{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9991537376586743,
  "eval_steps": 500,
  "global_step": 1329,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022566995768688293,
      "grad_norm": 0.8098438599918217,
      "learning_rate": 8e-06,
      "loss": 0.762,
      "step": 10
    },
    {
      "epoch": 0.045133991537376586,
      "grad_norm": 0.6681173404835554,
      "learning_rate": 8e-06,
      "loss": 0.6779,
      "step": 20
    },
    {
      "epoch": 0.06770098730606489,
      "grad_norm": 0.6769925589969307,
      "learning_rate": 8e-06,
      "loss": 0.6608,
      "step": 30
    },
    {
      "epoch": 0.09026798307475317,
      "grad_norm": 0.7709936805487797,
      "learning_rate": 8e-06,
      "loss": 0.6386,
      "step": 40
    },
    {
      "epoch": 0.11283497884344147,
      "grad_norm": 0.8475092993138659,
      "learning_rate": 8e-06,
      "loss": 0.6327,
      "step": 50
    },
    {
      "epoch": 0.13540197461212977,
      "grad_norm": 0.6210694244553006,
      "learning_rate": 8e-06,
      "loss": 0.6322,
      "step": 60
    },
    {
      "epoch": 0.15796897038081806,
      "grad_norm": 0.6586422194308651,
      "learning_rate": 8e-06,
      "loss": 0.6278,
      "step": 70
    },
    {
      "epoch": 0.18053596614950634,
      "grad_norm": 0.7853929143077051,
      "learning_rate": 8e-06,
      "loss": 0.6298,
      "step": 80
    },
    {
      "epoch": 0.20310296191819463,
      "grad_norm": 0.6057098678411602,
      "learning_rate": 8e-06,
      "loss": 0.6275,
      "step": 90
    },
    {
      "epoch": 0.22566995768688294,
      "grad_norm": 0.7499138339051353,
      "learning_rate": 8e-06,
      "loss": 0.6268,
      "step": 100
    },
    {
      "epoch": 0.24823695345557123,
      "grad_norm": 0.5655634075592816,
      "learning_rate": 8e-06,
      "loss": 0.6174,
      "step": 110
    },
    {
      "epoch": 0.27080394922425954,
      "grad_norm": 0.7361003496415315,
      "learning_rate": 8e-06,
      "loss": 0.617,
      "step": 120
    },
    {
      "epoch": 0.2933709449929478,
      "grad_norm": 0.8683082631173074,
      "learning_rate": 8e-06,
      "loss": 0.6182,
      "step": 130
    },
    {
      "epoch": 0.3159379407616361,
      "grad_norm": 0.5646988292042954,
      "learning_rate": 8e-06,
      "loss": 0.6133,
      "step": 140
    },
    {
      "epoch": 0.3385049365303244,
      "grad_norm": 0.6029782847376515,
      "learning_rate": 8e-06,
      "loss": 0.6138,
      "step": 150
    },
    {
      "epoch": 0.3610719322990127,
      "grad_norm": 0.6303931877023011,
      "learning_rate": 8e-06,
      "loss": 0.6159,
      "step": 160
    },
    {
      "epoch": 0.383638928067701,
      "grad_norm": 0.6569685296950466,
      "learning_rate": 8e-06,
      "loss": 0.6119,
      "step": 170
    },
    {
      "epoch": 0.40620592383638926,
      "grad_norm": 0.6249135242981495,
      "learning_rate": 8e-06,
      "loss": 0.609,
      "step": 180
    },
    {
      "epoch": 0.4287729196050776,
      "grad_norm": 0.5284112044161535,
      "learning_rate": 8e-06,
      "loss": 0.6034,
      "step": 190
    },
    {
      "epoch": 0.4513399153737659,
      "grad_norm": 0.6297404102914753,
      "learning_rate": 8e-06,
      "loss": 0.6102,
      "step": 200
    },
    {
      "epoch": 0.47390691114245415,
      "grad_norm": 0.5558700755041068,
      "learning_rate": 8e-06,
      "loss": 0.6067,
      "step": 210
    },
    {
      "epoch": 0.49647390691114246,
      "grad_norm": 0.5432069151091344,
      "learning_rate": 8e-06,
      "loss": 0.5983,
      "step": 220
    },
    {
      "epoch": 0.5190409026798307,
      "grad_norm": 0.6986712446921519,
      "learning_rate": 8e-06,
      "loss": 0.6073,
      "step": 230
    },
    {
      "epoch": 0.5416078984485191,
      "grad_norm": 0.5292918643246928,
      "learning_rate": 8e-06,
      "loss": 0.6061,
      "step": 240
    },
    {
      "epoch": 0.5641748942172073,
      "grad_norm": 0.5860231750329836,
      "learning_rate": 8e-06,
      "loss": 0.6001,
      "step": 250
    },
    {
      "epoch": 0.5867418899858956,
      "grad_norm": 0.5677887993988292,
      "learning_rate": 8e-06,
      "loss": 0.6026,
      "step": 260
    },
    {
      "epoch": 0.609308885754584,
      "grad_norm": 0.6413253400261202,
      "learning_rate": 8e-06,
      "loss": 0.5981,
      "step": 270
    },
    {
      "epoch": 0.6318758815232722,
      "grad_norm": 0.6908472479913921,
      "learning_rate": 8e-06,
      "loss": 0.6048,
      "step": 280
    },
    {
      "epoch": 0.6544428772919605,
      "grad_norm": 0.714629823941289,
      "learning_rate": 8e-06,
      "loss": 0.5983,
      "step": 290
    },
    {
      "epoch": 0.6770098730606487,
      "grad_norm": 0.6802769614751161,
      "learning_rate": 8e-06,
      "loss": 0.6045,
      "step": 300
    },
    {
      "epoch": 0.6995768688293371,
      "grad_norm": 0.5316202008766112,
      "learning_rate": 8e-06,
      "loss": 0.5977,
      "step": 310
    },
    {
      "epoch": 0.7221438645980254,
      "grad_norm": 0.5196707182226418,
      "learning_rate": 8e-06,
      "loss": 0.6009,
      "step": 320
    },
    {
      "epoch": 0.7447108603667136,
      "grad_norm": 0.5751885287237052,
      "learning_rate": 8e-06,
      "loss": 0.5966,
      "step": 330
    },
    {
      "epoch": 0.767277856135402,
      "grad_norm": 0.5673409778556773,
      "learning_rate": 8e-06,
      "loss": 0.5961,
      "step": 340
    },
    {
      "epoch": 0.7898448519040903,
      "grad_norm": 0.7262338664772516,
      "learning_rate": 8e-06,
      "loss": 0.5974,
      "step": 350
    },
    {
      "epoch": 0.8124118476727785,
      "grad_norm": 0.7113621946621588,
      "learning_rate": 8e-06,
      "loss": 0.5965,
      "step": 360
    },
    {
      "epoch": 0.8349788434414669,
      "grad_norm": 0.6463560163040296,
      "learning_rate": 8e-06,
      "loss": 0.6035,
      "step": 370
    },
    {
      "epoch": 0.8575458392101551,
      "grad_norm": 0.6271190448585602,
      "learning_rate": 8e-06,
      "loss": 0.6004,
      "step": 380
    },
    {
      "epoch": 0.8801128349788434,
      "grad_norm": 0.5372250514850698,
      "learning_rate": 8e-06,
      "loss": 0.5943,
      "step": 390
    },
    {
      "epoch": 0.9026798307475318,
      "grad_norm": 0.5388593187512571,
      "learning_rate": 8e-06,
      "loss": 0.5967,
      "step": 400
    },
    {
      "epoch": 0.92524682651622,
      "grad_norm": 0.5747746875548279,
      "learning_rate": 8e-06,
      "loss": 0.5946,
      "step": 410
    },
    {
      "epoch": 0.9478138222849083,
      "grad_norm": 0.544568203789026,
      "learning_rate": 8e-06,
      "loss": 0.5952,
      "step": 420
    },
    {
      "epoch": 0.9703808180535967,
      "grad_norm": 0.5472361065364679,
      "learning_rate": 8e-06,
      "loss": 0.5895,
      "step": 430
    },
    {
      "epoch": 0.9929478138222849,
      "grad_norm": 0.6332591915298204,
      "learning_rate": 8e-06,
      "loss": 0.5945,
      "step": 440
    },
    {
      "epoch": 0.9997179125528914,
      "eval_loss": 0.592284083366394,
      "eval_runtime": 682.8659,
      "eval_samples_per_second": 17.487,
      "eval_steps_per_second": 0.548,
      "step": 443
    },
    {
      "epoch": 1.0155148095909732,
      "grad_norm": 0.8892493668408962,
      "learning_rate": 8e-06,
      "loss": 0.5895,
      "step": 450
    },
    {
      "epoch": 1.0380818053596614,
      "grad_norm": 0.6038498089412524,
      "learning_rate": 8e-06,
      "loss": 0.5113,
      "step": 460
    },
    {
      "epoch": 1.0606488011283497,
      "grad_norm": 0.6238682656833255,
      "learning_rate": 8e-06,
      "loss": 0.5247,
      "step": 470
    },
    {
      "epoch": 1.0832157968970382,
      "grad_norm": 0.5807234263348268,
      "learning_rate": 8e-06,
      "loss": 0.5133,
      "step": 480
    },
    {
      "epoch": 1.1057827926657264,
      "grad_norm": 0.5568353821457447,
      "learning_rate": 8e-06,
      "loss": 0.5231,
      "step": 490
    },
    {
      "epoch": 1.1283497884344147,
      "grad_norm": 0.5621085376910522,
      "learning_rate": 8e-06,
      "loss": 0.522,
      "step": 500
    },
    {
      "epoch": 1.150916784203103,
      "grad_norm": 0.5654215988228639,
      "learning_rate": 8e-06,
      "loss": 0.5236,
      "step": 510
    },
    {
      "epoch": 1.1734837799717912,
      "grad_norm": 0.5588139527559826,
      "learning_rate": 8e-06,
      "loss": 0.5166,
      "step": 520
    },
    {
      "epoch": 1.1960507757404795,
      "grad_norm": 0.6111576863151309,
      "learning_rate": 8e-06,
      "loss": 0.5229,
      "step": 530
    },
    {
      "epoch": 1.2186177715091677,
      "grad_norm": 0.5364873444486519,
      "learning_rate": 8e-06,
      "loss": 0.5207,
      "step": 540
    },
    {
      "epoch": 1.2411847672778562,
      "grad_norm": 0.5808607077321851,
      "learning_rate": 8e-06,
      "loss": 0.5256,
      "step": 550
    },
    {
      "epoch": 1.2637517630465445,
      "grad_norm": 0.5641539038251432,
      "learning_rate": 8e-06,
      "loss": 0.5274,
      "step": 560
    },
    {
      "epoch": 1.2863187588152327,
      "grad_norm": 0.5693079740970852,
      "learning_rate": 8e-06,
      "loss": 0.5251,
      "step": 570
    },
    {
      "epoch": 1.308885754583921,
      "grad_norm": 0.5334659094006734,
      "learning_rate": 8e-06,
      "loss": 0.5253,
      "step": 580
    },
    {
      "epoch": 1.3314527503526092,
      "grad_norm": 0.5183593764843117,
      "learning_rate": 8e-06,
      "loss": 0.5255,
      "step": 590
    },
    {
      "epoch": 1.3540197461212977,
      "grad_norm": 0.5492584837955853,
      "learning_rate": 8e-06,
      "loss": 0.5308,
      "step": 600
    },
    {
      "epoch": 1.376586741889986,
      "grad_norm": 0.5166832529517328,
      "learning_rate": 8e-06,
      "loss": 0.5238,
      "step": 610
    },
    {
      "epoch": 1.3991537376586742,
      "grad_norm": 0.5385347197696578,
      "learning_rate": 8e-06,
      "loss": 0.5282,
      "step": 620
    },
    {
      "epoch": 1.4217207334273625,
      "grad_norm": 0.5327757016233992,
      "learning_rate": 8e-06,
      "loss": 0.5265,
      "step": 630
    },
    {
      "epoch": 1.4442877291960508,
      "grad_norm": 0.5423403643408274,
      "learning_rate": 8e-06,
      "loss": 0.5265,
      "step": 640
    },
    {
      "epoch": 1.466854724964739,
      "grad_norm": 0.5108507098451446,
      "learning_rate": 8e-06,
      "loss": 0.5271,
      "step": 650
    },
    {
      "epoch": 1.4894217207334273,
      "grad_norm": 0.5933412207657776,
      "learning_rate": 8e-06,
      "loss": 0.5313,
      "step": 660
    },
    {
      "epoch": 1.5119887165021155,
      "grad_norm": 0.5372994750861314,
      "learning_rate": 8e-06,
      "loss": 0.526,
      "step": 670
    },
    {
      "epoch": 1.5345557122708038,
      "grad_norm": 0.5383813037017657,
      "learning_rate": 8e-06,
      "loss": 0.5207,
      "step": 680
    },
    {
      "epoch": 1.5571227080394923,
      "grad_norm": 0.5543179543330287,
      "learning_rate": 8e-06,
      "loss": 0.5227,
      "step": 690
    },
    {
      "epoch": 1.5796897038081805,
      "grad_norm": 0.5895790985790441,
      "learning_rate": 8e-06,
      "loss": 0.5271,
      "step": 700
    },
    {
      "epoch": 1.6022566995768688,
      "grad_norm": 0.5553208052647728,
      "learning_rate": 8e-06,
      "loss": 0.5299,
      "step": 710
    },
    {
      "epoch": 1.6248236953455573,
      "grad_norm": 0.561115144532539,
      "learning_rate": 8e-06,
      "loss": 0.5378,
      "step": 720
    },
    {
      "epoch": 1.6473906911142455,
      "grad_norm": 0.49871680939460455,
      "learning_rate": 8e-06,
      "loss": 0.5217,
      "step": 730
    },
    {
      "epoch": 1.6699576868829338,
      "grad_norm": 0.570896188106777,
      "learning_rate": 8e-06,
      "loss": 0.5371,
      "step": 740
    },
    {
      "epoch": 1.692524682651622,
      "grad_norm": 0.6051328663283235,
      "learning_rate": 8e-06,
      "loss": 0.5289,
      "step": 750
    },
    {
      "epoch": 1.7150916784203103,
      "grad_norm": 0.5248616038752071,
      "learning_rate": 8e-06,
      "loss": 0.5279,
      "step": 760
    },
    {
      "epoch": 1.7376586741889986,
      "grad_norm": 0.5690539656048229,
      "learning_rate": 8e-06,
      "loss": 0.5288,
      "step": 770
    },
    {
      "epoch": 1.7602256699576868,
      "grad_norm": 0.5524538136131857,
      "learning_rate": 8e-06,
      "loss": 0.5247,
      "step": 780
    },
    {
      "epoch": 1.782792665726375,
      "grad_norm": 0.5428666429411874,
      "learning_rate": 8e-06,
      "loss": 0.5283,
      "step": 790
    },
    {
      "epoch": 1.8053596614950633,
      "grad_norm": 0.5077539157975688,
      "learning_rate": 8e-06,
      "loss": 0.5237,
      "step": 800
    },
    {
      "epoch": 1.8279266572637518,
      "grad_norm": 0.7136058432901515,
      "learning_rate": 8e-06,
      "loss": 0.5342,
      "step": 810
    },
    {
      "epoch": 1.85049365303244,
      "grad_norm": 0.4952459997682776,
      "learning_rate": 8e-06,
      "loss": 0.5219,
      "step": 820
    },
    {
      "epoch": 1.8730606488011283,
      "grad_norm": 0.5557027207307267,
      "learning_rate": 8e-06,
      "loss": 0.5336,
      "step": 830
    },
    {
      "epoch": 1.8956276445698168,
      "grad_norm": 0.5248583495415717,
      "learning_rate": 8e-06,
      "loss": 0.5339,
      "step": 840
    },
    {
      "epoch": 1.918194640338505,
      "grad_norm": 0.5215256595623672,
      "learning_rate": 8e-06,
      "loss": 0.5224,
      "step": 850
    },
    {
      "epoch": 1.9407616361071933,
      "grad_norm": 0.5660058681691327,
      "learning_rate": 8e-06,
      "loss": 0.5275,
      "step": 860
    },
    {
      "epoch": 1.9633286318758816,
      "grad_norm": 0.5883997977420252,
      "learning_rate": 8e-06,
      "loss": 0.5337,
      "step": 870
    },
    {
      "epoch": 1.9858956276445698,
      "grad_norm": 0.6097901907552612,
      "learning_rate": 8e-06,
      "loss": 0.5319,
      "step": 880
    },
    {
      "epoch": 1.9994358251057829,
      "eval_loss": 0.5926612615585327,
      "eval_runtime": 682.9306,
      "eval_samples_per_second": 17.485,
      "eval_steps_per_second": 0.548,
      "step": 886
    },
    {
      "epoch": 2.008462623413258,
      "grad_norm": 1.0391908458600836,
      "learning_rate": 8e-06,
      "loss": 0.5456,
      "step": 890
    },
    {
      "epoch": 2.0310296191819464,
      "grad_norm": 0.6903178535769503,
      "learning_rate": 8e-06,
      "loss": 0.4427,
      "step": 900
    },
    {
      "epoch": 2.0535966149506346,
      "grad_norm": 0.6261713970420871,
      "learning_rate": 8e-06,
      "loss": 0.4433,
      "step": 910
    },
    {
      "epoch": 2.076163610719323,
      "grad_norm": 0.6678821939069286,
      "learning_rate": 8e-06,
      "loss": 0.436,
      "step": 920
    },
    {
      "epoch": 2.098730606488011,
      "grad_norm": 0.5758263684498833,
      "learning_rate": 8e-06,
      "loss": 0.4431,
      "step": 930
    },
    {
      "epoch": 2.1212976022566994,
      "grad_norm": 0.5609971997658122,
      "learning_rate": 8e-06,
      "loss": 0.4477,
      "step": 940
    },
    {
      "epoch": 2.143864598025388,
      "grad_norm": 0.582442843247943,
      "learning_rate": 8e-06,
      "loss": 0.4495,
      "step": 950
    },
    {
      "epoch": 2.1664315937940763,
      "grad_norm": 0.5924298229005652,
      "learning_rate": 8e-06,
      "loss": 0.446,
      "step": 960
    },
    {
      "epoch": 2.1889985895627646,
      "grad_norm": 0.6218286190533895,
      "learning_rate": 8e-06,
      "loss": 0.4452,
      "step": 970
    },
    {
      "epoch": 2.211565585331453,
      "grad_norm": 0.5683387910554794,
      "learning_rate": 8e-06,
      "loss": 0.4411,
      "step": 980
    },
    {
      "epoch": 2.234132581100141,
      "grad_norm": 0.5544577664955718,
      "learning_rate": 8e-06,
      "loss": 0.4412,
      "step": 990
    },
    {
      "epoch": 2.2566995768688294,
      "grad_norm": 0.583290358927714,
      "learning_rate": 8e-06,
      "loss": 0.4491,
      "step": 1000
    },
    {
      "epoch": 2.2792665726375176,
      "grad_norm": 0.5887013752718141,
      "learning_rate": 8e-06,
      "loss": 0.4552,
      "step": 1010
    },
    {
      "epoch": 2.301833568406206,
      "grad_norm": 0.5668094677365206,
      "learning_rate": 8e-06,
      "loss": 0.451,
      "step": 1020
    },
    {
      "epoch": 2.324400564174894,
      "grad_norm": 0.5959991657625883,
      "learning_rate": 8e-06,
      "loss": 0.455,
      "step": 1030
    },
    {
      "epoch": 2.3469675599435824,
      "grad_norm": 0.5501770342348836,
      "learning_rate": 8e-06,
      "loss": 0.4537,
      "step": 1040
    },
    {
      "epoch": 2.3695345557122707,
      "grad_norm": 0.5632019457048635,
      "learning_rate": 8e-06,
      "loss": 0.4518,
      "step": 1050
    },
    {
      "epoch": 2.392101551480959,
      "grad_norm": 0.6088140958777798,
      "learning_rate": 8e-06,
      "loss": 0.4513,
      "step": 1060
    },
    {
      "epoch": 2.414668547249647,
      "grad_norm": 0.5440923707181681,
      "learning_rate": 8e-06,
      "loss": 0.4528,
      "step": 1070
    },
    {
      "epoch": 2.4372355430183354,
      "grad_norm": 0.6119221799698635,
      "learning_rate": 8e-06,
      "loss": 0.4555,
      "step": 1080
    },
    {
      "epoch": 2.459802538787024,
      "grad_norm": 0.5605061835390044,
      "learning_rate": 8e-06,
      "loss": 0.4543,
      "step": 1090
    },
    {
      "epoch": 2.4823695345557124,
      "grad_norm": 0.5629648754585153,
      "learning_rate": 8e-06,
      "loss": 0.458,
      "step": 1100
    },
    {
      "epoch": 2.5049365303244007,
      "grad_norm": 0.5772914670657768,
      "learning_rate": 8e-06,
      "loss": 0.4607,
      "step": 1110
    },
    {
      "epoch": 2.527503526093089,
      "grad_norm": 0.5653792747875842,
      "learning_rate": 8e-06,
      "loss": 0.4526,
      "step": 1120
    },
    {
      "epoch": 2.550070521861777,
      "grad_norm": 0.558407539047876,
      "learning_rate": 8e-06,
      "loss": 0.4574,
      "step": 1130
    },
    {
      "epoch": 2.5726375176304654,
      "grad_norm": 0.5662238187953264,
      "learning_rate": 8e-06,
      "loss": 0.4558,
      "step": 1140
    },
    {
      "epoch": 2.5952045133991537,
      "grad_norm": 0.6169753182959905,
      "learning_rate": 8e-06,
      "loss": 0.4565,
      "step": 1150
    },
    {
      "epoch": 2.617771509167842,
      "grad_norm": 0.5322964093260222,
      "learning_rate": 8e-06,
      "loss": 0.4602,
      "step": 1160
    },
    {
      "epoch": 2.64033850493653,
      "grad_norm": 0.5723855454624965,
      "learning_rate": 8e-06,
      "loss": 0.4503,
      "step": 1170
    },
    {
      "epoch": 2.6629055007052185,
      "grad_norm": 0.5935111008703569,
      "learning_rate": 8e-06,
      "loss": 0.4604,
      "step": 1180
    },
    {
      "epoch": 2.685472496473907,
      "grad_norm": 0.5576336178579941,
      "learning_rate": 8e-06,
      "loss": 0.4611,
      "step": 1190
    },
    {
      "epoch": 2.7080394922425954,
      "grad_norm": 0.6292800808856862,
      "learning_rate": 8e-06,
      "loss": 0.4602,
      "step": 1200
    },
    {
      "epoch": 2.7306064880112837,
      "grad_norm": 0.5927583083748548,
      "learning_rate": 8e-06,
      "loss": 0.4615,
      "step": 1210
    },
    {
      "epoch": 2.753173483779972,
      "grad_norm": 0.5917512881175462,
      "learning_rate": 8e-06,
      "loss": 0.4588,
      "step": 1220
    },
    {
      "epoch": 2.77574047954866,
      "grad_norm": 0.5978443540694188,
      "learning_rate": 8e-06,
      "loss": 0.4652,
      "step": 1230
    },
    {
      "epoch": 2.7983074753173485,
      "grad_norm": 0.6224749609079188,
      "learning_rate": 8e-06,
      "loss": 0.4633,
      "step": 1240
    },
    {
      "epoch": 2.8208744710860367,
      "grad_norm": 0.5513937808090881,
      "learning_rate": 8e-06,
      "loss": 0.4637,
      "step": 1250
    },
    {
      "epoch": 2.843441466854725,
      "grad_norm": 0.5831860330095678,
      "learning_rate": 8e-06,
      "loss": 0.4654,
      "step": 1260
    },
    {
      "epoch": 2.8660084626234132,
      "grad_norm": 0.5497952194715802,
      "learning_rate": 8e-06,
      "loss": 0.4629,
      "step": 1270
    },
    {
      "epoch": 2.8885754583921015,
      "grad_norm": 0.536467856442936,
      "learning_rate": 8e-06,
      "loss": 0.4613,
      "step": 1280
    },
    {
      "epoch": 2.9111424541607898,
      "grad_norm": 0.5573752705862949,
      "learning_rate": 8e-06,
      "loss": 0.4645,
      "step": 1290
    },
    {
      "epoch": 2.933709449929478,
      "grad_norm": 0.5390577255486722,
      "learning_rate": 8e-06,
      "loss": 0.4607,
      "step": 1300
    },
    {
      "epoch": 2.9562764456981663,
      "grad_norm": 0.5773369710560571,
      "learning_rate": 8e-06,
      "loss": 0.4645,
      "step": 1310
    },
    {
      "epoch": 2.9788434414668545,
      "grad_norm": 0.5570394961520608,
      "learning_rate": 8e-06,
      "loss": 0.4618,
      "step": 1320
    },
    {
      "epoch": 2.9991537376586743,
      "eval_loss": 0.620595395565033,
      "eval_runtime": 683.8083,
      "eval_samples_per_second": 17.462,
      "eval_steps_per_second": 0.547,
      "step": 1329
    },
    {
      "epoch": 2.9991537376586743,
      "step": 1329,
      "total_flos": 5064195066298368.0,
      "train_loss": 0.5323991782688574,
      "train_runtime": 119702.7172,
      "train_samples_per_second": 5.686,
      "train_steps_per_second": 0.011
    }
  ],
  "logging_steps": 10,
  "max_steps": 1329,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 5064195066298368.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}