{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0121558378411232,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000121558378411232,
      "grad_norm": 1.3522109985351562,
      "learning_rate": 2e-05,
      "loss": 9.0768,
      "step": 1
    },
    {
      "epoch": 0.000121558378411232,
      "eval_loss": 2.5203659534454346,
      "eval_runtime": 130.544,
      "eval_samples_per_second": 26.535,
      "eval_steps_per_second": 13.268,
      "step": 1
    },
    {
      "epoch": 0.000243116756822464,
      "grad_norm": 0.9176049828529358,
      "learning_rate": 4e-05,
      "loss": 8.9894,
      "step": 2
    },
    {
      "epoch": 0.000364675135233696,
      "grad_norm": 1.0146596431732178,
      "learning_rate": 6e-05,
      "loss": 9.935,
      "step": 3
    },
    {
      "epoch": 0.000486233513644928,
      "grad_norm": 1.0469788312911987,
      "learning_rate": 8e-05,
      "loss": 9.3424,
      "step": 4
    },
    {
      "epoch": 0.00060779189205616,
      "grad_norm": 0.8254321813583374,
      "learning_rate": 0.0001,
      "loss": 8.339,
      "step": 5
    },
    {
      "epoch": 0.000729350270467392,
      "grad_norm": 1.032138705253601,
      "learning_rate": 0.00012,
      "loss": 9.6692,
      "step": 6
    },
    {
      "epoch": 0.000850908648878624,
      "grad_norm": 1.692064881324768,
      "learning_rate": 0.00014,
      "loss": 9.8725,
      "step": 7
    },
    {
      "epoch": 0.000972467027289856,
      "grad_norm": 1.5163041353225708,
      "learning_rate": 0.00016,
      "loss": 9.3607,
      "step": 8
    },
    {
      "epoch": 0.001094025405701088,
      "grad_norm": 3.152874231338501,
      "learning_rate": 0.00018,
      "loss": 9.9624,
      "step": 9
    },
    {
      "epoch": 0.00121558378411232,
      "grad_norm": 1.7264574766159058,
      "learning_rate": 0.0002,
      "loss": 10.4001,
      "step": 10
    },
    {
      "epoch": 0.0013371421625235518,
      "grad_norm": 4.396702766418457,
      "learning_rate": 0.0001999863304992469,
      "loss": 8.8946,
      "step": 11
    },
    {
      "epoch": 0.001458700540934784,
      "grad_norm": 1.9022140502929688,
      "learning_rate": 0.00019994532573409262,
      "loss": 10.3819,
      "step": 12
    },
    {
      "epoch": 0.001580258919346016,
      "grad_norm": 2.1845006942749023,
      "learning_rate": 0.00019987699691483048,
      "loss": 9.6356,
      "step": 13
    },
    {
      "epoch": 0.001701817297757248,
      "grad_norm": 2.10140061378479,
      "learning_rate": 0.00019978136272187747,
      "loss": 9.6127,
      "step": 14
    },
    {
      "epoch": 0.0018233756761684798,
      "grad_norm": 2.068610668182373,
      "learning_rate": 0.000199658449300667,
      "loss": 11.08,
      "step": 15
    },
    {
      "epoch": 0.001944934054579712,
      "grad_norm": 3.655803680419922,
      "learning_rate": 0.00019950829025450114,
      "loss": 10.0545,
      "step": 16
    },
    {
      "epoch": 0.002066492432990944,
      "grad_norm": 1.8618426322937012,
      "learning_rate": 0.00019933092663536382,
      "loss": 9.6545,
      "step": 17
    },
    {
      "epoch": 0.002188050811402176,
      "grad_norm": 1.8773517608642578,
      "learning_rate": 0.00019912640693269752,
      "loss": 7.7819,
      "step": 18
    },
    {
      "epoch": 0.002309609189813408,
      "grad_norm": 2.198024272918701,
      "learning_rate": 0.00019889478706014687,
      "loss": 9.8384,
      "step": 19
    },
    {
      "epoch": 0.00243116756822464,
      "grad_norm": 2.1132476329803467,
      "learning_rate": 0.00019863613034027224,
      "loss": 8.5882,
      "step": 20
    },
    {
      "epoch": 0.0025527259466358717,
      "grad_norm": 2.646947145462036,
      "learning_rate": 0.00019835050748723824,
      "loss": 9.4244,
      "step": 21
    },
    {
      "epoch": 0.0026742843250471037,
      "grad_norm": 2.169708728790283,
      "learning_rate": 0.00019803799658748094,
      "loss": 8.9,
      "step": 22
    },
    {
      "epoch": 0.002795842703458336,
      "grad_norm": 4.217128276824951,
      "learning_rate": 0.00019769868307835994,
      "loss": 8.5476,
      "step": 23
    },
    {
      "epoch": 0.002917401081869568,
      "grad_norm": 1.9587572813034058,
      "learning_rate": 0.0001973326597248006,
      "loss": 9.5256,
      "step": 24
    },
    {
      "epoch": 0.0030389594602808,
      "grad_norm": 4.422936916351318,
      "learning_rate": 0.00019694002659393305,
      "loss": 8.403,
      "step": 25
    },
    {
      "epoch": 0.003160517838692032,
      "grad_norm": 1.6125566959381104,
      "learning_rate": 0.00019652089102773488,
      "loss": 9.2696,
      "step": 26
    },
    {
      "epoch": 0.003282076217103264,
      "grad_norm": 1.9092199802398682,
      "learning_rate": 0.00019607536761368484,
      "loss": 9.0772,
      "step": 27
    },
    {
      "epoch": 0.003403634595514496,
      "grad_norm": 3.2192418575286865,
      "learning_rate": 0.00019560357815343577,
      "loss": 9.7968,
      "step": 28
    },
    {
      "epoch": 0.0035251929739257277,
      "grad_norm": 2.5830280780792236,
      "learning_rate": 0.00019510565162951537,
      "loss": 9.7017,
      "step": 29
    },
    {
      "epoch": 0.0036467513523369597,
      "grad_norm": 2.7067151069641113,
      "learning_rate": 0.00019458172417006347,
      "loss": 10.3412,
      "step": 30
    },
    {
      "epoch": 0.0037683097307481916,
      "grad_norm": 3.9291067123413086,
      "learning_rate": 0.00019403193901161613,
      "loss": 9.8539,
      "step": 31
    },
    {
      "epoch": 0.003889868109159424,
      "grad_norm": 1.7529088258743286,
      "learning_rate": 0.0001934564464599461,
      "loss": 8.7478,
      "step": 32
    },
    {
      "epoch": 0.004011426487570656,
      "grad_norm": 1.7117114067077637,
      "learning_rate": 0.00019285540384897073,
      "loss": 8.765,
      "step": 33
    },
    {
      "epoch": 0.004132984865981888,
      "grad_norm": 1.856972575187683,
      "learning_rate": 0.00019222897549773848,
      "loss": 9.777,
      "step": 34
    },
    {
      "epoch": 0.00425454324439312,
      "grad_norm": 2.3596813678741455,
      "learning_rate": 0.00019157733266550575,
      "loss": 9.5862,
      "step": 35
    },
    {
      "epoch": 0.004376101622804352,
      "grad_norm": 2.5083954334259033,
      "learning_rate": 0.00019090065350491626,
      "loss": 9.3247,
      "step": 36
    },
    {
      "epoch": 0.004497660001215584,
      "grad_norm": 1.3706068992614746,
      "learning_rate": 0.00019019912301329592,
      "loss": 9.3214,
      "step": 37
    },
    {
      "epoch": 0.004619218379626816,
      "grad_norm": 1.7020275592803955,
      "learning_rate": 0.00018947293298207635,
      "loss": 8.5611,
      "step": 38
    },
    {
      "epoch": 0.004740776758038048,
      "grad_norm": 1.8647181987762451,
      "learning_rate": 0.0001887222819443612,
      "loss": 9.9951,
      "step": 39
    },
    {
      "epoch": 0.00486233513644928,
      "grad_norm": 2.506580352783203,
      "learning_rate": 0.0001879473751206489,
      "loss": 9.6237,
      "step": 40
    },
    {
      "epoch": 0.0049838935148605115,
      "grad_norm": 1.9629899263381958,
      "learning_rate": 0.00018714842436272773,
      "loss": 9.371,
      "step": 41
    },
    {
      "epoch": 0.0051054518932717435,
      "grad_norm": 2.3143656253814697,
      "learning_rate": 0.00018632564809575742,
      "loss": 9.235,
      "step": 42
    },
    {
      "epoch": 0.005227010271682975,
      "grad_norm": 2.5331368446350098,
      "learning_rate": 0.0001854792712585539,
      "loss": 10.1562,
      "step": 43
    },
    {
      "epoch": 0.005348568650094207,
      "grad_norm": 4.555860996246338,
      "learning_rate": 0.00018460952524209355,
      "loss": 8.2419,
      "step": 44
    },
    {
      "epoch": 0.005470127028505439,
      "grad_norm": 1.6661875247955322,
      "learning_rate": 0.00018371664782625287,
      "loss": 8.2566,
      "step": 45
    },
    {
      "epoch": 0.005591685406916672,
      "grad_norm": 1.7546186447143555,
      "learning_rate": 0.00018280088311480201,
      "loss": 9.1446,
      "step": 46
    },
    {
      "epoch": 0.005713243785327904,
      "grad_norm": 1.751132845878601,
      "learning_rate": 0.00018186248146866927,
      "loss": 8.6259,
      "step": 47
    },
    {
      "epoch": 0.005834802163739136,
      "grad_norm": 2.203023672103882,
      "learning_rate": 0.00018090169943749476,
      "loss": 9.3622,
      "step": 48
    },
    {
      "epoch": 0.005956360542150368,
      "grad_norm": 2.7363836765289307,
      "learning_rate": 0.0001799187996894925,
      "loss": 8.0726,
      "step": 49
    },
    {
      "epoch": 0.0060779189205616,
      "grad_norm": 2.010042905807495,
      "learning_rate": 0.00017891405093963938,
      "loss": 9.8848,
      "step": 50
    },
    {
      "epoch": 0.0060779189205616,
      "eval_loss": 2.22426700592041,
      "eval_runtime": 130.4637,
      "eval_samples_per_second": 26.551,
      "eval_steps_per_second": 13.276,
      "step": 50
    },
    {
      "epoch": 0.006199477298972832,
      "grad_norm": 2.2631587982177734,
      "learning_rate": 0.00017788772787621126,
      "loss": 9.446,
      "step": 51
    },
    {
      "epoch": 0.006321035677384064,
      "grad_norm": 4.675655364990234,
      "learning_rate": 0.00017684011108568592,
      "loss": 9.3449,
      "step": 52
    },
    {
      "epoch": 0.006442594055795296,
      "grad_norm": 1.7152106761932373,
      "learning_rate": 0.0001757714869760335,
      "loss": 9.475,
      "step": 53
    },
    {
      "epoch": 0.006564152434206528,
      "grad_norm": 1.5290554761886597,
      "learning_rate": 0.0001746821476984154,
      "loss": 9.117,
      "step": 54
    },
    {
      "epoch": 0.00668571081261776,
      "grad_norm": 2.0921902656555176,
      "learning_rate": 0.00017357239106731317,
      "loss": 9.5546,
      "step": 55
    },
    {
      "epoch": 0.006807269191028992,
      "grad_norm": 2.1920764446258545,
      "learning_rate": 0.00017244252047910892,
      "loss": 8.953,
      "step": 56
    },
    {
      "epoch": 0.0069288275694402235,
      "grad_norm": 1.7566354274749756,
      "learning_rate": 0.00017129284482913972,
      "loss": 9.6787,
      "step": 57
    },
    {
      "epoch": 0.0070503859478514555,
      "grad_norm": 1.4819419384002686,
      "learning_rate": 0.00017012367842724887,
      "loss": 7.3843,
      "step": 58
    },
    {
      "epoch": 0.007171944326262687,
      "grad_norm": 1.6789450645446777,
      "learning_rate": 0.0001689353409118566,
      "loss": 9.802,
      "step": 59
    },
    {
      "epoch": 0.007293502704673919,
      "grad_norm": 1.282571792602539,
      "learning_rate": 0.00016772815716257412,
      "loss": 7.7288,
      "step": 60
    },
    {
      "epoch": 0.007415061083085151,
      "grad_norm": 2.066798448562622,
      "learning_rate": 0.0001665024572113848,
      "loss": 9.3806,
      "step": 61
    },
    {
      "epoch": 0.007536619461496383,
      "grad_norm": 1.7693638801574707,
      "learning_rate": 0.00016525857615241687,
      "loss": 9.6393,
      "step": 62
    },
    {
      "epoch": 0.007658177839907615,
      "grad_norm": 1.7502071857452393,
      "learning_rate": 0.00016399685405033167,
      "loss": 8.3708,
      "step": 63
    },
    {
      "epoch": 0.007779736218318848,
      "grad_norm": 2.8502800464630127,
      "learning_rate": 0.0001627176358473537,
      "loss": 8.8738,
      "step": 64
    },
    {
      "epoch": 0.00790129459673008,
      "grad_norm": 2.4103214740753174,
      "learning_rate": 0.0001614212712689668,
      "loss": 9.5765,
      "step": 65
    },
    {
      "epoch": 0.008022852975141312,
      "grad_norm": 1.8917535543441772,
      "learning_rate": 0.00016010811472830252,
      "loss": 9.4486,
      "step": 66
    },
    {
      "epoch": 0.008144411353552544,
      "grad_norm": 1.5890737771987915,
      "learning_rate": 0.00015877852522924732,
      "loss": 8.5677,
      "step": 67
    },
    {
      "epoch": 0.008265969731963776,
      "grad_norm": 2.1370444297790527,
      "learning_rate": 0.00015743286626829437,
      "loss": 9.4762,
      "step": 68
    },
    {
      "epoch": 0.008387528110375008,
      "grad_norm": 1.7275190353393555,
      "learning_rate": 0.0001560715057351673,
      "loss": 8.829,
      "step": 69
    },
    {
      "epoch": 0.00850908648878624,
      "grad_norm": 1.7048512697219849,
      "learning_rate": 0.00015469481581224272,
      "loss": 8.8259,
      "step": 70
    },
    {
      "epoch": 0.008630644867197472,
      "grad_norm": 1.903066635131836,
      "learning_rate": 0.0001533031728727994,
      "loss": 9.6929,
      "step": 71
    },
    {
      "epoch": 0.008752203245608704,
      "grad_norm": 1.5013515949249268,
      "learning_rate": 0.00015189695737812152,
      "loss": 8.1273,
      "step": 72
    },
    {
      "epoch": 0.008873761624019936,
      "grad_norm": 1.6483365297317505,
      "learning_rate": 0.0001504765537734844,
      "loss": 8.8742,
      "step": 73
    },
    {
      "epoch": 0.008995320002431167,
      "grad_norm": 1.8312402963638306,
      "learning_rate": 0.00014904235038305083,
      "loss": 8.7848,
      "step": 74
    },
    {
      "epoch": 0.0091168783808424,
      "grad_norm": 1.3816986083984375,
      "learning_rate": 0.00014759473930370736,
      "loss": 8.2036,
      "step": 75
    },
    {
      "epoch": 0.009238436759253631,
      "grad_norm": 2.2364020347595215,
      "learning_rate": 0.0001461341162978688,
      "loss": 10.4628,
      "step": 76
    },
    {
      "epoch": 0.009359995137664863,
      "grad_norm": 1.573431134223938,
      "learning_rate": 0.00014466088068528068,
      "loss": 8.8974,
      "step": 77
    },
    {
      "epoch": 0.009481553516076095,
      "grad_norm": 2.187255859375,
      "learning_rate": 0.00014317543523384928,
      "loss": 8.5312,
      "step": 78
    },
    {
      "epoch": 0.009603111894487327,
      "grad_norm": 2.0174520015716553,
      "learning_rate": 0.00014167818604952906,
      "loss": 8.829,
      "step": 79
    },
    {
      "epoch": 0.00972467027289856,
      "grad_norm": 1.8616173267364502,
      "learning_rate": 0.00014016954246529696,
      "loss": 8.3692,
      "step": 80
    },
    {
      "epoch": 0.009846228651309791,
      "grad_norm": 1.8460533618927002,
      "learning_rate": 0.00013864991692924523,
      "loss": 8.6283,
      "step": 81
    },
    {
      "epoch": 0.009967787029721023,
      "grad_norm": 2.5459718704223633,
      "learning_rate": 0.00013711972489182208,
      "loss": 8.4909,
      "step": 82
    },
    {
      "epoch": 0.010089345408132255,
      "grad_norm": 1.9989314079284668,
      "learning_rate": 0.00013557938469225167,
      "loss": 8.9659,
      "step": 83
    },
    {
      "epoch": 0.010210903786543487,
      "grad_norm": 1.3886724710464478,
      "learning_rate": 0.00013402931744416433,
      "loss": 9.1106,
      "step": 84
    },
    {
      "epoch": 0.010332462164954719,
      "grad_norm": 2.354243040084839,
      "learning_rate": 0.00013246994692046836,
      "loss": 9.2569,
      "step": 85
    },
    {
      "epoch": 0.01045402054336595,
      "grad_norm": 2.085102081298828,
      "learning_rate": 0.00013090169943749476,
      "loss": 8.9907,
      "step": 86
    },
    {
      "epoch": 0.010575578921777183,
      "grad_norm": 1.2773852348327637,
      "learning_rate": 0.0001293250037384465,
      "loss": 8.7438,
      "step": 87
    },
    {
      "epoch": 0.010697137300188415,
      "grad_norm": 1.6545124053955078,
      "learning_rate": 0.00012774029087618446,
      "loss": 8.7085,
      "step": 88
    },
    {
      "epoch": 0.010818695678599647,
      "grad_norm": 2.1138100624084473,
      "learning_rate": 0.00012614799409538198,
      "loss": 8.8577,
      "step": 89
    },
    {
      "epoch": 0.010940254057010879,
      "grad_norm": 1.8220653533935547,
      "learning_rate": 0.00012454854871407994,
      "loss": 9.198,
      "step": 90
    },
    {
      "epoch": 0.011061812435422112,
      "grad_norm": 1.6138783693313599,
      "learning_rate": 0.00012294239200467516,
      "loss": 8.9333,
      "step": 91
    },
    {
      "epoch": 0.011183370813833344,
      "grad_norm": 1.6465097665786743,
      "learning_rate": 0.0001213299630743747,
      "loss": 9.123,
      "step": 92
    },
    {
      "epoch": 0.011304929192244576,
      "grad_norm": 1.7768160104751587,
      "learning_rate": 0.00011971170274514802,
      "loss": 8.6597,
      "step": 93
    },
    {
      "epoch": 0.011426487570655808,
      "grad_norm": 1.6465460062026978,
      "learning_rate": 0.000118088053433211,
      "loss": 9.841,
      "step": 94
    },
    {
      "epoch": 0.01154804594906704,
      "grad_norm": 1.3596290349960327,
      "learning_rate": 0.00011645945902807341,
      "loss": 8.5273,
      "step": 95
    },
    {
      "epoch": 0.011669604327478272,
      "grad_norm": 1.612764596939087,
      "learning_rate": 0.0001148263647711842,
      "loss": 8.4275,
      "step": 96
    },
    {
      "epoch": 0.011791162705889504,
      "grad_norm": 2.3744266033172607,
      "learning_rate": 0.00011318921713420691,
      "loss": 9.6372,
      "step": 97
    },
    {
      "epoch": 0.011912721084300736,
      "grad_norm": 1.4123613834381104,
      "learning_rate": 0.00011154846369695863,
      "loss": 8.4314,
      "step": 98
    },
    {
      "epoch": 0.012034279462711968,
      "grad_norm": 1.9357587099075317,
      "learning_rate": 0.0001099045530250463,
      "loss": 8.7244,
      "step": 99
    },
    {
      "epoch": 0.0121558378411232,
      "grad_norm": 1.6507443189620972,
      "learning_rate": 0.00010825793454723325,
      "loss": 10.0314,
      "step": 100
    },
    {
      "epoch": 0.0121558378411232,
      "eval_loss": 2.20096755027771,
      "eval_runtime": 130.4185,
      "eval_samples_per_second": 26.561,
      "eval_steps_per_second": 13.28,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.873061628346368e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}