{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010140445165542767,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010140445165542768,
      "grad_norm": 8.04444694519043,
      "learning_rate": 1e-05,
      "loss": 15.717,
      "step": 1
    },
    {
      "epoch": 0.00010140445165542768,
      "eval_loss": 8.308691024780273,
      "eval_runtime": 2539.4691,
      "eval_samples_per_second": 3.27,
      "eval_steps_per_second": 0.409,
      "step": 1
    },
    {
      "epoch": 0.00020280890331085536,
      "grad_norm": 7.203917980194092,
      "learning_rate": 2e-05,
      "loss": 14.1263,
      "step": 2
    },
    {
      "epoch": 0.000304213354966283,
      "grad_norm": 7.024128437042236,
      "learning_rate": 3e-05,
      "loss": 15.3502,
      "step": 3
    },
    {
      "epoch": 0.0004056178066217107,
      "grad_norm": 8.651090621948242,
      "learning_rate": 4e-05,
      "loss": 17.9991,
      "step": 4
    },
    {
      "epoch": 0.0005070222582771384,
      "grad_norm": 7.7485151290893555,
      "learning_rate": 5e-05,
      "loss": 17.5751,
      "step": 5
    },
    {
      "epoch": 0.000608426709932566,
      "grad_norm": 8.532367706298828,
      "learning_rate": 6e-05,
      "loss": 15.1637,
      "step": 6
    },
    {
      "epoch": 0.0007098311615879937,
      "grad_norm": 9.773588180541992,
      "learning_rate": 7e-05,
      "loss": 15.8518,
      "step": 7
    },
    {
      "epoch": 0.0008112356132434214,
      "grad_norm": 14.653646469116211,
      "learning_rate": 8e-05,
      "loss": 13.1565,
      "step": 8
    },
    {
      "epoch": 0.000912640064898849,
      "grad_norm": 13.511507987976074,
      "learning_rate": 9e-05,
      "loss": 16.018,
      "step": 9
    },
    {
      "epoch": 0.000912640064898849,
      "eval_loss": 6.607507705688477,
      "eval_runtime": 2532.554,
      "eval_samples_per_second": 3.279,
      "eval_steps_per_second": 0.41,
      "step": 9
    },
    {
      "epoch": 0.0010140445165542768,
      "grad_norm": 14.838384628295898,
      "learning_rate": 0.0001,
      "loss": 13.0172,
      "step": 10
    },
    {
      "epoch": 0.0011154489682097045,
      "grad_norm": 10.868144035339355,
      "learning_rate": 9.99695413509548e-05,
      "loss": 11.4453,
      "step": 11
    },
    {
      "epoch": 0.001216853419865132,
      "grad_norm": 12.606634140014648,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.4203,
      "step": 12
    },
    {
      "epoch": 0.0013182578715205597,
      "grad_norm": 13.766972541809082,
      "learning_rate": 9.972609476841367e-05,
      "loss": 7.9603,
      "step": 13
    },
    {
      "epoch": 0.0014196623231759874,
      "grad_norm": 9.558253288269043,
      "learning_rate": 9.951340343707852e-05,
      "loss": 6.3498,
      "step": 14
    },
    {
      "epoch": 0.0015210667748314151,
      "grad_norm": 17.133962631225586,
      "learning_rate": 9.924038765061042e-05,
      "loss": 7.24,
      "step": 15
    },
    {
      "epoch": 0.0016224712264868428,
      "grad_norm": 12.555543899536133,
      "learning_rate": 9.890738003669029e-05,
      "loss": 5.7092,
      "step": 16
    },
    {
      "epoch": 0.0017238756781422703,
      "grad_norm": 13.254968643188477,
      "learning_rate": 9.851478631379982e-05,
      "loss": 5.4401,
      "step": 17
    },
    {
      "epoch": 0.001825280129797698,
      "grad_norm": 15.194214820861816,
      "learning_rate": 9.806308479691595e-05,
      "loss": 3.2668,
      "step": 18
    },
    {
      "epoch": 0.001825280129797698,
      "eval_loss": 1.8347294330596924,
      "eval_runtime": 2535.231,
      "eval_samples_per_second": 3.276,
      "eval_steps_per_second": 0.41,
      "step": 18
    },
    {
      "epoch": 0.0019266845814531258,
      "grad_norm": 12.147256851196289,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.8558,
      "step": 19
    },
    {
      "epoch": 0.0020280890331085535,
      "grad_norm": 12.598443031311035,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.3306,
      "step": 20
    },
    {
      "epoch": 0.0021294934847639812,
      "grad_norm": 13.3068265914917,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.489,
      "step": 21
    },
    {
      "epoch": 0.002230897936419409,
      "grad_norm": 12.66015338897705,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.642,
      "step": 22
    },
    {
      "epoch": 0.0023323023880748367,
      "grad_norm": 14.067517280578613,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.4228,
      "step": 23
    },
    {
      "epoch": 0.002433706839730264,
      "grad_norm": 15.590002059936523,
      "learning_rate": 9.414737964294636e-05,
      "loss": 3.6261,
      "step": 24
    },
    {
      "epoch": 0.0025351112913856917,
      "grad_norm": 17.668914794921875,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.724,
      "step": 25
    },
    {
      "epoch": 0.0026365157430411194,
      "grad_norm": 11.551734924316406,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.6014,
      "step": 26
    },
    {
      "epoch": 0.002737920194696547,
      "grad_norm": 12.696028709411621,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.9341,
      "step": 27
    },
    {
      "epoch": 0.002737920194696547,
      "eval_loss": 1.0254631042480469,
      "eval_runtime": 2531.8043,
      "eval_samples_per_second": 3.28,
      "eval_steps_per_second": 0.41,
      "step": 27
    },
    {
      "epoch": 0.002839324646351975,
      "grad_norm": 15.396026611328125,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.137,
      "step": 28
    },
    {
      "epoch": 0.0029407290980074025,
      "grad_norm": 8.307568550109863,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.1559,
      "step": 29
    },
    {
      "epoch": 0.0030421335496628303,
      "grad_norm": 7.1335039138793945,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.0939,
      "step": 30
    },
    {
      "epoch": 0.003143538001318258,
      "grad_norm": 10.62819766998291,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.8892,
      "step": 31
    },
    {
      "epoch": 0.0032449424529736857,
      "grad_norm": 11.622336387634277,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.6192,
      "step": 32
    },
    {
      "epoch": 0.0033463469046291134,
      "grad_norm": 17.134801864624023,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.4415,
      "step": 33
    },
    {
      "epoch": 0.0034477513562845407,
      "grad_norm": 10.51050090789795,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.087,
      "step": 34
    },
    {
      "epoch": 0.0035491558079399684,
      "grad_norm": 13.633468627929688,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.2582,
      "step": 35
    },
    {
      "epoch": 0.003650560259595396,
      "grad_norm": 7.963433742523193,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.8015,
      "step": 36
    },
    {
      "epoch": 0.003650560259595396,
      "eval_loss": 0.7936967611312866,
      "eval_runtime": 2531.3442,
      "eval_samples_per_second": 3.281,
      "eval_steps_per_second": 0.41,
      "step": 36
    },
    {
      "epoch": 0.003751964711250824,
      "grad_norm": 9.670333862304688,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.2679,
      "step": 37
    },
    {
      "epoch": 0.0038533691629062516,
      "grad_norm": 6.487051963806152,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.0628,
      "step": 38
    },
    {
      "epoch": 0.003954773614561679,
      "grad_norm": 4.90863037109375,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.7516,
      "step": 39
    },
    {
      "epoch": 0.004056178066217107,
      "grad_norm": 10.051084518432617,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.357,
      "step": 40
    },
    {
      "epoch": 0.004157582517872535,
      "grad_norm": 12.850255966186523,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.7103,
      "step": 41
    },
    {
      "epoch": 0.0042589869695279624,
      "grad_norm": 5.273253917694092,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.9891,
      "step": 42
    },
    {
      "epoch": 0.00436039142118339,
      "grad_norm": 8.386213302612305,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.1369,
      "step": 43
    },
    {
      "epoch": 0.004461795872838818,
      "grad_norm": 6.173641681671143,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.6839,
      "step": 44
    },
    {
      "epoch": 0.004563200324494246,
      "grad_norm": 7.425925254821777,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.1384,
      "step": 45
    },
    {
      "epoch": 0.004563200324494246,
      "eval_loss": 0.6476368308067322,
      "eval_runtime": 2531.2596,
      "eval_samples_per_second": 3.281,
      "eval_steps_per_second": 0.41,
      "step": 45
    },
    {
      "epoch": 0.004664604776149673,
      "grad_norm": 8.646309852600098,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.5463,
      "step": 46
    },
    {
      "epoch": 0.004766009227805101,
      "grad_norm": 7.022440433502197,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.6431,
      "step": 47
    },
    {
      "epoch": 0.004867413679460528,
      "grad_norm": 6.80689811706543,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.917,
      "step": 48
    },
    {
      "epoch": 0.004968818131115956,
      "grad_norm": 7.6442179679870605,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.0936,
      "step": 49
    },
    {
      "epoch": 0.005070222582771383,
      "grad_norm": 6.82839298248291,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.2947,
      "step": 50
    },
    {
      "epoch": 0.005171627034426811,
      "grad_norm": 3.3004310131073,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.3217,
      "step": 51
    },
    {
      "epoch": 0.005273031486082239,
      "grad_norm": 5.62235164642334,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.9575,
      "step": 52
    },
    {
      "epoch": 0.0053744359377376665,
      "grad_norm": 7.620309352874756,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.2226,
      "step": 53
    },
    {
      "epoch": 0.005475840389393094,
      "grad_norm": 8.745861053466797,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.6828,
      "step": 54
    },
    {
      "epoch": 0.005475840389393094,
      "eval_loss": 0.6036913394927979,
      "eval_runtime": 2531.9889,
      "eval_samples_per_second": 3.28,
      "eval_steps_per_second": 0.41,
      "step": 54
    },
    {
      "epoch": 0.005577244841048522,
      "grad_norm": 10.150721549987793,
      "learning_rate": 5e-05,
      "loss": 2.0877,
      "step": 55
    },
    {
      "epoch": 0.00567864929270395,
      "grad_norm": 3.8740344047546387,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.4245,
      "step": 56
    },
    {
      "epoch": 0.005780053744359377,
      "grad_norm": 6.276011943817139,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.2457,
      "step": 57
    },
    {
      "epoch": 0.005881458196014805,
      "grad_norm": 6.720104217529297,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.9674,
      "step": 58
    },
    {
      "epoch": 0.005982862647670233,
      "grad_norm": 7.648861885070801,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.0365,
      "step": 59
    },
    {
      "epoch": 0.0060842670993256605,
      "grad_norm": 8.60343074798584,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.7826,
      "step": 60
    },
    {
      "epoch": 0.006185671550981088,
      "grad_norm": 7.075626850128174,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.5154,
      "step": 61
    },
    {
      "epoch": 0.006287076002636516,
      "grad_norm": 7.07039213180542,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.1351,
      "step": 62
    },
    {
      "epoch": 0.006388480454291944,
      "grad_norm": 8.246896743774414,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.3934,
      "step": 63
    },
    {
      "epoch": 0.006388480454291944,
      "eval_loss": 0.48226019740104675,
      "eval_runtime": 2531.0027,
      "eval_samples_per_second": 3.281,
      "eval_steps_per_second": 0.411,
      "step": 63
    },
    {
      "epoch": 0.006489884905947371,
      "grad_norm": 8.647876739501953,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8872,
      "step": 64
    },
    {
      "epoch": 0.006591289357602799,
      "grad_norm": 11.226241111755371,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.624,
      "step": 65
    },
    {
      "epoch": 0.006692693809258227,
      "grad_norm": 7.301259994506836,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.9862,
      "step": 66
    },
    {
      "epoch": 0.006794098260913654,
      "grad_norm": 7.271656036376953,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.4684,
      "step": 67
    },
    {
      "epoch": 0.006895502712569081,
      "grad_norm": 8.438143730163574,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.5884,
      "step": 68
    },
    {
      "epoch": 0.006996907164224509,
      "grad_norm": 6.952368259429932,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.0669,
      "step": 69
    },
    {
      "epoch": 0.007098311615879937,
      "grad_norm": 4.599670886993408,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.4172,
      "step": 70
    },
    {
      "epoch": 0.0071997160675353646,
      "grad_norm": 5.724601745605469,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.998,
      "step": 71
    },
    {
      "epoch": 0.007301120519190792,
      "grad_norm": 4.842506408691406,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.6398,
      "step": 72
    },
    {
      "epoch": 0.007301120519190792,
      "eval_loss": 0.449500173330307,
      "eval_runtime": 2531.0415,
      "eval_samples_per_second": 3.281,
      "eval_steps_per_second": 0.411,
      "step": 72
    },
    {
      "epoch": 0.00740252497084622,
      "grad_norm": 4.754809379577637,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.3237,
      "step": 73
    },
    {
      "epoch": 0.007503929422501648,
      "grad_norm": 8.848258972167969,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.8927,
      "step": 74
    },
    {
      "epoch": 0.007605333874157075,
      "grad_norm": 8.805027961730957,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.2199,
      "step": 75
    },
    {
      "epoch": 0.007706738325812503,
      "grad_norm": 9.314416885375977,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.3086,
      "step": 76
    },
    {
      "epoch": 0.007808142777467931,
      "grad_norm": 6.936118125915527,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.9047,
      "step": 77
    },
    {
      "epoch": 0.007909547229123359,
      "grad_norm": 3.753873109817505,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.3682,
      "step": 78
    },
    {
      "epoch": 0.008010951680778786,
      "grad_norm": 7.8667120933532715,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.5332,
      "step": 79
    },
    {
      "epoch": 0.008112356132434214,
      "grad_norm": 7.0443525314331055,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.7697,
      "step": 80
    },
    {
      "epoch": 0.008213760584089642,
      "grad_norm": 8.24865436553955,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.6488,
      "step": 81
    },
    {
      "epoch": 0.008213760584089642,
      "eval_loss": 0.41231730580329895,
      "eval_runtime": 2536.3196,
      "eval_samples_per_second": 3.274,
      "eval_steps_per_second": 0.41,
      "step": 81
    },
    {
      "epoch": 0.00831516503574507,
      "grad_norm": 15.85305404663086,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7362,
      "step": 82
    },
    {
      "epoch": 0.008416569487400497,
      "grad_norm": 7.095248222351074,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.8771,
      "step": 83
    },
    {
      "epoch": 0.008517973939055925,
      "grad_norm": 17.029613494873047,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.7971,
      "step": 84
    },
    {
      "epoch": 0.008619378390711353,
      "grad_norm": 8.894125938415527,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.8214,
      "step": 85
    },
    {
      "epoch": 0.00872078284236678,
      "grad_norm": 5.424424648284912,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.4995,
      "step": 86
    },
    {
      "epoch": 0.008822187294022208,
      "grad_norm": 7.909368991851807,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.0184,
      "step": 87
    },
    {
      "epoch": 0.008923591745677636,
      "grad_norm": 5.472009658813477,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.9246,
      "step": 88
    },
    {
      "epoch": 0.009024996197333063,
      "grad_norm": 4.643977642059326,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.3992,
      "step": 89
    },
    {
      "epoch": 0.009126400648988491,
      "grad_norm": 7.8704400062561035,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.1878,
      "step": 90
    },
    {
      "epoch": 0.009126400648988491,
      "eval_loss": 0.40286701917648315,
      "eval_runtime": 2545.441,
      "eval_samples_per_second": 3.263,
      "eval_steps_per_second": 0.408,
      "step": 90
    },
    {
      "epoch": 0.009227805100643919,
      "grad_norm": 10.073358535766602,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.2557,
      "step": 91
    },
    {
      "epoch": 0.009329209552299347,
      "grad_norm": 4.862026691436768,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.4489,
      "step": 92
    },
    {
      "epoch": 0.009430614003954774,
      "grad_norm": 10.518214225769043,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.5892,
      "step": 93
    },
    {
      "epoch": 0.009532018455610202,
      "grad_norm": 8.495722770690918,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.2313,
      "step": 94
    },
    {
      "epoch": 0.00963342290726563,
      "grad_norm": 7.1495208740234375,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.1939,
      "step": 95
    },
    {
      "epoch": 0.009734827358921056,
      "grad_norm": 6.811301231384277,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.7795,
      "step": 96
    },
    {
      "epoch": 0.009836231810576484,
      "grad_norm": 5.596134662628174,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.9895,
      "step": 97
    },
    {
      "epoch": 0.009937636262231911,
      "grad_norm": 6.312773704528809,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.7823,
      "step": 98
    },
    {
      "epoch": 0.010039040713887339,
      "grad_norm": 6.789220809936523,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.8785,
      "step": 99
    },
    {
      "epoch": 0.010039040713887339,
      "eval_loss": 0.39961904287338257,
      "eval_runtime": 2544.0002,
      "eval_samples_per_second": 3.265,
      "eval_steps_per_second": 0.408,
      "step": 99
    },
    {
      "epoch": 0.010140445165542767,
      "grad_norm": 8.310434341430664,
      "learning_rate": 0.0,
      "loss": 0.508,
      "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": 2.462942402445312e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}