{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.507177033492823,
  "eval_steps": 500,
  "global_step": 106,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004784688995215311,
      "grad_norm": 0.14709724485874176,
      "learning_rate": 2e-05,
      "loss": 1.2491,
      "step": 1
    },
    {
      "epoch": 0.009569377990430622,
      "grad_norm": 0.17019398510456085,
      "learning_rate": 4e-05,
      "loss": 1.4909,
      "step": 2
    },
    {
      "epoch": 0.014354066985645933,
      "grad_norm": 0.17654545605182648,
      "learning_rate": 6e-05,
      "loss": 1.5363,
      "step": 3
    },
    {
      "epoch": 0.019138755980861243,
      "grad_norm": 0.1930554211139679,
      "learning_rate": 8e-05,
      "loss": 1.6395,
      "step": 4
    },
    {
      "epoch": 0.023923444976076555,
      "grad_norm": 0.2117353081703186,
      "learning_rate": 0.0001,
      "loss": 1.7391,
      "step": 5
    },
    {
      "epoch": 0.028708133971291867,
      "grad_norm": 0.20174962282180786,
      "learning_rate": 9.999407114490384e-05,
      "loss": 1.6012,
      "step": 6
    },
    {
      "epoch": 0.03349282296650718,
      "grad_norm": 0.21089714765548706,
      "learning_rate": 9.99762859856683e-05,
      "loss": 1.5543,
      "step": 7
    },
    {
      "epoch": 0.03827751196172249,
      "grad_norm": 0.21190762519836426,
      "learning_rate": 9.994664874011863e-05,
      "loss": 1.4511,
      "step": 8
    },
    {
      "epoch": 0.0430622009569378,
      "grad_norm": 0.22505144774913788,
      "learning_rate": 9.990516643685222e-05,
      "loss": 1.4619,
      "step": 9
    },
    {
      "epoch": 0.04784688995215311,
      "grad_norm": 0.23618264496326447,
      "learning_rate": 9.985184891357164e-05,
      "loss": 1.5113,
      "step": 10
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 0.23488004505634308,
      "learning_rate": 9.978670881475172e-05,
      "loss": 1.502,
      "step": 11
    },
    {
      "epoch": 0.05741626794258373,
      "grad_norm": 0.24843598902225494,
      "learning_rate": 9.970976158864073e-05,
      "loss": 1.5901,
      "step": 12
    },
    {
      "epoch": 0.06220095693779904,
      "grad_norm": 0.25334247946739197,
      "learning_rate": 9.96210254835968e-05,
      "loss": 1.4698,
      "step": 13
    },
    {
      "epoch": 0.06698564593301436,
      "grad_norm": 0.2642665505409241,
      "learning_rate": 9.952052154376026e-05,
      "loss": 1.5525,
      "step": 14
    },
    {
      "epoch": 0.07177033492822966,
      "grad_norm": 0.2637348175048828,
      "learning_rate": 9.940827360406297e-05,
      "loss": 1.4046,
      "step": 15
    },
    {
      "epoch": 0.07655502392344497,
      "grad_norm": 0.28210246562957764,
      "learning_rate": 9.928430828457572e-05,
      "loss": 1.3994,
      "step": 16
    },
    {
      "epoch": 0.08133971291866028,
      "grad_norm": 0.3060890734195709,
      "learning_rate": 9.91486549841951e-05,
      "loss": 1.6673,
      "step": 17
    },
    {
      "epoch": 0.0861244019138756,
      "grad_norm": 0.2893538475036621,
      "learning_rate": 9.90013458736716e-05,
      "loss": 1.5797,
      "step": 18
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 0.29651427268981934,
      "learning_rate": 9.884241588798005e-05,
      "loss": 1.4553,
      "step": 19
    },
    {
      "epoch": 0.09569377990430622,
      "grad_norm": 0.311667263507843,
      "learning_rate": 9.867190271803465e-05,
      "loss": 1.4259,
      "step": 20
    },
    {
      "epoch": 0.10047846889952153,
      "grad_norm": 0.32705116271972656,
      "learning_rate": 9.848984680175049e-05,
      "loss": 1.5493,
      "step": 21
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 0.33383113145828247,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.5034,
      "step": 22
    },
    {
      "epoch": 0.11004784688995216,
      "grad_norm": 0.3618900179862976,
      "learning_rate": 9.809128215864097e-05,
      "loss": 1.7059,
      "step": 23
    },
    {
      "epoch": 0.11483253588516747,
      "grad_norm": 0.36600548028945923,
      "learning_rate": 9.787486795309621e-05,
      "loss": 1.7853,
      "step": 24
    },
    {
      "epoch": 0.11961722488038277,
      "grad_norm": 0.3755670189857483,
      "learning_rate": 9.764710002135784e-05,
      "loss": 1.5303,
      "step": 25
    },
    {
      "epoch": 0.12440191387559808,
      "grad_norm": 0.3820343613624573,
      "learning_rate": 9.74080323795483e-05,
      "loss": 1.687,
      "step": 26
    },
    {
      "epoch": 0.1291866028708134,
      "grad_norm": 0.3974711000919342,
      "learning_rate": 9.715772172356388e-05,
      "loss": 1.7679,
      "step": 27
    },
    {
      "epoch": 0.1339712918660287,
      "grad_norm": 0.4264979064464569,
      "learning_rate": 9.689622741562892e-05,
      "loss": 1.6876,
      "step": 28
    },
    {
      "epoch": 0.13875598086124402,
      "grad_norm": 0.4498402178287506,
      "learning_rate": 9.662361147021779e-05,
      "loss": 1.7944,
      "step": 29
    },
    {
      "epoch": 0.14354066985645933,
      "grad_norm": 0.4634323716163635,
      "learning_rate": 9.633993853934803e-05,
      "loss": 2.0416,
      "step": 30
    },
    {
      "epoch": 0.14832535885167464,
      "grad_norm": 0.467655211687088,
      "learning_rate": 9.60452758972477e-05,
      "loss": 1.9583,
      "step": 31
    },
    {
      "epoch": 0.15311004784688995,
      "grad_norm": 0.4708121716976166,
      "learning_rate": 9.573969342440106e-05,
      "loss": 1.7343,
      "step": 32
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 0.49835681915283203,
      "learning_rate": 9.542326359097619e-05,
      "loss": 1.7304,
      "step": 33
    },
    {
      "epoch": 0.16267942583732056,
      "grad_norm": 0.4945959150791168,
      "learning_rate": 9.509606143963832e-05,
      "loss": 1.8515,
      "step": 34
    },
    {
      "epoch": 0.1674641148325359,
      "grad_norm": 0.532650887966156,
      "learning_rate": 9.475816456775313e-05,
      "loss": 1.955,
      "step": 35
    },
    {
      "epoch": 0.1722488038277512,
      "grad_norm": 0.5782840847969055,
      "learning_rate": 9.440965310898424e-05,
      "loss": 1.9727,
      "step": 36
    },
    {
      "epoch": 0.17703349282296652,
      "grad_norm": 0.6085786819458008,
      "learning_rate": 9.405060971428923e-05,
      "loss": 1.9417,
      "step": 37
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.5588628053665161,
      "learning_rate": 9.368111953231848e-05,
      "loss": 1.9105,
      "step": 38
    },
    {
      "epoch": 0.18660287081339713,
      "grad_norm": 0.6089487671852112,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.9613,
      "step": 39
    },
    {
      "epoch": 0.19138755980861244,
      "grad_norm": 0.6214700937271118,
      "learning_rate": 9.291115176786814e-05,
      "loss": 2.0116,
      "step": 40
    },
    {
      "epoch": 0.19617224880382775,
      "grad_norm": 0.6787968277931213,
      "learning_rate": 9.251085678648072e-05,
      "loss": 1.9211,
      "step": 41
    },
    {
      "epoch": 0.20095693779904306,
      "grad_norm": 0.8012039065361023,
      "learning_rate": 9.210048017669726e-05,
      "loss": 2.0415,
      "step": 42
    },
    {
      "epoch": 0.20574162679425836,
      "grad_norm": 0.7107148766517639,
      "learning_rate": 9.168011926105598e-05,
      "loss": 1.9067,
      "step": 43
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.8137962818145752,
      "learning_rate": 9.124987372991511e-05,
      "loss": 1.9049,
      "step": 44
    },
    {
      "epoch": 0.215311004784689,
      "grad_norm": 0.8808148503303528,
      "learning_rate": 9.08098456178111e-05,
      "loss": 2.0898,
      "step": 45
    },
    {
      "epoch": 0.22009569377990432,
      "grad_norm": 1.1123590469360352,
      "learning_rate": 9.036013927926048e-05,
      "loss": 2.2945,
      "step": 46
    },
    {
      "epoch": 0.22488038277511962,
      "grad_norm": 1.2723033428192139,
      "learning_rate": 8.9900861364012e-05,
      "loss": 2.0564,
      "step": 47
    },
    {
      "epoch": 0.22966507177033493,
      "grad_norm": 1.601427674293518,
      "learning_rate": 8.943212079175391e-05,
      "loss": 1.8703,
      "step": 48
    },
    {
      "epoch": 0.23444976076555024,
      "grad_norm": 2.2030014991760254,
      "learning_rate": 8.895402872628352e-05,
      "loss": 2.0263,
      "step": 49
    },
    {
      "epoch": 0.23923444976076555,
      "grad_norm": 3.696323871612549,
      "learning_rate": 8.846669854914396e-05,
      "loss": 2.6416,
      "step": 50
    },
    {
      "epoch": 0.24401913875598086,
      "grad_norm": 0.3211597800254822,
      "learning_rate": 8.797024583273537e-05,
      "loss": 1.5625,
      "step": 51
    },
    {
      "epoch": 0.24880382775119617,
      "grad_norm": 0.36418232321739197,
      "learning_rate": 8.746478831290648e-05,
      "loss": 1.6543,
      "step": 52
    },
    {
      "epoch": 0.2535885167464115,
      "grad_norm": 0.4147177040576935,
      "learning_rate": 8.695044586103296e-05,
      "loss": 1.5142,
      "step": 53
    },
    {
      "epoch": 0.2583732057416268,
      "grad_norm": 0.40443918108940125,
      "learning_rate": 8.642734045558952e-05,
      "loss": 1.5673,
      "step": 54
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 0.39546626806259155,
      "learning_rate": 8.58955961532221e-05,
      "loss": 1.6391,
      "step": 55
    },
    {
      "epoch": 0.2679425837320574,
      "grad_norm": 0.3606320321559906,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.605,
      "step": 56
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.35251346230506897,
      "learning_rate": 8.480669729814635e-05,
      "loss": 1.3353,
      "step": 57
    },
    {
      "epoch": 0.27751196172248804,
      "grad_norm": 0.3432234227657318,
      "learning_rate": 8.424980098237903e-05,
      "loss": 1.59,
      "step": 58
    },
    {
      "epoch": 0.2822966507177033,
      "grad_norm": 0.3411220908164978,
      "learning_rate": 8.368478218232787e-05,
      "loss": 1.5685,
      "step": 59
    },
    {
      "epoch": 0.28708133971291866,
      "grad_norm": 0.2974628210067749,
      "learning_rate": 8.311177489457652e-05,
      "loss": 1.6432,
      "step": 60
    },
    {
      "epoch": 0.291866028708134,
      "grad_norm": 0.32686975598335266,
      "learning_rate": 8.25309150102121e-05,
      "loss": 1.6631,
      "step": 61
    },
    {
      "epoch": 0.2966507177033493,
      "grad_norm": 0.28340205550193787,
      "learning_rate": 8.194234028259806e-05,
      "loss": 1.4545,
      "step": 62
    },
    {
      "epoch": 0.3014354066985646,
      "grad_norm": 0.2994033098220825,
      "learning_rate": 8.134619029470534e-05,
      "loss": 1.5692,
      "step": 63
    },
    {
      "epoch": 0.3062200956937799,
      "grad_norm": 0.31368395686149597,
      "learning_rate": 8.074260642600964e-05,
      "loss": 1.4963,
      "step": 64
    },
    {
      "epoch": 0.31100478468899523,
      "grad_norm": 0.298289030790329,
      "learning_rate": 8.013173181896283e-05,
      "loss": 1.499,
      "step": 65
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 0.30118173360824585,
      "learning_rate": 7.951371134504599e-05,
      "loss": 1.3931,
      "step": 66
    },
    {
      "epoch": 0.32057416267942584,
      "grad_norm": 0.3297058045864105,
      "learning_rate": 7.888869157041257e-05,
      "loss": 1.6554,
      "step": 67
    },
    {
      "epoch": 0.3253588516746411,
      "grad_norm": 0.3186734616756439,
      "learning_rate": 7.82568207211296e-05,
      "loss": 1.4705,
      "step": 68
    },
    {
      "epoch": 0.33014354066985646,
      "grad_norm": 0.3129718601703644,
      "learning_rate": 7.76182486480253e-05,
      "loss": 1.4966,
      "step": 69
    },
    {
      "epoch": 0.3349282296650718,
      "grad_norm": 0.31505700945854187,
      "learning_rate": 7.697312679115125e-05,
      "loss": 1.5135,
      "step": 70
    },
    {
      "epoch": 0.3397129186602871,
      "grad_norm": 0.3435811996459961,
      "learning_rate": 7.63216081438678e-05,
      "loss": 1.4485,
      "step": 71
    },
    {
      "epoch": 0.3444976076555024,
      "grad_norm": 0.3319874703884125,
      "learning_rate": 7.566384721656104e-05,
      "loss": 1.5681,
      "step": 72
    },
    {
      "epoch": 0.3492822966507177,
      "grad_norm": 0.3534000813961029,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.5403,
      "step": 73
    },
    {
      "epoch": 0.35406698564593303,
      "grad_norm": 0.33617714047431946,
      "learning_rate": 7.433022392834282e-05,
      "loss": 1.4595,
      "step": 74
    },
    {
      "epoch": 0.3588516746411483,
      "grad_norm": 0.3658270537853241,
      "learning_rate": 7.365467784180051e-05,
      "loss": 1.6116,
      "step": 75
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.3672615885734558,
      "learning_rate": 7.297352194896739e-05,
      "loss": 1.5343,
      "step": 76
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 0.4313615560531616,
      "learning_rate": 7.228691778882693e-05,
      "loss": 1.6585,
      "step": 77
    },
    {
      "epoch": 0.37320574162679426,
      "grad_norm": 0.3559150695800781,
      "learning_rate": 7.159502819244206e-05,
      "loss": 1.5485,
      "step": 78
    },
    {
      "epoch": 0.37799043062200954,
      "grad_norm": 0.44446811079978943,
      "learning_rate": 7.089801724433917e-05,
      "loss": 1.8183,
      "step": 79
    },
    {
      "epoch": 0.3827751196172249,
      "grad_norm": 0.4031125009059906,
      "learning_rate": 7.019605024359474e-05,
      "loss": 1.7408,
      "step": 80
    },
    {
      "epoch": 0.3875598086124402,
      "grad_norm": 0.4458540678024292,
      "learning_rate": 6.948929366463396e-05,
      "loss": 1.8305,
      "step": 81
    },
    {
      "epoch": 0.3923444976076555,
      "grad_norm": 0.47091686725616455,
      "learning_rate": 6.877791511775063e-05,
      "loss": 1.6138,
      "step": 82
    },
    {
      "epoch": 0.39712918660287083,
      "grad_norm": 0.46907365322113037,
      "learning_rate": 6.806208330935766e-05,
      "loss": 1.7399,
      "step": 83
    },
    {
      "epoch": 0.4019138755980861,
      "grad_norm": 0.5174430012702942,
      "learning_rate": 6.734196800197762e-05,
      "loss": 1.8187,
      "step": 84
    },
    {
      "epoch": 0.40669856459330145,
      "grad_norm": 0.5630610585212708,
      "learning_rate": 6.661773997398298e-05,
      "loss": 2.0938,
      "step": 85
    },
    {
      "epoch": 0.41148325358851673,
      "grad_norm": 0.49577152729034424,
      "learning_rate": 6.588957097909508e-05,
      "loss": 1.8769,
      "step": 86
    },
    {
      "epoch": 0.41626794258373206,
      "grad_norm": 0.5209452509880066,
      "learning_rate": 6.515763370565218e-05,
      "loss": 1.8037,
      "step": 87
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.5780702829360962,
      "learning_rate": 6.442210173565561e-05,
      "loss": 2.012,
      "step": 88
    },
    {
      "epoch": 0.4258373205741627,
      "grad_norm": 0.5638837814331055,
      "learning_rate": 6.368314950360415e-05,
      "loss": 1.9684,
      "step": 89
    },
    {
      "epoch": 0.430622009569378,
      "grad_norm": 0.6348680257797241,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.7803,
      "step": 90
    },
    {
      "epoch": 0.4354066985645933,
      "grad_norm": 0.6502403616905212,
      "learning_rate": 6.219568600541886e-05,
      "loss": 1.8694,
      "step": 91
    },
    {
      "epoch": 0.44019138755980863,
      "grad_norm": 0.7062990665435791,
      "learning_rate": 6.14475274975067e-05,
      "loss": 2.005,
      "step": 92
    },
    {
      "epoch": 0.4449760765550239,
      "grad_norm": 0.7276941537857056,
      "learning_rate": 6.069665416032487e-05,
      "loss": 2.0282,
      "step": 93
    },
    {
      "epoch": 0.44976076555023925,
      "grad_norm": 0.8595307469367981,
      "learning_rate": 5.9943244066641834e-05,
      "loss": 2.1893,
      "step": 94
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.9870045781135559,
      "learning_rate": 5.918747589082853e-05,
      "loss": 2.1732,
      "step": 95
    },
    {
      "epoch": 0.45933014354066987,
      "grad_norm": 1.0758846998214722,
      "learning_rate": 5.842952886648496e-05,
      "loss": 2.1482,
      "step": 96
    },
    {
      "epoch": 0.46411483253588515,
      "grad_norm": 1.308895468711853,
      "learning_rate": 5.7669582743934284e-05,
      "loss": 2.0192,
      "step": 97
    },
    {
      "epoch": 0.4688995215311005,
      "grad_norm": 1.2809703350067139,
      "learning_rate": 5.6907817747594116e-05,
      "loss": 1.5592,
      "step": 98
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 2.426992893218994,
      "learning_rate": 5.614441453323571e-05,
      "loss": 2.0581,
      "step": 99
    },
    {
      "epoch": 0.4784688995215311,
      "grad_norm": 4.334367752075195,
      "learning_rate": 5.5379554145140574e-05,
      "loss": 2.1415,
      "step": 100
    },
    {
      "epoch": 0.48325358851674644,
      "grad_norm": 0.22294622659683228,
      "learning_rate": 5.4613417973165106e-05,
      "loss": 1.477,
      "step": 101
    },
    {
      "epoch": 0.4880382775119617,
      "grad_norm": 0.23113781213760376,
      "learning_rate": 5.38461877097232e-05,
      "loss": 1.3895,
      "step": 102
    },
    {
      "epoch": 0.49282296650717705,
      "grad_norm": 0.2687288522720337,
      "learning_rate": 5.307804530669716e-05,
      "loss": 1.5935,
      "step": 103
    },
    {
      "epoch": 0.49760765550239233,
      "grad_norm": 0.3015460968017578,
      "learning_rate": 5.230917293228699e-05,
      "loss": 1.7237,
      "step": 104
    },
    {
      "epoch": 0.5023923444976076,
      "grad_norm": 0.31039535999298096,
      "learning_rate": 5.153975292780853e-05,
      "loss": 1.4133,
      "step": 105
    },
    {
      "epoch": 0.507177033492823,
      "grad_norm": 0.2957954406738281,
      "learning_rate": 5.0769967764450345e-05,
      "loss": 1.4559,
      "step": 106
    }
  ],
  "logging_steps": 1,
  "max_steps": 209,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 53,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4139404071206912e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}