{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010662614873014922,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010662614873014921,
      "grad_norm": 0.09556058794260025,
      "learning_rate": 1e-05,
      "loss": 10.8347,
      "step": 1
    },
    {
      "epoch": 0.00010662614873014921,
      "eval_loss": 10.834606170654297,
      "eval_runtime": 38.6886,
      "eval_samples_per_second": 408.285,
      "eval_steps_per_second": 204.143,
      "step": 1
    },
    {
      "epoch": 0.00021325229746029843,
      "grad_norm": 0.09524369239807129,
      "learning_rate": 2e-05,
      "loss": 10.8334,
      "step": 2
    },
    {
      "epoch": 0.00031987844619044766,
      "grad_norm": 0.10252054035663605,
      "learning_rate": 3e-05,
      "loss": 10.8366,
      "step": 3
    },
    {
      "epoch": 0.00042650459492059686,
      "grad_norm": 0.09081214666366577,
      "learning_rate": 4e-05,
      "loss": 10.8363,
      "step": 4
    },
    {
      "epoch": 0.0005331307436507461,
      "grad_norm": 0.0959392711520195,
      "learning_rate": 5e-05,
      "loss": 10.8339,
      "step": 5
    },
    {
      "epoch": 0.0006397568923808953,
      "grad_norm": 0.08222699910402298,
      "learning_rate": 6e-05,
      "loss": 10.831,
      "step": 6
    },
    {
      "epoch": 0.0007463830411110445,
      "grad_norm": 0.08778945356607437,
      "learning_rate": 7e-05,
      "loss": 10.8336,
      "step": 7
    },
    {
      "epoch": 0.0008530091898411937,
      "grad_norm": 0.08124235272407532,
      "learning_rate": 8e-05,
      "loss": 10.8334,
      "step": 8
    },
    {
      "epoch": 0.0009596353385713429,
      "grad_norm": 0.09498875588178635,
      "learning_rate": 9e-05,
      "loss": 10.8362,
      "step": 9
    },
    {
      "epoch": 0.0010662614873014921,
      "grad_norm": 0.10160056501626968,
      "learning_rate": 0.0001,
      "loss": 10.8318,
      "step": 10
    },
    {
      "epoch": 0.0011728876360316413,
      "grad_norm": 0.09773286432027817,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.8302,
      "step": 11
    },
    {
      "epoch": 0.0012795137847617906,
      "grad_norm": 0.09210336208343506,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.8307,
      "step": 12
    },
    {
      "epoch": 0.0013861399334919398,
      "grad_norm": 0.10203942656517029,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.8322,
      "step": 13
    },
    {
      "epoch": 0.001492766082222089,
      "grad_norm": 0.09077027440071106,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.8305,
      "step": 14
    },
    {
      "epoch": 0.001599392230952238,
      "grad_norm": 0.09403304755687714,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.8301,
      "step": 15
    },
    {
      "epoch": 0.0017060183796823874,
      "grad_norm": 0.10645323991775513,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.8306,
      "step": 16
    },
    {
      "epoch": 0.0018126445284125366,
      "grad_norm": 0.10251530259847641,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.8273,
      "step": 17
    },
    {
      "epoch": 0.0019192706771426857,
      "grad_norm": 0.10220959782600403,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.8284,
      "step": 18
    },
    {
      "epoch": 0.002025896825872835,
      "grad_norm": 0.09652484208345413,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.8268,
      "step": 19
    },
    {
      "epoch": 0.0021325229746029842,
      "grad_norm": 0.1007598266005516,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.8307,
      "step": 20
    },
    {
      "epoch": 0.0022391491233331334,
      "grad_norm": 0.10961519926786423,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.8255,
      "step": 21
    },
    {
      "epoch": 0.0023457752720632825,
      "grad_norm": 0.10666362196207047,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.8288,
      "step": 22
    },
    {
      "epoch": 0.0024524014207934317,
      "grad_norm": 0.12087945640087128,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.8274,
      "step": 23
    },
    {
      "epoch": 0.0025590275695235812,
      "grad_norm": 0.10848045349121094,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.8294,
      "step": 24
    },
    {
      "epoch": 0.0026656537182537304,
      "grad_norm": 0.0989118367433548,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.8252,
      "step": 25
    },
    {
      "epoch": 0.0026656537182537304,
      "eval_loss": 10.827045440673828,
      "eval_runtime": 27.3777,
      "eval_samples_per_second": 576.966,
      "eval_steps_per_second": 288.483,
      "step": 25
    },
    {
      "epoch": 0.0027722798669838795,
      "grad_norm": 0.1026577427983284,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.8233,
      "step": 26
    },
    {
      "epoch": 0.0028789060157140287,
      "grad_norm": 0.10963460057973862,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.8291,
      "step": 27
    },
    {
      "epoch": 0.002985532164444178,
      "grad_norm": 0.1128157526254654,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.8313,
      "step": 28
    },
    {
      "epoch": 0.003092158313174327,
      "grad_norm": 0.11681310087442398,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.8269,
      "step": 29
    },
    {
      "epoch": 0.003198784461904476,
      "grad_norm": 0.10859231650829315,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.8291,
      "step": 30
    },
    {
      "epoch": 0.0033054106106346257,
      "grad_norm": 0.12530773878097534,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.8255,
      "step": 31
    },
    {
      "epoch": 0.003412036759364775,
      "grad_norm": 0.1253245323896408,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.8218,
      "step": 32
    },
    {
      "epoch": 0.003518662908094924,
      "grad_norm": 0.1236739233136177,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.8226,
      "step": 33
    },
    {
      "epoch": 0.003625289056825073,
      "grad_norm": 0.13345038890838623,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.8218,
      "step": 34
    },
    {
      "epoch": 0.0037319152055552223,
      "grad_norm": 0.13090018928050995,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.8221,
      "step": 35
    },
    {
      "epoch": 0.0038385413542853714,
      "grad_norm": 0.12226233631372452,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.8265,
      "step": 36
    },
    {
      "epoch": 0.003945167503015521,
      "grad_norm": 0.13375620543956757,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.8199,
      "step": 37
    },
    {
      "epoch": 0.00405179365174567,
      "grad_norm": 0.1250225007534027,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.8218,
      "step": 38
    },
    {
      "epoch": 0.004158419800475819,
      "grad_norm": 0.12829391658306122,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.8198,
      "step": 39
    },
    {
      "epoch": 0.0042650459492059685,
      "grad_norm": 0.14134521782398224,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.8201,
      "step": 40
    },
    {
      "epoch": 0.004371672097936118,
      "grad_norm": 0.13157622516155243,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.8164,
      "step": 41
    },
    {
      "epoch": 0.004478298246666267,
      "grad_norm": 0.13519853353500366,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.8196,
      "step": 42
    },
    {
      "epoch": 0.004584924395396416,
      "grad_norm": 0.14817938208580017,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.8187,
      "step": 43
    },
    {
      "epoch": 0.004691550544126565,
      "grad_norm": 0.15691693127155304,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.8158,
      "step": 44
    },
    {
      "epoch": 0.004798176692856714,
      "grad_norm": 0.1444297581911087,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.8157,
      "step": 45
    },
    {
      "epoch": 0.004904802841586863,
      "grad_norm": 0.1577857881784439,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.8182,
      "step": 46
    },
    {
      "epoch": 0.0050114289903170125,
      "grad_norm": 0.15604552626609802,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.8133,
      "step": 47
    },
    {
      "epoch": 0.0051180551390471625,
      "grad_norm": 0.15347470343112946,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.8167,
      "step": 48
    },
    {
      "epoch": 0.005224681287777312,
      "grad_norm": 0.13201665878295898,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.8135,
      "step": 49
    },
    {
      "epoch": 0.005331307436507461,
      "grad_norm": 0.14732328057289124,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.8147,
      "step": 50
    },
    {
      "epoch": 0.005331307436507461,
      "eval_loss": 10.814597129821777,
      "eval_runtime": 27.1128,
      "eval_samples_per_second": 582.603,
      "eval_steps_per_second": 291.302,
      "step": 50
    },
    {
      "epoch": 0.00543793358523761,
      "grad_norm": 0.14409305155277252,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.8113,
      "step": 51
    },
    {
      "epoch": 0.005544559733967759,
      "grad_norm": 0.1595422625541687,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.8159,
      "step": 52
    },
    {
      "epoch": 0.005651185882697908,
      "grad_norm": 0.16688624024391174,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.8131,
      "step": 53
    },
    {
      "epoch": 0.005757812031428057,
      "grad_norm": 0.1620035171508789,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.8132,
      "step": 54
    },
    {
      "epoch": 0.0058644381801582065,
      "grad_norm": 0.16980452835559845,
      "learning_rate": 5e-05,
      "loss": 10.8129,
      "step": 55
    },
    {
      "epoch": 0.005971064328888356,
      "grad_norm": 0.1535421460866928,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.815,
      "step": 56
    },
    {
      "epoch": 0.006077690477618505,
      "grad_norm": 0.15803158283233643,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.8153,
      "step": 57
    },
    {
      "epoch": 0.006184316626348654,
      "grad_norm": 0.15988963842391968,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.8119,
      "step": 58
    },
    {
      "epoch": 0.006290942775078803,
      "grad_norm": 0.17502981424331665,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.8123,
      "step": 59
    },
    {
      "epoch": 0.006397568923808952,
      "grad_norm": 0.1722036898136139,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.8102,
      "step": 60
    },
    {
      "epoch": 0.006504195072539101,
      "grad_norm": 0.16091673076152802,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.8059,
      "step": 61
    },
    {
      "epoch": 0.006610821221269251,
      "grad_norm": 0.17409998178482056,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.8091,
      "step": 62
    },
    {
      "epoch": 0.0067174473699994006,
      "grad_norm": 0.20849758386611938,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.799,
      "step": 63
    },
    {
      "epoch": 0.00682407351872955,
      "grad_norm": 0.16407425701618195,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.8124,
      "step": 64
    },
    {
      "epoch": 0.006930699667459699,
      "grad_norm": 0.18425709009170532,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.8096,
      "step": 65
    },
    {
      "epoch": 0.007037325816189848,
      "grad_norm": 0.17111074924468994,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.8096,
      "step": 66
    },
    {
      "epoch": 0.007143951964919997,
      "grad_norm": 0.17965374886989594,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.8084,
      "step": 67
    },
    {
      "epoch": 0.007250578113650146,
      "grad_norm": 0.19009314477443695,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.807,
      "step": 68
    },
    {
      "epoch": 0.0073572042623802954,
      "grad_norm": 0.18505646288394928,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.8075,
      "step": 69
    },
    {
      "epoch": 0.007463830411110445,
      "grad_norm": 0.17133325338363647,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.8074,
      "step": 70
    },
    {
      "epoch": 0.007570456559840594,
      "grad_norm": 0.16672495007514954,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.8064,
      "step": 71
    },
    {
      "epoch": 0.007677082708570743,
      "grad_norm": 0.18847358226776123,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.8077,
      "step": 72
    },
    {
      "epoch": 0.007783708857300892,
      "grad_norm": 0.17686216533184052,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.808,
      "step": 73
    },
    {
      "epoch": 0.007890335006031042,
      "grad_norm": 0.1777198761701584,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.8043,
      "step": 74
    },
    {
      "epoch": 0.00799696115476119,
      "grad_norm": 0.17206279933452606,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.8071,
      "step": 75
    },
    {
      "epoch": 0.00799696115476119,
      "eval_loss": 10.805438995361328,
      "eval_runtime": 50.9217,
      "eval_samples_per_second": 310.202,
      "eval_steps_per_second": 155.101,
      "step": 75
    },
    {
      "epoch": 0.00810358730349134,
      "grad_norm": 0.19393402338027954,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.8052,
      "step": 76
    },
    {
      "epoch": 0.008210213452221489,
      "grad_norm": 0.17306220531463623,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.8092,
      "step": 77
    },
    {
      "epoch": 0.008316839600951639,
      "grad_norm": 0.18071946501731873,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.8096,
      "step": 78
    },
    {
      "epoch": 0.008423465749681787,
      "grad_norm": 0.18262875080108643,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.8112,
      "step": 79
    },
    {
      "epoch": 0.008530091898411937,
      "grad_norm": 0.18377819657325745,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.8096,
      "step": 80
    },
    {
      "epoch": 0.008636718047142085,
      "grad_norm": 0.1848413050174713,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.8044,
      "step": 81
    },
    {
      "epoch": 0.008743344195872235,
      "grad_norm": 0.1873786747455597,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.8058,
      "step": 82
    },
    {
      "epoch": 0.008849970344602385,
      "grad_norm": 0.20228584110736847,
      "learning_rate": 8.548121372247918e-06,
      "loss": 10.8059,
      "step": 83
    },
    {
      "epoch": 0.008956596493332534,
      "grad_norm": 0.19265606999397278,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.8088,
      "step": 84
    },
    {
      "epoch": 0.009063222642062684,
      "grad_norm": 0.17763932049274445,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.7996,
      "step": 85
    },
    {
      "epoch": 0.009169848790792832,
      "grad_norm": 0.17844876646995544,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.802,
      "step": 86
    },
    {
      "epoch": 0.009276474939522982,
      "grad_norm": 0.17362311482429504,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.8022,
      "step": 87
    },
    {
      "epoch": 0.00938310108825313,
      "grad_norm": 0.18764075636863708,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.8014,
      "step": 88
    },
    {
      "epoch": 0.00948972723698328,
      "grad_norm": 0.20152869820594788,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 10.8044,
      "step": 89
    },
    {
      "epoch": 0.009596353385713428,
      "grad_norm": 0.19738389551639557,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.8073,
      "step": 90
    },
    {
      "epoch": 0.009702979534443578,
      "grad_norm": 0.19693444669246674,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.7984,
      "step": 91
    },
    {
      "epoch": 0.009809605683173727,
      "grad_norm": 0.20395702123641968,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.801,
      "step": 92
    },
    {
      "epoch": 0.009916231831903877,
      "grad_norm": 0.1859755963087082,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.8075,
      "step": 93
    },
    {
      "epoch": 0.010022857980634025,
      "grad_norm": 0.18670888245105743,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.8028,
      "step": 94
    },
    {
      "epoch": 0.010129484129364175,
      "grad_norm": 0.1718273162841797,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.806,
      "step": 95
    },
    {
      "epoch": 0.010236110278094325,
      "grad_norm": 0.2033439427614212,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.8003,
      "step": 96
    },
    {
      "epoch": 0.010342736426824473,
      "grad_norm": 0.16593502461910248,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 10.8075,
      "step": 97
    },
    {
      "epoch": 0.010449362575554623,
      "grad_norm": 0.1901598572731018,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.8042,
      "step": 98
    },
    {
      "epoch": 0.010555988724284772,
      "grad_norm": 0.1914721131324768,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.8042,
      "step": 99
    },
    {
      "epoch": 0.010662614873014922,
      "grad_norm": 0.19154879450798035,
      "learning_rate": 0.0,
      "loss": 10.8053,
      "step": 100
    },
    {
      "epoch": 0.010662614873014922,
      "eval_loss": 10.803692817687988,
      "eval_runtime": 73.6667,
      "eval_samples_per_second": 214.425,
      "eval_steps_per_second": 107.213,
      "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": 44295971143680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}