{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007444353457902181,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.444353457902182e-05,
      "grad_norm": 5.151248931884766,
      "learning_rate": 1e-05,
      "loss": 7.2804,
      "step": 1
    },
    {
      "epoch": 7.444353457902182e-05,
      "eval_loss": 3.691481828689575,
      "eval_runtime": 1767.9007,
      "eval_samples_per_second": 6.399,
      "eval_steps_per_second": 0.8,
      "step": 1
    },
    {
      "epoch": 0.00014888706915804363,
      "grad_norm": 5.574091911315918,
      "learning_rate": 2e-05,
      "loss": 6.8087,
      "step": 2
    },
    {
      "epoch": 0.00022333060373706543,
      "grad_norm": 6.583240032196045,
      "learning_rate": 3e-05,
      "loss": 7.4991,
      "step": 3
    },
    {
      "epoch": 0.00029777413831608726,
      "grad_norm": 7.723240852355957,
      "learning_rate": 4e-05,
      "loss": 7.3727,
      "step": 4
    },
    {
      "epoch": 0.00037221767289510904,
      "grad_norm": 7.146822929382324,
      "learning_rate": 5e-05,
      "loss": 7.589,
      "step": 5
    },
    {
      "epoch": 0.00044666120747413086,
      "grad_norm": 5.943253517150879,
      "learning_rate": 6e-05,
      "loss": 7.1408,
      "step": 6
    },
    {
      "epoch": 0.0005211047420531526,
      "grad_norm": 5.8936567306518555,
      "learning_rate": 7e-05,
      "loss": 6.3064,
      "step": 7
    },
    {
      "epoch": 0.0005955482766321745,
      "grad_norm": 6.6715006828308105,
      "learning_rate": 8e-05,
      "loss": 6.9143,
      "step": 8
    },
    {
      "epoch": 0.0006699918112111963,
      "grad_norm": 5.5412397384643555,
      "learning_rate": 9e-05,
      "loss": 6.6761,
      "step": 9
    },
    {
      "epoch": 0.0006699918112111963,
      "eval_loss": 3.125314950942993,
      "eval_runtime": 1767.6234,
      "eval_samples_per_second": 6.4,
      "eval_steps_per_second": 0.8,
      "step": 9
    },
    {
      "epoch": 0.0007444353457902181,
      "grad_norm": 5.38551139831543,
      "learning_rate": 0.0001,
      "loss": 6.3362,
      "step": 10
    },
    {
      "epoch": 0.00081887888036924,
      "grad_norm": 5.784944534301758,
      "learning_rate": 9.99695413509548e-05,
      "loss": 6.6751,
      "step": 11
    },
    {
      "epoch": 0.0008933224149482617,
      "grad_norm": 3.3652117252349854,
      "learning_rate": 9.987820251299122e-05,
      "loss": 5.7,
      "step": 12
    },
    {
      "epoch": 0.0009677659495272835,
      "grad_norm": 4.88051176071167,
      "learning_rate": 9.972609476841367e-05,
      "loss": 6.2621,
      "step": 13
    },
    {
      "epoch": 0.0010422094841063053,
      "grad_norm": 4.1151957511901855,
      "learning_rate": 9.951340343707852e-05,
      "loss": 4.9353,
      "step": 14
    },
    {
      "epoch": 0.0011166530186853272,
      "grad_norm": 5.122547626495361,
      "learning_rate": 9.924038765061042e-05,
      "loss": 5.7967,
      "step": 15
    },
    {
      "epoch": 0.001191096553264349,
      "grad_norm": 3.537735939025879,
      "learning_rate": 9.890738003669029e-05,
      "loss": 5.2971,
      "step": 16
    },
    {
      "epoch": 0.0012655400878433707,
      "grad_norm": 5.475334167480469,
      "learning_rate": 9.851478631379982e-05,
      "loss": 5.1532,
      "step": 17
    },
    {
      "epoch": 0.0013399836224223926,
      "grad_norm": 3.737473249435425,
      "learning_rate": 9.806308479691595e-05,
      "loss": 4.9393,
      "step": 18
    },
    {
      "epoch": 0.0013399836224223926,
      "eval_loss": 2.506638526916504,
      "eval_runtime": 1767.4169,
      "eval_samples_per_second": 6.4,
      "eval_steps_per_second": 0.8,
      "step": 18
    },
    {
      "epoch": 0.0014144271570014145,
      "grad_norm": 4.7049455642700195,
      "learning_rate": 9.755282581475769e-05,
      "loss": 4.9206,
      "step": 19
    },
    {
      "epoch": 0.0014888706915804361,
      "grad_norm": 6.552593231201172,
      "learning_rate": 9.698463103929542e-05,
      "loss": 5.2775,
      "step": 20
    },
    {
      "epoch": 0.001563314226159458,
      "grad_norm": 5.3727006912231445,
      "learning_rate": 9.635919272833938e-05,
      "loss": 5.118,
      "step": 21
    },
    {
      "epoch": 0.00163775776073848,
      "grad_norm": 5.317840576171875,
      "learning_rate": 9.567727288213005e-05,
      "loss": 4.803,
      "step": 22
    },
    {
      "epoch": 0.0017122012953175016,
      "grad_norm": 4.539938926696777,
      "learning_rate": 9.493970231495835e-05,
      "loss": 5.135,
      "step": 23
    },
    {
      "epoch": 0.0017866448298965235,
      "grad_norm": 4.396689414978027,
      "learning_rate": 9.414737964294636e-05,
      "loss": 5.0626,
      "step": 24
    },
    {
      "epoch": 0.0018610883644755453,
      "grad_norm": 5.591919898986816,
      "learning_rate": 9.330127018922194e-05,
      "loss": 4.9377,
      "step": 25
    },
    {
      "epoch": 0.001935531899054567,
      "grad_norm": 5.289370059967041,
      "learning_rate": 9.24024048078213e-05,
      "loss": 4.9941,
      "step": 26
    },
    {
      "epoch": 0.002009975433633589,
      "grad_norm": 4.290406227111816,
      "learning_rate": 9.145187862775209e-05,
      "loss": 4.6914,
      "step": 27
    },
    {
      "epoch": 0.002009975433633589,
      "eval_loss": 2.353606700897217,
      "eval_runtime": 1767.7261,
      "eval_samples_per_second": 6.399,
      "eval_steps_per_second": 0.8,
      "step": 27
    },
    {
      "epoch": 0.0020844189682126106,
      "grad_norm": 4.002117156982422,
      "learning_rate": 9.045084971874738e-05,
      "loss": 4.9571,
      "step": 28
    },
    {
      "epoch": 0.0021588625027916327,
      "grad_norm": 3.881159543991089,
      "learning_rate": 8.940053768033609e-05,
      "loss": 5.0725,
      "step": 29
    },
    {
      "epoch": 0.0022333060373706543,
      "grad_norm": 3.603145122528076,
      "learning_rate": 8.83022221559489e-05,
      "loss": 4.321,
      "step": 30
    },
    {
      "epoch": 0.002307749571949676,
      "grad_norm": 3.503277540206909,
      "learning_rate": 8.715724127386972e-05,
      "loss": 4.5718,
      "step": 31
    },
    {
      "epoch": 0.002382193106528698,
      "grad_norm": 3.276064872741699,
      "learning_rate": 8.596699001693255e-05,
      "loss": 4.5048,
      "step": 32
    },
    {
      "epoch": 0.0024566366411077198,
      "grad_norm": 5.377702713012695,
      "learning_rate": 8.473291852294987e-05,
      "loss": 4.7984,
      "step": 33
    },
    {
      "epoch": 0.0025310801756867414,
      "grad_norm": 3.474898099899292,
      "learning_rate": 8.345653031794292e-05,
      "loss": 4.4094,
      "step": 34
    },
    {
      "epoch": 0.0026055237102657635,
      "grad_norm": 3.3915939331054688,
      "learning_rate": 8.213938048432697e-05,
      "loss": 4.7176,
      "step": 35
    },
    {
      "epoch": 0.002679967244844785,
      "grad_norm": 3.340555191040039,
      "learning_rate": 8.07830737662829e-05,
      "loss": 4.6689,
      "step": 36
    },
    {
      "epoch": 0.002679967244844785,
      "eval_loss": 2.2815229892730713,
      "eval_runtime": 1767.7073,
      "eval_samples_per_second": 6.399,
      "eval_steps_per_second": 0.8,
      "step": 36
    },
    {
      "epoch": 0.002754410779423807,
      "grad_norm": 2.8861300945281982,
      "learning_rate": 7.938926261462366e-05,
      "loss": 4.5286,
      "step": 37
    },
    {
      "epoch": 0.002828854314002829,
      "grad_norm": 3.717245101928711,
      "learning_rate": 7.795964517353735e-05,
      "loss": 4.8513,
      "step": 38
    },
    {
      "epoch": 0.0029032978485818506,
      "grad_norm": 3.825446605682373,
      "learning_rate": 7.649596321166024e-05,
      "loss": 4.5213,
      "step": 39
    },
    {
      "epoch": 0.0029777413831608723,
      "grad_norm": 2.5980708599090576,
      "learning_rate": 7.500000000000001e-05,
      "loss": 4.0336,
      "step": 40
    },
    {
      "epoch": 0.0030521849177398944,
      "grad_norm": 2.8092334270477295,
      "learning_rate": 7.347357813929454e-05,
      "loss": 4.5833,
      "step": 41
    },
    {
      "epoch": 0.003126628452318916,
      "grad_norm": 3.5244638919830322,
      "learning_rate": 7.191855733945387e-05,
      "loss": 4.3809,
      "step": 42
    },
    {
      "epoch": 0.0032010719868979377,
      "grad_norm": 2.505378246307373,
      "learning_rate": 7.033683215379002e-05,
      "loss": 4.2914,
      "step": 43
    },
    {
      "epoch": 0.00327551552147696,
      "grad_norm": 3.5163636207580566,
      "learning_rate": 6.873032967079561e-05,
      "loss": 4.2931,
      "step": 44
    },
    {
      "epoch": 0.0033499590560559815,
      "grad_norm": 2.8587241172790527,
      "learning_rate": 6.710100716628344e-05,
      "loss": 4.5006,
      "step": 45
    },
    {
      "epoch": 0.0033499590560559815,
      "eval_loss": 2.252880573272705,
      "eval_runtime": 1767.4985,
      "eval_samples_per_second": 6.4,
      "eval_steps_per_second": 0.8,
      "step": 45
    },
    {
      "epoch": 0.003424402590635003,
      "grad_norm": 3.2841475009918213,
      "learning_rate": 6.545084971874738e-05,
      "loss": 4.5221,
      "step": 46
    },
    {
      "epoch": 0.0034988461252140252,
      "grad_norm": 2.5982000827789307,
      "learning_rate": 6.378186779084995e-05,
      "loss": 4.3101,
      "step": 47
    },
    {
      "epoch": 0.003573289659793047,
      "grad_norm": 2.996198892593384,
      "learning_rate": 6.209609477998338e-05,
      "loss": 4.3395,
      "step": 48
    },
    {
      "epoch": 0.0036477331943720686,
      "grad_norm": 3.302053213119507,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 4.2372,
      "step": 49
    },
    {
      "epoch": 0.0037221767289510907,
      "grad_norm": 2.7011287212371826,
      "learning_rate": 5.868240888334653e-05,
      "loss": 4.4329,
      "step": 50
    },
    {
      "epoch": 0.0037966202635301123,
      "grad_norm": 3.153855323791504,
      "learning_rate": 5.695865504800327e-05,
      "loss": 4.5354,
      "step": 51
    },
    {
      "epoch": 0.003871063798109134,
      "grad_norm": 2.995307683944702,
      "learning_rate": 5.522642316338268e-05,
      "loss": 4.5714,
      "step": 52
    },
    {
      "epoch": 0.003945507332688156,
      "grad_norm": 2.6616311073303223,
      "learning_rate": 5.348782368720626e-05,
      "loss": 4.8438,
      "step": 53
    },
    {
      "epoch": 0.004019950867267178,
      "grad_norm": 3.238128423690796,
      "learning_rate": 5.174497483512506e-05,
      "loss": 4.5399,
      "step": 54
    },
    {
      "epoch": 0.004019950867267178,
      "eval_loss": 2.2302262783050537,
      "eval_runtime": 1768.0752,
      "eval_samples_per_second": 6.398,
      "eval_steps_per_second": 0.8,
      "step": 54
    },
    {
      "epoch": 0.0040943944018462,
      "grad_norm": 3.4774889945983887,
      "learning_rate": 5e-05,
      "loss": 4.8392,
      "step": 55
    },
    {
      "epoch": 0.004168837936425221,
      "grad_norm": 3.0078999996185303,
      "learning_rate": 4.825502516487497e-05,
      "loss": 4.4709,
      "step": 56
    },
    {
      "epoch": 0.004243281471004243,
      "grad_norm": 3.2432363033294678,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 4.637,
      "step": 57
    },
    {
      "epoch": 0.004317725005583265,
      "grad_norm": 3.2105965614318848,
      "learning_rate": 4.477357683661734e-05,
      "loss": 4.5779,
      "step": 58
    },
    {
      "epoch": 0.0043921685401622865,
      "grad_norm": 2.6800873279571533,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 4.3625,
      "step": 59
    },
    {
      "epoch": 0.004466612074741309,
      "grad_norm": 3.262176513671875,
      "learning_rate": 4.131759111665349e-05,
      "loss": 4.1969,
      "step": 60
    },
    {
      "epoch": 0.004541055609320331,
      "grad_norm": 2.9372072219848633,
      "learning_rate": 3.960441545911204e-05,
      "loss": 4.1523,
      "step": 61
    },
    {
      "epoch": 0.004615499143899352,
      "grad_norm": 2.9124231338500977,
      "learning_rate": 3.790390522001662e-05,
      "loss": 4.5237,
      "step": 62
    },
    {
      "epoch": 0.004689942678478374,
      "grad_norm": 2.900690793991089,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 4.2416,
      "step": 63
    },
    {
      "epoch": 0.004689942678478374,
      "eval_loss": 2.2146337032318115,
      "eval_runtime": 1767.3,
      "eval_samples_per_second": 6.401,
      "eval_steps_per_second": 0.8,
      "step": 63
    },
    {
      "epoch": 0.004764386213057396,
      "grad_norm": 2.9719340801239014,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 4.5135,
      "step": 64
    },
    {
      "epoch": 0.004838829747636417,
      "grad_norm": 3.173430919647217,
      "learning_rate": 3.289899283371657e-05,
      "loss": 4.8038,
      "step": 65
    },
    {
      "epoch": 0.0049132732822154395,
      "grad_norm": 2.8161659240722656,
      "learning_rate": 3.12696703292044e-05,
      "loss": 4.1105,
      "step": 66
    },
    {
      "epoch": 0.004987716816794462,
      "grad_norm": 3.183793067932129,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 4.8421,
      "step": 67
    },
    {
      "epoch": 0.005062160351373483,
      "grad_norm": 2.864166498184204,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 4.2092,
      "step": 68
    },
    {
      "epoch": 0.005136603885952505,
      "grad_norm": 2.8501057624816895,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 4.047,
      "step": 69
    },
    {
      "epoch": 0.005211047420531527,
      "grad_norm": 2.7789459228515625,
      "learning_rate": 2.500000000000001e-05,
      "loss": 4.2556,
      "step": 70
    },
    {
      "epoch": 0.005285490955110548,
      "grad_norm": 3.697779893875122,
      "learning_rate": 2.350403678833976e-05,
      "loss": 4.7224,
      "step": 71
    },
    {
      "epoch": 0.00535993448968957,
      "grad_norm": 3.2184338569641113,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 4.1861,
      "step": 72
    },
    {
      "epoch": 0.00535993448968957,
      "eval_loss": 2.202742099761963,
      "eval_runtime": 1767.887,
      "eval_samples_per_second": 6.399,
      "eval_steps_per_second": 0.8,
      "step": 72
    },
    {
      "epoch": 0.0054343780242685925,
      "grad_norm": 2.9179012775421143,
      "learning_rate": 2.061073738537635e-05,
      "loss": 4.5787,
      "step": 73
    },
    {
      "epoch": 0.005508821558847614,
      "grad_norm": 2.9405431747436523,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 4.0358,
      "step": 74
    },
    {
      "epoch": 0.005583265093426636,
      "grad_norm": 3.5514421463012695,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 4.6476,
      "step": 75
    },
    {
      "epoch": 0.005657708628005658,
      "grad_norm": 3.482083797454834,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 5.0748,
      "step": 76
    },
    {
      "epoch": 0.005732152162584679,
      "grad_norm": 3.336946964263916,
      "learning_rate": 1.526708147705013e-05,
      "loss": 4.3167,
      "step": 77
    },
    {
      "epoch": 0.005806595697163701,
      "grad_norm": 2.958566427230835,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 4.8344,
      "step": 78
    },
    {
      "epoch": 0.005881039231742723,
      "grad_norm": 2.784067392349243,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 4.1894,
      "step": 79
    },
    {
      "epoch": 0.0059554827663217446,
      "grad_norm": 3.0680527687072754,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 4.7619,
      "step": 80
    },
    {
      "epoch": 0.006029926300900767,
      "grad_norm": 2.970621347427368,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 4.1997,
      "step": 81
    },
    {
      "epoch": 0.006029926300900767,
      "eval_loss": 2.1963963508605957,
      "eval_runtime": 1768.5617,
      "eval_samples_per_second": 6.396,
      "eval_steps_per_second": 0.8,
      "step": 81
    },
    {
      "epoch": 0.006104369835479789,
      "grad_norm": 3.0712950229644775,
      "learning_rate": 9.549150281252633e-06,
      "loss": 4.5019,
      "step": 82
    },
    {
      "epoch": 0.00617881337005881,
      "grad_norm": 2.5973801612854004,
      "learning_rate": 8.548121372247918e-06,
      "loss": 4.2906,
      "step": 83
    },
    {
      "epoch": 0.006253256904637832,
      "grad_norm": 2.581934928894043,
      "learning_rate": 7.597595192178702e-06,
      "loss": 3.8983,
      "step": 84
    },
    {
      "epoch": 0.006327700439216854,
      "grad_norm": 2.9472391605377197,
      "learning_rate": 6.698729810778065e-06,
      "loss": 4.1401,
      "step": 85
    },
    {
      "epoch": 0.006402143973795875,
      "grad_norm": 2.82492733001709,
      "learning_rate": 5.852620357053651e-06,
      "loss": 4.1082,
      "step": 86
    },
    {
      "epoch": 0.0064765875083748975,
      "grad_norm": 3.395123243331909,
      "learning_rate": 5.060297685041659e-06,
      "loss": 4.2731,
      "step": 87
    },
    {
      "epoch": 0.00655103104295392,
      "grad_norm": 3.4191434383392334,
      "learning_rate": 4.322727117869951e-06,
      "loss": 4.5354,
      "step": 88
    },
    {
      "epoch": 0.006625474577532941,
      "grad_norm": 3.413599967956543,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 4.7829,
      "step": 89
    },
    {
      "epoch": 0.006699918112111963,
      "grad_norm": 3.189854383468628,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 4.4412,
      "step": 90
    },
    {
      "epoch": 0.006699918112111963,
      "eval_loss": 2.1938297748565674,
      "eval_runtime": 1767.8921,
      "eval_samples_per_second": 6.399,
      "eval_steps_per_second": 0.8,
      "step": 90
    },
    {
      "epoch": 0.006774361646690985,
      "grad_norm": 4.145727157592773,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 4.099,
      "step": 91
    },
    {
      "epoch": 0.006848805181270006,
      "grad_norm": 2.8019332885742188,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 4.6641,
      "step": 92
    },
    {
      "epoch": 0.006923248715849028,
      "grad_norm": 2.8234806060791016,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 4.2909,
      "step": 93
    },
    {
      "epoch": 0.0069976922504280505,
      "grad_norm": 2.6929306983947754,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 4.3875,
      "step": 94
    },
    {
      "epoch": 0.007072135785007072,
      "grad_norm": 3.3331360816955566,
      "learning_rate": 7.596123493895991e-07,
      "loss": 4.9137,
      "step": 95
    },
    {
      "epoch": 0.007146579319586094,
      "grad_norm": 3.2792673110961914,
      "learning_rate": 4.865965629214819e-07,
      "loss": 4.3802,
      "step": 96
    },
    {
      "epoch": 0.007221022854165116,
      "grad_norm": 3.153491497039795,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 4.3517,
      "step": 97
    },
    {
      "epoch": 0.007295466388744137,
      "grad_norm": 2.901925802230835,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 4.2306,
      "step": 98
    },
    {
      "epoch": 0.007369909923323159,
      "grad_norm": 2.977510690689087,
      "learning_rate": 3.04586490452119e-08,
      "loss": 4.3099,
      "step": 99
    },
    {
      "epoch": 0.007369909923323159,
      "eval_loss": 2.1932551860809326,
      "eval_runtime": 1767.8313,
      "eval_samples_per_second": 6.399,
      "eval_steps_per_second": 0.8,
      "step": 99
    },
    {
      "epoch": 0.007444353457902181,
      "grad_norm": 2.916205883026123,
      "learning_rate": 0.0,
      "loss": 4.3172,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2695579394048e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}