{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.99836867862969,
  "eval_steps": 100,
  "global_step": 306,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01631321370309951,
      "grad_norm": 2.53125,
      "learning_rate": 3.225806451612903e-06,
      "loss": 1.4286,
      "mean_token_accuracy": 0.6584272754958135,
      "step": 5
    },
    {
      "epoch": 0.03262642740619902,
      "grad_norm": 2.4375,
      "learning_rate": 6.451612903225806e-06,
      "loss": 1.4087,
      "mean_token_accuracy": 0.662085565849035,
      "step": 10
    },
    {
      "epoch": 0.048939641109298535,
      "grad_norm": 2.640625,
      "learning_rate": 9.67741935483871e-06,
      "loss": 1.5058,
      "mean_token_accuracy": 0.6418076518243186,
      "step": 15
    },
    {
      "epoch": 0.06525285481239804,
      "grad_norm": 1.7421875,
      "learning_rate": 1.2903225806451613e-05,
      "loss": 1.4118,
      "mean_token_accuracy": 0.6534564204767823,
      "step": 20
    },
    {
      "epoch": 0.08156606851549755,
      "grad_norm": 1.515625,
      "learning_rate": 1.6129032258064517e-05,
      "loss": 1.3321,
      "mean_token_accuracy": 0.6651619066075792,
      "step": 25
    },
    {
      "epoch": 0.09787928221859707,
      "grad_norm": 1.3671875,
      "learning_rate": 1.935483870967742e-05,
      "loss": 1.3164,
      "mean_token_accuracy": 0.6717782021288032,
      "step": 30
    },
    {
      "epoch": 0.11419249592169657,
      "grad_norm": 1.3359375,
      "learning_rate": 1.9989561243382313e-05,
      "loss": 1.1912,
      "mean_token_accuracy": 0.694698959999242,
      "step": 35
    },
    {
      "epoch": 0.13050570962479607,
      "grad_norm": 1.3203125,
      "learning_rate": 1.9947191143073185e-05,
      "loss": 1.2719,
      "mean_token_accuracy": 0.6780847732470013,
      "step": 40
    },
    {
      "epoch": 0.1468189233278956,
      "grad_norm": 1.234375,
      "learning_rate": 1.9872375372801627e-05,
      "loss": 1.1799,
      "mean_token_accuracy": 0.6968185226866065,
      "step": 45
    },
    {
      "epoch": 0.1631321370309951,
      "grad_norm": 1.2421875,
      "learning_rate": 1.9765357966059638e-05,
      "loss": 1.2948,
      "mean_token_accuracy": 0.672758400550632,
      "step": 50
    },
    {
      "epoch": 0.17944535073409462,
      "grad_norm": 1.203125,
      "learning_rate": 1.9626487991384194e-05,
      "loss": 1.217,
      "mean_token_accuracy": 0.6891739777463799,
      "step": 55
    },
    {
      "epoch": 0.19575856443719414,
      "grad_norm": 1.2109375,
      "learning_rate": 1.945621841376825e-05,
      "loss": 1.1489,
      "mean_token_accuracy": 0.7052165754765654,
      "step": 60
    },
    {
      "epoch": 0.21207177814029363,
      "grad_norm": 1.296875,
      "learning_rate": 1.9255104617183068e-05,
      "loss": 1.2015,
      "mean_token_accuracy": 0.6921520639873796,
      "step": 65
    },
    {
      "epoch": 0.22838499184339314,
      "grad_norm": 1.140625,
      "learning_rate": 1.9023802593031156e-05,
      "loss": 1.2204,
      "mean_token_accuracy": 0.6918742825268815,
      "step": 70
    },
    {
      "epoch": 0.24469820554649266,
      "grad_norm": 1.234375,
      "learning_rate": 1.8763066800438638e-05,
      "loss": 1.2876,
      "mean_token_accuracy": 0.6744394009627726,
      "step": 75
    },
    {
      "epoch": 0.26101141924959215,
      "grad_norm": 1.2421875,
      "learning_rate": 1.8473747705366427e-05,
      "loss": 1.2127,
      "mean_token_accuracy": 0.6919606949918741,
      "step": 80
    },
    {
      "epoch": 0.27732463295269166,
      "grad_norm": 1.234375,
      "learning_rate": 1.8156789006567018e-05,
      "loss": 1.2829,
      "mean_token_accuracy": 0.6730983288833745,
      "step": 85
    },
    {
      "epoch": 0.2936378466557912,
      "grad_norm": 1.171875,
      "learning_rate": 1.7813224557435313e-05,
      "loss": 1.2617,
      "mean_token_accuracy": 0.677167603530814,
      "step": 90
    },
    {
      "epoch": 0.3099510603588907,
      "grad_norm": 1.1953125,
      "learning_rate": 1.744417499379372e-05,
      "loss": 1.2741,
      "mean_token_accuracy": 0.6805341821135611,
      "step": 95
    },
    {
      "epoch": 0.3262642740619902,
      "grad_norm": 1.125,
      "learning_rate": 1.7050844078611058e-05,
      "loss": 1.2389,
      "mean_token_accuracy": 0.6857057946710582,
      "step": 100
    },
    {
      "epoch": 0.3425774877650897,
      "grad_norm": 1.2578125,
      "learning_rate": 1.663451477557792e-05,
      "loss": 1.2223,
      "mean_token_accuracy": 0.687469468283924,
      "step": 105
    },
    {
      "epoch": 0.35889070146818924,
      "grad_norm": 1.234375,
      "learning_rate": 1.6196545064345813e-05,
      "loss": 1.214,
      "mean_token_accuracy": 0.6902886780811677,
      "step": 110
    },
    {
      "epoch": 0.37520391517128876,
      "grad_norm": 1.203125,
      "learning_rate": 1.5738363511079776e-05,
      "loss": 1.2245,
      "mean_token_accuracy": 0.6857961919369919,
      "step": 115
    },
    {
      "epoch": 0.3915171288743883,
      "grad_norm": 1.2109375,
      "learning_rate": 1.5261464608772487e-05,
      "loss": 1.1697,
      "mean_token_accuracy": 0.7004586354413661,
      "step": 120
    },
    {
      "epoch": 0.4078303425774878,
      "grad_norm": 1.1875,
      "learning_rate": 1.476740390251875e-05,
      "loss": 1.1864,
      "mean_token_accuracy": 0.6946914374684998,
      "step": 125
    },
    {
      "epoch": 0.42414355628058725,
      "grad_norm": 1.2578125,
      "learning_rate": 1.4257792915650728e-05,
      "loss": 1.2256,
      "mean_token_accuracy": 0.6917642628755305,
      "step": 130
    },
    {
      "epoch": 0.44045676998368677,
      "grad_norm": 1.2109375,
      "learning_rate": 1.3734293893283783e-05,
      "loss": 1.2234,
      "mean_token_accuracy": 0.6803009834502376,
      "step": 135
    },
    {
      "epoch": 0.4567699836867863,
      "grad_norm": 1.296875,
      "learning_rate": 1.3198614380418412e-05,
      "loss": 1.2891,
      "mean_token_accuracy": 0.66906340898559,
      "step": 140
    },
    {
      "epoch": 0.4730831973898858,
      "grad_norm": 1.140625,
      "learning_rate": 1.2652501652283378e-05,
      "loss": 1.2833,
      "mean_token_accuracy": 0.6748017583716992,
      "step": 145
    },
    {
      "epoch": 0.4893964110929853,
      "grad_norm": 1.234375,
      "learning_rate": 1.2097737015087094e-05,
      "loss": 1.1936,
      "mean_token_accuracy": 0.691278874465356,
      "step": 150
    },
    {
      "epoch": 0.5057096247960848,
      "grad_norm": 1.140625,
      "learning_rate": 1.1536129995766995e-05,
      "loss": 1.1923,
      "mean_token_accuracy": 0.6915639418258935,
      "step": 155
    },
    {
      "epoch": 0.5220228384991843,
      "grad_norm": 1.2578125,
      "learning_rate": 1.0969512439688816e-05,
      "loss": 1.2689,
      "mean_token_accuracy": 0.6795721711260161,
      "step": 160
    },
    {
      "epoch": 0.5383360522022839,
      "grad_norm": 1.2109375,
      "learning_rate": 1.0399732535547735e-05,
      "loss": 1.2322,
      "mean_token_accuracy": 0.6911618495404431,
      "step": 165
    },
    {
      "epoch": 0.5546492659053833,
      "grad_norm": 1.140625,
      "learning_rate": 9.828648786961009e-06,
      "loss": 1.3013,
      "mean_token_accuracy": 0.6691213045203754,
      "step": 170
    },
    {
      "epoch": 0.5709624796084829,
      "grad_norm": 1.140625,
      "learning_rate": 9.25812395041548e-06,
      "loss": 1.2362,
      "mean_token_accuracy": 0.6846231446931508,
      "step": 175
    },
    {
      "epoch": 0.5872756933115824,
      "grad_norm": 1.1171875,
      "learning_rate": 8.690018959343071e-06,
      "loss": 1.1778,
      "mean_token_accuracy": 0.6980786468955738,
      "step": 180
    },
    {
      "epoch": 0.6035889070146819,
      "grad_norm": 1.1796875,
      "learning_rate": 8.126186854142752e-06,
      "loss": 1.1546,
      "mean_token_accuracy": 0.698524151500448,
      "step": 185
    },
    {
      "epoch": 0.6199021207177814,
      "grad_norm": 1.1875,
      "learning_rate": 7.568466737947905e-06,
      "loss": 1.1121,
      "mean_token_accuracy": 0.7087621864221246,
      "step": 190
    },
    {
      "epoch": 0.636215334420881,
      "grad_norm": 1.28125,
      "learning_rate": 7.018677777854158e-06,
      "loss": 1.2979,
      "mean_token_accuracy": 0.6694032774839085,
      "step": 195
    },
    {
      "epoch": 0.6525285481239804,
      "grad_norm": 1.2734375,
      "learning_rate": 6.478613271174453e-06,
      "loss": 1.3048,
      "mean_token_accuracy": 0.6659829648734708,
      "step": 200
    },
    {
      "epoch": 0.6688417618270799,
      "grad_norm": 1.2265625,
      "learning_rate": 5.950034796075948e-06,
      "loss": 1.2435,
      "mean_token_accuracy": 0.6830356432134138,
      "step": 205
    },
    {
      "epoch": 0.6851549755301795,
      "grad_norm": 1.203125,
      "learning_rate": 5.434666465678176e-06,
      "loss": 1.3219,
      "mean_token_accuracy": 0.6673393247330371,
      "step": 210
    },
    {
      "epoch": 0.7014681892332789,
      "grad_norm": 1.3046875,
      "learning_rate": 4.934189304354418e-06,
      "loss": 1.2301,
      "mean_token_accuracy": 0.6839774101528373,
      "step": 215
    },
    {
      "epoch": 0.7177814029363785,
      "grad_norm": 1.1328125,
      "learning_rate": 4.450235764579598e-06,
      "loss": 1.2208,
      "mean_token_accuracy": 0.6862650424423485,
      "step": 220
    },
    {
      "epoch": 0.734094616639478,
      "grad_norm": 1.265625,
      "learning_rate": 3.984384402209613e-06,
      "loss": 1.2143,
      "mean_token_accuracy": 0.6849734049971641,
      "step": 225
    },
    {
      "epoch": 0.7504078303425775,
      "grad_norm": 1.140625,
      "learning_rate": 3.538154727560259e-06,
      "loss": 1.1558,
      "mean_token_accuracy": 0.6994565541878519,
      "step": 230
    },
    {
      "epoch": 0.766721044045677,
      "grad_norm": 1.09375,
      "learning_rate": 3.1130022490803856e-06,
      "loss": 1.1774,
      "mean_token_accuracy": 0.6945823398256653,
      "step": 235
    },
    {
      "epoch": 0.7830342577487766,
      "grad_norm": 1.25,
      "learning_rate": 2.7103137257858867e-06,
      "loss": 1.142,
      "mean_token_accuracy": 0.7025941539981695,
      "step": 240
    },
    {
      "epoch": 0.799347471451876,
      "grad_norm": 1.2109375,
      "learning_rate": 2.3314026439400217e-06,
      "loss": 1.2946,
      "mean_token_accuracy": 0.6670428901128733,
      "step": 245
    },
    {
      "epoch": 0.8156606851549756,
      "grad_norm": 1.09375,
      "learning_rate": 1.9775049327342486e-06,
      "loss": 1.1889,
      "mean_token_accuracy": 0.6966172545481755,
      "step": 250
    },
    {
      "epoch": 0.831973898858075,
      "grad_norm": 1.1640625,
      "learning_rate": 1.649774932944075e-06,
      "loss": 1.1777,
      "mean_token_accuracy": 0.7020263962587155,
      "step": 255
    },
    {
      "epoch": 0.8482871125611745,
      "grad_norm": 1.1796875,
      "learning_rate": 1.3492816317093894e-06,
      "loss": 1.1444,
      "mean_token_accuracy": 0.7035694430910295,
      "step": 260
    },
    {
      "epoch": 0.8646003262642741,
      "grad_norm": 1.1171875,
      "learning_rate": 1.0770051757206078e-06,
      "loss": 1.1997,
      "mean_token_accuracy": 0.6922763738951797,
      "step": 265
    },
    {
      "epoch": 0.8809135399673735,
      "grad_norm": 1.140625,
      "learning_rate": 8.338336741838837e-07,
      "loss": 1.1993,
      "mean_token_accuracy": 0.6892363770014897,
      "step": 270
    },
    {
      "epoch": 0.8972267536704731,
      "grad_norm": 1.1328125,
      "learning_rate": 6.205603019934791e-07,
      "loss": 1.2311,
      "mean_token_accuracy": 0.6834054369061775,
      "step": 275
    },
    {
      "epoch": 0.9135399673735726,
      "grad_norm": 1.1328125,
      "learning_rate": 4.3788071256013033e-07,
      "loss": 1.2076,
      "mean_token_accuracy": 0.6909252205130498,
      "step": 280
    },
    {
      "epoch": 0.9298531810766721,
      "grad_norm": 1.1640625,
      "learning_rate": 2.863907687341949e-07,
      "loss": 1.1762,
      "mean_token_accuracy": 0.69716578948841,
      "step": 285
    },
    {
      "epoch": 0.9461663947797716,
      "grad_norm": 1.1484375,
      "learning_rate": 1.665845992249071e-07,
      "loss": 1.1792,
      "mean_token_accuracy": 0.6928531967188305,
      "step": 290
    },
    {
      "epoch": 0.9624796084828712,
      "grad_norm": 1.3046875,
      "learning_rate": 7.885298685522235e-08,
      "loss": 1.1642,
      "mean_token_accuracy": 0.694887794722856,
      "step": 295
    },
    {
      "epoch": 0.9787928221859706,
      "grad_norm": 1.28125,
      "learning_rate": 2.348209390947376e-08,
      "loss": 1.234,
      "mean_token_accuracy": 0.6835920887329172,
      "step": 300
    },
    {
      "epoch": 0.9951060358890701,
      "grad_norm": 1.203125,
      "learning_rate": 6.525287314851358e-10,
      "loss": 1.1268,
      "mean_token_accuracy": 0.7035911209586428,
      "step": 305
    },
    {
      "epoch": 0.99836867862969,
      "mean_token_accuracy": 0.7046485858069031,
      "step": 306,
      "total_flos": 7.883277455484518e+16,
      "train_loss": 1.23619465266957,
      "train_runtime": 1783.7305,
      "train_samples_per_second": 1.374,
      "train_steps_per_second": 0.172
    }
  ],
  "logging_steps": 5,
  "max_steps": 306,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.883277455484518e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}