{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9990375360923965,
  "eval_steps": 500,
  "global_step": 519,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0019249278152069298,
      "grad_norm": 9833.949798287254,
      "learning_rate": 5.769230769230769e-06,
      "loss": 31.1205,
      "step": 1
    },
    {
      "epoch": 0.009624639076034648,
      "grad_norm": 3973.4641256325745,
      "learning_rate": 2.8846153846153845e-05,
      "loss": 21.4091,
      "step": 5
    },
    {
      "epoch": 0.019249278152069296,
      "grad_norm": 1204.353307038186,
      "learning_rate": 5.769230769230769e-05,
      "loss": 21.7988,
      "step": 10
    },
    {
      "epoch": 0.028873917228103944,
      "grad_norm": 2719.4113741924452,
      "learning_rate": 8.653846153846152e-05,
      "loss": 13.1493,
      "step": 15
    },
    {
      "epoch": 0.03849855630413859,
      "grad_norm": 1285.5933097188467,
      "learning_rate": 0.00011538461538461538,
      "loss": 14.9997,
      "step": 20
    },
    {
      "epoch": 0.04812319538017324,
      "grad_norm": 1368.1133931918484,
      "learning_rate": 0.00014423076923076922,
      "loss": 14.5096,
      "step": 25
    },
    {
      "epoch": 0.05774783445620789,
      "grad_norm": 1789.116574641265,
      "learning_rate": 0.00017307692307692304,
      "loss": 12.9147,
      "step": 30
    },
    {
      "epoch": 0.06737247353224254,
      "grad_norm": 606.4253426587204,
      "learning_rate": 0.00020192307692307691,
      "loss": 10.387,
      "step": 35
    },
    {
      "epoch": 0.07699711260827719,
      "grad_norm": 676.8551431719706,
      "learning_rate": 0.00023076923076923076,
      "loss": 11.1262,
      "step": 40
    },
    {
      "epoch": 0.08662175168431184,
      "grad_norm": 1231.7385257559686,
      "learning_rate": 0.0002596153846153846,
      "loss": 12.1561,
      "step": 45
    },
    {
      "epoch": 0.09624639076034648,
      "grad_norm": 653.2469828069383,
      "learning_rate": 0.00028846153846153843,
      "loss": 14.788,
      "step": 50
    },
    {
      "epoch": 0.10587102983638114,
      "grad_norm": 936.634056698483,
      "learning_rate": 0.00029996945395293625,
      "loss": 16.5564,
      "step": 55
    },
    {
      "epoch": 0.11549566891241578,
      "grad_norm": 1440.9242545303139,
      "learning_rate": 0.0002997828287165724,
      "loss": 15.2974,
      "step": 60
    },
    {
      "epoch": 0.12512030798845045,
      "grad_norm": 638.446747223475,
      "learning_rate": 0.00029942675913693153,
      "loss": 15.8667,
      "step": 65
    },
    {
      "epoch": 0.1347449470644851,
      "grad_norm": 200.266845272572,
      "learning_rate": 0.0002989016480237121,
      "loss": 12.8657,
      "step": 70
    },
    {
      "epoch": 0.14436958614051973,
      "grad_norm": 89.69963142129608,
      "learning_rate": 0.0002982080894176895,
      "loss": 10.8674,
      "step": 75
    },
    {
      "epoch": 0.15399422521655437,
      "grad_norm": 161.99501564355919,
      "learning_rate": 0.0002973468679186978,
      "loss": 10.3407,
      "step": 80
    },
    {
      "epoch": 0.16361886429258904,
      "grad_norm": 53.94884234688268,
      "learning_rate": 0.0002963189577980372,
      "loss": 8.3512,
      "step": 85
    },
    {
      "epoch": 0.17324350336862368,
      "grad_norm": 62.03416025335345,
      "learning_rate": 0.0002951255218963139,
      "loss": 7.7878,
      "step": 90
    },
    {
      "epoch": 0.18286814244465832,
      "grad_norm": 39.794164043801786,
      "learning_rate": 0.0002937679103079571,
      "loss": 7.2552,
      "step": 95
    },
    {
      "epoch": 0.19249278152069296,
      "grad_norm": 50.8231434503254,
      "learning_rate": 0.00029224765885390143,
      "loss": 6.6276,
      "step": 100
    },
    {
      "epoch": 0.20211742059672763,
      "grad_norm": 69.05369995252939,
      "learning_rate": 0.0002905664873441643,
      "loss": 6.6291,
      "step": 105
    },
    {
      "epoch": 0.21174205967276227,
      "grad_norm": 53.35632399080608,
      "learning_rate": 0.00028872629763228145,
      "loss": 6.029,
      "step": 110
    },
    {
      "epoch": 0.22136669874879691,
      "grad_norm": 31.195519429891153,
      "learning_rate": 0.0002867291714638035,
      "loss": 5.6465,
      "step": 115
    },
    {
      "epoch": 0.23099133782483156,
      "grad_norm": 52.701945055972324,
      "learning_rate": 0.0002845773681212862,
      "loss": 5.5662,
      "step": 120
    },
    {
      "epoch": 0.24061597690086622,
      "grad_norm": 77.35992519654677,
      "learning_rate": 0.00028227332186843884,
      "loss": 5.6873,
      "step": 125
    },
    {
      "epoch": 0.2502406159769009,
      "grad_norm": 51.024242740357835,
      "learning_rate": 0.0002798196391963229,
      "loss": 5.5508,
      "step": 130
    },
    {
      "epoch": 0.2598652550529355,
      "grad_norm": 51.18618353864925,
      "learning_rate": 0.0002772190958747147,
      "loss": 5.3892,
      "step": 135
    },
    {
      "epoch": 0.2694898941289702,
      "grad_norm": 58.56789915561519,
      "learning_rate": 0.00027447463381196973,
      "loss": 5.2978,
      "step": 140
    },
    {
      "epoch": 0.2791145332050048,
      "grad_norm": 23.98785567254054,
      "learning_rate": 0.0002715893577269389,
      "loss": 5.0187,
      "step": 145
    },
    {
      "epoch": 0.28873917228103946,
      "grad_norm": 29.781239631615374,
      "learning_rate": 0.0002685665316367035,
      "loss": 5.0355,
      "step": 150
    },
    {
      "epoch": 0.2983638113570741,
      "grad_norm": 39.95978701958715,
      "learning_rate": 0.0002654095751641007,
      "loss": 5.0902,
      "step": 155
    },
    {
      "epoch": 0.30798845043310874,
      "grad_norm": 52.37392360884158,
      "learning_rate": 0.00026212205966921786,
      "loss": 4.9294,
      "step": 160
    },
    {
      "epoch": 0.3176130895091434,
      "grad_norm": 17.241602171689465,
      "learning_rate": 0.0002587077042092314,
      "loss": 4.8938,
      "step": 165
    },
    {
      "epoch": 0.3272377285851781,
      "grad_norm": 13.689917458219496,
      "learning_rate": 0.00025517037133116085,
      "loss": 4.6402,
      "step": 170
    },
    {
      "epoch": 0.3368623676612127,
      "grad_norm": 20.769636603545532,
      "learning_rate": 0.0002515140627022976,
      "loss": 4.7864,
      "step": 175
    },
    {
      "epoch": 0.34648700673724736,
      "grad_norm": 38.55999150285036,
      "learning_rate": 0.00024774291458325127,
      "loss": 4.7515,
      "step": 180
    },
    {
      "epoch": 0.35611164581328203,
      "grad_norm": 13.304187798246316,
      "learning_rate": 0.00024386119314873578,
      "loss": 4.5423,
      "step": 185
    },
    {
      "epoch": 0.36573628488931664,
      "grad_norm": 59.93010691011633,
      "learning_rate": 0.00023987328966138704,
      "loss": 4.5956,
      "step": 190
    },
    {
      "epoch": 0.3753609239653513,
      "grad_norm": 17.66294429465663,
      "learning_rate": 0.00023578371550407354,
      "loss": 4.5076,
      "step": 195
    },
    {
      "epoch": 0.3849855630413859,
      "grad_norm": 7.3884347256705745,
      "learning_rate": 0.0002315970970763186,
      "loss": 4.2684,
      "step": 200
    },
    {
      "epoch": 0.3946102021174206,
      "grad_norm": 33.762369347498066,
      "learning_rate": 0.00022731817056060802,
      "loss": 4.2404,
      "step": 205
    },
    {
      "epoch": 0.40423484119345526,
      "grad_norm": 20.386360679132945,
      "learning_rate": 0.00022295177656450404,
      "loss": 4.294,
      "step": 210
    },
    {
      "epoch": 0.4138594802694899,
      "grad_norm": 28.236859859544925,
      "learning_rate": 0.00021850285464462677,
      "loss": 4.1248,
      "step": 215
    },
    {
      "epoch": 0.42348411934552455,
      "grad_norm": 39.626801274084244,
      "learning_rate": 0.0002139764377186976,
      "loss": 4.0508,
      "step": 220
    },
    {
      "epoch": 0.4331087584215592,
      "grad_norm": 15.698244933481332,
      "learning_rate": 0.00020937764637196638,
      "loss": 3.915,
      "step": 225
    },
    {
      "epoch": 0.44273339749759383,
      "grad_norm": 32.50383319470333,
      "learning_rate": 0.00020471168306446336,
      "loss": 3.9952,
      "step": 230
    },
    {
      "epoch": 0.4523580365736285,
      "grad_norm": 15.613973762528445,
      "learning_rate": 0.0001999838262456287,
      "loss": 4.0167,
      "step": 235
    },
    {
      "epoch": 0.4619826756496631,
      "grad_norm": 7.560143232774055,
      "learning_rate": 0.0001951994243829781,
      "loss": 3.9707,
      "step": 240
    },
    {
      "epoch": 0.4716073147256978,
      "grad_norm": 51.81465410028492,
      "learning_rate": 0.00019036388991155846,
      "loss": 3.7988,
      "step": 245
    },
    {
      "epoch": 0.48123195380173245,
      "grad_norm": 26.4525846375415,
      "learning_rate": 0.0001854826931110403,
      "loss": 3.7806,
      "step": 250
    },
    {
      "epoch": 0.49085659287776706,
      "grad_norm": 21.59913708750363,
      "learning_rate": 0.0001805613559173714,
      "loss": 3.6756,
      "step": 255
    },
    {
      "epoch": 0.5004812319538018,
      "grad_norm": 9.476011704621481,
      "learning_rate": 0.0001756054456759944,
      "loss": 3.5717,
      "step": 260
    },
    {
      "epoch": 0.5101058710298364,
      "grad_norm": 8.391576754509806,
      "learning_rate": 0.00017062056884369325,
      "loss": 3.5459,
      "step": 265
    },
    {
      "epoch": 0.519730510105871,
      "grad_norm": 28.78324805703396,
      "learning_rate": 0.0001656123646461951,
      "loss": 3.4701,
      "step": 270
    },
    {
      "epoch": 0.5293551491819056,
      "grad_norm": 11.001402915726699,
      "learning_rate": 0.00016058649869870098,
      "loss": 3.5334,
      "step": 275
    },
    {
      "epoch": 0.5389797882579404,
      "grad_norm": 6.8987788835950665,
      "learning_rate": 0.00015554865659656367,
      "loss": 3.4547,
      "step": 280
    },
    {
      "epoch": 0.548604427333975,
      "grad_norm": 9.323168999693845,
      "learning_rate": 0.00015050453748336224,
      "loss": 3.3446,
      "step": 285
    },
    {
      "epoch": 0.5582290664100096,
      "grad_norm": 5.3748827349335775,
      "learning_rate": 0.00014545984760365,
      "loss": 3.2687,
      "step": 290
    },
    {
      "epoch": 0.5678537054860443,
      "grad_norm": 5.367511603419207,
      "learning_rate": 0.00014042029384766938,
      "loss": 3.2708,
      "step": 295
    },
    {
      "epoch": 0.5774783445620789,
      "grad_norm": 12.526033486379177,
      "learning_rate": 0.00013539157729533678,
      "loss": 3.2415,
      "step": 300
    },
    {
      "epoch": 0.5871029836381135,
      "grad_norm": 14.896281107597598,
      "learning_rate": 0.00013037938676679957,
      "loss": 3.2106,
      "step": 305
    },
    {
      "epoch": 0.5967276227141483,
      "grad_norm": 12.127131320650086,
      "learning_rate": 0.00012538939238686286,
      "loss": 3.1497,
      "step": 310
    },
    {
      "epoch": 0.6063522617901829,
      "grad_norm": 8.461594875316374,
      "learning_rate": 0.0001204272391705654,
      "loss": 3.0511,
      "step": 315
    },
    {
      "epoch": 0.6159769008662175,
      "grad_norm": 4.919949282741493,
      "learning_rate": 0.00011549854063716169,
      "loss": 3.1097,
      "step": 320
    },
    {
      "epoch": 0.6256015399422522,
      "grad_norm": 5.0799921762929925,
      "learning_rate": 0.00011060887245973355,
      "loss": 3.0301,
      "step": 325
    },
    {
      "epoch": 0.6352261790182868,
      "grad_norm": 6.47369845719392,
      "learning_rate": 0.00010576376615761647,
      "loss": 2.9608,
      "step": 330
    },
    {
      "epoch": 0.6448508180943214,
      "grad_norm": 7.124047081231151,
      "learning_rate": 0.00010096870283877523,
      "loss": 3.0135,
      "step": 335
    },
    {
      "epoch": 0.6544754571703562,
      "grad_norm": 8.31297997032083,
      "learning_rate": 9.62291069992085e-05,
      "loss": 2.9059,
      "step": 340
    },
    {
      "epoch": 0.6641000962463908,
      "grad_norm": 5.136687672624436,
      "learning_rate": 9.155034038639637e-05,
      "loss": 2.8699,
      "step": 345
    },
    {
      "epoch": 0.6737247353224254,
      "grad_norm": 9.36693811377479,
      "learning_rate": 8.693769593373337e-05,
      "loss": 2.7094,
      "step": 350
    },
    {
      "epoch": 0.6833493743984601,
      "grad_norm": 6.847104207590687,
      "learning_rate": 8.239639177280888e-05,
      "loss": 2.7623,
      "step": 355
    },
    {
      "epoch": 0.6929740134744947,
      "grad_norm": 11.941229453450356,
      "learning_rate": 7.793156533030761e-05,
      "loss": 2.7692,
      "step": 360
    },
    {
      "epoch": 0.7025986525505293,
      "grad_norm": 7.1577287914651935,
      "learning_rate": 7.354826751620954e-05,
      "loss": 2.6581,
      "step": 365
    },
    {
      "epoch": 0.7122232916265641,
      "grad_norm": 9.1635159385854,
      "learning_rate": 6.925145700986301e-05,
      "loss": 2.6512,
      "step": 370
    },
    {
      "epoch": 0.7218479307025987,
      "grad_norm": 7.88033732049449,
      "learning_rate": 6.504599465039542e-05,
      "loss": 2.6299,
      "step": 375
    },
    {
      "epoch": 0.7314725697786333,
      "grad_norm": 11.935678139850591,
      "learning_rate": 6.093663793780725e-05,
      "loss": 2.554,
      "step": 380
    },
    {
      "epoch": 0.7410972088546679,
      "grad_norm": 4.8026362420751285,
      "learning_rate": 5.692803565096988e-05,
      "loss": 2.5404,
      "step": 385
    },
    {
      "epoch": 0.7507218479307026,
      "grad_norm": 7.28758130289109,
      "learning_rate": 5.302472258861687e-05,
      "loss": 2.5256,
      "step": 390
    },
    {
      "epoch": 0.7603464870067372,
      "grad_norm": 4.9526592835021885,
      "learning_rate": 4.923111443927615e-05,
      "loss": 2.4819,
      "step": 395
    },
    {
      "epoch": 0.7699711260827719,
      "grad_norm": 4.8819904543262025,
      "learning_rate": 4.5551502785948405e-05,
      "loss": 2.5104,
      "step": 400
    },
    {
      "epoch": 0.7795957651588066,
      "grad_norm": 6.287198504138435,
      "learning_rate": 4.199005025118158e-05,
      "loss": 2.4187,
      "step": 405
    },
    {
      "epoch": 0.7892204042348412,
      "grad_norm": 6.291582745557658,
      "learning_rate": 3.855078578803424e-05,
      "loss": 2.3766,
      "step": 410
    },
    {
      "epoch": 0.7988450433108758,
      "grad_norm": 3.273436919662468,
      "learning_rate": 3.5237600122254437e-05,
      "loss": 2.4711,
      "step": 415
    },
    {
      "epoch": 0.8084696823869105,
      "grad_norm": 4.223924239880851,
      "learning_rate": 3.2054241350831046e-05,
      "loss": 2.3606,
      "step": 420
    },
    {
      "epoch": 0.8180943214629451,
      "grad_norm": 4.552913809634341,
      "learning_rate": 2.9004310701895837e-05,
      "loss": 2.3599,
      "step": 425
    },
    {
      "epoch": 0.8277189605389798,
      "grad_norm": 4.724368774995479,
      "learning_rate": 2.6091258460773862e-05,
      "loss": 2.4209,
      "step": 430
    },
    {
      "epoch": 0.8373435996150145,
      "grad_norm": 2.1385694187612194,
      "learning_rate": 2.3318380066789787e-05,
      "loss": 2.2896,
      "step": 435
    },
    {
      "epoch": 0.8469682386910491,
      "grad_norm": 3.108099479602538,
      "learning_rate": 2.0688812385247176e-05,
      "loss": 2.3179,
      "step": 440
    },
    {
      "epoch": 0.8565928777670837,
      "grad_norm": 2.870974039675886,
      "learning_rate": 1.8205530158796505e-05,
      "loss": 2.2415,
      "step": 445
    },
    {
      "epoch": 0.8662175168431184,
      "grad_norm": 2.74292535298438,
      "learning_rate": 1.587134264220778e-05,
      "loss": 2.3037,
      "step": 450
    },
    {
      "epoch": 0.875842155919153,
      "grad_norm": 1.9132580940232193,
      "learning_rate": 1.3688890424353726e-05,
      "loss": 2.2324,
      "step": 455
    },
    {
      "epoch": 0.8854667949951877,
      "grad_norm": 1.6426233529700058,
      "learning_rate": 1.1660642440999196e-05,
      "loss": 2.2031,
      "step": 460
    },
    {
      "epoch": 0.8950914340712224,
      "grad_norm": 2.036914499117152,
      "learning_rate": 9.788893181776297e-06,
      "loss": 2.2569,
      "step": 465
    },
    {
      "epoch": 0.904716073147257,
      "grad_norm": 2.3703240916735893,
      "learning_rate": 8.07576009450408e-06,
      "loss": 2.1718,
      "step": 470
    },
    {
      "epoch": 0.9143407122232916,
      "grad_norm": 1.963971475130326,
      "learning_rate": 6.5231811897903714e-06,
      "loss": 2.198,
      "step": 475
    },
    {
      "epoch": 0.9239653512993262,
      "grad_norm": 1.6385713856807373,
      "learning_rate": 5.13291284862452e-06,
      "loss": 2.1811,
      "step": 480
    },
    {
      "epoch": 0.933589990375361,
      "grad_norm": 1.7172361943571977,
      "learning_rate": 3.906527835442064e-06,
      "loss": 2.2004,
      "step": 485
    },
    {
      "epoch": 0.9432146294513956,
      "grad_norm": 1.8271284556111347,
      "learning_rate": 2.8454135189082684e-06,
      "loss": 2.2041,
      "step": 490
    },
    {
      "epoch": 0.9528392685274302,
      "grad_norm": 1.5811216247900128,
      "learning_rate": 1.950770302434157e-06,
      "loss": 2.1713,
      "step": 495
    },
    {
      "epoch": 0.9624639076034649,
      "grad_norm": 1.542394985664717,
      "learning_rate": 1.223610266200009e-06,
      "loss": 2.1716,
      "step": 500
    },
    {
      "epoch": 0.9720885466794995,
      "grad_norm": 1.4288680519545454,
      "learning_rate": 6.647560222224957e-07,
      "loss": 2.1115,
      "step": 505
    },
    {
      "epoch": 0.9817131857555341,
      "grad_norm": 1.6294272207246967,
      "learning_rate": 2.748397837611105e-07,
      "loss": 2.1781,
      "step": 510
    },
    {
      "epoch": 0.9913378248315688,
      "grad_norm": 1.6532836279501169,
      "learning_rate": 5.430265011625579e-08,
      "loss": 2.1274,
      "step": 515
    },
    {
      "epoch": 0.9990375360923965,
      "eval_loss": 5.616799831390381,
      "eval_runtime": 1.4307,
      "eval_samples_per_second": 4.194,
      "eval_steps_per_second": 0.699,
      "step": 519
    },
    {
      "epoch": 0.9990375360923965,
      "step": 519,
      "total_flos": 17850320289792.0,
      "train_loss": 5.281234926800737,
      "train_runtime": 7794.1138,
      "train_samples_per_second": 2.133,
      "train_steps_per_second": 0.067
    }
  ],
  "logging_steps": 5,
  "max_steps": 519,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 17850320289792.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}