{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0184314809694959,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000184314809694959,
      "grad_norm": 0.8788601756095886,
      "learning_rate": 1e-05,
      "loss": 15.6282,
      "step": 1
    },
    {
      "epoch": 0.000184314809694959,
      "eval_loss": 1.1763184070587158,
      "eval_runtime": 666.3911,
      "eval_samples_per_second": 13.713,
      "eval_steps_per_second": 6.856,
      "step": 1
    },
    {
      "epoch": 0.000368629619389918,
      "grad_norm": 0.9271673560142517,
      "learning_rate": 2e-05,
      "loss": 18.2169,
      "step": 2
    },
    {
      "epoch": 0.000552944429084877,
      "grad_norm": 1.0230611562728882,
      "learning_rate": 3e-05,
      "loss": 19.1548,
      "step": 3
    },
    {
      "epoch": 0.000737259238779836,
      "grad_norm": 1.2503995895385742,
      "learning_rate": 4e-05,
      "loss": 19.7396,
      "step": 4
    },
    {
      "epoch": 0.0009215740484747949,
      "grad_norm": 1.0606725215911865,
      "learning_rate": 5e-05,
      "loss": 18.0634,
      "step": 5
    },
    {
      "epoch": 0.001105888858169754,
      "grad_norm": 1.2605953216552734,
      "learning_rate": 6e-05,
      "loss": 18.8287,
      "step": 6
    },
    {
      "epoch": 0.001290203667864713,
      "grad_norm": 1.2701598405838013,
      "learning_rate": 7e-05,
      "loss": 19.9074,
      "step": 7
    },
    {
      "epoch": 0.001474518477559672,
      "grad_norm": 1.9293956756591797,
      "learning_rate": 8e-05,
      "loss": 19.0916,
      "step": 8
    },
    {
      "epoch": 0.0016588332872546309,
      "grad_norm": 1.6402465105056763,
      "learning_rate": 9e-05,
      "loss": 19.5295,
      "step": 9
    },
    {
      "epoch": 0.0018431480969495898,
      "grad_norm": 1.5588271617889404,
      "learning_rate": 0.0001,
      "loss": 17.3427,
      "step": 10
    },
    {
      "epoch": 0.0020274629066445488,
      "grad_norm": 2.605191230773926,
      "learning_rate": 9.99695413509548e-05,
      "loss": 19.5935,
      "step": 11
    },
    {
      "epoch": 0.002211777716339508,
      "grad_norm": 2.8112478256225586,
      "learning_rate": 9.987820251299122e-05,
      "loss": 19.056,
      "step": 12
    },
    {
      "epoch": 0.0023960925260344667,
      "grad_norm": 2.4318063259124756,
      "learning_rate": 9.972609476841367e-05,
      "loss": 16.4965,
      "step": 13
    },
    {
      "epoch": 0.002580407335729426,
      "grad_norm": 2.231241464614868,
      "learning_rate": 9.951340343707852e-05,
      "loss": 16.1551,
      "step": 14
    },
    {
      "epoch": 0.002764722145424385,
      "grad_norm": 2.131531238555908,
      "learning_rate": 9.924038765061042e-05,
      "loss": 15.1915,
      "step": 15
    },
    {
      "epoch": 0.002949036955119344,
      "grad_norm": 2.4537222385406494,
      "learning_rate": 9.890738003669029e-05,
      "loss": 16.6483,
      "step": 16
    },
    {
      "epoch": 0.003133351764814303,
      "grad_norm": 2.561370849609375,
      "learning_rate": 9.851478631379982e-05,
      "loss": 18.017,
      "step": 17
    },
    {
      "epoch": 0.0033176665745092617,
      "grad_norm": 2.1956608295440674,
      "learning_rate": 9.806308479691595e-05,
      "loss": 16.0174,
      "step": 18
    },
    {
      "epoch": 0.003501981384204221,
      "grad_norm": 2.512251853942871,
      "learning_rate": 9.755282581475769e-05,
      "loss": 17.9428,
      "step": 19
    },
    {
      "epoch": 0.0036862961938991796,
      "grad_norm": 2.9903564453125,
      "learning_rate": 9.698463103929542e-05,
      "loss": 17.3539,
      "step": 20
    },
    {
      "epoch": 0.003870611003594139,
      "grad_norm": 3.720118284225464,
      "learning_rate": 9.635919272833938e-05,
      "loss": 16.1073,
      "step": 21
    },
    {
      "epoch": 0.0040549258132890975,
      "grad_norm": 2.6069421768188477,
      "learning_rate": 9.567727288213005e-05,
      "loss": 17.1097,
      "step": 22
    },
    {
      "epoch": 0.004239240622984057,
      "grad_norm": 3.625659465789795,
      "learning_rate": 9.493970231495835e-05,
      "loss": 16.492,
      "step": 23
    },
    {
      "epoch": 0.004423555432679016,
      "grad_norm": 3.269760847091675,
      "learning_rate": 9.414737964294636e-05,
      "loss": 17.1478,
      "step": 24
    },
    {
      "epoch": 0.004607870242373975,
      "grad_norm": 3.4485795497894287,
      "learning_rate": 9.330127018922194e-05,
      "loss": 15.6912,
      "step": 25
    },
    {
      "epoch": 0.004607870242373975,
      "eval_loss": 0.9960303902626038,
      "eval_runtime": 1404.223,
      "eval_samples_per_second": 6.508,
      "eval_steps_per_second": 3.254,
      "step": 25
    },
    {
      "epoch": 0.004792185052068933,
      "grad_norm": 2.7202582359313965,
      "learning_rate": 9.24024048078213e-05,
      "loss": 13.5389,
      "step": 26
    },
    {
      "epoch": 0.0049764998617638926,
      "grad_norm": 2.6659634113311768,
      "learning_rate": 9.145187862775209e-05,
      "loss": 14.5577,
      "step": 27
    },
    {
      "epoch": 0.005160814671458852,
      "grad_norm": 4.281832695007324,
      "learning_rate": 9.045084971874738e-05,
      "loss": 17.1426,
      "step": 28
    },
    {
      "epoch": 0.005345129481153811,
      "grad_norm": 3.1669583320617676,
      "learning_rate": 8.940053768033609e-05,
      "loss": 16.0,
      "step": 29
    },
    {
      "epoch": 0.00552944429084877,
      "grad_norm": 2.387568235397339,
      "learning_rate": 8.83022221559489e-05,
      "loss": 13.9167,
      "step": 30
    },
    {
      "epoch": 0.005713759100543728,
      "grad_norm": 2.6549859046936035,
      "learning_rate": 8.715724127386972e-05,
      "loss": 16.1657,
      "step": 31
    },
    {
      "epoch": 0.005898073910238688,
      "grad_norm": 2.539720058441162,
      "learning_rate": 8.596699001693255e-05,
      "loss": 15.6407,
      "step": 32
    },
    {
      "epoch": 0.006082388719933647,
      "grad_norm": 2.3321993350982666,
      "learning_rate": 8.473291852294987e-05,
      "loss": 18.3296,
      "step": 33
    },
    {
      "epoch": 0.006266703529628606,
      "grad_norm": 2.712390661239624,
      "learning_rate": 8.345653031794292e-05,
      "loss": 15.1686,
      "step": 34
    },
    {
      "epoch": 0.006451018339323564,
      "grad_norm": 2.700092077255249,
      "learning_rate": 8.213938048432697e-05,
      "loss": 15.2214,
      "step": 35
    },
    {
      "epoch": 0.006635333149018523,
      "grad_norm": 2.7663819789886475,
      "learning_rate": 8.07830737662829e-05,
      "loss": 13.7843,
      "step": 36
    },
    {
      "epoch": 0.006819647958713483,
      "grad_norm": 3.1760430335998535,
      "learning_rate": 7.938926261462366e-05,
      "loss": 15.4004,
      "step": 37
    },
    {
      "epoch": 0.007003962768408442,
      "grad_norm": 3.0473711490631104,
      "learning_rate": 7.795964517353735e-05,
      "loss": 16.2851,
      "step": 38
    },
    {
      "epoch": 0.007188277578103401,
      "grad_norm": 2.7892091274261475,
      "learning_rate": 7.649596321166024e-05,
      "loss": 16.1028,
      "step": 39
    },
    {
      "epoch": 0.007372592387798359,
      "grad_norm": 2.9921717643737793,
      "learning_rate": 7.500000000000001e-05,
      "loss": 16.5546,
      "step": 40
    },
    {
      "epoch": 0.0075569071974933184,
      "grad_norm": 2.8188507556915283,
      "learning_rate": 7.347357813929454e-05,
      "loss": 14.6144,
      "step": 41
    },
    {
      "epoch": 0.007741222007188278,
      "grad_norm": 2.5206265449523926,
      "learning_rate": 7.191855733945387e-05,
      "loss": 15.7602,
      "step": 42
    },
    {
      "epoch": 0.007925536816883237,
      "grad_norm": 2.6154024600982666,
      "learning_rate": 7.033683215379002e-05,
      "loss": 14.8239,
      "step": 43
    },
    {
      "epoch": 0.008109851626578195,
      "grad_norm": 2.918642282485962,
      "learning_rate": 6.873032967079561e-05,
      "loss": 16.3377,
      "step": 44
    },
    {
      "epoch": 0.008294166436273155,
      "grad_norm": 3.6406195163726807,
      "learning_rate": 6.710100716628344e-05,
      "loss": 14.1718,
      "step": 45
    },
    {
      "epoch": 0.008478481245968113,
      "grad_norm": 3.333871841430664,
      "learning_rate": 6.545084971874738e-05,
      "loss": 15.0592,
      "step": 46
    },
    {
      "epoch": 0.008662796055663072,
      "grad_norm": 2.552996873855591,
      "learning_rate": 6.378186779084995e-05,
      "loss": 15.2334,
      "step": 47
    },
    {
      "epoch": 0.008847110865358032,
      "grad_norm": 3.554128408432007,
      "learning_rate": 6.209609477998338e-05,
      "loss": 15.1196,
      "step": 48
    },
    {
      "epoch": 0.00903142567505299,
      "grad_norm": 3.3099277019500732,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 15.5887,
      "step": 49
    },
    {
      "epoch": 0.00921574048474795,
      "grad_norm": 2.6520323753356934,
      "learning_rate": 5.868240888334653e-05,
      "loss": 14.5928,
      "step": 50
    },
    {
      "epoch": 0.00921574048474795,
      "eval_loss": 0.9393519163131714,
      "eval_runtime": 1033.5121,
      "eval_samples_per_second": 8.842,
      "eval_steps_per_second": 4.421,
      "step": 50
    },
    {
      "epoch": 0.009400055294442908,
      "grad_norm": 5.914913654327393,
      "learning_rate": 5.695865504800327e-05,
      "loss": 15.4272,
      "step": 51
    },
    {
      "epoch": 0.009584370104137867,
      "grad_norm": 3.3482983112335205,
      "learning_rate": 5.522642316338268e-05,
      "loss": 14.2869,
      "step": 52
    },
    {
      "epoch": 0.009768684913832827,
      "grad_norm": 3.017594337463379,
      "learning_rate": 5.348782368720626e-05,
      "loss": 13.4869,
      "step": 53
    },
    {
      "epoch": 0.009952999723527785,
      "grad_norm": 2.4376871585845947,
      "learning_rate": 5.174497483512506e-05,
      "loss": 14.8098,
      "step": 54
    },
    {
      "epoch": 0.010137314533222745,
      "grad_norm": 2.880479574203491,
      "learning_rate": 5e-05,
      "loss": 16.5282,
      "step": 55
    },
    {
      "epoch": 0.010321629342917703,
      "grad_norm": 2.3686859607696533,
      "learning_rate": 4.825502516487497e-05,
      "loss": 16.0699,
      "step": 56
    },
    {
      "epoch": 0.010505944152612662,
      "grad_norm": 3.141923666000366,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 15.7888,
      "step": 57
    },
    {
      "epoch": 0.010690258962307622,
      "grad_norm": 2.8970398902893066,
      "learning_rate": 4.477357683661734e-05,
      "loss": 15.1017,
      "step": 58
    },
    {
      "epoch": 0.01087457377200258,
      "grad_norm": 2.902411460876465,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 14.0615,
      "step": 59
    },
    {
      "epoch": 0.01105888858169754,
      "grad_norm": 2.852792263031006,
      "learning_rate": 4.131759111665349e-05,
      "loss": 15.066,
      "step": 60
    },
    {
      "epoch": 0.011243203391392498,
      "grad_norm": 3.0440077781677246,
      "learning_rate": 3.960441545911204e-05,
      "loss": 14.7994,
      "step": 61
    },
    {
      "epoch": 0.011427518201087457,
      "grad_norm": 3.3743836879730225,
      "learning_rate": 3.790390522001662e-05,
      "loss": 13.4009,
      "step": 62
    },
    {
      "epoch": 0.011611833010782417,
      "grad_norm": 2.8256423473358154,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 13.7566,
      "step": 63
    },
    {
      "epoch": 0.011796147820477375,
      "grad_norm": 3.897556781768799,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 12.8892,
      "step": 64
    },
    {
      "epoch": 0.011980462630172335,
      "grad_norm": 2.8186323642730713,
      "learning_rate": 3.289899283371657e-05,
      "loss": 14.7145,
      "step": 65
    },
    {
      "epoch": 0.012164777439867294,
      "grad_norm": 2.807522773742676,
      "learning_rate": 3.12696703292044e-05,
      "loss": 15.2427,
      "step": 66
    },
    {
      "epoch": 0.012349092249562252,
      "grad_norm": 2.9150967597961426,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 13.5557,
      "step": 67
    },
    {
      "epoch": 0.012533407059257212,
      "grad_norm": 5.2960734367370605,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 15.1555,
      "step": 68
    },
    {
      "epoch": 0.01271772186895217,
      "grad_norm": 3.0016136169433594,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 15.3366,
      "step": 69
    },
    {
      "epoch": 0.012902036678647128,
      "grad_norm": 3.7237014770507812,
      "learning_rate": 2.500000000000001e-05,
      "loss": 15.8775,
      "step": 70
    },
    {
      "epoch": 0.013086351488342089,
      "grad_norm": 2.5541751384735107,
      "learning_rate": 2.350403678833976e-05,
      "loss": 17.1665,
      "step": 71
    },
    {
      "epoch": 0.013270666298037047,
      "grad_norm": 2.961252450942993,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 13.6807,
      "step": 72
    },
    {
      "epoch": 0.013454981107732007,
      "grad_norm": 3.0874316692352295,
      "learning_rate": 2.061073738537635e-05,
      "loss": 14.1517,
      "step": 73
    },
    {
      "epoch": 0.013639295917426965,
      "grad_norm": 2.96282696723938,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 13.6729,
      "step": 74
    },
    {
      "epoch": 0.013823610727121923,
      "grad_norm": 3.6580657958984375,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 12.8585,
      "step": 75
    },
    {
      "epoch": 0.013823610727121923,
      "eval_loss": 0.9254669547080994,
      "eval_runtime": 884.5666,
      "eval_samples_per_second": 10.33,
      "eval_steps_per_second": 5.165,
      "step": 75
    },
    {
      "epoch": 0.014007925536816884,
      "grad_norm": 2.3390562534332275,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 13.8937,
      "step": 76
    },
    {
      "epoch": 0.014192240346511842,
      "grad_norm": 2.683678388595581,
      "learning_rate": 1.526708147705013e-05,
      "loss": 15.438,
      "step": 77
    },
    {
      "epoch": 0.014376555156206802,
      "grad_norm": 5.658468246459961,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 15.7764,
      "step": 78
    },
    {
      "epoch": 0.01456086996590176,
      "grad_norm": 3.1090362071990967,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 14.5516,
      "step": 79
    },
    {
      "epoch": 0.014745184775596719,
      "grad_norm": 3.179821491241455,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 15.0476,
      "step": 80
    },
    {
      "epoch": 0.014929499585291679,
      "grad_norm": 2.848442554473877,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 15.2354,
      "step": 81
    },
    {
      "epoch": 0.015113814394986637,
      "grad_norm": 3.253157138824463,
      "learning_rate": 9.549150281252633e-06,
      "loss": 14.9676,
      "step": 82
    },
    {
      "epoch": 0.015298129204681597,
      "grad_norm": 2.540839910507202,
      "learning_rate": 8.548121372247918e-06,
      "loss": 13.5173,
      "step": 83
    },
    {
      "epoch": 0.015482444014376555,
      "grad_norm": 3.3609635829925537,
      "learning_rate": 7.597595192178702e-06,
      "loss": 14.5952,
      "step": 84
    },
    {
      "epoch": 0.015666758824071515,
      "grad_norm": 2.7323286533355713,
      "learning_rate": 6.698729810778065e-06,
      "loss": 14.0839,
      "step": 85
    },
    {
      "epoch": 0.015851073633766474,
      "grad_norm": 4.066798210144043,
      "learning_rate": 5.852620357053651e-06,
      "loss": 17.1209,
      "step": 86
    },
    {
      "epoch": 0.016035388443461432,
      "grad_norm": 3.078782796859741,
      "learning_rate": 5.060297685041659e-06,
      "loss": 14.7559,
      "step": 87
    },
    {
      "epoch": 0.01621970325315639,
      "grad_norm": 3.0598742961883545,
      "learning_rate": 4.322727117869951e-06,
      "loss": 15.3079,
      "step": 88
    },
    {
      "epoch": 0.01640401806285135,
      "grad_norm": 2.5015692710876465,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 14.9962,
      "step": 89
    },
    {
      "epoch": 0.01658833287254631,
      "grad_norm": 3.5916836261749268,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 15.5513,
      "step": 90
    },
    {
      "epoch": 0.01677264768224127,
      "grad_norm": 2.995640516281128,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 14.5251,
      "step": 91
    },
    {
      "epoch": 0.016956962491936227,
      "grad_norm": 2.552497148513794,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 14.2207,
      "step": 92
    },
    {
      "epoch": 0.017141277301631185,
      "grad_norm": 3.029528856277466,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 14.8641,
      "step": 93
    },
    {
      "epoch": 0.017325592111326144,
      "grad_norm": 3.5024685859680176,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 13.5346,
      "step": 94
    },
    {
      "epoch": 0.017509906921021105,
      "grad_norm": 3.124312400817871,
      "learning_rate": 7.596123493895991e-07,
      "loss": 14.1115,
      "step": 95
    },
    {
      "epoch": 0.017694221730716064,
      "grad_norm": 2.546924352645874,
      "learning_rate": 4.865965629214819e-07,
      "loss": 13.6974,
      "step": 96
    },
    {
      "epoch": 0.017878536540411022,
      "grad_norm": 3.2306652069091797,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 12.876,
      "step": 97
    },
    {
      "epoch": 0.01806285135010598,
      "grad_norm": 3.7203729152679443,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 13.3507,
      "step": 98
    },
    {
      "epoch": 0.01824716615980094,
      "grad_norm": 4.0581583976745605,
      "learning_rate": 3.04586490452119e-08,
      "loss": 14.288,
      "step": 99
    },
    {
      "epoch": 0.0184314809694959,
      "grad_norm": 3.7890498638153076,
      "learning_rate": 0.0,
      "loss": 15.2926,
      "step": 100
    },
    {
      "epoch": 0.0184314809694959,
      "eval_loss": 0.9233623743057251,
      "eval_runtime": 2176.616,
      "eval_samples_per_second": 4.198,
      "eval_steps_per_second": 2.099,
      "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": 1.9820564151533568e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}