{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 84,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03614457831325301,
      "grad_norm": 3.5530667304992676,
      "learning_rate": 0.0,
      "loss": 0.8157972693443298,
      "step": 1
    },
    {
      "epoch": 0.07228915662650602,
      "grad_norm": 3.475752353668213,
      "learning_rate": 1.111111111111111e-06,
      "loss": 0.8220954537391663,
      "step": 2
    },
    {
      "epoch": 0.10843373493975904,
      "grad_norm": 3.383586883544922,
      "learning_rate": 2.222222222222222e-06,
      "loss": 0.8105647563934326,
      "step": 3
    },
    {
      "epoch": 0.14457831325301204,
      "grad_norm": 3.3059158325195312,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.7966299057006836,
      "step": 4
    },
    {
      "epoch": 0.18072289156626506,
      "grad_norm": 2.887650728225708,
      "learning_rate": 4.444444444444444e-06,
      "loss": 0.7848972082138062,
      "step": 5
    },
    {
      "epoch": 0.21686746987951808,
      "grad_norm": 2.0149731636047363,
      "learning_rate": 5.555555555555557e-06,
      "loss": 0.7373118996620178,
      "step": 6
    },
    {
      "epoch": 0.25301204819277107,
      "grad_norm": 1.521030068397522,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.7128340601921082,
      "step": 7
    },
    {
      "epoch": 0.2891566265060241,
      "grad_norm": 1.3453000783920288,
      "learning_rate": 7.77777777777778e-06,
      "loss": 0.706008791923523,
      "step": 8
    },
    {
      "epoch": 0.3253012048192771,
      "grad_norm": 1.3435814380645752,
      "learning_rate": 8.888888888888888e-06,
      "loss": 0.7266546487808228,
      "step": 9
    },
    {
      "epoch": 0.3614457831325301,
      "grad_norm": 2.6775221824645996,
      "learning_rate": 1e-05,
      "loss": 0.7641190886497498,
      "step": 10
    },
    {
      "epoch": 0.39759036144578314,
      "grad_norm": 2.31797456741333,
      "learning_rate": 9.995614150494293e-06,
      "loss": 0.7511537075042725,
      "step": 11
    },
    {
      "epoch": 0.43373493975903615,
      "grad_norm": 1.8419780731201172,
      "learning_rate": 9.982464296247523e-06,
      "loss": 0.725541353225708,
      "step": 12
    },
    {
      "epoch": 0.46987951807228917,
      "grad_norm": 1.5448116064071655,
      "learning_rate": 9.960573506572391e-06,
      "loss": 0.7165950536727905,
      "step": 13
    },
    {
      "epoch": 0.5060240963855421,
      "grad_norm": 1.3775088787078857,
      "learning_rate": 9.929980185352525e-06,
      "loss": 0.7150700688362122,
      "step": 14
    },
    {
      "epoch": 0.5421686746987951,
      "grad_norm": 1.2375344038009644,
      "learning_rate": 9.890738003669029e-06,
      "loss": 0.7106208801269531,
      "step": 15
    },
    {
      "epoch": 0.5783132530120482,
      "grad_norm": 1.0106751918792725,
      "learning_rate": 9.842915805643156e-06,
      "loss": 0.6804662942886353,
      "step": 16
    },
    {
      "epoch": 0.6144578313253012,
      "grad_norm": 1.026816487312317,
      "learning_rate": 9.786597487660336e-06,
      "loss": 0.6793582439422607,
      "step": 17
    },
    {
      "epoch": 0.6506024096385542,
      "grad_norm": 0.960710346698761,
      "learning_rate": 9.721881851187406e-06,
      "loss": 0.6606736779212952,
      "step": 18
    },
    {
      "epoch": 0.6867469879518072,
      "grad_norm": 0.8846614956855774,
      "learning_rate": 9.648882429441258e-06,
      "loss": 0.6600944399833679,
      "step": 19
    },
    {
      "epoch": 0.7228915662650602,
      "grad_norm": 0.7778003215789795,
      "learning_rate": 9.567727288213005e-06,
      "loss": 0.6360255479812622,
      "step": 20
    },
    {
      "epoch": 0.7590361445783133,
      "grad_norm": 0.7867444157600403,
      "learning_rate": 9.478558801197065e-06,
      "loss": 0.6492308378219604,
      "step": 21
    },
    {
      "epoch": 0.7951807228915663,
      "grad_norm": 0.9391480684280396,
      "learning_rate": 9.381533400219319e-06,
      "loss": 0.6748710870742798,
      "step": 22
    },
    {
      "epoch": 0.8313253012048193,
      "grad_norm": 0.7031015157699585,
      "learning_rate": 9.276821300802535e-06,
      "loss": 0.6428183913230896,
      "step": 23
    },
    {
      "epoch": 0.8674698795180723,
      "grad_norm": 0.6937193274497986,
      "learning_rate": 9.164606203550498e-06,
      "loss": 0.6585266590118408,
      "step": 24
    },
    {
      "epoch": 0.9036144578313253,
      "grad_norm": 0.6111941933631897,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.6351627111434937,
      "step": 25
    },
    {
      "epoch": 0.9397590361445783,
      "grad_norm": 0.6165474653244019,
      "learning_rate": 8.9184672866292e-06,
      "loss": 0.6526360511779785,
      "step": 26
    },
    {
      "epoch": 0.9759036144578314,
      "grad_norm": 0.5291957855224609,
      "learning_rate": 8.784975278258783e-06,
      "loss": 0.6265251636505127,
      "step": 27
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6292035579681396,
      "learning_rate": 8.644843137107058e-06,
      "loss": 0.6393284797668457,
      "step": 28
    },
    {
      "epoch": 1.036144578313253,
      "grad_norm": 0.5975921750068665,
      "learning_rate": 8.498316702566828e-06,
      "loss": 0.5895029306411743,
      "step": 29
    },
    {
      "epoch": 1.072289156626506,
      "grad_norm": 0.5670790672302246,
      "learning_rate": 8.345653031794292e-06,
      "loss": 0.5864728093147278,
      "step": 30
    },
    {
      "epoch": 1.108433734939759,
      "grad_norm": 0.7133178114891052,
      "learning_rate": 8.18711994874345e-06,
      "loss": 0.5745179653167725,
      "step": 31
    },
    {
      "epoch": 1.144578313253012,
      "grad_norm": 0.5750840306282043,
      "learning_rate": 8.022995574311876e-06,
      "loss": 0.5763933658599854,
      "step": 32
    },
    {
      "epoch": 1.180722891566265,
      "grad_norm": 0.5429960489273071,
      "learning_rate": 7.85356783842216e-06,
      "loss": 0.5829252600669861,
      "step": 33
    },
    {
      "epoch": 1.216867469879518,
      "grad_norm": 0.5182336568832397,
      "learning_rate": 7.679133974894984e-06,
      "loss": 0.5825693011283875,
      "step": 34
    },
    {
      "epoch": 1.2530120481927711,
      "grad_norm": 0.5491313934326172,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.5764566659927368,
      "step": 35
    },
    {
      "epoch": 1.2891566265060241,
      "grad_norm": 0.5254521369934082,
      "learning_rate": 7.31648017559931e-06,
      "loss": 0.5880482792854309,
      "step": 36
    },
    {
      "epoch": 1.3253012048192772,
      "grad_norm": 0.5171566009521484,
      "learning_rate": 7.128896457825364e-06,
      "loss": 0.6008750200271606,
      "step": 37
    },
    {
      "epoch": 1.3614457831325302,
      "grad_norm": 0.46462559700012207,
      "learning_rate": 6.9375779322605154e-06,
      "loss": 0.5682947635650635,
      "step": 38
    },
    {
      "epoch": 1.3975903614457832,
      "grad_norm": 0.5075864791870117,
      "learning_rate": 6.7428602366090764e-06,
      "loss": 0.5605165362358093,
      "step": 39
    },
    {
      "epoch": 1.4337349397590362,
      "grad_norm": 0.49260249733924866,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.5598280429840088,
      "step": 40
    },
    {
      "epoch": 1.4698795180722892,
      "grad_norm": 0.4913742244243622,
      "learning_rate": 6.344599103076329e-06,
      "loss": 0.5590924024581909,
      "step": 41
    },
    {
      "epoch": 1.5060240963855422,
      "grad_norm": 0.43512162566185,
      "learning_rate": 6.141754350553279e-06,
      "loss": 0.5489959716796875,
      "step": 42
    },
    {
      "epoch": 1.5421686746987953,
      "grad_norm": 0.46241137385368347,
      "learning_rate": 5.936906572928625e-06,
      "loss": 0.5644493103027344,
      "step": 43
    },
    {
      "epoch": 1.5783132530120483,
      "grad_norm": 0.43606171011924744,
      "learning_rate": 5.730415142812059e-06,
      "loss": 0.5436263084411621,
      "step": 44
    },
    {
      "epoch": 1.6144578313253013,
      "grad_norm": 0.5366220474243164,
      "learning_rate": 5.522642316338268e-06,
      "loss": 0.5769392251968384,
      "step": 45
    },
    {
      "epoch": 1.6506024096385543,
      "grad_norm": 0.5427200794219971,
      "learning_rate": 5.3139525976465675e-06,
      "loss": 0.5742834210395813,
      "step": 46
    },
    {
      "epoch": 1.6867469879518073,
      "grad_norm": 0.4113039970397949,
      "learning_rate": 5.1047120994167855e-06,
      "loss": 0.5463815927505493,
      "step": 47
    },
    {
      "epoch": 1.7228915662650603,
      "grad_norm": 0.44332143664360046,
      "learning_rate": 4.895287900583216e-06,
      "loss": 0.572960615158081,
      "step": 48
    },
    {
      "epoch": 1.7590361445783134,
      "grad_norm": 0.4870039224624634,
      "learning_rate": 4.686047402353433e-06,
      "loss": 0.5843434929847717,
      "step": 49
    },
    {
      "epoch": 1.7951807228915664,
      "grad_norm": 0.44245144724845886,
      "learning_rate": 4.477357683661734e-06,
      "loss": 0.5725433230400085,
      "step": 50
    },
    {
      "epoch": 1.8313253012048194,
      "grad_norm": 0.43352383375167847,
      "learning_rate": 4.269584857187942e-06,
      "loss": 0.55963134765625,
      "step": 51
    },
    {
      "epoch": 1.8674698795180724,
      "grad_norm": 0.45807719230651855,
      "learning_rate": 4.063093427071376e-06,
      "loss": 0.5634369850158691,
      "step": 52
    },
    {
      "epoch": 1.9036144578313254,
      "grad_norm": 0.4268049895763397,
      "learning_rate": 3.8582456494467214e-06,
      "loss": 0.582618772983551,
      "step": 53
    },
    {
      "epoch": 1.9397590361445785,
      "grad_norm": 0.4014423191547394,
      "learning_rate": 3.655400896923672e-06,
      "loss": 0.5639011859893799,
      "step": 54
    },
    {
      "epoch": 1.9759036144578315,
      "grad_norm": 0.4203037917613983,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.5671670436859131,
      "step": 55
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.5056357979774475,
      "learning_rate": 3.2571397633909252e-06,
      "loss": 0.5666017532348633,
      "step": 56
    },
    {
      "epoch": 2.036144578313253,
      "grad_norm": 0.42152824997901917,
      "learning_rate": 3.0624220677394854e-06,
      "loss": 0.5147315263748169,
      "step": 57
    },
    {
      "epoch": 2.072289156626506,
      "grad_norm": 0.4358435273170471,
      "learning_rate": 2.871103542174637e-06,
      "loss": 0.5106508731842041,
      "step": 58
    },
    {
      "epoch": 2.108433734939759,
      "grad_norm": 0.4385116994380951,
      "learning_rate": 2.683519824400693e-06,
      "loss": 0.5132982134819031,
      "step": 59
    },
    {
      "epoch": 2.144578313253012,
      "grad_norm": 0.42670226097106934,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.504179060459137,
      "step": 60
    },
    {
      "epoch": 2.180722891566265,
      "grad_norm": 0.48987889289855957,
      "learning_rate": 2.320866025105016e-06,
      "loss": 0.5210374593734741,
      "step": 61
    },
    {
      "epoch": 2.216867469879518,
      "grad_norm": 0.4328784942626953,
      "learning_rate": 2.146432161577842e-06,
      "loss": 0.5118027925491333,
      "step": 62
    },
    {
      "epoch": 2.253012048192771,
      "grad_norm": 0.3858642578125,
      "learning_rate": 1.977004425688126e-06,
      "loss": 0.4922132194042206,
      "step": 63
    },
    {
      "epoch": 2.289156626506024,
      "grad_norm": 0.38921093940734863,
      "learning_rate": 1.8128800512565514e-06,
      "loss": 0.501984715461731,
      "step": 64
    },
    {
      "epoch": 2.325301204819277,
      "grad_norm": 0.3826121389865875,
      "learning_rate": 1.6543469682057105e-06,
      "loss": 0.5015629529953003,
      "step": 65
    },
    {
      "epoch": 2.36144578313253,
      "grad_norm": 0.40731289982795715,
      "learning_rate": 1.5016832974331725e-06,
      "loss": 0.5080351829528809,
      "step": 66
    },
    {
      "epoch": 2.397590361445783,
      "grad_norm": 0.3691997826099396,
      "learning_rate": 1.3551568628929434e-06,
      "loss": 0.5081236362457275,
      "step": 67
    },
    {
      "epoch": 2.433734939759036,
      "grad_norm": 0.3707135319709778,
      "learning_rate": 1.2150247217412186e-06,
      "loss": 0.5000795125961304,
      "step": 68
    },
    {
      "epoch": 2.4698795180722892,
      "grad_norm": 0.4231833517551422,
      "learning_rate": 1.0815327133708015e-06,
      "loss": 0.489562064409256,
      "step": 69
    },
    {
      "epoch": 2.5060240963855422,
      "grad_norm": 0.44199568033218384,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.5084055066108704,
      "step": 70
    },
    {
      "epoch": 2.5421686746987953,
      "grad_norm": 0.3709920048713684,
      "learning_rate": 8.353937964495029e-07,
      "loss": 0.5084290504455566,
      "step": 71
    },
    {
      "epoch": 2.5783132530120483,
      "grad_norm": 0.39795491099357605,
      "learning_rate": 7.23178699197467e-07,
      "loss": 0.513380229473114,
      "step": 72
    },
    {
      "epoch": 2.6144578313253013,
      "grad_norm": 0.36789605021476746,
      "learning_rate": 6.184665997806832e-07,
      "loss": 0.47666290402412415,
      "step": 73
    },
    {
      "epoch": 2.6506024096385543,
      "grad_norm": 0.38667839765548706,
      "learning_rate": 5.214411988029355e-07,
      "loss": 0.4979460835456848,
      "step": 74
    },
    {
      "epoch": 2.6867469879518073,
      "grad_norm": 0.5737469792366028,
      "learning_rate": 4.322727117869951e-07,
      "loss": 0.5057819485664368,
      "step": 75
    },
    {
      "epoch": 2.7228915662650603,
      "grad_norm": 0.4119950234889984,
      "learning_rate": 3.511175705587433e-07,
      "loss": 0.4980058968067169,
      "step": 76
    },
    {
      "epoch": 2.7590361445783134,
      "grad_norm": 0.38781502842903137,
      "learning_rate": 2.7811814881259503e-07,
      "loss": 0.5025761723518372,
      "step": 77
    },
    {
      "epoch": 2.7951807228915664,
      "grad_norm": 0.394298255443573,
      "learning_rate": 2.134025123396638e-07,
      "loss": 0.4871373176574707,
      "step": 78
    },
    {
      "epoch": 2.8313253012048194,
      "grad_norm": 0.34674161672592163,
      "learning_rate": 1.5708419435684463e-07,
      "loss": 0.5203001499176025,
      "step": 79
    },
    {
      "epoch": 2.8674698795180724,
      "grad_norm": 0.3848899006843567,
      "learning_rate": 1.0926199633097156e-07,
      "loss": 0.4973796010017395,
      "step": 80
    },
    {
      "epoch": 2.9036144578313254,
      "grad_norm": 0.3862093985080719,
      "learning_rate": 7.001981464747565e-08,
      "loss": 0.5090079307556152,
      "step": 81
    },
    {
      "epoch": 2.9397590361445785,
      "grad_norm": 0.39008447527885437,
      "learning_rate": 3.9426493427611177e-08,
      "loss": 0.5036866068840027,
      "step": 82
    },
    {
      "epoch": 2.9759036144578315,
      "grad_norm": 0.3627244830131531,
      "learning_rate": 1.753570375247815e-08,
      "loss": 0.5087746977806091,
      "step": 83
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.4105032980442047,
      "learning_rate": 4.385849505708084e-09,
      "loss": 0.5212332010269165,
      "step": 84
    }
  ],
  "logging_steps": 1,
  "max_steps": 84,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 105954970763264.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}