{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 50,
  "global_step": 71,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014222222222222223,
      "grad_norm": 0.10009177774190903,
      "learning_rate": 0.0,
      "loss": 0.704937219619751,
      "step": 1
    },
    {
      "epoch": 0.028444444444444446,
      "grad_norm": 0.10451912879943848,
      "learning_rate": 4.5454545454545457e-07,
      "loss": 0.7318670749664307,
      "step": 2
    },
    {
      "epoch": 0.042666666666666665,
      "grad_norm": 0.07928935438394547,
      "learning_rate": 9.090909090909091e-07,
      "loss": 0.6017104387283325,
      "step": 3
    },
    {
      "epoch": 0.05688888888888889,
      "grad_norm": 0.048069290816783905,
      "learning_rate": 1.3636363636363636e-06,
      "loss": 0.6029032468795776,
      "step": 4
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 0.02866927720606327,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 0.5051919221878052,
      "step": 5
    },
    {
      "epoch": 0.08533333333333333,
      "grad_norm": 0.022201435640454292,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 0.5942293405532837,
      "step": 6
    },
    {
      "epoch": 0.09955555555555555,
      "grad_norm": 0.018263086676597595,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 0.5781338214874268,
      "step": 7
    },
    {
      "epoch": 0.11377777777777778,
      "grad_norm": 0.01827927492558956,
      "learning_rate": 3.181818181818182e-06,
      "loss": 0.5180214047431946,
      "step": 8
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.014687157236039639,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 0.5420116186141968,
      "step": 9
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 0.012042663060128689,
      "learning_rate": 4.0909090909090915e-06,
      "loss": 0.5345908403396606,
      "step": 10
    },
    {
      "epoch": 0.15644444444444444,
      "grad_norm": 0.012934447266161442,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.46689414978027344,
      "step": 11
    },
    {
      "epoch": 0.17066666666666666,
      "grad_norm": 0.012295619584619999,
      "learning_rate": 5e-06,
      "loss": 0.5062131881713867,
      "step": 12
    },
    {
      "epoch": 0.18488888888888888,
      "grad_norm": 0.011856353841722012,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 0.5063096880912781,
      "step": 13
    },
    {
      "epoch": 0.1991111111111111,
      "grad_norm": 0.009451798163354397,
      "learning_rate": 5.90909090909091e-06,
      "loss": 0.5130602121353149,
      "step": 14
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 0.01111016795039177,
      "learning_rate": 6.363636363636364e-06,
      "loss": 0.5016045570373535,
      "step": 15
    },
    {
      "epoch": 0.22755555555555557,
      "grad_norm": 0.010735263116657734,
      "learning_rate": 6.818181818181818e-06,
      "loss": 0.49827253818511963,
      "step": 16
    },
    {
      "epoch": 0.24177777777777779,
      "grad_norm": 0.010710126720368862,
      "learning_rate": 7.272727272727273e-06,
      "loss": 0.479993999004364,
      "step": 17
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.009600787423551083,
      "learning_rate": 7.727272727272727e-06,
      "loss": 0.4925128221511841,
      "step": 18
    },
    {
      "epoch": 0.2702222222222222,
      "grad_norm": 0.010486789979040623,
      "learning_rate": 8.181818181818183e-06,
      "loss": 0.5188871622085571,
      "step": 19
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 0.013396799564361572,
      "learning_rate": 8.636363636363637e-06,
      "loss": 0.5192517042160034,
      "step": 20
    },
    {
      "epoch": 0.2986666666666667,
      "grad_norm": 0.009299715980887413,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.4580157399177551,
      "step": 21
    },
    {
      "epoch": 0.3128888888888889,
      "grad_norm": 0.009691477753221989,
      "learning_rate": 9.545454545454547e-06,
      "loss": 0.49455106258392334,
      "step": 22
    },
    {
      "epoch": 0.32711111111111113,
      "grad_norm": 0.008896945044398308,
      "learning_rate": 1e-05,
      "loss": 0.48672014474868774,
      "step": 23
    },
    {
      "epoch": 0.3413333333333333,
      "grad_norm": 0.009234798140823841,
      "learning_rate": 9.999323662872998e-06,
      "loss": 0.5052967071533203,
      "step": 24
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.009167873300611973,
      "learning_rate": 9.99729483446475e-06,
      "loss": 0.4740435779094696,
      "step": 25
    },
    {
      "epoch": 0.36977777777777776,
      "grad_norm": 0.009001555852591991,
      "learning_rate": 9.993914063644053e-06,
      "loss": 0.47315946221351624,
      "step": 26
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.00915393978357315,
      "learning_rate": 9.989182265027232e-06,
      "loss": 0.4557237923145294,
      "step": 27
    },
    {
      "epoch": 0.3982222222222222,
      "grad_norm": 0.008505849167704582,
      "learning_rate": 9.98310071873072e-06,
      "loss": 0.46317678689956665,
      "step": 28
    },
    {
      "epoch": 0.41244444444444445,
      "grad_norm": 0.008668503724038601,
      "learning_rate": 9.975671070024741e-06,
      "loss": 0.4533114433288574,
      "step": 29
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 0.009284070692956448,
      "learning_rate": 9.966895328888195e-06,
      "loss": 0.5624005794525146,
      "step": 30
    },
    {
      "epoch": 0.4408888888888889,
      "grad_norm": 0.00935022346675396,
      "learning_rate": 9.956775869464901e-06,
      "loss": 0.4420597553253174,
      "step": 31
    },
    {
      "epoch": 0.45511111111111113,
      "grad_norm": 0.008682326413691044,
      "learning_rate": 9.945315429421307e-06,
      "loss": 0.4745720624923706,
      "step": 32
    },
    {
      "epoch": 0.4693333333333333,
      "grad_norm": 0.007816251367330551,
      "learning_rate": 9.932517109205849e-06,
      "loss": 0.439736545085907,
      "step": 33
    },
    {
      "epoch": 0.48355555555555557,
      "grad_norm": 0.009315130300819874,
      "learning_rate": 9.918384371210178e-06,
      "loss": 0.5357447862625122,
      "step": 34
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 0.009141312912106514,
      "learning_rate": 9.902921038832456e-06,
      "loss": 0.519463062286377,
      "step": 35
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.008826862089335918,
      "learning_rate": 9.886131295443003e-06,
      "loss": 0.48377716541290283,
      "step": 36
    },
    {
      "epoch": 0.5262222222222223,
      "grad_norm": 0.008700878359377384,
      "learning_rate": 9.868019683252543e-06,
      "loss": 0.48436683416366577,
      "step": 37
    },
    {
      "epoch": 0.5404444444444444,
      "grad_norm": 0.011412105523049831,
      "learning_rate": 9.848591102083375e-06,
      "loss": 0.4949312210083008,
      "step": 38
    },
    {
      "epoch": 0.5546666666666666,
      "grad_norm": 0.009214675053954124,
      "learning_rate": 9.82785080804381e-06,
      "loss": 0.4901079535484314,
      "step": 39
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 0.01163570862263441,
      "learning_rate": 9.805804412106197e-06,
      "loss": 0.6070311665534973,
      "step": 40
    },
    {
      "epoch": 0.5831111111111111,
      "grad_norm": 0.009325762279331684,
      "learning_rate": 9.782457878588977e-06,
      "loss": 0.48412975668907166,
      "step": 41
    },
    {
      "epoch": 0.5973333333333334,
      "grad_norm": 0.008266489021480083,
      "learning_rate": 9.75781752354311e-06,
      "loss": 0.4440661072731018,
      "step": 42
    },
    {
      "epoch": 0.6115555555555555,
      "grad_norm": 0.00843313243240118,
      "learning_rate": 9.731890013043367e-06,
      "loss": 0.502442479133606,
      "step": 43
    },
    {
      "epoch": 0.6257777777777778,
      "grad_norm": 0.00934070535004139,
      "learning_rate": 9.704682361384941e-06,
      "loss": 0.47924768924713135,
      "step": 44
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.010360248386859894,
      "learning_rate": 9.676201929185809e-06,
      "loss": 0.4161364436149597,
      "step": 45
    },
    {
      "epoch": 0.6542222222222223,
      "grad_norm": 0.0094041982665658,
      "learning_rate": 9.646456421395447e-06,
      "loss": 0.48306071758270264,
      "step": 46
    },
    {
      "epoch": 0.6684444444444444,
      "grad_norm": 0.009070150554180145,
      "learning_rate": 9.615453885210368e-06,
      "loss": 0.4774249792098999,
      "step": 47
    },
    {
      "epoch": 0.6826666666666666,
      "grad_norm": 0.009771023876965046,
      "learning_rate": 9.583202707897075e-06,
      "loss": 0.4948921203613281,
      "step": 48
    },
    {
      "epoch": 0.6968888888888889,
      "grad_norm": 0.008749130181968212,
      "learning_rate": 9.549711614523007e-06,
      "loss": 0.4825429916381836,
      "step": 49
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.007630312815308571,
      "learning_rate": 9.514989665596114e-06,
      "loss": 0.46055319905281067,
      "step": 50
    },
    {
      "epoch": 0.7111111111111111,
      "eval_loss": 0.48781517148017883,
      "eval_runtime": 4.5903,
      "eval_samples_per_second": 43.57,
      "eval_steps_per_second": 21.785,
      "step": 50
    },
    {
      "epoch": 0.7253333333333334,
      "grad_norm": 0.008408056572079659,
      "learning_rate": 9.479046254613673e-06,
      "loss": 0.4626312255859375,
      "step": 51
    },
    {
      "epoch": 0.7395555555555555,
      "grad_norm": 0.007699670735746622,
      "learning_rate": 9.441891105521005e-06,
      "loss": 0.4499070644378662,
      "step": 52
    },
    {
      "epoch": 0.7537777777777778,
      "grad_norm": 0.009070169180631638,
      "learning_rate": 9.40353427008083e-06,
      "loss": 0.4825657606124878,
      "step": 53
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.007915646769106388,
      "learning_rate": 9.3639861251539e-06,
      "loss": 0.4534468650817871,
      "step": 54
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 0.011336776427924633,
      "learning_rate": 9.323257369891702e-06,
      "loss": 0.4988631010055542,
      "step": 55
    },
    {
      "epoch": 0.7964444444444444,
      "grad_norm": 0.00761911366134882,
      "learning_rate": 9.281359022841966e-06,
      "loss": 0.4371437728404999,
      "step": 56
    },
    {
      "epoch": 0.8106666666666666,
      "grad_norm": 0.009316994808614254,
      "learning_rate": 9.238302418967757e-06,
      "loss": 0.4956932067871094,
      "step": 57
    },
    {
      "epoch": 0.8248888888888889,
      "grad_norm": 0.009821794927120209,
      "learning_rate": 9.194099206580981e-06,
      "loss": 0.5392974615097046,
      "step": 58
    },
    {
      "epoch": 0.8391111111111111,
      "grad_norm": 0.008422416634857655,
      "learning_rate": 9.14876134419111e-06,
      "loss": 0.47983357310295105,
      "step": 59
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 0.00837004091590643,
      "learning_rate": 9.102301097269974e-06,
      "loss": 0.5183510780334473,
      "step": 60
    },
    {
      "epoch": 0.8675555555555555,
      "grad_norm": 0.008596297353506088,
      "learning_rate": 9.05473103493355e-06,
      "loss": 0.47292786836624146,
      "step": 61
    },
    {
      "epoch": 0.8817777777777778,
      "grad_norm": 0.009059637784957886,
      "learning_rate": 9.006064026541549e-06,
      "loss": 0.5188573598861694,
      "step": 62
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.007816917262971401,
      "learning_rate": 8.956313238215824e-06,
      "loss": 0.45641395449638367,
      "step": 63
    },
    {
      "epoch": 0.9102222222222223,
      "grad_norm": 0.007985202595591545,
      "learning_rate": 8.905492129278478e-06,
      "loss": 0.4586361050605774,
      "step": 64
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 0.007170964498072863,
      "learning_rate": 8.85361444861063e-06,
      "loss": 0.4394378066062927,
      "step": 65
    },
    {
      "epoch": 0.9386666666666666,
      "grad_norm": 0.00909162126481533,
      "learning_rate": 8.800694230932885e-06,
      "loss": 0.509820818901062,
      "step": 66
    },
    {
      "epoch": 0.9528888888888889,
      "grad_norm": 0.00786044355481863,
      "learning_rate": 8.74674579300843e-06,
      "loss": 0.43584880232810974,
      "step": 67
    },
    {
      "epoch": 0.9671111111111111,
      "grad_norm": 0.00832363311201334,
      "learning_rate": 8.691783729769874e-06,
      "loss": 0.4317135214805603,
      "step": 68
    },
    {
      "epoch": 0.9813333333333333,
      "grad_norm": 0.008376957848668098,
      "learning_rate": 8.635822910370793e-06,
      "loss": 0.49933016300201416,
      "step": 69
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 0.00835558120161295,
      "learning_rate": 8.578878474163115e-06,
      "loss": 0.46570393443107605,
      "step": 70
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.013256405480206013,
      "learning_rate": 8.520965826601394e-06,
      "loss": 0.45107918977737427,
      "step": 71
    }
  ],
  "logging_steps": 1,
  "max_steps": 213,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6226691949002752e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}