{
  "best_global_step": 500,
  "best_metric": 0.8945327997207642,
  "best_model_checkpoint": "runs/instruct_run_24b/checkpoints/checkpoint-500",
  "epoch": 0.21574973031283712,
  "eval_steps": 100,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008629989212513484,
      "grad_norm": 1.9118273258209229,
      "learning_rate": 8.984725965858042e-08,
      "loss": 1.398809790611267,
      "step": 2
    },
    {
      "epoch": 0.001725997842502697,
      "grad_norm": 1.785147786140442,
      "learning_rate": 2.6954177897574125e-07,
      "loss": 1.3699476718902588,
      "step": 4
    },
    {
      "epoch": 0.0025889967637540453,
      "grad_norm": 1.6857414245605469,
      "learning_rate": 4.492362982929021e-07,
      "loss": 1.4487650394439697,
      "step": 6
    },
    {
      "epoch": 0.003451995685005394,
      "grad_norm": 1.7351312637329102,
      "learning_rate": 6.28930817610063e-07,
      "loss": 1.3360817432403564,
      "step": 8
    },
    {
      "epoch": 0.004314994606256742,
      "grad_norm": 1.7769269943237305,
      "learning_rate": 8.086253369272238e-07,
      "loss": 1.4294791221618652,
      "step": 10
    },
    {
      "epoch": 0.005177993527508091,
      "grad_norm": 1.776668906211853,
      "learning_rate": 9.883198562443846e-07,
      "loss": 1.3927934169769287,
      "step": 12
    },
    {
      "epoch": 0.006040992448759439,
      "grad_norm": 1.500367283821106,
      "learning_rate": 1.1680143755615454e-06,
      "loss": 1.4140764474868774,
      "step": 14
    },
    {
      "epoch": 0.006903991370010788,
      "grad_norm": 1.7255949974060059,
      "learning_rate": 1.3477088948787064e-06,
      "loss": 1.3873623609542847,
      "step": 16
    },
    {
      "epoch": 0.007766990291262136,
      "grad_norm": 1.9073798656463623,
      "learning_rate": 1.5274034141958671e-06,
      "loss": 1.4562759399414062,
      "step": 18
    },
    {
      "epoch": 0.008629989212513484,
      "grad_norm": 1.7253859043121338,
      "learning_rate": 1.707097933513028e-06,
      "loss": 1.4264800548553467,
      "step": 20
    },
    {
      "epoch": 0.009492988133764833,
      "grad_norm": 1.4858287572860718,
      "learning_rate": 1.8867924528301887e-06,
      "loss": 1.3717138767242432,
      "step": 22
    },
    {
      "epoch": 0.010355987055016181,
      "grad_norm": 1.7516961097717285,
      "learning_rate": 2.0664869721473496e-06,
      "loss": 1.3605879545211792,
      "step": 24
    },
    {
      "epoch": 0.01121898597626753,
      "grad_norm": 1.754793643951416,
      "learning_rate": 2.2461814914645104e-06,
      "loss": 1.465327262878418,
      "step": 26
    },
    {
      "epoch": 0.012081984897518877,
      "grad_norm": 1.5204869508743286,
      "learning_rate": 2.425876010781671e-06,
      "loss": 1.3205785751342773,
      "step": 28
    },
    {
      "epoch": 0.012944983818770227,
      "grad_norm": 2.03002667427063,
      "learning_rate": 2.605570530098832e-06,
      "loss": 1.4751381874084473,
      "step": 30
    },
    {
      "epoch": 0.013807982740021575,
      "grad_norm": 1.6153842210769653,
      "learning_rate": 2.785265049415993e-06,
      "loss": 1.3976212739944458,
      "step": 32
    },
    {
      "epoch": 0.014670981661272923,
      "grad_norm": 1.7034062147140503,
      "learning_rate": 2.964959568733154e-06,
      "loss": 1.4062179327011108,
      "step": 34
    },
    {
      "epoch": 0.015533980582524271,
      "grad_norm": 1.5724587440490723,
      "learning_rate": 3.1446540880503146e-06,
      "loss": 1.2940696477890015,
      "step": 36
    },
    {
      "epoch": 0.01639697950377562,
      "grad_norm": 1.7072066068649292,
      "learning_rate": 3.324348607367475e-06,
      "loss": 1.4216598272323608,
      "step": 38
    },
    {
      "epoch": 0.017259978425026967,
      "grad_norm": 1.6051130294799805,
      "learning_rate": 3.504043126684636e-06,
      "loss": 1.4204131364822388,
      "step": 40
    },
    {
      "epoch": 0.018122977346278317,
      "grad_norm": 1.5114386081695557,
      "learning_rate": 3.683737646001797e-06,
      "loss": 1.3492953777313232,
      "step": 42
    },
    {
      "epoch": 0.018985976267529667,
      "grad_norm": 1.5557284355163574,
      "learning_rate": 3.863432165318958e-06,
      "loss": 1.4241598844528198,
      "step": 44
    },
    {
      "epoch": 0.019848975188781013,
      "grad_norm": 1.5814268589019775,
      "learning_rate": 4.0431266846361185e-06,
      "loss": 1.3903125524520874,
      "step": 46
    },
    {
      "epoch": 0.020711974110032363,
      "grad_norm": 1.53256356716156,
      "learning_rate": 4.22282120395328e-06,
      "loss": 1.3726638555526733,
      "step": 48
    },
    {
      "epoch": 0.021574973031283712,
      "grad_norm": 1.5670084953308105,
      "learning_rate": 4.40251572327044e-06,
      "loss": 1.2536468505859375,
      "step": 50
    },
    {
      "epoch": 0.02243797195253506,
      "grad_norm": 1.3708246946334839,
      "learning_rate": 4.582210242587602e-06,
      "loss": 1.2309948205947876,
      "step": 52
    },
    {
      "epoch": 0.02330097087378641,
      "grad_norm": 1.5670109987258911,
      "learning_rate": 4.7619047619047615e-06,
      "loss": 1.3564441204071045,
      "step": 54
    },
    {
      "epoch": 0.024163969795037755,
      "grad_norm": 1.3550655841827393,
      "learning_rate": 4.941599281221923e-06,
      "loss": 1.2251620292663574,
      "step": 56
    },
    {
      "epoch": 0.025026968716289105,
      "grad_norm": 1.4416121244430542,
      "learning_rate": 5.121293800539084e-06,
      "loss": 1.2395249605178833,
      "step": 58
    },
    {
      "epoch": 0.025889967637540454,
      "grad_norm": 1.4638670682907104,
      "learning_rate": 5.300988319856245e-06,
      "loss": 1.3229656219482422,
      "step": 60
    },
    {
      "epoch": 0.0267529665587918,
      "grad_norm": 1.2204002141952515,
      "learning_rate": 5.4806828391734054e-06,
      "loss": 1.1076340675354004,
      "step": 62
    },
    {
      "epoch": 0.02761596548004315,
      "grad_norm": 1.2641915082931519,
      "learning_rate": 5.660377358490566e-06,
      "loss": 1.237392544746399,
      "step": 64
    },
    {
      "epoch": 0.0284789644012945,
      "grad_norm": 1.4635342359542847,
      "learning_rate": 5.840071877807727e-06,
      "loss": 1.3567079305648804,
      "step": 66
    },
    {
      "epoch": 0.029341963322545846,
      "grad_norm": 1.5813465118408203,
      "learning_rate": 6.019766397124888e-06,
      "loss": 1.3595421314239502,
      "step": 68
    },
    {
      "epoch": 0.030204962243797196,
      "grad_norm": 1.435356616973877,
      "learning_rate": 6.1994609164420485e-06,
      "loss": 1.2183864116668701,
      "step": 70
    },
    {
      "epoch": 0.031067961165048542,
      "grad_norm": 1.4559556245803833,
      "learning_rate": 6.37915543575921e-06,
      "loss": 1.2084243297576904,
      "step": 72
    },
    {
      "epoch": 0.03193096008629989,
      "grad_norm": 1.2870471477508545,
      "learning_rate": 6.558849955076371e-06,
      "loss": 1.2476426362991333,
      "step": 74
    },
    {
      "epoch": 0.03279395900755124,
      "grad_norm": 1.3345798254013062,
      "learning_rate": 6.738544474393531e-06,
      "loss": 1.2200642824172974,
      "step": 76
    },
    {
      "epoch": 0.03365695792880259,
      "grad_norm": 1.48223876953125,
      "learning_rate": 6.918238993710692e-06,
      "loss": 1.2497955560684204,
      "step": 78
    },
    {
      "epoch": 0.034519956850053934,
      "grad_norm": 1.2421257495880127,
      "learning_rate": 7.097933513027853e-06,
      "loss": 1.1987318992614746,
      "step": 80
    },
    {
      "epoch": 0.035382955771305284,
      "grad_norm": 1.5042678117752075,
      "learning_rate": 7.277628032345015e-06,
      "loss": 1.218438982963562,
      "step": 82
    },
    {
      "epoch": 0.036245954692556634,
      "grad_norm": 1.3047534227371216,
      "learning_rate": 7.457322551662174e-06,
      "loss": 1.1181117296218872,
      "step": 84
    },
    {
      "epoch": 0.037108953613807984,
      "grad_norm": 1.3297117948532104,
      "learning_rate": 7.637017070979335e-06,
      "loss": 1.047302484512329,
      "step": 86
    },
    {
      "epoch": 0.03797195253505933,
      "grad_norm": 1.4515916109085083,
      "learning_rate": 7.816711590296496e-06,
      "loss": 1.1821871995925903,
      "step": 88
    },
    {
      "epoch": 0.038834951456310676,
      "grad_norm": 1.5435426235198975,
      "learning_rate": 7.996406109613658e-06,
      "loss": 1.1171189546585083,
      "step": 90
    },
    {
      "epoch": 0.039697950377562026,
      "grad_norm": 1.5270947217941284,
      "learning_rate": 8.176100628930818e-06,
      "loss": 1.067047357559204,
      "step": 92
    },
    {
      "epoch": 0.040560949298813376,
      "grad_norm": 2.4402992725372314,
      "learning_rate": 8.35579514824798e-06,
      "loss": 1.0745081901550293,
      "step": 94
    },
    {
      "epoch": 0.041423948220064725,
      "grad_norm": 1.7703081369400024,
      "learning_rate": 8.53548966756514e-06,
      "loss": 1.252164602279663,
      "step": 96
    },
    {
      "epoch": 0.042286947141316075,
      "grad_norm": 1.4324337244033813,
      "learning_rate": 8.715184186882301e-06,
      "loss": 1.1030420064926147,
      "step": 98
    },
    {
      "epoch": 0.043149946062567425,
      "grad_norm": 1.3258590698242188,
      "learning_rate": 8.89487870619946e-06,
      "loss": 1.0817893743515015,
      "step": 100
    },
    {
      "epoch": 0.043149946062567425,
      "eval_loss": 1.128923773765564,
      "eval_runtime": 825.0166,
      "eval_samples_per_second": 2.497,
      "eval_steps_per_second": 2.497,
      "step": 100
    },
    {
      "epoch": 0.04401294498381877,
      "grad_norm": 1.5833592414855957,
      "learning_rate": 9.074573225516622e-06,
      "loss": 1.0982940196990967,
      "step": 102
    },
    {
      "epoch": 0.04487594390507012,
      "grad_norm": 1.5289201736450195,
      "learning_rate": 9.254267744833784e-06,
      "loss": 1.0529299974441528,
      "step": 104
    },
    {
      "epoch": 0.04573894282632147,
      "grad_norm": 1.4507837295532227,
      "learning_rate": 9.433962264150944e-06,
      "loss": 1.0896434783935547,
      "step": 106
    },
    {
      "epoch": 0.04660194174757282,
      "grad_norm": 1.3846485614776611,
      "learning_rate": 9.613656783468104e-06,
      "loss": 1.1196398735046387,
      "step": 108
    },
    {
      "epoch": 0.04746494066882417,
      "grad_norm": 1.4094940423965454,
      "learning_rate": 9.793351302785265e-06,
      "loss": 1.1305382251739502,
      "step": 110
    },
    {
      "epoch": 0.04832793959007551,
      "grad_norm": 1.7674189805984497,
      "learning_rate": 9.973045822102427e-06,
      "loss": 1.0138700008392334,
      "step": 112
    },
    {
      "epoch": 0.04919093851132686,
      "grad_norm": 1.6083961725234985,
      "learning_rate": 1.0152740341419587e-05,
      "loss": 1.0583173036575317,
      "step": 114
    },
    {
      "epoch": 0.05005393743257821,
      "grad_norm": 1.7483229637145996,
      "learning_rate": 1.0332434860736747e-05,
      "loss": 1.1116671562194824,
      "step": 116
    },
    {
      "epoch": 0.05091693635382956,
      "grad_norm": 1.8256834745407104,
      "learning_rate": 1.0512129380053909e-05,
      "loss": 1.0832366943359375,
      "step": 118
    },
    {
      "epoch": 0.05177993527508091,
      "grad_norm": 1.5875557661056519,
      "learning_rate": 1.069182389937107e-05,
      "loss": 1.1089236736297607,
      "step": 120
    },
    {
      "epoch": 0.05264293419633225,
      "grad_norm": 1.6553549766540527,
      "learning_rate": 1.087151841868823e-05,
      "loss": 1.1191619634628296,
      "step": 122
    },
    {
      "epoch": 0.0535059331175836,
      "grad_norm": 1.3675798177719116,
      "learning_rate": 1.1051212938005392e-05,
      "loss": 1.031973958015442,
      "step": 124
    },
    {
      "epoch": 0.05436893203883495,
      "grad_norm": 1.5343760251998901,
      "learning_rate": 1.1230907457322552e-05,
      "loss": 0.9964010119438171,
      "step": 126
    },
    {
      "epoch": 0.0552319309600863,
      "grad_norm": 1.5928982496261597,
      "learning_rate": 1.1410601976639713e-05,
      "loss": 1.1144609451293945,
      "step": 128
    },
    {
      "epoch": 0.05609492988133765,
      "grad_norm": 1.6411585807800293,
      "learning_rate": 1.1590296495956873e-05,
      "loss": 0.9953935146331787,
      "step": 130
    },
    {
      "epoch": 0.056957928802589,
      "grad_norm": 1.6077220439910889,
      "learning_rate": 1.1769991015274035e-05,
      "loss": 0.9940203428268433,
      "step": 132
    },
    {
      "epoch": 0.05782092772384034,
      "grad_norm": 1.7327438592910767,
      "learning_rate": 1.1949685534591196e-05,
      "loss": 1.045546293258667,
      "step": 134
    },
    {
      "epoch": 0.05868392664509169,
      "grad_norm": 1.607404112815857,
      "learning_rate": 1.2129380053908356e-05,
      "loss": 0.9932523369789124,
      "step": 136
    },
    {
      "epoch": 0.05954692556634304,
      "grad_norm": 1.5056802034378052,
      "learning_rate": 1.2309074573225516e-05,
      "loss": 0.9584172368049622,
      "step": 138
    },
    {
      "epoch": 0.06040992448759439,
      "grad_norm": 1.5453966856002808,
      "learning_rate": 1.2488769092542678e-05,
      "loss": 0.9733421206474304,
      "step": 140
    },
    {
      "epoch": 0.06127292340884574,
      "grad_norm": 1.546397089958191,
      "learning_rate": 1.2668463611859838e-05,
      "loss": 0.9971115589141846,
      "step": 142
    },
    {
      "epoch": 0.062135922330097085,
      "grad_norm": 1.5259592533111572,
      "learning_rate": 1.2848158131177e-05,
      "loss": 1.0994833707809448,
      "step": 144
    },
    {
      "epoch": 0.06299892125134844,
      "grad_norm": 1.56397545337677,
      "learning_rate": 1.302785265049416e-05,
      "loss": 1.0203801393508911,
      "step": 146
    },
    {
      "epoch": 0.06386192017259978,
      "grad_norm": 1.618053674697876,
      "learning_rate": 1.320754716981132e-05,
      "loss": 1.0223872661590576,
      "step": 148
    },
    {
      "epoch": 0.06472491909385113,
      "grad_norm": 1.9544042348861694,
      "learning_rate": 1.3387241689128482e-05,
      "loss": 1.0207403898239136,
      "step": 150
    },
    {
      "epoch": 0.06558791801510248,
      "grad_norm": 1.7001299858093262,
      "learning_rate": 1.3566936208445644e-05,
      "loss": 1.025482177734375,
      "step": 152
    },
    {
      "epoch": 0.06645091693635383,
      "grad_norm": 1.9833810329437256,
      "learning_rate": 1.3746630727762804e-05,
      "loss": 1.0077980756759644,
      "step": 154
    },
    {
      "epoch": 0.06731391585760518,
      "grad_norm": 1.6378769874572754,
      "learning_rate": 1.3926325247079966e-05,
      "loss": 1.0046619176864624,
      "step": 156
    },
    {
      "epoch": 0.06817691477885653,
      "grad_norm": 1.762683629989624,
      "learning_rate": 1.4106019766397124e-05,
      "loss": 1.0332108736038208,
      "step": 158
    },
    {
      "epoch": 0.06903991370010787,
      "grad_norm": 1.5698739290237427,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.973042905330658,
      "step": 160
    },
    {
      "epoch": 0.06990291262135923,
      "grad_norm": 1.6132292747497559,
      "learning_rate": 1.4465408805031447e-05,
      "loss": 0.9966566562652588,
      "step": 162
    },
    {
      "epoch": 0.07076591154261057,
      "grad_norm": 1.989534616470337,
      "learning_rate": 1.4645103324348609e-05,
      "loss": 1.078708529472351,
      "step": 164
    },
    {
      "epoch": 0.07162891046386193,
      "grad_norm": 1.8199284076690674,
      "learning_rate": 1.4824797843665769e-05,
      "loss": 0.9075545072555542,
      "step": 166
    },
    {
      "epoch": 0.07249190938511327,
      "grad_norm": 1.6908831596374512,
      "learning_rate": 1.500449236298293e-05,
      "loss": 0.9268680810928345,
      "step": 168
    },
    {
      "epoch": 0.07335490830636461,
      "grad_norm": 1.5648242235183716,
      "learning_rate": 1.5184186882300092e-05,
      "loss": 1.0361101627349854,
      "step": 170
    },
    {
      "epoch": 0.07421790722761597,
      "grad_norm": 1.8292360305786133,
      "learning_rate": 1.5363881401617252e-05,
      "loss": 0.9197717905044556,
      "step": 172
    },
    {
      "epoch": 0.07508090614886731,
      "grad_norm": 1.6882517337799072,
      "learning_rate": 1.554357592093441e-05,
      "loss": 0.9661652445793152,
      "step": 174
    },
    {
      "epoch": 0.07594390507011867,
      "grad_norm": 1.695921778678894,
      "learning_rate": 1.572327044025157e-05,
      "loss": 1.0006932020187378,
      "step": 176
    },
    {
      "epoch": 0.07680690399137001,
      "grad_norm": 2.0128681659698486,
      "learning_rate": 1.5902964959568733e-05,
      "loss": 1.0096064805984497,
      "step": 178
    },
    {
      "epoch": 0.07766990291262135,
      "grad_norm": 1.6833231449127197,
      "learning_rate": 1.6082659478885895e-05,
      "loss": 0.972679853439331,
      "step": 180
    },
    {
      "epoch": 0.07853290183387271,
      "grad_norm": 1.6940670013427734,
      "learning_rate": 1.6262353998203056e-05,
      "loss": 0.9232968091964722,
      "step": 182
    },
    {
      "epoch": 0.07939590075512405,
      "grad_norm": 2.0851218700408936,
      "learning_rate": 1.6442048517520218e-05,
      "loss": 0.981245219707489,
      "step": 184
    },
    {
      "epoch": 0.08025889967637541,
      "grad_norm": 1.3769028186798096,
      "learning_rate": 1.662174303683738e-05,
      "loss": 0.9762678146362305,
      "step": 186
    },
    {
      "epoch": 0.08112189859762675,
      "grad_norm": 1.85263192653656,
      "learning_rate": 1.6801437556154538e-05,
      "loss": 0.9905523061752319,
      "step": 188
    },
    {
      "epoch": 0.08198489751887811,
      "grad_norm": 1.654221534729004,
      "learning_rate": 1.69811320754717e-05,
      "loss": 0.8457058072090149,
      "step": 190
    },
    {
      "epoch": 0.08284789644012945,
      "grad_norm": 1.7715294361114502,
      "learning_rate": 1.7160826594788858e-05,
      "loss": 1.0171988010406494,
      "step": 192
    },
    {
      "epoch": 0.0837108953613808,
      "grad_norm": 1.7162128686904907,
      "learning_rate": 1.734052111410602e-05,
      "loss": 0.9767695069313049,
      "step": 194
    },
    {
      "epoch": 0.08457389428263215,
      "grad_norm": 1.7938538789749146,
      "learning_rate": 1.752021563342318e-05,
      "loss": 0.9786219596862793,
      "step": 196
    },
    {
      "epoch": 0.0854368932038835,
      "grad_norm": 1.944226861000061,
      "learning_rate": 1.7699910152740342e-05,
      "loss": 0.9941093921661377,
      "step": 198
    },
    {
      "epoch": 0.08629989212513485,
      "grad_norm": 1.816835880279541,
      "learning_rate": 1.7879604672057504e-05,
      "loss": 0.8924376964569092,
      "step": 200
    },
    {
      "epoch": 0.08629989212513485,
      "eval_loss": 0.981117308139801,
      "eval_runtime": 826.4469,
      "eval_samples_per_second": 2.493,
      "eval_steps_per_second": 2.493,
      "step": 200
    },
    {
      "epoch": 0.08716289104638619,
      "grad_norm": 1.8230189085006714,
      "learning_rate": 1.8059299191374666e-05,
      "loss": 0.9908216595649719,
      "step": 202
    },
    {
      "epoch": 0.08802588996763754,
      "grad_norm": 1.8223077058792114,
      "learning_rate": 1.8238993710691824e-05,
      "loss": 0.9657744765281677,
      "step": 204
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 1.811195731163025,
      "learning_rate": 1.8418688230008986e-05,
      "loss": 0.9397313594818115,
      "step": 206
    },
    {
      "epoch": 0.08975188781014024,
      "grad_norm": 1.579998254776001,
      "learning_rate": 1.8598382749326147e-05,
      "loss": 0.8770087361335754,
      "step": 208
    },
    {
      "epoch": 0.09061488673139159,
      "grad_norm": 1.592136263847351,
      "learning_rate": 1.8778077268643305e-05,
      "loss": 0.922799825668335,
      "step": 210
    },
    {
      "epoch": 0.09147788565264293,
      "grad_norm": 1.9334869384765625,
      "learning_rate": 1.8957771787960467e-05,
      "loss": 0.9007947444915771,
      "step": 212
    },
    {
      "epoch": 0.09234088457389428,
      "grad_norm": 1.8619475364685059,
      "learning_rate": 1.913746630727763e-05,
      "loss": 0.9261049628257751,
      "step": 214
    },
    {
      "epoch": 0.09320388349514563,
      "grad_norm": 1.751584529876709,
      "learning_rate": 1.931716082659479e-05,
      "loss": 0.9319002628326416,
      "step": 216
    },
    {
      "epoch": 0.09406688241639698,
      "grad_norm": 2.1829185485839844,
      "learning_rate": 1.9496855345911952e-05,
      "loss": 0.947629451751709,
      "step": 218
    },
    {
      "epoch": 0.09492988133764833,
      "grad_norm": 1.8973567485809326,
      "learning_rate": 1.967654986522911e-05,
      "loss": 0.9213902354240417,
      "step": 220
    },
    {
      "epoch": 0.09579288025889968,
      "grad_norm": 1.9995585680007935,
      "learning_rate": 1.985624438454627e-05,
      "loss": 0.9058182835578918,
      "step": 222
    },
    {
      "epoch": 0.09665587918015102,
      "grad_norm": 1.9369088411331177,
      "learning_rate": 2.0035938903863433e-05,
      "loss": 0.8918466567993164,
      "step": 224
    },
    {
      "epoch": 0.09751887810140238,
      "grad_norm": 2.1926183700561523,
      "learning_rate": 2.0215633423180595e-05,
      "loss": 1.009294033050537,
      "step": 226
    },
    {
      "epoch": 0.09838187702265372,
      "grad_norm": 1.872399926185608,
      "learning_rate": 2.0395327942497757e-05,
      "loss": 0.9543544054031372,
      "step": 228
    },
    {
      "epoch": 0.09924487594390508,
      "grad_norm": 2.011009454727173,
      "learning_rate": 2.0575022461814915e-05,
      "loss": 0.9188834428787231,
      "step": 230
    },
    {
      "epoch": 0.10010787486515642,
      "grad_norm": 1.8422952890396118,
      "learning_rate": 2.0754716981132076e-05,
      "loss": 0.84498131275177,
      "step": 232
    },
    {
      "epoch": 0.10097087378640776,
      "grad_norm": 2.208738088607788,
      "learning_rate": 2.0934411500449238e-05,
      "loss": 0.9864624738693237,
      "step": 234
    },
    {
      "epoch": 0.10183387270765912,
      "grad_norm": 1.6119916439056396,
      "learning_rate": 2.1114106019766396e-05,
      "loss": 0.928769588470459,
      "step": 236
    },
    {
      "epoch": 0.10269687162891046,
      "grad_norm": 1.906336784362793,
      "learning_rate": 2.1293800539083558e-05,
      "loss": 0.885361909866333,
      "step": 238
    },
    {
      "epoch": 0.10355987055016182,
      "grad_norm": 2.046064615249634,
      "learning_rate": 2.147349505840072e-05,
      "loss": 0.9497957229614258,
      "step": 240
    },
    {
      "epoch": 0.10442286947141316,
      "grad_norm": 2.1612143516540527,
      "learning_rate": 2.165318957771788e-05,
      "loss": 0.958332896232605,
      "step": 242
    },
    {
      "epoch": 0.1052858683926645,
      "grad_norm": 2.139829635620117,
      "learning_rate": 2.1832884097035043e-05,
      "loss": 1.0089390277862549,
      "step": 244
    },
    {
      "epoch": 0.10614886731391586,
      "grad_norm": 1.9842045307159424,
      "learning_rate": 2.2012578616352204e-05,
      "loss": 0.9627355933189392,
      "step": 246
    },
    {
      "epoch": 0.1070118662351672,
      "grad_norm": 1.968578577041626,
      "learning_rate": 2.2192273135669366e-05,
      "loss": 0.9260450601577759,
      "step": 248
    },
    {
      "epoch": 0.10787486515641856,
      "grad_norm": 2.192275047302246,
      "learning_rate": 2.2371967654986524e-05,
      "loss": 1.0654462575912476,
      "step": 250
    },
    {
      "epoch": 0.1087378640776699,
      "grad_norm": 2.0267577171325684,
      "learning_rate": 2.2551662174303682e-05,
      "loss": 0.9680672883987427,
      "step": 252
    },
    {
      "epoch": 0.10960086299892124,
      "grad_norm": 1.9834461212158203,
      "learning_rate": 2.2731356693620844e-05,
      "loss": 1.0027307271957397,
      "step": 254
    },
    {
      "epoch": 0.1104638619201726,
      "grad_norm": 2.0105156898498535,
      "learning_rate": 2.2911051212938006e-05,
      "loss": 1.0050861835479736,
      "step": 256
    },
    {
      "epoch": 0.11132686084142394,
      "grad_norm": 1.9150307178497314,
      "learning_rate": 2.3090745732255167e-05,
      "loss": 0.8955062627792358,
      "step": 258
    },
    {
      "epoch": 0.1121898597626753,
      "grad_norm": 2.100795269012451,
      "learning_rate": 2.327044025157233e-05,
      "loss": 0.941332221031189,
      "step": 260
    },
    {
      "epoch": 0.11305285868392664,
      "grad_norm": 1.837814211845398,
      "learning_rate": 2.345013477088949e-05,
      "loss": 0.9292652606964111,
      "step": 262
    },
    {
      "epoch": 0.113915857605178,
      "grad_norm": 1.9122955799102783,
      "learning_rate": 2.3629829290206652e-05,
      "loss": 0.9460650682449341,
      "step": 264
    },
    {
      "epoch": 0.11477885652642934,
      "grad_norm": 1.9168611764907837,
      "learning_rate": 2.380952380952381e-05,
      "loss": 0.8730320334434509,
      "step": 266
    },
    {
      "epoch": 0.11564185544768069,
      "grad_norm": 2.1184403896331787,
      "learning_rate": 2.3989218328840972e-05,
      "loss": 0.9194066524505615,
      "step": 268
    },
    {
      "epoch": 0.11650485436893204,
      "grad_norm": 1.910470962524414,
      "learning_rate": 2.4168912848158133e-05,
      "loss": 0.8994337320327759,
      "step": 270
    },
    {
      "epoch": 0.11736785329018339,
      "grad_norm": 1.9906529188156128,
      "learning_rate": 2.434860736747529e-05,
      "loss": 0.8509554266929626,
      "step": 272
    },
    {
      "epoch": 0.11823085221143474,
      "grad_norm": 2.5982062816619873,
      "learning_rate": 2.4528301886792453e-05,
      "loss": 1.0223658084869385,
      "step": 274
    },
    {
      "epoch": 0.11909385113268608,
      "grad_norm": 1.8959418535232544,
      "learning_rate": 2.4707996406109615e-05,
      "loss": 0.8702670931816101,
      "step": 276
    },
    {
      "epoch": 0.11995685005393743,
      "grad_norm": 2.115907669067383,
      "learning_rate": 2.4887690925426776e-05,
      "loss": 0.9471842050552368,
      "step": 278
    },
    {
      "epoch": 0.12081984897518878,
      "grad_norm": 2.0255353450775146,
      "learning_rate": 2.5067385444743935e-05,
      "loss": 0.805242657661438,
      "step": 280
    },
    {
      "epoch": 0.12168284789644013,
      "grad_norm": 1.9394105672836304,
      "learning_rate": 2.52470799640611e-05,
      "loss": 0.9008285999298096,
      "step": 282
    },
    {
      "epoch": 0.12254584681769148,
      "grad_norm": 2.2017428874969482,
      "learning_rate": 2.5426774483378258e-05,
      "loss": 0.950639009475708,
      "step": 284
    },
    {
      "epoch": 0.12340884573894283,
      "grad_norm": 4.048379421234131,
      "learning_rate": 2.5606469002695423e-05,
      "loss": 0.9673396944999695,
      "step": 286
    },
    {
      "epoch": 0.12427184466019417,
      "grad_norm": 1.812450647354126,
      "learning_rate": 2.578616352201258e-05,
      "loss": 0.8251164555549622,
      "step": 288
    },
    {
      "epoch": 0.12513484358144553,
      "grad_norm": 1.9298596382141113,
      "learning_rate": 2.596585804132974e-05,
      "loss": 0.9397821426391602,
      "step": 290
    },
    {
      "epoch": 0.12599784250269688,
      "grad_norm": 2.0862202644348145,
      "learning_rate": 2.61455525606469e-05,
      "loss": 0.95896315574646,
      "step": 292
    },
    {
      "epoch": 0.1268608414239482,
      "grad_norm": 2.113429307937622,
      "learning_rate": 2.632524707996406e-05,
      "loss": 0.9547653198242188,
      "step": 294
    },
    {
      "epoch": 0.12772384034519957,
      "grad_norm": 2.0666873455047607,
      "learning_rate": 2.6504941599281224e-05,
      "loss": 0.9351654052734375,
      "step": 296
    },
    {
      "epoch": 0.12858683926645093,
      "grad_norm": 2.0679547786712646,
      "learning_rate": 2.6684636118598382e-05,
      "loss": 0.9268350005149841,
      "step": 298
    },
    {
      "epoch": 0.12944983818770225,
      "grad_norm": 2.028594493865967,
      "learning_rate": 2.6864330637915547e-05,
      "loss": 0.8522316813468933,
      "step": 300
    },
    {
      "epoch": 0.12944983818770225,
      "eval_loss": 0.9384957551956177,
      "eval_runtime": 835.4727,
      "eval_samples_per_second": 2.466,
      "eval_steps_per_second": 2.466,
      "step": 300
    },
    {
      "epoch": 0.1303128371089536,
      "grad_norm": 2.1932919025421143,
      "learning_rate": 2.7044025157232706e-05,
      "loss": 0.9460103511810303,
      "step": 302
    },
    {
      "epoch": 0.13117583603020497,
      "grad_norm": 2.275789737701416,
      "learning_rate": 2.722371967654987e-05,
      "loss": 0.9642201662063599,
      "step": 304
    },
    {
      "epoch": 0.13203883495145632,
      "grad_norm": 1.9120908975601196,
      "learning_rate": 2.740341419586703e-05,
      "loss": 0.869883120059967,
      "step": 306
    },
    {
      "epoch": 0.13290183387270765,
      "grad_norm": 1.9676507711410522,
      "learning_rate": 2.7583108715184187e-05,
      "loss": 0.8595444560050964,
      "step": 308
    },
    {
      "epoch": 0.133764832793959,
      "grad_norm": 1.7901391983032227,
      "learning_rate": 2.776280323450135e-05,
      "loss": 0.8541103601455688,
      "step": 310
    },
    {
      "epoch": 0.13462783171521037,
      "grad_norm": 2.160867691040039,
      "learning_rate": 2.7942497753818507e-05,
      "loss": 1.0146855115890503,
      "step": 312
    },
    {
      "epoch": 0.1354908306364617,
      "grad_norm": 2.0809009075164795,
      "learning_rate": 2.8122192273135672e-05,
      "loss": 0.9228161573410034,
      "step": 314
    },
    {
      "epoch": 0.13635382955771305,
      "grad_norm": 1.9626725912094116,
      "learning_rate": 2.830188679245283e-05,
      "loss": 0.8527485132217407,
      "step": 316
    },
    {
      "epoch": 0.1372168284789644,
      "grad_norm": 1.9569967985153198,
      "learning_rate": 2.8481581311769995e-05,
      "loss": 0.8136687278747559,
      "step": 318
    },
    {
      "epoch": 0.13807982740021574,
      "grad_norm": 2.301692247390747,
      "learning_rate": 2.8661275831087153e-05,
      "loss": 0.8999513387680054,
      "step": 320
    },
    {
      "epoch": 0.1389428263214671,
      "grad_norm": 2.0247251987457275,
      "learning_rate": 2.884097035040431e-05,
      "loss": 0.9751577973365784,
      "step": 322
    },
    {
      "epoch": 0.13980582524271845,
      "grad_norm": 2.019547462463379,
      "learning_rate": 2.9020664869721477e-05,
      "loss": 0.8741729259490967,
      "step": 324
    },
    {
      "epoch": 0.1406688241639698,
      "grad_norm": 2.3503618240356445,
      "learning_rate": 2.9200359389038635e-05,
      "loss": 0.948066234588623,
      "step": 326
    },
    {
      "epoch": 0.14153182308522114,
      "grad_norm": 2.544365406036377,
      "learning_rate": 2.9380053908355796e-05,
      "loss": 1.008673906326294,
      "step": 328
    },
    {
      "epoch": 0.1423948220064725,
      "grad_norm": 3.1647145748138428,
      "learning_rate": 2.9559748427672958e-05,
      "loss": 0.9492161273956299,
      "step": 330
    },
    {
      "epoch": 0.14325782092772385,
      "grad_norm": 2.0551259517669678,
      "learning_rate": 2.973944294699012e-05,
      "loss": 0.9077466130256653,
      "step": 332
    },
    {
      "epoch": 0.14412081984897518,
      "grad_norm": 1.6792620420455933,
      "learning_rate": 2.9919137466307278e-05,
      "loss": 0.8839989304542542,
      "step": 334
    },
    {
      "epoch": 0.14498381877022654,
      "grad_norm": 1.7771215438842773,
      "learning_rate": 3.0098831985624436e-05,
      "loss": 0.855834424495697,
      "step": 336
    },
    {
      "epoch": 0.1458468176914779,
      "grad_norm": 2.030884027481079,
      "learning_rate": 3.02785265049416e-05,
      "loss": 0.8477111458778381,
      "step": 338
    },
    {
      "epoch": 0.14670981661272922,
      "grad_norm": 2.4177005290985107,
      "learning_rate": 3.045822102425876e-05,
      "loss": 0.9139004945755005,
      "step": 340
    },
    {
      "epoch": 0.14757281553398058,
      "grad_norm": 2.094775438308716,
      "learning_rate": 3.063791554357592e-05,
      "loss": 0.8836029767990112,
      "step": 342
    },
    {
      "epoch": 0.14843581445523193,
      "grad_norm": 2.0046238899230957,
      "learning_rate": 3.081761006289308e-05,
      "loss": 0.9318807125091553,
      "step": 344
    },
    {
      "epoch": 0.1492988133764833,
      "grad_norm": 2.40739369392395,
      "learning_rate": 3.0997304582210244e-05,
      "loss": 0.8916489481925964,
      "step": 346
    },
    {
      "epoch": 0.15016181229773462,
      "grad_norm": 2.1190497875213623,
      "learning_rate": 3.11769991015274e-05,
      "loss": 0.90766441822052,
      "step": 348
    },
    {
      "epoch": 0.15102481121898598,
      "grad_norm": 2.721255302429199,
      "learning_rate": 3.135669362084457e-05,
      "loss": 0.9210623502731323,
      "step": 350
    },
    {
      "epoch": 0.15188781014023733,
      "grad_norm": 2.4988787174224854,
      "learning_rate": 3.1536388140161726e-05,
      "loss": 0.9134353399276733,
      "step": 352
    },
    {
      "epoch": 0.15275080906148866,
      "grad_norm": 2.6075687408447266,
      "learning_rate": 3.1716082659478884e-05,
      "loss": 0.9127986431121826,
      "step": 354
    },
    {
      "epoch": 0.15361380798274002,
      "grad_norm": 1.9883074760437012,
      "learning_rate": 3.189577717879605e-05,
      "loss": 0.8019667863845825,
      "step": 356
    },
    {
      "epoch": 0.15447680690399138,
      "grad_norm": 2.058591365814209,
      "learning_rate": 3.207547169811321e-05,
      "loss": 0.8417298197746277,
      "step": 358
    },
    {
      "epoch": 0.1553398058252427,
      "grad_norm": 2.0510308742523193,
      "learning_rate": 3.225516621743037e-05,
      "loss": 0.909717321395874,
      "step": 360
    },
    {
      "epoch": 0.15620280474649406,
      "grad_norm": 2.3204104900360107,
      "learning_rate": 3.243486073674753e-05,
      "loss": 0.9414666295051575,
      "step": 362
    },
    {
      "epoch": 0.15706580366774542,
      "grad_norm": 1.9658725261688232,
      "learning_rate": 3.2614555256064695e-05,
      "loss": 0.8631396889686584,
      "step": 364
    },
    {
      "epoch": 0.15792880258899678,
      "grad_norm": 2.2223057746887207,
      "learning_rate": 3.2794249775381853e-05,
      "loss": 0.8996705412864685,
      "step": 366
    },
    {
      "epoch": 0.1587918015102481,
      "grad_norm": 1.9815107583999634,
      "learning_rate": 3.297394429469901e-05,
      "loss": 0.8185732364654541,
      "step": 368
    },
    {
      "epoch": 0.15965480043149946,
      "grad_norm": 2.319581985473633,
      "learning_rate": 3.315363881401618e-05,
      "loss": 0.9952898025512695,
      "step": 370
    },
    {
      "epoch": 0.16051779935275082,
      "grad_norm": 1.7916827201843262,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.7604310512542725,
      "step": 372
    },
    {
      "epoch": 0.16138079827400215,
      "grad_norm": 1.955737590789795,
      "learning_rate": 3.35130278526505e-05,
      "loss": 0.7867834568023682,
      "step": 374
    },
    {
      "epoch": 0.1622437971952535,
      "grad_norm": 2.409783124923706,
      "learning_rate": 3.369272237196766e-05,
      "loss": 0.9106539487838745,
      "step": 376
    },
    {
      "epoch": 0.16310679611650486,
      "grad_norm": 2.2521097660064697,
      "learning_rate": 3.3872416891284816e-05,
      "loss": 0.8945732712745667,
      "step": 378
    },
    {
      "epoch": 0.16396979503775622,
      "grad_norm": 2.357815742492676,
      "learning_rate": 3.4052111410601975e-05,
      "loss": 0.8950189352035522,
      "step": 380
    },
    {
      "epoch": 0.16483279395900755,
      "grad_norm": 2.347301721572876,
      "learning_rate": 3.423180592991914e-05,
      "loss": 0.9965803623199463,
      "step": 382
    },
    {
      "epoch": 0.1656957928802589,
      "grad_norm": 2.054586887359619,
      "learning_rate": 3.44115004492363e-05,
      "loss": 0.9081383347511292,
      "step": 384
    },
    {
      "epoch": 0.16655879180151026,
      "grad_norm": 2.1550471782684326,
      "learning_rate": 3.4591194968553456e-05,
      "loss": 0.874001681804657,
      "step": 386
    },
    {
      "epoch": 0.1674217907227616,
      "grad_norm": 1.6929951906204224,
      "learning_rate": 3.477088948787062e-05,
      "loss": 0.9111959934234619,
      "step": 388
    },
    {
      "epoch": 0.16828478964401294,
      "grad_norm": 2.0102803707122803,
      "learning_rate": 3.495058400718778e-05,
      "loss": 0.8915985226631165,
      "step": 390
    },
    {
      "epoch": 0.1691477885652643,
      "grad_norm": 4.215941429138184,
      "learning_rate": 3.5130278526504944e-05,
      "loss": 1.0158213376998901,
      "step": 392
    },
    {
      "epoch": 0.17001078748651563,
      "grad_norm": 1.864119529724121,
      "learning_rate": 3.53099730458221e-05,
      "loss": 0.7811702489852905,
      "step": 394
    },
    {
      "epoch": 0.170873786407767,
      "grad_norm": 1.9778105020523071,
      "learning_rate": 3.548966756513927e-05,
      "loss": 0.931502103805542,
      "step": 396
    },
    {
      "epoch": 0.17173678532901834,
      "grad_norm": 2.0757675170898438,
      "learning_rate": 3.5669362084456426e-05,
      "loss": 0.9409074187278748,
      "step": 398
    },
    {
      "epoch": 0.1725997842502697,
      "grad_norm": 1.5847891569137573,
      "learning_rate": 3.5849056603773584e-05,
      "loss": 0.8159269094467163,
      "step": 400
    },
    {
      "epoch": 0.1725997842502697,
      "eval_loss": 0.9124138355255127,
      "eval_runtime": 832.6331,
      "eval_samples_per_second": 2.474,
      "eval_steps_per_second": 2.474,
      "step": 400
    },
    {
      "epoch": 0.17346278317152103,
      "grad_norm": 1.8158049583435059,
      "learning_rate": 3.602875112309075e-05,
      "loss": 0.8901475667953491,
      "step": 402
    },
    {
      "epoch": 0.17432578209277239,
      "grad_norm": 1.9448504447937012,
      "learning_rate": 3.620844564240791e-05,
      "loss": 0.8330907821655273,
      "step": 404
    },
    {
      "epoch": 0.17518878101402374,
      "grad_norm": 2.028280019760132,
      "learning_rate": 3.638814016172507e-05,
      "loss": 0.870513916015625,
      "step": 406
    },
    {
      "epoch": 0.17605177993527507,
      "grad_norm": 2.2005157470703125,
      "learning_rate": 3.656783468104223e-05,
      "loss": 0.8064979910850525,
      "step": 408
    },
    {
      "epoch": 0.17691477885652643,
      "grad_norm": 2.2756290435791016,
      "learning_rate": 3.6747529200359395e-05,
      "loss": 0.8457443714141846,
      "step": 410
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 2.0970261096954346,
      "learning_rate": 3.6927223719676554e-05,
      "loss": 0.7478897571563721,
      "step": 412
    },
    {
      "epoch": 0.1786407766990291,
      "grad_norm": 1.8917485475540161,
      "learning_rate": 3.710691823899371e-05,
      "loss": 0.863377034664154,
      "step": 414
    },
    {
      "epoch": 0.17950377562028047,
      "grad_norm": 2.0429933071136475,
      "learning_rate": 3.728661275831088e-05,
      "loss": 0.8654620051383972,
      "step": 416
    },
    {
      "epoch": 0.18036677454153183,
      "grad_norm": 2.005125045776367,
      "learning_rate": 3.7466307277628035e-05,
      "loss": 0.8295455574989319,
      "step": 418
    },
    {
      "epoch": 0.18122977346278318,
      "grad_norm": 2.3852169513702393,
      "learning_rate": 3.764600179694519e-05,
      "loss": 0.8728633522987366,
      "step": 420
    },
    {
      "epoch": 0.1820927723840345,
      "grad_norm": 1.8731592893600464,
      "learning_rate": 3.782569631626235e-05,
      "loss": 0.8217283487319946,
      "step": 422
    },
    {
      "epoch": 0.18295577130528587,
      "grad_norm": 2.2818236351013184,
      "learning_rate": 3.8005390835579516e-05,
      "loss": 0.8869860172271729,
      "step": 424
    },
    {
      "epoch": 0.18381877022653723,
      "grad_norm": 2.0646233558654785,
      "learning_rate": 3.8185085354896675e-05,
      "loss": 0.9732091426849365,
      "step": 426
    },
    {
      "epoch": 0.18468176914778855,
      "grad_norm": 1.9991949796676636,
      "learning_rate": 3.836477987421384e-05,
      "loss": 0.9012333154678345,
      "step": 428
    },
    {
      "epoch": 0.1855447680690399,
      "grad_norm": 2.209775447845459,
      "learning_rate": 3.8544474393531e-05,
      "loss": 0.867533802986145,
      "step": 430
    },
    {
      "epoch": 0.18640776699029127,
      "grad_norm": 2.1242146492004395,
      "learning_rate": 3.8724168912848156e-05,
      "loss": 0.8697446584701538,
      "step": 432
    },
    {
      "epoch": 0.1872707659115426,
      "grad_norm": 1.771337628364563,
      "learning_rate": 3.890386343216532e-05,
      "loss": 0.8712933659553528,
      "step": 434
    },
    {
      "epoch": 0.18813376483279395,
      "grad_norm": 2.133652925491333,
      "learning_rate": 3.908355795148248e-05,
      "loss": 0.8638070821762085,
      "step": 436
    },
    {
      "epoch": 0.1889967637540453,
      "grad_norm": 1.9354501962661743,
      "learning_rate": 3.9263252470799644e-05,
      "loss": 0.8255205750465393,
      "step": 438
    },
    {
      "epoch": 0.18985976267529667,
      "grad_norm": 1.9564658403396606,
      "learning_rate": 3.94429469901168e-05,
      "loss": 0.9652490019798279,
      "step": 440
    },
    {
      "epoch": 0.190722761596548,
      "grad_norm": 1.9733822345733643,
      "learning_rate": 3.962264150943397e-05,
      "loss": 0.8960518836975098,
      "step": 442
    },
    {
      "epoch": 0.19158576051779935,
      "grad_norm": 2.1670451164245605,
      "learning_rate": 3.9802336028751126e-05,
      "loss": 0.9555241465568542,
      "step": 444
    },
    {
      "epoch": 0.1924487594390507,
      "grad_norm": 2.0059614181518555,
      "learning_rate": 3.9982030548068284e-05,
      "loss": 0.8238654732704163,
      "step": 446
    },
    {
      "epoch": 0.19331175836030204,
      "grad_norm": 1.9803026914596558,
      "learning_rate": 4.016172506738545e-05,
      "loss": 0.8701026439666748,
      "step": 448
    },
    {
      "epoch": 0.1941747572815534,
      "grad_norm": 1.8800172805786133,
      "learning_rate": 4.034141958670261e-05,
      "loss": 0.8927714228630066,
      "step": 450
    },
    {
      "epoch": 0.19503775620280475,
      "grad_norm": 1.8555818796157837,
      "learning_rate": 4.052111410601977e-05,
      "loss": 0.8635751008987427,
      "step": 452
    },
    {
      "epoch": 0.1959007551240561,
      "grad_norm": 2.5119166374206543,
      "learning_rate": 4.070080862533693e-05,
      "loss": 0.925403892993927,
      "step": 454
    },
    {
      "epoch": 0.19676375404530744,
      "grad_norm": 2.0825788974761963,
      "learning_rate": 4.088050314465409e-05,
      "loss": 0.8917028307914734,
      "step": 456
    },
    {
      "epoch": 0.1976267529665588,
      "grad_norm": 2.4413394927978516,
      "learning_rate": 4.1060197663971254e-05,
      "loss": 0.9097893834114075,
      "step": 458
    },
    {
      "epoch": 0.19848975188781015,
      "grad_norm": 2.503617286682129,
      "learning_rate": 4.123989218328841e-05,
      "loss": 0.8284633755683899,
      "step": 460
    },
    {
      "epoch": 0.19935275080906148,
      "grad_norm": 1.9360398054122925,
      "learning_rate": 4.141958670260557e-05,
      "loss": 0.8743083477020264,
      "step": 462
    },
    {
      "epoch": 0.20021574973031284,
      "grad_norm": 1.9228297472000122,
      "learning_rate": 4.159928122192273e-05,
      "loss": 0.837934136390686,
      "step": 464
    },
    {
      "epoch": 0.2010787486515642,
      "grad_norm": 2.3240439891815186,
      "learning_rate": 4.1778975741239893e-05,
      "loss": 0.831945538520813,
      "step": 466
    },
    {
      "epoch": 0.20194174757281552,
      "grad_norm": 1.879684329032898,
      "learning_rate": 4.195867026055705e-05,
      "loss": 0.8012097477912903,
      "step": 468
    },
    {
      "epoch": 0.20280474649406688,
      "grad_norm": 2.2995200157165527,
      "learning_rate": 4.213836477987422e-05,
      "loss": 0.8670937418937683,
      "step": 470
    },
    {
      "epoch": 0.20366774541531824,
      "grad_norm": 2.098020553588867,
      "learning_rate": 4.2318059299191375e-05,
      "loss": 0.88299161195755,
      "step": 472
    },
    {
      "epoch": 0.2045307443365696,
      "grad_norm": 2.0588274002075195,
      "learning_rate": 4.249775381850854e-05,
      "loss": 0.9045401811599731,
      "step": 474
    },
    {
      "epoch": 0.20539374325782092,
      "grad_norm": 1.8832436800003052,
      "learning_rate": 4.26774483378257e-05,
      "loss": 0.9787635803222656,
      "step": 476
    },
    {
      "epoch": 0.20625674217907228,
      "grad_norm": 2.3451809883117676,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.8874871730804443,
      "step": 478
    },
    {
      "epoch": 0.20711974110032363,
      "grad_norm": 1.8093878030776978,
      "learning_rate": 4.303683737646002e-05,
      "loss": 0.794157087802887,
      "step": 480
    },
    {
      "epoch": 0.20798274002157496,
      "grad_norm": 1.8396174907684326,
      "learning_rate": 4.321653189577718e-05,
      "loss": 0.792723536491394,
      "step": 482
    },
    {
      "epoch": 0.20884573894282632,
      "grad_norm": 2.3939783573150635,
      "learning_rate": 4.3396226415094345e-05,
      "loss": 0.9221814274787903,
      "step": 484
    },
    {
      "epoch": 0.20970873786407768,
      "grad_norm": 2.2652194499969482,
      "learning_rate": 4.35759209344115e-05,
      "loss": 0.8716039061546326,
      "step": 486
    },
    {
      "epoch": 0.210571736785329,
      "grad_norm": 2.068258762359619,
      "learning_rate": 4.375561545372867e-05,
      "loss": 0.8517807126045227,
      "step": 488
    },
    {
      "epoch": 0.21143473570658036,
      "grad_norm": 2.264620542526245,
      "learning_rate": 4.3935309973045826e-05,
      "loss": 0.8699264526367188,
      "step": 490
    },
    {
      "epoch": 0.21229773462783172,
      "grad_norm": 2.0821611881256104,
      "learning_rate": 4.4115004492362984e-05,
      "loss": 0.8760254383087158,
      "step": 492
    },
    {
      "epoch": 0.21316073354908308,
      "grad_norm": 1.9486546516418457,
      "learning_rate": 4.429469901168015e-05,
      "loss": 0.8957411050796509,
      "step": 494
    },
    {
      "epoch": 0.2140237324703344,
      "grad_norm": 2.092957019805908,
      "learning_rate": 4.447439353099731e-05,
      "loss": 0.981200635433197,
      "step": 496
    },
    {
      "epoch": 0.21488673139158576,
      "grad_norm": 2.325758218765259,
      "learning_rate": 4.4654088050314466e-05,
      "loss": 0.8295405507087708,
      "step": 498
    },
    {
      "epoch": 0.21574973031283712,
      "grad_norm": 2.251295566558838,
      "learning_rate": 4.4833782569631624e-05,
      "loss": 0.8463165163993835,
      "step": 500
    },
    {
      "epoch": 0.21574973031283712,
      "eval_loss": 0.8945327997207642,
      "eval_runtime": 822.9776,
      "eval_samples_per_second": 2.503,
      "eval_steps_per_second": 2.503,
      "step": 500
    }
  ],
  "logging_steps": 2,
  "max_steps": 13908,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.001
      },
      "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": 5.2025749846072934e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}