{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.99626400996264,
  "eval_steps": 500,
  "global_step": 1203,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024906600249066,
      "grad_norm": 10.55736720812015,
      "learning_rate": 5e-06,
      "loss": 0.899,
      "step": 10
    },
    {
      "epoch": 0.049813200498132,
      "grad_norm": 2.4056192000192786,
      "learning_rate": 5e-06,
      "loss": 0.7632,
      "step": 20
    },
    {
      "epoch": 0.074719800747198,
      "grad_norm": 1.0776649113170846,
      "learning_rate": 5e-06,
      "loss": 0.7213,
      "step": 30
    },
    {
      "epoch": 0.099626400996264,
      "grad_norm": 1.2974590316911792,
      "learning_rate": 5e-06,
      "loss": 0.6892,
      "step": 40
    },
    {
      "epoch": 0.12453300124533001,
      "grad_norm": 0.8664841939523225,
      "learning_rate": 5e-06,
      "loss": 0.6708,
      "step": 50
    },
    {
      "epoch": 0.149439601494396,
      "grad_norm": 0.7916914326975599,
      "learning_rate": 5e-06,
      "loss": 0.6504,
      "step": 60
    },
    {
      "epoch": 0.17434620174346202,
      "grad_norm": 0.8355113234133088,
      "learning_rate": 5e-06,
      "loss": 0.6407,
      "step": 70
    },
    {
      "epoch": 0.199252801992528,
      "grad_norm": 0.6185509662301869,
      "learning_rate": 5e-06,
      "loss": 0.6377,
      "step": 80
    },
    {
      "epoch": 0.22415940224159403,
      "grad_norm": 0.5793150300164642,
      "learning_rate": 5e-06,
      "loss": 0.6276,
      "step": 90
    },
    {
      "epoch": 0.24906600249066002,
      "grad_norm": 0.5522899454819212,
      "learning_rate": 5e-06,
      "loss": 0.6229,
      "step": 100
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 0.6471095275689863,
      "learning_rate": 5e-06,
      "loss": 0.6154,
      "step": 110
    },
    {
      "epoch": 0.298879202988792,
      "grad_norm": 0.6264851589702339,
      "learning_rate": 5e-06,
      "loss": 0.6104,
      "step": 120
    },
    {
      "epoch": 0.32378580323785805,
      "grad_norm": 0.705297908293922,
      "learning_rate": 5e-06,
      "loss": 0.6094,
      "step": 130
    },
    {
      "epoch": 0.34869240348692404,
      "grad_norm": 0.620653193497072,
      "learning_rate": 5e-06,
      "loss": 0.6079,
      "step": 140
    },
    {
      "epoch": 0.37359900373599003,
      "grad_norm": 0.9444217688486999,
      "learning_rate": 5e-06,
      "loss": 0.5983,
      "step": 150
    },
    {
      "epoch": 0.398505603985056,
      "grad_norm": 0.6034795779576418,
      "learning_rate": 5e-06,
      "loss": 0.6044,
      "step": 160
    },
    {
      "epoch": 0.42341220423412207,
      "grad_norm": 0.4974203412589217,
      "learning_rate": 5e-06,
      "loss": 0.5962,
      "step": 170
    },
    {
      "epoch": 0.44831880448318806,
      "grad_norm": 0.728230577535382,
      "learning_rate": 5e-06,
      "loss": 0.5975,
      "step": 180
    },
    {
      "epoch": 0.47322540473225405,
      "grad_norm": 0.49214457212025137,
      "learning_rate": 5e-06,
      "loss": 0.5986,
      "step": 190
    },
    {
      "epoch": 0.49813200498132004,
      "grad_norm": 0.5432395369586009,
      "learning_rate": 5e-06,
      "loss": 0.5885,
      "step": 200
    },
    {
      "epoch": 0.523038605230386,
      "grad_norm": 0.5473973456491285,
      "learning_rate": 5e-06,
      "loss": 0.5901,
      "step": 210
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 0.5759522711461309,
      "learning_rate": 5e-06,
      "loss": 0.586,
      "step": 220
    },
    {
      "epoch": 0.572851805728518,
      "grad_norm": 0.5583334053126371,
      "learning_rate": 5e-06,
      "loss": 0.5878,
      "step": 230
    },
    {
      "epoch": 0.597758405977584,
      "grad_norm": 0.7058646192825392,
      "learning_rate": 5e-06,
      "loss": 0.5818,
      "step": 240
    },
    {
      "epoch": 0.6226650062266501,
      "grad_norm": 0.5788660860127395,
      "learning_rate": 5e-06,
      "loss": 0.5853,
      "step": 250
    },
    {
      "epoch": 0.6475716064757161,
      "grad_norm": 0.6402936090502463,
      "learning_rate": 5e-06,
      "loss": 0.5769,
      "step": 260
    },
    {
      "epoch": 0.6724782067247821,
      "grad_norm": 0.5496743019012175,
      "learning_rate": 5e-06,
      "loss": 0.5762,
      "step": 270
    },
    {
      "epoch": 0.6973848069738481,
      "grad_norm": 0.5455503536049673,
      "learning_rate": 5e-06,
      "loss": 0.5808,
      "step": 280
    },
    {
      "epoch": 0.7222914072229141,
      "grad_norm": 0.5883422768851626,
      "learning_rate": 5e-06,
      "loss": 0.5747,
      "step": 290
    },
    {
      "epoch": 0.7471980074719801,
      "grad_norm": 0.7956726883043881,
      "learning_rate": 5e-06,
      "loss": 0.5717,
      "step": 300
    },
    {
      "epoch": 0.772104607721046,
      "grad_norm": 0.6813019491351078,
      "learning_rate": 5e-06,
      "loss": 0.5722,
      "step": 310
    },
    {
      "epoch": 0.797011207970112,
      "grad_norm": 0.5185381604929972,
      "learning_rate": 5e-06,
      "loss": 0.5724,
      "step": 320
    },
    {
      "epoch": 0.821917808219178,
      "grad_norm": 0.6909227667005327,
      "learning_rate": 5e-06,
      "loss": 0.5691,
      "step": 330
    },
    {
      "epoch": 0.8468244084682441,
      "grad_norm": 0.4796775398588659,
      "learning_rate": 5e-06,
      "loss": 0.5652,
      "step": 340
    },
    {
      "epoch": 0.8717310087173101,
      "grad_norm": 0.5758165163544798,
      "learning_rate": 5e-06,
      "loss": 0.5736,
      "step": 350
    },
    {
      "epoch": 0.8966376089663761,
      "grad_norm": 0.5892321233613834,
      "learning_rate": 5e-06,
      "loss": 0.5663,
      "step": 360
    },
    {
      "epoch": 0.9215442092154421,
      "grad_norm": 0.5088131774112012,
      "learning_rate": 5e-06,
      "loss": 0.5674,
      "step": 370
    },
    {
      "epoch": 0.9464508094645081,
      "grad_norm": 0.5017508892526636,
      "learning_rate": 5e-06,
      "loss": 0.563,
      "step": 380
    },
    {
      "epoch": 0.9713574097135741,
      "grad_norm": 0.6797455724948757,
      "learning_rate": 5e-06,
      "loss": 0.5674,
      "step": 390
    },
    {
      "epoch": 0.9962640099626401,
      "grad_norm": 0.5319255477795009,
      "learning_rate": 5e-06,
      "loss": 0.562,
      "step": 400
    },
    {
      "epoch": 0.9987546699875467,
      "eval_loss": 0.5648990869522095,
      "eval_runtime": 215.2105,
      "eval_samples_per_second": 50.272,
      "eval_steps_per_second": 0.395,
      "step": 401
    },
    {
      "epoch": 1.0211706102117062,
      "grad_norm": 0.6332423226665538,
      "learning_rate": 5e-06,
      "loss": 0.5373,
      "step": 410
    },
    {
      "epoch": 1.046077210460772,
      "grad_norm": 0.5250206863412192,
      "learning_rate": 5e-06,
      "loss": 0.5262,
      "step": 420
    },
    {
      "epoch": 1.0709838107098382,
      "grad_norm": 0.6270808658082102,
      "learning_rate": 5e-06,
      "loss": 0.5275,
      "step": 430
    },
    {
      "epoch": 1.095890410958904,
      "grad_norm": 0.5516867253896128,
      "learning_rate": 5e-06,
      "loss": 0.5262,
      "step": 440
    },
    {
      "epoch": 1.1207970112079702,
      "grad_norm": 0.5358792491430266,
      "learning_rate": 5e-06,
      "loss": 0.5319,
      "step": 450
    },
    {
      "epoch": 1.145703611457036,
      "grad_norm": 0.7694988300392477,
      "learning_rate": 5e-06,
      "loss": 0.5251,
      "step": 460
    },
    {
      "epoch": 1.1706102117061021,
      "grad_norm": 0.5425248792129497,
      "learning_rate": 5e-06,
      "loss": 0.5255,
      "step": 470
    },
    {
      "epoch": 1.195516811955168,
      "grad_norm": 0.6608067800821592,
      "learning_rate": 5e-06,
      "loss": 0.5312,
      "step": 480
    },
    {
      "epoch": 1.2204234122042341,
      "grad_norm": 0.5892306715949471,
      "learning_rate": 5e-06,
      "loss": 0.5292,
      "step": 490
    },
    {
      "epoch": 1.2453300124533002,
      "grad_norm": 0.6342257885292061,
      "learning_rate": 5e-06,
      "loss": 0.5282,
      "step": 500
    },
    {
      "epoch": 1.270236612702366,
      "grad_norm": 0.6358865929230534,
      "learning_rate": 5e-06,
      "loss": 0.5256,
      "step": 510
    },
    {
      "epoch": 1.2951432129514322,
      "grad_norm": 0.5977464268642516,
      "learning_rate": 5e-06,
      "loss": 0.5216,
      "step": 520
    },
    {
      "epoch": 1.320049813200498,
      "grad_norm": 0.5713712938047752,
      "learning_rate": 5e-06,
      "loss": 0.5246,
      "step": 530
    },
    {
      "epoch": 1.3449564134495642,
      "grad_norm": 0.5806626902728351,
      "learning_rate": 5e-06,
      "loss": 0.522,
      "step": 540
    },
    {
      "epoch": 1.36986301369863,
      "grad_norm": 0.6614502597905593,
      "learning_rate": 5e-06,
      "loss": 0.5232,
      "step": 550
    },
    {
      "epoch": 1.3947696139476962,
      "grad_norm": 0.5826714843440824,
      "learning_rate": 5e-06,
      "loss": 0.5243,
      "step": 560
    },
    {
      "epoch": 1.419676214196762,
      "grad_norm": 0.5870354154595686,
      "learning_rate": 5e-06,
      "loss": 0.5277,
      "step": 570
    },
    {
      "epoch": 1.4445828144458281,
      "grad_norm": 0.5517404762107168,
      "learning_rate": 5e-06,
      "loss": 0.5185,
      "step": 580
    },
    {
      "epoch": 1.4694894146948942,
      "grad_norm": 0.6548505841520894,
      "learning_rate": 5e-06,
      "loss": 0.5254,
      "step": 590
    },
    {
      "epoch": 1.4943960149439601,
      "grad_norm": 0.4798373315690756,
      "learning_rate": 5e-06,
      "loss": 0.5223,
      "step": 600
    },
    {
      "epoch": 1.519302615193026,
      "grad_norm": 0.561260368162772,
      "learning_rate": 5e-06,
      "loss": 0.5208,
      "step": 610
    },
    {
      "epoch": 1.544209215442092,
      "grad_norm": 0.4776435289710049,
      "learning_rate": 5e-06,
      "loss": 0.5169,
      "step": 620
    },
    {
      "epoch": 1.5691158156911582,
      "grad_norm": 0.5736062837326033,
      "learning_rate": 5e-06,
      "loss": 0.518,
      "step": 630
    },
    {
      "epoch": 1.5940224159402243,
      "grad_norm": 0.5605397398468376,
      "learning_rate": 5e-06,
      "loss": 0.519,
      "step": 640
    },
    {
      "epoch": 1.6189290161892902,
      "grad_norm": 0.5414003173485504,
      "learning_rate": 5e-06,
      "loss": 0.5141,
      "step": 650
    },
    {
      "epoch": 1.643835616438356,
      "grad_norm": 0.5029725162688677,
      "learning_rate": 5e-06,
      "loss": 0.5123,
      "step": 660
    },
    {
      "epoch": 1.6687422166874222,
      "grad_norm": 0.49094415690364374,
      "learning_rate": 5e-06,
      "loss": 0.5103,
      "step": 670
    },
    {
      "epoch": 1.6936488169364883,
      "grad_norm": 0.6443717801298894,
      "learning_rate": 5e-06,
      "loss": 0.5173,
      "step": 680
    },
    {
      "epoch": 1.7185554171855542,
      "grad_norm": 0.6131661065579275,
      "learning_rate": 5e-06,
      "loss": 0.5123,
      "step": 690
    },
    {
      "epoch": 1.74346201743462,
      "grad_norm": 0.5102402228309177,
      "learning_rate": 5e-06,
      "loss": 0.5117,
      "step": 700
    },
    {
      "epoch": 1.7683686176836861,
      "grad_norm": 0.6532768204087063,
      "learning_rate": 5e-06,
      "loss": 0.5116,
      "step": 710
    },
    {
      "epoch": 1.7932752179327522,
      "grad_norm": 0.5359103919656766,
      "learning_rate": 5e-06,
      "loss": 0.5112,
      "step": 720
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.4654117626073739,
      "learning_rate": 5e-06,
      "loss": 0.5108,
      "step": 730
    },
    {
      "epoch": 1.8430884184308842,
      "grad_norm": 0.4816605018327504,
      "learning_rate": 5e-06,
      "loss": 0.5125,
      "step": 740
    },
    {
      "epoch": 1.86799501867995,
      "grad_norm": 0.5078445355540058,
      "learning_rate": 5e-06,
      "loss": 0.5174,
      "step": 750
    },
    {
      "epoch": 1.8929016189290162,
      "grad_norm": 0.5123586401271214,
      "learning_rate": 5e-06,
      "loss": 0.5103,
      "step": 760
    },
    {
      "epoch": 1.9178082191780823,
      "grad_norm": 0.512594100070009,
      "learning_rate": 5e-06,
      "loss": 0.5125,
      "step": 770
    },
    {
      "epoch": 1.9427148194271482,
      "grad_norm": 0.5251535719075618,
      "learning_rate": 5e-06,
      "loss": 0.5097,
      "step": 780
    },
    {
      "epoch": 1.967621419676214,
      "grad_norm": 0.5598844434696433,
      "learning_rate": 5e-06,
      "loss": 0.5114,
      "step": 790
    },
    {
      "epoch": 1.9925280199252802,
      "grad_norm": 0.5580903372050761,
      "learning_rate": 5e-06,
      "loss": 0.5112,
      "step": 800
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5391710996627808,
      "eval_runtime": 215.2899,
      "eval_samples_per_second": 50.253,
      "eval_steps_per_second": 0.395,
      "step": 803
    },
    {
      "epoch": 2.0174346201743463,
      "grad_norm": 0.7489739683512228,
      "learning_rate": 5e-06,
      "loss": 0.4772,
      "step": 810
    },
    {
      "epoch": 2.0423412204234124,
      "grad_norm": 0.6206410773051714,
      "learning_rate": 5e-06,
      "loss": 0.4773,
      "step": 820
    },
    {
      "epoch": 2.067247820672478,
      "grad_norm": 0.5964416221117852,
      "learning_rate": 5e-06,
      "loss": 0.4774,
      "step": 830
    },
    {
      "epoch": 2.092154420921544,
      "grad_norm": 0.7072977668899793,
      "learning_rate": 5e-06,
      "loss": 0.4734,
      "step": 840
    },
    {
      "epoch": 2.1170610211706102,
      "grad_norm": 0.4869213806678473,
      "learning_rate": 5e-06,
      "loss": 0.4738,
      "step": 850
    },
    {
      "epoch": 2.1419676214196763,
      "grad_norm": 0.5559708671866962,
      "learning_rate": 5e-06,
      "loss": 0.4739,
      "step": 860
    },
    {
      "epoch": 2.166874221668742,
      "grad_norm": 0.590838180422237,
      "learning_rate": 5e-06,
      "loss": 0.4781,
      "step": 870
    },
    {
      "epoch": 2.191780821917808,
      "grad_norm": 0.5449563311605545,
      "learning_rate": 5e-06,
      "loss": 0.4768,
      "step": 880
    },
    {
      "epoch": 2.216687422166874,
      "grad_norm": 0.49509703126867355,
      "learning_rate": 5e-06,
      "loss": 0.4702,
      "step": 890
    },
    {
      "epoch": 2.2415940224159403,
      "grad_norm": 0.583235606431074,
      "learning_rate": 5e-06,
      "loss": 0.4785,
      "step": 900
    },
    {
      "epoch": 2.2665006226650064,
      "grad_norm": 0.5224340118110492,
      "learning_rate": 5e-06,
      "loss": 0.4688,
      "step": 910
    },
    {
      "epoch": 2.291407222914072,
      "grad_norm": 0.5751594164855693,
      "learning_rate": 5e-06,
      "loss": 0.4685,
      "step": 920
    },
    {
      "epoch": 2.316313823163138,
      "grad_norm": 0.5440703036591379,
      "learning_rate": 5e-06,
      "loss": 0.4773,
      "step": 930
    },
    {
      "epoch": 2.3412204234122043,
      "grad_norm": 0.7610931862664628,
      "learning_rate": 5e-06,
      "loss": 0.472,
      "step": 940
    },
    {
      "epoch": 2.3661270236612704,
      "grad_norm": 0.5531311055353737,
      "learning_rate": 5e-06,
      "loss": 0.4708,
      "step": 950
    },
    {
      "epoch": 2.391033623910336,
      "grad_norm": 0.511600827539314,
      "learning_rate": 5e-06,
      "loss": 0.4764,
      "step": 960
    },
    {
      "epoch": 2.415940224159402,
      "grad_norm": 0.5621388473604839,
      "learning_rate": 5e-06,
      "loss": 0.4792,
      "step": 970
    },
    {
      "epoch": 2.4408468244084682,
      "grad_norm": 0.574647600528262,
      "learning_rate": 5e-06,
      "loss": 0.4722,
      "step": 980
    },
    {
      "epoch": 2.4657534246575343,
      "grad_norm": 0.5174894983673209,
      "learning_rate": 5e-06,
      "loss": 0.4752,
      "step": 990
    },
    {
      "epoch": 2.4906600249066004,
      "grad_norm": 0.49985821335778424,
      "learning_rate": 5e-06,
      "loss": 0.4824,
      "step": 1000
    },
    {
      "epoch": 2.515566625155666,
      "grad_norm": 0.6533346544154589,
      "learning_rate": 5e-06,
      "loss": 0.468,
      "step": 1010
    },
    {
      "epoch": 2.540473225404732,
      "grad_norm": 0.5759385792339666,
      "learning_rate": 5e-06,
      "loss": 0.4759,
      "step": 1020
    },
    {
      "epoch": 2.5653798256537983,
      "grad_norm": 0.5706835517348989,
      "learning_rate": 5e-06,
      "loss": 0.473,
      "step": 1030
    },
    {
      "epoch": 2.5902864259028644,
      "grad_norm": 0.48023447741714353,
      "learning_rate": 5e-06,
      "loss": 0.4758,
      "step": 1040
    },
    {
      "epoch": 2.61519302615193,
      "grad_norm": 0.48468151801419096,
      "learning_rate": 5e-06,
      "loss": 0.4721,
      "step": 1050
    },
    {
      "epoch": 2.640099626400996,
      "grad_norm": 0.5091065263641408,
      "learning_rate": 5e-06,
      "loss": 0.479,
      "step": 1060
    },
    {
      "epoch": 2.6650062266500623,
      "grad_norm": 0.5876312291375192,
      "learning_rate": 5e-06,
      "loss": 0.471,
      "step": 1070
    },
    {
      "epoch": 2.6899128268991284,
      "grad_norm": 0.5815028633704035,
      "learning_rate": 5e-06,
      "loss": 0.4762,
      "step": 1080
    },
    {
      "epoch": 2.7148194271481945,
      "grad_norm": 0.5605250992780186,
      "learning_rate": 5e-06,
      "loss": 0.4735,
      "step": 1090
    },
    {
      "epoch": 2.73972602739726,
      "grad_norm": 0.5741942655339728,
      "learning_rate": 5e-06,
      "loss": 0.4747,
      "step": 1100
    },
    {
      "epoch": 2.7646326276463262,
      "grad_norm": 0.4775069856578055,
      "learning_rate": 5e-06,
      "loss": 0.4757,
      "step": 1110
    },
    {
      "epoch": 2.7895392278953923,
      "grad_norm": 0.498224788090082,
      "learning_rate": 5e-06,
      "loss": 0.4741,
      "step": 1120
    },
    {
      "epoch": 2.8144458281444584,
      "grad_norm": 0.48637748558305866,
      "learning_rate": 5e-06,
      "loss": 0.4767,
      "step": 1130
    },
    {
      "epoch": 2.839352428393524,
      "grad_norm": 0.5090237580915907,
      "learning_rate": 5e-06,
      "loss": 0.4734,
      "step": 1140
    },
    {
      "epoch": 2.86425902864259,
      "grad_norm": 0.4947938642895003,
      "learning_rate": 5e-06,
      "loss": 0.4782,
      "step": 1150
    },
    {
      "epoch": 2.8891656288916563,
      "grad_norm": 0.5195966815447782,
      "learning_rate": 5e-06,
      "loss": 0.4803,
      "step": 1160
    },
    {
      "epoch": 2.9140722291407224,
      "grad_norm": 0.5212585367090384,
      "learning_rate": 5e-06,
      "loss": 0.4722,
      "step": 1170
    },
    {
      "epoch": 2.9389788293897885,
      "grad_norm": 0.514479905781623,
      "learning_rate": 5e-06,
      "loss": 0.4752,
      "step": 1180
    },
    {
      "epoch": 2.963885429638854,
      "grad_norm": 0.5039971892926054,
      "learning_rate": 5e-06,
      "loss": 0.475,
      "step": 1190
    },
    {
      "epoch": 2.9887920298879203,
      "grad_norm": 0.4924909134578761,
      "learning_rate": 5e-06,
      "loss": 0.4697,
      "step": 1200
    },
    {
      "epoch": 2.99626400996264,
      "eval_loss": 0.5331025123596191,
      "eval_runtime": 217.1359,
      "eval_samples_per_second": 49.826,
      "eval_steps_per_second": 0.391,
      "step": 1203
    },
    {
      "epoch": 2.99626400996264,
      "step": 1203,
      "total_flos": 2014651046952960.0,
      "train_loss": 0.5350556444943397,
      "train_runtime": 35909.5127,
      "train_samples_per_second": 17.172,
      "train_steps_per_second": 0.034
    }
  ],
  "logging_steps": 10,
  "max_steps": 1203,
  "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": 2014651046952960.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}