{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00453953938807009,
  "eval_steps": 9,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.052719184093454e-05,
      "grad_norm": 0.13207685947418213,
      "learning_rate": 1e-05,
      "loss": 11.7594,
      "step": 1
    },
    {
      "epoch": 6.052719184093454e-05,
      "eval_loss": 11.75540542602539,
      "eval_runtime": 336.684,
      "eval_samples_per_second": 41.324,
      "eval_steps_per_second": 5.168,
      "step": 1
    },
    {
      "epoch": 0.00012105438368186908,
      "grad_norm": 0.11833270639181137,
      "learning_rate": 2e-05,
      "loss": 11.7469,
      "step": 2
    },
    {
      "epoch": 0.00018158157552280362,
      "grad_norm": 0.10774674266576767,
      "learning_rate": 3e-05,
      "loss": 11.7576,
      "step": 3
    },
    {
      "epoch": 0.00024210876736373817,
      "grad_norm": 0.13722410798072815,
      "learning_rate": 4e-05,
      "loss": 11.7599,
      "step": 4
    },
    {
      "epoch": 0.0003026359592046727,
      "grad_norm": 0.09991803765296936,
      "learning_rate": 5e-05,
      "loss": 11.7486,
      "step": 5
    },
    {
      "epoch": 0.00036316315104560723,
      "grad_norm": 0.10965510457754135,
      "learning_rate": 6e-05,
      "loss": 11.7538,
      "step": 6
    },
    {
      "epoch": 0.00042369034288654176,
      "grad_norm": 0.10765465348958969,
      "learning_rate": 7e-05,
      "loss": 11.7692,
      "step": 7
    },
    {
      "epoch": 0.00048421753472747633,
      "grad_norm": 0.11706217378377914,
      "learning_rate": 8e-05,
      "loss": 11.7464,
      "step": 8
    },
    {
      "epoch": 0.0005447447265684109,
      "grad_norm": 0.1186530739068985,
      "learning_rate": 9e-05,
      "loss": 11.7557,
      "step": 9
    },
    {
      "epoch": 0.0005447447265684109,
      "eval_loss": 11.75403881072998,
      "eval_runtime": 336.8051,
      "eval_samples_per_second": 41.309,
      "eval_steps_per_second": 5.166,
      "step": 9
    },
    {
      "epoch": 0.0006052719184093454,
      "grad_norm": 0.12054545432329178,
      "learning_rate": 0.0001,
      "loss": 11.7687,
      "step": 10
    },
    {
      "epoch": 0.00066579911025028,
      "grad_norm": 0.1153390109539032,
      "learning_rate": 9.99695413509548e-05,
      "loss": 11.7483,
      "step": 11
    },
    {
      "epoch": 0.0007263263020912145,
      "grad_norm": 0.10140057653188705,
      "learning_rate": 9.987820251299122e-05,
      "loss": 11.7596,
      "step": 12
    },
    {
      "epoch": 0.000786853493932149,
      "grad_norm": 0.11120553314685822,
      "learning_rate": 9.972609476841367e-05,
      "loss": 11.7471,
      "step": 13
    },
    {
      "epoch": 0.0008473806857730835,
      "grad_norm": 0.15375909209251404,
      "learning_rate": 9.951340343707852e-05,
      "loss": 11.758,
      "step": 14
    },
    {
      "epoch": 0.0009079078776140181,
      "grad_norm": 0.1310228556394577,
      "learning_rate": 9.924038765061042e-05,
      "loss": 11.7618,
      "step": 15
    },
    {
      "epoch": 0.0009684350694549527,
      "grad_norm": 0.10679139196872711,
      "learning_rate": 9.890738003669029e-05,
      "loss": 11.7509,
      "step": 16
    },
    {
      "epoch": 0.001028962261295887,
      "grad_norm": 0.14143402874469757,
      "learning_rate": 9.851478631379982e-05,
      "loss": 11.7501,
      "step": 17
    },
    {
      "epoch": 0.0010894894531368218,
      "grad_norm": 0.13829779624938965,
      "learning_rate": 9.806308479691595e-05,
      "loss": 11.7651,
      "step": 18
    },
    {
      "epoch": 0.0010894894531368218,
      "eval_loss": 11.7505521774292,
      "eval_runtime": 336.7853,
      "eval_samples_per_second": 41.311,
      "eval_steps_per_second": 5.166,
      "step": 18
    },
    {
      "epoch": 0.0011500166449777563,
      "grad_norm": 0.11990591883659363,
      "learning_rate": 9.755282581475769e-05,
      "loss": 11.7548,
      "step": 19
    },
    {
      "epoch": 0.0012105438368186909,
      "grad_norm": 0.11656098812818527,
      "learning_rate": 9.698463103929542e-05,
      "loss": 11.7514,
      "step": 20
    },
    {
      "epoch": 0.0012710710286596254,
      "grad_norm": 0.1342959702014923,
      "learning_rate": 9.635919272833938e-05,
      "loss": 11.7626,
      "step": 21
    },
    {
      "epoch": 0.00133159822050056,
      "grad_norm": 0.16343383491039276,
      "learning_rate": 9.567727288213005e-05,
      "loss": 11.7487,
      "step": 22
    },
    {
      "epoch": 0.0013921254123414944,
      "grad_norm": 0.12727664411067963,
      "learning_rate": 9.493970231495835e-05,
      "loss": 11.7447,
      "step": 23
    },
    {
      "epoch": 0.001452652604182429,
      "grad_norm": 0.1371912658214569,
      "learning_rate": 9.414737964294636e-05,
      "loss": 11.7325,
      "step": 24
    },
    {
      "epoch": 0.0015131797960233635,
      "grad_norm": 0.1473395824432373,
      "learning_rate": 9.330127018922194e-05,
      "loss": 11.754,
      "step": 25
    },
    {
      "epoch": 0.001573706987864298,
      "grad_norm": 0.10818126052618027,
      "learning_rate": 9.24024048078213e-05,
      "loss": 11.7497,
      "step": 26
    },
    {
      "epoch": 0.0016342341797052325,
      "grad_norm": 0.11172839999198914,
      "learning_rate": 9.145187862775209e-05,
      "loss": 11.7515,
      "step": 27
    },
    {
      "epoch": 0.0016342341797052325,
      "eval_loss": 11.746716499328613,
      "eval_runtime": 336.6687,
      "eval_samples_per_second": 41.325,
      "eval_steps_per_second": 5.168,
      "step": 27
    },
    {
      "epoch": 0.001694761371546167,
      "grad_norm": 0.13919688761234283,
      "learning_rate": 9.045084971874738e-05,
      "loss": 11.7464,
      "step": 28
    },
    {
      "epoch": 0.0017552885633871018,
      "grad_norm": 0.15092803537845612,
      "learning_rate": 8.940053768033609e-05,
      "loss": 11.7521,
      "step": 29
    },
    {
      "epoch": 0.0018158157552280363,
      "grad_norm": 0.11896580457687378,
      "learning_rate": 8.83022221559489e-05,
      "loss": 11.7569,
      "step": 30
    },
    {
      "epoch": 0.0018763429470689708,
      "grad_norm": 0.15489861369132996,
      "learning_rate": 8.715724127386972e-05,
      "loss": 11.7423,
      "step": 31
    },
    {
      "epoch": 0.0019368701389099053,
      "grad_norm": 0.12833209335803986,
      "learning_rate": 8.596699001693255e-05,
      "loss": 11.7435,
      "step": 32
    },
    {
      "epoch": 0.0019973973307508396,
      "grad_norm": 0.17080430686473846,
      "learning_rate": 8.473291852294987e-05,
      "loss": 11.741,
      "step": 33
    },
    {
      "epoch": 0.002057924522591774,
      "grad_norm": 0.13555097579956055,
      "learning_rate": 8.345653031794292e-05,
      "loss": 11.7462,
      "step": 34
    },
    {
      "epoch": 0.002118451714432709,
      "grad_norm": 0.16032513976097107,
      "learning_rate": 8.213938048432697e-05,
      "loss": 11.7443,
      "step": 35
    },
    {
      "epoch": 0.0021789789062736436,
      "grad_norm": 0.14690877497196198,
      "learning_rate": 8.07830737662829e-05,
      "loss": 11.7408,
      "step": 36
    },
    {
      "epoch": 0.0021789789062736436,
      "eval_loss": 11.74258804321289,
      "eval_runtime": 336.8294,
      "eval_samples_per_second": 41.306,
      "eval_steps_per_second": 5.166,
      "step": 36
    },
    {
      "epoch": 0.002239506098114578,
      "grad_norm": 0.1442859023809433,
      "learning_rate": 7.938926261462366e-05,
      "loss": 11.7285,
      "step": 37
    },
    {
      "epoch": 0.0023000332899555127,
      "grad_norm": 0.13616201281547546,
      "learning_rate": 7.795964517353735e-05,
      "loss": 11.7437,
      "step": 38
    },
    {
      "epoch": 0.002360560481796447,
      "grad_norm": 0.14922216534614563,
      "learning_rate": 7.649596321166024e-05,
      "loss": 11.7439,
      "step": 39
    },
    {
      "epoch": 0.0024210876736373817,
      "grad_norm": 0.1569993942975998,
      "learning_rate": 7.500000000000001e-05,
      "loss": 11.7464,
      "step": 40
    },
    {
      "epoch": 0.0024816148654783162,
      "grad_norm": 0.17072947323322296,
      "learning_rate": 7.347357813929454e-05,
      "loss": 11.7408,
      "step": 41
    },
    {
      "epoch": 0.0025421420573192507,
      "grad_norm": 0.15454956889152527,
      "learning_rate": 7.191855733945387e-05,
      "loss": 11.7503,
      "step": 42
    },
    {
      "epoch": 0.0026026692491601853,
      "grad_norm": 0.1716042160987854,
      "learning_rate": 7.033683215379002e-05,
      "loss": 11.7476,
      "step": 43
    },
    {
      "epoch": 0.00266319644100112,
      "grad_norm": 0.14393147826194763,
      "learning_rate": 6.873032967079561e-05,
      "loss": 11.7505,
      "step": 44
    },
    {
      "epoch": 0.0027237236328420543,
      "grad_norm": 0.17059223353862762,
      "learning_rate": 6.710100716628344e-05,
      "loss": 11.7454,
      "step": 45
    },
    {
      "epoch": 0.0027237236328420543,
      "eval_loss": 11.738289833068848,
      "eval_runtime": 336.5624,
      "eval_samples_per_second": 41.339,
      "eval_steps_per_second": 5.17,
      "step": 45
    },
    {
      "epoch": 0.002784250824682989,
      "grad_norm": 0.18637433648109436,
      "learning_rate": 6.545084971874738e-05,
      "loss": 11.7379,
      "step": 46
    },
    {
      "epoch": 0.0028447780165239234,
      "grad_norm": 0.13882829248905182,
      "learning_rate": 6.378186779084995e-05,
      "loss": 11.7332,
      "step": 47
    },
    {
      "epoch": 0.002905305208364858,
      "grad_norm": 0.18253403902053833,
      "learning_rate": 6.209609477998338e-05,
      "loss": 11.7234,
      "step": 48
    },
    {
      "epoch": 0.0029658324002057924,
      "grad_norm": 0.1677316427230835,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 11.7309,
      "step": 49
    },
    {
      "epoch": 0.003026359592046727,
      "grad_norm": 0.18898844718933105,
      "learning_rate": 5.868240888334653e-05,
      "loss": 11.7309,
      "step": 50
    },
    {
      "epoch": 0.0030868867838876614,
      "grad_norm": 0.17324720323085785,
      "learning_rate": 5.695865504800327e-05,
      "loss": 11.7242,
      "step": 51
    },
    {
      "epoch": 0.003147413975728596,
      "grad_norm": 0.17566855251789093,
      "learning_rate": 5.522642316338268e-05,
      "loss": 11.7339,
      "step": 52
    },
    {
      "epoch": 0.0032079411675695305,
      "grad_norm": 0.15504898130893707,
      "learning_rate": 5.348782368720626e-05,
      "loss": 11.7377,
      "step": 53
    },
    {
      "epoch": 0.003268468359410465,
      "grad_norm": 0.21223460137844086,
      "learning_rate": 5.174497483512506e-05,
      "loss": 11.731,
      "step": 54
    },
    {
      "epoch": 0.003268468359410465,
      "eval_loss": 11.734041213989258,
      "eval_runtime": 336.8451,
      "eval_samples_per_second": 41.304,
      "eval_steps_per_second": 5.166,
      "step": 54
    },
    {
      "epoch": 0.0033289955512513995,
      "grad_norm": 0.17628130316734314,
      "learning_rate": 5e-05,
      "loss": 11.7371,
      "step": 55
    },
    {
      "epoch": 0.003389522743092334,
      "grad_norm": 0.1927989423274994,
      "learning_rate": 4.825502516487497e-05,
      "loss": 11.7333,
      "step": 56
    },
    {
      "epoch": 0.0034500499349332686,
      "grad_norm": 0.22302095592021942,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 11.7331,
      "step": 57
    },
    {
      "epoch": 0.0035105771267742035,
      "grad_norm": 0.20894654095172882,
      "learning_rate": 4.477357683661734e-05,
      "loss": 11.733,
      "step": 58
    },
    {
      "epoch": 0.003571104318615138,
      "grad_norm": 0.14698632061481476,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 11.7369,
      "step": 59
    },
    {
      "epoch": 0.0036316315104560726,
      "grad_norm": 0.2037297785282135,
      "learning_rate": 4.131759111665349e-05,
      "loss": 11.7279,
      "step": 60
    },
    {
      "epoch": 0.003692158702297007,
      "grad_norm": 0.21877123415470123,
      "learning_rate": 3.960441545911204e-05,
      "loss": 11.7148,
      "step": 61
    },
    {
      "epoch": 0.0037526858941379416,
      "grad_norm": 0.20271418988704681,
      "learning_rate": 3.790390522001662e-05,
      "loss": 11.7348,
      "step": 62
    },
    {
      "epoch": 0.003813213085978876,
      "grad_norm": 0.17619234323501587,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 11.729,
      "step": 63
    },
    {
      "epoch": 0.003813213085978876,
      "eval_loss": 11.730371475219727,
      "eval_runtime": 336.6702,
      "eval_samples_per_second": 41.325,
      "eval_steps_per_second": 5.168,
      "step": 63
    },
    {
      "epoch": 0.0038737402778198106,
      "grad_norm": 0.2054615467786789,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 11.719,
      "step": 64
    },
    {
      "epoch": 0.003934267469660745,
      "grad_norm": 0.22925786674022675,
      "learning_rate": 3.289899283371657e-05,
      "loss": 11.7188,
      "step": 65
    },
    {
      "epoch": 0.003994794661501679,
      "grad_norm": 0.2713838219642639,
      "learning_rate": 3.12696703292044e-05,
      "loss": 11.7308,
      "step": 66
    },
    {
      "epoch": 0.004055321853342614,
      "grad_norm": 0.19096967577934265,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 11.7403,
      "step": 67
    },
    {
      "epoch": 0.004115849045183548,
      "grad_norm": 0.20774328708648682,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 11.7415,
      "step": 68
    },
    {
      "epoch": 0.004176376237024483,
      "grad_norm": 0.19622094929218292,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 11.7333,
      "step": 69
    },
    {
      "epoch": 0.004236903428865418,
      "grad_norm": 0.17385007441043854,
      "learning_rate": 2.500000000000001e-05,
      "loss": 11.739,
      "step": 70
    },
    {
      "epoch": 0.004297430620706352,
      "grad_norm": 0.24730053544044495,
      "learning_rate": 2.350403678833976e-05,
      "loss": 11.7334,
      "step": 71
    },
    {
      "epoch": 0.004357957812547287,
      "grad_norm": 0.21336118876934052,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 11.7287,
      "step": 72
    },
    {
      "epoch": 0.004357957812547287,
      "eval_loss": 11.72767162322998,
      "eval_runtime": 336.8377,
      "eval_samples_per_second": 41.305,
      "eval_steps_per_second": 5.166,
      "step": 72
    },
    {
      "epoch": 0.004418485004388221,
      "grad_norm": 0.22774222493171692,
      "learning_rate": 2.061073738537635e-05,
      "loss": 11.7243,
      "step": 73
    },
    {
      "epoch": 0.004479012196229156,
      "grad_norm": 0.15189680457115173,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 11.7261,
      "step": 74
    },
    {
      "epoch": 0.00453953938807009,
      "grad_norm": 0.19341489672660828,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 11.7306,
      "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": 15277503283200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}