{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9690721649484537,
  "eval_steps": 500,
  "global_step": 72,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 5.915778602285194,
      "learning_rate": 1e-05,
      "loss": 0.8792,
      "step": 1
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 5.8603827031333084,
      "learning_rate": 2e-05,
      "loss": 0.8614,
      "step": 2
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 2.389431167985615,
      "learning_rate": 3.0000000000000004e-05,
      "loss": 0.7805,
      "step": 3
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": 6.417214780576867,
      "learning_rate": 4e-05,
      "loss": 0.814,
      "step": 4
    },
    {
      "epoch": 0.20618556701030927,
      "grad_norm": 11.939221948728905,
      "learning_rate": 5e-05,
      "loss": 0.9298,
      "step": 5
    },
    {
      "epoch": 0.24742268041237114,
      "grad_norm": 6.9814740650793325,
      "learning_rate": 6.000000000000001e-05,
      "loss": 0.8568,
      "step": 6
    },
    {
      "epoch": 0.28865979381443296,
      "grad_norm": 3.6246783341840567,
      "learning_rate": 7.000000000000001e-05,
      "loss": 0.7715,
      "step": 7
    },
    {
      "epoch": 0.32989690721649484,
      "grad_norm": 3.6153784587221103,
      "learning_rate": 8e-05,
      "loss": 0.7178,
      "step": 8
    },
    {
      "epoch": 0.3711340206185567,
      "grad_norm": 2.8561476958479033,
      "learning_rate": 7.99518182482069e-05,
      "loss": 0.7012,
      "step": 9
    },
    {
      "epoch": 0.41237113402061853,
      "grad_norm": 4.7389040141058745,
      "learning_rate": 7.980738906688788e-05,
      "loss": 0.7192,
      "step": 10
    },
    {
      "epoch": 0.4536082474226804,
      "grad_norm": 1.851735179019456,
      "learning_rate": 7.956706039859124e-05,
      "loss": 0.668,
      "step": 11
    },
    {
      "epoch": 0.4948453608247423,
      "grad_norm": 2.566052664304911,
      "learning_rate": 7.923141121612922e-05,
      "loss": 0.6467,
      "step": 12
    },
    {
      "epoch": 0.5360824742268041,
      "grad_norm": 2.109709868788535,
      "learning_rate": 7.880125012778177e-05,
      "loss": 0.6382,
      "step": 13
    },
    {
      "epoch": 0.5773195876288659,
      "grad_norm": 1.1642435087248661,
      "learning_rate": 7.827761342928836e-05,
      "loss": 0.6351,
      "step": 14
    },
    {
      "epoch": 0.6185567010309279,
      "grad_norm": 1.6106209130732594,
      "learning_rate": 7.766176260732084e-05,
      "loss": 0.6166,
      "step": 15
    },
    {
      "epoch": 0.6597938144329897,
      "grad_norm": 1.6043870099285942,
      "learning_rate": 7.695518130045147e-05,
      "loss": 0.6185,
      "step": 16
    },
    {
      "epoch": 0.7010309278350515,
      "grad_norm": 1.293862536715366,
      "learning_rate": 7.615957172493774e-05,
      "loss": 0.5974,
      "step": 17
    },
    {
      "epoch": 0.7422680412371134,
      "grad_norm": 2.2409334842691684,
      "learning_rate": 7.52768505739342e-05,
      "loss": 0.6219,
      "step": 18
    },
    {
      "epoch": 0.7835051546391752,
      "grad_norm": 1.4417193913598108,
      "learning_rate": 7.430914440001089e-05,
      "loss": 0.5906,
      "step": 19
    },
    {
      "epoch": 0.8247422680412371,
      "grad_norm": 1.3514593246304274,
      "learning_rate": 7.325878449210182e-05,
      "loss": 0.5944,
      "step": 20
    },
    {
      "epoch": 0.865979381443299,
      "grad_norm": 1.363145184880837,
      "learning_rate": 7.21283012592258e-05,
      "loss": 0.5681,
      "step": 21
    },
    {
      "epoch": 0.9072164948453608,
      "grad_norm": 1.2754755318969895,
      "learning_rate": 7.092041813450948e-05,
      "loss": 0.569,
      "step": 22
    },
    {
      "epoch": 0.9484536082474226,
      "grad_norm": 0.915459394115844,
      "learning_rate": 6.963804501419837e-05,
      "loss": 0.5688,
      "step": 23
    },
    {
      "epoch": 0.9896907216494846,
      "grad_norm": 1.1109562944094746,
      "learning_rate": 6.828427124746191e-05,
      "loss": 0.5538,
      "step": 24
    },
    {
      "epoch": 1.0309278350515463,
      "grad_norm": 0.8680910496687467,
      "learning_rate": 6.686235819388075e-05,
      "loss": 0.5439,
      "step": 25
    },
    {
      "epoch": 1.0721649484536082,
      "grad_norm": 1.2171423374867043,
      "learning_rate": 6.537573136654582e-05,
      "loss": 0.5383,
      "step": 26
    },
    {
      "epoch": 1.1134020618556701,
      "grad_norm": 1.0157065682371955,
      "learning_rate": 6.382797217969734e-05,
      "loss": 0.5447,
      "step": 27
    },
    {
      "epoch": 1.1546391752577319,
      "grad_norm": 0.7994213284155107,
      "learning_rate": 6.22228093207841e-05,
      "loss": 0.5319,
      "step": 28
    },
    {
      "epoch": 1.1958762886597938,
      "grad_norm": 0.8988540949081338,
      "learning_rate": 6.056410976772887e-05,
      "loss": 0.537,
      "step": 29
    },
    {
      "epoch": 1.2371134020618557,
      "grad_norm": 1.045458971592603,
      "learning_rate": 5.8855869473039924e-05,
      "loss": 0.5224,
      "step": 30
    },
    {
      "epoch": 1.2783505154639174,
      "grad_norm": 0.5299013843819147,
      "learning_rate": 5.710220373721129e-05,
      "loss": 0.511,
      "step": 31
    },
    {
      "epoch": 1.3195876288659794,
      "grad_norm": 0.9465183460092941,
      "learning_rate": 5.5307337294603595e-05,
      "loss": 0.518,
      "step": 32
    },
    {
      "epoch": 1.3608247422680413,
      "grad_norm": 0.9065353984406849,
      "learning_rate": 5.347559413568881e-05,
      "loss": 0.5119,
      "step": 33
    },
    {
      "epoch": 1.402061855670103,
      "grad_norm": 0.5286929584512716,
      "learning_rate": 5.16113870901785e-05,
      "loss": 0.5117,
      "step": 34
    },
    {
      "epoch": 1.443298969072165,
      "grad_norm": 0.892318482543648,
      "learning_rate": 4.971920719613056e-05,
      "loss": 0.5076,
      "step": 35
    },
    {
      "epoch": 1.4845360824742269,
      "grad_norm": 0.4717303094088032,
      "learning_rate": 4.780361288064514e-05,
      "loss": 0.503,
      "step": 36
    },
    {
      "epoch": 1.5257731958762886,
      "grad_norm": 0.7191312321422306,
      "learning_rate": 4.586921897821447e-05,
      "loss": 0.5098,
      "step": 37
    },
    {
      "epoch": 1.5670103092783505,
      "grad_norm": 0.47146206682277086,
      "learning_rate": 4.392068561318244e-05,
      "loss": 0.4945,
      "step": 38
    },
    {
      "epoch": 1.6082474226804124,
      "grad_norm": 0.7403012163582166,
      "learning_rate": 4.1962706973096726e-05,
      "loss": 0.4953,
      "step": 39
    },
    {
      "epoch": 1.6494845360824741,
      "grad_norm": 0.4223331865451386,
      "learning_rate": 4e-05,
      "loss": 0.501,
      "step": 40
    },
    {
      "epoch": 1.690721649484536,
      "grad_norm": 0.6840090672209329,
      "learning_rate": 3.803729302690328e-05,
      "loss": 0.4918,
      "step": 41
    },
    {
      "epoch": 1.731958762886598,
      "grad_norm": 0.4650006670070441,
      "learning_rate": 3.6079314386817575e-05,
      "loss": 0.4852,
      "step": 42
    },
    {
      "epoch": 1.7731958762886597,
      "grad_norm": 0.4894585869827011,
      "learning_rate": 3.4130781021785535e-05,
      "loss": 0.4897,
      "step": 43
    },
    {
      "epoch": 1.8144329896907216,
      "grad_norm": 0.47462294184562975,
      "learning_rate": 3.219638711935488e-05,
      "loss": 0.4919,
      "step": 44
    },
    {
      "epoch": 1.8556701030927836,
      "grad_norm": 0.33553667803311904,
      "learning_rate": 3.028079280386945e-05,
      "loss": 0.4846,
      "step": 45
    },
    {
      "epoch": 1.8969072164948453,
      "grad_norm": 0.40264815726534753,
      "learning_rate": 2.8388612909821515e-05,
      "loss": 0.4865,
      "step": 46
    },
    {
      "epoch": 1.9381443298969072,
      "grad_norm": 0.29046340066307474,
      "learning_rate": 2.6524405864311203e-05,
      "loss": 0.4828,
      "step": 47
    },
    {
      "epoch": 1.9793814432989691,
      "grad_norm": 0.3630940519896004,
      "learning_rate": 2.4692662705396412e-05,
      "loss": 0.4896,
      "step": 48
    },
    {
      "epoch": 2.020618556701031,
      "grad_norm": 0.29324409805459234,
      "learning_rate": 2.2897796262788728e-05,
      "loss": 0.4781,
      "step": 49
    },
    {
      "epoch": 2.0618556701030926,
      "grad_norm": 0.29703895032031474,
      "learning_rate": 2.1144130526960093e-05,
      "loss": 0.4651,
      "step": 50
    },
    {
      "epoch": 2.1030927835051547,
      "grad_norm": 0.32087301061531515,
      "learning_rate": 1.9435890232271136e-05,
      "loss": 0.4684,
      "step": 51
    },
    {
      "epoch": 2.1443298969072164,
      "grad_norm": 0.21482829598588496,
      "learning_rate": 1.7777190679215923e-05,
      "loss": 0.4625,
      "step": 52
    },
    {
      "epoch": 2.1855670103092786,
      "grad_norm": 0.25824983057026213,
      "learning_rate": 1.617202782030267e-05,
      "loss": 0.4694,
      "step": 53
    },
    {
      "epoch": 2.2268041237113403,
      "grad_norm": 0.34339533921143434,
      "learning_rate": 1.4624268633454187e-05,
      "loss": 0.4671,
      "step": 54
    },
    {
      "epoch": 2.268041237113402,
      "grad_norm": 0.21104502743064882,
      "learning_rate": 1.3137641806119264e-05,
      "loss": 0.4519,
      "step": 55
    },
    {
      "epoch": 2.3092783505154637,
      "grad_norm": 0.24004005785815857,
      "learning_rate": 1.1715728752538103e-05,
      "loss": 0.4659,
      "step": 56
    },
    {
      "epoch": 2.350515463917526,
      "grad_norm": 0.23313541333770835,
      "learning_rate": 1.0361954985801646e-05,
      "loss": 0.4603,
      "step": 57
    },
    {
      "epoch": 2.3917525773195876,
      "grad_norm": 0.20350216506185997,
      "learning_rate": 9.07958186549052e-06,
      "loss": 0.4613,
      "step": 58
    },
    {
      "epoch": 2.4329896907216497,
      "grad_norm": 0.20198630626376185,
      "learning_rate": 7.871698740774208e-06,
      "loss": 0.46,
      "step": 59
    },
    {
      "epoch": 2.4742268041237114,
      "grad_norm": 0.194949563636136,
      "learning_rate": 6.7412155078981865e-06,
      "loss": 0.458,
      "step": 60
    },
    {
      "epoch": 2.515463917525773,
      "grad_norm": 0.14941010498220864,
      "learning_rate": 5.690855599989121e-06,
      "loss": 0.456,
      "step": 61
    },
    {
      "epoch": 2.556701030927835,
      "grad_norm": 0.15790500602219348,
      "learning_rate": 4.723149426065803e-06,
      "loss": 0.4533,
      "step": 62
    },
    {
      "epoch": 2.597938144329897,
      "grad_norm": 0.1636000215831201,
      "learning_rate": 3.840428275062267e-06,
      "loss": 0.4668,
      "step": 63
    },
    {
      "epoch": 2.6391752577319587,
      "grad_norm": 0.14421574699719078,
      "learning_rate": 3.0448186995485307e-06,
      "loss": 0.4556,
      "step": 64
    },
    {
      "epoch": 2.680412371134021,
      "grad_norm": 0.12670796224434785,
      "learning_rate": 2.3382373926791722e-06,
      "loss": 0.4621,
      "step": 65
    },
    {
      "epoch": 2.7216494845360826,
      "grad_norm": 0.11802437342505168,
      "learning_rate": 1.7223865707116472e-06,
      "loss": 0.4479,
      "step": 66
    },
    {
      "epoch": 2.7628865979381443,
      "grad_norm": 0.11470202289963577,
      "learning_rate": 1.1987498722182411e-06,
      "loss": 0.4554,
      "step": 67
    },
    {
      "epoch": 2.804123711340206,
      "grad_norm": 0.11064912896935304,
      "learning_rate": 7.685887838707828e-07,
      "loss": 0.4546,
      "step": 68
    },
    {
      "epoch": 2.845360824742268,
      "grad_norm": 0.11098592310547126,
      "learning_rate": 4.3293960140875946e-07,
      "loss": 0.4593,
      "step": 69
    },
    {
      "epoch": 2.88659793814433,
      "grad_norm": 0.11733219406123296,
      "learning_rate": 1.926109331121273e-07,
      "loss": 0.4613,
      "step": 70
    },
    {
      "epoch": 2.927835051546392,
      "grad_norm": 0.1177256209521773,
      "learning_rate": 4.8181751793103806e-08,
      "loss": 0.4534,
      "step": 71
    },
    {
      "epoch": 2.9690721649484537,
      "grad_norm": 0.10324701234321615,
      "learning_rate": 0.0,
      "loss": 0.4659,
      "step": 72
    },
    {
      "epoch": 2.9690721649484537,
      "step": 72,
      "total_flos": 1.8527734203290747e+18,
      "train_loss": 0.5522520401411586,
      "train_runtime": 15811.9484,
      "train_samples_per_second": 2.351,
      "train_steps_per_second": 0.005
    }
  ],
  "logging_steps": 1,
  "max_steps": 72,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.8527734203290747e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}