{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0032895458233733197,
  "eval_steps": 9,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.386061097831093e-05,
      "grad_norm": 0.10043748468160629,
      "learning_rate": 1e-05,
      "loss": 10.3679,
      "step": 1
    },
    {
      "epoch": 4.386061097831093e-05,
      "eval_loss": 10.372465133666992,
      "eval_runtime": 286.375,
      "eval_samples_per_second": 67.045,
      "eval_steps_per_second": 8.381,
      "step": 1
    },
    {
      "epoch": 8.772122195662186e-05,
      "grad_norm": 0.07904290407896042,
      "learning_rate": 2e-05,
      "loss": 10.384,
      "step": 2
    },
    {
      "epoch": 0.00013158183293493278,
      "grad_norm": 0.08990306407213211,
      "learning_rate": 3e-05,
      "loss": 10.3806,
      "step": 3
    },
    {
      "epoch": 0.00017544244391324372,
      "grad_norm": 0.08300121128559113,
      "learning_rate": 4e-05,
      "loss": 10.379,
      "step": 4
    },
    {
      "epoch": 0.00021930305489155464,
      "grad_norm": 0.10797716677188873,
      "learning_rate": 5e-05,
      "loss": 10.3875,
      "step": 5
    },
    {
      "epoch": 0.00026316366586986555,
      "grad_norm": 0.12022226303815842,
      "learning_rate": 6e-05,
      "loss": 10.3697,
      "step": 6
    },
    {
      "epoch": 0.00030702427684817647,
      "grad_norm": 0.11509042233228683,
      "learning_rate": 7e-05,
      "loss": 10.3746,
      "step": 7
    },
    {
      "epoch": 0.00035088488782648744,
      "grad_norm": 0.10822642594575882,
      "learning_rate": 8e-05,
      "loss": 10.3679,
      "step": 8
    },
    {
      "epoch": 0.00039474549880479836,
      "grad_norm": 0.11744695156812668,
      "learning_rate": 9e-05,
      "loss": 10.3775,
      "step": 9
    },
    {
      "epoch": 0.00039474549880479836,
      "eval_loss": 10.371199607849121,
      "eval_runtime": 286.4036,
      "eval_samples_per_second": 67.038,
      "eval_steps_per_second": 8.38,
      "step": 9
    },
    {
      "epoch": 0.0004386061097831093,
      "grad_norm": 0.08792486041784286,
      "learning_rate": 0.0001,
      "loss": 10.3841,
      "step": 10
    },
    {
      "epoch": 0.0004824667207614202,
      "grad_norm": 0.18052351474761963,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.3768,
      "step": 11
    },
    {
      "epoch": 0.0005263273317397311,
      "grad_norm": 0.10901749134063721,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3686,
      "step": 12
    },
    {
      "epoch": 0.0005701879427180421,
      "grad_norm": 0.12148555368185043,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.3674,
      "step": 13
    },
    {
      "epoch": 0.0006140485536963529,
      "grad_norm": 0.15141719579696655,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.3568,
      "step": 14
    },
    {
      "epoch": 0.0006579091646746639,
      "grad_norm": 0.13673336803913116,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.357,
      "step": 15
    },
    {
      "epoch": 0.0007017697756529749,
      "grad_norm": 0.1090550422668457,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.3686,
      "step": 16
    },
    {
      "epoch": 0.0007456303866312857,
      "grad_norm": 0.12227842211723328,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.367,
      "step": 17
    },
    {
      "epoch": 0.0007894909976095967,
      "grad_norm": 0.12432891130447388,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.3589,
      "step": 18
    },
    {
      "epoch": 0.0007894909976095967,
      "eval_loss": 10.367905616760254,
      "eval_runtime": 286.4026,
      "eval_samples_per_second": 67.039,
      "eval_steps_per_second": 8.38,
      "step": 18
    },
    {
      "epoch": 0.0008333516085879076,
      "grad_norm": 0.09832531958818436,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.373,
      "step": 19
    },
    {
      "epoch": 0.0008772122195662185,
      "grad_norm": 0.1374433934688568,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.3661,
      "step": 20
    },
    {
      "epoch": 0.0009210728305445295,
      "grad_norm": 0.12131146341562271,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.365,
      "step": 21
    },
    {
      "epoch": 0.0009649334415228404,
      "grad_norm": 0.14021863043308258,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.3637,
      "step": 22
    },
    {
      "epoch": 0.0010087940525011514,
      "grad_norm": 0.09942276775836945,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.3705,
      "step": 23
    },
    {
      "epoch": 0.0010526546634794622,
      "grad_norm": 0.12141352891921997,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.375,
      "step": 24
    },
    {
      "epoch": 0.0010965152744577733,
      "grad_norm": 0.1361175924539566,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3731,
      "step": 25
    },
    {
      "epoch": 0.0011403758854360842,
      "grad_norm": 0.1491241157054901,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.3667,
      "step": 26
    },
    {
      "epoch": 0.001184236496414395,
      "grad_norm": 0.10183785855770111,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.3657,
      "step": 27
    },
    {
      "epoch": 0.001184236496414395,
      "eval_loss": 10.364358901977539,
      "eval_runtime": 286.4073,
      "eval_samples_per_second": 67.037,
      "eval_steps_per_second": 8.38,
      "step": 27
    },
    {
      "epoch": 0.0012280971073927059,
      "grad_norm": 0.1549397110939026,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3657,
      "step": 28
    },
    {
      "epoch": 0.001271957718371017,
      "grad_norm": 0.13460959494113922,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.3638,
      "step": 29
    },
    {
      "epoch": 0.0013158183293493278,
      "grad_norm": 0.1680450737476349,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3497,
      "step": 30
    },
    {
      "epoch": 0.0013596789403276387,
      "grad_norm": 0.17578570544719696,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.3535,
      "step": 31
    },
    {
      "epoch": 0.0014035395513059498,
      "grad_norm": 0.13843394815921783,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.3702,
      "step": 32
    },
    {
      "epoch": 0.0014474001622842606,
      "grad_norm": 0.11930979043245316,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.3567,
      "step": 33
    },
    {
      "epoch": 0.0014912607732625715,
      "grad_norm": 0.16353154182434082,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.3558,
      "step": 34
    },
    {
      "epoch": 0.0015351213842408826,
      "grad_norm": 0.14352919161319733,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.365,
      "step": 35
    },
    {
      "epoch": 0.0015789819952191934,
      "grad_norm": 0.12820452451705933,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3786,
      "step": 36
    },
    {
      "epoch": 0.0015789819952191934,
      "eval_loss": 10.36049747467041,
      "eval_runtime": 286.4801,
      "eval_samples_per_second": 67.02,
      "eval_steps_per_second": 8.378,
      "step": 36
    },
    {
      "epoch": 0.0016228426061975043,
      "grad_norm": 0.1572307050228119,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.354,
      "step": 37
    },
    {
      "epoch": 0.0016667032171758152,
      "grad_norm": 0.14594314992427826,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.365,
      "step": 38
    },
    {
      "epoch": 0.0017105638281541262,
      "grad_norm": 0.16759568452835083,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.368,
      "step": 39
    },
    {
      "epoch": 0.001754424439132437,
      "grad_norm": 0.1462918370962143,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3652,
      "step": 40
    },
    {
      "epoch": 0.001798285050110748,
      "grad_norm": 0.12642958760261536,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.3728,
      "step": 41
    },
    {
      "epoch": 0.001842145661089059,
      "grad_norm": 0.13390545547008514,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.3578,
      "step": 42
    },
    {
      "epoch": 0.00188600627206737,
      "grad_norm": 0.19535711407661438,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.3566,
      "step": 43
    },
    {
      "epoch": 0.0019298668830456808,
      "grad_norm": 0.20104841887950897,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.349,
      "step": 44
    },
    {
      "epoch": 0.0019737274940239916,
      "grad_norm": 0.19125540554523468,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.36,
      "step": 45
    },
    {
      "epoch": 0.0019737274940239916,
      "eval_loss": 10.356492042541504,
      "eval_runtime": 286.2165,
      "eval_samples_per_second": 67.082,
      "eval_steps_per_second": 8.385,
      "step": 45
    },
    {
      "epoch": 0.0020175881050023027,
      "grad_norm": 0.20440174639225006,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3542,
      "step": 46
    },
    {
      "epoch": 0.002061448715980614,
      "grad_norm": 0.25062036514282227,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.3474,
      "step": 47
    },
    {
      "epoch": 0.0021053093269589244,
      "grad_norm": 0.20420685410499573,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.3493,
      "step": 48
    },
    {
      "epoch": 0.0021491699379372355,
      "grad_norm": 0.17665934562683105,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.3618,
      "step": 49
    },
    {
      "epoch": 0.0021930305489155466,
      "grad_norm": 0.22118310630321503,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.3426,
      "step": 50
    },
    {
      "epoch": 0.0022368911598938572,
      "grad_norm": 0.2247057557106018,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.3506,
      "step": 51
    },
    {
      "epoch": 0.0022807517708721683,
      "grad_norm": 0.18720436096191406,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.358,
      "step": 52
    },
    {
      "epoch": 0.0023246123818504794,
      "grad_norm": 0.19579781591892242,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.3548,
      "step": 53
    },
    {
      "epoch": 0.00236847299282879,
      "grad_norm": 0.12509997189044952,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.3671,
      "step": 54
    },
    {
      "epoch": 0.00236847299282879,
      "eval_loss": 10.352391242980957,
      "eval_runtime": 286.4387,
      "eval_samples_per_second": 67.03,
      "eval_steps_per_second": 8.379,
      "step": 54
    },
    {
      "epoch": 0.002412333603807101,
      "grad_norm": 0.14832502603530884,
      "learning_rate": 5e-05,
      "loss": 10.3538,
      "step": 55
    },
    {
      "epoch": 0.0024561942147854118,
      "grad_norm": 0.1959301084280014,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.3498,
      "step": 56
    },
    {
      "epoch": 0.002500054825763723,
      "grad_norm": 0.21363425254821777,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.363,
      "step": 57
    },
    {
      "epoch": 0.002543915436742034,
      "grad_norm": 0.12494485080242157,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.3565,
      "step": 58
    },
    {
      "epoch": 0.0025877760477203446,
      "grad_norm": 0.19558563828468323,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.3621,
      "step": 59
    },
    {
      "epoch": 0.0026316366586986556,
      "grad_norm": 0.185495525598526,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.3486,
      "step": 60
    },
    {
      "epoch": 0.0026754972696769667,
      "grad_norm": 0.21020500361919403,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.3453,
      "step": 61
    },
    {
      "epoch": 0.0027193578806552774,
      "grad_norm": 0.2363358736038208,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.3425,
      "step": 62
    },
    {
      "epoch": 0.0027632184916335885,
      "grad_norm": 0.270352303981781,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.3452,
      "step": 63
    },
    {
      "epoch": 0.0027632184916335885,
      "eval_loss": 10.349072456359863,
      "eval_runtime": 286.3258,
      "eval_samples_per_second": 67.056,
      "eval_steps_per_second": 8.382,
      "step": 63
    },
    {
      "epoch": 0.0028070791026118995,
      "grad_norm": 0.21777836978435516,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.3522,
      "step": 64
    },
    {
      "epoch": 0.00285093971359021,
      "grad_norm": 0.29503583908081055,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.3568,
      "step": 65
    },
    {
      "epoch": 0.0028948003245685213,
      "grad_norm": 0.29024678468704224,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.3352,
      "step": 66
    },
    {
      "epoch": 0.0029386609355468323,
      "grad_norm": 0.22545352578163147,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.3506,
      "step": 67
    },
    {
      "epoch": 0.002982521546525143,
      "grad_norm": 0.23708412051200867,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.3354,
      "step": 68
    },
    {
      "epoch": 0.003026382157503454,
      "grad_norm": 0.22012007236480713,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.3486,
      "step": 69
    },
    {
      "epoch": 0.003070242768481765,
      "grad_norm": 0.21860839426517487,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3508,
      "step": 70
    },
    {
      "epoch": 0.003114103379460076,
      "grad_norm": 0.2507653534412384,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.3356,
      "step": 71
    },
    {
      "epoch": 0.003157963990438387,
      "grad_norm": 0.26605838537216187,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.3328,
      "step": 72
    },
    {
      "epoch": 0.003157963990438387,
      "eval_loss": 10.346505165100098,
      "eval_runtime": 286.401,
      "eval_samples_per_second": 67.039,
      "eval_steps_per_second": 8.38,
      "step": 72
    },
    {
      "epoch": 0.003201824601416698,
      "grad_norm": 0.19735638797283173,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3472,
      "step": 73
    },
    {
      "epoch": 0.0032456852123950086,
      "grad_norm": 0.24469499289989471,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.3426,
      "step": 74
    },
    {
      "epoch": 0.0032895458233733197,
      "grad_norm": 0.22693535685539246,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.3425,
      "step": 75
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7139283959808.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}