{
  "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": 0.6439659821018778,
      "learning_rate": 1.4705882352941177e-06,
      "loss": 1.1017,
      "step": 5
    },
    {
      "epoch": 0.05917159763313609,
      "grad_norm": 0.5057877785583942,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 1.1007,
      "step": 10
    },
    {
      "epoch": 0.08875739644970414,
      "grad_norm": 0.34275947536219825,
      "learning_rate": 4.411764705882353e-06,
      "loss": 1.0629,
      "step": 15
    },
    {
      "epoch": 0.11834319526627218,
      "grad_norm": 0.33577063948976177,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.0051,
      "step": 20
    },
    {
      "epoch": 0.14792899408284024,
      "grad_norm": 0.2949471201474794,
      "learning_rate": 7.352941176470589e-06,
      "loss": 0.949,
      "step": 25
    },
    {
      "epoch": 0.17751479289940827,
      "grad_norm": 0.21159349877560912,
      "learning_rate": 8.823529411764707e-06,
      "loss": 0.9046,
      "step": 30
    },
    {
      "epoch": 0.20710059171597633,
      "grad_norm": 0.15856411969263493,
      "learning_rate": 1.0294117647058823e-05,
      "loss": 0.888,
      "step": 35
    },
    {
      "epoch": 0.23668639053254437,
      "grad_norm": 0.1353999900027582,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 0.8801,
      "step": 40
    },
    {
      "epoch": 0.26627218934911245,
      "grad_norm": 0.13487701799423293,
      "learning_rate": 1.323529411764706e-05,
      "loss": 0.8569,
      "step": 45
    },
    {
      "epoch": 0.2958579881656805,
      "grad_norm": 0.10937715780925006,
      "learning_rate": 1.4705882352941179e-05,
      "loss": 0.8411,
      "step": 50
    },
    {
      "epoch": 0.3254437869822485,
      "grad_norm": 0.10116789827792308,
      "learning_rate": 1.6176470588235296e-05,
      "loss": 0.8256,
      "step": 55
    },
    {
      "epoch": 0.35502958579881655,
      "grad_norm": 0.09486346656051839,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 0.8314,
      "step": 60
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.09783173154524022,
      "learning_rate": 1.911764705882353e-05,
      "loss": 0.8011,
      "step": 65
    },
    {
      "epoch": 0.41420118343195267,
      "grad_norm": 0.09449363160697857,
      "learning_rate": 1.999946602771351e-05,
      "loss": 0.7999,
      "step": 70
    },
    {
      "epoch": 0.4437869822485207,
      "grad_norm": 0.09797892714489181,
      "learning_rate": 1.9993459494370938e-05,
      "loss": 0.8084,
      "step": 75
    },
    {
      "epoch": 0.47337278106508873,
      "grad_norm": 0.09083934620130703,
      "learning_rate": 1.9980782984658682e-05,
      "loss": 0.7872,
      "step": 80
    },
    {
      "epoch": 0.5029585798816568,
      "grad_norm": 0.09674625831588454,
      "learning_rate": 1.996144495931251e-05,
      "loss": 0.789,
      "step": 85
    },
    {
      "epoch": 0.5325443786982249,
      "grad_norm": 0.09153750269543345,
      "learning_rate": 1.9935458325191365e-05,
      "loss": 0.7865,
      "step": 90
    },
    {
      "epoch": 0.5621301775147929,
      "grad_norm": 0.0957908326296121,
      "learning_rate": 1.9902840426662897e-05,
      "loss": 0.7924,
      "step": 95
    },
    {
      "epoch": 0.591715976331361,
      "grad_norm": 0.09259701132768274,
      "learning_rate": 1.9863613034027224e-05,
      "loss": 0.7665,
      "step": 100
    },
    {
      "epoch": 0.591715976331361,
      "eval_loss": 0.8009439706802368,
      "eval_runtime": 1.9876,
      "eval_samples_per_second": 64.399,
      "eval_steps_per_second": 2.012,
      "step": 100
    },
    {
      "epoch": 0.621301775147929,
      "grad_norm": 0.09861544877125988,
      "learning_rate": 1.9817802328986696e-05,
      "loss": 0.7689,
      "step": 105
    },
    {
      "epoch": 0.650887573964497,
      "grad_norm": 0.09818067763821876,
      "learning_rate": 1.9765438887171327e-05,
      "loss": 0.7788,
      "step": 110
    },
    {
      "epoch": 0.6804733727810651,
      "grad_norm": 0.10112115466155701,
      "learning_rate": 1.970655765773159e-05,
      "loss": 0.772,
      "step": 115
    },
    {
      "epoch": 0.7100591715976331,
      "grad_norm": 0.0914598701096024,
      "learning_rate": 1.9641197940012136e-05,
      "loss": 0.7596,
      "step": 120
    },
    {
      "epoch": 0.7396449704142012,
      "grad_norm": 0.10299550351836897,
      "learning_rate": 1.956940335732209e-05,
      "loss": 0.7608,
      "step": 125
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.09676217855032584,
      "learning_rate": 1.9491221827819348e-05,
      "loss": 0.7608,
      "step": 130
    },
    {
      "epoch": 0.7988165680473372,
      "grad_norm": 0.10054271920883129,
      "learning_rate": 1.9406705532528373e-05,
      "loss": 0.7625,
      "step": 135
    },
    {
      "epoch": 0.8284023668639053,
      "grad_norm": 0.09316749954420439,
      "learning_rate": 1.9315910880512792e-05,
      "loss": 0.7526,
      "step": 140
    },
    {
      "epoch": 0.8579881656804734,
      "grad_norm": 0.09924380627210336,
      "learning_rate": 1.921889847122605e-05,
      "loss": 0.758,
      "step": 145
    },
    {
      "epoch": 0.8875739644970414,
      "grad_norm": 0.0935394258583913,
      "learning_rate": 1.911573305406528e-05,
      "loss": 0.7667,
      "step": 150
    },
    {
      "epoch": 0.9171597633136095,
      "grad_norm": 0.0941062409493051,
      "learning_rate": 1.9006483485155338e-05,
      "loss": 0.7597,
      "step": 155
    },
    {
      "epoch": 0.9467455621301775,
      "grad_norm": 0.0945515154197286,
      "learning_rate": 1.8891222681391853e-05,
      "loss": 0.7583,
      "step": 160
    },
    {
      "epoch": 0.9763313609467456,
      "grad_norm": 0.0944093533101716,
      "learning_rate": 1.877002757177403e-05,
      "loss": 0.7402,
      "step": 165
    },
    {
      "epoch": 1.0059171597633136,
      "grad_norm": 0.1026209727213443,
      "learning_rate": 1.8642979046059595e-05,
      "loss": 0.7451,
      "step": 170
    },
    {
      "epoch": 1.0355029585798816,
      "grad_norm": 0.09253733372936898,
      "learning_rate": 1.8510161900776186e-05,
      "loss": 0.7227,
      "step": 175
    },
    {
      "epoch": 1.0650887573964498,
      "grad_norm": 0.10701582057186095,
      "learning_rate": 1.8371664782625287e-05,
      "loss": 0.7235,
      "step": 180
    },
    {
      "epoch": 1.0946745562130178,
      "grad_norm": 0.10901317779074045,
      "learning_rate": 1.8227580129316368e-05,
      "loss": 0.7297,
      "step": 185
    },
    {
      "epoch": 1.1242603550295858,
      "grad_norm": 0.09272510989071414,
      "learning_rate": 1.8078004107870797e-05,
      "loss": 0.7269,
      "step": 190
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 0.09753000927785783,
      "learning_rate": 1.7923036550436706e-05,
      "loss": 0.7225,
      "step": 195
    },
    {
      "epoch": 1.183431952662722,
      "grad_norm": 0.10006006351926447,
      "learning_rate": 1.7762780887657576e-05,
      "loss": 0.7224,
      "step": 200
    },
    {
      "epoch": 1.183431952662722,
      "eval_loss": 0.7682048082351685,
      "eval_runtime": 1.9381,
      "eval_samples_per_second": 66.045,
      "eval_steps_per_second": 2.064,
      "step": 200
    },
    {
      "epoch": 1.21301775147929,
      "grad_norm": 0.08514109288732025,
      "learning_rate": 1.759734407963911e-05,
      "loss": 0.7141,
      "step": 205
    },
    {
      "epoch": 1.242603550295858,
      "grad_norm": 0.10153944071881804,
      "learning_rate": 1.74268365445604e-05,
      "loss": 0.7251,
      "step": 210
    },
    {
      "epoch": 1.272189349112426,
      "grad_norm": 0.08516674487530249,
      "learning_rate": 1.725137208497705e-05,
      "loss": 0.7095,
      "step": 215
    },
    {
      "epoch": 1.301775147928994,
      "grad_norm": 0.09000557413388141,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 0.7221,
      "step": 220
    },
    {
      "epoch": 1.331360946745562,
      "grad_norm": 0.10261984193674742,
      "learning_rate": 1.688604406645903e-05,
      "loss": 0.7248,
      "step": 225
    },
    {
      "epoch": 1.3609467455621302,
      "grad_norm": 0.09063724453079985,
      "learning_rate": 1.6696424339928153e-05,
      "loss": 0.7189,
      "step": 230
    },
    {
      "epoch": 1.3905325443786982,
      "grad_norm": 0.0876664358809029,
      "learning_rate": 1.6502335190958135e-05,
      "loss": 0.7115,
      "step": 235
    },
    {
      "epoch": 1.4201183431952662,
      "grad_norm": 0.08926784554788682,
      "learning_rate": 1.6303906161279554e-05,
      "loss": 0.7052,
      "step": 240
    },
    {
      "epoch": 1.4497041420118344,
      "grad_norm": 0.09216166902850643,
      "learning_rate": 1.6101269689207656e-05,
      "loss": 0.7304,
      "step": 245
    },
    {
      "epoch": 1.4792899408284024,
      "grad_norm": 0.09489888582394233,
      "learning_rate": 1.5894561021248535e-05,
      "loss": 0.7094,
      "step": 250
    },
    {
      "epoch": 1.5088757396449703,
      "grad_norm": 0.09815715101407019,
      "learning_rate": 1.568391812183097e-05,
      "loss": 0.7125,
      "step": 255
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.11023233541754712,
      "learning_rate": 1.5469481581224274e-05,
      "loss": 0.7203,
      "step": 260
    },
    {
      "epoch": 1.5680473372781065,
      "grad_norm": 0.0990016959835567,
      "learning_rate": 1.5251394521703496e-05,
      "loss": 0.7162,
      "step": 265
    },
    {
      "epoch": 1.5976331360946747,
      "grad_norm": 0.09361562420520224,
      "learning_rate": 1.5029802502024788e-05,
      "loss": 0.7143,
      "step": 270
    },
    {
      "epoch": 1.6272189349112427,
      "grad_norm": 0.09061363853326403,
      "learning_rate": 1.4804853420274471e-05,
      "loss": 0.7178,
      "step": 275
    },
    {
      "epoch": 1.6568047337278107,
      "grad_norm": 0.09054748720794353,
      "learning_rate": 1.4576697415156818e-05,
      "loss": 0.7072,
      "step": 280
    },
    {
      "epoch": 1.6863905325443787,
      "grad_norm": 0.09231829692501531,
      "learning_rate": 1.434548676578634e-05,
      "loss": 0.7154,
      "step": 285
    },
    {
      "epoch": 1.7159763313609466,
      "grad_norm": 0.08703936573542412,
      "learning_rate": 1.4111375790051511e-05,
      "loss": 0.7011,
      "step": 290
    },
    {
      "epoch": 1.7455621301775148,
      "grad_norm": 0.08968479884070231,
      "learning_rate": 1.3874520741617734e-05,
      "loss": 0.7122,
      "step": 295
    },
    {
      "epoch": 1.7751479289940828,
      "grad_norm": 0.09437837766978704,
      "learning_rate": 1.3635079705638298e-05,
      "loss": 0.7017,
      "step": 300
    },
    {
      "epoch": 1.7751479289940828,
      "eval_loss": 0.752805233001709,
      "eval_runtime": 1.9496,
      "eval_samples_per_second": 65.655,
      "eval_steps_per_second": 2.052,
      "step": 300
    },
    {
      "epoch": 1.804733727810651,
      "grad_norm": 0.08903936053110759,
      "learning_rate": 1.3393212493242964e-05,
      "loss": 0.725,
      "step": 305
    },
    {
      "epoch": 1.834319526627219,
      "grad_norm": 0.08414153400589117,
      "learning_rate": 1.3149080534874519e-05,
      "loss": 0.7054,
      "step": 310
    },
    {
      "epoch": 1.863905325443787,
      "grad_norm": 0.09439034181825776,
      "learning_rate": 1.2902846772544625e-05,
      "loss": 0.7021,
      "step": 315
    },
    {
      "epoch": 1.893491124260355,
      "grad_norm": 0.08964239172806014,
      "learning_rate": 1.2654675551080724e-05,
      "loss": 0.7064,
      "step": 320
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.09358273223772219,
      "learning_rate": 1.2404732508436693e-05,
      "loss": 0.6996,
      "step": 325
    },
    {
      "epoch": 1.952662721893491,
      "grad_norm": 0.08800666939014279,
      "learning_rate": 1.2153184465140413e-05,
      "loss": 0.7137,
      "step": 330
    },
    {
      "epoch": 1.9822485207100593,
      "grad_norm": 0.09777074659138213,
      "learning_rate": 1.1900199312952047e-05,
      "loss": 0.7061,
      "step": 335
    },
    {
      "epoch": 2.0118343195266273,
      "grad_norm": 0.08420032391185793,
      "learning_rate": 1.164594590280734e-05,
      "loss": 0.6848,
      "step": 340
    },
    {
      "epoch": 2.0414201183431953,
      "grad_norm": 0.09709124491718055,
      "learning_rate": 1.1390593932120742e-05,
      "loss": 0.6797,
      "step": 345
    },
    {
      "epoch": 2.0710059171597632,
      "grad_norm": 0.08513494025885673,
      "learning_rate": 1.1134313831523547e-05,
      "loss": 0.6783,
      "step": 350
    },
    {
      "epoch": 2.100591715976331,
      "grad_norm": 0.08526343643130264,
      "learning_rate": 1.0877276651112662e-05,
      "loss": 0.683,
      "step": 355
    },
    {
      "epoch": 2.1301775147928996,
      "grad_norm": 0.08415048962920803,
      "learning_rate": 1.0619653946285948e-05,
      "loss": 0.6699,
      "step": 360
    },
    {
      "epoch": 2.1597633136094676,
      "grad_norm": 0.08993894149758148,
      "learning_rate": 1.0361617663240253e-05,
      "loss": 0.6616,
      "step": 365
    },
    {
      "epoch": 2.1893491124260356,
      "grad_norm": 0.08779637319471659,
      "learning_rate": 1.0103340024208674e-05,
      "loss": 0.6681,
      "step": 370
    },
    {
      "epoch": 2.2189349112426036,
      "grad_norm": 0.07716142615588464,
      "learning_rate": 9.844993412513533e-06,
      "loss": 0.6847,
      "step": 375
    },
    {
      "epoch": 2.2485207100591715,
      "grad_norm": 0.09680115255291638,
      "learning_rate": 9.586750257511868e-06,
      "loss": 0.6748,
      "step": 380
    },
    {
      "epoch": 2.2781065088757395,
      "grad_norm": 0.08727553994241195,
      "learning_rate": 9.328782919510186e-06,
      "loss": 0.6727,
      "step": 385
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.08569274603060249,
      "learning_rate": 9.0712635747253e-06,
      "loss": 0.6722,
      "step": 390
    },
    {
      "epoch": 2.337278106508876,
      "grad_norm": 0.08838223625297882,
      "learning_rate": 8.81436410036804e-06,
      "loss": 0.6792,
      "step": 395
    },
    {
      "epoch": 2.366863905325444,
      "grad_norm": 0.08243129604747186,
      "learning_rate": 8.558255959926533e-06,
      "loss": 0.6775,
      "step": 400
    },
    {
      "epoch": 2.366863905325444,
      "eval_loss": 0.7467715740203857,
      "eval_runtime": 1.954,
      "eval_samples_per_second": 65.506,
      "eval_steps_per_second": 2.047,
      "step": 400
    },
    {
      "epoch": 2.396449704142012,
      "grad_norm": 0.08372814834591441,
      "learning_rate": 8.30311008872561e-06,
      "loss": 0.6867,
      "step": 405
    },
    {
      "epoch": 2.42603550295858,
      "grad_norm": 0.08520010748643847,
      "learning_rate": 8.04909677983872e-06,
      "loss": 0.677,
      "step": 410
    },
    {
      "epoch": 2.455621301775148,
      "grad_norm": 0.08436113404879492,
      "learning_rate": 7.796385570428527e-06,
      "loss": 0.6811,
      "step": 415
    },
    {
      "epoch": 2.485207100591716,
      "grad_norm": 0.07770487004133524,
      "learning_rate": 7.545145128592009e-06,
      "loss": 0.6775,
      "step": 420
    },
    {
      "epoch": 2.5147928994082838,
      "grad_norm": 0.07873507288955481,
      "learning_rate": 7.295543140785604e-06,
      "loss": 0.6607,
      "step": 425
    },
    {
      "epoch": 2.544378698224852,
      "grad_norm": 0.08216416278696723,
      "learning_rate": 7.0477461999055365e-06,
      "loss": 0.6721,
      "step": 430
    },
    {
      "epoch": 2.57396449704142,
      "grad_norm": 0.07808001669903655,
      "learning_rate": 6.801919694098034e-06,
      "loss": 0.669,
      "step": 435
    },
    {
      "epoch": 2.603550295857988,
      "grad_norm": 0.07827371958864436,
      "learning_rate": 6.558227696373617e-06,
      "loss": 0.6737,
      "step": 440
    },
    {
      "epoch": 2.633136094674556,
      "grad_norm": 0.09029552025645185,
      "learning_rate": 6.316832855099173e-06,
      "loss": 0.68,
      "step": 445
    },
    {
      "epoch": 2.662721893491124,
      "grad_norm": 0.08627523522424184,
      "learning_rate": 6.077896285440874e-06,
      "loss": 0.6781,
      "step": 450
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.0944458646122902,
      "learning_rate": 5.841577461830408e-06,
      "loss": 0.6856,
      "step": 455
    },
    {
      "epoch": 2.7218934911242605,
      "grad_norm": 0.08627859291249917,
      "learning_rate": 5.608034111526298e-06,
      "loss": 0.6828,
      "step": 460
    },
    {
      "epoch": 2.7514792899408285,
      "grad_norm": 0.07636613357565422,
      "learning_rate": 5.377422109341332e-06,
      "loss": 0.6631,
      "step": 465
    },
    {
      "epoch": 2.7810650887573964,
      "grad_norm": 0.07763420602167485,
      "learning_rate": 5.149895373606405e-06,
      "loss": 0.6706,
      "step": 470
    },
    {
      "epoch": 2.8106508875739644,
      "grad_norm": 0.0797684563299413,
      "learning_rate": 4.92560576344013e-06,
      "loss": 0.6726,
      "step": 475
    },
    {
      "epoch": 2.8402366863905324,
      "grad_norm": 0.0743258532275492,
      "learning_rate": 4.704702977392914e-06,
      "loss": 0.6681,
      "step": 480
    },
    {
      "epoch": 2.8698224852071004,
      "grad_norm": 0.08260380529165902,
      "learning_rate": 4.487334453532998e-06,
      "loss": 0.6732,
      "step": 485
    },
    {
      "epoch": 2.899408284023669,
      "grad_norm": 0.07603345763322027,
      "learning_rate": 4.2736452710412645e-06,
      "loss": 0.6759,
      "step": 490
    },
    {
      "epoch": 2.9289940828402368,
      "grad_norm": 0.0788588593958065,
      "learning_rate": 4.063778053380446e-06,
      "loss": 0.6669,
      "step": 495
    },
    {
      "epoch": 2.9585798816568047,
      "grad_norm": 0.0765652404714636,
      "learning_rate": 3.857872873103322e-06,
      "loss": 0.6694,
      "step": 500
    },
    {
      "epoch": 2.9585798816568047,
      "eval_loss": 0.7420404553413391,
      "eval_runtime": 1.949,
      "eval_samples_per_second": 65.673,
      "eval_steps_per_second": 2.052,
      "step": 500
    },
    {
      "epoch": 2.9881656804733727,
      "grad_norm": 0.07687126382252668,
      "learning_rate": 3.6560671583635467e-06,
      "loss": 0.6723,
      "step": 505
    },
    {
      "epoch": 3.0177514792899407,
      "grad_norm": 0.07912130181111991,
      "learning_rate": 3.4584956011913693e-06,
      "loss": 0.6602,
      "step": 510
    },
    {
      "epoch": 3.0473372781065087,
      "grad_norm": 0.07360557876355839,
      "learning_rate": 3.2652900675956e-06,
      "loss": 0.6566,
      "step": 515
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 0.0787952110142718,
      "learning_rate": 3.0765795095517026e-06,
      "loss": 0.6599,
      "step": 520
    },
    {
      "epoch": 3.106508875739645,
      "grad_norm": 0.07557678307758718,
      "learning_rate": 2.8924898789348645e-06,
      "loss": 0.6659,
      "step": 525
    },
    {
      "epoch": 3.136094674556213,
      "grad_norm": 0.07175247734719413,
      "learning_rate": 2.713144043455388e-06,
      "loss": 0.6646,
      "step": 530
    },
    {
      "epoch": 3.165680473372781,
      "grad_norm": 0.07747698601868783,
      "learning_rate": 2.538661704652595e-06,
      "loss": 0.6605,
      "step": 535
    },
    {
      "epoch": 3.195266272189349,
      "grad_norm": 0.0718076928664842,
      "learning_rate": 2.369159318001937e-06,
      "loss": 0.6543,
      "step": 540
    },
    {
      "epoch": 3.224852071005917,
      "grad_norm": 0.07533978001859822,
      "learning_rate": 2.2047500151886047e-06,
      "loss": 0.6531,
      "step": 545
    },
    {
      "epoch": 3.2544378698224854,
      "grad_norm": 0.07485842542784214,
      "learning_rate": 2.045543528599607e-06,
      "loss": 0.6646,
      "step": 550
    },
    {
      "epoch": 3.2840236686390534,
      "grad_norm": 0.0708662804937619,
      "learning_rate": 1.8916461180845968e-06,
      "loss": 0.648,
      "step": 555
    },
    {
      "epoch": 3.3136094674556213,
      "grad_norm": 0.0757464412979693,
      "learning_rate": 1.743160500034443e-06,
      "loss": 0.6395,
      "step": 560
    },
    {
      "epoch": 3.3431952662721893,
      "grad_norm": 0.07734435238783051,
      "learning_rate": 1.6001857788247755e-06,
      "loss": 0.6495,
      "step": 565
    },
    {
      "epoch": 3.3727810650887573,
      "grad_norm": 0.0725938998129201,
      "learning_rate": 1.4628173806703594e-06,
      "loss": 0.6552,
      "step": 570
    },
    {
      "epoch": 3.4023668639053253,
      "grad_norm": 0.07170585944252475,
      "learning_rate": 1.3311469899343698e-06,
      "loss": 0.6556,
      "step": 575
    },
    {
      "epoch": 3.4319526627218933,
      "grad_norm": 0.07035425662199751,
      "learning_rate": 1.2052624879351105e-06,
      "loss": 0.6514,
      "step": 580
    },
    {
      "epoch": 3.4615384615384617,
      "grad_norm": 0.0716406331513175,
      "learning_rate": 1.0852478942910228e-06,
      "loss": 0.6556,
      "step": 585
    },
    {
      "epoch": 3.4911242603550297,
      "grad_norm": 0.07161356638036934,
      "learning_rate": 9.711833108431234e-07,
      "loss": 0.6501,
      "step": 590
    },
    {
      "epoch": 3.5207100591715976,
      "grad_norm": 0.0707175122399628,
      "learning_rate": 8.631448681922994e-07,
      "loss": 0.6607,
      "step": 595
    },
    {
      "epoch": 3.5502958579881656,
      "grad_norm": 0.07021197999680215,
      "learning_rate": 7.612046748871327e-07,
      "loss": 0.6649,
      "step": 600
    },
    {
      "epoch": 3.5502958579881656,
      "eval_loss": 0.7433957457542419,
      "eval_runtime": 1.9404,
      "eval_samples_per_second": 65.967,
      "eval_steps_per_second": 2.061,
      "step": 600
    },
    {
      "epoch": 3.5798816568047336,
      "grad_norm": 0.06889588969409026,
      "learning_rate": 6.65430769296207e-07,
      "loss": 0.6427,
      "step": 605
    },
    {
      "epoch": 3.609467455621302,
      "grad_norm": 0.07042732460501529,
      "learning_rate": 5.758870741969635e-07,
      "loss": 0.6524,
      "step": 610
    },
    {
      "epoch": 3.63905325443787,
      "grad_norm": 0.06830708719143527,
      "learning_rate": 4.926333541114558e-07,
      "loss": 0.6604,
      "step": 615
    },
    {
      "epoch": 3.668639053254438,
      "grad_norm": 0.07062137013338904,
      "learning_rate": 4.1572517541747294e-07,
      "loss": 0.6541,
      "step": 620
    },
    {
      "epoch": 3.698224852071006,
      "grad_norm": 0.06967910127337004,
      "learning_rate": 3.4521386926163134e-07,
      "loss": 0.6491,
      "step": 625
    },
    {
      "epoch": 3.727810650887574,
      "grad_norm": 0.06931589660694865,
      "learning_rate": 2.811464972992195e-07,
      "loss": 0.6444,
      "step": 630
    },
    {
      "epoch": 3.757396449704142,
      "grad_norm": 0.06857941794190696,
      "learning_rate": 2.2356582028363548e-07,
      "loss": 0.652,
      "step": 635
    },
    {
      "epoch": 3.78698224852071,
      "grad_norm": 0.07146304965594258,
      "learning_rate": 1.7251026952640583e-07,
      "loss": 0.6547,
      "step": 640
    },
    {
      "epoch": 3.8165680473372783,
      "grad_norm": 0.06914829105737026,
      "learning_rate": 1.2801392124681233e-07,
      "loss": 0.6419,
      "step": 645
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 0.06976851389737697,
      "learning_rate": 9.010647382825421e-08,
      "loss": 0.6559,
      "step": 650
    },
    {
      "epoch": 3.8757396449704142,
      "grad_norm": 0.06949483068766184,
      "learning_rate": 5.881322799653699e-08,
      "loss": 0.6559,
      "step": 655
    },
    {
      "epoch": 3.905325443786982,
      "grad_norm": 0.06853851606881345,
      "learning_rate": 3.4155069933301535e-08,
      "loss": 0.6515,
      "step": 660
    },
    {
      "epoch": 3.93491124260355,
      "grad_norm": 0.07221419070779167,
      "learning_rate": 1.6148457335876112e-08,
      "loss": 0.646,
      "step": 665
    },
    {
      "epoch": 3.9644970414201186,
      "grad_norm": 0.06942961780673317,
      "learning_rate": 4.80540843283972e-09,
      "loss": 0.6653,
      "step": 670
    },
    {
      "epoch": 3.994082840236686,
      "grad_norm": 0.0680541699351626,
      "learning_rate": 1.3349396265516235e-10,
      "loss": 0.6561,
      "step": 675
    },
    {
      "epoch": 4.0,
      "step": 676,
      "total_flos": 308009150447616.0,
      "train_loss": 0.7185798888728463,
      "train_runtime": 4924.3182,
      "train_samples_per_second": 17.554,
      "train_steps_per_second": 0.137
    }
  ],
  "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": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 308009150447616.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}