{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03385168729503861,
  "eval_steps": 20,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004231460911879826,
      "grad_norm": 1.6379058361053467,
      "learning_rate": 2e-05,
      "loss": 2.4891,
      "step": 1
    },
    {
      "epoch": 0.0004231460911879826,
      "eval_loss": 2.7103111743927,
      "eval_runtime": 63.2579,
      "eval_samples_per_second": 31.459,
      "eval_steps_per_second": 7.873,
      "step": 1
    },
    {
      "epoch": 0.0008462921823759652,
      "grad_norm": 1.6534020900726318,
      "learning_rate": 4e-05,
      "loss": 2.6718,
      "step": 2
    },
    {
      "epoch": 0.0012694382735639479,
      "grad_norm": 1.7026811838150024,
      "learning_rate": 6e-05,
      "loss": 2.6471,
      "step": 3
    },
    {
      "epoch": 0.0016925843647519305,
      "grad_norm": 1.6745214462280273,
      "learning_rate": 8e-05,
      "loss": 2.6711,
      "step": 4
    },
    {
      "epoch": 0.002115730455939913,
      "grad_norm": 1.5553100109100342,
      "learning_rate": 0.0001,
      "loss": 2.5945,
      "step": 5
    },
    {
      "epoch": 0.0025388765471278957,
      "grad_norm": 1.4465041160583496,
      "learning_rate": 0.00012,
      "loss": 2.6169,
      "step": 6
    },
    {
      "epoch": 0.0029620226383158784,
      "grad_norm": 1.3366378545761108,
      "learning_rate": 0.00014,
      "loss": 2.6392,
      "step": 7
    },
    {
      "epoch": 0.003385168729503861,
      "grad_norm": 1.3913536071777344,
      "learning_rate": 0.00016,
      "loss": 2.5899,
      "step": 8
    },
    {
      "epoch": 0.003808314820691844,
      "grad_norm": 1.4674654006958008,
      "learning_rate": 0.00018,
      "loss": 2.5501,
      "step": 9
    },
    {
      "epoch": 0.004231460911879826,
      "grad_norm": 1.5482183694839478,
      "learning_rate": 0.0002,
      "loss": 2.5371,
      "step": 10
    },
    {
      "epoch": 0.004654607003067809,
      "grad_norm": 1.5878816843032837,
      "learning_rate": 0.00019989930665413147,
      "loss": 2.55,
      "step": 11
    },
    {
      "epoch": 0.0050777530942557915,
      "grad_norm": 1.4205892086029053,
      "learning_rate": 0.00019959742939952392,
      "loss": 2.4969,
      "step": 12
    },
    {
      "epoch": 0.005500899185443774,
      "grad_norm": 1.4903907775878906,
      "learning_rate": 0.00019909497617679348,
      "loss": 2.3645,
      "step": 13
    },
    {
      "epoch": 0.005924045276631757,
      "grad_norm": 1.3923956155776978,
      "learning_rate": 0.00019839295885986296,
      "loss": 2.3951,
      "step": 14
    },
    {
      "epoch": 0.006347191367819739,
      "grad_norm": 1.3330631256103516,
      "learning_rate": 0.00019749279121818235,
      "loss": 2.4397,
      "step": 15
    },
    {
      "epoch": 0.006770337459007722,
      "grad_norm": 1.3482651710510254,
      "learning_rate": 0.00019639628606958533,
      "loss": 2.4354,
      "step": 16
    },
    {
      "epoch": 0.0071934835501957055,
      "grad_norm": 1.3089728355407715,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.3894,
      "step": 17
    },
    {
      "epoch": 0.007616629641383688,
      "grad_norm": 1.2744436264038086,
      "learning_rate": 0.00019362348706397373,
      "loss": 2.3651,
      "step": 18
    },
    {
      "epoch": 0.00803977573257167,
      "grad_norm": 1.23836350440979,
      "learning_rate": 0.0001919527772551451,
      "loss": 2.2486,
      "step": 19
    },
    {
      "epoch": 0.008462921823759652,
      "grad_norm": 1.2774382829666138,
      "learning_rate": 0.0001900968867902419,
      "loss": 2.3211,
      "step": 20
    },
    {
      "epoch": 0.008462921823759652,
      "eval_loss": 2.3435285091400146,
      "eval_runtime": 72.0517,
      "eval_samples_per_second": 27.619,
      "eval_steps_per_second": 6.912,
      "step": 20
    },
    {
      "epoch": 0.008886067914947636,
      "grad_norm": 1.351232886314392,
      "learning_rate": 0.0001880595531856738,
      "loss": 2.3451,
      "step": 21
    },
    {
      "epoch": 0.009309214006135618,
      "grad_norm": 1.3749635219573975,
      "learning_rate": 0.00018584487936018661,
      "loss": 2.4502,
      "step": 22
    },
    {
      "epoch": 0.009732360097323601,
      "grad_norm": 1.4125924110412598,
      "learning_rate": 0.00018345732537213027,
      "loss": 2.4342,
      "step": 23
    },
    {
      "epoch": 0.010155506188511583,
      "grad_norm": 1.326550841331482,
      "learning_rate": 0.00018090169943749476,
      "loss": 2.3139,
      "step": 24
    },
    {
      "epoch": 0.010578652279699566,
      "grad_norm": 1.1940902471542358,
      "learning_rate": 0.000178183148246803,
      "loss": 2.3268,
      "step": 25
    },
    {
      "epoch": 0.011001798370887548,
      "grad_norm": 1.294498085975647,
      "learning_rate": 0.00017530714660036112,
      "loss": 2.2343,
      "step": 26
    },
    {
      "epoch": 0.011424944462075532,
      "grad_norm": 1.4341365098953247,
      "learning_rate": 0.00017227948638273916,
      "loss": 2.2412,
      "step": 27
    },
    {
      "epoch": 0.011848090553263513,
      "grad_norm": 1.4379862546920776,
      "learning_rate": 0.00016910626489868649,
      "loss": 2.3088,
      "step": 28
    },
    {
      "epoch": 0.012271236644451497,
      "grad_norm": 1.807862401008606,
      "learning_rate": 0.00016579387259397127,
      "loss": 2.3386,
      "step": 29
    },
    {
      "epoch": 0.012694382735639479,
      "grad_norm": 1.4435659646987915,
      "learning_rate": 0.00016234898018587337,
      "loss": 2.2997,
      "step": 30
    },
    {
      "epoch": 0.013117528826827462,
      "grad_norm": 1.380933403968811,
      "learning_rate": 0.00015877852522924732,
      "loss": 2.2587,
      "step": 31
    },
    {
      "epoch": 0.013540674918015444,
      "grad_norm": 1.3532695770263672,
      "learning_rate": 0.00015508969814521025,
      "loss": 2.389,
      "step": 32
    },
    {
      "epoch": 0.013963821009203427,
      "grad_norm": 1.3885740041732788,
      "learning_rate": 0.00015128992774059063,
      "loss": 2.2765,
      "step": 33
    },
    {
      "epoch": 0.014386967100391411,
      "grad_norm": 1.6315644979476929,
      "learning_rate": 0.00014738686624729986,
      "loss": 2.2364,
      "step": 34
    },
    {
      "epoch": 0.014810113191579393,
      "grad_norm": 1.5489228963851929,
      "learning_rate": 0.00014338837391175582,
      "loss": 2.1861,
      "step": 35
    },
    {
      "epoch": 0.015233259282767376,
      "grad_norm": 1.4338537454605103,
      "learning_rate": 0.00013930250316539238,
      "loss": 2.1853,
      "step": 36
    },
    {
      "epoch": 0.015656405373955358,
      "grad_norm": 1.3952263593673706,
      "learning_rate": 0.0001351374824081343,
      "loss": 2.2732,
      "step": 37
    },
    {
      "epoch": 0.01607955146514334,
      "grad_norm": 1.3308148384094238,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.2248,
      "step": 38
    },
    {
      "epoch": 0.016502697556331325,
      "grad_norm": 1.477274775505066,
      "learning_rate": 0.00012660368455666752,
      "loss": 2.2161,
      "step": 39
    },
    {
      "epoch": 0.016925843647519305,
      "grad_norm": 1.3079551458358765,
      "learning_rate": 0.00012225209339563145,
      "loss": 2.1925,
      "step": 40
    },
    {
      "epoch": 0.016925843647519305,
      "eval_loss": 2.211884021759033,
      "eval_runtime": 75.9809,
      "eval_samples_per_second": 26.191,
      "eval_steps_per_second": 6.554,
      "step": 40
    },
    {
      "epoch": 0.01734898973870729,
      "grad_norm": 1.243667483329773,
      "learning_rate": 0.00011785568947986367,
      "loss": 2.282,
      "step": 41
    },
    {
      "epoch": 0.017772135829895272,
      "grad_norm": 5.15204381942749,
      "learning_rate": 0.00011342332658176555,
      "loss": 2.3092,
      "step": 42
    },
    {
      "epoch": 0.018195281921083255,
      "grad_norm": 1.3127551078796387,
      "learning_rate": 0.00010896393089034336,
      "loss": 2.185,
      "step": 43
    },
    {
      "epoch": 0.018618428012271235,
      "grad_norm": 1.3681222200393677,
      "learning_rate": 0.00010448648303505151,
      "loss": 2.2499,
      "step": 44
    },
    {
      "epoch": 0.01904157410345922,
      "grad_norm": 1.3882651329040527,
      "learning_rate": 0.0001,
      "loss": 2.168,
      "step": 45
    },
    {
      "epoch": 0.019464720194647202,
      "grad_norm": 1.2424044609069824,
      "learning_rate": 9.551351696494854e-05,
      "loss": 2.1857,
      "step": 46
    },
    {
      "epoch": 0.019887866285835186,
      "grad_norm": 1.449005365371704,
      "learning_rate": 9.103606910965666e-05,
      "loss": 2.3204,
      "step": 47
    },
    {
      "epoch": 0.020311012377023166,
      "grad_norm": 1.2062491178512573,
      "learning_rate": 8.657667341823448e-05,
      "loss": 2.1174,
      "step": 48
    },
    {
      "epoch": 0.02073415846821115,
      "grad_norm": 4.882323741912842,
      "learning_rate": 8.214431052013634e-05,
      "loss": 2.3162,
      "step": 49
    },
    {
      "epoch": 0.021157304559399133,
      "grad_norm": 1.4830926656723022,
      "learning_rate": 7.774790660436858e-05,
      "loss": 2.4003,
      "step": 50
    },
    {
      "epoch": 0.021580450650587116,
      "grad_norm": 1.2459235191345215,
      "learning_rate": 7.339631544333249e-05,
      "loss": 2.1419,
      "step": 51
    },
    {
      "epoch": 0.022003596741775096,
      "grad_norm": 1.3951412439346313,
      "learning_rate": 6.909830056250527e-05,
      "loss": 2.114,
      "step": 52
    },
    {
      "epoch": 0.02242674283296308,
      "grad_norm": 1.2715801000595093,
      "learning_rate": 6.486251759186572e-05,
      "loss": 2.0807,
      "step": 53
    },
    {
      "epoch": 0.022849888924151063,
      "grad_norm": 1.1952708959579468,
      "learning_rate": 6.069749683460765e-05,
      "loss": 2.1682,
      "step": 54
    },
    {
      "epoch": 0.023273035015339047,
      "grad_norm": 1.1247831583023071,
      "learning_rate": 5.6611626088244194e-05,
      "loss": 2.062,
      "step": 55
    },
    {
      "epoch": 0.023696181106527027,
      "grad_norm": 1.2911661863327026,
      "learning_rate": 5.261313375270014e-05,
      "loss": 2.234,
      "step": 56
    },
    {
      "epoch": 0.02411932719771501,
      "grad_norm": 1.1771955490112305,
      "learning_rate": 4.87100722594094e-05,
      "loss": 2.2042,
      "step": 57
    },
    {
      "epoch": 0.024542473288902994,
      "grad_norm": 1.1919941902160645,
      "learning_rate": 4.491030185478976e-05,
      "loss": 2.0736,
      "step": 58
    },
    {
      "epoch": 0.024965619380090977,
      "grad_norm": 1.3543719053268433,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.1515,
      "step": 59
    },
    {
      "epoch": 0.025388765471278957,
      "grad_norm": 1.123665452003479,
      "learning_rate": 3.7651019814126654e-05,
      "loss": 2.1566,
      "step": 60
    },
    {
      "epoch": 0.025388765471278957,
      "eval_loss": 2.16865873336792,
      "eval_runtime": 25.383,
      "eval_samples_per_second": 78.399,
      "eval_steps_per_second": 19.619,
      "step": 60
    },
    {
      "epoch": 0.02581191156246694,
      "grad_norm": 1.132775068283081,
      "learning_rate": 3.4206127406028745e-05,
      "loss": 2.2303,
      "step": 61
    },
    {
      "epoch": 0.026235057653654924,
      "grad_norm": 1.1115837097167969,
      "learning_rate": 3.089373510131354e-05,
      "loss": 2.1469,
      "step": 62
    },
    {
      "epoch": 0.026658203744842908,
      "grad_norm": 1.1179817914962769,
      "learning_rate": 2.7720513617260856e-05,
      "loss": 2.1541,
      "step": 63
    },
    {
      "epoch": 0.027081349836030888,
      "grad_norm": 1.3277086019515991,
      "learning_rate": 2.4692853399638917e-05,
      "loss": 2.1514,
      "step": 64
    },
    {
      "epoch": 0.02750449592721887,
      "grad_norm": 1.1748079061508179,
      "learning_rate": 2.181685175319702e-05,
      "loss": 2.0713,
      "step": 65
    },
    {
      "epoch": 0.027927642018406855,
      "grad_norm": 1.210524559020996,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 2.1612,
      "step": 66
    },
    {
      "epoch": 0.02835078810959484,
      "grad_norm": 1.1560407876968384,
      "learning_rate": 1.6542674627869737e-05,
      "loss": 2.2039,
      "step": 67
    },
    {
      "epoch": 0.028773934200782822,
      "grad_norm": 1.1386845111846924,
      "learning_rate": 1.415512063981339e-05,
      "loss": 2.1411,
      "step": 68
    },
    {
      "epoch": 0.029197080291970802,
      "grad_norm": 1.0700095891952515,
      "learning_rate": 1.19404468143262e-05,
      "loss": 2.1263,
      "step": 69
    },
    {
      "epoch": 0.029620226383158785,
      "grad_norm": 1.1910362243652344,
      "learning_rate": 9.903113209758096e-06,
      "loss": 2.27,
      "step": 70
    },
    {
      "epoch": 0.03004337247434677,
      "grad_norm": 1.1575465202331543,
      "learning_rate": 8.047222744854943e-06,
      "loss": 2.156,
      "step": 71
    },
    {
      "epoch": 0.030466518565534752,
      "grad_norm": 1.1447267532348633,
      "learning_rate": 6.37651293602628e-06,
      "loss": 2.1257,
      "step": 72
    },
    {
      "epoch": 0.030889664656722732,
      "grad_norm": 1.1838666200637817,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 2.2088,
      "step": 73
    },
    {
      "epoch": 0.031312810747910716,
      "grad_norm": 1.1437898874282837,
      "learning_rate": 3.6037139304146762e-06,
      "loss": 2.0872,
      "step": 74
    },
    {
      "epoch": 0.031735956839098696,
      "grad_norm": 1.1745190620422363,
      "learning_rate": 2.5072087818176382e-06,
      "loss": 2.1591,
      "step": 75
    },
    {
      "epoch": 0.03215910293028668,
      "grad_norm": 1.2256075143814087,
      "learning_rate": 1.6070411401370334e-06,
      "loss": 2.1358,
      "step": 76
    },
    {
      "epoch": 0.03258224902147466,
      "grad_norm": 1.3967663049697876,
      "learning_rate": 9.0502382320653e-07,
      "loss": 2.1687,
      "step": 77
    },
    {
      "epoch": 0.03300539511266265,
      "grad_norm": 1.205739140510559,
      "learning_rate": 4.025706004760932e-07,
      "loss": 2.2164,
      "step": 78
    },
    {
      "epoch": 0.03342854120385063,
      "grad_norm": 1.2898608446121216,
      "learning_rate": 1.0069334586854107e-07,
      "loss": 2.2109,
      "step": 79
    },
    {
      "epoch": 0.03385168729503861,
      "grad_norm": 1.1767884492874146,
      "learning_rate": 0.0,
      "loss": 2.2616,
      "step": 80
    },
    {
      "epoch": 0.03385168729503861,
      "eval_loss": 2.162363290786743,
      "eval_runtime": 25.534,
      "eval_samples_per_second": 77.935,
      "eval_steps_per_second": 19.503,
      "step": 80
    }
  ],
  "logging_steps": 1,
  "max_steps": 80,
  "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": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1476504563220480.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}