{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.28901734104046245,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002890173410404624,
      "grad_norm": 2.18648099899292,
      "learning_rate": 1e-05,
      "loss": 3.9098,
      "step": 1
    },
    {
      "epoch": 0.002890173410404624,
      "eval_loss": 3.771548271179199,
      "eval_runtime": 9.5374,
      "eval_samples_per_second": 30.616,
      "eval_steps_per_second": 3.879,
      "step": 1
    },
    {
      "epoch": 0.005780346820809248,
      "grad_norm": 2.5637943744659424,
      "learning_rate": 2e-05,
      "loss": 3.8253,
      "step": 2
    },
    {
      "epoch": 0.008670520231213872,
      "grad_norm": 2.2409257888793945,
      "learning_rate": 3e-05,
      "loss": 3.4431,
      "step": 3
    },
    {
      "epoch": 0.011560693641618497,
      "grad_norm": 2.114107847213745,
      "learning_rate": 4e-05,
      "loss": 3.6387,
      "step": 4
    },
    {
      "epoch": 0.014450867052023121,
      "grad_norm": 2.1709423065185547,
      "learning_rate": 5e-05,
      "loss": 3.3399,
      "step": 5
    },
    {
      "epoch": 0.017341040462427744,
      "grad_norm": 2.1868350505828857,
      "learning_rate": 6e-05,
      "loss": 3.7193,
      "step": 6
    },
    {
      "epoch": 0.02023121387283237,
      "grad_norm": 2.3975000381469727,
      "learning_rate": 7e-05,
      "loss": 3.6587,
      "step": 7
    },
    {
      "epoch": 0.023121387283236993,
      "grad_norm": 2.3437464237213135,
      "learning_rate": 8e-05,
      "loss": 3.9804,
      "step": 8
    },
    {
      "epoch": 0.02601156069364162,
      "grad_norm": 2.5270299911499023,
      "learning_rate": 9e-05,
      "loss": 3.7135,
      "step": 9
    },
    {
      "epoch": 0.02601156069364162,
      "eval_loss": 3.517235279083252,
      "eval_runtime": 8.901,
      "eval_samples_per_second": 32.805,
      "eval_steps_per_second": 4.157,
      "step": 9
    },
    {
      "epoch": 0.028901734104046242,
      "grad_norm": 2.024913787841797,
      "learning_rate": 0.0001,
      "loss": 3.1592,
      "step": 10
    },
    {
      "epoch": 0.031791907514450865,
      "grad_norm": 2.1370906829833984,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.9475,
      "step": 11
    },
    {
      "epoch": 0.03468208092485549,
      "grad_norm": 2.334064245223999,
      "learning_rate": 9.987820251299122e-05,
      "loss": 3.5657,
      "step": 12
    },
    {
      "epoch": 0.03757225433526012,
      "grad_norm": 2.2035064697265625,
      "learning_rate": 9.972609476841367e-05,
      "loss": 3.4261,
      "step": 13
    },
    {
      "epoch": 0.04046242774566474,
      "grad_norm": 2.4026477336883545,
      "learning_rate": 9.951340343707852e-05,
      "loss": 3.5981,
      "step": 14
    },
    {
      "epoch": 0.04335260115606936,
      "grad_norm": 2.204759120941162,
      "learning_rate": 9.924038765061042e-05,
      "loss": 3.2382,
      "step": 15
    },
    {
      "epoch": 0.046242774566473986,
      "grad_norm": 2.8506884574890137,
      "learning_rate": 9.890738003669029e-05,
      "loss": 3.0232,
      "step": 16
    },
    {
      "epoch": 0.049132947976878616,
      "grad_norm": 2.8348145484924316,
      "learning_rate": 9.851478631379982e-05,
      "loss": 3.1734,
      "step": 17
    },
    {
      "epoch": 0.05202312138728324,
      "grad_norm": 2.285172939300537,
      "learning_rate": 9.806308479691595e-05,
      "loss": 3.1164,
      "step": 18
    },
    {
      "epoch": 0.05202312138728324,
      "eval_loss": 3.125600814819336,
      "eval_runtime": 8.9013,
      "eval_samples_per_second": 32.804,
      "eval_steps_per_second": 4.157,
      "step": 18
    },
    {
      "epoch": 0.05491329479768786,
      "grad_norm": 2.6271793842315674,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.3178,
      "step": 19
    },
    {
      "epoch": 0.057803468208092484,
      "grad_norm": 2.7905006408691406,
      "learning_rate": 9.698463103929542e-05,
      "loss": 3.0927,
      "step": 20
    },
    {
      "epoch": 0.06069364161849711,
      "grad_norm": 2.440577983856201,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.8579,
      "step": 21
    },
    {
      "epoch": 0.06358381502890173,
      "grad_norm": 2.4865357875823975,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.9136,
      "step": 22
    },
    {
      "epoch": 0.06647398843930635,
      "grad_norm": 3.051366090774536,
      "learning_rate": 9.493970231495835e-05,
      "loss": 3.0936,
      "step": 23
    },
    {
      "epoch": 0.06936416184971098,
      "grad_norm": 3.029160261154175,
      "learning_rate": 9.414737964294636e-05,
      "loss": 3.0779,
      "step": 24
    },
    {
      "epoch": 0.07225433526011561,
      "grad_norm": 2.521898031234741,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.9553,
      "step": 25
    },
    {
      "epoch": 0.07514450867052024,
      "grad_norm": 2.6830172538757324,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.9984,
      "step": 26
    },
    {
      "epoch": 0.07803468208092486,
      "grad_norm": 2.6048848628997803,
      "learning_rate": 9.145187862775209e-05,
      "loss": 3.146,
      "step": 27
    },
    {
      "epoch": 0.07803468208092486,
      "eval_loss": 2.980114221572876,
      "eval_runtime": 8.8703,
      "eval_samples_per_second": 32.919,
      "eval_steps_per_second": 4.171,
      "step": 27
    },
    {
      "epoch": 0.08092485549132948,
      "grad_norm": 2.5352957248687744,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.8203,
      "step": 28
    },
    {
      "epoch": 0.0838150289017341,
      "grad_norm": 2.465588331222534,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.8266,
      "step": 29
    },
    {
      "epoch": 0.08670520231213873,
      "grad_norm": 2.6173558235168457,
      "learning_rate": 8.83022221559489e-05,
      "loss": 3.0962,
      "step": 30
    },
    {
      "epoch": 0.08959537572254335,
      "grad_norm": 2.6473875045776367,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.8749,
      "step": 31
    },
    {
      "epoch": 0.09248554913294797,
      "grad_norm": 2.5935564041137695,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.7621,
      "step": 32
    },
    {
      "epoch": 0.0953757225433526,
      "grad_norm": 2.4422733783721924,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.7569,
      "step": 33
    },
    {
      "epoch": 0.09826589595375723,
      "grad_norm": 2.623366355895996,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.8016,
      "step": 34
    },
    {
      "epoch": 0.10115606936416185,
      "grad_norm": 2.533163547515869,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.9004,
      "step": 35
    },
    {
      "epoch": 0.10404624277456648,
      "grad_norm": 2.4128429889678955,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.7106,
      "step": 36
    },
    {
      "epoch": 0.10404624277456648,
      "eval_loss": 2.8798065185546875,
      "eval_runtime": 8.8724,
      "eval_samples_per_second": 32.911,
      "eval_steps_per_second": 4.17,
      "step": 36
    },
    {
      "epoch": 0.1069364161849711,
      "grad_norm": 2.8826918601989746,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.6589,
      "step": 37
    },
    {
      "epoch": 0.10982658959537572,
      "grad_norm": 2.6255695819854736,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.9028,
      "step": 38
    },
    {
      "epoch": 0.11271676300578035,
      "grad_norm": 2.598806619644165,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.9346,
      "step": 39
    },
    {
      "epoch": 0.11560693641618497,
      "grad_norm": 2.8739166259765625,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.2118,
      "step": 40
    },
    {
      "epoch": 0.11849710982658959,
      "grad_norm": 2.8248085975646973,
      "learning_rate": 7.347357813929454e-05,
      "loss": 3.0775,
      "step": 41
    },
    {
      "epoch": 0.12138728323699421,
      "grad_norm": 2.626497745513916,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.6998,
      "step": 42
    },
    {
      "epoch": 0.12427745664739884,
      "grad_norm": 2.717621088027954,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.9985,
      "step": 43
    },
    {
      "epoch": 0.12716763005780346,
      "grad_norm": 2.500718355178833,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.545,
      "step": 44
    },
    {
      "epoch": 0.13005780346820808,
      "grad_norm": 2.7403721809387207,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.8951,
      "step": 45
    },
    {
      "epoch": 0.13005780346820808,
      "eval_loss": 2.8127658367156982,
      "eval_runtime": 8.8782,
      "eval_samples_per_second": 32.89,
      "eval_steps_per_second": 4.168,
      "step": 45
    },
    {
      "epoch": 0.1329479768786127,
      "grad_norm": 2.7176103591918945,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.5859,
      "step": 46
    },
    {
      "epoch": 0.13583815028901733,
      "grad_norm": 2.871258020401001,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.7279,
      "step": 47
    },
    {
      "epoch": 0.13872832369942195,
      "grad_norm": 2.6269922256469727,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.7583,
      "step": 48
    },
    {
      "epoch": 0.1416184971098266,
      "grad_norm": 2.6989223957061768,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.7658,
      "step": 49
    },
    {
      "epoch": 0.14450867052023122,
      "grad_norm": 3.0512256622314453,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.8892,
      "step": 50
    },
    {
      "epoch": 0.14739884393063585,
      "grad_norm": 2.6319949626922607,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.6159,
      "step": 51
    },
    {
      "epoch": 0.15028901734104047,
      "grad_norm": 2.8516249656677246,
      "learning_rate": 5.522642316338268e-05,
      "loss": 2.5317,
      "step": 52
    },
    {
      "epoch": 0.1531791907514451,
      "grad_norm": 2.524003505706787,
      "learning_rate": 5.348782368720626e-05,
      "loss": 2.5472,
      "step": 53
    },
    {
      "epoch": 0.15606936416184972,
      "grad_norm": 2.6813533306121826,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.5822,
      "step": 54
    },
    {
      "epoch": 0.15606936416184972,
      "eval_loss": 2.7581820487976074,
      "eval_runtime": 8.8741,
      "eval_samples_per_second": 32.905,
      "eval_steps_per_second": 4.169,
      "step": 54
    },
    {
      "epoch": 0.15895953757225434,
      "grad_norm": 2.7405776977539062,
      "learning_rate": 5e-05,
      "loss": 2.8394,
      "step": 55
    },
    {
      "epoch": 0.16184971098265896,
      "grad_norm": 2.9321837425231934,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.7286,
      "step": 56
    },
    {
      "epoch": 0.16473988439306358,
      "grad_norm": 2.7207789421081543,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 2.8384,
      "step": 57
    },
    {
      "epoch": 0.1676300578034682,
      "grad_norm": 3.089175224304199,
      "learning_rate": 4.477357683661734e-05,
      "loss": 2.5763,
      "step": 58
    },
    {
      "epoch": 0.17052023121387283,
      "grad_norm": 2.720059394836426,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 2.5755,
      "step": 59
    },
    {
      "epoch": 0.17341040462427745,
      "grad_norm": 2.922912359237671,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.7125,
      "step": 60
    },
    {
      "epoch": 0.17630057803468208,
      "grad_norm": 3.258070468902588,
      "learning_rate": 3.960441545911204e-05,
      "loss": 2.9284,
      "step": 61
    },
    {
      "epoch": 0.1791907514450867,
      "grad_norm": 2.626788854598999,
      "learning_rate": 3.790390522001662e-05,
      "loss": 2.5523,
      "step": 62
    },
    {
      "epoch": 0.18208092485549132,
      "grad_norm": 2.9130256175994873,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 2.5155,
      "step": 63
    },
    {
      "epoch": 0.18208092485549132,
      "eval_loss": 2.7157061100006104,
      "eval_runtime": 8.8827,
      "eval_samples_per_second": 32.873,
      "eval_steps_per_second": 4.165,
      "step": 63
    },
    {
      "epoch": 0.18497109826589594,
      "grad_norm": 2.973673105239868,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.6407,
      "step": 64
    },
    {
      "epoch": 0.18786127167630057,
      "grad_norm": 2.944984197616577,
      "learning_rate": 3.289899283371657e-05,
      "loss": 2.6636,
      "step": 65
    },
    {
      "epoch": 0.1907514450867052,
      "grad_norm": 2.981041669845581,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.7202,
      "step": 66
    },
    {
      "epoch": 0.1936416184971098,
      "grad_norm": 3.1164071559906006,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 2.7492,
      "step": 67
    },
    {
      "epoch": 0.19653179190751446,
      "grad_norm": 2.923830509185791,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.447,
      "step": 68
    },
    {
      "epoch": 0.1994219653179191,
      "grad_norm": 2.7833638191223145,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.4775,
      "step": 69
    },
    {
      "epoch": 0.2023121387283237,
      "grad_norm": 3.2872817516326904,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.3148,
      "step": 70
    },
    {
      "epoch": 0.20520231213872833,
      "grad_norm": 2.7457706928253174,
      "learning_rate": 2.350403678833976e-05,
      "loss": 2.473,
      "step": 71
    },
    {
      "epoch": 0.20809248554913296,
      "grad_norm": 3.0364837646484375,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 2.7785,
      "step": 72
    },
    {
      "epoch": 0.20809248554913296,
      "eval_loss": 2.6876657009124756,
      "eval_runtime": 8.8791,
      "eval_samples_per_second": 32.886,
      "eval_steps_per_second": 4.167,
      "step": 72
    },
    {
      "epoch": 0.21098265895953758,
      "grad_norm": 2.7354369163513184,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.5588,
      "step": 73
    },
    {
      "epoch": 0.2138728323699422,
      "grad_norm": 2.9190850257873535,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 2.8077,
      "step": 74
    },
    {
      "epoch": 0.21676300578034682,
      "grad_norm": 2.9655392169952393,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 2.4385,
      "step": 75
    },
    {
      "epoch": 0.21965317919075145,
      "grad_norm": 3.0310251712799072,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 2.8126,
      "step": 76
    },
    {
      "epoch": 0.22254335260115607,
      "grad_norm": 3.0896308422088623,
      "learning_rate": 1.526708147705013e-05,
      "loss": 2.6872,
      "step": 77
    },
    {
      "epoch": 0.2254335260115607,
      "grad_norm": 3.4779391288757324,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 3.1186,
      "step": 78
    },
    {
      "epoch": 0.22832369942196531,
      "grad_norm": 3.025620937347412,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 2.6581,
      "step": 79
    },
    {
      "epoch": 0.23121387283236994,
      "grad_norm": 2.913504123687744,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 2.639,
      "step": 80
    },
    {
      "epoch": 0.23410404624277456,
      "grad_norm": 2.745175838470459,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 2.6848,
      "step": 81
    },
    {
      "epoch": 0.23410404624277456,
      "eval_loss": 2.67075252532959,
      "eval_runtime": 8.8806,
      "eval_samples_per_second": 32.881,
      "eval_steps_per_second": 4.166,
      "step": 81
    },
    {
      "epoch": 0.23699421965317918,
      "grad_norm": 2.941321849822998,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.659,
      "step": 82
    },
    {
      "epoch": 0.2398843930635838,
      "grad_norm": 2.9211745262145996,
      "learning_rate": 8.548121372247918e-06,
      "loss": 2.7253,
      "step": 83
    },
    {
      "epoch": 0.24277456647398843,
      "grad_norm": 3.229653835296631,
      "learning_rate": 7.597595192178702e-06,
      "loss": 2.6702,
      "step": 84
    },
    {
      "epoch": 0.24566473988439305,
      "grad_norm": 3.0195236206054688,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.5184,
      "step": 85
    },
    {
      "epoch": 0.24855491329479767,
      "grad_norm": 3.188051462173462,
      "learning_rate": 5.852620357053651e-06,
      "loss": 2.8108,
      "step": 86
    },
    {
      "epoch": 0.2514450867052023,
      "grad_norm": 3.2656967639923096,
      "learning_rate": 5.060297685041659e-06,
      "loss": 2.5328,
      "step": 87
    },
    {
      "epoch": 0.2543352601156069,
      "grad_norm": 2.820098638534546,
      "learning_rate": 4.322727117869951e-06,
      "loss": 2.7201,
      "step": 88
    },
    {
      "epoch": 0.25722543352601157,
      "grad_norm": 2.7186193466186523,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 2.6101,
      "step": 89
    },
    {
      "epoch": 0.26011560693641617,
      "grad_norm": 2.8825700283050537,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.5704,
      "step": 90
    },
    {
      "epoch": 0.26011560693641617,
      "eval_loss": 2.6646721363067627,
      "eval_runtime": 8.8756,
      "eval_samples_per_second": 32.899,
      "eval_steps_per_second": 4.169,
      "step": 90
    },
    {
      "epoch": 0.2630057803468208,
      "grad_norm": 2.956404209136963,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.3967,
      "step": 91
    },
    {
      "epoch": 0.2658959537572254,
      "grad_norm": 3.350674629211426,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 2.7052,
      "step": 92
    },
    {
      "epoch": 0.26878612716763006,
      "grad_norm": 3.1574625968933105,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 2.8255,
      "step": 93
    },
    {
      "epoch": 0.27167630057803466,
      "grad_norm": 2.9273691177368164,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.2784,
      "step": 94
    },
    {
      "epoch": 0.2745664739884393,
      "grad_norm": 3.1357064247131348,
      "learning_rate": 7.596123493895991e-07,
      "loss": 2.8564,
      "step": 95
    },
    {
      "epoch": 0.2774566473988439,
      "grad_norm": 3.1920857429504395,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2.5804,
      "step": 96
    },
    {
      "epoch": 0.28034682080924855,
      "grad_norm": 2.7851128578186035,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 2.6682,
      "step": 97
    },
    {
      "epoch": 0.2832369942196532,
      "grad_norm": 3.0959720611572266,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.6304,
      "step": 98
    },
    {
      "epoch": 0.2861271676300578,
      "grad_norm": 2.8245437145233154,
      "learning_rate": 3.04586490452119e-08,
      "loss": 2.7105,
      "step": 99
    },
    {
      "epoch": 0.2861271676300578,
      "eval_loss": 2.663463592529297,
      "eval_runtime": 8.8745,
      "eval_samples_per_second": 32.903,
      "eval_steps_per_second": 4.169,
      "step": 99
    },
    {
      "epoch": 0.28901734104046245,
      "grad_norm": 2.9880802631378174,
      "learning_rate": 0.0,
      "loss": 2.706,
      "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": 9677225695641600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}