{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.34371643394199786,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0034371643394199786,
      "grad_norm": 0.5334700345993042,
      "learning_rate": 1e-05,
      "loss": 2.5683,
      "step": 1
    },
    {
      "epoch": 0.0034371643394199786,
      "eval_loss": 2.636681318283081,
      "eval_runtime": 16.6995,
      "eval_samples_per_second": 29.342,
      "eval_steps_per_second": 29.342,
      "step": 1
    },
    {
      "epoch": 0.006874328678839957,
      "grad_norm": 0.5012644529342651,
      "learning_rate": 2e-05,
      "loss": 2.5063,
      "step": 2
    },
    {
      "epoch": 0.010311493018259935,
      "grad_norm": 0.5937795639038086,
      "learning_rate": 3e-05,
      "loss": 2.6041,
      "step": 3
    },
    {
      "epoch": 0.013748657357679914,
      "grad_norm": 0.44918254017829895,
      "learning_rate": 4e-05,
      "loss": 2.5385,
      "step": 4
    },
    {
      "epoch": 0.017185821697099892,
      "grad_norm": 0.4823933243751526,
      "learning_rate": 5e-05,
      "loss": 2.5282,
      "step": 5
    },
    {
      "epoch": 0.02062298603651987,
      "grad_norm": 0.4484499990940094,
      "learning_rate": 6e-05,
      "loss": 2.6244,
      "step": 6
    },
    {
      "epoch": 0.02406015037593985,
      "grad_norm": 0.7811288833618164,
      "learning_rate": 7e-05,
      "loss": 2.669,
      "step": 7
    },
    {
      "epoch": 0.02749731471535983,
      "grad_norm": 0.6050478219985962,
      "learning_rate": 8e-05,
      "loss": 2.5652,
      "step": 8
    },
    {
      "epoch": 0.030934479054779807,
      "grad_norm": 0.3714107275009155,
      "learning_rate": 9e-05,
      "loss": 2.5476,
      "step": 9
    },
    {
      "epoch": 0.034371643394199784,
      "grad_norm": 0.48898109793663025,
      "learning_rate": 0.0001,
      "loss": 2.4549,
      "step": 10
    },
    {
      "epoch": 0.03780880773361976,
      "grad_norm": 0.5035548210144043,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.5455,
      "step": 11
    },
    {
      "epoch": 0.04124597207303974,
      "grad_norm": 0.3796736001968384,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.5758,
      "step": 12
    },
    {
      "epoch": 0.04468313641245972,
      "grad_norm": 0.7549750208854675,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.4608,
      "step": 13
    },
    {
      "epoch": 0.0481203007518797,
      "grad_norm": 0.4282947778701782,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.6564,
      "step": 14
    },
    {
      "epoch": 0.05155746509129968,
      "grad_norm": 0.33888301253318787,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.4809,
      "step": 15
    },
    {
      "epoch": 0.05499462943071966,
      "grad_norm": 0.30642518401145935,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.3737,
      "step": 16
    },
    {
      "epoch": 0.058431793770139635,
      "grad_norm": 0.37518784403800964,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.4509,
      "step": 17
    },
    {
      "epoch": 0.06186895810955961,
      "grad_norm": 0.32034221291542053,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.4367,
      "step": 18
    },
    {
      "epoch": 0.0653061224489796,
      "grad_norm": 0.5690639019012451,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.3744,
      "step": 19
    },
    {
      "epoch": 0.06874328678839957,
      "grad_norm": 0.35108500719070435,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.3465,
      "step": 20
    },
    {
      "epoch": 0.07218045112781955,
      "grad_norm": 0.4233250021934509,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.4106,
      "step": 21
    },
    {
      "epoch": 0.07561761546723952,
      "grad_norm": 0.2957749664783478,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.387,
      "step": 22
    },
    {
      "epoch": 0.07905477980665951,
      "grad_norm": 0.4620259404182434,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.5992,
      "step": 23
    },
    {
      "epoch": 0.08249194414607948,
      "grad_norm": 0.33380621671676636,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.3997,
      "step": 24
    },
    {
      "epoch": 0.08592910848549946,
      "grad_norm": 0.47963470220565796,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.4815,
      "step": 25
    },
    {
      "epoch": 0.08936627282491943,
      "grad_norm": 0.7058689594268799,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.2882,
      "step": 26
    },
    {
      "epoch": 0.09280343716433942,
      "grad_norm": 0.31185293197631836,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.3354,
      "step": 27
    },
    {
      "epoch": 0.0962406015037594,
      "grad_norm": 0.7282019257545471,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.4109,
      "step": 28
    },
    {
      "epoch": 0.09967776584317938,
      "grad_norm": 0.41433587670326233,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.4216,
      "step": 29
    },
    {
      "epoch": 0.10311493018259936,
      "grad_norm": 0.3362176716327667,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.4594,
      "step": 30
    },
    {
      "epoch": 0.10655209452201933,
      "grad_norm": 0.3251080811023712,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.3187,
      "step": 31
    },
    {
      "epoch": 0.10998925886143932,
      "grad_norm": 0.2905067503452301,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.2976,
      "step": 32
    },
    {
      "epoch": 0.11342642320085929,
      "grad_norm": 0.6331003308296204,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.3578,
      "step": 33
    },
    {
      "epoch": 0.11686358754027927,
      "grad_norm": 0.4537586271762848,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.2121,
      "step": 34
    },
    {
      "epoch": 0.12030075187969924,
      "grad_norm": 0.43433278799057007,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.3014,
      "step": 35
    },
    {
      "epoch": 0.12373791621911923,
      "grad_norm": 0.3546953797340393,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.2345,
      "step": 36
    },
    {
      "epoch": 0.1271750805585392,
      "grad_norm": 0.40316927433013916,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.3044,
      "step": 37
    },
    {
      "epoch": 0.1306122448979592,
      "grad_norm": 0.3827572762966156,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.2661,
      "step": 38
    },
    {
      "epoch": 0.13404940923737915,
      "grad_norm": 0.3343763053417206,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.2766,
      "step": 39
    },
    {
      "epoch": 0.13748657357679914,
      "grad_norm": 0.2966914772987366,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.3064,
      "step": 40
    },
    {
      "epoch": 0.14092373791621912,
      "grad_norm": 0.30342233180999756,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.3846,
      "step": 41
    },
    {
      "epoch": 0.1443609022556391,
      "grad_norm": 0.2643699049949646,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.3035,
      "step": 42
    },
    {
      "epoch": 0.14779806659505906,
      "grad_norm": 0.35844695568084717,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.2482,
      "step": 43
    },
    {
      "epoch": 0.15123523093447905,
      "grad_norm": 0.2792685627937317,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.2494,
      "step": 44
    },
    {
      "epoch": 0.15467239527389903,
      "grad_norm": 0.29278451204299927,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.3016,
      "step": 45
    },
    {
      "epoch": 0.15810955961331902,
      "grad_norm": 0.3153465688228607,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.2621,
      "step": 46
    },
    {
      "epoch": 0.161546723952739,
      "grad_norm": 0.39804384112358093,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.2838,
      "step": 47
    },
    {
      "epoch": 0.16498388829215896,
      "grad_norm": 0.29693296551704407,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.2569,
      "step": 48
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 0.4537481367588043,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.2107,
      "step": 49
    },
    {
      "epoch": 0.17185821697099893,
      "grad_norm": 0.2757551670074463,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.2964,
      "step": 50
    },
    {
      "epoch": 0.17185821697099893,
      "eval_loss": 2.3215746879577637,
      "eval_runtime": 16.7462,
      "eval_samples_per_second": 29.26,
      "eval_steps_per_second": 29.26,
      "step": 50
    },
    {
      "epoch": 0.1752953813104189,
      "grad_norm": 0.3440859317779541,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.2643,
      "step": 51
    },
    {
      "epoch": 0.17873254564983887,
      "grad_norm": 0.3143952488899231,
      "learning_rate": 5.522642316338268e-05,
      "loss": 2.3741,
      "step": 52
    },
    {
      "epoch": 0.18216970998925885,
      "grad_norm": 0.5445249676704407,
      "learning_rate": 5.348782368720626e-05,
      "loss": 2.3737,
      "step": 53
    },
    {
      "epoch": 0.18560687432867884,
      "grad_norm": 0.29417288303375244,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.2626,
      "step": 54
    },
    {
      "epoch": 0.18904403866809882,
      "grad_norm": 0.2821301519870758,
      "learning_rate": 5e-05,
      "loss": 2.2226,
      "step": 55
    },
    {
      "epoch": 0.1924812030075188,
      "grad_norm": 0.5049765706062317,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.2056,
      "step": 56
    },
    {
      "epoch": 0.19591836734693877,
      "grad_norm": 0.2741824984550476,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 2.0916,
      "step": 57
    },
    {
      "epoch": 0.19935553168635875,
      "grad_norm": 0.2932296097278595,
      "learning_rate": 4.477357683661734e-05,
      "loss": 2.1948,
      "step": 58
    },
    {
      "epoch": 0.20279269602577873,
      "grad_norm": 0.2703547477722168,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 2.2377,
      "step": 59
    },
    {
      "epoch": 0.20622986036519872,
      "grad_norm": 0.5145007371902466,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.2336,
      "step": 60
    },
    {
      "epoch": 0.20966702470461868,
      "grad_norm": 0.3122769594192505,
      "learning_rate": 3.960441545911204e-05,
      "loss": 2.1879,
      "step": 61
    },
    {
      "epoch": 0.21310418904403866,
      "grad_norm": 0.2763988673686981,
      "learning_rate": 3.790390522001662e-05,
      "loss": 2.2149,
      "step": 62
    },
    {
      "epoch": 0.21654135338345865,
      "grad_norm": 0.31647786498069763,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 2.1863,
      "step": 63
    },
    {
      "epoch": 0.21997851772287863,
      "grad_norm": 0.5407307744026184,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.2516,
      "step": 64
    },
    {
      "epoch": 0.22341568206229862,
      "grad_norm": 0.31190451979637146,
      "learning_rate": 3.289899283371657e-05,
      "loss": 2.2059,
      "step": 65
    },
    {
      "epoch": 0.22685284640171857,
      "grad_norm": 0.3045297861099243,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.2161,
      "step": 66
    },
    {
      "epoch": 0.23029001074113856,
      "grad_norm": 0.3111981153488159,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 2.2722,
      "step": 67
    },
    {
      "epoch": 0.23372717508055854,
      "grad_norm": 0.5072479844093323,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.1672,
      "step": 68
    },
    {
      "epoch": 0.23716433941997853,
      "grad_norm": 0.4372091293334961,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.3158,
      "step": 69
    },
    {
      "epoch": 0.24060150375939848,
      "grad_norm": 0.28215134143829346,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.2365,
      "step": 70
    },
    {
      "epoch": 0.24403866809881847,
      "grad_norm": 0.3402535915374756,
      "learning_rate": 2.350403678833976e-05,
      "loss": 2.2135,
      "step": 71
    },
    {
      "epoch": 0.24747583243823845,
      "grad_norm": 0.46998509764671326,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 2.3625,
      "step": 72
    },
    {
      "epoch": 0.25091299677765844,
      "grad_norm": 0.2795167565345764,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.1809,
      "step": 73
    },
    {
      "epoch": 0.2543501611170784,
      "grad_norm": 0.37644481658935547,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 2.2632,
      "step": 74
    },
    {
      "epoch": 0.2577873254564984,
      "grad_norm": 0.32024654746055603,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 2.2528,
      "step": 75
    },
    {
      "epoch": 0.2612244897959184,
      "grad_norm": 0.31380581855773926,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 2.2103,
      "step": 76
    },
    {
      "epoch": 0.2646616541353383,
      "grad_norm": 0.35320228338241577,
      "learning_rate": 1.526708147705013e-05,
      "loss": 2.2328,
      "step": 77
    },
    {
      "epoch": 0.2680988184747583,
      "grad_norm": 0.3124861419200897,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 2.2054,
      "step": 78
    },
    {
      "epoch": 0.2715359828141783,
      "grad_norm": 0.4113110899925232,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 2.0905,
      "step": 79
    },
    {
      "epoch": 0.2749731471535983,
      "grad_norm": 0.47795024514198303,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 2.3201,
      "step": 80
    },
    {
      "epoch": 0.27841031149301826,
      "grad_norm": 0.29258468747138977,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 2.2022,
      "step": 81
    },
    {
      "epoch": 0.28184747583243824,
      "grad_norm": 0.28537437319755554,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.2611,
      "step": 82
    },
    {
      "epoch": 0.28528464017185823,
      "grad_norm": 0.3414091467857361,
      "learning_rate": 8.548121372247918e-06,
      "loss": 2.2069,
      "step": 83
    },
    {
      "epoch": 0.2887218045112782,
      "grad_norm": 0.39266514778137207,
      "learning_rate": 7.597595192178702e-06,
      "loss": 2.2485,
      "step": 84
    },
    {
      "epoch": 0.2921589688506982,
      "grad_norm": 0.5153230428695679,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.1257,
      "step": 85
    },
    {
      "epoch": 0.2955961331901181,
      "grad_norm": 0.31598207354545593,
      "learning_rate": 5.852620357053651e-06,
      "loss": 2.1899,
      "step": 86
    },
    {
      "epoch": 0.2990332975295381,
      "grad_norm": 0.3173138201236725,
      "learning_rate": 5.060297685041659e-06,
      "loss": 2.209,
      "step": 87
    },
    {
      "epoch": 0.3024704618689581,
      "grad_norm": 0.28669506311416626,
      "learning_rate": 4.322727117869951e-06,
      "loss": 2.1869,
      "step": 88
    },
    {
      "epoch": 0.3059076262083781,
      "grad_norm": 0.31095296144485474,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 2.164,
      "step": 89
    },
    {
      "epoch": 0.30934479054779807,
      "grad_norm": 0.27381399273872375,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.202,
      "step": 90
    },
    {
      "epoch": 0.31278195488721805,
      "grad_norm": 0.4227629601955414,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.3388,
      "step": 91
    },
    {
      "epoch": 0.31621911922663803,
      "grad_norm": 0.4945060908794403,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 2.1518,
      "step": 92
    },
    {
      "epoch": 0.319656283566058,
      "grad_norm": 0.3266584873199463,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 2.3398,
      "step": 93
    },
    {
      "epoch": 0.323093447905478,
      "grad_norm": 0.2841348648071289,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.1788,
      "step": 94
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": 0.2800915539264679,
      "learning_rate": 7.596123493895991e-07,
      "loss": 2.121,
      "step": 95
    },
    {
      "epoch": 0.3299677765843179,
      "grad_norm": 0.3364481031894684,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2.2739,
      "step": 96
    },
    {
      "epoch": 0.3334049409237379,
      "grad_norm": 0.5338711738586426,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 2.2574,
      "step": 97
    },
    {
      "epoch": 0.3368421052631579,
      "grad_norm": 0.29511675238609314,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.1717,
      "step": 98
    },
    {
      "epoch": 0.34027926960257787,
      "grad_norm": 0.31296125054359436,
      "learning_rate": 3.04586490452119e-08,
      "loss": 2.1663,
      "step": 99
    },
    {
      "epoch": 0.34371643394199786,
      "grad_norm": 0.2975694537162781,
      "learning_rate": 0.0,
      "loss": 2.1862,
      "step": 100
    },
    {
      "epoch": 0.34371643394199786,
      "eval_loss": 2.2586705684661865,
      "eval_runtime": 16.6976,
      "eval_samples_per_second": 29.345,
      "eval_steps_per_second": 29.345,
      "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": 2162580270612480.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}