{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2178649237472767,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002178649237472767,
      "grad_norm": 0.9198092818260193,
      "learning_rate": 1e-05,
      "loss": 2.7151,
      "step": 1
    },
    {
      "epoch": 0.002178649237472767,
      "eval_loss": 1.4438984394073486,
      "eval_runtime": 63.6435,
      "eval_samples_per_second": 6.081,
      "eval_steps_per_second": 0.77,
      "step": 1
    },
    {
      "epoch": 0.004357298474945534,
      "grad_norm": 0.9449625611305237,
      "learning_rate": 2e-05,
      "loss": 2.8151,
      "step": 2
    },
    {
      "epoch": 0.006535947712418301,
      "grad_norm": 0.9119125604629517,
      "learning_rate": 3e-05,
      "loss": 2.9119,
      "step": 3
    },
    {
      "epoch": 0.008714596949891068,
      "grad_norm": 0.9674502015113831,
      "learning_rate": 4e-05,
      "loss": 2.8157,
      "step": 4
    },
    {
      "epoch": 0.010893246187363835,
      "grad_norm": 0.9883757829666138,
      "learning_rate": 5e-05,
      "loss": 2.8768,
      "step": 5
    },
    {
      "epoch": 0.013071895424836602,
      "grad_norm": 0.9771690964698792,
      "learning_rate": 6e-05,
      "loss": 3.1472,
      "step": 6
    },
    {
      "epoch": 0.015250544662309368,
      "grad_norm": 1.2254856824874878,
      "learning_rate": 7e-05,
      "loss": 2.7488,
      "step": 7
    },
    {
      "epoch": 0.017429193899782137,
      "grad_norm": 1.9455372095108032,
      "learning_rate": 8e-05,
      "loss": 2.615,
      "step": 8
    },
    {
      "epoch": 0.0196078431372549,
      "grad_norm": 1.188912034034729,
      "learning_rate": 9e-05,
      "loss": 2.6818,
      "step": 9
    },
    {
      "epoch": 0.0196078431372549,
      "eval_loss": 1.2748327255249023,
      "eval_runtime": 63.6623,
      "eval_samples_per_second": 6.079,
      "eval_steps_per_second": 0.77,
      "step": 9
    },
    {
      "epoch": 0.02178649237472767,
      "grad_norm": 1.1046169996261597,
      "learning_rate": 0.0001,
      "loss": 2.4862,
      "step": 10
    },
    {
      "epoch": 0.023965141612200435,
      "grad_norm": 1.140702247619629,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.6588,
      "step": 11
    },
    {
      "epoch": 0.026143790849673203,
      "grad_norm": 1.100024938583374,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.3629,
      "step": 12
    },
    {
      "epoch": 0.02832244008714597,
      "grad_norm": 1.133280873298645,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.309,
      "step": 13
    },
    {
      "epoch": 0.030501089324618737,
      "grad_norm": 1.1353580951690674,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.401,
      "step": 14
    },
    {
      "epoch": 0.032679738562091505,
      "grad_norm": 1.2960582971572876,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.298,
      "step": 15
    },
    {
      "epoch": 0.034858387799564274,
      "grad_norm": 1.2568838596343994,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.2967,
      "step": 16
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 1.2687550783157349,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.9983,
      "step": 17
    },
    {
      "epoch": 0.0392156862745098,
      "grad_norm": 1.3108571767807007,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.1777,
      "step": 18
    },
    {
      "epoch": 0.0392156862745098,
      "eval_loss": 1.0612674951553345,
      "eval_runtime": 63.6208,
      "eval_samples_per_second": 6.083,
      "eval_steps_per_second": 0.77,
      "step": 18
    },
    {
      "epoch": 0.04139433551198257,
      "grad_norm": 1.2421090602874756,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.1237,
      "step": 19
    },
    {
      "epoch": 0.04357298474945534,
      "grad_norm": 1.2717667818069458,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.0674,
      "step": 20
    },
    {
      "epoch": 0.0457516339869281,
      "grad_norm": 1.5267056226730347,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.2134,
      "step": 21
    },
    {
      "epoch": 0.04793028322440087,
      "grad_norm": 1.3219244480133057,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.0757,
      "step": 22
    },
    {
      "epoch": 0.05010893246187364,
      "grad_norm": 2.458014488220215,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.1298,
      "step": 23
    },
    {
      "epoch": 0.05228758169934641,
      "grad_norm": 1.3178763389587402,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.976,
      "step": 24
    },
    {
      "epoch": 0.054466230936819175,
      "grad_norm": 1.464354395866394,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.1124,
      "step": 25
    },
    {
      "epoch": 0.05664488017429194,
      "grad_norm": 3.1391263008117676,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.0881,
      "step": 26
    },
    {
      "epoch": 0.058823529411764705,
      "grad_norm": 1.312290906906128,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.8875,
      "step": 27
    },
    {
      "epoch": 0.058823529411764705,
      "eval_loss": 1.0010426044464111,
      "eval_runtime": 63.6531,
      "eval_samples_per_second": 6.08,
      "eval_steps_per_second": 0.77,
      "step": 27
    },
    {
      "epoch": 0.06100217864923747,
      "grad_norm": 1.45926833152771,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.1062,
      "step": 28
    },
    {
      "epoch": 0.06318082788671024,
      "grad_norm": 1.319545030593872,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.8661,
      "step": 29
    },
    {
      "epoch": 0.06535947712418301,
      "grad_norm": 1.4982140064239502,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.9231,
      "step": 30
    },
    {
      "epoch": 0.06753812636165578,
      "grad_norm": 1.494714379310608,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.8508,
      "step": 31
    },
    {
      "epoch": 0.06971677559912855,
      "grad_norm": 1.421554684638977,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.9356,
      "step": 32
    },
    {
      "epoch": 0.0718954248366013,
      "grad_norm": 1.840808391571045,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.8936,
      "step": 33
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 1.348752737045288,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.9958,
      "step": 34
    },
    {
      "epoch": 0.07625272331154684,
      "grad_norm": 1.445092797279358,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.9379,
      "step": 35
    },
    {
      "epoch": 0.0784313725490196,
      "grad_norm": 1.3066115379333496,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.152,
      "step": 36
    },
    {
      "epoch": 0.0784313725490196,
      "eval_loss": 0.9629685282707214,
      "eval_runtime": 63.6264,
      "eval_samples_per_second": 6.082,
      "eval_steps_per_second": 0.77,
      "step": 36
    },
    {
      "epoch": 0.08061002178649238,
      "grad_norm": 1.3450731039047241,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.8907,
      "step": 37
    },
    {
      "epoch": 0.08278867102396514,
      "grad_norm": 1.2317782640457153,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.6973,
      "step": 38
    },
    {
      "epoch": 0.08496732026143791,
      "grad_norm": 1.4453401565551758,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.882,
      "step": 39
    },
    {
      "epoch": 0.08714596949891068,
      "grad_norm": 1.2838209867477417,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.0322,
      "step": 40
    },
    {
      "epoch": 0.08932461873638345,
      "grad_norm": 1.446647047996521,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.8212,
      "step": 41
    },
    {
      "epoch": 0.0915032679738562,
      "grad_norm": 1.3220431804656982,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.9573,
      "step": 42
    },
    {
      "epoch": 0.09368191721132897,
      "grad_norm": 1.4899321794509888,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.0206,
      "step": 43
    },
    {
      "epoch": 0.09586056644880174,
      "grad_norm": 1.4026318788528442,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.9114,
      "step": 44
    },
    {
      "epoch": 0.09803921568627451,
      "grad_norm": 1.5946420431137085,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.8127,
      "step": 45
    },
    {
      "epoch": 0.09803921568627451,
      "eval_loss": 0.936172366142273,
      "eval_runtime": 63.6149,
      "eval_samples_per_second": 6.083,
      "eval_steps_per_second": 0.77,
      "step": 45
    },
    {
      "epoch": 0.10021786492374728,
      "grad_norm": 1.2588008642196655,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.8878,
      "step": 46
    },
    {
      "epoch": 0.10239651416122005,
      "grad_norm": 1.3478667736053467,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.9031,
      "step": 47
    },
    {
      "epoch": 0.10457516339869281,
      "grad_norm": 1.408197045326233,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.0725,
      "step": 48
    },
    {
      "epoch": 0.10675381263616558,
      "grad_norm": 1.3039942979812622,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.7085,
      "step": 49
    },
    {
      "epoch": 0.10893246187363835,
      "grad_norm": 1.3145512342453003,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.8257,
      "step": 50
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 1.3988362550735474,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.8748,
      "step": 51
    },
    {
      "epoch": 0.11328976034858387,
      "grad_norm": 1.3726601600646973,
      "learning_rate": 5.522642316338268e-05,
      "loss": 2.0158,
      "step": 52
    },
    {
      "epoch": 0.11546840958605664,
      "grad_norm": 1.333004355430603,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.8631,
      "step": 53
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 1.4668630361557007,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.8015,
      "step": 54
    },
    {
      "epoch": 0.11764705882352941,
      "eval_loss": 0.9176331162452698,
      "eval_runtime": 63.6089,
      "eval_samples_per_second": 6.084,
      "eval_steps_per_second": 0.77,
      "step": 54
    },
    {
      "epoch": 0.11982570806100218,
      "grad_norm": 1.4083083868026733,
      "learning_rate": 5e-05,
      "loss": 1.8677,
      "step": 55
    },
    {
      "epoch": 0.12200435729847495,
      "grad_norm": 1.4715665578842163,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.847,
      "step": 56
    },
    {
      "epoch": 0.12418300653594772,
      "grad_norm": 1.4060428142547607,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.6689,
      "step": 57
    },
    {
      "epoch": 0.12636165577342048,
      "grad_norm": 1.4863489866256714,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.7699,
      "step": 58
    },
    {
      "epoch": 0.12854030501089325,
      "grad_norm": 1.3359904289245605,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.9346,
      "step": 59
    },
    {
      "epoch": 0.13071895424836602,
      "grad_norm": 1.452951431274414,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.978,
      "step": 60
    },
    {
      "epoch": 0.1328976034858388,
      "grad_norm": 1.3285267353057861,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.6478,
      "step": 61
    },
    {
      "epoch": 0.13507625272331156,
      "grad_norm": 1.4526207447052002,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.8832,
      "step": 62
    },
    {
      "epoch": 0.13725490196078433,
      "grad_norm": 1.3983100652694702,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.8115,
      "step": 63
    },
    {
      "epoch": 0.13725490196078433,
      "eval_loss": 0.9005686640739441,
      "eval_runtime": 63.6036,
      "eval_samples_per_second": 6.085,
      "eval_steps_per_second": 0.77,
      "step": 63
    },
    {
      "epoch": 0.1394335511982571,
      "grad_norm": 1.3702726364135742,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.9095,
      "step": 64
    },
    {
      "epoch": 0.14161220043572983,
      "grad_norm": 1.2157334089279175,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.6402,
      "step": 65
    },
    {
      "epoch": 0.1437908496732026,
      "grad_norm": 1.388006567955017,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.7927,
      "step": 66
    },
    {
      "epoch": 0.14596949891067537,
      "grad_norm": 1.4038636684417725,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.7986,
      "step": 67
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 1.4844595193862915,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.9496,
      "step": 68
    },
    {
      "epoch": 0.1503267973856209,
      "grad_norm": 1.5678737163543701,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.9151,
      "step": 69
    },
    {
      "epoch": 0.15250544662309368,
      "grad_norm": 1.5263280868530273,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.9183,
      "step": 70
    },
    {
      "epoch": 0.15468409586056645,
      "grad_norm": 1.4814729690551758,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.7335,
      "step": 71
    },
    {
      "epoch": 0.1568627450980392,
      "grad_norm": 1.6117812395095825,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.8991,
      "step": 72
    },
    {
      "epoch": 0.1568627450980392,
      "eval_loss": 0.8903294205665588,
      "eval_runtime": 63.6061,
      "eval_samples_per_second": 6.084,
      "eval_steps_per_second": 0.77,
      "step": 72
    },
    {
      "epoch": 0.15904139433551198,
      "grad_norm": 1.336901307106018,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.5583,
      "step": 73
    },
    {
      "epoch": 0.16122004357298475,
      "grad_norm": 1.5692085027694702,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.8606,
      "step": 74
    },
    {
      "epoch": 0.16339869281045752,
      "grad_norm": 1.4867205619812012,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.8198,
      "step": 75
    },
    {
      "epoch": 0.1655773420479303,
      "grad_norm": 1.8424410820007324,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.7089,
      "step": 76
    },
    {
      "epoch": 0.16775599128540306,
      "grad_norm": 1.5348371267318726,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.8777,
      "step": 77
    },
    {
      "epoch": 0.16993464052287582,
      "grad_norm": 1.4218686819076538,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.8016,
      "step": 78
    },
    {
      "epoch": 0.1721132897603486,
      "grad_norm": 1.4566261768341064,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 1.7037,
      "step": 79
    },
    {
      "epoch": 0.17429193899782136,
      "grad_norm": 1.4800132513046265,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.7889,
      "step": 80
    },
    {
      "epoch": 0.17647058823529413,
      "grad_norm": 1.4129917621612549,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.8648,
      "step": 81
    },
    {
      "epoch": 0.17647058823529413,
      "eval_loss": 0.884328305721283,
      "eval_runtime": 63.6367,
      "eval_samples_per_second": 6.081,
      "eval_steps_per_second": 0.77,
      "step": 81
    },
    {
      "epoch": 0.1786492374727669,
      "grad_norm": 2.1455793380737305,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.9025,
      "step": 82
    },
    {
      "epoch": 0.18082788671023964,
      "grad_norm": 1.6186474561691284,
      "learning_rate": 8.548121372247918e-06,
      "loss": 2.0026,
      "step": 83
    },
    {
      "epoch": 0.1830065359477124,
      "grad_norm": 1.6770442724227905,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.9087,
      "step": 84
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 1.7015310525894165,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.9845,
      "step": 85
    },
    {
      "epoch": 0.18736383442265794,
      "grad_norm": 1.4738478660583496,
      "learning_rate": 5.852620357053651e-06,
      "loss": 1.8843,
      "step": 86
    },
    {
      "epoch": 0.1895424836601307,
      "grad_norm": 1.548987627029419,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.9916,
      "step": 87
    },
    {
      "epoch": 0.19172113289760348,
      "grad_norm": 1.4082995653152466,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.7131,
      "step": 88
    },
    {
      "epoch": 0.19389978213507625,
      "grad_norm": 1.434032678604126,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 1.8378,
      "step": 89
    },
    {
      "epoch": 0.19607843137254902,
      "grad_norm": 1.4525424242019653,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.606,
      "step": 90
    },
    {
      "epoch": 0.19607843137254902,
      "eval_loss": 0.8813257217407227,
      "eval_runtime": 63.7104,
      "eval_samples_per_second": 6.074,
      "eval_steps_per_second": 0.769,
      "step": 90
    },
    {
      "epoch": 0.19825708061002179,
      "grad_norm": 1.4912457466125488,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.6441,
      "step": 91
    },
    {
      "epoch": 0.20043572984749455,
      "grad_norm": 1.4377028942108154,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.8356,
      "step": 92
    },
    {
      "epoch": 0.20261437908496732,
      "grad_norm": 1.555307388305664,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.7871,
      "step": 93
    },
    {
      "epoch": 0.2047930283224401,
      "grad_norm": 1.4429875612258911,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.716,
      "step": 94
    },
    {
      "epoch": 0.20697167755991286,
      "grad_norm": 1.669837236404419,
      "learning_rate": 7.596123493895991e-07,
      "loss": 1.7517,
      "step": 95
    },
    {
      "epoch": 0.20915032679738563,
      "grad_norm": 1.4851337671279907,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.7941,
      "step": 96
    },
    {
      "epoch": 0.2113289760348584,
      "grad_norm": 1.3839343786239624,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 1.7239,
      "step": 97
    },
    {
      "epoch": 0.21350762527233116,
      "grad_norm": 1.7010775804519653,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 1.8666,
      "step": 98
    },
    {
      "epoch": 0.21568627450980393,
      "grad_norm": 1.3769611120224,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.6545,
      "step": 99
    },
    {
      "epoch": 0.21568627450980393,
      "eval_loss": 0.8808857798576355,
      "eval_runtime": 63.6882,
      "eval_samples_per_second": 6.076,
      "eval_steps_per_second": 0.769,
      "step": 99
    },
    {
      "epoch": 0.2178649237472767,
      "grad_norm": 1.4309481382369995,
      "learning_rate": 0.0,
      "loss": 1.7055,
      "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": 1.294949098192896e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}