{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 1250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 4.869012355804443,
      "learning_rate": 1.5873015873015872e-05,
      "loss": 1.1684,
      "step": 10
    },
    {
      "epoch": 0.16,
      "grad_norm": 5.065932750701904,
      "learning_rate": 3.1746031746031745e-05,
      "loss": 0.6254,
      "step": 20
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.7544628381729126,
      "learning_rate": 4.761904761904762e-05,
      "loss": 0.3667,
      "step": 30
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.402125597000122,
      "learning_rate": 6.349206349206349e-05,
      "loss": 0.2619,
      "step": 40
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.5777990818023682,
      "learning_rate": 7.936507936507937e-05,
      "loss": 0.211,
      "step": 50
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.0018945932388306,
      "learning_rate": 9.523809523809524e-05,
      "loss": 0.1758,
      "step": 60
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.201993465423584,
      "learning_rate": 9.999141931470729e-05,
      "loss": 0.1447,
      "step": 70
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.9454079866409302,
      "learning_rate": 9.994939855811362e-05,
      "loss": 0.1282,
      "step": 80
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.1873888969421387,
      "learning_rate": 9.987239108233668e-05,
      "loss": 0.1169,
      "step": 90
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.8586097359657288,
      "learning_rate": 9.976045082674319e-05,
      "loss": 0.105,
      "step": 100
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.0581028461456299,
      "learning_rate": 9.961365619912989e-05,
      "loss": 0.1102,
      "step": 110
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.5893928408622742,
      "learning_rate": 9.94321100208032e-05,
      "loss": 0.1056,
      "step": 120
    },
    {
      "epoch": 1.04,
      "grad_norm": 1.3466310501098633,
      "learning_rate": 9.921593945455869e-05,
      "loss": 0.0826,
      "step": 130
    },
    {
      "epoch": 1.12,
      "grad_norm": 1.1419179439544678,
      "learning_rate": 9.896529591561093e-05,
      "loss": 0.0899,
      "step": 140
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.5349047183990479,
      "learning_rate": 9.868035496553546e-05,
      "loss": 0.0823,
      "step": 150
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.6395344734191895,
      "learning_rate": 9.836131618929819e-05,
      "loss": 0.0816,
      "step": 160
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.7662268877029419,
      "learning_rate": 9.800840305545715e-05,
      "loss": 0.0773,
      "step": 170
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.6182479858398438,
      "learning_rate": 9.762186275963563e-05,
      "loss": 0.0667,
      "step": 180
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.28476619720458984,
      "learning_rate": 9.720196605137565e-05,
      "loss": 0.0662,
      "step": 190
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.528924286365509,
      "learning_rate": 9.674900704449324e-05,
      "loss": 0.0699,
      "step": 200
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.420554518699646,
      "learning_rate": 9.626330301106837e-05,
      "loss": 0.0624,
      "step": 210
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.40601664781570435,
      "learning_rate": 9.574519415921396e-05,
      "loss": 0.0631,
      "step": 220
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.4216195046901703,
      "learning_rate": 9.519504339477932e-05,
      "loss": 0.064,
      "step": 230
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.35759010910987854,
      "learning_rate": 9.46132360671552e-05,
      "loss": 0.0645,
      "step": 240
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7622753977775574,
      "learning_rate": 9.400017969935848e-05,
      "loss": 0.0558,
      "step": 250
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.6483420729637146,
      "learning_rate": 9.335630370258533e-05,
      "loss": 0.061,
      "step": 260
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.6169353723526001,
      "learning_rate": 9.26820590754331e-05,
      "loss": 0.0553,
      "step": 270
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.6126364469528198,
      "learning_rate": 9.197791808800135e-05,
      "loss": 0.0552,
      "step": 280
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.45238834619522095,
      "learning_rate": 9.124437395109353e-05,
      "loss": 0.051,
      "step": 290
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.4955156743526459,
      "learning_rate": 9.048194047075069e-05,
      "loss": 0.0556,
      "step": 300
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.7795207500457764,
      "learning_rate": 8.969115168835954e-05,
      "loss": 0.0573,
      "step": 310
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.4718877971172333,
      "learning_rate": 8.887256150658684e-05,
      "loss": 0.0473,
      "step": 320
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.3217944800853729,
      "learning_rate": 8.802674330140192e-05,
      "loss": 0.0499,
      "step": 330
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 0.4460347592830658,
      "learning_rate": 8.715428952045936e-05,
      "loss": 0.0553,
      "step": 340
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.3968408703804016,
      "learning_rate": 8.625581126812312e-05,
      "loss": 0.0512,
      "step": 350
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.32385963201522827,
      "learning_rate": 8.533193787742251e-05,
      "loss": 0.0514,
      "step": 360
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.5356223583221436,
      "learning_rate": 8.438331646924013e-05,
      "loss": 0.0463,
      "step": 370
    },
    {
      "epoch": 3.04,
      "grad_norm": 0.6326996088027954,
      "learning_rate": 8.341061149904045e-05,
      "loss": 0.0465,
      "step": 380
    },
    {
      "epoch": 3.12,
      "grad_norm": 0.547283411026001,
      "learning_rate": 8.24145042914565e-05,
      "loss": 0.0505,
      "step": 390
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.4946414828300476,
      "learning_rate": 8.13956925630605e-05,
      "loss": 0.0416,
      "step": 400
    },
    {
      "epoch": 3.2800000000000002,
      "grad_norm": 0.24442224204540253,
      "learning_rate": 8.035488993365312e-05,
      "loss": 0.0464,
      "step": 410
    },
    {
      "epoch": 3.36,
      "grad_norm": 0.4730175733566284,
      "learning_rate": 7.929282542641325e-05,
      "loss": 0.0444,
      "step": 420
    },
    {
      "epoch": 3.44,
      "grad_norm": 0.2920738458633423,
      "learning_rate": 7.821024295725865e-05,
      "loss": 0.0467,
      "step": 430
    },
    {
      "epoch": 3.52,
      "grad_norm": 0.2938491106033325,
      "learning_rate": 7.710790081377502e-05,
      "loss": 0.0425,
      "step": 440
    },
    {
      "epoch": 3.6,
      "grad_norm": 0.41461989283561707,
      "learning_rate": 7.598657112407865e-05,
      "loss": 0.0413,
      "step": 450
    },
    {
      "epoch": 3.68,
      "grad_norm": 0.36295655369758606,
      "learning_rate": 7.484703931598445e-05,
      "loss": 0.0384,
      "step": 460
    },
    {
      "epoch": 3.76,
      "grad_norm": 0.38623902201652527,
      "learning_rate": 7.369010356685833e-05,
      "loss": 0.0418,
      "step": 470
    },
    {
      "epoch": 3.84,
      "grad_norm": 0.4889287054538727,
      "learning_rate": 7.251657424453928e-05,
      "loss": 0.044,
      "step": 480
    },
    {
      "epoch": 3.92,
      "grad_norm": 0.4019559919834137,
      "learning_rate": 7.132727333972265e-05,
      "loss": 0.0368,
      "step": 490
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.0160191059112549,
      "learning_rate": 7.012303389020234e-05,
      "loss": 0.0495,
      "step": 500
    },
    {
      "epoch": 4.08,
      "grad_norm": 0.3743612766265869,
      "learning_rate": 6.890469939737506e-05,
      "loss": 0.04,
      "step": 510
    },
    {
      "epoch": 4.16,
      "grad_norm": 0.306122362613678,
      "learning_rate": 6.767312323541555e-05,
      "loss": 0.0393,
      "step": 520
    },
    {
      "epoch": 4.24,
      "grad_norm": 0.5479507446289062,
      "learning_rate": 6.64291680535363e-05,
      "loss": 0.0394,
      "step": 530
    },
    {
      "epoch": 4.32,
      "grad_norm": 0.3650203049182892,
      "learning_rate": 6.517370517175081e-05,
      "loss": 0.0456,
      "step": 540
    },
    {
      "epoch": 4.4,
      "grad_norm": 0.31947705149650574,
      "learning_rate": 6.390761397056328e-05,
      "loss": 0.0331,
      "step": 550
    },
    {
      "epoch": 4.48,
      "grad_norm": 0.8813490271568298,
      "learning_rate": 6.26317812750126e-05,
      "loss": 0.0395,
      "step": 560
    },
    {
      "epoch": 4.5600000000000005,
      "grad_norm": 0.21433396637439728,
      "learning_rate": 6.134710073350156e-05,
      "loss": 0.0402,
      "step": 570
    },
    {
      "epoch": 4.64,
      "grad_norm": 0.2874234616756439,
      "learning_rate": 6.005447219184702e-05,
      "loss": 0.038,
      "step": 580
    },
    {
      "epoch": 4.72,
      "grad_norm": 0.3092989921569824,
      "learning_rate": 5.87548010629889e-05,
      "loss": 0.0355,
      "step": 590
    },
    {
      "epoch": 4.8,
      "grad_norm": 0.3180033564567566,
      "learning_rate": 5.7448997692799764e-05,
      "loss": 0.0407,
      "step": 600
    },
    {
      "epoch": 4.88,
      "grad_norm": 0.5046788454055786,
      "learning_rate": 5.61379767224393e-05,
      "loss": 0.0384,
      "step": 610
    },
    {
      "epoch": 4.96,
      "grad_norm": 0.2650161385536194,
      "learning_rate": 5.482265644769998e-05,
      "loss": 0.0371,
      "step": 620
    },
    {
      "epoch": 5.04,
      "grad_norm": 0.264657586812973,
      "learning_rate": 5.3503958175793055e-05,
      "loss": 0.0399,
      "step": 630
    },
    {
      "epoch": 5.12,
      "grad_norm": 0.3759991526603699,
      "learning_rate": 5.218280558002506e-05,
      "loss": 0.0326,
      "step": 640
    },
    {
      "epoch": 5.2,
      "grad_norm": 0.48156824707984924,
      "learning_rate": 5.086012405281717e-05,
      "loss": 0.0384,
      "step": 650
    },
    {
      "epoch": 5.28,
      "grad_norm": 0.4213162064552307,
      "learning_rate": 4.9536840057520224e-05,
      "loss": 0.0384,
      "step": 660
    },
    {
      "epoch": 5.36,
      "grad_norm": 0.41504690051078796,
      "learning_rate": 4.821388047947979e-05,
      "loss": 0.0373,
      "step": 670
    },
    {
      "epoch": 5.44,
      "grad_norm": 0.24580952525138855,
      "learning_rate": 4.689217197680554e-05,
      "loss": 0.0339,
      "step": 680
    },
    {
      "epoch": 5.52,
      "grad_norm": 0.35898831486701965,
      "learning_rate": 4.5572640331299875e-05,
      "loss": 0.033,
      "step": 690
    },
    {
      "epoch": 5.6,
      "grad_norm": 0.39469045400619507,
      "learning_rate": 4.425620980000026e-05,
      "loss": 0.0327,
      "step": 700
    },
    {
      "epoch": 5.68,
      "grad_norm": 0.27831265330314636,
      "learning_rate": 4.294380246778966e-05,
      "loss": 0.037,
      "step": 710
    },
    {
      "epoch": 5.76,
      "grad_norm": 0.2990424633026123,
      "learning_rate": 4.163633760152834e-05,
      "loss": 0.0367,
      "step": 720
    },
    {
      "epoch": 5.84,
      "grad_norm": 0.34065642952919006,
      "learning_rate": 4.03347310061597e-05,
      "loss": 0.0354,
      "step": 730
    },
    {
      "epoch": 5.92,
      "grad_norm": 0.4730483591556549,
      "learning_rate": 3.903989438324077e-05,
      "loss": 0.0349,
      "step": 740
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.24116595089435577,
      "learning_rate": 3.775273469234712e-05,
      "loss": 0.0322,
      "step": 750
    },
    {
      "epoch": 6.08,
      "grad_norm": 0.2788262963294983,
      "learning_rate": 3.6474153515799e-05,
      "loss": 0.0346,
      "step": 760
    },
    {
      "epoch": 6.16,
      "grad_norm": 0.28659942746162415,
      "learning_rate": 3.520504642715424e-05,
      "loss": 0.0367,
      "step": 770
    },
    {
      "epoch": 6.24,
      "grad_norm": 0.28894150257110596,
      "learning_rate": 3.39463023639097e-05,
      "loss": 0.0372,
      "step": 780
    },
    {
      "epoch": 6.32,
      "grad_norm": 0.42454323172569275,
      "learning_rate": 3.2698803004851026e-05,
      "loss": 0.0282,
      "step": 790
    },
    {
      "epoch": 6.4,
      "grad_norm": 0.34259018301963806,
      "learning_rate": 3.1463422152486674e-05,
      "loss": 0.0315,
      "step": 800
    },
    {
      "epoch": 6.48,
      "grad_norm": 0.3654833436012268,
      "learning_rate": 3.024102512099889e-05,
      "loss": 0.0294,
      "step": 810
    },
    {
      "epoch": 6.5600000000000005,
      "grad_norm": 0.26922348141670227,
      "learning_rate": 2.9032468130140168e-05,
      "loss": 0.0274,
      "step": 820
    },
    {
      "epoch": 6.64,
      "grad_norm": 0.2571790814399719,
      "learning_rate": 2.783859770549996e-05,
      "loss": 0.0313,
      "step": 830
    },
    {
      "epoch": 6.72,
      "grad_norm": 0.26845499873161316,
      "learning_rate": 2.6660250085561457e-05,
      "loss": 0.0277,
      "step": 840
    },
    {
      "epoch": 6.8,
      "grad_norm": 0.20030668377876282,
      "learning_rate": 2.54982506359641e-05,
      "loss": 0.0341,
      "step": 850
    },
    {
      "epoch": 6.88,
      "grad_norm": 0.3981160521507263,
      "learning_rate": 2.435341327138168e-05,
      "loss": 0.0293,
      "step": 860
    },
    {
      "epoch": 6.96,
      "grad_norm": 0.3079529106616974,
      "learning_rate": 2.3226539885421343e-05,
      "loss": 0.0311,
      "step": 870
    },
    {
      "epoch": 7.04,
      "grad_norm": 0.15538842976093292,
      "learning_rate": 2.2118419788942672e-05,
      "loss": 0.0297,
      "step": 880
    },
    {
      "epoch": 7.12,
      "grad_norm": 0.35271063446998596,
      "learning_rate": 2.1029829157190117e-05,
      "loss": 0.0311,
      "step": 890
    },
    {
      "epoch": 7.2,
      "grad_norm": 0.3626379668712616,
      "learning_rate": 1.9961530486126327e-05,
      "loss": 0.0318,
      "step": 900
    },
    {
      "epoch": 7.28,
      "grad_norm": 0.32586774230003357,
      "learning_rate": 1.8914272058347088e-05,
      "loss": 0.0285,
      "step": 910
    },
    {
      "epoch": 7.36,
      "grad_norm": 0.23219723999500275,
      "learning_rate": 1.7888787418951645e-05,
      "loss": 0.0276,
      "step": 920
    },
    {
      "epoch": 7.44,
      "grad_norm": 0.2271978110074997,
      "learning_rate": 1.6885794861736183e-05,
      "loss": 0.024,
      "step": 930
    },
    {
      "epoch": 7.52,
      "grad_norm": 0.5763266086578369,
      "learning_rate": 1.5905996926069628e-05,
      "loss": 0.032,
      "step": 940
    },
    {
      "epoch": 7.6,
      "grad_norm": 0.30359622836112976,
      "learning_rate": 1.4950079904804759e-05,
      "loss": 0.0244,
      "step": 950
    },
    {
      "epoch": 7.68,
      "grad_norm": 0.2251555472612381,
      "learning_rate": 1.4018713363569035e-05,
      "loss": 0.0306,
      "step": 960
    },
    {
      "epoch": 7.76,
      "grad_norm": 0.48927322030067444,
      "learning_rate": 1.3112549671771796e-05,
      "loss": 0.0303,
      "step": 970
    },
    {
      "epoch": 7.84,
      "grad_norm": 0.206648051738739,
      "learning_rate": 1.2232223545656552e-05,
      "loss": 0.0294,
      "step": 980
    },
    {
      "epoch": 7.92,
      "grad_norm": 0.3137107193470001,
      "learning_rate": 1.1378351603718312e-05,
      "loss": 0.0298,
      "step": 990
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.47006338834762573,
      "learning_rate": 1.0551531934797243e-05,
      "loss": 0.0319,
      "step": 1000
    },
    {
      "epoch": 8.08,
      "grad_norm": 0.27968037128448486,
      "learning_rate": 9.752343679151399e-06,
      "loss": 0.0233,
      "step": 1010
    },
    {
      "epoch": 8.16,
      "grad_norm": 0.2268412709236145,
      "learning_rate": 8.981346622801905e-06,
      "loss": 0.0285,
      "step": 1020
    },
    {
      "epoch": 8.24,
      "grad_norm": 0.17193864285945892,
      "learning_rate": 8.239080805434513e-06,
      "loss": 0.0297,
      "step": 1030
    },
    {
      "epoch": 8.32,
      "grad_norm": 0.3541881740093231,
      "learning_rate": 7.526066142132521e-06,
      "loss": 0.0228,
      "step": 1040
    },
    {
      "epoch": 8.4,
      "grad_norm": 0.20205742120742798,
      "learning_rate": 6.842802059205727e-06,
      "loss": 0.0252,
      "step": 1050
    },
    {
      "epoch": 8.48,
      "grad_norm": 0.3247056007385254,
      "learning_rate": 6.189767144370645e-06,
      "loss": 0.0233,
      "step": 1060
    },
    {
      "epoch": 8.56,
      "grad_norm": 0.23709805309772491,
      "learning_rate": 5.567418811526981e-06,
      "loss": 0.0256,
      "step": 1070
    },
    {
      "epoch": 8.64,
      "grad_norm": 0.20851150155067444,
      "learning_rate": 4.976192980365124e-06,
      "loss": 0.0283,
      "step": 1080
    },
    {
      "epoch": 8.72,
      "grad_norm": 0.26959723234176636,
      "learning_rate": 4.416503771029201e-06,
      "loss": 0.0255,
      "step": 1090
    },
    {
      "epoch": 8.8,
      "grad_norm": 0.32582834362983704,
      "learning_rate": 3.888743214049346e-06,
      "loss": 0.0256,
      "step": 1100
    },
    {
      "epoch": 8.88,
      "grad_norm": 0.18712686002254486,
      "learning_rate": 3.393280975746588e-06,
      "loss": 0.0228,
      "step": 1110
    },
    {
      "epoch": 8.96,
      "grad_norm": 0.2023114413022995,
      "learning_rate": 2.9304640993025988e-06,
      "loss": 0.0229,
      "step": 1120
    },
    {
      "epoch": 9.04,
      "grad_norm": 0.177691251039505,
      "learning_rate": 2.500616761675578e-06,
      "loss": 0.0238,
      "step": 1130
    },
    {
      "epoch": 9.12,
      "grad_norm": 0.21255093812942505,
      "learning_rate": 2.104040046532768e-06,
      "loss": 0.0282,
      "step": 1140
    },
    {
      "epoch": 9.2,
      "grad_norm": 0.35373473167419434,
      "learning_rate": 1.7410117333583498e-06,
      "loss": 0.0243,
      "step": 1150
    },
    {
      "epoch": 9.28,
      "grad_norm": 0.2814777195453644,
      "learning_rate": 1.4117861028847267e-06,
      "loss": 0.0247,
      "step": 1160
    },
    {
      "epoch": 9.36,
      "grad_norm": 0.2685955762863159,
      "learning_rate": 1.1165937589833087e-06,
      "loss": 0.0262,
      "step": 1170
    },
    {
      "epoch": 9.44,
      "grad_norm": 0.1922096461057663,
      "learning_rate": 8.55641467139534e-07,
      "loss": 0.0266,
      "step": 1180
    },
    {
      "epoch": 9.52,
      "grad_norm": 0.2045939713716507,
      "learning_rate": 6.291120096254433e-07,
      "loss": 0.0234,
      "step": 1190
    },
    {
      "epoch": 9.6,
      "grad_norm": 0.22145062685012817,
      "learning_rate": 4.371640574710345e-07,
      "loss": 0.0232,
      "step": 1200
    },
    {
      "epoch": 9.68,
      "grad_norm": 0.2229902297258377,
      "learning_rate": 2.7993205932420053e-07,
      "loss": 0.0286,
      "step": 1210
    },
    {
      "epoch": 9.76,
      "grad_norm": 0.22045257687568665,
      "learning_rate": 1.5752614727712057e-07,
      "loss": 0.0214,
      "step": 1220
    },
    {
      "epoch": 9.84,
      "grad_norm": 0.2349853515625,
      "learning_rate": 7.003205972494486e-08,
      "loss": 0.024,
      "step": 1230
    },
    {
      "epoch": 9.92,
      "grad_norm": 0.32890427112579346,
      "learning_rate": 1.7511081310922495e-08,
      "loss": 0.0234,
      "step": 1240
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.8977156281471252,
      "learning_rate": 0.0,
      "loss": 0.0235,
      "step": 1250
    },
    {
      "epoch": 10.0,
      "step": 1250,
      "total_flos": 1.7818885277831808e+17,
      "train_loss": 0.06373299721479415,
      "train_runtime": 1560.6933,
      "train_samples_per_second": 50.926,
      "train_steps_per_second": 0.801
    }
  ],
  "logging_steps": 10,
  "max_steps": 1250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7818885277831808e+17,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}