{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.030557677616501147,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00030557677616501144,
      "grad_norm": 2.4270410537719727,
      "learning_rate": 2e-05,
      "loss": 4.3691,
      "step": 1
    },
    {
      "epoch": 0.00030557677616501144,
      "eval_loss": 3.825514316558838,
      "eval_runtime": 44.62,
      "eval_samples_per_second": 30.883,
      "eval_steps_per_second": 15.442,
      "step": 1
    },
    {
      "epoch": 0.0006111535523300229,
      "grad_norm": 1.158055305480957,
      "learning_rate": 4e-05,
      "loss": 1.9265,
      "step": 2
    },
    {
      "epoch": 0.0009167303284950344,
      "grad_norm": 1.5009372234344482,
      "learning_rate": 6e-05,
      "loss": 4.1948,
      "step": 3
    },
    {
      "epoch": 0.0012223071046600458,
      "grad_norm": 1.4214242696762085,
      "learning_rate": 8e-05,
      "loss": 3.1941,
      "step": 4
    },
    {
      "epoch": 0.0015278838808250573,
      "grad_norm": 1.7152305841445923,
      "learning_rate": 0.0001,
      "loss": 3.3993,
      "step": 5
    },
    {
      "epoch": 0.0018334606569900688,
      "grad_norm": 1.6367850303649902,
      "learning_rate": 0.00012,
      "loss": 4.2454,
      "step": 6
    },
    {
      "epoch": 0.0021390374331550803,
      "grad_norm": 1.2402284145355225,
      "learning_rate": 0.00014,
      "loss": 2.3504,
      "step": 7
    },
    {
      "epoch": 0.0024446142093200915,
      "grad_norm": 1.5380349159240723,
      "learning_rate": 0.00016,
      "loss": 3.6695,
      "step": 8
    },
    {
      "epoch": 0.0027501909854851033,
      "grad_norm": 2.2115941047668457,
      "learning_rate": 0.00018,
      "loss": 3.8667,
      "step": 9
    },
    {
      "epoch": 0.0030557677616501145,
      "grad_norm": 2.173429489135742,
      "learning_rate": 0.0002,
      "loss": 3.0004,
      "step": 10
    },
    {
      "epoch": 0.0033613445378151263,
      "grad_norm": 2.2001826763153076,
      "learning_rate": 0.0001999863304992469,
      "loss": 2.6077,
      "step": 11
    },
    {
      "epoch": 0.0036669213139801375,
      "grad_norm": 2.234281539916992,
      "learning_rate": 0.00019994532573409262,
      "loss": 3.6697,
      "step": 12
    },
    {
      "epoch": 0.003972498090145149,
      "grad_norm": 2.308614492416382,
      "learning_rate": 0.00019987699691483048,
      "loss": 2.7118,
      "step": 13
    },
    {
      "epoch": 0.0042780748663101605,
      "grad_norm": 2.648648500442505,
      "learning_rate": 0.00019978136272187747,
      "loss": 3.2435,
      "step": 14
    },
    {
      "epoch": 0.004583651642475172,
      "grad_norm": 1.7936925888061523,
      "learning_rate": 0.000199658449300667,
      "loss": 2.1392,
      "step": 15
    },
    {
      "epoch": 0.004889228418640183,
      "grad_norm": 2.6367146968841553,
      "learning_rate": 0.00019950829025450114,
      "loss": 3.592,
      "step": 16
    },
    {
      "epoch": 0.005194805194805195,
      "grad_norm": 2.5174176692962646,
      "learning_rate": 0.00019933092663536382,
      "loss": 2.977,
      "step": 17
    },
    {
      "epoch": 0.0055003819709702065,
      "grad_norm": 2.296748399734497,
      "learning_rate": 0.00019912640693269752,
      "loss": 3.093,
      "step": 18
    },
    {
      "epoch": 0.005805958747135217,
      "grad_norm": 3.448976993560791,
      "learning_rate": 0.00019889478706014687,
      "loss": 3.0724,
      "step": 19
    },
    {
      "epoch": 0.006111535523300229,
      "grad_norm": 2.230823278427124,
      "learning_rate": 0.00019863613034027224,
      "loss": 2.7141,
      "step": 20
    },
    {
      "epoch": 0.006417112299465241,
      "grad_norm": 2.3661162853240967,
      "learning_rate": 0.00019835050748723824,
      "loss": 3.6851,
      "step": 21
    },
    {
      "epoch": 0.0067226890756302525,
      "grad_norm": 1.993086338043213,
      "learning_rate": 0.00019803799658748094,
      "loss": 3.8929,
      "step": 22
    },
    {
      "epoch": 0.007028265851795263,
      "grad_norm": 1.727256417274475,
      "learning_rate": 0.00019769868307835994,
      "loss": 2.7433,
      "step": 23
    },
    {
      "epoch": 0.007333842627960275,
      "grad_norm": 2.6137921810150146,
      "learning_rate": 0.0001973326597248006,
      "loss": 3.9081,
      "step": 24
    },
    {
      "epoch": 0.007639419404125287,
      "grad_norm": 1.9214521646499634,
      "learning_rate": 0.00019694002659393305,
      "loss": 3.451,
      "step": 25
    },
    {
      "epoch": 0.007944996180290298,
      "grad_norm": 2.5544991493225098,
      "learning_rate": 0.00019652089102773488,
      "loss": 2.4955,
      "step": 26
    },
    {
      "epoch": 0.00825057295645531,
      "grad_norm": 3.0405311584472656,
      "learning_rate": 0.00019607536761368484,
      "loss": 3.6993,
      "step": 27
    },
    {
      "epoch": 0.008556149732620321,
      "grad_norm": 1.412721037864685,
      "learning_rate": 0.00019560357815343577,
      "loss": 3.4813,
      "step": 28
    },
    {
      "epoch": 0.008861726508785332,
      "grad_norm": 1.844821572303772,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.4911,
      "step": 29
    },
    {
      "epoch": 0.009167303284950344,
      "grad_norm": 2.185194730758667,
      "learning_rate": 0.00019458172417006347,
      "loss": 3.0409,
      "step": 30
    },
    {
      "epoch": 0.009472880061115355,
      "grad_norm": 2.528438091278076,
      "learning_rate": 0.00019403193901161613,
      "loss": 4.4194,
      "step": 31
    },
    {
      "epoch": 0.009778456837280366,
      "grad_norm": 2.3545053005218506,
      "learning_rate": 0.0001934564464599461,
      "loss": 3.9219,
      "step": 32
    },
    {
      "epoch": 0.010084033613445379,
      "grad_norm": 2.4586379528045654,
      "learning_rate": 0.00019285540384897073,
      "loss": 3.8094,
      "step": 33
    },
    {
      "epoch": 0.01038961038961039,
      "grad_norm": 2.5422775745391846,
      "learning_rate": 0.00019222897549773848,
      "loss": 1.9784,
      "step": 34
    },
    {
      "epoch": 0.0106951871657754,
      "grad_norm": 1.6043715476989746,
      "learning_rate": 0.00019157733266550575,
      "loss": 2.5754,
      "step": 35
    },
    {
      "epoch": 0.011000763941940413,
      "grad_norm": 2.428220510482788,
      "learning_rate": 0.00019090065350491626,
      "loss": 3.7738,
      "step": 36
    },
    {
      "epoch": 0.011306340718105424,
      "grad_norm": 2.145481586456299,
      "learning_rate": 0.00019019912301329592,
      "loss": 3.2982,
      "step": 37
    },
    {
      "epoch": 0.011611917494270435,
      "grad_norm": 1.5569844245910645,
      "learning_rate": 0.00018947293298207635,
      "loss": 1.7218,
      "step": 38
    },
    {
      "epoch": 0.011917494270435447,
      "grad_norm": 2.1777217388153076,
      "learning_rate": 0.0001887222819443612,
      "loss": 2.581,
      "step": 39
    },
    {
      "epoch": 0.012223071046600458,
      "grad_norm": 2.7405147552490234,
      "learning_rate": 0.0001879473751206489,
      "loss": 3.8181,
      "step": 40
    },
    {
      "epoch": 0.012528647822765469,
      "grad_norm": 1.6006349325180054,
      "learning_rate": 0.00018714842436272773,
      "loss": 2.0009,
      "step": 41
    },
    {
      "epoch": 0.012834224598930482,
      "grad_norm": 1.8577955961227417,
      "learning_rate": 0.00018632564809575742,
      "loss": 3.3277,
      "step": 42
    },
    {
      "epoch": 0.013139801375095492,
      "grad_norm": 1.7019318342208862,
      "learning_rate": 0.0001854792712585539,
      "loss": 3.6416,
      "step": 43
    },
    {
      "epoch": 0.013445378151260505,
      "grad_norm": 2.172180414199829,
      "learning_rate": 0.00018460952524209355,
      "loss": 3.5653,
      "step": 44
    },
    {
      "epoch": 0.013750954927425516,
      "grad_norm": 1.173954963684082,
      "learning_rate": 0.00018371664782625287,
      "loss": 2.4792,
      "step": 45
    },
    {
      "epoch": 0.014056531703590527,
      "grad_norm": 2.2119481563568115,
      "learning_rate": 0.00018280088311480201,
      "loss": 3.7178,
      "step": 46
    },
    {
      "epoch": 0.01436210847975554,
      "grad_norm": 1.043997883796692,
      "learning_rate": 0.00018186248146866927,
      "loss": 2.3083,
      "step": 47
    },
    {
      "epoch": 0.01466768525592055,
      "grad_norm": 1.6460810899734497,
      "learning_rate": 0.00018090169943749476,
      "loss": 2.4319,
      "step": 48
    },
    {
      "epoch": 0.014973262032085561,
      "grad_norm": 1.5691938400268555,
      "learning_rate": 0.0001799187996894925,
      "loss": 2.5601,
      "step": 49
    },
    {
      "epoch": 0.015278838808250574,
      "grad_norm": 2.165229320526123,
      "learning_rate": 0.00017891405093963938,
      "loss": 3.1488,
      "step": 50
    },
    {
      "epoch": 0.015278838808250574,
      "eval_loss": 3.244551658630371,
      "eval_runtime": 43.5009,
      "eval_samples_per_second": 31.678,
      "eval_steps_per_second": 15.839,
      "step": 50
    },
    {
      "epoch": 0.015584415584415584,
      "grad_norm": 2.4259822368621826,
      "learning_rate": 0.00017788772787621126,
      "loss": 4.0701,
      "step": 51
    },
    {
      "epoch": 0.015889992360580595,
      "grad_norm": 1.828935146331787,
      "learning_rate": 0.00017684011108568592,
      "loss": 3.8272,
      "step": 52
    },
    {
      "epoch": 0.016195569136745608,
      "grad_norm": 1.6015702486038208,
      "learning_rate": 0.0001757714869760335,
      "loss": 4.0941,
      "step": 53
    },
    {
      "epoch": 0.01650114591291062,
      "grad_norm": 1.4622135162353516,
      "learning_rate": 0.0001746821476984154,
      "loss": 2.8427,
      "step": 54
    },
    {
      "epoch": 0.01680672268907563,
      "grad_norm": 2.106966018676758,
      "learning_rate": 0.00017357239106731317,
      "loss": 2.3866,
      "step": 55
    },
    {
      "epoch": 0.017112299465240642,
      "grad_norm": 2.9907472133636475,
      "learning_rate": 0.00017244252047910892,
      "loss": 3.2555,
      "step": 56
    },
    {
      "epoch": 0.017417876241405655,
      "grad_norm": 1.2781822681427002,
      "learning_rate": 0.00017129284482913972,
      "loss": 2.8657,
      "step": 57
    },
    {
      "epoch": 0.017723453017570664,
      "grad_norm": 1.5655877590179443,
      "learning_rate": 0.00017012367842724887,
      "loss": 2.6976,
      "step": 58
    },
    {
      "epoch": 0.018029029793735676,
      "grad_norm": 1.7124484777450562,
      "learning_rate": 0.0001689353409118566,
      "loss": 2.5161,
      "step": 59
    },
    {
      "epoch": 0.01833460656990069,
      "grad_norm": 2.1622180938720703,
      "learning_rate": 0.00016772815716257412,
      "loss": 2.9102,
      "step": 60
    },
    {
      "epoch": 0.018640183346065698,
      "grad_norm": 1.4135297536849976,
      "learning_rate": 0.0001665024572113848,
      "loss": 1.7485,
      "step": 61
    },
    {
      "epoch": 0.01894576012223071,
      "grad_norm": 1.8781421184539795,
      "learning_rate": 0.00016525857615241687,
      "loss": 3.8095,
      "step": 62
    },
    {
      "epoch": 0.019251336898395723,
      "grad_norm": 1.5626355409622192,
      "learning_rate": 0.00016399685405033167,
      "loss": 1.9366,
      "step": 63
    },
    {
      "epoch": 0.019556913674560732,
      "grad_norm": 1.412752389907837,
      "learning_rate": 0.0001627176358473537,
      "loss": 1.9336,
      "step": 64
    },
    {
      "epoch": 0.019862490450725745,
      "grad_norm": 5.998400688171387,
      "learning_rate": 0.0001614212712689668,
      "loss": 3.1919,
      "step": 65
    },
    {
      "epoch": 0.020168067226890758,
      "grad_norm": 1.5334243774414062,
      "learning_rate": 0.00016010811472830252,
      "loss": 2.7113,
      "step": 66
    },
    {
      "epoch": 0.020473644003055767,
      "grad_norm": 2.1354057788848877,
      "learning_rate": 0.00015877852522924732,
      "loss": 2.988,
      "step": 67
    },
    {
      "epoch": 0.02077922077922078,
      "grad_norm": 1.9327161312103271,
      "learning_rate": 0.00015743286626829437,
      "loss": 2.9572,
      "step": 68
    },
    {
      "epoch": 0.021084797555385792,
      "grad_norm": 2.1718881130218506,
      "learning_rate": 0.0001560715057351673,
      "loss": 3.5648,
      "step": 69
    },
    {
      "epoch": 0.0213903743315508,
      "grad_norm": 1.8955811262130737,
      "learning_rate": 0.00015469481581224272,
      "loss": 3.1244,
      "step": 70
    },
    {
      "epoch": 0.021695951107715813,
      "grad_norm": 1.5830830335617065,
      "learning_rate": 0.0001533031728727994,
      "loss": 2.7921,
      "step": 71
    },
    {
      "epoch": 0.022001527883880826,
      "grad_norm": 2.2739856243133545,
      "learning_rate": 0.00015189695737812152,
      "loss": 3.5455,
      "step": 72
    },
    {
      "epoch": 0.022307104660045835,
      "grad_norm": 0.9828822612762451,
      "learning_rate": 0.0001504765537734844,
      "loss": 1.6882,
      "step": 73
    },
    {
      "epoch": 0.022612681436210848,
      "grad_norm": 1.9325013160705566,
      "learning_rate": 0.00014904235038305083,
      "loss": 2.1146,
      "step": 74
    },
    {
      "epoch": 0.02291825821237586,
      "grad_norm": 1.3537631034851074,
      "learning_rate": 0.00014759473930370736,
      "loss": 2.2816,
      "step": 75
    },
    {
      "epoch": 0.02322383498854087,
      "grad_norm": 1.826690673828125,
      "learning_rate": 0.0001461341162978688,
      "loss": 1.5235,
      "step": 76
    },
    {
      "epoch": 0.023529411764705882,
      "grad_norm": 1.8681014776229858,
      "learning_rate": 0.00014466088068528068,
      "loss": 4.0703,
      "step": 77
    },
    {
      "epoch": 0.023834988540870895,
      "grad_norm": 4.881453514099121,
      "learning_rate": 0.00014317543523384928,
      "loss": 3.2547,
      "step": 78
    },
    {
      "epoch": 0.024140565317035904,
      "grad_norm": 2.301090955734253,
      "learning_rate": 0.00014167818604952906,
      "loss": 2.3378,
      "step": 79
    },
    {
      "epoch": 0.024446142093200916,
      "grad_norm": 1.1395305395126343,
      "learning_rate": 0.00014016954246529696,
      "loss": 1.5157,
      "step": 80
    },
    {
      "epoch": 0.02475171886936593,
      "grad_norm": 1.7658803462982178,
      "learning_rate": 0.00013864991692924523,
      "loss": 4.2361,
      "step": 81
    },
    {
      "epoch": 0.025057295645530938,
      "grad_norm": 1.827609896659851,
      "learning_rate": 0.00013711972489182208,
      "loss": 3.0601,
      "step": 82
    },
    {
      "epoch": 0.02536287242169595,
      "grad_norm": 1.9651907682418823,
      "learning_rate": 0.00013557938469225167,
      "loss": 3.6306,
      "step": 83
    },
    {
      "epoch": 0.025668449197860963,
      "grad_norm": 2.074267625808716,
      "learning_rate": 0.00013402931744416433,
      "loss": 2.9667,
      "step": 84
    },
    {
      "epoch": 0.025974025974025976,
      "grad_norm": 1.3315553665161133,
      "learning_rate": 0.00013246994692046836,
      "loss": 1.88,
      "step": 85
    },
    {
      "epoch": 0.026279602750190985,
      "grad_norm": 1.5968420505523682,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.7276,
      "step": 86
    },
    {
      "epoch": 0.026585179526355997,
      "grad_norm": 1.9459774494171143,
      "learning_rate": 0.0001293250037384465,
      "loss": 2.5366,
      "step": 87
    },
    {
      "epoch": 0.02689075630252101,
      "grad_norm": 1.9473600387573242,
      "learning_rate": 0.00012774029087618446,
      "loss": 3.8513,
      "step": 88
    },
    {
      "epoch": 0.02719633307868602,
      "grad_norm": 1.4431513547897339,
      "learning_rate": 0.00012614799409538198,
      "loss": 2.5023,
      "step": 89
    },
    {
      "epoch": 0.02750190985485103,
      "grad_norm": 3.223552703857422,
      "learning_rate": 0.00012454854871407994,
      "loss": 2.0943,
      "step": 90
    },
    {
      "epoch": 0.027807486631016044,
      "grad_norm": 2.679762363433838,
      "learning_rate": 0.00012294239200467516,
      "loss": 3.3053,
      "step": 91
    },
    {
      "epoch": 0.028113063407181053,
      "grad_norm": 2.0697975158691406,
      "learning_rate": 0.0001213299630743747,
      "loss": 3.5176,
      "step": 92
    },
    {
      "epoch": 0.028418640183346066,
      "grad_norm": 2.661999464035034,
      "learning_rate": 0.00011971170274514802,
      "loss": 3.7355,
      "step": 93
    },
    {
      "epoch": 0.02872421695951108,
      "grad_norm": 1.8615680932998657,
      "learning_rate": 0.000118088053433211,
      "loss": 2.0932,
      "step": 94
    },
    {
      "epoch": 0.029029793735676088,
      "grad_norm": 2.583749532699585,
      "learning_rate": 0.00011645945902807341,
      "loss": 4.0713,
      "step": 95
    },
    {
      "epoch": 0.0293353705118411,
      "grad_norm": 1.8530974388122559,
      "learning_rate": 0.0001148263647711842,
      "loss": 1.5702,
      "step": 96
    },
    {
      "epoch": 0.029640947288006113,
      "grad_norm": 1.7810598611831665,
      "learning_rate": 0.00011318921713420691,
      "loss": 3.71,
      "step": 97
    },
    {
      "epoch": 0.029946524064171122,
      "grad_norm": 2.1363232135772705,
      "learning_rate": 0.00011154846369695863,
      "loss": 3.1915,
      "step": 98
    },
    {
      "epoch": 0.030252100840336135,
      "grad_norm": 1.8341383934020996,
      "learning_rate": 0.0001099045530250463,
      "loss": 2.4543,
      "step": 99
    },
    {
      "epoch": 0.030557677616501147,
      "grad_norm": 1.8934003114700317,
      "learning_rate": 0.00010825793454723325,
      "loss": 2.6079,
      "step": 100
    },
    {
      "epoch": 0.030557677616501147,
      "eval_loss": 3.186122417449951,
      "eval_runtime": 43.6356,
      "eval_samples_per_second": 31.58,
      "eval_steps_per_second": 15.79,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "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": 1.895803354349568e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}