55
    },
    {
      "epoch": 0.05758157389635317,
      "grad_norm": 0.9711771607398987,
      "learning_rate": 7.343296994678593e-05,
      "loss": 0.2739,
      "mean_token_accuracy": 0.8992493629455567,
      "num_tokens": 9521312.0,
      "step": 60
    },
    {
      "epoch": 0.06238003838771593,
      "grad_norm": 0.986544132232666,
      "learning_rate": 7.339746111897856e-05,
      "loss": 0.2652,
      "mean_token_accuracy": 0.8993094563484192,
      "num_tokens": 10328920.0,
      "step": 65
    },
    {
      "epoch": 0.0671785028790787,
      "grad_norm": 1.0141630172729492,
      "learning_rate": 7.335527237444306e-05,
      "loss": 0.2582,
      "mean_token_accuracy": 0.9018368721008301,
      "num_tokens": 11129367.0,
      "step": 70
    },
    {
      "epoch": 0.07197696737044146,
      "grad_norm": 1.9091362953186035,
      "learning_rate": 7.330641397840763e-05,
      "loss": 0.2532,
      "mean_token_accuracy": 0.9050414323806762,
      "num_tokens": 11925943.0,
      "step": 75
    },
    {
      "epoch": 0.07677543186180422,
      "grad_norm": 0.6851639747619629,
      "learning_rate": 7.32508978189384e-05,
      "loss": 0.2463,
      "mean_token_accuracy": 0.9032415986061096,
      "num_tokens": 12715832.0,
      "step": 80
    },
    {
      "epoch": 0.08157389635316699,
      "grad_norm": 0.9245691299438477,
      "learning_rate": 7.318873740404686e-05,
      "loss": 0.2409,
      "mean_token_accuracy": 0.9095496535301208,
      "num_tokens": 13512930.0,
      "step": 85
    },
    {
      "epoch": 0.08637236084452975,
      "grad_norm": 1.114152431488037,
      "learning_rate": 7.311994785840315e-05,
      "loss": 0.236,
      "mean_token_accuracy": 0.9103517293930053,
      "num_tokens": 14310763.0,
      "step": 90
    },
    {
      "epoch": 0.09117082533589252,
      "grad_norm": 0.6443946361541748,
      "learning_rate": 7.304454591965593e-05,
      "loss": 0.2337,
      "mean_token_accuracy": 0.9106445193290711,
      "num_tokens": 15077828.0,
      "step": 95
    },
    {
      "epoch": 0.09596928982725528,
      "grad_norm": 0.8331279158592224,
      "learning_rate": 7.296254993435989e-05,
      "loss": 0.2407,
      "mean_token_accuracy": 0.9029403924942017,
      "num_tokens": 15876828.0,
      "step": 100
    },
    {
      "epoch": 0.10076775431861804,
      "grad_norm": 1.4841084480285645,
      "learning_rate": 7.287397985351168e-05,
      "loss": 0.245,
      "mean_token_accuracy": 0.9005821108818054,
      "num_tokens": 16684191.0,
      "step": 105
    },
    {
      "epoch": 0.10556621880998081,
      "grad_norm": 0.5702885985374451,
      "learning_rate": 7.27788572276955e-05,
      "loss": 0.2268,
      "mean_token_accuracy": 0.905585777759552,
      "num_tokens": 17499344.0,
      "step": 110
    },
    {
      "epoch": 0.11036468330134357,
      "grad_norm": 0.6955417990684509,
      "learning_rate": 7.267720520183951e-05,
      "loss": 0.228,
      "mean_token_accuracy": 0.9089990615844726,
      "num_tokens": 18311988.0,
      "step": 115
    },
    {
      "epoch": 0.11516314779270634,
      "grad_norm": 0.8562710881233215,
      "learning_rate": 7.256904850958429e-05,
      "loss": 0.2313,
      "mean_token_accuracy": 0.9063257932662964,
      "num_tokens": 19117619.0,
      "step": 120
    },
    {
      "epoch": 0.1199616122840691,
      "grad_norm": 0.5443550944328308,
      "learning_rate": 7.245441346726467e-05,
      "loss": 0.2237,
      "mean_token_accuracy": 0.9092974305152893,
      "num_tokens": 19905936.0,
      "step": 125
    },
    {
      "epoch": 0.12476007677543186,
      "grad_norm": 0.6315863728523254,
      "learning_rate": 7.233332796750656e-05,
      "loss": 0.2152,
      "mean_token_accuracy": 0.9135099887847901,
      "num_tokens": 20687613.0,
      "step": 130
    },
    {
      "epoch": 0.1295585412667946,
      "grad_norm": 0.9352563619613647,
      "learning_rate": 7.220582147244025e-05,
      "loss": 0.217,
      "mean_token_accuracy": 0.9076200485229492,
      "num_tokens": 21492115.0,
      "step": 135
    },
    {
      "epoch": 0.1343570057581574,
      "grad_norm": 0.8867104649543762,
      "learning_rate": 7.207192500653172e-05,
      "loss": 0.2312,
      "mean_token_accuracy": 0.9056767225265503,
      "num_tokens": 22272734.0,
      "step": 140
    },
    {
      "epoch": 0.13915547024952016,
      "grad_norm": 0.6146453022956848,
      "learning_rate": 7.193167114903386e-05,
      "loss": 0.2261,
      "mean_token_accuracy": 0.905716347694397,
      "num_tokens": 23051480.0,
      "step": 145
    },
    {
      "epoch": 0.14395393474088292,
      "grad_norm": 1.0299674272537231,
      "learning_rate": 7.178509402605946e-05,
      "loss": 0.2346,
      "mean_token_accuracy": 0.9057998061180115,
      "num_tokens": 23843143.0,
      "step": 150
    },
    {
      "epoch": 0.14875239923224567,
      "grad_norm": 0.810525119304657,
      "learning_rate": 7.16322293022777e-05,
      "loss": 0.2307,
      "mean_token_accuracy": 0.9111165881156922,
      "num_tokens": 24637524.0,
      "step": 155
    },
    {
      "epoch": 0.15355086372360843,
      "grad_norm": 0.4699096977710724,
      "learning_rate": 7.147311417223636e-05,
      "loss": 0.2297,
      "mean_token_accuracy": 0.9072130799293519,
      "num_tokens": 25434785.0,
      "step": 160
    },
    {
      "epoch": 0.15834932821497122,
      "grad_norm": 0.8143472671508789,
      "learning_rate": 7.130778735131171e-05,
      "loss": 0.2186,
      "mean_token_accuracy": 0.9113067984580994,
      "num_tokens": 26236980.0,
      "step": 165
    },
    {
      "epoch": 0.16314779270633398,
      "grad_norm": 0.5336032509803772,
      "learning_rate": 7.113628906628854e-05,
      "loss": 0.2186,
      "mean_token_accuracy": 0.9100312232971192,
      "num_tokens": 27022193.0,
      "step": 170
    },
    {
      "epoch": 0.16794625719769674,
      "grad_norm": 0.5377821922302246,
      "learning_rate": 7.095866104557217e-05,
      "loss": 0.2136,
      "mean_token_accuracy": 0.9070743322372437,
      "num_tokens": 27814657.0,
      "step": 175
    },
    {
      "epoch": 0.1727447216890595,
      "grad_norm": 0.4592677354812622,
      "learning_rate": 7.077494650903529e-05,
      "loss": 0.2115,
      "mean_token_accuracy": 0.909694254398346,
      "num_tokens": 28609492.0,
      "step": 180
    },
    {
      "epoch": 0.17754318618042225,
      "grad_norm": 0.9938281178474426,
      "learning_rate": 7.058519015750186e-05,
      "loss": 0.2187,
      "mean_token_accuracy": 0.9073381423950195,
      "num_tokens": 29402462.0,
      "step": 185
    },
    {
      "epoch": 0.18234165067178504,
      "grad_norm": 0.5051109194755554,
      "learning_rate": 7.038943816187062e-05,
      "loss": 0.2174,
      "mean_token_accuracy": 0.9115898251533509,
      "num_tokens": 30207426.0,
      "step": 190
    },
    {
      "epoch": 0.1871401151631478,
      "grad_norm": 0.6154143214225769,
      "learning_rate": 7.018773815188091e-05,
      "loss": 0.2008,
      "mean_token_accuracy": 0.9124987602233887,
      "num_tokens": 30985559.0,
      "step": 195
    },
    {
      "epoch": 0.19193857965451055,
      "grad_norm": 0.6422397494316101,
      "learning_rate": 6.998013920452367e-05,
      "loss": 0.2071,
      "mean_token_accuracy": 0.9167937636375427,
      "num_tokens": 31763312.0,
      "step": 200
    },
    {
      "epoch": 0.1967370441458733,
      "grad_norm": 0.5240011215209961,
      "learning_rate": 6.976669183210004e-05,
      "loss": 0.2196,
      "mean_token_accuracy": 0.9105538129806519,
      "num_tokens": 32546702.0,
      "step": 205
    },
    {
      "epoch": 0.20153550863723607,
      "grad_norm": 0.48978161811828613,
      "learning_rate": 6.954744796993096e-05,
      "loss": 0.2165,
      "mean_token_accuracy": 0.9121721982955933,
      "num_tokens": 33362696.0,
      "step": 210
    },
    {
      "epoch": 0.20633397312859886,
      "grad_norm": 0.6336808204650879,
      "learning_rate": 6.932246096372041e-05,
      "loss": 0.2257,
      "mean_token_accuracy": 0.9081306457519531,
      "num_tokens": 34162694.0,
      "step": 215
    },
    {
      "epoch": 0.21113243761996162,
      "grad_norm": 0.47279420495033264,
      "learning_rate": 6.909178555657557e-05,
      "loss": 0.2116,
      "mean_token_accuracy": 0.9091696262359619,
      "num_tokens": 34949786.0,
      "step": 220
    },
    {
      "epoch": 0.21593090211132437,
      "grad_norm": 0.5637255907058716,
      "learning_rate": 6.885547787568674e-05,
      "loss": 0.209,
      "mean_token_accuracy": 0.9129250407218933,
      "num_tokens": 35750169.0,
      "step": 225
    },
    {
      "epoch": 0.22072936660268713,
      "grad_norm": 1.205546498298645,
      "learning_rate": 6.861359541867084e-05,
      "loss": 0.2012,
      "mean_token_accuracy": 0.9175987482070923,
      "num_tokens": 36542344.0,
      "step": 230
    },
    {
      "epoch": 0.2255278310940499,
      "grad_norm": 0.8636100888252258,
      "learning_rate": 6.836619703958119e-05,
      "loss": 0.2041,
      "mean_token_accuracy": 0.9169086694717408,
      "num_tokens": 37351148.0,
      "step": 235
    },
    {
      "epoch": 0.23032629558541268,
      "grad_norm": 0.6066936254501343,
      "learning_rate": 6.811334293458733e-05,
      "loss": 0.1971,
      "mean_token_accuracy": 0.9161781072616577,
      "num_tokens": 38114955.0,
      "step": 240
    },
    {
      "epoch": 0.23512476007677544,
      "grad_norm": 0.5045466423034668,
      "learning_rate": 6.78550946273283e-05,
      "loss": 0.1991,
      "mean_token_accuracy": 0.9162214040756226,
      "num_tokens": 38908489.0,
      "step": 245
    },
    {
      "epoch": 0.2399232245681382,
      "grad_norm": 0.4524458646774292,
      "learning_rate": 6.759151495394289e-05,
      "loss": 0.2079,
      "mean_token_accuracy": 0.9115633845329285,
      "num_tokens": 39711511.0,
      "step": 250
    },
    {
      "epoch": 0.24472168905950095,
      "grad_norm": 0.3954505920410156,
      "learning_rate": 6.732266804778059e-05,
      "loss": 0.2071,
      "mean_token_accuracy": 0.9117343664169312,
      "num_tokens": 40499386.0,
      "step": 255
    },
    {
      "epoch": 0.2495201535508637,
      "grad_norm": 0.8436290621757507,
      "learning_rate": 6.704861932379685e-05,
      "loss": 0.2021,
      "mean_token_accuracy": 0.9147255301475525,
      "num_tokens": 41305685.0,
      "step": 260
    },
    {
      "epoch": 0.2543186180422265,
      "grad_norm": 0.47678083181381226,
      "learning_rate": 6.676943546263647e-05,
      "loss": 0.2084,
      "mean_token_accuracy": 0.9162402510643005,
      "num_tokens": 42099299.0,
      "step": 265
    },
    {
      "epoch": 0.2591170825335892,
      "grad_norm": 0.6068950295448303,
      "learning_rate": 6.648518439440924e-05,
      "loss": 0.2101,
      "mean_token_accuracy": 0.9077034235000611,
      "num_tokens": 42916607.0,
      "step": 270
    },
    {
      "epoch": 0.263915547024952,
      "grad_norm": 0.49654993414878845,
      "learning_rate": 6.619593528216123e-05,
      "loss": 0.2048,
      "mean_token_accuracy": 0.9157393455505372,
      "num_tokens": 43714272.0,
      "step": 275
    },
    {
      "epoch": 0.2687140115163148,
      "grad_norm": 0.7558993697166443,
      "learning_rate": 6.590175850504635e-05,
      "loss": 0.2071,
      "mean_token_accuracy": 0.9156303167343139,
      "num_tokens": 44506596.0,
      "step": 280
    },
    {
      "epoch": 0.27351247600767753,
      "grad_norm": 0.4323616623878479,
      "learning_rate": 6.560272564120192e-05,
      "loss": 0.1981,
      "mean_token_accuracy": 0.9156986951828003,
      "num_tokens": 45282564.0,
      "step": 285
    },
    {
      "epoch": 0.2783109404990403,
      "grad_norm": 0.3599900007247925,
      "learning_rate": 6.52989094503325e-05,
      "loss": 0.2077,
      "mean_token_accuracy": 0.9143546223640442,
      "num_tokens": 46098513.0,
      "step": 290
    },
    {
      "epoch": 0.28310940499040305,
      "grad_norm": 0.33340930938720703,
      "learning_rate": 6.499038385600624e-05,
      "loss": 0.1938,
      "mean_token_accuracy": 0.9212781906127929,
      "num_tokens": 46887829.0,
      "step": 295
    },
    {
      "epoch": 0.28790786948176583,
      "grad_norm": 0.306796133518219,
      "learning_rate": 6.467722392766801e-05,
      "loss": 0.1959,
      "mean_token_accuracy": 0.9193766951560974,
      "num_tokens": 47691699.0,
      "step": 300
    },
    {
      "epoch": 0.2927063339731286,
      "grad_norm": 0.3488706648349762,
      "learning_rate": 6.435950586237382e-05,
      "loss": 0.2066,
      "mean_token_accuracy": 0.9102665543556213,
      "num_tokens": 48486193.0,
      "step": 305
    },
    {
      "epoch": 0.29750479846449135,
      "grad_norm": 0.5964604020118713,
      "learning_rate": 6.403730696625067e-05,
      "loss": 0.1893,
      "mean_token_accuracy": 0.9162996411323547,
      "num_tokens": 49288543.0,
      "step": 310
    },
    {
      "epoch": 0.30230326295585414,
      "grad_norm": 0.3607555627822876,
      "learning_rate": 6.371070563568684e-05,
      "loss": 0.1923,
      "mean_token_accuracy": 0.9159826397895813,
      "num_tokens": 50087277.0,
      "step": 315
    },
    {
      "epoch": 0.30710172744721687,
      "grad_norm": 0.5310798287391663,
      "learning_rate": 6.337978133825659e-05,
      "loss": 0.1871,
      "mean_token_accuracy": 0.9196419477462768,
      "num_tokens": 50868001.0,
      "step": 320
    },
    {
      "epoch": 0.31190019193857965,
      "grad_norm": 0.5248069167137146,
      "learning_rate": 6.304461459338445e-05,
      "loss": 0.2029,
      "mean_token_accuracy": 0.9152723550796509,
      "num_tokens": 51662419.0,
      "step": 325
    },
    {
      "epoch": 0.31669865642994244,
      "grad_norm": 0.3722710907459259,
      "learning_rate": 6.270528695275349e-05,
      "loss": 0.201,
      "mean_token_accuracy": 0.91062912940979,
      "num_tokens": 52446100.0,
      "step": 330
    },
    {
      "epoch": 0.32149712092130517,
      "grad_norm": 0.36808404326438904,
      "learning_rate": 6.236188098046236e-05,
      "loss": 0.2001,
      "mean_token_accuracy": 0.9152203679084778,
      "num_tokens": 53244169.0,
      "step": 335
    },
    {
      "epoch": 0.32629558541266795,
      "grad_norm": 0.25250986218452454,
      "learning_rate": 6.201448023293617e-05,
      "loss": 0.2013,
      "mean_token_accuracy": 0.911141550540924,
      "num_tokens": 54040490.0,
      "step": 340
    },
    {
      "epoch": 0.3310940499040307,
      "grad_norm": 0.31841546297073364,
      "learning_rate": 6.166316923859576e-05,
      "loss": 0.2054,
      "mean_token_accuracy": 0.9115605592727661,
      "num_tokens": 54866178.0,
      "step": 345
    },
    {
      "epoch": 0.33589251439539347,
      "grad_norm": 26.990447998046875,
      "learning_rate": 6.130803347729047e-05,
      "loss": 0.1908,
      "mean_token_accuracy": 0.9202599406242371,
      "num_tokens": 55653730.0,
      "step": 350
    },
    {
      "epoch": 0.34069097888675626,
      "grad_norm": 0.30666667222976685,
      "learning_rate": 6.094915935949953e-05,
      "loss": 0.1885,
      "mean_token_accuracy": 0.9189923286437989,
      "num_tokens": 56444777.0,
      "step": 355
    },
    {
      "epoch": 0.345489443378119,
      "grad_norm": 0.4795357882976532,
      "learning_rate": 6.0586634205306915e-05,
      "loss": 0.1956,
      "mean_token_accuracy": 0.9183237552642822,
      "num_tokens": 57253377.0,
      "step": 360
    },
    {
      "epoch": 0.3502879078694818,
      "grad_norm": 0.23285166919231415,
      "learning_rate": 6.022054622315494e-05,
      "loss": 0.1871,
      "mean_token_accuracy": 0.9199147820472717,
      "num_tokens": 58042662.0,
      "step": 365
    },
    {
      "epoch": 0.3550863723608445,
      "grad_norm": 0.4314901530742645,
      "learning_rate": 5.9850984488381596e-05,
      "loss": 0.1962,
      "mean_token_accuracy": 0.9169607877731323,
      "num_tokens": 58831799.0,
      "step": 370
    },
    {
      "epoch": 0.3598848368522073,
      "grad_norm": 0.3640917241573334,
      "learning_rate": 5.94780389215471e-05,
      "loss": 0.1933,
      "mean_token_accuracy": 0.9174081683158875,
      "num_tokens": 59645117.0,
      "step": 375
    },
    {
      "epoch": 0.3646833013435701,
      "grad_norm": 0.2740689516067505,
      "learning_rate": 5.910180026655467e-05,
      "loss": 0.1907,
      "mean_token_accuracy": 0.9203463912010192,
      "num_tokens": 60430338.0,
      "step": 380
    },
    {
      "epoch": 0.3694817658349328,
      "grad_norm": 0.2786269783973694,
      "learning_rate": 5.872236006857106e-05,
      "loss": 0.185,
      "mean_token_accuracy": 0.9187370657920837,
      "num_tokens": 61209084.0,
      "step": 385
    },
    {
      "epoch": 0.3742802303262956,
      "grad_norm": 0.24551868438720703,
      "learning_rate": 5.833981065175203e-05,
      "loss": 0.1857,
      "mean_token_accuracy": 0.9178588390350342,
      "num_tokens": 62007757.0,
      "step": 390
    },
    {
      "epoch": 0.3790786948176583,
      "grad_norm": 0.6173501014709473,
      "learning_rate": 5.7954245096778384e-05,
      "loss": 0.189,
      "mean_token_accuracy": 0.9154422998428344,
      "num_tokens": 62797095.0,
      "step": 395
    },
    {
      "epoch": 0.3838771593090211,
      "grad_norm": 0.22034378349781036,
      "learning_rate": 5.756575721820784e-05,
      "loss": 0.2012,
      "mean_token_accuracy": 0.909715449810028,
      "num_tokens": 63594142.0,
      "step": 400
    },
    {
      "epoch": 0.3886756238003839,
      "grad_norm": 0.39530545473098755,
      "learning_rate": 5.717444154164841e-05,
      "loss": 0.1912,
      "mean_token_accuracy": 0.9185901284217834,
      "num_tokens": 64395013.0,
      "step": 405
    },
    {
      "epoch": 0.3934740882917466,
      "grad_norm": 0.5130671262741089,
      "learning_rate": 5.678039328075872e-05,
      "loss": 0.2055,
      "mean_token_accuracy": 0.9089265704154968,
      "num_tokens": 65183834.0,
      "step": 410
    },
    {
      "epoch": 0.3982725527831094,
      "grad_norm": 0.25764885544776917,
      "learning_rate": 5.638370831408094e-05,
      "loss": 0.201,
      "mean_token_accuracy": 0.9145246505737304,
      "num_tokens": 65971151.0,
      "step": 415
    },
    {
      "epoch": 0.40307101727447214,
      "grad_norm": 1.2055509090423584,
      "learning_rate": 5.5984483161711884e-05,
      "loss": 0.2015,
      "mean_token_accuracy": 0.9111255884170533,
      "num_tokens": 66785774.0,
      "step": 420
    },
    {
      "epoch": 0.40786948176583493,
      "grad_norm": 0.25073662400245667,
      "learning_rate": 5.5582814961818154e-05,
      "loss": 0.1953,
      "mean_token_accuracy": 0.9116534113883972,
      "num_tokens": 67574032.0,
      "step": 425
    },
    {
      "epoch": 0.4126679462571977,
      "grad_norm": 0.46643003821372986,
      "learning_rate": 5.5178801447000696e-05,
      "loss": 0.2133,
      "mean_token_accuracy": 0.9100813388824462,
      "num_tokens": 68372777.0,
      "step": 430
    },
    {
      "epoch": 0.41746641074856045,
      "grad_norm": 0.20133262872695923,
      "learning_rate": 5.4772540920514845e-05,
      "loss": 0.1939,
      "mean_token_accuracy": 0.916495680809021,
      "num_tokens": 69170895.0,
      "step": 435
    },
    {
      "epoch": 0.42226487523992323,
      "grad_norm": 0.23032309114933014,
      "learning_rate": 5.4364132232351584e-05,
      "loss": 0.2009,
      "mean_token_accuracy": 0.9147676229476929,
      "num_tokens": 69973680.0,
      "step": 440
    },
    {
      "epoch": 0.42706333973128596,
      "grad_norm": 0.33535414934158325,
      "learning_rate": 5.395367475518553e-05,
      "loss": 0.1898,
      "mean_token_accuracy": 0.9177168607711792,
      "num_tokens": 70753938.0,
      "step": 445
    },
    {
      "epoch": 0.43186180422264875,
      "grad_norm": 0.41969069838523865,
      "learning_rate": 5.3541268360196046e-05,
      "loss": 0.1918,
      "mean_token_accuracy": 0.91667799949646,
      "num_tokens": 71546158.0,
      "step": 450
    },
    {
      "epoch": 0.43666026871401153,
      "grad_norm": 0.20039504766464233,
      "learning_rate": 5.3127013392766776e-05,
      "loss": 0.1955,
      "mean_token_accuracy": 0.9168407678604126,
      "num_tokens": 72367912.0,
      "step": 455
    },
    {
      "epoch": 0.44145873320537427,
      "grad_norm": 0.2675475776195526,
      "learning_rate": 5.271101064807009e-05,
      "loss": 0.1944,
      "mean_token_accuracy": 0.9160084128379822,
      "num_tokens": 73158030.0,
      "step": 460
    }
  ],
  "logging_steps": 5,
  "max_steps": 1042,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 2.2135909642812785e+18,
  "train_batch_size": 24,
  "trial_name": null,
  "trial_params": null
}