{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08421052631578947,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008421052631578948,
      "grad_norm": 29.74006462097168,
      "learning_rate": 1e-05,
      "loss": 4.6635,
      "step": 1
    },
    {
      "epoch": 0.0008421052631578948,
      "eval_loss": 4.599607944488525,
      "eval_runtime": 28.7101,
      "eval_samples_per_second": 34.831,
      "eval_steps_per_second": 4.354,
      "step": 1
    },
    {
      "epoch": 0.0016842105263157896,
      "grad_norm": 31.42214584350586,
      "learning_rate": 2e-05,
      "loss": 4.8812,
      "step": 2
    },
    {
      "epoch": 0.0025263157894736842,
      "grad_norm": 28.822940826416016,
      "learning_rate": 3e-05,
      "loss": 4.4176,
      "step": 3
    },
    {
      "epoch": 0.003368421052631579,
      "grad_norm": 23.323659896850586,
      "learning_rate": 4e-05,
      "loss": 4.1315,
      "step": 4
    },
    {
      "epoch": 0.004210526315789474,
      "grad_norm": 13.657670974731445,
      "learning_rate": 5e-05,
      "loss": 3.7565,
      "step": 5
    },
    {
      "epoch": 0.0050526315789473685,
      "grad_norm": 10.201245307922363,
      "learning_rate": 6e-05,
      "loss": 3.2939,
      "step": 6
    },
    {
      "epoch": 0.005894736842105263,
      "grad_norm": 11.039713859558105,
      "learning_rate": 7e-05,
      "loss": 3.5258,
      "step": 7
    },
    {
      "epoch": 0.006736842105263158,
      "grad_norm": 6.523703098297119,
      "learning_rate": 8e-05,
      "loss": 2.8563,
      "step": 8
    },
    {
      "epoch": 0.007578947368421052,
      "grad_norm": 10.33078384399414,
      "learning_rate": 9e-05,
      "loss": 2.7121,
      "step": 9
    },
    {
      "epoch": 0.007578947368421052,
      "eval_loss": 2.6245853900909424,
      "eval_runtime": 28.7107,
      "eval_samples_per_second": 34.83,
      "eval_steps_per_second": 4.354,
      "step": 9
    },
    {
      "epoch": 0.008421052631578947,
      "grad_norm": 9.98810863494873,
      "learning_rate": 0.0001,
      "loss": 3.0674,
      "step": 10
    },
    {
      "epoch": 0.009263157894736843,
      "grad_norm": 6.940089225769043,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.4005,
      "step": 11
    },
    {
      "epoch": 0.010105263157894737,
      "grad_norm": 5.037336826324463,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.9071,
      "step": 12
    },
    {
      "epoch": 0.010947368421052631,
      "grad_norm": 3.5909926891326904,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.7824,
      "step": 13
    },
    {
      "epoch": 0.011789473684210527,
      "grad_norm": 3.8077168464660645,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.6997,
      "step": 14
    },
    {
      "epoch": 0.01263157894736842,
      "grad_norm": 3.8731205463409424,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.4925,
      "step": 15
    },
    {
      "epoch": 0.013473684210526317,
      "grad_norm": 4.64369010925293,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.4637,
      "step": 16
    },
    {
      "epoch": 0.01431578947368421,
      "grad_norm": 3.8383593559265137,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.2305,
      "step": 17
    },
    {
      "epoch": 0.015157894736842105,
      "grad_norm": 5.049322605133057,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.1185,
      "step": 18
    },
    {
      "epoch": 0.015157894736842105,
      "eval_loss": 1.1053184270858765,
      "eval_runtime": 28.7185,
      "eval_samples_per_second": 34.821,
      "eval_steps_per_second": 4.353,
      "step": 18
    },
    {
      "epoch": 0.016,
      "grad_norm": 9.18146800994873,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.1192,
      "step": 19
    },
    {
      "epoch": 0.016842105263157894,
      "grad_norm": 3.4365334510803223,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.0367,
      "step": 20
    },
    {
      "epoch": 0.01768421052631579,
      "grad_norm": 3.0855212211608887,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.881,
      "step": 21
    },
    {
      "epoch": 0.018526315789473686,
      "grad_norm": 3.045132875442505,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.8593,
      "step": 22
    },
    {
      "epoch": 0.01936842105263158,
      "grad_norm": 1.7933003902435303,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.8186,
      "step": 23
    },
    {
      "epoch": 0.020210526315789474,
      "grad_norm": 2.677367687225342,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.7228,
      "step": 24
    },
    {
      "epoch": 0.021052631578947368,
      "grad_norm": 2.2343409061431885,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.7265,
      "step": 25
    },
    {
      "epoch": 0.021894736842105262,
      "grad_norm": 1.7142243385314941,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.683,
      "step": 26
    },
    {
      "epoch": 0.02273684210526316,
      "grad_norm": 3.214435577392578,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.718,
      "step": 27
    },
    {
      "epoch": 0.02273684210526316,
      "eval_loss": 0.6878807544708252,
      "eval_runtime": 28.7343,
      "eval_samples_per_second": 34.802,
      "eval_steps_per_second": 4.35,
      "step": 27
    },
    {
      "epoch": 0.023578947368421053,
      "grad_norm": 1.9839012622833252,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6446,
      "step": 28
    },
    {
      "epoch": 0.024421052631578948,
      "grad_norm": 1.6361652612686157,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.668,
      "step": 29
    },
    {
      "epoch": 0.02526315789473684,
      "grad_norm": 2.7082302570343018,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.6683,
      "step": 30
    },
    {
      "epoch": 0.026105263157894736,
      "grad_norm": 1.7003586292266846,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.6807,
      "step": 31
    },
    {
      "epoch": 0.026947368421052633,
      "grad_norm": 1.5261609554290771,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.6146,
      "step": 32
    },
    {
      "epoch": 0.027789473684210527,
      "grad_norm": 2.0998878479003906,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.676,
      "step": 33
    },
    {
      "epoch": 0.02863157894736842,
      "grad_norm": 1.1744210720062256,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.648,
      "step": 34
    },
    {
      "epoch": 0.029473684210526315,
      "grad_norm": 0.9713230133056641,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.6781,
      "step": 35
    },
    {
      "epoch": 0.03031578947368421,
      "grad_norm": 3.680906057357788,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.6691,
      "step": 36
    },
    {
      "epoch": 0.03031578947368421,
      "eval_loss": 0.6558133363723755,
      "eval_runtime": 28.6878,
      "eval_samples_per_second": 34.858,
      "eval_steps_per_second": 4.357,
      "step": 36
    },
    {
      "epoch": 0.031157894736842107,
      "grad_norm": 1.511498212814331,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.6563,
      "step": 37
    },
    {
      "epoch": 0.032,
      "grad_norm": 1.281856894493103,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.6374,
      "step": 38
    },
    {
      "epoch": 0.032842105263157895,
      "grad_norm": 0.5086827278137207,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.6181,
      "step": 39
    },
    {
      "epoch": 0.03368421052631579,
      "grad_norm": 0.8291170001029968,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.6923,
      "step": 40
    },
    {
      "epoch": 0.03452631578947368,
      "grad_norm": 1.0818743705749512,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.6605,
      "step": 41
    },
    {
      "epoch": 0.03536842105263158,
      "grad_norm": 0.7888435125350952,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.6562,
      "step": 42
    },
    {
      "epoch": 0.03621052631578947,
      "grad_norm": 1.2603929042816162,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.6422,
      "step": 43
    },
    {
      "epoch": 0.03705263157894737,
      "grad_norm": 1.2151390314102173,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.6493,
      "step": 44
    },
    {
      "epoch": 0.037894736842105266,
      "grad_norm": 0.6896181702613831,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.6372,
      "step": 45
    },
    {
      "epoch": 0.037894736842105266,
      "eval_loss": 0.6379881501197815,
      "eval_runtime": 28.6964,
      "eval_samples_per_second": 34.848,
      "eval_steps_per_second": 4.356,
      "step": 45
    },
    {
      "epoch": 0.03873684210526316,
      "grad_norm": 0.7597723007202148,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.6494,
      "step": 46
    },
    {
      "epoch": 0.039578947368421054,
      "grad_norm": 0.47444620728492737,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.649,
      "step": 47
    },
    {
      "epoch": 0.04042105263157895,
      "grad_norm": 0.8695865869522095,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.6465,
      "step": 48
    },
    {
      "epoch": 0.04126315789473684,
      "grad_norm": 0.7049533724784851,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.6201,
      "step": 49
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 0.818119466304779,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.6475,
      "step": 50
    },
    {
      "epoch": 0.04294736842105263,
      "grad_norm": 0.6151592135429382,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.6265,
      "step": 51
    },
    {
      "epoch": 0.043789473684210524,
      "grad_norm": 0.5425090193748474,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.6481,
      "step": 52
    },
    {
      "epoch": 0.04463157894736842,
      "grad_norm": 0.51148921251297,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.6227,
      "step": 53
    },
    {
      "epoch": 0.04547368421052632,
      "grad_norm": 0.49863481521606445,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.6397,
      "step": 54
    },
    {
      "epoch": 0.04547368421052632,
      "eval_loss": 0.6352894306182861,
      "eval_runtime": 28.7122,
      "eval_samples_per_second": 34.828,
      "eval_steps_per_second": 4.354,
      "step": 54
    },
    {
      "epoch": 0.04631578947368421,
      "grad_norm": 0.7179785370826721,
      "learning_rate": 5e-05,
      "loss": 0.6644,
      "step": 55
    },
    {
      "epoch": 0.04715789473684211,
      "grad_norm": 0.6957202553749084,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.6482,
      "step": 56
    },
    {
      "epoch": 0.048,
      "grad_norm": 0.47261208295822144,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.637,
      "step": 57
    },
    {
      "epoch": 0.048842105263157895,
      "grad_norm": 0.9482942819595337,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.6306,
      "step": 58
    },
    {
      "epoch": 0.04968421052631579,
      "grad_norm": 0.42428135871887207,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.6208,
      "step": 59
    },
    {
      "epoch": 0.05052631578947368,
      "grad_norm": 0.2713795304298401,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.6347,
      "step": 60
    },
    {
      "epoch": 0.05136842105263158,
      "grad_norm": 0.5890096426010132,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.6379,
      "step": 61
    },
    {
      "epoch": 0.05221052631578947,
      "grad_norm": 0.6223120093345642,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.6292,
      "step": 62
    },
    {
      "epoch": 0.053052631578947365,
      "grad_norm": 0.47491008043289185,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.631,
      "step": 63
    },
    {
      "epoch": 0.053052631578947365,
      "eval_loss": 0.6267176270484924,
      "eval_runtime": 28.6879,
      "eval_samples_per_second": 34.858,
      "eval_steps_per_second": 4.357,
      "step": 63
    },
    {
      "epoch": 0.053894736842105266,
      "grad_norm": 0.8451453447341919,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6133,
      "step": 64
    },
    {
      "epoch": 0.05473684210526316,
      "grad_norm": 0.6316500306129456,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.6295,
      "step": 65
    },
    {
      "epoch": 0.055578947368421054,
      "grad_norm": 0.475432813167572,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.6283,
      "step": 66
    },
    {
      "epoch": 0.05642105263157895,
      "grad_norm": 0.4279637038707733,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.6353,
      "step": 67
    },
    {
      "epoch": 0.05726315789473684,
      "grad_norm": 0.39883410930633545,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.6273,
      "step": 68
    },
    {
      "epoch": 0.058105263157894736,
      "grad_norm": 0.4334561824798584,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.6238,
      "step": 69
    },
    {
      "epoch": 0.05894736842105263,
      "grad_norm": 0.3239782452583313,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.6227,
      "step": 70
    },
    {
      "epoch": 0.059789473684210524,
      "grad_norm": 0.46495527029037476,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.6244,
      "step": 71
    },
    {
      "epoch": 0.06063157894736842,
      "grad_norm": 0.3789292573928833,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.6284,
      "step": 72
    },
    {
      "epoch": 0.06063157894736842,
      "eval_loss": 0.6295309066772461,
      "eval_runtime": 28.6861,
      "eval_samples_per_second": 34.86,
      "eval_steps_per_second": 4.358,
      "step": 72
    },
    {
      "epoch": 0.06147368421052631,
      "grad_norm": 0.2577737867832184,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6167,
      "step": 73
    },
    {
      "epoch": 0.06231578947368421,
      "grad_norm": 0.4692973494529724,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.6137,
      "step": 74
    },
    {
      "epoch": 0.06315789473684211,
      "grad_norm": 0.28481587767601013,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.6147,
      "step": 75
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.3419746458530426,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.6167,
      "step": 76
    },
    {
      "epoch": 0.0648421052631579,
      "grad_norm": 0.7516468167304993,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.6367,
      "step": 77
    },
    {
      "epoch": 0.06568421052631579,
      "grad_norm": 0.5556538105010986,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.6365,
      "step": 78
    },
    {
      "epoch": 0.06652631578947368,
      "grad_norm": 0.4769613742828369,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.63,
      "step": 79
    },
    {
      "epoch": 0.06736842105263158,
      "grad_norm": 0.4179724454879761,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.6188,
      "step": 80
    },
    {
      "epoch": 0.06821052631578947,
      "grad_norm": 0.497568279504776,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.6318,
      "step": 81
    },
    {
      "epoch": 0.06821052631578947,
      "eval_loss": 0.62742018699646,
      "eval_runtime": 28.6954,
      "eval_samples_per_second": 34.849,
      "eval_steps_per_second": 4.356,
      "step": 81
    },
    {
      "epoch": 0.06905263157894737,
      "grad_norm": 0.6568834781646729,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.6382,
      "step": 82
    },
    {
      "epoch": 0.06989473684210526,
      "grad_norm": 0.44247978925704956,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.6287,
      "step": 83
    },
    {
      "epoch": 0.07073684210526315,
      "grad_norm": 0.48621073365211487,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.6372,
      "step": 84
    },
    {
      "epoch": 0.07157894736842105,
      "grad_norm": 0.493594765663147,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.6298,
      "step": 85
    },
    {
      "epoch": 0.07242105263157894,
      "grad_norm": 0.47130337357521057,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.6161,
      "step": 86
    },
    {
      "epoch": 0.07326315789473684,
      "grad_norm": 0.370483934879303,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.6283,
      "step": 87
    },
    {
      "epoch": 0.07410526315789474,
      "grad_norm": 0.4378347098827362,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.6229,
      "step": 88
    },
    {
      "epoch": 0.07494736842105264,
      "grad_norm": 0.5102152824401855,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.6225,
      "step": 89
    },
    {
      "epoch": 0.07578947368421053,
      "grad_norm": 0.4649106562137604,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.6318,
      "step": 90
    },
    {
      "epoch": 0.07578947368421053,
      "eval_loss": 0.6250188946723938,
      "eval_runtime": 28.6886,
      "eval_samples_per_second": 34.857,
      "eval_steps_per_second": 4.357,
      "step": 90
    },
    {
      "epoch": 0.07663157894736843,
      "grad_norm": 0.4687817692756653,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.6187,
      "step": 91
    },
    {
      "epoch": 0.07747368421052632,
      "grad_norm": 0.369341641664505,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.6219,
      "step": 92
    },
    {
      "epoch": 0.07831578947368421,
      "grad_norm": 0.41136807203292847,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.6191,
      "step": 93
    },
    {
      "epoch": 0.07915789473684211,
      "grad_norm": 0.3214464485645294,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.6222,
      "step": 94
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.4911435544490814,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.6334,
      "step": 95
    },
    {
      "epoch": 0.0808421052631579,
      "grad_norm": 0.4080554246902466,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.6431,
      "step": 96
    },
    {
      "epoch": 0.08168421052631579,
      "grad_norm": 0.39761316776275635,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.6264,
      "step": 97
    },
    {
      "epoch": 0.08252631578947368,
      "grad_norm": 0.42710548639297485,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.6246,
      "step": 98
    },
    {
      "epoch": 0.08336842105263158,
      "grad_norm": 0.4810851812362671,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.6293,
      "step": 99
    },
    {
      "epoch": 0.08336842105263158,
      "eval_loss": 0.6246677041053772,
      "eval_runtime": 28.7191,
      "eval_samples_per_second": 34.82,
      "eval_steps_per_second": 4.352,
      "step": 99
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 0.27740001678466797,
      "learning_rate": 0.0,
      "loss": 0.6241,
      "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": 1.02936877203456e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}