{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9984067976633032,
  "eval_steps": 500,
  "global_step": 470,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002124269782262347,
      "grad_norm": 0.9608867223105472,
      "learning_rate": 4.255319148936171e-06,
      "loss": 1.6209,
      "step": 1
    },
    {
      "epoch": 0.010621348911311737,
      "grad_norm": 1.008471490037168,
      "learning_rate": 2.1276595744680852e-05,
      "loss": 1.6199,
      "step": 5
    },
    {
      "epoch": 0.021242697822623474,
      "grad_norm": 0.26269444126063646,
      "learning_rate": 4.2553191489361704e-05,
      "loss": 1.5721,
      "step": 10
    },
    {
      "epoch": 0.03186404673393521,
      "grad_norm": 0.22796802020916335,
      "learning_rate": 6.382978723404256e-05,
      "loss": 1.5352,
      "step": 15
    },
    {
      "epoch": 0.04248539564524695,
      "grad_norm": 0.19620571386797234,
      "learning_rate": 8.510638297872341e-05,
      "loss": 1.4921,
      "step": 20
    },
    {
      "epoch": 0.053106744556558685,
      "grad_norm": 0.2014364121241671,
      "learning_rate": 0.00010638297872340425,
      "loss": 1.4569,
      "step": 25
    },
    {
      "epoch": 0.06372809346787042,
      "grad_norm": 0.14918854171943344,
      "learning_rate": 0.00012765957446808513,
      "loss": 1.4115,
      "step": 30
    },
    {
      "epoch": 0.07434944237918216,
      "grad_norm": 0.13584276036738227,
      "learning_rate": 0.00014893617021276596,
      "loss": 1.3582,
      "step": 35
    },
    {
      "epoch": 0.0849707912904939,
      "grad_norm": 0.1362041776273294,
      "learning_rate": 0.00017021276595744682,
      "loss": 1.3364,
      "step": 40
    },
    {
      "epoch": 0.09559214020180563,
      "grad_norm": 0.12938558071544978,
      "learning_rate": 0.00019148936170212768,
      "loss": 1.348,
      "step": 45
    },
    {
      "epoch": 0.10621348911311737,
      "grad_norm": 0.10380081880060799,
      "learning_rate": 0.0001999751793267259,
      "loss": 1.3054,
      "step": 50
    },
    {
      "epoch": 0.11683483802442911,
      "grad_norm": 0.1143838187685618,
      "learning_rate": 0.00019982354205260347,
      "loss": 1.2693,
      "step": 55
    },
    {
      "epoch": 0.12745618693574085,
      "grad_norm": 0.11149288198876389,
      "learning_rate": 0.0001995342655949951,
      "loss": 1.2794,
      "step": 60
    },
    {
      "epoch": 0.13807753584705257,
      "grad_norm": 0.09311862817149338,
      "learning_rate": 0.000199107748815478,
      "loss": 1.2873,
      "step": 65
    },
    {
      "epoch": 0.14869888475836432,
      "grad_norm": 0.09599961949976782,
      "learning_rate": 0.000198544579806,
      "loss": 1.2646,
      "step": 70
    },
    {
      "epoch": 0.15932023366967604,
      "grad_norm": 0.11732897723147062,
      "learning_rate": 0.00019784553507800349,
      "loss": 1.2609,
      "step": 75
    },
    {
      "epoch": 0.1699415825809878,
      "grad_norm": 0.09291613696202214,
      "learning_rate": 0.00019701157849175228,
      "loss": 1.2493,
      "step": 80
    },
    {
      "epoch": 0.18056293149229952,
      "grad_norm": 0.09277470552310135,
      "learning_rate": 0.00019604385992733715,
      "loss": 1.2582,
      "step": 85
    },
    {
      "epoch": 0.19118428040361127,
      "grad_norm": 0.09620615117699073,
      "learning_rate": 0.0001949437136991925,
      "loss": 1.2494,
      "step": 90
    },
    {
      "epoch": 0.201805629314923,
      "grad_norm": 0.09446376086527693,
      "learning_rate": 0.00019371265671631037,
      "loss": 1.2334,
      "step": 95
    },
    {
      "epoch": 0.21242697822623474,
      "grad_norm": 0.09732108560985277,
      "learning_rate": 0.00019235238639068856,
      "loss": 1.2471,
      "step": 100
    },
    {
      "epoch": 0.22304832713754646,
      "grad_norm": 0.0969859129107049,
      "learning_rate": 0.00019086477829689685,
      "loss": 1.2436,
      "step": 105
    },
    {
      "epoch": 0.23366967604885822,
      "grad_norm": 0.09815487872535014,
      "learning_rate": 0.00018925188358598813,
      "loss": 1.226,
      "step": 110
    },
    {
      "epoch": 0.24429102496016994,
      "grad_norm": 0.1258570306173551,
      "learning_rate": 0.00018751592615732005,
      "loss": 1.2419,
      "step": 115
    },
    {
      "epoch": 0.2549123738714817,
      "grad_norm": 0.107383152586875,
      "learning_rate": 0.00018565929959218758,
      "loss": 1.2366,
      "step": 120
    },
    {
      "epoch": 0.2655337227827934,
      "grad_norm": 0.10102976615766632,
      "learning_rate": 0.00018368456385349334,
      "loss": 1.2382,
      "step": 125
    },
    {
      "epoch": 0.27615507169410514,
      "grad_norm": 0.10456038759256343,
      "learning_rate": 0.00018159444175600703,
      "loss": 1.2342,
      "step": 130
    },
    {
      "epoch": 0.2867764206054169,
      "grad_norm": 0.11461394118247933,
      "learning_rate": 0.000179391815212081,
      "loss": 1.2401,
      "step": 135
    },
    {
      "epoch": 0.29739776951672864,
      "grad_norm": 0.1057527291904125,
      "learning_rate": 0.00017707972125799735,
      "loss": 1.2193,
      "step": 140
    },
    {
      "epoch": 0.30801911842804036,
      "grad_norm": 0.10177183771950413,
      "learning_rate": 0.0001746613478664271,
      "loss": 1.2424,
      "step": 145
    },
    {
      "epoch": 0.3186404673393521,
      "grad_norm": 0.09313461051969327,
      "learning_rate": 0.00017214002955077393,
      "loss": 1.2234,
      "step": 150
    },
    {
      "epoch": 0.3292618162506638,
      "grad_norm": 0.1051850821585042,
      "learning_rate": 0.00016951924276746425,
      "loss": 1.2023,
      "step": 155
    },
    {
      "epoch": 0.3398831651619756,
      "grad_norm": 0.09840584460636738,
      "learning_rate": 0.0001668026011225225,
      "loss": 1.2303,
      "step": 160
    },
    {
      "epoch": 0.3505045140732873,
      "grad_norm": 0.09133411062766343,
      "learning_rate": 0.00016399385038904138,
      "loss": 1.208,
      "step": 165
    },
    {
      "epoch": 0.36112586298459903,
      "grad_norm": 0.0924953491335953,
      "learning_rate": 0.00016109686334241655,
      "loss": 1.1899,
      "step": 170
    },
    {
      "epoch": 0.37174721189591076,
      "grad_norm": 0.0943384109563561,
      "learning_rate": 0.00015811563442046767,
      "loss": 1.2141,
      "step": 175
    },
    {
      "epoch": 0.38236856080722254,
      "grad_norm": 0.10914200480049749,
      "learning_rate": 0.00015505427421580808,
      "loss": 1.2248,
      "step": 180
    },
    {
      "epoch": 0.39298990971853426,
      "grad_norm": 0.10932571445854564,
      "learning_rate": 0.00015191700380805752,
      "loss": 1.2106,
      "step": 185
    },
    {
      "epoch": 0.403611258629846,
      "grad_norm": 0.13346508581550925,
      "learning_rate": 0.00014870814894371245,
      "loss": 1.2028,
      "step": 190
    },
    {
      "epoch": 0.4142326075411577,
      "grad_norm": 0.09705115895523017,
      "learning_rate": 0.0001454321340716992,
      "loss": 1.2132,
      "step": 195
    },
    {
      "epoch": 0.4248539564524695,
      "grad_norm": 0.10424666730333806,
      "learning_rate": 0.0001420934762428335,
      "loss": 1.1932,
      "step": 200
    },
    {
      "epoch": 0.4354753053637812,
      "grad_norm": 0.10930559886929381,
      "learning_rate": 0.00013869677888159887,
      "loss": 1.2173,
      "step": 205
    },
    {
      "epoch": 0.44609665427509293,
      "grad_norm": 0.09409418865590193,
      "learning_rate": 0.00013524672543882996,
      "loss": 1.2084,
      "step": 210
    },
    {
      "epoch": 0.45671800318640465,
      "grad_norm": 0.09729338720333791,
      "learning_rate": 0.00013174807293405428,
      "loss": 1.2045,
      "step": 215
    },
    {
      "epoch": 0.46733935209771643,
      "grad_norm": 0.09424609585385203,
      "learning_rate": 0.00012820564539639512,
      "loss": 1.2114,
      "step": 220
    },
    {
      "epoch": 0.47796070100902815,
      "grad_norm": 0.09285062218223354,
      "learning_rate": 0.0001246243272130804,
      "loss": 1.2196,
      "step": 225
    },
    {
      "epoch": 0.4885820499203399,
      "grad_norm": 0.09947551088527716,
      "learning_rate": 0.00012100905639472779,
      "loss": 1.2119,
      "step": 230
    },
    {
      "epoch": 0.4992033988316516,
      "grad_norm": 0.09909407559931054,
      "learning_rate": 0.00011736481776669306,
      "loss": 1.2143,
      "step": 235
    },
    {
      "epoch": 0.5098247477429634,
      "grad_norm": 0.10088313629264518,
      "learning_rate": 0.00011369663609586854,
      "loss": 1.1898,
      "step": 240
    },
    {
      "epoch": 0.5204460966542751,
      "grad_norm": 0.09420246322941377,
      "learning_rate": 0.00011000956916240985,
      "loss": 1.1856,
      "step": 245
    },
    {
      "epoch": 0.5310674455655868,
      "grad_norm": 0.09209874396416272,
      "learning_rate": 0.00010630870078594249,
      "loss": 1.2112,
      "step": 250
    },
    {
      "epoch": 0.5416887944768985,
      "grad_norm": 0.09464167718791672,
      "learning_rate": 0.0001025991338158651,
      "loss": 1.1794,
      "step": 255
    },
    {
      "epoch": 0.5523101433882103,
      "grad_norm": 0.09518574121409505,
      "learning_rate": 9.888598309541347e-05,
      "loss": 1.2122,
      "step": 260
    },
    {
      "epoch": 0.562931492299522,
      "grad_norm": 0.0934895122551569,
      "learning_rate": 9.517436840918766e-05,
      "loss": 1.1972,
      "step": 265
    },
    {
      "epoch": 0.5735528412108338,
      "grad_norm": 0.09613849052521826,
      "learning_rate": 9.146940742386553e-05,
      "loss": 1.198,
      "step": 270
    },
    {
      "epoch": 0.5841741901221456,
      "grad_norm": 0.10787364626079722,
      "learning_rate": 8.777620863183657e-05,
      "loss": 1.2048,
      "step": 275
    },
    {
      "epoch": 0.5947955390334573,
      "grad_norm": 0.10205009540360997,
      "learning_rate": 8.409986430748545e-05,
      "loss": 1.2082,
      "step": 280
    },
    {
      "epoch": 0.605416887944769,
      "grad_norm": 0.09826378546823292,
      "learning_rate": 8.044544348583755e-05,
      "loss": 1.1881,
      "step": 285
    },
    {
      "epoch": 0.6160382368560807,
      "grad_norm": 0.0880761899795154,
      "learning_rate": 7.681798497324716e-05,
      "loss": 1.1914,
      "step": 290
    },
    {
      "epoch": 0.6266595857673924,
      "grad_norm": 0.09544723804744151,
      "learning_rate": 7.322249039976608e-05,
      "loss": 1.1963,
      "step": 295
    },
    {
      "epoch": 0.6372809346787042,
      "grad_norm": 0.09352140706616008,
      "learning_rate": 6.966391732277143e-05,
      "loss": 1.2067,
      "step": 300
    },
    {
      "epoch": 0.6479022835900159,
      "grad_norm": 0.09564701019738492,
      "learning_rate": 6.614717239136246e-05,
      "loss": 1.2115,
      "step": 305
    },
    {
      "epoch": 0.6585236325013276,
      "grad_norm": 0.08893207822102751,
      "learning_rate": 6.267710458095053e-05,
      "loss": 1.212,
      "step": 310
    },
    {
      "epoch": 0.6691449814126395,
      "grad_norm": 0.09531523433315588,
      "learning_rate": 5.9258498507371194e-05,
      "loss": 1.2092,
      "step": 315
    },
    {
      "epoch": 0.6797663303239512,
      "grad_norm": 0.09807635264275837,
      "learning_rate": 5.589606782973683e-05,
      "loss": 1.1948,
      "step": 320
    },
    {
      "epoch": 0.6903876792352629,
      "grad_norm": 0.09015123776400549,
      "learning_rate": 5.259444875112624e-05,
      "loss": 1.1961,
      "step": 325
    },
    {
      "epoch": 0.7010090281465746,
      "grad_norm": 0.09609066637705146,
      "learning_rate": 4.93581936260724e-05,
      "loss": 1.1907,
      "step": 330
    },
    {
      "epoch": 0.7116303770578863,
      "grad_norm": 0.10045278634192746,
      "learning_rate": 4.6191764683662744e-05,
      "loss": 1.2061,
      "step": 335
    },
    {
      "epoch": 0.7222517259691981,
      "grad_norm": 0.09313267074455285,
      "learning_rate": 4.309952787490689e-05,
      "loss": 1.18,
      "step": 340
    },
    {
      "epoch": 0.7328730748805098,
      "grad_norm": 0.09412892775955094,
      "learning_rate": 4.008574685285442e-05,
      "loss": 1.2014,
      "step": 345
    },
    {
      "epoch": 0.7434944237918215,
      "grad_norm": 0.09326142454266173,
      "learning_rate": 3.7154577093764334e-05,
      "loss": 1.2008,
      "step": 350
    },
    {
      "epoch": 0.7541157727031333,
      "grad_norm": 0.09023610029430787,
      "learning_rate": 3.4310060167430725e-05,
      "loss": 1.2036,
      "step": 355
    },
    {
      "epoch": 0.7647371216144451,
      "grad_norm": 0.09605450130530022,
      "learning_rate": 3.155611816456586e-05,
      "loss": 1.1867,
      "step": 360
    },
    {
      "epoch": 0.7753584705257568,
      "grad_norm": 0.08909810024970242,
      "learning_rate": 2.889654828892393e-05,
      "loss": 1.1968,
      "step": 365
    },
    {
      "epoch": 0.7859798194370685,
      "grad_norm": 0.09574483963539772,
      "learning_rate": 2.6335017621622116e-05,
      "loss": 1.1995,
      "step": 370
    },
    {
      "epoch": 0.7966011683483802,
      "grad_norm": 0.09515266933305087,
      "learning_rate": 2.3875058064877807e-05,
      "loss": 1.1985,
      "step": 375
    },
    {
      "epoch": 0.807222517259692,
      "grad_norm": 0.09082877760407207,
      "learning_rate": 2.1520061472133902e-05,
      "loss": 1.199,
      "step": 380
    },
    {
      "epoch": 0.8178438661710037,
      "grad_norm": 0.08871492165043048,
      "learning_rate": 1.927327497128706e-05,
      "loss": 1.2056,
      "step": 385
    },
    {
      "epoch": 0.8284652150823154,
      "grad_norm": 0.09486662553716946,
      "learning_rate": 1.7137796487466797e-05,
      "loss": 1.193,
      "step": 390
    },
    {
      "epoch": 0.8390865639936272,
      "grad_norm": 0.0901905857527847,
      "learning_rate": 1.5116570471539293e-05,
      "loss": 1.186,
      "step": 395
    },
    {
      "epoch": 0.849707912904939,
      "grad_norm": 0.0885164111129225,
      "learning_rate": 1.3212383840225329e-05,
      "loss": 1.1981,
      "step": 400
    },
    {
      "epoch": 0.8603292618162507,
      "grad_norm": 0.09557246358632707,
      "learning_rate": 1.1427862133430156e-05,
      "loss": 1.1964,
      "step": 405
    },
    {
      "epoch": 0.8709506107275624,
      "grad_norm": 0.09211165789637583,
      "learning_rate": 9.765465894083636e-06,
      "loss": 1.1778,
      "step": 410
    },
    {
      "epoch": 0.8815719596388741,
      "grad_norm": 0.09006878763713062,
      "learning_rate": 8.227487275482592e-06,
      "loss": 1.1819,
      "step": 415
    },
    {
      "epoch": 0.8921933085501859,
      "grad_norm": 0.08884359305311183,
      "learning_rate": 6.81604688081271e-06,
      "loss": 1.1881,
      "step": 420
    },
    {
      "epoch": 0.9028146574614976,
      "grad_norm": 0.09137953280960603,
      "learning_rate": 5.533090839208133e-06,
      "loss": 1.1826,
      "step": 425
    },
    {
      "epoch": 0.9134360063728093,
      "grad_norm": 0.08709835466499691,
      "learning_rate": 4.380388122380141e-06,
      "loss": 1.2113,
      "step": 430
    },
    {
      "epoch": 0.924057355284121,
      "grad_norm": 0.0863419000253536,
      "learning_rate": 3.359528105515064e-06,
      "loss": 1.1898,
      "step": 435
    },
    {
      "epoch": 0.9346787041954329,
      "grad_norm": 0.09252141283028179,
      "learning_rate": 2.471918375804105e-06,
      "loss": 1.1902,
      "step": 440
    },
    {
      "epoch": 0.9453000531067446,
      "grad_norm": 0.09000706743960567,
      "learning_rate": 1.7187827916271382e-06,
      "loss": 1.1975,
      "step": 445
    },
    {
      "epoch": 0.9559214020180563,
      "grad_norm": 0.08910671944326799,
      "learning_rate": 1.1011597950663865e-06,
      "loss": 1.1879,
      "step": 450
    },
    {
      "epoch": 0.966542750929368,
      "grad_norm": 0.08866423842439104,
      "learning_rate": 6.199009800765265e-07,
      "loss": 1.1773,
      "step": 455
    },
    {
      "epoch": 0.9771640998406798,
      "grad_norm": 0.09241447437367215,
      "learning_rate": 2.756699182858369e-07,
      "loss": 1.1917,
      "step": 460
    },
    {
      "epoch": 0.9877854487519915,
      "grad_norm": 0.08660231126732977,
      "learning_rate": 6.894124404711599e-08,
      "loss": 1.2142,
      "step": 465
    },
    {
      "epoch": 0.9984067976633032,
      "grad_norm": 0.08759385215944408,
      "learning_rate": 0.0,
      "loss": 1.2016,
      "step": 470
    },
    {
      "epoch": 0.9984067976633032,
      "eval_runtime": 4.2231,
      "eval_samples_per_second": 2.368,
      "eval_steps_per_second": 0.71,
      "step": 470
    },
    {
      "epoch": 0.9984067976633032,
      "step": 470,
      "total_flos": 3.0618166709610086e+17,
      "train_loss": 1.2359964916046629,
      "train_runtime": 17731.1519,
      "train_samples_per_second": 3.397,
      "train_steps_per_second": 0.027
    }
  ],
  "logging_steps": 5,
  "max_steps": 470,
  "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": 3.0618166709610086e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}