{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 100,
  "global_step": 676,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029585798816568046,
      "grad_norm": 0.273715414576951,
      "learning_rate": 1.4705882352941177e-06,
      "loss": 1.0932,
      "step": 5
    },
    {
      "epoch": 0.05917159763313609,
      "grad_norm": 0.25607253057272245,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 1.1088,
      "step": 10
    },
    {
      "epoch": 0.08875739644970414,
      "grad_norm": 0.21894764040661824,
      "learning_rate": 4.411764705882353e-06,
      "loss": 1.0732,
      "step": 15
    },
    {
      "epoch": 0.11834319526627218,
      "grad_norm": 0.17170786918530545,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.036,
      "step": 20
    },
    {
      "epoch": 0.14792899408284024,
      "grad_norm": 0.12790707767016407,
      "learning_rate": 7.352941176470589e-06,
      "loss": 0.9931,
      "step": 25
    },
    {
      "epoch": 0.17751479289940827,
      "grad_norm": 0.09309535178100455,
      "learning_rate": 8.823529411764707e-06,
      "loss": 0.9431,
      "step": 30
    },
    {
      "epoch": 0.20710059171597633,
      "grad_norm": 0.08279026125112854,
      "learning_rate": 1.0294117647058823e-05,
      "loss": 0.917,
      "step": 35
    },
    {
      "epoch": 0.23668639053254437,
      "grad_norm": 0.07249043677776425,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 0.8928,
      "step": 40
    },
    {
      "epoch": 0.26627218934911245,
      "grad_norm": 0.05554103399201748,
      "learning_rate": 1.323529411764706e-05,
      "loss": 0.8345,
      "step": 45
    },
    {
      "epoch": 0.2958579881656805,
      "grad_norm": 0.05264820026871137,
      "learning_rate": 1.4705882352941179e-05,
      "loss": 0.8485,
      "step": 50
    },
    {
      "epoch": 0.3254437869822485,
      "grad_norm": 0.05077619199201636,
      "learning_rate": 1.6176470588235296e-05,
      "loss": 0.8181,
      "step": 55
    },
    {
      "epoch": 0.35502958579881655,
      "grad_norm": 0.04520606514293075,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 0.8058,
      "step": 60
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.04189278713749456,
      "learning_rate": 1.911764705882353e-05,
      "loss": 0.8093,
      "step": 65
    },
    {
      "epoch": 0.41420118343195267,
      "grad_norm": 0.04251974085259441,
      "learning_rate": 1.999946602771351e-05,
      "loss": 0.7899,
      "step": 70
    },
    {
      "epoch": 0.4437869822485207,
      "grad_norm": 0.04231610734472337,
      "learning_rate": 1.9993459494370938e-05,
      "loss": 0.7836,
      "step": 75
    },
    {
      "epoch": 0.47337278106508873,
      "grad_norm": 0.04031036781676351,
      "learning_rate": 1.9980782984658682e-05,
      "loss": 0.7624,
      "step": 80
    },
    {
      "epoch": 0.5029585798816568,
      "grad_norm": 0.042460210719998615,
      "learning_rate": 1.996144495931251e-05,
      "loss": 0.7687,
      "step": 85
    },
    {
      "epoch": 0.5325443786982249,
      "grad_norm": 0.042675110454449806,
      "learning_rate": 1.9935458325191365e-05,
      "loss": 0.7561,
      "step": 90
    },
    {
      "epoch": 0.5621301775147929,
      "grad_norm": 0.04388761175680471,
      "learning_rate": 1.9902840426662897e-05,
      "loss": 0.7676,
      "step": 95
    },
    {
      "epoch": 0.591715976331361,
      "grad_norm": 0.04391166921833054,
      "learning_rate": 1.9863613034027224e-05,
      "loss": 0.7472,
      "step": 100
    },
    {
      "epoch": 0.591715976331361,
      "eval_loss": 0.7797093987464905,
      "eval_runtime": 4.4687,
      "eval_samples_per_second": 28.643,
      "eval_steps_per_second": 0.895,
      "step": 100
    },
    {
      "epoch": 0.621301775147929,
      "grad_norm": 0.044684667850870004,
      "learning_rate": 1.9817802328986696e-05,
      "loss": 0.7472,
      "step": 105
    },
    {
      "epoch": 0.650887573964497,
      "grad_norm": 0.04258826815441478,
      "learning_rate": 1.9765438887171327e-05,
      "loss": 0.7401,
      "step": 110
    },
    {
      "epoch": 0.6804733727810651,
      "grad_norm": 0.043588774390386845,
      "learning_rate": 1.970655765773159e-05,
      "loss": 0.7444,
      "step": 115
    },
    {
      "epoch": 0.7100591715976331,
      "grad_norm": 0.0421267232664435,
      "learning_rate": 1.9641197940012136e-05,
      "loss": 0.7475,
      "step": 120
    },
    {
      "epoch": 0.7396449704142012,
      "grad_norm": 0.04267447120568237,
      "learning_rate": 1.956940335732209e-05,
      "loss": 0.7253,
      "step": 125
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.04086371969080693,
      "learning_rate": 1.9491221827819348e-05,
      "loss": 0.7409,
      "step": 130
    },
    {
      "epoch": 0.7988165680473372,
      "grad_norm": 0.04043252227097711,
      "learning_rate": 1.9406705532528373e-05,
      "loss": 0.7415,
      "step": 135
    },
    {
      "epoch": 0.8284023668639053,
      "grad_norm": 0.04682668124904222,
      "learning_rate": 1.9315910880512792e-05,
      "loss": 0.7384,
      "step": 140
    },
    {
      "epoch": 0.8579881656804734,
      "grad_norm": 0.039654489161062144,
      "learning_rate": 1.921889847122605e-05,
      "loss": 0.7307,
      "step": 145
    },
    {
      "epoch": 0.8875739644970414,
      "grad_norm": 0.03634493426436461,
      "learning_rate": 1.911573305406528e-05,
      "loss": 0.7232,
      "step": 150
    },
    {
      "epoch": 0.9171597633136095,
      "grad_norm": 0.03777827199813164,
      "learning_rate": 1.9006483485155338e-05,
      "loss": 0.7311,
      "step": 155
    },
    {
      "epoch": 0.9467455621301775,
      "grad_norm": 0.037213189706460266,
      "learning_rate": 1.8891222681391853e-05,
      "loss": 0.7264,
      "step": 160
    },
    {
      "epoch": 0.9763313609467456,
      "grad_norm": 0.038261030390930505,
      "learning_rate": 1.877002757177403e-05,
      "loss": 0.7016,
      "step": 165
    },
    {
      "epoch": 1.0059171597633136,
      "grad_norm": 0.03631182055849725,
      "learning_rate": 1.8642979046059595e-05,
      "loss": 0.7236,
      "step": 170
    },
    {
      "epoch": 1.0355029585798816,
      "grad_norm": 0.03503196580297209,
      "learning_rate": 1.8510161900776186e-05,
      "loss": 0.7111,
      "step": 175
    },
    {
      "epoch": 1.0650887573964498,
      "grad_norm": 0.034698922298204,
      "learning_rate": 1.8371664782625287e-05,
      "loss": 0.6932,
      "step": 180
    },
    {
      "epoch": 1.0946745562130178,
      "grad_norm": 0.03743423699320259,
      "learning_rate": 1.8227580129316368e-05,
      "loss": 0.6978,
      "step": 185
    },
    {
      "epoch": 1.1242603550295858,
      "grad_norm": 0.03524202782151412,
      "learning_rate": 1.8078004107870797e-05,
      "loss": 0.6917,
      "step": 190
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 0.0375298216668594,
      "learning_rate": 1.7923036550436706e-05,
      "loss": 0.7008,
      "step": 195
    },
    {
      "epoch": 1.183431952662722,
      "grad_norm": 0.03867347532761606,
      "learning_rate": 1.7762780887657576e-05,
      "loss": 0.6983,
      "step": 200
    },
    {
      "epoch": 1.183431952662722,
      "eval_loss": 0.7385222315788269,
      "eval_runtime": 3.9324,
      "eval_samples_per_second": 32.55,
      "eval_steps_per_second": 1.017,
      "step": 200
    },
    {
      "epoch": 1.21301775147929,
      "grad_norm": 0.03581826767546664,
      "learning_rate": 1.759734407963911e-05,
      "loss": 0.6965,
      "step": 205
    },
    {
      "epoch": 1.242603550295858,
      "grad_norm": 0.03481595103836402,
      "learning_rate": 1.74268365445604e-05,
      "loss": 0.6934,
      "step": 210
    },
    {
      "epoch": 1.272189349112426,
      "grad_norm": 0.035504494692074985,
      "learning_rate": 1.725137208497705e-05,
      "loss": 0.6948,
      "step": 215
    },
    {
      "epoch": 1.301775147928994,
      "grad_norm": 0.03598240955650257,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 0.7142,
      "step": 220
    },
    {
      "epoch": 1.331360946745562,
      "grad_norm": 0.03521212900070517,
      "learning_rate": 1.688604406645903e-05,
      "loss": 0.6872,
      "step": 225
    },
    {
      "epoch": 1.3609467455621302,
      "grad_norm": 0.03596491066327463,
      "learning_rate": 1.6696424339928153e-05,
      "loss": 0.6997,
      "step": 230
    },
    {
      "epoch": 1.3905325443786982,
      "grad_norm": 0.038371795676484494,
      "learning_rate": 1.6502335190958135e-05,
      "loss": 0.6984,
      "step": 235
    },
    {
      "epoch": 1.4201183431952662,
      "grad_norm": 0.037370481323347235,
      "learning_rate": 1.6303906161279554e-05,
      "loss": 0.692,
      "step": 240
    },
    {
      "epoch": 1.4497041420118344,
      "grad_norm": 0.03647746950156188,
      "learning_rate": 1.6101269689207656e-05,
      "loss": 0.6876,
      "step": 245
    },
    {
      "epoch": 1.4792899408284024,
      "grad_norm": 0.03733051388477393,
      "learning_rate": 1.5894561021248535e-05,
      "loss": 0.6985,
      "step": 250
    },
    {
      "epoch": 1.5088757396449703,
      "grad_norm": 0.035570820273413836,
      "learning_rate": 1.568391812183097e-05,
      "loss": 0.686,
      "step": 255
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.036503955812673176,
      "learning_rate": 1.5469481581224274e-05,
      "loss": 0.685,
      "step": 260
    },
    {
      "epoch": 1.5680473372781065,
      "grad_norm": 0.03435240635441457,
      "learning_rate": 1.5251394521703496e-05,
      "loss": 0.6827,
      "step": 265
    },
    {
      "epoch": 1.5976331360946747,
      "grad_norm": 0.035999442546033864,
      "learning_rate": 1.5029802502024788e-05,
      "loss": 0.6725,
      "step": 270
    },
    {
      "epoch": 1.6272189349112427,
      "grad_norm": 0.034967385411919655,
      "learning_rate": 1.4804853420274471e-05,
      "loss": 0.6708,
      "step": 275
    },
    {
      "epoch": 1.6568047337278107,
      "grad_norm": 0.038500018340142106,
      "learning_rate": 1.4576697415156818e-05,
      "loss": 0.6907,
      "step": 280
    },
    {
      "epoch": 1.6863905325443787,
      "grad_norm": 0.03607936811358716,
      "learning_rate": 1.434548676578634e-05,
      "loss": 0.6871,
      "step": 285
    },
    {
      "epoch": 1.7159763313609466,
      "grad_norm": 0.037935982292038796,
      "learning_rate": 1.4111375790051511e-05,
      "loss": 0.6916,
      "step": 290
    },
    {
      "epoch": 1.7455621301775148,
      "grad_norm": 0.03740588603655693,
      "learning_rate": 1.3874520741617734e-05,
      "loss": 0.6769,
      "step": 295
    },
    {
      "epoch": 1.7751479289940828,
      "grad_norm": 0.03781316521720255,
      "learning_rate": 1.3635079705638298e-05,
      "loss": 0.6787,
      "step": 300
    },
    {
      "epoch": 1.7751479289940828,
      "eval_loss": 0.7225233912467957,
      "eval_runtime": 3.896,
      "eval_samples_per_second": 32.854,
      "eval_steps_per_second": 1.027,
      "step": 300
    },
    {
      "epoch": 1.804733727810651,
      "grad_norm": 0.03684147982867632,
      "learning_rate": 1.3393212493242964e-05,
      "loss": 0.673,
      "step": 305
    },
    {
      "epoch": 1.834319526627219,
      "grad_norm": 0.036958930405955645,
      "learning_rate": 1.3149080534874519e-05,
      "loss": 0.6905,
      "step": 310
    },
    {
      "epoch": 1.863905325443787,
      "grad_norm": 0.035393072247303925,
      "learning_rate": 1.2902846772544625e-05,
      "loss": 0.6753,
      "step": 315
    },
    {
      "epoch": 1.893491124260355,
      "grad_norm": 0.036598478130330056,
      "learning_rate": 1.2654675551080724e-05,
      "loss": 0.6788,
      "step": 320
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.03999854077781464,
      "learning_rate": 1.2404732508436693e-05,
      "loss": 0.685,
      "step": 325
    },
    {
      "epoch": 1.952662721893491,
      "grad_norm": 0.037405932928342996,
      "learning_rate": 1.2153184465140413e-05,
      "loss": 0.6786,
      "step": 330
    },
    {
      "epoch": 1.9822485207100593,
      "grad_norm": 0.03798868898695689,
      "learning_rate": 1.1900199312952047e-05,
      "loss": 0.6814,
      "step": 335
    },
    {
      "epoch": 2.0118343195266273,
      "grad_norm": 0.036285061868877304,
      "learning_rate": 1.164594590280734e-05,
      "loss": 0.6621,
      "step": 340
    },
    {
      "epoch": 2.0414201183431953,
      "grad_norm": 0.03539055447805874,
      "learning_rate": 1.1390593932120742e-05,
      "loss": 0.6558,
      "step": 345
    },
    {
      "epoch": 2.0710059171597632,
      "grad_norm": 0.03711001548763239,
      "learning_rate": 1.1134313831523547e-05,
      "loss": 0.6481,
      "step": 350
    },
    {
      "epoch": 2.100591715976331,
      "grad_norm": 0.03734529118643292,
      "learning_rate": 1.0877276651112662e-05,
      "loss": 0.6634,
      "step": 355
    },
    {
      "epoch": 2.1301775147928996,
      "grad_norm": 0.03389709396902985,
      "learning_rate": 1.0619653946285948e-05,
      "loss": 0.6462,
      "step": 360
    },
    {
      "epoch": 2.1597633136094676,
      "grad_norm": 0.03664036555545947,
      "learning_rate": 1.0361617663240253e-05,
      "loss": 0.6574,
      "step": 365
    },
    {
      "epoch": 2.1893491124260356,
      "grad_norm": 0.03346490721266862,
      "learning_rate": 1.0103340024208674e-05,
      "loss": 0.6598,
      "step": 370
    },
    {
      "epoch": 2.2189349112426036,
      "grad_norm": 0.034686393706828245,
      "learning_rate": 9.844993412513533e-06,
      "loss": 0.6592,
      "step": 375
    },
    {
      "epoch": 2.2485207100591715,
      "grad_norm": 0.03692685900091157,
      "learning_rate": 9.586750257511868e-06,
      "loss": 0.6449,
      "step": 380
    },
    {
      "epoch": 2.2781065088757395,
      "grad_norm": 0.038895408749169386,
      "learning_rate": 9.328782919510186e-06,
      "loss": 0.65,
      "step": 385
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.03540745344286993,
      "learning_rate": 9.0712635747253e-06,
      "loss": 0.6554,
      "step": 390
    },
    {
      "epoch": 2.337278106508876,
      "grad_norm": 0.03688747957225052,
      "learning_rate": 8.81436410036804e-06,
      "loss": 0.6607,
      "step": 395
    },
    {
      "epoch": 2.366863905325444,
      "grad_norm": 0.03816522039597042,
      "learning_rate": 8.558255959926533e-06,
      "loss": 0.6562,
      "step": 400
    },
    {
      "epoch": 2.366863905325444,
      "eval_loss": 0.7159731984138489,
      "eval_runtime": 3.8971,
      "eval_samples_per_second": 32.845,
      "eval_steps_per_second": 1.026,
      "step": 400
    },
    {
      "epoch": 2.396449704142012,
      "grad_norm": 0.0375298273903243,
      "learning_rate": 8.30311008872561e-06,
      "loss": 0.668,
      "step": 405
    },
    {
      "epoch": 2.42603550295858,
      "grad_norm": 0.037252957514754846,
      "learning_rate": 8.04909677983872e-06,
      "loss": 0.6488,
      "step": 410
    },
    {
      "epoch": 2.455621301775148,
      "grad_norm": 0.034558480195383684,
      "learning_rate": 7.796385570428527e-06,
      "loss": 0.6557,
      "step": 415
    },
    {
      "epoch": 2.485207100591716,
      "grad_norm": 0.034157530882768045,
      "learning_rate": 7.545145128592009e-06,
      "loss": 0.6533,
      "step": 420
    },
    {
      "epoch": 2.5147928994082838,
      "grad_norm": 0.034024165783053784,
      "learning_rate": 7.295543140785604e-06,
      "loss": 0.6504,
      "step": 425
    },
    {
      "epoch": 2.544378698224852,
      "grad_norm": 0.034461272139452596,
      "learning_rate": 7.0477461999055365e-06,
      "loss": 0.6571,
      "step": 430
    },
    {
      "epoch": 2.57396449704142,
      "grad_norm": 0.034971434146786405,
      "learning_rate": 6.801919694098034e-06,
      "loss": 0.6712,
      "step": 435
    },
    {
      "epoch": 2.603550295857988,
      "grad_norm": 0.03448445678829296,
      "learning_rate": 6.558227696373617e-06,
      "loss": 0.6652,
      "step": 440
    },
    {
      "epoch": 2.633136094674556,
      "grad_norm": 0.03348089812222311,
      "learning_rate": 6.316832855099173e-06,
      "loss": 0.6723,
      "step": 445
    },
    {
      "epoch": 2.662721893491124,
      "grad_norm": 0.03493485618572703,
      "learning_rate": 6.077896285440874e-06,
      "loss": 0.6539,
      "step": 450
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.03536236462581573,
      "learning_rate": 5.841577461830408e-06,
      "loss": 0.6599,
      "step": 455
    },
    {
      "epoch": 2.7218934911242605,
      "grad_norm": 0.03573184501168575,
      "learning_rate": 5.608034111526298e-06,
      "loss": 0.6536,
      "step": 460
    },
    {
      "epoch": 2.7514792899408285,
      "grad_norm": 0.036220794443416506,
      "learning_rate": 5.377422109341332e-06,
      "loss": 0.6535,
      "step": 465
    },
    {
      "epoch": 2.7810650887573964,
      "grad_norm": 0.03312709314385146,
      "learning_rate": 5.149895373606405e-06,
      "loss": 0.6527,
      "step": 470
    },
    {
      "epoch": 2.8106508875739644,
      "grad_norm": 0.033750629304806705,
      "learning_rate": 4.92560576344013e-06,
      "loss": 0.6573,
      "step": 475
    },
    {
      "epoch": 2.8402366863905324,
      "grad_norm": 0.032923605874122096,
      "learning_rate": 4.704702977392914e-06,
      "loss": 0.6473,
      "step": 480
    },
    {
      "epoch": 2.8698224852071004,
      "grad_norm": 0.03393122814303807,
      "learning_rate": 4.487334453532998e-06,
      "loss": 0.6521,
      "step": 485
    },
    {
      "epoch": 2.899408284023669,
      "grad_norm": 0.03509666798145451,
      "learning_rate": 4.2736452710412645e-06,
      "loss": 0.6585,
      "step": 490
    },
    {
      "epoch": 2.9289940828402368,
      "grad_norm": 0.03470523621346759,
      "learning_rate": 4.063778053380446e-06,
      "loss": 0.6619,
      "step": 495
    },
    {
      "epoch": 2.9585798816568047,
      "grad_norm": 0.0336359519522038,
      "learning_rate": 3.857872873103322e-06,
      "loss": 0.6541,
      "step": 500
    },
    {
      "epoch": 2.9585798816568047,
      "eval_loss": 0.71187424659729,
      "eval_runtime": 3.7206,
      "eval_samples_per_second": 34.403,
      "eval_steps_per_second": 1.075,
      "step": 500
    },
    {
      "epoch": 2.9881656804733727,
      "grad_norm": 0.03587797192025539,
      "learning_rate": 3.6560671583635467e-06,
      "loss": 0.6569,
      "step": 505
    },
    {
      "epoch": 3.0177514792899407,
      "grad_norm": 0.03305695905729717,
      "learning_rate": 3.4584956011913693e-06,
      "loss": 0.6461,
      "step": 510
    },
    {
      "epoch": 3.0473372781065087,
      "grad_norm": 0.03403480180885219,
      "learning_rate": 3.2652900675956e-06,
      "loss": 0.6539,
      "step": 515
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 0.03268608410343077,
      "learning_rate": 3.0765795095517026e-06,
      "loss": 0.6405,
      "step": 520
    },
    {
      "epoch": 3.106508875739645,
      "grad_norm": 0.03491737032051446,
      "learning_rate": 2.8924898789348645e-06,
      "loss": 0.647,
      "step": 525
    },
    {
      "epoch": 3.136094674556213,
      "grad_norm": 0.032276848618409466,
      "learning_rate": 2.713144043455388e-06,
      "loss": 0.6405,
      "step": 530
    },
    {
      "epoch": 3.165680473372781,
      "grad_norm": 0.033487052568174885,
      "learning_rate": 2.538661704652595e-06,
      "loss": 0.651,
      "step": 535
    },
    {
      "epoch": 3.195266272189349,
      "grad_norm": 0.033817519825495954,
      "learning_rate": 2.369159318001937e-06,
      "loss": 0.6387,
      "step": 540
    },
    {
      "epoch": 3.224852071005917,
      "grad_norm": 0.03269007602295336,
      "learning_rate": 2.2047500151886047e-06,
      "loss": 0.6458,
      "step": 545
    },
    {
      "epoch": 3.2544378698224854,
      "grad_norm": 0.033514564267276344,
      "learning_rate": 2.045543528599607e-06,
      "loss": 0.6424,
      "step": 550
    },
    {
      "epoch": 3.2840236686390534,
      "grad_norm": 0.034200978342252324,
      "learning_rate": 1.8916461180845968e-06,
      "loss": 0.6455,
      "step": 555
    },
    {
      "epoch": 3.3136094674556213,
      "grad_norm": 0.03388367192276365,
      "learning_rate": 1.743160500034443e-06,
      "loss": 0.6423,
      "step": 560
    },
    {
      "epoch": 3.3431952662721893,
      "grad_norm": 0.033724924768830294,
      "learning_rate": 1.6001857788247755e-06,
      "loss": 0.6503,
      "step": 565
    },
    {
      "epoch": 3.3727810650887573,
      "grad_norm": 0.03236222939177426,
      "learning_rate": 1.4628173806703594e-06,
      "loss": 0.6478,
      "step": 570
    },
    {
      "epoch": 3.4023668639053253,
      "grad_norm": 0.033444745364966555,
      "learning_rate": 1.3311469899343698e-06,
      "loss": 0.6401,
      "step": 575
    },
    {
      "epoch": 3.4319526627218933,
      "grad_norm": 0.03258583715714408,
      "learning_rate": 1.2052624879351105e-06,
      "loss": 0.6395,
      "step": 580
    },
    {
      "epoch": 3.4615384615384617,
      "grad_norm": 0.032141899740800166,
      "learning_rate": 1.0852478942910228e-06,
      "loss": 0.6378,
      "step": 585
    },
    {
      "epoch": 3.4911242603550297,
      "grad_norm": 0.03345191292753584,
      "learning_rate": 9.711833108431234e-07,
      "loss": 0.6419,
      "step": 590
    },
    {
      "epoch": 3.5207100591715976,
      "grad_norm": 0.032834136562105674,
      "learning_rate": 8.631448681922994e-07,
      "loss": 0.631,
      "step": 595
    },
    {
      "epoch": 3.5502958579881656,
      "grad_norm": 0.033520073507518476,
      "learning_rate": 7.612046748871327e-07,
      "loss": 0.6384,
      "step": 600
    },
    {
      "epoch": 3.5502958579881656,
      "eval_loss": 0.7116674780845642,
      "eval_runtime": 3.72,
      "eval_samples_per_second": 34.409,
      "eval_steps_per_second": 1.075,
      "step": 600
    },
    {
      "epoch": 3.5798816568047336,
      "grad_norm": 0.03331998096099112,
      "learning_rate": 6.65430769296207e-07,
      "loss": 0.648,
      "step": 605
    },
    {
      "epoch": 3.609467455621302,
      "grad_norm": 0.033780344219381676,
      "learning_rate": 5.758870741969635e-07,
      "loss": 0.6534,
      "step": 610
    },
    {
      "epoch": 3.63905325443787,
      "grad_norm": 0.03229033935128746,
      "learning_rate": 4.926333541114558e-07,
      "loss": 0.6385,
      "step": 615
    },
    {
      "epoch": 3.668639053254438,
      "grad_norm": 0.034015562004934635,
      "learning_rate": 4.1572517541747294e-07,
      "loss": 0.6516,
      "step": 620
    },
    {
      "epoch": 3.698224852071006,
      "grad_norm": 0.032207786257717,
      "learning_rate": 3.4521386926163134e-07,
      "loss": 0.6465,
      "step": 625
    },
    {
      "epoch": 3.727810650887574,
      "grad_norm": 0.032943851509488704,
      "learning_rate": 2.811464972992195e-07,
      "loss": 0.6458,
      "step": 630
    },
    {
      "epoch": 3.757396449704142,
      "grad_norm": 0.03193926093707804,
      "learning_rate": 2.2356582028363548e-07,
      "loss": 0.6332,
      "step": 635
    },
    {
      "epoch": 3.78698224852071,
      "grad_norm": 0.03166937065451693,
      "learning_rate": 1.7251026952640583e-07,
      "loss": 0.6345,
      "step": 640
    },
    {
      "epoch": 3.8165680473372783,
      "grad_norm": 0.03299614094632811,
      "learning_rate": 1.2801392124681233e-07,
      "loss": 0.6394,
      "step": 645
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 0.033872962074929854,
      "learning_rate": 9.010647382825421e-08,
      "loss": 0.6416,
      "step": 650
    },
    {
      "epoch": 3.8757396449704142,
      "grad_norm": 0.032350769195266166,
      "learning_rate": 5.881322799653699e-08,
      "loss": 0.6428,
      "step": 655
    },
    {
      "epoch": 3.905325443786982,
      "grad_norm": 0.03157444405607885,
      "learning_rate": 3.4155069933301535e-08,
      "loss": 0.6439,
      "step": 660
    },
    {
      "epoch": 3.93491124260355,
      "grad_norm": 0.03356100155061544,
      "learning_rate": 1.6148457335876112e-08,
      "loss": 0.6403,
      "step": 665
    },
    {
      "epoch": 3.9644970414201186,
      "grad_norm": 0.03227590694531526,
      "learning_rate": 4.80540843283972e-09,
      "loss": 0.6368,
      "step": 670
    },
    {
      "epoch": 3.994082840236686,
      "grad_norm": 0.03249410651012755,
      "learning_rate": 1.3349396265516235e-10,
      "loss": 0.6345,
      "step": 675
    },
    {
      "epoch": 4.0,
      "step": 676,
      "total_flos": 308009150447616.0,
      "train_loss": 0.7016454796642947,
      "train_runtime": 9927.1291,
      "train_samples_per_second": 8.705,
      "train_steps_per_second": 0.068
    }
  ],
  "logging_steps": 5,
  "max_steps": 676,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 308009150447616.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}