{
  "best_global_step": 3000,
  "best_metric": 0.5210983753204346,
  "best_model_checkpoint": "/scratch/gk_checkpoint_lora/checkpoint-3000",
  "epoch": 1.959792477302205,
  "eval_steps": 200,
  "global_step": 3400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 0.8664254155755043,
      "epoch": 0.02882259691598213,
      "grad_norm": 2.775977611541748,
      "learning_rate": 9.800000000000001e-06,
      "loss": 3.2154922485351562,
      "mean_token_accuracy": 0.5048915630578995,
      "num_tokens": 270598.0,
      "step": 50
    },
    {
      "entropy": 1.210615372657776,
      "epoch": 0.05764519383196426,
      "grad_norm": 1.1605831384658813,
      "learning_rate": 1.98e-05,
      "loss": 2.068811798095703,
      "mean_token_accuracy": 0.5692685562372207,
      "num_tokens": 543717.0,
      "step": 100
    },
    {
      "entropy": 0.7421895080804825,
      "epoch": 0.08646779074794639,
      "grad_norm": 0.25959399342536926,
      "learning_rate": 1.9989568984484556e-05,
      "loss": 0.8849951171875,
      "mean_token_accuracy": 0.8145365649461747,
      "num_tokens": 813682.0,
      "step": 150
    },
    {
      "entropy": 0.6125312650203705,
      "epoch": 0.11529038766392852,
      "grad_norm": 0.24997037649154663,
      "learning_rate": 1.9957442896851584e-05,
      "loss": 0.691104507446289,
      "mean_token_accuracy": 0.862597424685955,
      "num_tokens": 1085263.0,
      "step": 200
    },
    {
      "epoch": 0.11529038766392852,
      "eval_entropy": 0.5956721862680033,
      "eval_loss": 0.6279548406600952,
      "eval_mean_token_accuracy": 0.8725619774115713,
      "eval_num_tokens": 1085263.0,
      "eval_runtime": 25.3455,
      "eval_samples_per_second": 59.695,
      "eval_steps_per_second": 7.496,
      "step": 200
    },
    {
      "entropy": 0.6464120636880398,
      "epoch": 0.14411298457991065,
      "grad_norm": 0.2776671051979065,
      "learning_rate": 1.9903687176430222e-05,
      "loss": 0.6937020874023437,
      "mean_token_accuracy": 0.8613211107254028,
      "num_tokens": 1359193.0,
      "step": 250
    },
    {
      "entropy": 0.6303374738991261,
      "epoch": 0.17293558149589278,
      "grad_norm": 0.23006124794483185,
      "learning_rate": 1.9828418591803025e-05,
      "loss": 0.674161376953125,
      "mean_token_accuracy": 0.865567267537117,
      "num_tokens": 1633225.0,
      "step": 300
    },
    {
      "entropy": 0.6267825645208359,
      "epoch": 0.2017581784118749,
      "grad_norm": 0.264813095331192,
      "learning_rate": 1.973180064195894e-05,
      "loss": 0.6597396850585937,
      "mean_token_accuracy": 0.8673095554113388,
      "num_tokens": 1905535.0,
      "step": 350
    },
    {
      "entropy": 0.6219879929721356,
      "epoch": 0.23058077532785703,
      "grad_norm": 0.3037996292114258,
      "learning_rate": 1.9614043201139513e-05,
      "loss": 0.6504788208007812,
      "mean_token_accuracy": 0.868158842921257,
      "num_tokens": 2177042.0,
      "step": 400
    },
    {
      "epoch": 0.23058077532785703,
      "eval_entropy": 0.5888996227791435,
      "eval_loss": 0.5949175357818604,
      "eval_mean_token_accuracy": 0.8765835507919914,
      "eval_num_tokens": 2177042.0,
      "eval_runtime": 25.3953,
      "eval_samples_per_second": 59.578,
      "eval_steps_per_second": 7.482,
      "step": 400
    },
    {
      "entropy": 0.6223398548364639,
      "epoch": 0.2594033722438392,
      "grad_norm": 0.27440914511680603,
      "learning_rate": 1.9475402062948533e-05,
      "loss": 0.6479128265380859,
      "mean_token_accuracy": 0.8684594085812569,
      "num_tokens": 2452073.0,
      "step": 450
    },
    {
      "entropy": 0.610146201401949,
      "epoch": 0.2882259691598213,
      "grad_norm": 0.3176165521144867,
      "learning_rate": 1.9316178384715195e-05,
      "loss": 0.6257384109497071,
      "mean_token_accuracy": 0.8711106261610985,
      "num_tokens": 2724641.0,
      "step": 500
    },
    {
      "entropy": 0.5934953857213259,
      "epoch": 0.31704856607580345,
      "grad_norm": 0.2879047095775604,
      "learning_rate": 1.9136718033317887e-05,
      "loss": 0.6003322601318359,
      "mean_token_accuracy": 0.8751304519176483,
      "num_tokens": 2994313.0,
      "step": 550
    },
    {
      "entropy": 0.5552539291977883,
      "epoch": 0.34587116299178555,
      "grad_norm": 0.31590884923934937,
      "learning_rate": 1.8937410833889517e-05,
      "loss": 0.5751915740966796,
      "mean_token_accuracy": 0.8799619308114052,
      "num_tokens": 3262166.0,
      "step": 600
    },
    {
      "epoch": 0.34587116299178555,
      "eval_entropy": 0.5373091018513629,
      "eval_loss": 0.5472979545593262,
      "eval_mean_token_accuracy": 0.882329721827256,
      "eval_num_tokens": 3262166.0,
      "eval_runtime": 25.4147,
      "eval_samples_per_second": 59.533,
      "eval_steps_per_second": 7.476,
      "step": 600
    },
    {
      "entropy": 0.6037677505612373,
      "epoch": 0.3746937599077677,
      "grad_norm": 0.24785549938678741,
      "learning_rate": 1.871868972303645e-05,
      "loss": 0.6383477020263671,
      "mean_token_accuracy": 0.868063251376152,
      "num_tokens": 3540715.0,
      "step": 650
    },
    {
      "entropy": 0.5363423094898462,
      "epoch": 0.4035163568237498,
      "grad_norm": 0.2744317650794983,
      "learning_rate": 1.848102980841029e-05,
      "loss": 0.5591300964355469,
      "mean_token_accuracy": 0.8841247257590293,
      "num_tokens": 3809747.0,
      "step": 700
    },
    {
      "entropy": 0.5646945191174746,
      "epoch": 0.43233895373973197,
      "grad_norm": 0.22471845149993896,
      "learning_rate": 1.8224947336675485e-05,
      "loss": 0.5917744064331054,
      "mean_token_accuracy": 0.8773607212305069,
      "num_tokens": 4084262.0,
      "step": 750
    },
    {
      "entropy": 0.5565017917752266,
      "epoch": 0.46116155065571407,
      "grad_norm": 0.24923403561115265,
      "learning_rate": 1.79509985721144e-05,
      "loss": 0.581727409362793,
      "mean_token_accuracy": 0.8778996297717094,
      "num_tokens": 4358564.0,
      "step": 800
    },
    {
      "epoch": 0.46116155065571407,
      "eval_entropy": 0.5298120318274749,
      "eval_loss": 0.5324572324752808,
      "eval_mean_token_accuracy": 0.8855449488288478,
      "eval_num_tokens": 4358564.0,
      "eval_runtime": 25.3391,
      "eval_samples_per_second": 59.71,
      "eval_steps_per_second": 7.498,
      "step": 800
    },
    {
      "entropy": 0.5551759076118469,
      "epoch": 0.4899841475716962,
      "grad_norm": 0.2890514135360718,
      "learning_rate": 1.765977858830583e-05,
      "loss": 0.5757025909423829,
      "mean_token_accuracy": 0.8784776413440705,
      "num_tokens": 4631480.0,
      "step": 850
    },
    {
      "entropy": 0.5454864390939475,
      "epoch": 0.5188067444876784,
      "grad_norm": 0.23076863586902618,
      "learning_rate": 1.735191997550167e-05,
      "loss": 0.5680808258056641,
      "mean_token_accuracy": 0.88047192633152,
      "num_tokens": 4904344.0,
      "step": 900
    },
    {
      "entropy": 0.5318841424584388,
      "epoch": 0.5476293414036605,
      "grad_norm": 0.23075300455093384,
      "learning_rate": 1.7028091466509602e-05,
      "loss": 0.555275650024414,
      "mean_token_accuracy": 0.884403744339943,
      "num_tokens": 5172046.0,
      "step": 950
    },
    {
      "entropy": 0.5584682691097259,
      "epoch": 0.5764519383196426,
      "grad_norm": 0.22157496213912964,
      "learning_rate": 1.668899648406662e-05,
      "loss": 0.5754995346069336,
      "mean_token_accuracy": 0.877709536254406,
      "num_tokens": 5445539.0,
      "step": 1000
    },
    {
      "epoch": 0.5764519383196426,
      "eval_entropy": 0.5218244160476484,
      "eval_loss": 0.530579686164856,
      "eval_mean_token_accuracy": 0.8847430721709603,
      "eval_num_tokens": 5445539.0,
      "eval_runtime": 25.2955,
      "eval_samples_per_second": 59.813,
      "eval_steps_per_second": 7.511,
      "step": 1000
    },
    {
      "entropy": 0.5296673697978258,
      "epoch": 0.6052745352356247,
      "grad_norm": 0.2421996146440506,
      "learning_rate": 1.6335371612858827e-05,
      "loss": 0.552278709411621,
      "mean_token_accuracy": 0.884430148601532,
      "num_tokens": 5713428.0,
      "step": 1050
    },
    {
      "entropy": 0.5427714378386735,
      "epoch": 0.6340971321516069,
      "grad_norm": 0.22103162109851837,
      "learning_rate": 1.5967984999506623e-05,
      "loss": 0.5644734954833984,
      "mean_token_accuracy": 0.8810071355104446,
      "num_tokens": 5985117.0,
      "step": 1100
    },
    {
      "entropy": 0.5319583508372306,
      "epoch": 0.662919729067589,
      "grad_norm": 0.25406044721603394,
      "learning_rate": 1.558763468399081e-05,
      "loss": 0.551100959777832,
      "mean_token_accuracy": 0.8851462480425835,
      "num_tokens": 6254015.0,
      "step": 1150
    },
    {
      "entropy": 0.5286855664849281,
      "epoch": 0.6917423259835711,
      "grad_norm": 0.24316425621509552,
      "learning_rate": 1.5195146866144093e-05,
      "loss": 0.5527534484863281,
      "mean_token_accuracy": 0.8843164274096489,
      "num_tokens": 6524236.0,
      "step": 1200
    },
    {
      "epoch": 0.6917423259835711,
      "eval_entropy": 0.5235515671341042,
      "eval_loss": 0.5270145535469055,
      "eval_mean_token_accuracy": 0.8862221178255583,
      "eval_num_tokens": 6524236.0,
      "eval_runtime": 25.2946,
      "eval_samples_per_second": 59.815,
      "eval_steps_per_second": 7.511,
      "step": 1200
    },
    {
      "entropy": 0.5438067949563264,
      "epoch": 0.7205649228995532,
      "grad_norm": 0.2850089967250824,
      "learning_rate": 1.4791374110973555e-05,
      "loss": 0.5662718963623047,
      "mean_token_accuracy": 0.8811582899093628,
      "num_tokens": 6798500.0,
      "step": 1250
    },
    {
      "entropy": 0.5394456747919321,
      "epoch": 0.7493875198155354,
      "grad_norm": 0.2898014783859253,
      "learning_rate": 1.4377193496712517e-05,
      "loss": 0.5550812149047851,
      "mean_token_accuracy": 0.8827075427770614,
      "num_tokens": 7068572.0,
      "step": 1300
    },
    {
      "entropy": 0.5455511239916087,
      "epoch": 0.7782101167315175,
      "grad_norm": 0.22777394950389862,
      "learning_rate": 1.395350470962454e-05,
      "loss": 0.5698577117919922,
      "mean_token_accuracy": 0.8805486962199212,
      "num_tokens": 7338828.0,
      "step": 1350
    },
    {
      "entropy": 0.5357480451464653,
      "epoch": 0.8070327136474996,
      "grad_norm": 0.22745366394519806,
      "learning_rate": 1.3521228089698138e-05,
      "loss": 0.555338134765625,
      "mean_token_accuracy": 0.8834168764948845,
      "num_tokens": 7608634.0,
      "step": 1400
    },
    {
      "epoch": 0.8070327136474996,
      "eval_entropy": 0.5221125764282126,
      "eval_loss": 0.5261030197143555,
      "eval_mean_token_accuracy": 0.8857603835432153,
      "eval_num_tokens": 7608634.0,
      "eval_runtime": 25.3733,
      "eval_samples_per_second": 59.63,
      "eval_steps_per_second": 7.488,
      "step": 1400
    },
    {
      "entropy": 0.5366402574628591,
      "epoch": 0.8358553105634817,
      "grad_norm": 0.3329956531524658,
      "learning_rate": 1.3081302631477272e-05,
      "loss": 0.5528204345703125,
      "mean_token_accuracy": 0.883393512070179,
      "num_tokens": 7876795.0,
      "step": 1450
    },
    {
      "entropy": 0.5442750995606184,
      "epoch": 0.8646779074794639,
      "grad_norm": 0.22092807292938232,
      "learning_rate": 1.263468394437032e-05,
      "loss": 0.5658491897583008,
      "mean_token_accuracy": 0.8810335186123848,
      "num_tokens": 8149031.0,
      "step": 1500
    },
    {
      "entropy": 0.5575385902076959,
      "epoch": 0.893500504395446,
      "grad_norm": 0.22535692155361176,
      "learning_rate": 1.218234217686808e-05,
      "loss": 0.577353744506836,
      "mean_token_accuracy": 0.878656555712223,
      "num_tokens": 8420950.0,
      "step": 1550
    },
    {
      "entropy": 0.5398243299871683,
      "epoch": 0.9223231013114281,
      "grad_norm": 0.2995174527168274,
      "learning_rate": 1.1725259909179875e-05,
      "loss": 0.5575567626953125,
      "mean_token_accuracy": 0.882205625474453,
      "num_tokens": 8690831.0,
      "step": 1600
    },
    {
      "epoch": 0.9223231013114281,
      "eval_entropy": 0.5169236369823155,
      "eval_loss": 0.5248522162437439,
      "eval_mean_token_accuracy": 0.8859441503098137,
      "eval_num_tokens": 8690831.0,
      "eval_runtime": 25.3236,
      "eval_samples_per_second": 59.747,
      "eval_steps_per_second": 7.503,
      "step": 1600
    },
    {
      "entropy": 0.5338192899525166,
      "epoch": 0.9511456982274102,
      "grad_norm": 0.3139007091522217,
      "learning_rate": 1.1264430018865391e-05,
      "loss": 0.5552957916259765,
      "mean_token_accuracy": 0.8834528475999832,
      "num_tokens": 8961415.0,
      "step": 1650
    },
    {
      "entropy": 0.5275231996178626,
      "epoch": 0.9799682951433925,
      "grad_norm": 0.2292962670326233,
      "learning_rate": 1.0800853524098543e-05,
      "loss": 0.5416835021972656,
      "mean_token_accuracy": 0.8851530715823174,
      "num_tokens": 9229637.0,
      "step": 1700
    },
    {
      "entropy": 0.5638248626161461,
      "epoch": 1.0086467790747946,
      "grad_norm": 0.23777392506599426,
      "learning_rate": 1.0335537409248204e-05,
      "loss": 0.5851130676269531,
      "mean_token_accuracy": 0.8776284435286594,
      "num_tokens": 9499446.0,
      "step": 1750
    },
    {
      "entropy": 0.5698649657517671,
      "epoch": 1.0374693759907767,
      "grad_norm": 0.2397402822971344,
      "learning_rate": 9.869492437499167e-06,
      "loss": 0.5934230804443359,
      "mean_token_accuracy": 0.8746954175829887,
      "num_tokens": 9775732.0,
      "step": 1800
    },
    {
      "epoch": 1.0374693759907767,
      "eval_entropy": 0.5189189992452923,
      "eval_loss": 0.5238012671470642,
      "eval_mean_token_accuracy": 0.8859998445761831,
      "eval_num_tokens": 9775732.0,
      "eval_runtime": 25.2908,
      "eval_samples_per_second": 59.824,
      "eval_steps_per_second": 7.513,
      "step": 1800
    },
    {
      "entropy": 0.5613676090538502,
      "epoch": 1.0662919729067588,
      "grad_norm": 0.2651011645793915,
      "learning_rate": 9.403730955264677e-06,
      "loss": 0.5792824935913086,
      "mean_token_accuracy": 0.8779774031043053,
      "num_tokens": 10051416.0,
      "step": 1850
    },
    {
      "entropy": 0.564930793941021,
      "epoch": 1.0951145698227411,
      "grad_norm": 0.2934422194957733,
      "learning_rate": 8.939264693159926e-06,
      "loss": 0.5857321166992188,
      "mean_token_accuracy": 0.8772886765003204,
      "num_tokens": 10325112.0,
      "step": 1900
    },
    {
      "entropy": 0.5554238288849592,
      "epoch": 1.1239371667387232,
      "grad_norm": 0.2599495053291321,
      "learning_rate": 8.477102568313138e-06,
      "loss": 0.5767181015014649,
      "mean_token_accuracy": 0.8785749426484109,
      "num_tokens": 10599513.0,
      "step": 1950
    },
    {
      "entropy": 0.5364625386148691,
      "epoch": 1.1527597636547053,
      "grad_norm": 0.2258245348930359,
      "learning_rate": 8.01824849278814e-06,
      "loss": 0.555483169555664,
      "mean_token_accuracy": 0.883213449716568,
      "num_tokens": 10869586.0,
      "step": 2000
    },
    {
      "epoch": 1.1527597636547053,
      "eval_entropy": 0.519798114582112,
      "eval_loss": 0.5227712988853455,
      "eval_mean_token_accuracy": 0.8866353715720929,
      "eval_num_tokens": 10869586.0,
      "eval_runtime": 25.2263,
      "eval_samples_per_second": 59.977,
      "eval_steps_per_second": 7.532,
      "step": 2000
    },
    {
      "entropy": 0.5413903272151948,
      "epoch": 1.1815823605706874,
      "grad_norm": 0.2601049542427063,
      "learning_rate": 7.5636991928790226e-06,
      "loss": 0.5650748443603516,
      "mean_token_accuracy": 0.8822926163673401,
      "num_tokens": 11142115.0,
      "step": 2050
    },
    {
      "entropy": 0.5441782039403915,
      "epoch": 1.2104049574866695,
      "grad_norm": 0.23305267095565796,
      "learning_rate": 7.1144420440136945e-06,
      "loss": 0.5608541870117187,
      "mean_token_accuracy": 0.8806314519047738,
      "num_tokens": 11414459.0,
      "step": 2100
    },
    {
      "entropy": 0.5373694878071547,
      "epoch": 1.2392275544026516,
      "grad_norm": 0.2710422873497009,
      "learning_rate": 6.671452925969549e-06,
      "loss": 0.5601076126098633,
      "mean_token_accuracy": 0.8817597103118896,
      "num_tokens": 11686439.0,
      "step": 2150
    },
    {
      "entropy": 0.5512064357846975,
      "epoch": 1.2680501513186337,
      "grad_norm": 0.24875891208648682,
      "learning_rate": 6.2356941030600036e-06,
      "loss": 0.572663803100586,
      "mean_token_accuracy": 0.8795112228393555,
      "num_tokens": 11959949.0,
      "step": 2200
    },
    {
      "epoch": 1.2680501513186337,
      "eval_entropy": 0.5157758243774113,
      "eval_loss": 0.5222153663635254,
      "eval_mean_token_accuracy": 0.8866087377071381,
      "eval_num_tokens": 11959949.0,
      "eval_runtime": 25.3435,
      "eval_samples_per_second": 59.7,
      "eval_steps_per_second": 7.497,
      "step": 2200
    },
    {
      "entropy": 0.5333986005187035,
      "epoch": 1.296872748234616,
      "grad_norm": 0.2774944603443146,
      "learning_rate": 5.808112133896682e-06,
      "loss": 0.5507477569580078,
      "mean_token_accuracy": 0.8833928933739662,
      "num_tokens": 12230467.0,
      "step": 2250
    },
    {
      "entropy": 0.5385575620830059,
      "epoch": 1.325695345150598,
      "grad_norm": 0.24219754338264465,
      "learning_rate": 5.38963581526766e-06,
      "loss": 0.5618357849121094,
      "mean_token_accuracy": 0.8824037438631058,
      "num_tokens": 12500631.0,
      "step": 2300
    },
    {
      "entropy": 0.5562852944433689,
      "epoch": 1.3545179420665803,
      "grad_norm": 0.23605461418628693,
      "learning_rate": 4.981174164598023e-06,
      "loss": 0.5740032577514649,
      "mean_token_accuracy": 0.8787400788068771,
      "num_tokens": 12773793.0,
      "step": 2350
    },
    {
      "entropy": 0.5452473207563162,
      "epoch": 1.3833405389825624,
      "grad_norm": 0.23601187765598297,
      "learning_rate": 4.5836144453753595e-06,
      "loss": 0.5657626724243164,
      "mean_token_accuracy": 0.8807224997878075,
      "num_tokens": 13046257.0,
      "step": 2400
    },
    {
      "epoch": 1.3833405389825624,
      "eval_entropy": 0.5180542894884159,
      "eval_loss": 0.5217919945716858,
      "eval_mean_token_accuracy": 0.8867926757586629,
      "eval_num_tokens": 13046257.0,
      "eval_runtime": 25.2941,
      "eval_samples_per_second": 59.816,
      "eval_steps_per_second": 7.512,
      "step": 2400
    },
    {
      "entropy": 0.5406669420003891,
      "epoch": 1.4121631358985445,
      "grad_norm": 0.27414751052856445,
      "learning_rate": 4.197820239829295e-06,
      "loss": 0.5581526184082031,
      "mean_token_accuracy": 0.8821376091241837,
      "num_tokens": 13318117.0,
      "step": 2450
    },
    {
      "entropy": 0.5123971965163946,
      "epoch": 1.4409857328145266,
      "grad_norm": 0.27002713084220886,
      "learning_rate": 3.8246295730516455e-06,
      "loss": 0.5292396545410156,
      "mean_token_accuracy": 0.8868949916958809,
      "num_tokens": 13585112.0,
      "step": 2500
    },
    {
      "entropy": 0.5250877778977155,
      "epoch": 1.4698083297305087,
      "grad_norm": 0.2513103187084198,
      "learning_rate": 3.4648530926319634e-06,
      "loss": 0.5443946075439453,
      "mean_token_accuracy": 0.8851349979639054,
      "num_tokens": 13854892.0,
      "step": 2550
    },
    {
      "entropy": 0.5314137779176236,
      "epoch": 1.4986309266464908,
      "grad_norm": 0.21981389820575714,
      "learning_rate": 3.1192723077627163e-06,
      "loss": 0.5500518798828125,
      "mean_token_accuracy": 0.8838223886489868,
      "num_tokens": 14126513.0,
      "step": 2600
    },
    {
      "epoch": 1.4986309266464908,
      "eval_entropy": 0.5145505380473638,
      "eval_loss": 0.5215311050415039,
      "eval_mean_token_accuracy": 0.8864174689117231,
      "eval_num_tokens": 14126513.0,
      "eval_runtime": 25.2961,
      "eval_samples_per_second": 59.812,
      "eval_steps_per_second": 7.511,
      "step": 2600
    },
    {
      "entropy": 0.5299251443892717,
      "epoch": 1.5274535235624729,
      "grad_norm": 0.2680607736110687,
      "learning_rate": 2.78863789163911e-06,
      "loss": 0.5511317825317383,
      "mean_token_accuracy": 0.8838860777020454,
      "num_tokens": 14396535.0,
      "step": 2650
    },
    {
      "entropy": 0.5394382092356682,
      "epoch": 1.5562761204784552,
      "grad_norm": 0.25587576627731323,
      "learning_rate": 2.4736680508410902e-06,
      "loss": 0.5560498809814454,
      "mean_token_accuracy": 0.8820542943477631,
      "num_tokens": 14666012.0,
      "step": 2700
    },
    {
      "entropy": 0.5438171474635601,
      "epoch": 1.585098717394437,
      "grad_norm": 0.22950419783592224,
      "learning_rate": 2.1750469652395777e-06,
      "loss": 0.5646057891845703,
      "mean_token_accuracy": 0.8806953200697899,
      "num_tokens": 14938072.0,
      "step": 2750
    },
    {
      "entropy": 0.5157144083827734,
      "epoch": 1.6139213143104194,
      "grad_norm": 0.23236404359340668,
      "learning_rate": 1.8934233018157822e-06,
      "loss": 0.5314432525634766,
      "mean_token_accuracy": 0.8868013408780098,
      "num_tokens": 15206239.0,
      "step": 2800
    },
    {
      "epoch": 1.6139213143104194,
      "eval_entropy": 0.514612096783362,
      "eval_loss": 0.5212787985801697,
      "eval_mean_token_accuracy": 0.8865814996393103,
      "eval_num_tokens": 15206239.0,
      "eval_runtime": 25.284,
      "eval_samples_per_second": 59.84,
      "eval_steps_per_second": 7.515,
      "step": 2800
    },
    {
      "entropy": 0.5607952538132668,
      "epoch": 1.6427439112264015,
      "grad_norm": 0.27139943838119507,
      "learning_rate": 1.6294088056218705e-06,
      "loss": 0.5802758026123047,
      "mean_token_accuracy": 0.8771729645133018,
      "num_tokens": 15479383.0,
      "step": 2850
    },
    {
      "entropy": 0.5458529234677553,
      "epoch": 1.6715665081423836,
      "grad_norm": 0.22497807443141937,
      "learning_rate": 1.3835769709437307e-06,
      "loss": 0.5699198913574218,
      "mean_token_accuracy": 0.8804216027259827,
      "num_tokens": 15754571.0,
      "step": 2900
    },
    {
      "entropy": 0.5275375150889158,
      "epoch": 1.7003891050583657,
      "grad_norm": 0.25096791982650757,
      "learning_rate": 1.1564617955523716e-06,
      "loss": 0.5493584060668946,
      "mean_token_accuracy": 0.8840730246901513,
      "num_tokens": 16024591.0,
      "step": 2950
    },
    {
      "entropy": 0.529434435814619,
      "epoch": 1.7292117019743478,
      "grad_norm": 0.20803657174110413,
      "learning_rate": 9.485566207498986e-07,
      "loss": 0.552624740600586,
      "mean_token_accuracy": 0.8842183569073677,
      "num_tokens": 16291960.0,
      "step": 3000
    },
    {
      "epoch": 1.7292117019743478,
      "eval_entropy": 0.5173903987595909,
      "eval_loss": 0.5210983753204346,
      "eval_mean_token_accuracy": 0.8867466380721645,
      "eval_num_tokens": 16291960.0,
      "eval_runtime": 25.2973,
      "eval_samples_per_second": 59.809,
      "eval_steps_per_second": 7.511,
      "step": 3000
    },
    {
      "entropy": 0.5379937102645636,
      "epoch": 1.7580342988903301,
      "grad_norm": 0.279082715511322,
      "learning_rate": 7.603130597298147e-07,
      "loss": 0.5518331146240234,
      "mean_token_accuracy": 0.8835244515538215,
      "num_tokens": 16562192.0,
      "step": 3050
    },
    {
      "entropy": 0.5540396096557378,
      "epoch": 1.786856895806312,
      "grad_norm": 0.23533675074577332,
      "learning_rate": 5.921400165794255e-07,
      "loss": 0.5790340423583984,
      "mean_token_accuracy": 0.8788801202178002,
      "num_tokens": 16834646.0,
      "step": 3100
    },
    {
      "entropy": 0.5152763035148382,
      "epoch": 1.8156794927222943,
      "grad_norm": 0.2803124487400055,
      "learning_rate": 4.444027980552901e-07,
      "loss": 0.5328571701049805,
      "mean_token_accuracy": 0.8869862693548203,
      "num_tokens": 17104758.0,
      "step": 3150
    },
    {
      "entropy": 0.5612848294526338,
      "epoch": 1.8445020896382764,
      "grad_norm": 0.26171237230300903,
      "learning_rate": 3.1742232006111374e-07,
      "loss": 0.5824931716918945,
      "mean_token_accuracy": 0.8772889456152916,
      "num_tokens": 17379954.0,
      "step": 3200
    },
    {
      "epoch": 1.8445020896382764,
      "eval_entropy": 0.516960418381189,
      "eval_loss": 0.5211681723594666,
      "eval_mean_token_accuracy": 0.8866549037004772,
      "eval_num_tokens": 17379954.0,
      "eval_runtime": 25.3046,
      "eval_samples_per_second": 59.791,
      "eval_steps_per_second": 7.509,
      "step": 3200
    },
    {
      "entropy": 0.5196366369724273,
      "epoch": 1.8733246865542585,
      "grad_norm": 0.6400351524353027,
      "learning_rate": 2.1147441055180074e-07,
      "loss": 0.5364640808105469,
      "mean_token_accuracy": 0.8855624732375145,
      "num_tokens": 17647943.0,
      "step": 3250
    },
    {
      "entropy": 0.5125804611295461,
      "epoch": 1.9021472834702406,
      "grad_norm": 0.24278956651687622,
      "learning_rate": 1.2678921037788118e-07,
      "loss": 0.5320493316650391,
      "mean_token_accuracy": 0.8888507178425789,
      "num_tokens": 17914413.0,
      "step": 3300
    },
    {
      "entropy": 0.5364588350057602,
      "epoch": 1.9309698803862227,
      "grad_norm": 0.2414465695619583,
      "learning_rate": 6.355067337181497e-08,
      "loss": 0.5448334121704101,
      "mean_token_accuracy": 0.8835894984006881,
      "num_tokens": 18184605.0,
      "step": 3350
    },
    {
      "entropy": 0.5623560689389706,
      "epoch": 1.959792477302205,
      "grad_norm": 0.31695693731307983,
      "learning_rate": 2.189616676208428e-08,
      "loss": 0.5812443923950196,
      "mean_token_accuracy": 0.877460196018219,
      "num_tokens": 18459900.0,
      "step": 3400
    },
    {
      "epoch": 1.959792477302205,
      "eval_entropy": 0.5174976312016186,
      "eval_loss": 0.5211665630340576,
      "eval_mean_token_accuracy": 0.8866490850323125,
      "eval_num_tokens": 18459900.0,
      "eval_runtime": 25.3065,
      "eval_samples_per_second": 59.787,
      "eval_steps_per_second": 7.508,
      "step": 3400
    }
  ],
  "logging_steps": 50,
  "max_steps": 3470,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.001481583701156e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}