{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.003514722293004824,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.514722293004824e-05,
      "grad_norm": 3.201282024383545,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 2.6534,
      "step": 1
    },
    {
      "epoch": 3.514722293004824e-05,
      "eval_loss": 3.5773849487304688,
      "eval_runtime": 122.8934,
      "eval_samples_per_second": 4.654,
      "eval_steps_per_second": 4.654,
      "step": 1
    },
    {
      "epoch": 7.029444586009648e-05,
      "grad_norm": 10.12950325012207,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 3.5291,
      "step": 2
    },
    {
      "epoch": 0.00010544166879014472,
      "grad_norm": 8.2281494140625,
      "learning_rate": 8.999999999999999e-05,
      "loss": 2.8958,
      "step": 3
    },
    {
      "epoch": 0.00014058889172019297,
      "grad_norm": 7.624779224395752,
      "learning_rate": 0.00011999999999999999,
      "loss": 3.5229,
      "step": 4
    },
    {
      "epoch": 0.0001757361146502412,
      "grad_norm": 9.272777557373047,
      "learning_rate": 0.00015,
      "loss": 2.3524,
      "step": 5
    },
    {
      "epoch": 0.00021088333758028944,
      "grad_norm": 7.767298221588135,
      "learning_rate": 0.00017999999999999998,
      "loss": 3.0476,
      "step": 6
    },
    {
      "epoch": 0.0002460305605103377,
      "grad_norm": 7.62408447265625,
      "learning_rate": 0.00020999999999999998,
      "loss": 2.8094,
      "step": 7
    },
    {
      "epoch": 0.00028117778344038594,
      "grad_norm": 12.137682914733887,
      "learning_rate": 0.00023999999999999998,
      "loss": 2.9913,
      "step": 8
    },
    {
      "epoch": 0.00031632500637043413,
      "grad_norm": 6.323672294616699,
      "learning_rate": 0.00027,
      "loss": 2.3277,
      "step": 9
    },
    {
      "epoch": 0.0003514722293004824,
      "grad_norm": 7.7393903732299805,
      "learning_rate": 0.0003,
      "loss": 2.6589,
      "step": 10
    },
    {
      "epoch": 0.00038661945223053063,
      "grad_norm": 3.816528081893921,
      "learning_rate": 0.00029990862405286433,
      "loss": 3.1351,
      "step": 11
    },
    {
      "epoch": 0.0004217666751605789,
      "grad_norm": 6.924014091491699,
      "learning_rate": 0.0002996346075389736,
      "loss": 2.9356,
      "step": 12
    },
    {
      "epoch": 0.00045691389809062713,
      "grad_norm": 7.251121997833252,
      "learning_rate": 0.00029917828430524096,
      "loss": 2.9646,
      "step": 13
    },
    {
      "epoch": 0.0004920611210206754,
      "grad_norm": 6.662265300750732,
      "learning_rate": 0.0002985402103112355,
      "loss": 3.2145,
      "step": 14
    },
    {
      "epoch": 0.0005272083439507236,
      "grad_norm": 7.596660614013672,
      "learning_rate": 0.0002977211629518312,
      "loss": 3.0197,
      "step": 15
    },
    {
      "epoch": 0.0005623555668807719,
      "grad_norm": 4.958890914916992,
      "learning_rate": 0.0002967221401100708,
      "loss": 2.8559,
      "step": 16
    },
    {
      "epoch": 0.0005975027898108201,
      "grad_norm": 6.678516387939453,
      "learning_rate": 0.0002955443589413994,
      "loss": 2.4536,
      "step": 17
    },
    {
      "epoch": 0.0006326500127408683,
      "grad_norm": 8.238439559936523,
      "learning_rate": 0.0002941892543907478,
      "loss": 3.123,
      "step": 18
    },
    {
      "epoch": 0.0006677972356709165,
      "grad_norm": 8.204689025878906,
      "learning_rate": 0.00029265847744427303,
      "loss": 3.4216,
      "step": 19
    },
    {
      "epoch": 0.0007029444586009648,
      "grad_norm": 7.485687732696533,
      "learning_rate": 0.0002909538931178862,
      "loss": 3.3373,
      "step": 20
    },
    {
      "epoch": 0.000738091681531013,
      "grad_norm": 6.295429229736328,
      "learning_rate": 0.0002890775781850181,
      "loss": 3.3456,
      "step": 21
    },
    {
      "epoch": 0.0007732389044610613,
      "grad_norm": 7.376994609832764,
      "learning_rate": 0.0002870318186463901,
      "loss": 3.282,
      "step": 22
    },
    {
      "epoch": 0.0008083861273911095,
      "grad_norm": 6.7084641456604,
      "learning_rate": 0.000284819106944875,
      "loss": 2.7638,
      "step": 23
    },
    {
      "epoch": 0.0008435333503211578,
      "grad_norm": 7.342163562774658,
      "learning_rate": 0.000282442138928839,
      "loss": 2.8477,
      "step": 24
    },
    {
      "epoch": 0.000878680573251206,
      "grad_norm": 6.798054218292236,
      "learning_rate": 0.0002799038105676658,
      "loss": 2.7685,
      "step": 25
    },
    {
      "epoch": 0.0009138277961812543,
      "grad_norm": 6.962170600891113,
      "learning_rate": 0.00027720721442346387,
      "loss": 2.8994,
      "step": 26
    },
    {
      "epoch": 0.0009489750191113025,
      "grad_norm": 8.554988861083984,
      "learning_rate": 0.0002743556358832562,
      "loss": 2.9583,
      "step": 27
    },
    {
      "epoch": 0.0009841222420413508,
      "grad_norm": 6.769901275634766,
      "learning_rate": 0.0002713525491562421,
      "loss": 2.7998,
      "step": 28
    },
    {
      "epoch": 0.001019269464971399,
      "grad_norm": 9.057374000549316,
      "learning_rate": 0.00026820161304100823,
      "loss": 3.3269,
      "step": 29
    },
    {
      "epoch": 0.0010544166879014473,
      "grad_norm": 10.272748947143555,
      "learning_rate": 0.00026490666646784665,
      "loss": 3.6792,
      "step": 30
    },
    {
      "epoch": 0.0010895639108314955,
      "grad_norm": 7.183256149291992,
      "learning_rate": 0.00026147172382160914,
      "loss": 2.88,
      "step": 31
    },
    {
      "epoch": 0.0011247111337615438,
      "grad_norm": 9.834364891052246,
      "learning_rate": 0.00025790097005079764,
      "loss": 2.9482,
      "step": 32
    },
    {
      "epoch": 0.001159858356691592,
      "grad_norm": 10.326171875,
      "learning_rate": 0.0002541987555688496,
      "loss": 2.7405,
      "step": 33
    },
    {
      "epoch": 0.0011950055796216402,
      "grad_norm": 8.075050354003906,
      "learning_rate": 0.0002503695909538287,
      "loss": 3.0049,
      "step": 34
    },
    {
      "epoch": 0.0012301528025516883,
      "grad_norm": 7.11674165725708,
      "learning_rate": 0.0002464181414529809,
      "loss": 2.9412,
      "step": 35
    },
    {
      "epoch": 0.0012653000254817365,
      "grad_norm": 6.559268951416016,
      "learning_rate": 0.0002423492212988487,
      "loss": 2.6168,
      "step": 36
    },
    {
      "epoch": 0.0013004472484117848,
      "grad_norm": 11.436878204345703,
      "learning_rate": 0.00023816778784387094,
      "loss": 3.4648,
      "step": 37
    },
    {
      "epoch": 0.001335594471341833,
      "grad_norm": 8.354622840881348,
      "learning_rate": 0.00023387893552061199,
      "loss": 3.0553,
      "step": 38
    },
    {
      "epoch": 0.0013707416942718813,
      "grad_norm": 6.86464262008667,
      "learning_rate": 0.0002294878896349807,
      "loss": 2.8184,
      "step": 39
    },
    {
      "epoch": 0.0014058889172019295,
      "grad_norm": 7.403708457946777,
      "learning_rate": 0.000225,
      "loss": 2.6431,
      "step": 40
    },
    {
      "epoch": 0.0014410361401319778,
      "grad_norm": 8.896238327026367,
      "learning_rate": 0.00022042073441788358,
      "loss": 2.9453,
      "step": 41
    },
    {
      "epoch": 0.001476183363062026,
      "grad_norm": 9.727499008178711,
      "learning_rate": 0.0002157556720183616,
      "loss": 3.0855,
      "step": 42
    },
    {
      "epoch": 0.0015113305859920743,
      "grad_norm": 9.778864860534668,
      "learning_rate": 0.00021101049646137003,
      "loss": 3.0316,
      "step": 43
    },
    {
      "epoch": 0.0015464778089221225,
      "grad_norm": 19.503732681274414,
      "learning_rate": 0.0002061909890123868,
      "loss": 3.5855,
      "step": 44
    },
    {
      "epoch": 0.0015816250318521708,
      "grad_norm": 8.386335372924805,
      "learning_rate": 0.00020130302149885031,
      "loss": 3.2382,
      "step": 45
    },
    {
      "epoch": 0.001616772254782219,
      "grad_norm": 9.492271423339844,
      "learning_rate": 0.0001963525491562421,
      "loss": 1.8511,
      "step": 46
    },
    {
      "epoch": 0.0016519194777122673,
      "grad_norm": 9.34842300415039,
      "learning_rate": 0.00019134560337254986,
      "loss": 2.8563,
      "step": 47
    },
    {
      "epoch": 0.0016870667006423155,
      "grad_norm": 15.09698486328125,
      "learning_rate": 0.00018628828433995013,
      "loss": 3.2323,
      "step": 48
    },
    {
      "epoch": 0.0017222139235723638,
      "grad_norm": 12.457684516906738,
      "learning_rate": 0.00018118675362266385,
      "loss": 3.075,
      "step": 49
    },
    {
      "epoch": 0.001757361146502412,
      "grad_norm": 11.620329856872559,
      "learning_rate": 0.00017604722665003956,
      "loss": 3.3615,
      "step": 50
    },
    {
      "epoch": 0.001757361146502412,
      "eval_loss": 2.9333691596984863,
      "eval_runtime": 122.5269,
      "eval_samples_per_second": 4.668,
      "eval_steps_per_second": 4.668,
      "step": 50
    },
    {
      "epoch": 0.0017925083694324603,
      "grad_norm": 6.184074878692627,
      "learning_rate": 0.0001708759651440098,
      "loss": 3.1531,
      "step": 51
    },
    {
      "epoch": 0.0018276555923625085,
      "grad_norm": 10.926563262939453,
      "learning_rate": 0.000165679269490148,
      "loss": 3.6512,
      "step": 52
    },
    {
      "epoch": 0.0018628028152925568,
      "grad_norm": 6.391138553619385,
      "learning_rate": 0.00016046347106161876,
      "loss": 2.8123,
      "step": 53
    },
    {
      "epoch": 0.001897950038222605,
      "grad_norm": 3.9918131828308105,
      "learning_rate": 0.00015523492450537517,
      "loss": 2.6699,
      "step": 54
    },
    {
      "epoch": 0.0019330972611526533,
      "grad_norm": 5.609512805938721,
      "learning_rate": 0.00015,
      "loss": 2.3293,
      "step": 55
    },
    {
      "epoch": 0.0019682444840827015,
      "grad_norm": 5.8025031089782715,
      "learning_rate": 0.0001447650754946249,
      "loss": 2.0517,
      "step": 56
    },
    {
      "epoch": 0.0020033917070127498,
      "grad_norm": 7.59370756149292,
      "learning_rate": 0.00013953652893838119,
      "loss": 3.0335,
      "step": 57
    },
    {
      "epoch": 0.002038538929942798,
      "grad_norm": 7.709898948669434,
      "learning_rate": 0.000134320730509852,
      "loss": 3.0555,
      "step": 58
    },
    {
      "epoch": 0.0020736861528728463,
      "grad_norm": 5.140454292297363,
      "learning_rate": 0.0001291240348559902,
      "loss": 2.6652,
      "step": 59
    },
    {
      "epoch": 0.0021088333758028945,
      "grad_norm": 6.058025360107422,
      "learning_rate": 0.00012395277334996044,
      "loss": 2.7671,
      "step": 60
    },
    {
      "epoch": 0.0021439805987329428,
      "grad_norm": 9.216087341308594,
      "learning_rate": 0.00011881324637733611,
      "loss": 2.7076,
      "step": 61
    },
    {
      "epoch": 0.002179127821662991,
      "grad_norm": 8.128350257873535,
      "learning_rate": 0.00011371171566004985,
      "loss": 2.7331,
      "step": 62
    },
    {
      "epoch": 0.0022142750445930393,
      "grad_norm": 7.724212169647217,
      "learning_rate": 0.00010865439662745013,
      "loss": 2.625,
      "step": 63
    },
    {
      "epoch": 0.0022494222675230875,
      "grad_norm": 5.113654613494873,
      "learning_rate": 0.0001036474508437579,
      "loss": 2.2554,
      "step": 64
    },
    {
      "epoch": 0.0022845694904531358,
      "grad_norm": 7.291034698486328,
      "learning_rate": 9.869697850114969e-05,
      "loss": 2.0766,
      "step": 65
    },
    {
      "epoch": 0.002319716713383184,
      "grad_norm": 6.133238792419434,
      "learning_rate": 9.380901098761319e-05,
      "loss": 2.6534,
      "step": 66
    },
    {
      "epoch": 0.0023548639363132323,
      "grad_norm": 8.07371711730957,
      "learning_rate": 8.898950353862998e-05,
      "loss": 3.2567,
      "step": 67
    },
    {
      "epoch": 0.0023900111592432805,
      "grad_norm": 8.47569465637207,
      "learning_rate": 8.424432798163836e-05,
      "loss": 2.3998,
      "step": 68
    },
    {
      "epoch": 0.0024251583821733283,
      "grad_norm": 6.5739850997924805,
      "learning_rate": 7.957926558211642e-05,
      "loss": 2.8606,
      "step": 69
    },
    {
      "epoch": 0.0024603056051033766,
      "grad_norm": 10.502620697021484,
      "learning_rate": 7.500000000000002e-05,
      "loss": 2.7211,
      "step": 70
    },
    {
      "epoch": 0.002495452828033425,
      "grad_norm": 6.819766998291016,
      "learning_rate": 7.051211036501928e-05,
      "loss": 2.7132,
      "step": 71
    },
    {
      "epoch": 0.002530600050963473,
      "grad_norm": 8.332561492919922,
      "learning_rate": 6.612106447938799e-05,
      "loss": 3.0188,
      "step": 72
    },
    {
      "epoch": 0.0025657472738935213,
      "grad_norm": 7.98085355758667,
      "learning_rate": 6.183221215612904e-05,
      "loss": 1.8015,
      "step": 73
    },
    {
      "epoch": 0.0026008944968235696,
      "grad_norm": 7.219940662384033,
      "learning_rate": 5.765077870115125e-05,
      "loss": 2.4322,
      "step": 74
    },
    {
      "epoch": 0.002636041719753618,
      "grad_norm": 7.731595993041992,
      "learning_rate": 5.358185854701909e-05,
      "loss": 3.1412,
      "step": 75
    },
    {
      "epoch": 0.002671188942683666,
      "grad_norm": 6.916698932647705,
      "learning_rate": 4.963040904617131e-05,
      "loss": 4.0983,
      "step": 76
    },
    {
      "epoch": 0.0027063361656137143,
      "grad_norm": 7.314121246337891,
      "learning_rate": 4.5801244431150394e-05,
      "loss": 2.8968,
      "step": 77
    },
    {
      "epoch": 0.0027414833885437626,
      "grad_norm": 7.5785441398620605,
      "learning_rate": 4.209902994920235e-05,
      "loss": 2.643,
      "step": 78
    },
    {
      "epoch": 0.002776630611473811,
      "grad_norm": 6.763470649719238,
      "learning_rate": 3.852827617839084e-05,
      "loss": 2.8279,
      "step": 79
    },
    {
      "epoch": 0.002811777834403859,
      "grad_norm": 8.693899154663086,
      "learning_rate": 3.509333353215331e-05,
      "loss": 2.7579,
      "step": 80
    },
    {
      "epoch": 0.0028469250573339073,
      "grad_norm": 5.903140068054199,
      "learning_rate": 3.1798386958991714e-05,
      "loss": 2.596,
      "step": 81
    },
    {
      "epoch": 0.0028820722802639556,
      "grad_norm": 6.02622127532959,
      "learning_rate": 2.8647450843757897e-05,
      "loss": 2.5302,
      "step": 82
    },
    {
      "epoch": 0.002917219503194004,
      "grad_norm": 6.922908306121826,
      "learning_rate": 2.5644364116743755e-05,
      "loss": 2.5549,
      "step": 83
    },
    {
      "epoch": 0.002952366726124052,
      "grad_norm": 6.8705973625183105,
      "learning_rate": 2.2792785576536105e-05,
      "loss": 2.7103,
      "step": 84
    },
    {
      "epoch": 0.0029875139490541003,
      "grad_norm": 8.229166030883789,
      "learning_rate": 2.009618943233419e-05,
      "loss": 3.2369,
      "step": 85
    },
    {
      "epoch": 0.0030226611719841485,
      "grad_norm": 5.061288833618164,
      "learning_rate": 1.755786107116095e-05,
      "loss": 2.3396,
      "step": 86
    },
    {
      "epoch": 0.003057808394914197,
      "grad_norm": 5.73906946182251,
      "learning_rate": 1.5180893055124977e-05,
      "loss": 2.1163,
      "step": 87
    },
    {
      "epoch": 0.003092955617844245,
      "grad_norm": 6.186309814453125,
      "learning_rate": 1.2968181353609852e-05,
      "loss": 3.2023,
      "step": 88
    },
    {
      "epoch": 0.0031281028407742933,
      "grad_norm": 8.73239517211914,
      "learning_rate": 1.0922421814981901e-05,
      "loss": 2.935,
      "step": 89
    },
    {
      "epoch": 0.0031632500637043415,
      "grad_norm": 8.442344665527344,
      "learning_rate": 9.046106882113751e-06,
      "loss": 2.048,
      "step": 90
    },
    {
      "epoch": 0.00319839728663439,
      "grad_norm": 9.889983177185059,
      "learning_rate": 7.34152255572697e-06,
      "loss": 3.0998,
      "step": 91
    },
    {
      "epoch": 0.003233544509564438,
      "grad_norm": 7.554132461547852,
      "learning_rate": 5.810745609252165e-06,
      "loss": 2.7425,
      "step": 92
    },
    {
      "epoch": 0.0032686917324944863,
      "grad_norm": 18.795644760131836,
      "learning_rate": 4.455641058600528e-06,
      "loss": 2.7303,
      "step": 93
    },
    {
      "epoch": 0.0033038389554245345,
      "grad_norm": 9.423656463623047,
      "learning_rate": 3.2778598899291465e-06,
      "loss": 3.1626,
      "step": 94
    },
    {
      "epoch": 0.003338986178354583,
      "grad_norm": 10.255327224731445,
      "learning_rate": 2.2788370481687965e-06,
      "loss": 3.7099,
      "step": 95
    },
    {
      "epoch": 0.003374133401284631,
      "grad_norm": 7.863884925842285,
      "learning_rate": 1.4597896887644456e-06,
      "loss": 2.9709,
      "step": 96
    },
    {
      "epoch": 0.0034092806242146793,
      "grad_norm": 9.880104064941406,
      "learning_rate": 8.217156947590064e-07,
      "loss": 3.5264,
      "step": 97
    },
    {
      "epoch": 0.0034444278471447275,
      "grad_norm": 8.848705291748047,
      "learning_rate": 3.653924610263703e-07,
      "loss": 2.9102,
      "step": 98
    },
    {
      "epoch": 0.003479575070074776,
      "grad_norm": 8.545324325561523,
      "learning_rate": 9.137594713563568e-08,
      "loss": 2.644,
      "step": 99
    },
    {
      "epoch": 0.003514722293004824,
      "grad_norm": 14.05859088897705,
      "learning_rate": 0.0,
      "loss": 3.0055,
      "step": 100
    },
    {
      "epoch": 0.003514722293004824,
      "eval_loss": 2.7083585262298584,
      "eval_runtime": 122.4923,
      "eval_samples_per_second": 4.67,
      "eval_steps_per_second": 4.67,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8964338123538432.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}