{
  "best_metric": 1.8782081604003906,
  "best_model_checkpoint": "outputs/checkpoint-100",
  "epoch": 0.14917024053701286,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014917024053701287,
      "grad_norm": 2.6047203540802,
      "learning_rate": 4e-05,
      "loss": 1.9885,
      "step": 1
    },
    {
      "epoch": 0.0029834048107402573,
      "grad_norm": 3.559100389480591,
      "learning_rate": 8e-05,
      "loss": 2.01,
      "step": 2
    },
    {
      "epoch": 0.004475107216110386,
      "grad_norm": 2.0908730030059814,
      "learning_rate": 0.00012,
      "loss": 1.9122,
      "step": 3
    },
    {
      "epoch": 0.005966809621480515,
      "grad_norm": 2.6787052154541016,
      "learning_rate": 0.00016,
      "loss": 1.8426,
      "step": 4
    },
    {
      "epoch": 0.007458512026850644,
      "grad_norm": 1.9292813539505005,
      "learning_rate": 0.0002,
      "loss": 1.767,
      "step": 5
    },
    {
      "epoch": 0.008950214432220773,
      "grad_norm": 1.3694391250610352,
      "learning_rate": 0.0001996638655462185,
      "loss": 1.9173,
      "step": 6
    },
    {
      "epoch": 0.0104419168375909,
      "grad_norm": 1.817445993423462,
      "learning_rate": 0.00019932773109243698,
      "loss": 1.8486,
      "step": 7
    },
    {
      "epoch": 0.01193361924296103,
      "grad_norm": 1.4658751487731934,
      "learning_rate": 0.00019899159663865548,
      "loss": 1.9785,
      "step": 8
    },
    {
      "epoch": 0.013425321648331158,
      "grad_norm": 1.6042131185531616,
      "learning_rate": 0.00019865546218487395,
      "loss": 1.9975,
      "step": 9
    },
    {
      "epoch": 0.014917024053701287,
      "grad_norm": 1.5578440427780151,
      "learning_rate": 0.00019831932773109245,
      "loss": 1.8709,
      "step": 10
    },
    {
      "epoch": 0.016408726459071415,
      "grad_norm": 1.6463985443115234,
      "learning_rate": 0.00019798319327731095,
      "loss": 1.838,
      "step": 11
    },
    {
      "epoch": 0.017900428864441546,
      "grad_norm": 1.4298287630081177,
      "learning_rate": 0.00019764705882352942,
      "loss": 1.9203,
      "step": 12
    },
    {
      "epoch": 0.019392131269811673,
      "grad_norm": 1.7401193380355835,
      "learning_rate": 0.00019731092436974792,
      "loss": 1.7784,
      "step": 13
    },
    {
      "epoch": 0.0208838336751818,
      "grad_norm": 2.249098062515259,
      "learning_rate": 0.00019697478991596642,
      "loss": 1.7385,
      "step": 14
    },
    {
      "epoch": 0.02237553608055193,
      "grad_norm": 1.2887922525405884,
      "learning_rate": 0.00019663865546218486,
      "loss": 1.8462,
      "step": 15
    },
    {
      "epoch": 0.02386723848592206,
      "grad_norm": 1.374350905418396,
      "learning_rate": 0.00019630252100840336,
      "loss": 1.8092,
      "step": 16
    },
    {
      "epoch": 0.025358940891292186,
      "grad_norm": 1.2544641494750977,
      "learning_rate": 0.00019596638655462186,
      "loss": 1.8555,
      "step": 17
    },
    {
      "epoch": 0.026850643296662317,
      "grad_norm": 1.4571586847305298,
      "learning_rate": 0.00019563025210084033,
      "loss": 1.8792,
      "step": 18
    },
    {
      "epoch": 0.028342345702032444,
      "grad_norm": 1.2989751100540161,
      "learning_rate": 0.00019529411764705883,
      "loss": 1.9073,
      "step": 19
    },
    {
      "epoch": 0.029834048107402575,
      "grad_norm": 1.1583518981933594,
      "learning_rate": 0.0001949579831932773,
      "loss": 1.9557,
      "step": 20
    },
    {
      "epoch": 0.0313257505127727,
      "grad_norm": 1.2384063005447388,
      "learning_rate": 0.0001946218487394958,
      "loss": 1.8436,
      "step": 21
    },
    {
      "epoch": 0.03281745291814283,
      "grad_norm": 1.4381242990493774,
      "learning_rate": 0.0001942857142857143,
      "loss": 1.7804,
      "step": 22
    },
    {
      "epoch": 0.03430915532351296,
      "grad_norm": 1.160043716430664,
      "learning_rate": 0.00019394957983193278,
      "loss": 1.8407,
      "step": 23
    },
    {
      "epoch": 0.03580085772888309,
      "grad_norm": 1.4776676893234253,
      "learning_rate": 0.00019361344537815127,
      "loss": 1.9378,
      "step": 24
    },
    {
      "epoch": 0.037292560134253215,
      "grad_norm": 1.365653157234192,
      "learning_rate": 0.00019327731092436975,
      "loss": 1.789,
      "step": 25
    },
    {
      "epoch": 0.037292560134253215,
      "eval_loss": 1.8776626586914062,
      "eval_runtime": 12.8602,
      "eval_samples_per_second": 4.977,
      "eval_steps_per_second": 2.488,
      "step": 25
    },
    {
      "epoch": 0.038784262539623346,
      "grad_norm": 1.3155896663665771,
      "learning_rate": 0.00019294117647058825,
      "loss": 1.8049,
      "step": 26
    },
    {
      "epoch": 0.04027596494499348,
      "grad_norm": 1.5831129550933838,
      "learning_rate": 0.00019260504201680674,
      "loss": 1.8892,
      "step": 27
    },
    {
      "epoch": 0.0417676673503636,
      "grad_norm": 1.278041958808899,
      "learning_rate": 0.00019226890756302522,
      "loss": 1.8892,
      "step": 28
    },
    {
      "epoch": 0.04325936975573373,
      "grad_norm": 1.1963578462600708,
      "learning_rate": 0.00019193277310924372,
      "loss": 1.8318,
      "step": 29
    },
    {
      "epoch": 0.04475107216110386,
      "grad_norm": 0.9278161525726318,
      "learning_rate": 0.00019159663865546221,
      "loss": 1.9127,
      "step": 30
    },
    {
      "epoch": 0.046242774566473986,
      "grad_norm": 1.434067964553833,
      "learning_rate": 0.0001912605042016807,
      "loss": 1.8937,
      "step": 31
    },
    {
      "epoch": 0.04773447697184412,
      "grad_norm": 1.3193391561508179,
      "learning_rate": 0.00019092436974789919,
      "loss": 1.7366,
      "step": 32
    },
    {
      "epoch": 0.04922617937721425,
      "grad_norm": 1.2383922338485718,
      "learning_rate": 0.00019058823529411766,
      "loss": 1.8462,
      "step": 33
    },
    {
      "epoch": 0.05071788178258437,
      "grad_norm": 1.178370714187622,
      "learning_rate": 0.00019025210084033613,
      "loss": 1.887,
      "step": 34
    },
    {
      "epoch": 0.0522095841879545,
      "grad_norm": 1.534515142440796,
      "learning_rate": 0.00018991596638655463,
      "loss": 1.7176,
      "step": 35
    },
    {
      "epoch": 0.05370128659332463,
      "grad_norm": 1.201993703842163,
      "learning_rate": 0.0001895798319327731,
      "loss": 1.8099,
      "step": 36
    },
    {
      "epoch": 0.05519298899869476,
      "grad_norm": 1.2329827547073364,
      "learning_rate": 0.0001892436974789916,
      "loss": 1.8096,
      "step": 37
    },
    {
      "epoch": 0.05668469140406489,
      "grad_norm": 1.255269169807434,
      "learning_rate": 0.0001889075630252101,
      "loss": 1.821,
      "step": 38
    },
    {
      "epoch": 0.05817639380943502,
      "grad_norm": 1.233344554901123,
      "learning_rate": 0.00018857142857142857,
      "loss": 1.7468,
      "step": 39
    },
    {
      "epoch": 0.05966809621480515,
      "grad_norm": 1.4332133531570435,
      "learning_rate": 0.00018823529411764707,
      "loss": 1.7706,
      "step": 40
    },
    {
      "epoch": 0.061159798620175274,
      "grad_norm": 1.202459454536438,
      "learning_rate": 0.00018789915966386554,
      "loss": 1.8073,
      "step": 41
    },
    {
      "epoch": 0.0626515010255454,
      "grad_norm": 2.1169466972351074,
      "learning_rate": 0.00018756302521008404,
      "loss": 1.8198,
      "step": 42
    },
    {
      "epoch": 0.06414320343091554,
      "grad_norm": 1.4463489055633545,
      "learning_rate": 0.00018722689075630254,
      "loss": 1.9105,
      "step": 43
    },
    {
      "epoch": 0.06563490583628566,
      "grad_norm": 1.0720268487930298,
      "learning_rate": 0.000186890756302521,
      "loss": 1.7282,
      "step": 44
    },
    {
      "epoch": 0.06712660824165578,
      "grad_norm": 1.3291202783584595,
      "learning_rate": 0.0001865546218487395,
      "loss": 1.8572,
      "step": 45
    },
    {
      "epoch": 0.06861831064702592,
      "grad_norm": 1.4792389869689941,
      "learning_rate": 0.000186218487394958,
      "loss": 1.8633,
      "step": 46
    },
    {
      "epoch": 0.07011001305239604,
      "grad_norm": 1.1921184062957764,
      "learning_rate": 0.00018588235294117648,
      "loss": 1.8363,
      "step": 47
    },
    {
      "epoch": 0.07160171545776618,
      "grad_norm": 1.0988856554031372,
      "learning_rate": 0.00018554621848739498,
      "loss": 1.9583,
      "step": 48
    },
    {
      "epoch": 0.0730934178631363,
      "grad_norm": 1.3254163265228271,
      "learning_rate": 0.00018521008403361345,
      "loss": 1.902,
      "step": 49
    },
    {
      "epoch": 0.07458512026850643,
      "grad_norm": 1.0671206712722778,
      "learning_rate": 0.00018487394957983195,
      "loss": 1.8353,
      "step": 50
    },
    {
      "epoch": 0.07458512026850643,
      "eval_loss": 1.8837151527404785,
      "eval_runtime": 9.6048,
      "eval_samples_per_second": 6.663,
      "eval_steps_per_second": 3.332,
      "step": 50
    },
    {
      "epoch": 0.07607682267387657,
      "grad_norm": 1.2634291648864746,
      "learning_rate": 0.00018453781512605045,
      "loss": 1.7784,
      "step": 51
    },
    {
      "epoch": 0.07756852507924669,
      "grad_norm": 1.1648616790771484,
      "learning_rate": 0.0001842016806722689,
      "loss": 1.6194,
      "step": 52
    },
    {
      "epoch": 0.07906022748461682,
      "grad_norm": 1.2529449462890625,
      "learning_rate": 0.0001838655462184874,
      "loss": 1.8644,
      "step": 53
    },
    {
      "epoch": 0.08055192988998695,
      "grad_norm": 1.230100393295288,
      "learning_rate": 0.0001835294117647059,
      "loss": 1.8477,
      "step": 54
    },
    {
      "epoch": 0.08204363229535708,
      "grad_norm": 1.111884593963623,
      "learning_rate": 0.00018319327731092437,
      "loss": 1.8443,
      "step": 55
    },
    {
      "epoch": 0.0835353347007272,
      "grad_norm": 1.145302176475525,
      "learning_rate": 0.00018285714285714286,
      "loss": 1.9136,
      "step": 56
    },
    {
      "epoch": 0.08502703710609734,
      "grad_norm": 1.1713634729385376,
      "learning_rate": 0.00018252100840336134,
      "loss": 1.8071,
      "step": 57
    },
    {
      "epoch": 0.08651873951146746,
      "grad_norm": 0.9681565761566162,
      "learning_rate": 0.00018218487394957984,
      "loss": 1.9432,
      "step": 58
    },
    {
      "epoch": 0.08801044191683759,
      "grad_norm": 1.2015904188156128,
      "learning_rate": 0.00018184873949579833,
      "loss": 1.774,
      "step": 59
    },
    {
      "epoch": 0.08950214432220772,
      "grad_norm": 1.0416995286941528,
      "learning_rate": 0.0001815126050420168,
      "loss": 1.8479,
      "step": 60
    },
    {
      "epoch": 0.09099384672757785,
      "grad_norm": 1.1236249208450317,
      "learning_rate": 0.0001811764705882353,
      "loss": 1.8281,
      "step": 61
    },
    {
      "epoch": 0.09248554913294797,
      "grad_norm": 1.6734750270843506,
      "learning_rate": 0.0001808403361344538,
      "loss": 1.7245,
      "step": 62
    },
    {
      "epoch": 0.09397725153831811,
      "grad_norm": 1.5988835096359253,
      "learning_rate": 0.00018050420168067228,
      "loss": 1.7511,
      "step": 63
    },
    {
      "epoch": 0.09546895394368823,
      "grad_norm": 1.3248356580734253,
      "learning_rate": 0.00018016806722689078,
      "loss": 1.8517,
      "step": 64
    },
    {
      "epoch": 0.09696065634905836,
      "grad_norm": 1.272733211517334,
      "learning_rate": 0.00017983193277310925,
      "loss": 1.8331,
      "step": 65
    },
    {
      "epoch": 0.0984523587544285,
      "grad_norm": 1.074728012084961,
      "learning_rate": 0.00017949579831932775,
      "loss": 1.903,
      "step": 66
    },
    {
      "epoch": 0.09994406115979862,
      "grad_norm": 0.9002382755279541,
      "learning_rate": 0.00017915966386554625,
      "loss": 1.6597,
      "step": 67
    },
    {
      "epoch": 0.10143576356516874,
      "grad_norm": 1.0076817274093628,
      "learning_rate": 0.00017882352941176472,
      "loss": 1.8571,
      "step": 68
    },
    {
      "epoch": 0.10292746597053888,
      "grad_norm": 1.0490552186965942,
      "learning_rate": 0.00017848739495798322,
      "loss": 1.9166,
      "step": 69
    },
    {
      "epoch": 0.104419168375909,
      "grad_norm": 1.1788151264190674,
      "learning_rate": 0.0001781512605042017,
      "loss": 1.8758,
      "step": 70
    },
    {
      "epoch": 0.10591087078127913,
      "grad_norm": 1.0090404748916626,
      "learning_rate": 0.00017781512605042016,
      "loss": 1.7205,
      "step": 71
    },
    {
      "epoch": 0.10740257318664927,
      "grad_norm": 1.176716685295105,
      "learning_rate": 0.00017747899159663866,
      "loss": 1.8767,
      "step": 72
    },
    {
      "epoch": 0.10889427559201939,
      "grad_norm": 1.2236241102218628,
      "learning_rate": 0.00017714285714285713,
      "loss": 1.8276,
      "step": 73
    },
    {
      "epoch": 0.11038597799738951,
      "grad_norm": 1.1437926292419434,
      "learning_rate": 0.00017680672268907563,
      "loss": 1.9052,
      "step": 74
    },
    {
      "epoch": 0.11187768040275965,
      "grad_norm": 1.3193964958190918,
      "learning_rate": 0.00017647058823529413,
      "loss": 1.8221,
      "step": 75
    },
    {
      "epoch": 0.11187768040275965,
      "eval_loss": 1.877716064453125,
      "eval_runtime": 9.6046,
      "eval_samples_per_second": 6.663,
      "eval_steps_per_second": 3.332,
      "step": 75
    },
    {
      "epoch": 0.11336938280812978,
      "grad_norm": 1.1918264627456665,
      "learning_rate": 0.0001761344537815126,
      "loss": 1.8814,
      "step": 76
    },
    {
      "epoch": 0.1148610852134999,
      "grad_norm": 1.232614517211914,
      "learning_rate": 0.0001757983193277311,
      "loss": 1.739,
      "step": 77
    },
    {
      "epoch": 0.11635278761887004,
      "grad_norm": 1.6352307796478271,
      "learning_rate": 0.0001754621848739496,
      "loss": 1.8363,
      "step": 78
    },
    {
      "epoch": 0.11784449002424016,
      "grad_norm": 1.2389256954193115,
      "learning_rate": 0.00017512605042016807,
      "loss": 1.8105,
      "step": 79
    },
    {
      "epoch": 0.1193361924296103,
      "grad_norm": 1.085701584815979,
      "learning_rate": 0.00017478991596638657,
      "loss": 1.8751,
      "step": 80
    },
    {
      "epoch": 0.12082789483498042,
      "grad_norm": 1.5276975631713867,
      "learning_rate": 0.00017445378151260504,
      "loss": 1.8892,
      "step": 81
    },
    {
      "epoch": 0.12231959724035055,
      "grad_norm": 1.2220733165740967,
      "learning_rate": 0.00017411764705882354,
      "loss": 1.7284,
      "step": 82
    },
    {
      "epoch": 0.12381129964572068,
      "grad_norm": 1.1983511447906494,
      "learning_rate": 0.00017378151260504204,
      "loss": 1.9117,
      "step": 83
    },
    {
      "epoch": 0.1253030020510908,
      "grad_norm": 1.185375690460205,
      "learning_rate": 0.0001734453781512605,
      "loss": 1.7894,
      "step": 84
    },
    {
      "epoch": 0.12679470445646093,
      "grad_norm": 1.1006300449371338,
      "learning_rate": 0.000173109243697479,
      "loss": 1.8714,
      "step": 85
    },
    {
      "epoch": 0.12828640686183107,
      "grad_norm": 1.0701563358306885,
      "learning_rate": 0.00017277310924369748,
      "loss": 1.9681,
      "step": 86
    },
    {
      "epoch": 0.12977810926720118,
      "grad_norm": 1.10486900806427,
      "learning_rate": 0.00017243697478991598,
      "loss": 1.8594,
      "step": 87
    },
    {
      "epoch": 0.13126981167257132,
      "grad_norm": 1.2423001527786255,
      "learning_rate": 0.00017210084033613448,
      "loss": 1.7603,
      "step": 88
    },
    {
      "epoch": 0.13276151407794146,
      "grad_norm": 1.2650513648986816,
      "learning_rate": 0.00017176470588235293,
      "loss": 1.8477,
      "step": 89
    },
    {
      "epoch": 0.13425321648331157,
      "grad_norm": 1.0919733047485352,
      "learning_rate": 0.00017142857142857143,
      "loss": 1.9019,
      "step": 90
    },
    {
      "epoch": 0.1357449188886817,
      "grad_norm": 1.1384038925170898,
      "learning_rate": 0.00017109243697478992,
      "loss": 1.7632,
      "step": 91
    },
    {
      "epoch": 0.13723662129405184,
      "grad_norm": 1.2927051782608032,
      "learning_rate": 0.0001707563025210084,
      "loss": 1.8592,
      "step": 92
    },
    {
      "epoch": 0.13872832369942195,
      "grad_norm": 1.2602596282958984,
      "learning_rate": 0.0001704201680672269,
      "loss": 1.746,
      "step": 93
    },
    {
      "epoch": 0.1402200261047921,
      "grad_norm": 1.2915674448013306,
      "learning_rate": 0.0001700840336134454,
      "loss": 1.8301,
      "step": 94
    },
    {
      "epoch": 0.14171172851016223,
      "grad_norm": 1.1027021408081055,
      "learning_rate": 0.00016974789915966387,
      "loss": 1.8711,
      "step": 95
    },
    {
      "epoch": 0.14320343091553236,
      "grad_norm": 1.2534444332122803,
      "learning_rate": 0.00016941176470588237,
      "loss": 1.8429,
      "step": 96
    },
    {
      "epoch": 0.14469513332090247,
      "grad_norm": 1.1659573316574097,
      "learning_rate": 0.00016907563025210084,
      "loss": 1.9125,
      "step": 97
    },
    {
      "epoch": 0.1461868357262726,
      "grad_norm": 0.9224597215652466,
      "learning_rate": 0.00016873949579831934,
      "loss": 1.7884,
      "step": 98
    },
    {
      "epoch": 0.14767853813164275,
      "grad_norm": 1.5108716487884521,
      "learning_rate": 0.00016840336134453784,
      "loss": 1.756,
      "step": 99
    },
    {
      "epoch": 0.14917024053701286,
      "grad_norm": 1.0304495096206665,
      "learning_rate": 0.0001680672268907563,
      "loss": 1.8496,
      "step": 100
    },
    {
      "epoch": 0.14917024053701286,
      "eval_loss": 1.8782081604003906,
      "eval_runtime": 9.6109,
      "eval_samples_per_second": 6.659,
      "eval_steps_per_second": 3.33,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1663984618746675e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}