{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0434593654932638,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000434593654932638,
      "grad_norm": 1.3132737874984741,
      "learning_rate": 1e-05,
      "loss": 10.4006,
      "step": 1
    },
    {
      "epoch": 0.000434593654932638,
      "eval_loss": 10.412358283996582,
      "eval_runtime": 4.3982,
      "eval_samples_per_second": 1762.306,
      "eval_steps_per_second": 55.25,
      "step": 1
    },
    {
      "epoch": 0.000869187309865276,
      "grad_norm": 1.264045238494873,
      "learning_rate": 2e-05,
      "loss": 10.4156,
      "step": 2
    },
    {
      "epoch": 0.001303780964797914,
      "grad_norm": 1.3569703102111816,
      "learning_rate": 3e-05,
      "loss": 10.4107,
      "step": 3
    },
    {
      "epoch": 0.001738374619730552,
      "grad_norm": 1.262238621711731,
      "learning_rate": 4e-05,
      "loss": 10.4171,
      "step": 4
    },
    {
      "epoch": 0.0021729682746631897,
      "grad_norm": 1.3592532873153687,
      "learning_rate": 5e-05,
      "loss": 10.4103,
      "step": 5
    },
    {
      "epoch": 0.002607561929595828,
      "grad_norm": 1.3463159799575806,
      "learning_rate": 6e-05,
      "loss": 10.4094,
      "step": 6
    },
    {
      "epoch": 0.003042155584528466,
      "grad_norm": 1.3761146068572998,
      "learning_rate": 7e-05,
      "loss": 10.4068,
      "step": 7
    },
    {
      "epoch": 0.003476749239461104,
      "grad_norm": 1.395202398300171,
      "learning_rate": 8e-05,
      "loss": 10.4009,
      "step": 8
    },
    {
      "epoch": 0.003911342894393742,
      "grad_norm": 1.3503137826919556,
      "learning_rate": 9e-05,
      "loss": 10.4024,
      "step": 9
    },
    {
      "epoch": 0.003911342894393742,
      "eval_loss": 10.399940490722656,
      "eval_runtime": 4.3771,
      "eval_samples_per_second": 1770.819,
      "eval_steps_per_second": 55.517,
      "step": 9
    },
    {
      "epoch": 0.004345936549326379,
      "grad_norm": 1.2571992874145508,
      "learning_rate": 0.0001,
      "loss": 10.4072,
      "step": 10
    },
    {
      "epoch": 0.0047805302042590175,
      "grad_norm": 1.3371496200561523,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.4061,
      "step": 11
    },
    {
      "epoch": 0.005215123859191656,
      "grad_norm": 1.3684200048446655,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.4007,
      "step": 12
    },
    {
      "epoch": 0.005649717514124294,
      "grad_norm": 1.4165489673614502,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.3896,
      "step": 13
    },
    {
      "epoch": 0.006084311169056932,
      "grad_norm": 1.4051456451416016,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.387,
      "step": 14
    },
    {
      "epoch": 0.00651890482398957,
      "grad_norm": 1.4135016202926636,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.3802,
      "step": 15
    },
    {
      "epoch": 0.006953498478922208,
      "grad_norm": 1.4162020683288574,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.3781,
      "step": 16
    },
    {
      "epoch": 0.007388092133854845,
      "grad_norm": 1.4314630031585693,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.3888,
      "step": 17
    },
    {
      "epoch": 0.007822685788787484,
      "grad_norm": 1.5304012298583984,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.3621,
      "step": 18
    },
    {
      "epoch": 0.007822685788787484,
      "eval_loss": 10.36774730682373,
      "eval_runtime": 4.3755,
      "eval_samples_per_second": 1771.438,
      "eval_steps_per_second": 55.536,
      "step": 18
    },
    {
      "epoch": 0.008257279443720122,
      "grad_norm": 1.4514573812484741,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3745,
      "step": 19
    },
    {
      "epoch": 0.008691873098652759,
      "grad_norm": 1.5256571769714355,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.3615,
      "step": 20
    },
    {
      "epoch": 0.009126466753585397,
      "grad_norm": 1.528025507926941,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.3546,
      "step": 21
    },
    {
      "epoch": 0.009561060408518035,
      "grad_norm": 1.59959876537323,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.3554,
      "step": 22
    },
    {
      "epoch": 0.009995654063450673,
      "grad_norm": 1.6324058771133423,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.3522,
      "step": 23
    },
    {
      "epoch": 0.010430247718383311,
      "grad_norm": 1.6419366598129272,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.3531,
      "step": 24
    },
    {
      "epoch": 0.01086484137331595,
      "grad_norm": 1.518904447555542,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3524,
      "step": 25
    },
    {
      "epoch": 0.011299435028248588,
      "grad_norm": 1.6594668626785278,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.3408,
      "step": 26
    },
    {
      "epoch": 0.011734028683181226,
      "grad_norm": 1.6574015617370605,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.3433,
      "step": 27
    },
    {
      "epoch": 0.011734028683181226,
      "eval_loss": 10.332037925720215,
      "eval_runtime": 4.4025,
      "eval_samples_per_second": 1760.591,
      "eval_steps_per_second": 55.196,
      "step": 27
    },
    {
      "epoch": 0.012168622338113864,
      "grad_norm": 1.6417022943496704,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3352,
      "step": 28
    },
    {
      "epoch": 0.012603215993046502,
      "grad_norm": 1.6392464637756348,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.3281,
      "step": 29
    },
    {
      "epoch": 0.01303780964797914,
      "grad_norm": 1.6714566946029663,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3287,
      "step": 30
    },
    {
      "epoch": 0.013472403302911778,
      "grad_norm": 1.6938108205795288,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.3242,
      "step": 31
    },
    {
      "epoch": 0.013906996957844416,
      "grad_norm": 1.8171216249465942,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.311,
      "step": 32
    },
    {
      "epoch": 0.014341590612777053,
      "grad_norm": 1.7566795349121094,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.3095,
      "step": 33
    },
    {
      "epoch": 0.01477618426770969,
      "grad_norm": 1.7736107110977173,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.2989,
      "step": 34
    },
    {
      "epoch": 0.015210777922642329,
      "grad_norm": 1.776149034500122,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.3029,
      "step": 35
    },
    {
      "epoch": 0.01564537157757497,
      "grad_norm": 1.7460124492645264,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3025,
      "step": 36
    },
    {
      "epoch": 0.01564537157757497,
      "eval_loss": 10.295435905456543,
      "eval_runtime": 4.3752,
      "eval_samples_per_second": 1771.593,
      "eval_steps_per_second": 55.541,
      "step": 36
    },
    {
      "epoch": 0.016079965232507605,
      "grad_norm": 1.8232313394546509,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.2951,
      "step": 37
    },
    {
      "epoch": 0.016514558887440245,
      "grad_norm": 1.7527620792388916,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.2857,
      "step": 38
    },
    {
      "epoch": 0.01694915254237288,
      "grad_norm": 1.7404676675796509,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.2875,
      "step": 39
    },
    {
      "epoch": 0.017383746197305518,
      "grad_norm": 1.8285305500030518,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.2828,
      "step": 40
    },
    {
      "epoch": 0.017818339852238158,
      "grad_norm": 1.7420995235443115,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.2849,
      "step": 41
    },
    {
      "epoch": 0.018252933507170794,
      "grad_norm": 1.7493330240249634,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.2871,
      "step": 42
    },
    {
      "epoch": 0.018687527162103434,
      "grad_norm": 1.7411251068115234,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.2775,
      "step": 43
    },
    {
      "epoch": 0.01912212081703607,
      "grad_norm": 1.7749557495117188,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.2578,
      "step": 44
    },
    {
      "epoch": 0.01955671447196871,
      "grad_norm": 1.7583379745483398,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.2678,
      "step": 45
    },
    {
      "epoch": 0.01955671447196871,
      "eval_loss": 10.261744499206543,
      "eval_runtime": 4.3669,
      "eval_samples_per_second": 1774.935,
      "eval_steps_per_second": 55.646,
      "step": 45
    },
    {
      "epoch": 0.019991308126901346,
      "grad_norm": 1.7365025281906128,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.2571,
      "step": 46
    },
    {
      "epoch": 0.020425901781833986,
      "grad_norm": 1.7217011451721191,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.2583,
      "step": 47
    },
    {
      "epoch": 0.020860495436766623,
      "grad_norm": 1.7320549488067627,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.2667,
      "step": 48
    },
    {
      "epoch": 0.021295089091699262,
      "grad_norm": 1.7598958015441895,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.2522,
      "step": 49
    },
    {
      "epoch": 0.0217296827466319,
      "grad_norm": 1.7420951128005981,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.2627,
      "step": 50
    },
    {
      "epoch": 0.02216427640156454,
      "grad_norm": 1.6855006217956543,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.2587,
      "step": 51
    },
    {
      "epoch": 0.022598870056497175,
      "grad_norm": 1.6962989568710327,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.2377,
      "step": 52
    },
    {
      "epoch": 0.02303346371142981,
      "grad_norm": 1.6561306715011597,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.2395,
      "step": 53
    },
    {
      "epoch": 0.02346805736636245,
      "grad_norm": 1.6776403188705444,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.2517,
      "step": 54
    },
    {
      "epoch": 0.02346805736636245,
      "eval_loss": 10.234784126281738,
      "eval_runtime": 4.3928,
      "eval_samples_per_second": 1764.474,
      "eval_steps_per_second": 55.318,
      "step": 54
    },
    {
      "epoch": 0.023902651021295088,
      "grad_norm": 1.6507542133331299,
      "learning_rate": 5e-05,
      "loss": 10.2472,
      "step": 55
    },
    {
      "epoch": 0.024337244676227728,
      "grad_norm": 1.6575618982315063,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.2308,
      "step": 56
    },
    {
      "epoch": 0.024771838331160364,
      "grad_norm": 1.6367050409317017,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.2184,
      "step": 57
    },
    {
      "epoch": 0.025206431986093004,
      "grad_norm": 1.634709358215332,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.2335,
      "step": 58
    },
    {
      "epoch": 0.02564102564102564,
      "grad_norm": 1.6403002738952637,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.2438,
      "step": 59
    },
    {
      "epoch": 0.02607561929595828,
      "grad_norm": 1.5752891302108765,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.2285,
      "step": 60
    },
    {
      "epoch": 0.026510212950890916,
      "grad_norm": 1.5749379396438599,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.2177,
      "step": 61
    },
    {
      "epoch": 0.026944806605823556,
      "grad_norm": 1.5850154161453247,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.2273,
      "step": 62
    },
    {
      "epoch": 0.027379400260756193,
      "grad_norm": 1.5233105421066284,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.2221,
      "step": 63
    },
    {
      "epoch": 0.027379400260756193,
      "eval_loss": 10.216018676757812,
      "eval_runtime": 4.396,
      "eval_samples_per_second": 1763.203,
      "eval_steps_per_second": 55.278,
      "step": 63
    },
    {
      "epoch": 0.027813993915688832,
      "grad_norm": 1.5639811754226685,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.2026,
      "step": 64
    },
    {
      "epoch": 0.02824858757062147,
      "grad_norm": 1.541033148765564,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.215,
      "step": 65
    },
    {
      "epoch": 0.028683181225554105,
      "grad_norm": 1.4939786195755005,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.1985,
      "step": 66
    },
    {
      "epoch": 0.029117774880486745,
      "grad_norm": 1.4225854873657227,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.2112,
      "step": 67
    },
    {
      "epoch": 0.02955236853541938,
      "grad_norm": 1.5087547302246094,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.214,
      "step": 68
    },
    {
      "epoch": 0.02998696219035202,
      "grad_norm": 1.4858537912368774,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.2253,
      "step": 69
    },
    {
      "epoch": 0.030421555845284658,
      "grad_norm": 1.4683682918548584,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.2205,
      "step": 70
    },
    {
      "epoch": 0.030856149500217298,
      "grad_norm": 1.4585028886795044,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.2128,
      "step": 71
    },
    {
      "epoch": 0.03129074315514994,
      "grad_norm": 1.476791262626648,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.2148,
      "step": 72
    },
    {
      "epoch": 0.03129074315514994,
      "eval_loss": 10.20433521270752,
      "eval_runtime": 4.3833,
      "eval_samples_per_second": 1768.31,
      "eval_steps_per_second": 55.438,
      "step": 72
    },
    {
      "epoch": 0.03172533681008257,
      "grad_norm": 1.4202309846878052,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.2038,
      "step": 73
    },
    {
      "epoch": 0.03215993046501521,
      "grad_norm": 1.4229024648666382,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.1987,
      "step": 74
    },
    {
      "epoch": 0.03259452411994785,
      "grad_norm": 1.4023692607879639,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.21,
      "step": 75
    },
    {
      "epoch": 0.03302911777488049,
      "grad_norm": 1.3915892839431763,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.2071,
      "step": 76
    },
    {
      "epoch": 0.03346371142981312,
      "grad_norm": 1.4067327976226807,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.1902,
      "step": 77
    },
    {
      "epoch": 0.03389830508474576,
      "grad_norm": 1.4121757745742798,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.192,
      "step": 78
    },
    {
      "epoch": 0.0343328987396784,
      "grad_norm": 1.445264220237732,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.2108,
      "step": 79
    },
    {
      "epoch": 0.034767492394611035,
      "grad_norm": 1.4060300588607788,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.1989,
      "step": 80
    },
    {
      "epoch": 0.035202086049543675,
      "grad_norm": 1.4106123447418213,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.2025,
      "step": 81
    },
    {
      "epoch": 0.035202086049543675,
      "eval_loss": 10.19814395904541,
      "eval_runtime": 4.4149,
      "eval_samples_per_second": 1755.627,
      "eval_steps_per_second": 55.04,
      "step": 81
    },
    {
      "epoch": 0.035636679704476315,
      "grad_norm": 1.4134420156478882,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.2071,
      "step": 82
    },
    {
      "epoch": 0.036071273359408955,
      "grad_norm": 1.3421871662139893,
      "learning_rate": 8.548121372247918e-06,
      "loss": 10.199,
      "step": 83
    },
    {
      "epoch": 0.03650586701434159,
      "grad_norm": 1.3774632215499878,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.19,
      "step": 84
    },
    {
      "epoch": 0.03694046066927423,
      "grad_norm": 1.3491445779800415,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.1879,
      "step": 85
    },
    {
      "epoch": 0.03737505432420687,
      "grad_norm": 1.3587225675582886,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.1965,
      "step": 86
    },
    {
      "epoch": 0.03780964797913951,
      "grad_norm": 1.3620103597640991,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.1911,
      "step": 87
    },
    {
      "epoch": 0.03824424163407214,
      "grad_norm": 1.337594985961914,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.1873,
      "step": 88
    },
    {
      "epoch": 0.03867883528900478,
      "grad_norm": 1.3280407190322876,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 10.2072,
      "step": 89
    },
    {
      "epoch": 0.03911342894393742,
      "grad_norm": 1.3855839967727661,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.2045,
      "step": 90
    },
    {
      "epoch": 0.03911342894393742,
      "eval_loss": 10.195647239685059,
      "eval_runtime": 4.3777,
      "eval_samples_per_second": 1770.565,
      "eval_steps_per_second": 55.509,
      "step": 90
    },
    {
      "epoch": 0.03954802259887006,
      "grad_norm": 1.3364759683609009,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.1887,
      "step": 91
    },
    {
      "epoch": 0.03998261625380269,
      "grad_norm": 1.2921222448349,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.1892,
      "step": 92
    },
    {
      "epoch": 0.04041720990873533,
      "grad_norm": 1.3389850854873657,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.2107,
      "step": 93
    },
    {
      "epoch": 0.04085180356366797,
      "grad_norm": 1.3627759218215942,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.2064,
      "step": 94
    },
    {
      "epoch": 0.041286397218600605,
      "grad_norm": 1.3275415897369385,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.1928,
      "step": 95
    },
    {
      "epoch": 0.041720990873533245,
      "grad_norm": 1.3738682270050049,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.2054,
      "step": 96
    },
    {
      "epoch": 0.042155584528465885,
      "grad_norm": 1.3698922395706177,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 10.2082,
      "step": 97
    },
    {
      "epoch": 0.042590178183398525,
      "grad_norm": 1.3257871866226196,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.1871,
      "step": 98
    },
    {
      "epoch": 0.04302477183833116,
      "grad_norm": 1.3610293865203857,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.192,
      "step": 99
    },
    {
      "epoch": 0.04302477183833116,
      "eval_loss": 10.195563316345215,
      "eval_runtime": 4.3766,
      "eval_samples_per_second": 1771.0,
      "eval_steps_per_second": 55.522,
      "step": 99
    },
    {
      "epoch": 0.0434593654932638,
      "grad_norm": 1.345515251159668,
      "learning_rate": 0.0,
      "loss": 10.1928,
      "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": 20920978636800.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}