{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.019436345966958212,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 4.318624496459961,
      "learning_rate": 0.00019805941782534764,
      "loss": 9.3465,
      "step": 1
    },
    {
      "epoch": 0.0,
      "grad_norm": 6.591656684875488,
      "learning_rate": 0.00019605881764529358,
      "loss": 12.8608,
      "step": 2
    },
    {
      "epoch": 0.0,
      "grad_norm": 9.56568431854248,
      "learning_rate": 0.00019405821746523957,
      "loss": 11.289,
      "step": 3
    },
    {
      "epoch": 0.0,
      "grad_norm": 7.295264720916748,
      "learning_rate": 0.00019205761728518557,
      "loss": 6.2966,
      "step": 4
    },
    {
      "epoch": 0.0,
      "grad_norm": 6.040774822235107,
      "learning_rate": 0.00019005701710513156,
      "loss": 4.4317,
      "step": 5
    },
    {
      "epoch": 0.0,
      "grad_norm": 13.841460227966309,
      "learning_rate": 0.00018805641692507753,
      "loss": 5.0921,
      "step": 6
    },
    {
      "epoch": 0.0,
      "grad_norm": 12.43684196472168,
      "learning_rate": 0.00018605581674502352,
      "loss": 3.8523,
      "step": 7
    },
    {
      "epoch": 0.0,
      "grad_norm": 7.349277973175049,
      "learning_rate": 0.00018405521656496952,
      "loss": 3.0653,
      "step": 8
    },
    {
      "epoch": 0.0,
      "grad_norm": 2.4729762077331543,
      "learning_rate": 0.00018205461638491548,
      "loss": 2.5825,
      "step": 9
    },
    {
      "epoch": 0.0,
      "grad_norm": 3.187196969985962,
      "learning_rate": 0.00018005401620486148,
      "loss": 2.1595,
      "step": 10
    },
    {
      "epoch": 0.0,
      "grad_norm": 2.3855996131896973,
      "learning_rate": 0.00017805341602480744,
      "loss": 2.1515,
      "step": 11
    },
    {
      "epoch": 0.0,
      "grad_norm": 2.119424343109131,
      "learning_rate": 0.00017605281584475344,
      "loss": 2.3592,
      "step": 12
    },
    {
      "epoch": 0.0,
      "grad_norm": 1.1523925065994263,
      "learning_rate": 0.00017405221566469943,
      "loss": 2.3854,
      "step": 13
    },
    {
      "epoch": 0.0,
      "grad_norm": 2.134817361831665,
      "learning_rate": 0.00017205161548464542,
      "loss": 1.4468,
      "step": 14
    },
    {
      "epoch": 0.0,
      "grad_norm": 1.452102780342102,
      "learning_rate": 0.00017005101530459136,
      "loss": 2.0123,
      "step": 15
    },
    {
      "epoch": 0.0,
      "grad_norm": 4.131059646606445,
      "learning_rate": 0.00016805041512453736,
      "loss": 2.1094,
      "step": 16
    },
    {
      "epoch": 0.0,
      "grad_norm": 2.092371940612793,
      "learning_rate": 0.00016604981494448335,
      "loss": 1.5696,
      "step": 17
    },
    {
      "epoch": 0.0,
      "grad_norm": 1.253164529800415,
      "learning_rate": 0.00016404921476442935,
      "loss": 1.4767,
      "step": 18
    },
    {
      "epoch": 0.0,
      "grad_norm": 1.338577151298523,
      "learning_rate": 0.0001620486145843753,
      "loss": 2.338,
      "step": 19
    },
    {
      "epoch": 0.0,
      "grad_norm": 1.121963381767273,
      "learning_rate": 0.0001600480144043213,
      "loss": 2.0752,
      "step": 20
    },
    {
      "epoch": 0.0,
      "grad_norm": 1.5833094120025635,
      "learning_rate": 0.0001580474142242673,
      "loss": 1.4675,
      "step": 21
    },
    {
      "epoch": 0.0,
      "grad_norm": 1.428231954574585,
      "learning_rate": 0.00015604681404421327,
      "loss": 1.3554,
      "step": 22
    },
    {
      "epoch": 0.0,
      "grad_norm": 1.5906881093978882,
      "learning_rate": 0.00015404621386415926,
      "loss": 1.703,
      "step": 23
    },
    {
      "epoch": 0.0,
      "grad_norm": 1.2706618309020996,
      "learning_rate": 0.00015204561368410523,
      "loss": 1.7487,
      "step": 24
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.8932807445526123,
      "learning_rate": 0.00015004501350405122,
      "loss": 1.8345,
      "step": 25
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.8607711791992188,
      "learning_rate": 0.00014804441332399721,
      "loss": 1.1681,
      "step": 26
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.011381983757019,
      "learning_rate": 0.0001460438131439432,
      "loss": 1.7756,
      "step": 27
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.0185519456863403,
      "learning_rate": 0.00014404321296388918,
      "loss": 1.3468,
      "step": 28
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.6411266326904297,
      "learning_rate": 0.00014204261278383514,
      "loss": 2.116,
      "step": 29
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.9967129826545715,
      "learning_rate": 0.00014004201260378114,
      "loss": 1.6774,
      "step": 30
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.3136436939239502,
      "learning_rate": 0.00013804141242372713,
      "loss": 2.0461,
      "step": 31
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.4330521821975708,
      "learning_rate": 0.00013604081224367312,
      "loss": 2.1365,
      "step": 32
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.1006214618682861,
      "learning_rate": 0.0001340402120636191,
      "loss": 0.4195,
      "step": 33
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.9954245686531067,
      "learning_rate": 0.00013203961188356508,
      "loss": 1.4915,
      "step": 34
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.8714771270751953,
      "learning_rate": 0.00013003901170351108,
      "loss": 1.4862,
      "step": 35
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.8504552841186523,
      "learning_rate": 0.00012803841152345704,
      "loss": 1.2124,
      "step": 36
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.5393089056015015,
      "learning_rate": 0.000126037811343403,
      "loss": 2.0633,
      "step": 37
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.018890142440796,
      "learning_rate": 0.000124037211163349,
      "loss": 0.6224,
      "step": 38
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.2864466905593872,
      "learning_rate": 0.000122036610983295,
      "loss": 1.795,
      "step": 39
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.0033133029937744,
      "learning_rate": 0.00012003601080324098,
      "loss": 0.7465,
      "step": 40
    },
    {
      "epoch": 0.01,
      "grad_norm": 3.63820481300354,
      "learning_rate": 0.00011803541062318697,
      "loss": 1.3544,
      "step": 41
    },
    {
      "epoch": 0.01,
      "grad_norm": 3.668487787246704,
      "learning_rate": 0.00011603481044313295,
      "loss": 1.9775,
      "step": 42
    },
    {
      "epoch": 0.01,
      "grad_norm": 11.158123016357422,
      "learning_rate": 0.00011403421026307892,
      "loss": 1.2352,
      "step": 43
    },
    {
      "epoch": 0.01,
      "grad_norm": 3.3200602531433105,
      "learning_rate": 0.00011203361008302491,
      "loss": 1.5836,
      "step": 44
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.0530873537063599,
      "learning_rate": 0.0001100330099029709,
      "loss": 1.5381,
      "step": 45
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.1884853839874268,
      "learning_rate": 0.00010803240972291689,
      "loss": 1.6451,
      "step": 46
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.3888977766036987,
      "learning_rate": 0.00010603180954286287,
      "loss": 1.5273,
      "step": 47
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.9774441123008728,
      "learning_rate": 0.00010403120936280886,
      "loss": 1.9541,
      "step": 48
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.068190097808838,
      "learning_rate": 0.00010203060918275482,
      "loss": 1.6002,
      "step": 49
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.28312087059021,
      "learning_rate": 0.00010003000900270081,
      "loss": 2.0254,
      "step": 50
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.3461538553237915,
      "learning_rate": 9.802940882264679e-05,
      "loss": 1.3561,
      "step": 51
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.3271141052246094,
      "learning_rate": 9.602880864259278e-05,
      "loss": 1.361,
      "step": 52
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.3316106796264648,
      "learning_rate": 9.402820846253876e-05,
      "loss": 1.7272,
      "step": 53
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.97672039270401,
      "learning_rate": 9.202760828248476e-05,
      "loss": 0.708,
      "step": 54
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.9566367864608765,
      "learning_rate": 9.002700810243074e-05,
      "loss": 1.5139,
      "step": 55
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.0057029724121094,
      "learning_rate": 8.802640792237672e-05,
      "loss": 1.2497,
      "step": 56
    },
    {
      "epoch": 0.01,
      "grad_norm": 9.65938663482666,
      "learning_rate": 8.602580774232271e-05,
      "loss": 1.4,
      "step": 57
    },
    {
      "epoch": 0.01,
      "grad_norm": 2.8687500953674316,
      "learning_rate": 8.402520756226868e-05,
      "loss": 2.0894,
      "step": 58
    },
    {
      "epoch": 0.01,
      "grad_norm": 7.262545108795166,
      "learning_rate": 8.202460738221467e-05,
      "loss": 0.9389,
      "step": 59
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.3187130689620972,
      "learning_rate": 8.002400720216065e-05,
      "loss": 1.3847,
      "step": 60
    },
    {
      "epoch": 0.01,
      "grad_norm": 5.589620590209961,
      "learning_rate": 7.802340702210663e-05,
      "loss": 0.4888,
      "step": 61
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.8035283088684082,
      "learning_rate": 7.602280684205261e-05,
      "loss": 1.3295,
      "step": 62
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.8805381059646606,
      "learning_rate": 7.402220666199861e-05,
      "loss": 1.6203,
      "step": 63
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.222285509109497,
      "learning_rate": 7.202160648194459e-05,
      "loss": 1.3659,
      "step": 64
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.1526193618774414,
      "learning_rate": 7.002100630189057e-05,
      "loss": 1.9816,
      "step": 65
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.8536458015441895,
      "learning_rate": 6.802040612183656e-05,
      "loss": 1.0255,
      "step": 66
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.1652932167053223,
      "learning_rate": 6.601980594178254e-05,
      "loss": 0.9737,
      "step": 67
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.8228743076324463,
      "learning_rate": 6.401920576172852e-05,
      "loss": 0.9365,
      "step": 68
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.7666674852371216,
      "learning_rate": 6.20186055816745e-05,
      "loss": 1.1326,
      "step": 69
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.9048521518707275,
      "learning_rate": 6.001800540162049e-05,
      "loss": 1.8278,
      "step": 70
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.013771891593933,
      "learning_rate": 5.801740522156648e-05,
      "loss": 1.2261,
      "step": 71
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.0149589776992798,
      "learning_rate": 5.601680504151246e-05,
      "loss": 1.7701,
      "step": 72
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.3616000413894653,
      "learning_rate": 5.4016204861458444e-05,
      "loss": 1.3506,
      "step": 73
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.3497377634048462,
      "learning_rate": 5.201560468140443e-05,
      "loss": 1.1989,
      "step": 74
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.9258934855461121,
      "learning_rate": 5.0015004501350405e-05,
      "loss": 1.5837,
      "step": 75
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.7765821814537048,
      "learning_rate": 4.801440432129639e-05,
      "loss": 1.3821,
      "step": 76
    },
    {
      "epoch": 0.01,
      "grad_norm": 1.5330684185028076,
      "learning_rate": 4.601380414124238e-05,
      "loss": 1.2167,
      "step": 77
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.8043363690376282,
      "learning_rate": 4.401320396118836e-05,
      "loss": 1.0048,
      "step": 78
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.0334686040878296,
      "learning_rate": 4.201260378113434e-05,
      "loss": 1.0847,
      "step": 79
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.02166748046875,
      "learning_rate": 4.0012003601080326e-05,
      "loss": 1.1226,
      "step": 80
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.7887734770774841,
      "learning_rate": 3.801140342102631e-05,
      "loss": 0.7872,
      "step": 81
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.9185380339622498,
      "learning_rate": 3.6010803240972294e-05,
      "loss": 0.9887,
      "step": 82
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.8893826007843018,
      "learning_rate": 3.401020306091828e-05,
      "loss": 1.3784,
      "step": 83
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.1666996479034424,
      "learning_rate": 3.200960288086426e-05,
      "loss": 1.5805,
      "step": 84
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.330802321434021,
      "learning_rate": 3.0009002700810245e-05,
      "loss": 1.2388,
      "step": 85
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.092350959777832,
      "learning_rate": 2.800840252075623e-05,
      "loss": 1.7721,
      "step": 86
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.0547586679458618,
      "learning_rate": 2.6007802340702216e-05,
      "loss": 1.8803,
      "step": 87
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.0033807754516602,
      "learning_rate": 2.4007202160648196e-05,
      "loss": 1.6825,
      "step": 88
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.6005492210388184,
      "learning_rate": 2.200660198059418e-05,
      "loss": 1.9344,
      "step": 89
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.8459662795066833,
      "learning_rate": 2.0006001800540163e-05,
      "loss": 1.0833,
      "step": 90
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.7953637838363647,
      "learning_rate": 1.8005401620486147e-05,
      "loss": 1.2859,
      "step": 91
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.0880411863327026,
      "learning_rate": 1.600480144043213e-05,
      "loss": 1.3714,
      "step": 92
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.3695777654647827,
      "learning_rate": 1.4004201260378114e-05,
      "loss": 1.3642,
      "step": 93
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.9539559483528137,
      "learning_rate": 1.2003601080324098e-05,
      "loss": 1.2392,
      "step": 94
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.958608865737915,
      "learning_rate": 1.0003000900270082e-05,
      "loss": 1.0437,
      "step": 95
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.9105627536773682,
      "learning_rate": 8.002400720216065e-06,
      "loss": 1.0925,
      "step": 96
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.4394004344940186,
      "learning_rate": 6.001800540162049e-06,
      "loss": 1.2812,
      "step": 97
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.986015260219574,
      "learning_rate": 4.001200360108033e-06,
      "loss": 1.1349,
      "step": 98
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.9465481042861938,
      "learning_rate": 2.0006001800540163e-06,
      "loss": 1.1348,
      "step": 99
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.0053468942642212,
      "learning_rate": 0.0,
      "loss": 1.1546,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 5736360454225920.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}