{
  "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": 0.09173738956451416,
      "learning_rate": 0.0,
      "loss": 1.005206823348999,
      "step": 1
    },
    {
      "epoch": 0.028444444444444446,
      "grad_norm": 0.09365915507078171,
      "learning_rate": 4.5454545454545457e-07,
      "loss": 1.0057916641235352,
      "step": 2
    },
    {
      "epoch": 0.042666666666666665,
      "grad_norm": 0.0689043328166008,
      "learning_rate": 9.090909090909091e-07,
      "loss": 0.9406883716583252,
      "step": 3
    },
    {
      "epoch": 0.05688888888888889,
      "grad_norm": 0.04593552276492119,
      "learning_rate": 1.3636363636363636e-06,
      "loss": 0.8941981792449951,
      "step": 4
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 0.03204488381743431,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 0.7926980257034302,
      "step": 5
    },
    {
      "epoch": 0.08533333333333333,
      "grad_norm": 0.027753565460443497,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 0.8305954933166504,
      "step": 6
    },
    {
      "epoch": 0.09955555555555555,
      "grad_norm": 0.03171968460083008,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 0.7948952913284302,
      "step": 7
    },
    {
      "epoch": 0.11377777777777778,
      "grad_norm": 0.026748575270175934,
      "learning_rate": 3.181818181818182e-06,
      "loss": 0.7530462741851807,
      "step": 8
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.023413579910993576,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 0.7157606482505798,
      "step": 9
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 0.020688239485025406,
      "learning_rate": 4.0909090909090915e-06,
      "loss": 0.7008587718009949,
      "step": 10
    },
    {
      "epoch": 0.15644444444444444,
      "grad_norm": 0.014185823500156403,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.6668463945388794,
      "step": 11
    },
    {
      "epoch": 0.17066666666666666,
      "grad_norm": 0.012938937172293663,
      "learning_rate": 5e-06,
      "loss": 0.6507903337478638,
      "step": 12
    },
    {
      "epoch": 0.18488888888888888,
      "grad_norm": 0.012045802548527718,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 0.6217454671859741,
      "step": 13
    },
    {
      "epoch": 0.1991111111111111,
      "grad_norm": 0.009660671465098858,
      "learning_rate": 5.90909090909091e-06,
      "loss": 0.6269917488098145,
      "step": 14
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 0.008694784715771675,
      "learning_rate": 6.363636363636364e-06,
      "loss": 0.5836964845657349,
      "step": 15
    },
    {
      "epoch": 0.22755555555555557,
      "grad_norm": 0.008789200335741043,
      "learning_rate": 6.818181818181818e-06,
      "loss": 0.6187424659729004,
      "step": 16
    },
    {
      "epoch": 0.24177777777777779,
      "grad_norm": 0.008197025395929813,
      "learning_rate": 7.272727272727273e-06,
      "loss": 0.5914188027381897,
      "step": 17
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.007580601144582033,
      "learning_rate": 7.727272727272727e-06,
      "loss": 0.5802223682403564,
      "step": 18
    },
    {
      "epoch": 0.2702222222222222,
      "grad_norm": 0.007013861555606127,
      "learning_rate": 8.181818181818183e-06,
      "loss": 0.5884265899658203,
      "step": 19
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 0.00683254050090909,
      "learning_rate": 8.636363636363637e-06,
      "loss": 0.5850374698638916,
      "step": 20
    },
    {
      "epoch": 0.2986666666666667,
      "grad_norm": 0.006111981347203255,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.5651419162750244,
      "step": 21
    },
    {
      "epoch": 0.3128888888888889,
      "grad_norm": 0.005564771592617035,
      "learning_rate": 9.545454545454547e-06,
      "loss": 0.553795576095581,
      "step": 22
    },
    {
      "epoch": 0.32711111111111113,
      "grad_norm": 0.0057683708146214485,
      "learning_rate": 1e-05,
      "loss": 0.5542658567428589,
      "step": 23
    },
    {
      "epoch": 0.3413333333333333,
      "grad_norm": 0.006690182723104954,
      "learning_rate": 9.999323662872998e-06,
      "loss": 0.5586982369422913,
      "step": 24
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.006314165890216827,
      "learning_rate": 9.99729483446475e-06,
      "loss": 0.5584714412689209,
      "step": 25
    },
    {
      "epoch": 0.36977777777777776,
      "grad_norm": 0.005813857074826956,
      "learning_rate": 9.993914063644053e-06,
      "loss": 0.5466614961624146,
      "step": 26
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.005381743889302015,
      "learning_rate": 9.989182265027232e-06,
      "loss": 0.5380265712738037,
      "step": 27
    },
    {
      "epoch": 0.3982222222222222,
      "grad_norm": 0.0049252682365477085,
      "learning_rate": 9.98310071873072e-06,
      "loss": 0.535520613193512,
      "step": 28
    },
    {
      "epoch": 0.41244444444444445,
      "grad_norm": 0.0048560877330601215,
      "learning_rate": 9.975671070024741e-06,
      "loss": 0.5377035140991211,
      "step": 29
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 0.004911178257316351,
      "learning_rate": 9.966895328888195e-06,
      "loss": 0.5570093989372253,
      "step": 30
    },
    {
      "epoch": 0.4408888888888889,
      "grad_norm": 0.004746970720589161,
      "learning_rate": 9.956775869464901e-06,
      "loss": 0.5285611748695374,
      "step": 31
    },
    {
      "epoch": 0.45511111111111113,
      "grad_norm": 0.0047261337749660015,
      "learning_rate": 9.945315429421307e-06,
      "loss": 0.5199858546257019,
      "step": 32
    },
    {
      "epoch": 0.4693333333333333,
      "grad_norm": 0.004447608254849911,
      "learning_rate": 9.932517109205849e-06,
      "loss": 0.5250071287155151,
      "step": 33
    },
    {
      "epoch": 0.48355555555555557,
      "grad_norm": 0.004617375787347555,
      "learning_rate": 9.918384371210178e-06,
      "loss": 0.5516105890274048,
      "step": 34
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 0.004378544166684151,
      "learning_rate": 9.902921038832456e-06,
      "loss": 0.5298895835876465,
      "step": 35
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.004164176061749458,
      "learning_rate": 9.886131295443003e-06,
      "loss": 0.5044555068016052,
      "step": 36
    },
    {
      "epoch": 0.5262222222222223,
      "grad_norm": 0.004092546179890633,
      "learning_rate": 9.868019683252543e-06,
      "loss": 0.5102939009666443,
      "step": 37
    },
    {
      "epoch": 0.5404444444444444,
      "grad_norm": 0.004554086830466986,
      "learning_rate": 9.848591102083375e-06,
      "loss": 0.5421494245529175,
      "step": 38
    },
    {
      "epoch": 0.5546666666666666,
      "grad_norm": 0.004217132460325956,
      "learning_rate": 9.82785080804381e-06,
      "loss": 0.5239347219467163,
      "step": 39
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 0.004286583047360182,
      "learning_rate": 9.805804412106197e-06,
      "loss": 0.5437066555023193,
      "step": 40
    },
    {
      "epoch": 0.5831111111111111,
      "grad_norm": 0.004261231981217861,
      "learning_rate": 9.782457878588977e-06,
      "loss": 0.5146951079368591,
      "step": 41
    },
    {
      "epoch": 0.5973333333333334,
      "grad_norm": 0.004209685139358044,
      "learning_rate": 9.75781752354311e-06,
      "loss": 0.4995099604129791,
      "step": 42
    },
    {
      "epoch": 0.6115555555555555,
      "grad_norm": 0.0039211539551615715,
      "learning_rate": 9.731890013043367e-06,
      "loss": 0.5249044299125671,
      "step": 43
    },
    {
      "epoch": 0.6257777777777778,
      "grad_norm": 0.0038641595747321844,
      "learning_rate": 9.704682361384941e-06,
      "loss": 0.4980819821357727,
      "step": 44
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.004069323651492596,
      "learning_rate": 9.676201929185809e-06,
      "loss": 0.5113821625709534,
      "step": 45
    },
    {
      "epoch": 0.6542222222222223,
      "grad_norm": 0.0038530679885298014,
      "learning_rate": 9.646456421395447e-06,
      "loss": 0.5072203278541565,
      "step": 46
    },
    {
      "epoch": 0.6684444444444444,
      "grad_norm": 0.003951605875045061,
      "learning_rate": 9.615453885210368e-06,
      "loss": 0.509921669960022,
      "step": 47
    },
    {
      "epoch": 0.6826666666666666,
      "grad_norm": 0.0038154355715960264,
      "learning_rate": 9.583202707897075e-06,
      "loss": 0.49035143852233887,
      "step": 48
    },
    {
      "epoch": 0.6968888888888889,
      "grad_norm": 0.004143900703638792,
      "learning_rate": 9.549711614523007e-06,
      "loss": 0.4858332574367523,
      "step": 49
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.0038300366140902042,
      "learning_rate": 9.514989665596114e-06,
      "loss": 0.49062296748161316,
      "step": 50
    },
    {
      "epoch": 0.7111111111111111,
      "eval_loss": 0.5049259662628174,
      "eval_runtime": 38.0442,
      "eval_samples_per_second": 5.257,
      "eval_steps_per_second": 2.629,
      "step": 50
    },
    {
      "epoch": 0.7253333333333334,
      "grad_norm": 0.003965203184634447,
      "learning_rate": 9.479046254613673e-06,
      "loss": 0.5013079643249512,
      "step": 51
    },
    {
      "epoch": 0.7395555555555555,
      "grad_norm": 0.003626414341852069,
      "learning_rate": 9.441891105521005e-06,
      "loss": 0.46776771545410156,
      "step": 52
    },
    {
      "epoch": 0.7537777777777778,
      "grad_norm": 0.003647371893748641,
      "learning_rate": 9.40353427008083e-06,
      "loss": 0.4870305061340332,
      "step": 53
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.0036924544256180525,
      "learning_rate": 9.3639861251539e-06,
      "loss": 0.48354169726371765,
      "step": 54
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 0.0037534767761826515,
      "learning_rate": 9.323257369891702e-06,
      "loss": 0.5097652673721313,
      "step": 55
    },
    {
      "epoch": 0.7964444444444444,
      "grad_norm": 0.003901001764461398,
      "learning_rate": 9.281359022841966e-06,
      "loss": 0.5023170709609985,
      "step": 56
    },
    {
      "epoch": 0.8106666666666666,
      "grad_norm": 0.0037305736914277077,
      "learning_rate": 9.238302418967757e-06,
      "loss": 0.49597933888435364,
      "step": 57
    },
    {
      "epoch": 0.8248888888888889,
      "grad_norm": 0.003764534369111061,
      "learning_rate": 9.194099206580981e-06,
      "loss": 0.504522442817688,
      "step": 58
    },
    {
      "epoch": 0.8391111111111111,
      "grad_norm": 0.004040914587676525,
      "learning_rate": 9.14876134419111e-06,
      "loss": 0.49795830249786377,
      "step": 59
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 0.003855582093819976,
      "learning_rate": 9.102301097269974e-06,
      "loss": 0.49624279141426086,
      "step": 60
    },
    {
      "epoch": 0.8675555555555555,
      "grad_norm": 0.003851535264402628,
      "learning_rate": 9.05473103493355e-06,
      "loss": 0.47714120149612427,
      "step": 61
    },
    {
      "epoch": 0.8817777777777778,
      "grad_norm": 0.004122862592339516,
      "learning_rate": 9.006064026541549e-06,
      "loss": 0.5046075582504272,
      "step": 62
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.0036710964050143957,
      "learning_rate": 8.956313238215824e-06,
      "loss": 0.45711296796798706,
      "step": 63
    },
    {
      "epoch": 0.9102222222222223,
      "grad_norm": 0.004037045873701572,
      "learning_rate": 8.905492129278478e-06,
      "loss": 0.4839310050010681,
      "step": 64
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 0.004081980790942907,
      "learning_rate": 8.85361444861063e-06,
      "loss": 0.4877704381942749,
      "step": 65
    },
    {
      "epoch": 0.9386666666666666,
      "grad_norm": 0.0037577205803245306,
      "learning_rate": 8.800694230932885e-06,
      "loss": 0.49369895458221436,
      "step": 66
    },
    {
      "epoch": 0.9528888888888889,
      "grad_norm": 0.0037781032733619213,
      "learning_rate": 8.74674579300843e-06,
      "loss": 0.4812237620353699,
      "step": 67
    },
    {
      "epoch": 0.9671111111111111,
      "grad_norm": 0.0046208929270505905,
      "learning_rate": 8.691783729769874e-06,
      "loss": 0.4722365736961365,
      "step": 68
    },
    {
      "epoch": 0.9813333333333333,
      "grad_norm": 0.004026597365736961,
      "learning_rate": 8.635822910370793e-06,
      "loss": 0.4962988495826721,
      "step": 69
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 0.004095569718629122,
      "learning_rate": 8.578878474163115e-06,
      "loss": 0.45991775393486023,
      "step": 70
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.006300764624029398,
      "learning_rate": 8.520965826601394e-06,
      "loss": 0.4934382140636444,
      "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": 1.7454250364554445e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}