{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1143,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0,
      "eval_loss": 2.1641297340393066,
      "eval_runtime": 4.2967,
      "eval_samples_per_second": 4.655,
      "eval_steps_per_second": 0.465,
      "step": 0
    },
    {
      "epoch": 0.0008750820389411508,
      "grad_norm": 6.37307071685791,
      "learning_rate": 2.915451895043732e-07,
      "loss": 1.6434,
      "step": 1
    },
    {
      "epoch": 0.008750820389411508,
      "grad_norm": 4.0545759201049805,
      "learning_rate": 2.915451895043732e-06,
      "loss": 1.6965,
      "step": 10
    },
    {
      "epoch": 0.017501640778823015,
      "grad_norm": 2.363191604614258,
      "learning_rate": 5.830903790087464e-06,
      "loss": 1.5272,
      "step": 20
    },
    {
      "epoch": 0.02625246116823452,
      "grad_norm": 1.6348848342895508,
      "learning_rate": 8.746355685131195e-06,
      "loss": 1.389,
      "step": 30
    },
    {
      "epoch": 0.03500328155764603,
      "grad_norm": 1.6716902256011963,
      "learning_rate": 1.1661807580174927e-05,
      "loss": 1.348,
      "step": 40
    },
    {
      "epoch": 0.04375410194705753,
      "grad_norm": 1.510228157043457,
      "learning_rate": 1.457725947521866e-05,
      "loss": 1.2997,
      "step": 50
    },
    {
      "epoch": 0.05250492233646904,
      "grad_norm": 1.6153247356414795,
      "learning_rate": 1.749271137026239e-05,
      "loss": 1.2665,
      "step": 60
    },
    {
      "epoch": 0.06125574272588055,
      "grad_norm": 1.446387767791748,
      "learning_rate": 2.0408163265306123e-05,
      "loss": 1.237,
      "step": 70
    },
    {
      "epoch": 0.07000656311529206,
      "grad_norm": 1.3039863109588623,
      "learning_rate": 2.3323615160349855e-05,
      "loss": 1.2341,
      "step": 80
    },
    {
      "epoch": 0.07875738350470357,
      "grad_norm": 1.4866383075714111,
      "learning_rate": 2.6239067055393584e-05,
      "loss": 1.2338,
      "step": 90
    },
    {
      "epoch": 0.08750820389411507,
      "grad_norm": 1.358859658241272,
      "learning_rate": 2.915451895043732e-05,
      "loss": 1.2331,
      "step": 100
    },
    {
      "epoch": 0.09625902428352658,
      "grad_norm": 1.847506046295166,
      "learning_rate": 3.206997084548105e-05,
      "loss": 1.1628,
      "step": 110
    },
    {
      "epoch": 0.10500984467293809,
      "grad_norm": 1.7742356061935425,
      "learning_rate": 3.498542274052478e-05,
      "loss": 1.1846,
      "step": 120
    },
    {
      "epoch": 0.1137606650623496,
      "grad_norm": 1.3415714502334595,
      "learning_rate": 3.790087463556852e-05,
      "loss": 1.1699,
      "step": 130
    },
    {
      "epoch": 0.1225114854517611,
      "grad_norm": 1.5319396257400513,
      "learning_rate": 4.0816326530612245e-05,
      "loss": 1.181,
      "step": 140
    },
    {
      "epoch": 0.1312623058411726,
      "grad_norm": 1.3915642499923706,
      "learning_rate": 4.373177842565598e-05,
      "loss": 1.189,
      "step": 150
    },
    {
      "epoch": 0.14001312623058412,
      "grad_norm": 1.175917625427246,
      "learning_rate": 4.664723032069971e-05,
      "loss": 1.1605,
      "step": 160
    },
    {
      "epoch": 0.14876394661999562,
      "grad_norm": 1.3125519752502441,
      "learning_rate": 4.956268221574344e-05,
      "loss": 1.1734,
      "step": 170
    },
    {
      "epoch": 0.15751476700940714,
      "grad_norm": 1.2966923713684082,
      "learning_rate": 5.247813411078717e-05,
      "loss": 1.2075,
      "step": 180
    },
    {
      "epoch": 0.16626558739881864,
      "grad_norm": 1.2630099058151245,
      "learning_rate": 5.539358600583091e-05,
      "loss": 1.1791,
      "step": 190
    },
    {
      "epoch": 0.17501640778823013,
      "grad_norm": 1.306665301322937,
      "learning_rate": 5.830903790087464e-05,
      "loss": 1.1469,
      "step": 200
    },
    {
      "epoch": 0.18376722817764166,
      "grad_norm": 1.19467031955719,
      "learning_rate": 6.122448979591838e-05,
      "loss": 1.185,
      "step": 210
    },
    {
      "epoch": 0.19251804856705315,
      "grad_norm": 1.416387677192688,
      "learning_rate": 6.41399416909621e-05,
      "loss": 1.2061,
      "step": 220
    },
    {
      "epoch": 0.20126886895646467,
      "grad_norm": 1.3546264171600342,
      "learning_rate": 6.705539358600583e-05,
      "loss": 1.2016,
      "step": 230
    },
    {
      "epoch": 0.21001968934587617,
      "grad_norm": 1.2417850494384766,
      "learning_rate": 6.997084548104956e-05,
      "loss": 1.1797,
      "step": 240
    },
    {
      "epoch": 0.2187705097352877,
      "grad_norm": 1.2703570127487183,
      "learning_rate": 7.28862973760933e-05,
      "loss": 1.2059,
      "step": 250
    },
    {
      "epoch": 0.2275213301246992,
      "grad_norm": 1.2479429244995117,
      "learning_rate": 7.580174927113704e-05,
      "loss": 1.1958,
      "step": 260
    },
    {
      "epoch": 0.23627215051411068,
      "grad_norm": 1.507601261138916,
      "learning_rate": 7.871720116618077e-05,
      "loss": 1.2151,
      "step": 270
    },
    {
      "epoch": 0.2450229709035222,
      "grad_norm": 1.2083854675292969,
      "learning_rate": 8.163265306122449e-05,
      "loss": 1.2202,
      "step": 280
    },
    {
      "epoch": 0.2537737912929337,
      "grad_norm": 1.2939566373825073,
      "learning_rate": 8.454810495626822e-05,
      "loss": 1.1916,
      "step": 290
    },
    {
      "epoch": 0.2625246116823452,
      "grad_norm": 1.2871382236480713,
      "learning_rate": 8.746355685131195e-05,
      "loss": 1.222,
      "step": 300
    },
    {
      "epoch": 0.27127543207175675,
      "grad_norm": 1.1558256149291992,
      "learning_rate": 9.037900874635569e-05,
      "loss": 1.2094,
      "step": 310
    },
    {
      "epoch": 0.28002625246116825,
      "grad_norm": 1.0638883113861084,
      "learning_rate": 9.329446064139942e-05,
      "loss": 1.2,
      "step": 320
    },
    {
      "epoch": 0.28877707285057974,
      "grad_norm": 1.1072458028793335,
      "learning_rate": 9.620991253644317e-05,
      "loss": 1.224,
      "step": 330
    },
    {
      "epoch": 0.29752789323999124,
      "grad_norm": 1.1332110166549683,
      "learning_rate": 9.912536443148688e-05,
      "loss": 1.2266,
      "step": 340
    },
    {
      "epoch": 0.30627871362940273,
      "grad_norm": 1.0537033081054688,
      "learning_rate": 9.999872800049233e-05,
      "loss": 1.2173,
      "step": 350
    },
    {
      "epoch": 0.3150295340188143,
      "grad_norm": 1.090928316116333,
      "learning_rate": 9.999249795462235e-05,
      "loss": 1.2416,
      "step": 360
    },
    {
      "epoch": 0.3237803544082258,
      "grad_norm": 1.0084835290908813,
      "learning_rate": 9.998107687592326e-05,
      "loss": 1.2094,
      "step": 370
    },
    {
      "epoch": 0.3325311747976373,
      "grad_norm": 1.82576584815979,
      "learning_rate": 9.996446595031691e-05,
      "loss": 1.2246,
      "step": 380
    },
    {
      "epoch": 0.34128199518704877,
      "grad_norm": 1.2305560111999512,
      "learning_rate": 9.994266690261928e-05,
      "loss": 1.2647,
      "step": 390
    },
    {
      "epoch": 0.35003281557646027,
      "grad_norm": 1.170067548751831,
      "learning_rate": 9.991568199636148e-05,
      "loss": 1.1829,
      "step": 400
    },
    {
      "epoch": 0.3587836359658718,
      "grad_norm": 1.0299819707870483,
      "learning_rate": 9.988351403355454e-05,
      "loss": 1.2471,
      "step": 410
    },
    {
      "epoch": 0.3675344563552833,
      "grad_norm": 0.9742593765258789,
      "learning_rate": 9.98461663543987e-05,
      "loss": 1.2049,
      "step": 420
    },
    {
      "epoch": 0.3762852767446948,
      "grad_norm": 0.9377045631408691,
      "learning_rate": 9.980364283693638e-05,
      "loss": 1.1963,
      "step": 430
    },
    {
      "epoch": 0.3850360971341063,
      "grad_norm": 1.0425899028778076,
      "learning_rate": 9.97559478966496e-05,
      "loss": 1.2167,
      "step": 440
    },
    {
      "epoch": 0.39378691752351785,
      "grad_norm": 0.9749513864517212,
      "learning_rate": 9.97030864860014e-05,
      "loss": 1.2166,
      "step": 450
    },
    {
      "epoch": 0.40253773791292935,
      "grad_norm": 1.0552780628204346,
      "learning_rate": 9.964506409392176e-05,
      "loss": 1.2228,
      "step": 460
    },
    {
      "epoch": 0.41128855830234085,
      "grad_norm": 1.0261808633804321,
      "learning_rate": 9.958188674523748e-05,
      "loss": 1.2252,
      "step": 470
    },
    {
      "epoch": 0.42003937869175234,
      "grad_norm": 0.9530945420265198,
      "learning_rate": 9.951356100004665e-05,
      "loss": 1.1845,
      "step": 480
    },
    {
      "epoch": 0.42879019908116384,
      "grad_norm": 0.8990481495857239,
      "learning_rate": 9.94400939530375e-05,
      "loss": 1.2283,
      "step": 490
    },
    {
      "epoch": 0.4375410194705754,
      "grad_norm": 0.9713592529296875,
      "learning_rate": 9.936149323275169e-05,
      "loss": 1.1945,
      "step": 500
    },
    {
      "epoch": 0.4462918398599869,
      "grad_norm": 1.003854513168335,
      "learning_rate": 9.927776700079216e-05,
      "loss": 1.2322,
      "step": 510
    },
    {
      "epoch": 0.4550426602493984,
      "grad_norm": 0.935400664806366,
      "learning_rate": 9.918892395097572e-05,
      "loss": 1.2272,
      "step": 520
    },
    {
      "epoch": 0.4637934806388099,
      "grad_norm": 1.075519323348999,
      "learning_rate": 9.90949733084303e-05,
      "loss": 1.2069,
      "step": 530
    },
    {
      "epoch": 0.47254430102822137,
      "grad_norm": 0.9949712157249451,
      "learning_rate": 9.8995924828637e-05,
      "loss": 1.2083,
      "step": 540
    },
    {
      "epoch": 0.4812951214176329,
      "grad_norm": 0.8942195773124695,
      "learning_rate": 9.889178879641717e-05,
      "loss": 1.2137,
      "step": 550
    },
    {
      "epoch": 0.4900459418070444,
      "grad_norm": 0.9525908827781677,
      "learning_rate": 9.878257602486445e-05,
      "loss": 1.2348,
      "step": 560
    },
    {
      "epoch": 0.4987967621964559,
      "grad_norm": 0.895167350769043,
      "learning_rate": 9.8668297854222e-05,
      "loss": 1.2034,
      "step": 570
    },
    {
      "epoch": 0.5075475825858674,
      "grad_norm": 1.0244312286376953,
      "learning_rate": 9.854896615070495e-05,
      "loss": 1.1942,
      "step": 580
    },
    {
      "epoch": 0.516298402975279,
      "grad_norm": 0.9835163950920105,
      "learning_rate": 9.842459330526826e-05,
      "loss": 1.2182,
      "step": 590
    },
    {
      "epoch": 0.5250492233646904,
      "grad_norm": 0.9238565564155579,
      "learning_rate": 9.829519223232006e-05,
      "loss": 1.1992,
      "step": 600
    },
    {
      "epoch": 0.533800043754102,
      "grad_norm": 0.9063233733177185,
      "learning_rate": 9.81607763683808e-05,
      "loss": 1.2135,
      "step": 610
    },
    {
      "epoch": 0.5425508641435135,
      "grad_norm": 0.9810764193534851,
      "learning_rate": 9.802135967068782e-05,
      "loss": 1.1909,
      "step": 620
    },
    {
      "epoch": 0.5513016845329249,
      "grad_norm": 0.9388274550437927,
      "learning_rate": 9.787695661574632e-05,
      "loss": 1.1693,
      "step": 630
    },
    {
      "epoch": 0.5600525049223365,
      "grad_norm": 0.933283805847168,
      "learning_rate": 9.772758219782601e-05,
      "loss": 1.1857,
      "step": 640
    },
    {
      "epoch": 0.5688033253117479,
      "grad_norm": 0.947989284992218,
      "learning_rate": 9.757325192740425e-05,
      "loss": 1.1901,
      "step": 650
    },
    {
      "epoch": 0.5775541457011595,
      "grad_norm": 0.8272686004638672,
      "learning_rate": 9.741398182955548e-05,
      "loss": 1.2087,
      "step": 660
    },
    {
      "epoch": 0.586304966090571,
      "grad_norm": 0.8907813429832458,
      "learning_rate": 9.724978844228717e-05,
      "loss": 1.201,
      "step": 670
    },
    {
      "epoch": 0.5950557864799825,
      "grad_norm": 0.8374966382980347,
      "learning_rate": 9.708068881482271e-05,
      "loss": 1.2028,
      "step": 680
    },
    {
      "epoch": 0.603806606869394,
      "grad_norm": 0.9283761382102966,
      "learning_rate": 9.690670050583095e-05,
      "loss": 1.1995,
      "step": 690
    },
    {
      "epoch": 0.6125574272588055,
      "grad_norm": 0.8573452234268188,
      "learning_rate": 9.672784158160307e-05,
      "loss": 1.1372,
      "step": 700
    },
    {
      "epoch": 0.621308247648217,
      "grad_norm": 0.8831506371498108,
      "learning_rate": 9.654413061417655e-05,
      "loss": 1.1626,
      "step": 710
    },
    {
      "epoch": 0.6300590680376286,
      "grad_norm": 0.9180812239646912,
      "learning_rate": 9.635558667940683e-05,
      "loss": 1.1466,
      "step": 720
    },
    {
      "epoch": 0.63880988842704,
      "grad_norm": 0.8657775521278381,
      "learning_rate": 9.616222935498646e-05,
      "loss": 1.2052,
      "step": 730
    },
    {
      "epoch": 0.6475607088164516,
      "grad_norm": 0.9488115310668945,
      "learning_rate": 9.596407871841229e-05,
      "loss": 1.1651,
      "step": 740
    },
    {
      "epoch": 0.656311529205863,
      "grad_norm": 0.8592752814292908,
      "learning_rate": 9.57611553449006e-05,
      "loss": 1.1953,
      "step": 750
    },
    {
      "epoch": 0.6650623495952745,
      "grad_norm": 0.889445960521698,
      "learning_rate": 9.555348030525076e-05,
      "loss": 1.1647,
      "step": 760
    },
    {
      "epoch": 0.6738131699846861,
      "grad_norm": 0.8997176885604858,
      "learning_rate": 9.534107516365725e-05,
      "loss": 1.167,
      "step": 770
    },
    {
      "epoch": 0.6825639903740975,
      "grad_norm": 0.8208065032958984,
      "learning_rate": 9.512396197547053e-05,
      "loss": 1.1631,
      "step": 780
    },
    {
      "epoch": 0.6913148107635091,
      "grad_norm": 0.8419785499572754,
      "learning_rate": 9.490216328490692e-05,
      "loss": 1.1857,
      "step": 790
    },
    {
      "epoch": 0.7000656311529205,
      "grad_norm": 0.8125676512718201,
      "learning_rate": 9.467570212270767e-05,
      "loss": 1.2426,
      "step": 800
    },
    {
      "epoch": 0.7088164515423321,
      "grad_norm": 0.9222508072853088,
      "learning_rate": 9.444460200374748e-05,
      "loss": 1.1452,
      "step": 810
    },
    {
      "epoch": 0.7175672719317436,
      "grad_norm": 0.8932722210884094,
      "learning_rate": 9.420888692459291e-05,
      "loss": 1.1647,
      "step": 820
    },
    {
      "epoch": 0.7263180923211551,
      "grad_norm": 0.817932665348053,
      "learning_rate": 9.396858136101066e-05,
      "loss": 1.1618,
      "step": 830
    },
    {
      "epoch": 0.7350689127105666,
      "grad_norm": 0.8717408180236816,
      "learning_rate": 9.372371026542595e-05,
      "loss": 1.1517,
      "step": 840
    },
    {
      "epoch": 0.7438197330999782,
      "grad_norm": 0.8578230142593384,
      "learning_rate": 9.347429906433174e-05,
      "loss": 1.2009,
      "step": 850
    },
    {
      "epoch": 0.7525705534893896,
      "grad_norm": 0.8276301622390747,
      "learning_rate": 9.322037365564845e-05,
      "loss": 1.1627,
      "step": 860
    },
    {
      "epoch": 0.7613213738788012,
      "grad_norm": 0.7934173941612244,
      "learning_rate": 9.296196040603475e-05,
      "loss": 1.1735,
      "step": 870
    },
    {
      "epoch": 0.7700721942682126,
      "grad_norm": 0.8270857930183411,
      "learning_rate": 9.269908614814995e-05,
      "loss": 1.149,
      "step": 880
    },
    {
      "epoch": 0.7788230146576242,
      "grad_norm": 1.0632795095443726,
      "learning_rate": 9.243177817786757e-05,
      "loss": 1.1937,
      "step": 890
    },
    {
      "epoch": 0.7875738350470357,
      "grad_norm": 0.8449203968048096,
      "learning_rate": 9.216006425144118e-05,
      "loss": 1.1787,
      "step": 900
    },
    {
      "epoch": 0.7963246554364471,
      "grad_norm": 0.7634311318397522,
      "learning_rate": 9.188397258262221e-05,
      "loss": 1.1445,
      "step": 910
    },
    {
      "epoch": 0.8050754758258587,
      "grad_norm": 0.7856956720352173,
      "learning_rate": 9.160353183973046e-05,
      "loss": 1.1519,
      "step": 920
    },
    {
      "epoch": 0.8138262962152701,
      "grad_norm": 0.8162206411361694,
      "learning_rate": 9.131877114267711e-05,
      "loss": 1.1282,
      "step": 930
    },
    {
      "epoch": 0.8225771166046817,
      "grad_norm": 0.8263719081878662,
      "learning_rate": 9.102972005994122e-05,
      "loss": 1.1127,
      "step": 940
    },
    {
      "epoch": 0.8313279369940932,
      "grad_norm": 0.831969141960144,
      "learning_rate": 9.073640860549931e-05,
      "loss": 1.1446,
      "step": 950
    },
    {
      "epoch": 0.8400787573835047,
      "grad_norm": 0.8127765655517578,
      "learning_rate": 9.043886723570884e-05,
      "loss": 1.1649,
      "step": 960
    },
    {
      "epoch": 0.8488295777729162,
      "grad_norm": 0.7642777562141418,
      "learning_rate": 9.013712684614582e-05,
      "loss": 1.1656,
      "step": 970
    },
    {
      "epoch": 0.8575803981623277,
      "grad_norm": 0.8071634769439697,
      "learning_rate": 8.983121876839657e-05,
      "loss": 1.1414,
      "step": 980
    },
    {
      "epoch": 0.8663312185517392,
      "grad_norm": 0.7789682149887085,
      "learning_rate": 8.95211747668046e-05,
      "loss": 1.1127,
      "step": 990
    },
    {
      "epoch": 0.8750820389411508,
      "grad_norm": 0.7899104356765747,
      "learning_rate": 8.920702703517204e-05,
      "loss": 1.1218,
      "step": 1000
    },
    {
      "epoch": 0.8838328593305622,
      "grad_norm": 0.726874053478241,
      "learning_rate": 8.888880819341702e-05,
      "loss": 1.1345,
      "step": 1010
    },
    {
      "epoch": 0.8925836797199738,
      "grad_norm": 0.8020316958427429,
      "learning_rate": 8.856655128418637e-05,
      "loss": 1.1229,
      "step": 1020
    },
    {
      "epoch": 0.9013345001093852,
      "grad_norm": 0.8466740250587463,
      "learning_rate": 8.824028976942465e-05,
      "loss": 1.1451,
      "step": 1030
    },
    {
      "epoch": 0.9100853204987968,
      "grad_norm": 0.7729008793830872,
      "learning_rate": 8.791005752689958e-05,
      "loss": 1.1204,
      "step": 1040
    },
    {
      "epoch": 0.9188361408882083,
      "grad_norm": 0.8055347204208374,
      "learning_rate": 8.757588884668434e-05,
      "loss": 1.1372,
      "step": 1050
    },
    {
      "epoch": 0.9275869612776197,
      "grad_norm": 0.8180489540100098,
      "learning_rate": 8.723781842759695e-05,
      "loss": 1.1632,
      "step": 1060
    },
    {
      "epoch": 0.9363377816670313,
      "grad_norm": 0.816849946975708,
      "learning_rate": 8.689588137359732e-05,
      "loss": 1.1226,
      "step": 1070
    },
    {
      "epoch": 0.9450886020564427,
      "grad_norm": 0.8028609752655029,
      "learning_rate": 8.655011319014216e-05,
      "loss": 1.1559,
      "step": 1080
    },
    {
      "epoch": 0.9538394224458543,
      "grad_norm": 0.8719303011894226,
      "learning_rate": 8.620054978049829e-05,
      "loss": 1.1522,
      "step": 1090
    },
    {
      "epoch": 0.9625902428352658,
      "grad_norm": 0.766177237033844,
      "learning_rate": 8.584722744201447e-05,
      "loss": 1.1186,
      "step": 1100
    },
    {
      "epoch": 0.9713410632246773,
      "grad_norm": 0.7790910005569458,
      "learning_rate": 8.549018286235255e-05,
      "loss": 1.1227,
      "step": 1110
    },
    {
      "epoch": 0.9800918836140888,
      "grad_norm": 0.7803717255592346,
      "learning_rate": 8.512945311567786e-05,
      "loss": 1.1186,
      "step": 1120
    },
    {
      "epoch": 0.9888427040035004,
      "grad_norm": 0.7084935307502747,
      "learning_rate": 8.476507565880957e-05,
      "loss": 1.1085,
      "step": 1130
    },
    {
      "epoch": 0.9975935243929118,
      "grad_norm": 0.7696670889854431,
      "learning_rate": 8.439708832733142e-05,
      "loss": 1.1123,
      "step": 1140
    }
  ],
  "logging_steps": 10,
  "max_steps": 3426,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500.0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7750297385159885e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}