{
  "best_metric": 6.946237564086914,
  "best_model_checkpoint": "./results/models/checkpoint-45320",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 45320,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05516328331862312,
      "grad_norm": 0.3359375,
      "learning_rate": 0.004994483671668138,
      "loss": 7.1096,
      "step": 500
    },
    {
      "epoch": 0.11032656663724624,
      "grad_norm": 0.2890625,
      "learning_rate": 0.004988967343336276,
      "loss": 6.9824,
      "step": 1000
    },
    {
      "epoch": 0.16548984995586938,
      "grad_norm": 0.369140625,
      "learning_rate": 0.004983451015004413,
      "loss": 6.971,
      "step": 1500
    },
    {
      "epoch": 0.22065313327449249,
      "grad_norm": 0.8046875,
      "learning_rate": 0.004977934686672551,
      "loss": 7.0129,
      "step": 2000
    },
    {
      "epoch": 0.2758164165931156,
      "grad_norm": 4.59375,
      "learning_rate": 0.004972418358340689,
      "loss": 7.0571,
      "step": 2500
    },
    {
      "epoch": 0.33097969991173876,
      "grad_norm": 4.03125,
      "learning_rate": 0.004966902030008827,
      "loss": 7.0532,
      "step": 3000
    },
    {
      "epoch": 0.3861429832303619,
      "grad_norm": 3.75,
      "learning_rate": 0.0049613857016769635,
      "loss": 7.0486,
      "step": 3500
    },
    {
      "epoch": 0.44130626654898497,
      "grad_norm": 9.125,
      "learning_rate": 0.004955869373345101,
      "loss": 7.0385,
      "step": 4000
    },
    {
      "epoch": 0.4964695498676081,
      "grad_norm": 9.1875,
      "learning_rate": 0.00495035304501324,
      "loss": 7.0304,
      "step": 4500
    },
    {
      "epoch": 0.5516328331862312,
      "grad_norm": 12.625,
      "learning_rate": 0.004944836716681377,
      "loss": 7.023,
      "step": 5000
    },
    {
      "epoch": 0.6067961165048543,
      "grad_norm": 8.6875,
      "learning_rate": 0.0049393203883495145,
      "loss": 7.0205,
      "step": 5500
    },
    {
      "epoch": 0.6619593998234775,
      "grad_norm": 7.6875,
      "learning_rate": 0.004933804060017652,
      "loss": 7.025,
      "step": 6000
    },
    {
      "epoch": 0.7171226831421006,
      "grad_norm": 4.96875,
      "learning_rate": 0.00492828773168579,
      "loss": 7.0285,
      "step": 6500
    },
    {
      "epoch": 0.7722859664607238,
      "grad_norm": 5.46875,
      "learning_rate": 0.004922771403353928,
      "loss": 7.025,
      "step": 7000
    },
    {
      "epoch": 0.8274492497793469,
      "grad_norm": 20.125,
      "learning_rate": 0.0049172550750220655,
      "loss": 7.0162,
      "step": 7500
    },
    {
      "epoch": 0.8826125330979699,
      "grad_norm": 7.1875,
      "learning_rate": 0.004911738746690203,
      "loss": 7.0154,
      "step": 8000
    },
    {
      "epoch": 0.9377758164165931,
      "grad_norm": 8.1875,
      "learning_rate": 0.004906222418358341,
      "loss": 7.0104,
      "step": 8500
    },
    {
      "epoch": 0.9929390997352162,
      "grad_norm": 6.71875,
      "learning_rate": 0.004900706090026478,
      "loss": 7.0374,
      "step": 9000
    },
    {
      "epoch": 1.0,
      "eval_loss": 7.0309014320373535,
      "eval_runtime": 9.4135,
      "eval_samples_per_second": 53.115,
      "eval_steps_per_second": 1.7,
      "step": 9064
    },
    {
      "epoch": 1.0481023830538394,
      "grad_norm": 3.5,
      "learning_rate": 0.0048951897616946165,
      "loss": 7.02,
      "step": 9500
    },
    {
      "epoch": 1.1032656663724625,
      "grad_norm": 10.5,
      "learning_rate": 0.004889673433362754,
      "loss": 7.0297,
      "step": 10000
    },
    {
      "epoch": 1.1584289496910856,
      "grad_norm": 8.875,
      "learning_rate": 0.004884157105030891,
      "loss": 7.0361,
      "step": 10500
    },
    {
      "epoch": 1.2135922330097086,
      "grad_norm": 3.5625,
      "learning_rate": 0.004878640776699029,
      "loss": 7.015,
      "step": 11000
    },
    {
      "epoch": 1.268755516328332,
      "grad_norm": 9.1875,
      "learning_rate": 0.0048731244483671676,
      "loss": 6.9996,
      "step": 11500
    },
    {
      "epoch": 1.323918799646955,
      "grad_norm": 13.625,
      "learning_rate": 0.0048676081200353044,
      "loss": 6.9975,
      "step": 12000
    },
    {
      "epoch": 1.379082082965578,
      "grad_norm": 6.34375,
      "learning_rate": 0.004862091791703442,
      "loss": 7.0081,
      "step": 12500
    },
    {
      "epoch": 1.4342453662842012,
      "grad_norm": 14.375,
      "learning_rate": 0.00485657546337158,
      "loss": 7.0008,
      "step": 13000
    },
    {
      "epoch": 1.4894086496028245,
      "grad_norm": 8.8125,
      "learning_rate": 0.004851059135039718,
      "loss": 6.9962,
      "step": 13500
    },
    {
      "epoch": 1.5445719329214476,
      "grad_norm": 22.625,
      "learning_rate": 0.0048455428067078555,
      "loss": 6.9928,
      "step": 14000
    },
    {
      "epoch": 1.5997352162400706,
      "grad_norm": 12.6875,
      "learning_rate": 0.004840026478375993,
      "loss": 6.9919,
      "step": 14500
    },
    {
      "epoch": 1.6548984995586937,
      "grad_norm": 53.75,
      "learning_rate": 0.004834510150044131,
      "loss": 6.9923,
      "step": 15000
    },
    {
      "epoch": 1.7100617828773168,
      "grad_norm": 9.9375,
      "learning_rate": 0.004828993821712269,
      "loss": 6.9966,
      "step": 15500
    },
    {
      "epoch": 1.7652250661959399,
      "grad_norm": 13.0625,
      "learning_rate": 0.004823477493380406,
      "loss": 6.9908,
      "step": 16000
    },
    {
      "epoch": 1.820388349514563,
      "grad_norm": 8.9375,
      "learning_rate": 0.004817961165048544,
      "loss": 6.9937,
      "step": 16500
    },
    {
      "epoch": 1.8755516328331863,
      "grad_norm": 42.0,
      "learning_rate": 0.004812444836716681,
      "loss": 6.9894,
      "step": 17000
    },
    {
      "epoch": 1.9307149161518093,
      "grad_norm": 17.5,
      "learning_rate": 0.004806928508384819,
      "loss": 6.9926,
      "step": 17500
    },
    {
      "epoch": 1.9858781994704324,
      "grad_norm": 30.75,
      "learning_rate": 0.004801412180052957,
      "loss": 6.9989,
      "step": 18000
    },
    {
      "epoch": 2.0,
      "eval_loss": 6.996521472930908,
      "eval_runtime": 8.6549,
      "eval_samples_per_second": 57.771,
      "eval_steps_per_second": 1.849,
      "step": 18128
    },
    {
      "epoch": 2.0410414827890557,
      "grad_norm": 12.125,
      "learning_rate": 0.004795895851721094,
      "loss": 6.9915,
      "step": 18500
    },
    {
      "epoch": 2.096204766107679,
      "grad_norm": 18.625,
      "learning_rate": 0.004790379523389232,
      "loss": 6.9839,
      "step": 19000
    },
    {
      "epoch": 2.151368049426302,
      "grad_norm": 21.25,
      "learning_rate": 0.00478486319505737,
      "loss": 6.9821,
      "step": 19500
    },
    {
      "epoch": 2.206531332744925,
      "grad_norm": 21.375,
      "learning_rate": 0.004779346866725508,
      "loss": 6.9842,
      "step": 20000
    },
    {
      "epoch": 2.261694616063548,
      "grad_norm": 16.625,
      "learning_rate": 0.004773830538393645,
      "loss": 6.9836,
      "step": 20500
    },
    {
      "epoch": 2.316857899382171,
      "grad_norm": 17.125,
      "learning_rate": 0.004768314210061783,
      "loss": 6.9837,
      "step": 21000
    },
    {
      "epoch": 2.372021182700794,
      "grad_norm": 8.9375,
      "learning_rate": 0.004762797881729921,
      "loss": 6.9822,
      "step": 21500
    },
    {
      "epoch": 2.4271844660194173,
      "grad_norm": 8.25,
      "learning_rate": 0.004757281553398059,
      "loss": 6.9791,
      "step": 22000
    },
    {
      "epoch": 2.4823477493380404,
      "grad_norm": 8.375,
      "learning_rate": 0.0047517652250661955,
      "loss": 6.986,
      "step": 22500
    },
    {
      "epoch": 2.537511032656664,
      "grad_norm": 10.6875,
      "learning_rate": 0.004746248896734333,
      "loss": 6.9807,
      "step": 23000
    },
    {
      "epoch": 2.592674315975287,
      "grad_norm": 14.375,
      "learning_rate": 0.004740732568402472,
      "loss": 6.9822,
      "step": 23500
    },
    {
      "epoch": 2.64783759929391,
      "grad_norm": 10.625,
      "learning_rate": 0.004735216240070609,
      "loss": 6.9701,
      "step": 24000
    },
    {
      "epoch": 2.703000882612533,
      "grad_norm": 11.75,
      "learning_rate": 0.0047296999117387465,
      "loss": 6.9707,
      "step": 24500
    },
    {
      "epoch": 2.758164165931156,
      "grad_norm": 30.375,
      "learning_rate": 0.004724183583406884,
      "loss": 6.9792,
      "step": 25000
    },
    {
      "epoch": 2.8133274492497793,
      "grad_norm": 17.25,
      "learning_rate": 0.004718667255075022,
      "loss": 6.9803,
      "step": 25500
    },
    {
      "epoch": 2.8684907325684024,
      "grad_norm": 9.0,
      "learning_rate": 0.00471315092674316,
      "loss": 6.9752,
      "step": 26000
    },
    {
      "epoch": 2.9236540158870254,
      "grad_norm": 6.0,
      "learning_rate": 0.0047076345984112975,
      "loss": 6.9687,
      "step": 26500
    },
    {
      "epoch": 2.978817299205649,
      "grad_norm": 12.0625,
      "learning_rate": 0.004702118270079435,
      "loss": 6.9635,
      "step": 27000
    },
    {
      "epoch": 3.0,
      "eval_loss": 6.960501194000244,
      "eval_runtime": 8.9893,
      "eval_samples_per_second": 55.622,
      "eval_steps_per_second": 1.78,
      "step": 27192
    },
    {
      "epoch": 3.033980582524272,
      "grad_norm": 15.25,
      "learning_rate": 0.004696601941747573,
      "loss": 6.9586,
      "step": 27500
    },
    {
      "epoch": 3.089143865842895,
      "grad_norm": 12.1875,
      "learning_rate": 0.004691085613415711,
      "loss": 6.9644,
      "step": 28000
    },
    {
      "epoch": 3.144307149161518,
      "grad_norm": 12.125,
      "learning_rate": 0.0046855692850838486,
      "loss": 6.955,
      "step": 28500
    },
    {
      "epoch": 3.1994704324801413,
      "grad_norm": 11.3125,
      "learning_rate": 0.004680052956751986,
      "loss": 6.9499,
      "step": 29000
    },
    {
      "epoch": 3.2546337157987644,
      "grad_norm": 9.0625,
      "learning_rate": 0.004674536628420123,
      "loss": 6.9522,
      "step": 29500
    },
    {
      "epoch": 3.3097969991173875,
      "grad_norm": 10.25,
      "learning_rate": 0.004669020300088262,
      "loss": 6.952,
      "step": 30000
    },
    {
      "epoch": 3.3649602824360105,
      "grad_norm": 15.6875,
      "learning_rate": 0.0046635039717564,
      "loss": 6.9524,
      "step": 30500
    },
    {
      "epoch": 3.4201235657546336,
      "grad_norm": 18.875,
      "learning_rate": 0.0046579876434245365,
      "loss": 6.9502,
      "step": 31000
    },
    {
      "epoch": 3.4752868490732567,
      "grad_norm": 8.6875,
      "learning_rate": 0.004652471315092674,
      "loss": 6.9465,
      "step": 31500
    },
    {
      "epoch": 3.5304501323918798,
      "grad_norm": 16.375,
      "learning_rate": 0.004646954986760812,
      "loss": 6.9453,
      "step": 32000
    },
    {
      "epoch": 3.585613415710503,
      "grad_norm": 20.5,
      "learning_rate": 0.00464143865842895,
      "loss": 6.9477,
      "step": 32500
    },
    {
      "epoch": 3.6407766990291264,
      "grad_norm": 15.5625,
      "learning_rate": 0.0046359223300970875,
      "loss": 6.9507,
      "step": 33000
    },
    {
      "epoch": 3.6959399823477495,
      "grad_norm": 47.5,
      "learning_rate": 0.004630406001765225,
      "loss": 6.9513,
      "step": 33500
    },
    {
      "epoch": 3.7511032656663725,
      "grad_norm": 17.125,
      "learning_rate": 0.004624889673433363,
      "loss": 6.9489,
      "step": 34000
    },
    {
      "epoch": 3.8062665489849956,
      "grad_norm": 190.0,
      "learning_rate": 0.004619373345101501,
      "loss": 6.9486,
      "step": 34500
    },
    {
      "epoch": 3.8614298323036187,
      "grad_norm": 12.375,
      "learning_rate": 0.0046138570167696385,
      "loss": 6.954,
      "step": 35000
    },
    {
      "epoch": 3.9165931156222418,
      "grad_norm": 12.25,
      "learning_rate": 0.004608340688437776,
      "loss": 6.945,
      "step": 35500
    },
    {
      "epoch": 3.971756398940865,
      "grad_norm": 9.6875,
      "learning_rate": 0.004602824360105914,
      "loss": 6.9449,
      "step": 36000
    },
    {
      "epoch": 4.0,
      "eval_loss": 6.9535441398620605,
      "eval_runtime": 9.4952,
      "eval_samples_per_second": 52.658,
      "eval_steps_per_second": 1.685,
      "step": 36256
    },
    {
      "epoch": 4.026919682259488,
      "grad_norm": 13.375,
      "learning_rate": 0.004597308031774051,
      "loss": 6.9449,
      "step": 36500
    },
    {
      "epoch": 4.0820829655781115,
      "grad_norm": 12.0625,
      "learning_rate": 0.0045917917034421895,
      "loss": 6.9412,
      "step": 37000
    },
    {
      "epoch": 4.1372462488967345,
      "grad_norm": 12.8125,
      "learning_rate": 0.004586275375110326,
      "loss": 6.9405,
      "step": 37500
    },
    {
      "epoch": 4.192409532215358,
      "grad_norm": 10.6875,
      "learning_rate": 0.004580759046778464,
      "loss": 6.9472,
      "step": 38000
    },
    {
      "epoch": 4.247572815533981,
      "grad_norm": 12.625,
      "learning_rate": 0.004575242718446602,
      "loss": 6.9417,
      "step": 38500
    },
    {
      "epoch": 4.302736098852604,
      "grad_norm": 7.96875,
      "learning_rate": 0.00456972639011474,
      "loss": 6.9397,
      "step": 39000
    },
    {
      "epoch": 4.357899382171227,
      "grad_norm": 9.5625,
      "learning_rate": 0.004564210061782877,
      "loss": 6.9399,
      "step": 39500
    },
    {
      "epoch": 4.41306266548985,
      "grad_norm": 8.9375,
      "learning_rate": 0.004558693733451015,
      "loss": 6.9393,
      "step": 40000
    },
    {
      "epoch": 4.468225948808473,
      "grad_norm": 12.875,
      "learning_rate": 0.004553177405119153,
      "loss": 6.9348,
      "step": 40500
    },
    {
      "epoch": 4.523389232127096,
      "grad_norm": 20.125,
      "learning_rate": 0.004547661076787291,
      "loss": 6.94,
      "step": 41000
    },
    {
      "epoch": 4.578552515445719,
      "grad_norm": 12.0,
      "learning_rate": 0.0045421447484554275,
      "loss": 6.9417,
      "step": 41500
    },
    {
      "epoch": 4.633715798764342,
      "grad_norm": 14.6875,
      "learning_rate": 0.004536628420123566,
      "loss": 6.9362,
      "step": 42000
    },
    {
      "epoch": 4.688879082082965,
      "grad_norm": 12.3125,
      "learning_rate": 0.004531112091791704,
      "loss": 6.9365,
      "step": 42500
    },
    {
      "epoch": 4.744042365401588,
      "grad_norm": 9.1875,
      "learning_rate": 0.004525595763459841,
      "loss": 6.9306,
      "step": 43000
    },
    {
      "epoch": 4.7992056487202115,
      "grad_norm": 36.5,
      "learning_rate": 0.0045200794351279786,
      "loss": 6.9657,
      "step": 43500
    },
    {
      "epoch": 4.854368932038835,
      "grad_norm": 33.25,
      "learning_rate": 0.004514563106796117,
      "loss": 6.953,
      "step": 44000
    },
    {
      "epoch": 4.9095322153574585,
      "grad_norm": 20.375,
      "learning_rate": 0.004509046778464254,
      "loss": 6.9506,
      "step": 44500
    },
    {
      "epoch": 4.964695498676081,
      "grad_norm": 7.875,
      "learning_rate": 0.004503530450132392,
      "loss": 6.9484,
      "step": 45000
    },
    {
      "epoch": 5.0,
      "eval_loss": 6.946237564086914,
      "eval_runtime": 8.659,
      "eval_samples_per_second": 57.744,
      "eval_steps_per_second": 1.848,
      "step": 45320
    }
  ],
  "logging_steps": 500,
  "max_steps": 453200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.553070427093514e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}