{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.023312740412635504,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00031083653883514007,
      "grad_norm": 0.09337017685174942,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 10.3634,
      "step": 1
    },
    {
      "epoch": 0.00031083653883514007,
      "eval_loss": 10.3756103515625,
      "eval_runtime": 10.9804,
      "eval_samples_per_second": 986.945,
      "eval_steps_per_second": 123.402,
      "step": 1
    },
    {
      "epoch": 0.0006216730776702801,
      "grad_norm": 0.08634893596172333,
      "learning_rate": 6.666666666666667e-05,
      "loss": 10.3728,
      "step": 2
    },
    {
      "epoch": 0.0009325096165054202,
      "grad_norm": 0.08781135827302933,
      "learning_rate": 0.0001,
      "loss": 10.3825,
      "step": 3
    },
    {
      "epoch": 0.0012433461553405603,
      "grad_norm": 0.09550037980079651,
      "learning_rate": 9.99524110790929e-05,
      "loss": 10.3786,
      "step": 4
    },
    {
      "epoch": 0.0015541826941757003,
      "grad_norm": 0.08240266889333725,
      "learning_rate": 9.980973490458728e-05,
      "loss": 10.3761,
      "step": 5
    },
    {
      "epoch": 0.0018650192330108403,
      "grad_norm": 0.09675638377666473,
      "learning_rate": 9.957224306869053e-05,
      "loss": 10.3742,
      "step": 6
    },
    {
      "epoch": 0.0021758557718459803,
      "grad_norm": 0.1124580129981041,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.3711,
      "step": 7
    },
    {
      "epoch": 0.0024866923106811206,
      "grad_norm": 0.1099642738699913,
      "learning_rate": 9.881480035599667e-05,
      "loss": 10.3753,
      "step": 8
    },
    {
      "epoch": 0.002797528849516261,
      "grad_norm": 0.12019800394773483,
      "learning_rate": 9.829629131445342e-05,
      "loss": 10.3676,
      "step": 9
    },
    {
      "epoch": 0.0031083653883514006,
      "grad_norm": 0.11259865760803223,
      "learning_rate": 9.768584753741134e-05,
      "loss": 10.3687,
      "step": 10
    },
    {
      "epoch": 0.003419201927186541,
      "grad_norm": 0.15891334414482117,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.3742,
      "step": 11
    },
    {
      "epoch": 0.0037300384660216806,
      "grad_norm": 0.14277303218841553,
      "learning_rate": 9.619397662556435e-05,
      "loss": 10.3754,
      "step": 12
    },
    {
      "epoch": 0.004040875004856821,
      "grad_norm": 0.12471364438533783,
      "learning_rate": 9.53153893518325e-05,
      "loss": 10.3675,
      "step": 13
    },
    {
      "epoch": 0.004351711543691961,
      "grad_norm": 0.1129114106297493,
      "learning_rate": 9.435054165891109e-05,
      "loss": 10.3758,
      "step": 14
    },
    {
      "epoch": 0.004662548082527101,
      "grad_norm": 0.10442539304494858,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3658,
      "step": 15
    },
    {
      "epoch": 0.004973384621362241,
      "grad_norm": 0.11816086620092392,
      "learning_rate": 9.21695722906443e-05,
      "loss": 10.3709,
      "step": 16
    },
    {
      "epoch": 0.005284221160197381,
      "grad_norm": 0.13966858386993408,
      "learning_rate": 9.09576022144496e-05,
      "loss": 10.3704,
      "step": 17
    },
    {
      "epoch": 0.005595057699032522,
      "grad_norm": 0.1264178454875946,
      "learning_rate": 8.966766701456177e-05,
      "loss": 10.3791,
      "step": 18
    },
    {
      "epoch": 0.005905894237867661,
      "grad_norm": 0.14117202162742615,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3764,
      "step": 19
    },
    {
      "epoch": 0.006216730776702801,
      "grad_norm": 0.13153833150863647,
      "learning_rate": 8.68638668405062e-05,
      "loss": 10.3678,
      "step": 20
    },
    {
      "epoch": 0.006527567315537942,
      "grad_norm": 0.15006625652313232,
      "learning_rate": 8.535533905932738e-05,
      "loss": 10.3714,
      "step": 21
    },
    {
      "epoch": 0.006838403854373082,
      "grad_norm": 0.2025146335363388,
      "learning_rate": 8.377951038078302e-05,
      "loss": 10.3657,
      "step": 22
    },
    {
      "epoch": 0.0071492403932082215,
      "grad_norm": 0.23157408833503723,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.3775,
      "step": 23
    },
    {
      "epoch": 0.007460076932043361,
      "grad_norm": 0.2149832844734192,
      "learning_rate": 8.043807145043604e-05,
      "loss": 10.3698,
      "step": 24
    },
    {
      "epoch": 0.007770913470878502,
      "grad_norm": 0.28313252329826355,
      "learning_rate": 7.86788218175523e-05,
      "loss": 10.3724,
      "step": 25
    },
    {
      "epoch": 0.007770913470878502,
      "eval_loss": 10.366267204284668,
      "eval_runtime": 10.9778,
      "eval_samples_per_second": 987.178,
      "eval_steps_per_second": 123.431,
      "step": 25
    },
    {
      "epoch": 0.008081750009713642,
      "grad_norm": 0.12113793939352036,
      "learning_rate": 7.68649804173412e-05,
      "loss": 10.3664,
      "step": 26
    },
    {
      "epoch": 0.008392586548548782,
      "grad_norm": 0.1222296953201294,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.358,
      "step": 27
    },
    {
      "epoch": 0.008703423087383921,
      "grad_norm": 0.1611909419298172,
      "learning_rate": 7.308743066175172e-05,
      "loss": 10.3606,
      "step": 28
    },
    {
      "epoch": 0.009014259626219063,
      "grad_norm": 0.16634967923164368,
      "learning_rate": 7.113091308703498e-05,
      "loss": 10.375,
      "step": 29
    },
    {
      "epoch": 0.009325096165054203,
      "grad_norm": 0.20806021988391876,
      "learning_rate": 6.91341716182545e-05,
      "loss": 10.3651,
      "step": 30
    },
    {
      "epoch": 0.009635932703889342,
      "grad_norm": 0.18134745955467224,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.3622,
      "step": 31
    },
    {
      "epoch": 0.009946769242724482,
      "grad_norm": 0.23395313322544098,
      "learning_rate": 6.503528997521366e-05,
      "loss": 10.3641,
      "step": 32
    },
    {
      "epoch": 0.010257605781559622,
      "grad_norm": 0.24909980595111847,
      "learning_rate": 6.294095225512603e-05,
      "loss": 10.3626,
      "step": 33
    },
    {
      "epoch": 0.010568442320394762,
      "grad_norm": 0.2704538106918335,
      "learning_rate": 6.0821980696905146e-05,
      "loss": 10.3612,
      "step": 34
    },
    {
      "epoch": 0.010879278859229902,
      "grad_norm": 0.30182722210884094,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.3618,
      "step": 35
    },
    {
      "epoch": 0.011190115398065043,
      "grad_norm": 0.30596181750297546,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 10.3671,
      "step": 36
    },
    {
      "epoch": 0.011500951936900183,
      "grad_norm": 0.3400585651397705,
      "learning_rate": 5.435778713738292e-05,
      "loss": 10.3525,
      "step": 37
    },
    {
      "epoch": 0.011811788475735323,
      "grad_norm": 0.25906017422676086,
      "learning_rate": 5.218096936826681e-05,
      "loss": 10.3615,
      "step": 38
    },
    {
      "epoch": 0.012122625014570463,
      "grad_norm": 0.16712762415409088,
      "learning_rate": 5e-05,
      "loss": 10.3603,
      "step": 39
    },
    {
      "epoch": 0.012433461553405602,
      "grad_norm": 0.18277670443058014,
      "learning_rate": 4.781903063173321e-05,
      "loss": 10.3596,
      "step": 40
    },
    {
      "epoch": 0.012744298092240742,
      "grad_norm": 0.21423067152500153,
      "learning_rate": 4.564221286261709e-05,
      "loss": 10.3575,
      "step": 41
    },
    {
      "epoch": 0.013055134631075884,
      "grad_norm": 0.2574392855167389,
      "learning_rate": 4.347369038899744e-05,
      "loss": 10.3572,
      "step": 42
    },
    {
      "epoch": 0.013365971169911024,
      "grad_norm": 0.29102233052253723,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.354,
      "step": 43
    },
    {
      "epoch": 0.013676807708746163,
      "grad_norm": 0.30868732929229736,
      "learning_rate": 3.917801930309486e-05,
      "loss": 10.3597,
      "step": 44
    },
    {
      "epoch": 0.013987644247581303,
      "grad_norm": 0.26494768261909485,
      "learning_rate": 3.705904774487396e-05,
      "loss": 10.3587,
      "step": 45
    },
    {
      "epoch": 0.014298480786416443,
      "grad_norm": 0.31784704327583313,
      "learning_rate": 3.4964710024786354e-05,
      "loss": 10.3514,
      "step": 46
    },
    {
      "epoch": 0.014609317325251583,
      "grad_norm": 0.31726884841918945,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.3488,
      "step": 47
    },
    {
      "epoch": 0.014920153864086723,
      "grad_norm": 0.3178487718105316,
      "learning_rate": 3.086582838174551e-05,
      "loss": 10.3527,
      "step": 48
    },
    {
      "epoch": 0.015230990402921864,
      "grad_norm": 0.42220181226730347,
      "learning_rate": 2.886908691296504e-05,
      "loss": 10.3521,
      "step": 49
    },
    {
      "epoch": 0.015541826941757004,
      "grad_norm": 0.511695146560669,
      "learning_rate": 2.6912569338248315e-05,
      "loss": 10.3413,
      "step": 50
    },
    {
      "epoch": 0.015541826941757004,
      "eval_loss": 10.35302734375,
      "eval_runtime": 10.9637,
      "eval_samples_per_second": 988.445,
      "eval_steps_per_second": 123.59,
      "step": 50
    },
    {
      "epoch": 0.015852663480592142,
      "grad_norm": 0.20533247292041779,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.361,
      "step": 51
    },
    {
      "epoch": 0.016163500019427283,
      "grad_norm": 0.22223378717899323,
      "learning_rate": 2.3135019582658802e-05,
      "loss": 10.3604,
      "step": 52
    },
    {
      "epoch": 0.016474336558262425,
      "grad_norm": 0.25299137830734253,
      "learning_rate": 2.132117818244771e-05,
      "loss": 10.3546,
      "step": 53
    },
    {
      "epoch": 0.016785173097097563,
      "grad_norm": 0.25883322954177856,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 10.3565,
      "step": 54
    },
    {
      "epoch": 0.017096009635932705,
      "grad_norm": 0.2713988721370697,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.3646,
      "step": 55
    },
    {
      "epoch": 0.017406846174767843,
      "grad_norm": 0.2855599522590637,
      "learning_rate": 1.622048961921699e-05,
      "loss": 10.3554,
      "step": 56
    },
    {
      "epoch": 0.017717682713602984,
      "grad_norm": 0.36550766229629517,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 10.3505,
      "step": 57
    },
    {
      "epoch": 0.018028519252438126,
      "grad_norm": 0.36669376492500305,
      "learning_rate": 1.3136133159493802e-05,
      "loss": 10.355,
      "step": 58
    },
    {
      "epoch": 0.018339355791273264,
      "grad_norm": 0.37321269512176514,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.3451,
      "step": 59
    },
    {
      "epoch": 0.018650192330108405,
      "grad_norm": 0.403087854385376,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 10.346,
      "step": 60
    },
    {
      "epoch": 0.018961028868943543,
      "grad_norm": 0.40181103348731995,
      "learning_rate": 9.042397785550405e-06,
      "loss": 10.3489,
      "step": 61
    },
    {
      "epoch": 0.019271865407778685,
      "grad_norm": 0.4040270745754242,
      "learning_rate": 7.830427709355725e-06,
      "loss": 10.3459,
      "step": 62
    },
    {
      "epoch": 0.019582701946613823,
      "grad_norm": 0.2971201241016388,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.3569,
      "step": 63
    },
    {
      "epoch": 0.019893538485448965,
      "grad_norm": 0.22685183584690094,
      "learning_rate": 5.649458341088915e-06,
      "loss": 10.3634,
      "step": 64
    },
    {
      "epoch": 0.020204375024284106,
      "grad_norm": 0.26825642585754395,
      "learning_rate": 4.684610648167503e-06,
      "loss": 10.3588,
      "step": 65
    },
    {
      "epoch": 0.020515211563119244,
      "grad_norm": 0.27809709310531616,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 10.3507,
      "step": 66
    },
    {
      "epoch": 0.020826048101954386,
      "grad_norm": 0.28404590487480164,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.3547,
      "step": 67
    },
    {
      "epoch": 0.021136884640789524,
      "grad_norm": 0.39761507511138916,
      "learning_rate": 2.314152462588659e-06,
      "loss": 10.3481,
      "step": 68
    },
    {
      "epoch": 0.021447721179624665,
      "grad_norm": 0.33398163318634033,
      "learning_rate": 1.70370868554659e-06,
      "loss": 10.3483,
      "step": 69
    },
    {
      "epoch": 0.021758557718459803,
      "grad_norm": 0.3218649625778198,
      "learning_rate": 1.1851996440033319e-06,
      "loss": 10.351,
      "step": 70
    },
    {
      "epoch": 0.022069394257294945,
      "grad_norm": 0.4155634939670563,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.3492,
      "step": 71
    },
    {
      "epoch": 0.022380230796130086,
      "grad_norm": 0.4435564875602722,
      "learning_rate": 4.277569313094809e-07,
      "loss": 10.3507,
      "step": 72
    },
    {
      "epoch": 0.022691067334965224,
      "grad_norm": 0.3702129125595093,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 10.3489,
      "step": 73
    },
    {
      "epoch": 0.023001903873800366,
      "grad_norm": 0.4705186188220978,
      "learning_rate": 4.7588920907110094e-08,
      "loss": 10.3482,
      "step": 74
    },
    {
      "epoch": 0.023312740412635504,
      "grad_norm": 0.5552557110786438,
      "learning_rate": 0.0,
      "loss": 10.3259,
      "step": 75
    },
    {
      "epoch": 0.023312740412635504,
      "eval_loss": 10.34955883026123,
      "eval_runtime": 10.958,
      "eval_samples_per_second": 988.961,
      "eval_steps_per_second": 123.654,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "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": 32076044697600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}