{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9943289224952743,
  "eval_steps": 500,
  "global_step": 1188,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02520478890989288,
      "grad_norm": 9.633888402845015,
      "learning_rate": 5e-06,
      "loss": 0.9444,
      "step": 10
    },
    {
      "epoch": 0.05040957781978576,
      "grad_norm": 1.6254228664238897,
      "learning_rate": 5e-06,
      "loss": 0.8095,
      "step": 20
    },
    {
      "epoch": 0.07561436672967864,
      "grad_norm": 0.8936028314003451,
      "learning_rate": 5e-06,
      "loss": 0.7596,
      "step": 30
    },
    {
      "epoch": 0.10081915563957151,
      "grad_norm": 0.9708205238462188,
      "learning_rate": 5e-06,
      "loss": 0.7334,
      "step": 40
    },
    {
      "epoch": 0.1260239445494644,
      "grad_norm": 0.8882056031134592,
      "learning_rate": 5e-06,
      "loss": 0.7166,
      "step": 50
    },
    {
      "epoch": 0.15122873345935728,
      "grad_norm": 0.8542020955227222,
      "learning_rate": 5e-06,
      "loss": 0.7004,
      "step": 60
    },
    {
      "epoch": 0.17643352236925017,
      "grad_norm": 0.719450185402131,
      "learning_rate": 5e-06,
      "loss": 0.6877,
      "step": 70
    },
    {
      "epoch": 0.20163831127914303,
      "grad_norm": 0.6838086991132964,
      "learning_rate": 5e-06,
      "loss": 0.676,
      "step": 80
    },
    {
      "epoch": 0.22684310018903592,
      "grad_norm": 0.6199036833773371,
      "learning_rate": 5e-06,
      "loss": 0.6754,
      "step": 90
    },
    {
      "epoch": 0.2520478890989288,
      "grad_norm": 0.5787703367375647,
      "learning_rate": 5e-06,
      "loss": 0.6562,
      "step": 100
    },
    {
      "epoch": 0.2772526780088217,
      "grad_norm": 0.633249705700733,
      "learning_rate": 5e-06,
      "loss": 0.665,
      "step": 110
    },
    {
      "epoch": 0.30245746691871456,
      "grad_norm": 0.6304627866586173,
      "learning_rate": 5e-06,
      "loss": 0.6634,
      "step": 120
    },
    {
      "epoch": 0.3276622558286074,
      "grad_norm": 0.5506728721157861,
      "learning_rate": 5e-06,
      "loss": 0.6549,
      "step": 130
    },
    {
      "epoch": 0.35286704473850034,
      "grad_norm": 0.5151002955744762,
      "learning_rate": 5e-06,
      "loss": 0.6522,
      "step": 140
    },
    {
      "epoch": 0.3780718336483932,
      "grad_norm": 0.5992082289679086,
      "learning_rate": 5e-06,
      "loss": 0.6528,
      "step": 150
    },
    {
      "epoch": 0.40327662255828606,
      "grad_norm": 0.4663777253829188,
      "learning_rate": 5e-06,
      "loss": 0.642,
      "step": 160
    },
    {
      "epoch": 0.428481411468179,
      "grad_norm": 0.5785034175448459,
      "learning_rate": 5e-06,
      "loss": 0.6469,
      "step": 170
    },
    {
      "epoch": 0.45368620037807184,
      "grad_norm": 0.6585860693219876,
      "learning_rate": 5e-06,
      "loss": 0.646,
      "step": 180
    },
    {
      "epoch": 0.4788909892879647,
      "grad_norm": 0.6722487645620258,
      "learning_rate": 5e-06,
      "loss": 0.6403,
      "step": 190
    },
    {
      "epoch": 0.5040957781978576,
      "grad_norm": 0.5254154176523609,
      "learning_rate": 5e-06,
      "loss": 0.6387,
      "step": 200
    },
    {
      "epoch": 0.5293005671077504,
      "grad_norm": 0.5128942747923588,
      "learning_rate": 5e-06,
      "loss": 0.6379,
      "step": 210
    },
    {
      "epoch": 0.5545053560176434,
      "grad_norm": 0.5642956436475494,
      "learning_rate": 5e-06,
      "loss": 0.6393,
      "step": 220
    },
    {
      "epoch": 0.5797101449275363,
      "grad_norm": 0.6837039476741191,
      "learning_rate": 5e-06,
      "loss": 0.6359,
      "step": 230
    },
    {
      "epoch": 0.6049149338374291,
      "grad_norm": 0.6667359902635842,
      "learning_rate": 5e-06,
      "loss": 0.6351,
      "step": 240
    },
    {
      "epoch": 0.630119722747322,
      "grad_norm": 0.6627848973706361,
      "learning_rate": 5e-06,
      "loss": 0.6343,
      "step": 250
    },
    {
      "epoch": 0.6553245116572148,
      "grad_norm": 0.5241036221432155,
      "learning_rate": 5e-06,
      "loss": 0.6279,
      "step": 260
    },
    {
      "epoch": 0.6805293005671077,
      "grad_norm": 0.576211583526909,
      "learning_rate": 5e-06,
      "loss": 0.6258,
      "step": 270
    },
    {
      "epoch": 0.7057340894770007,
      "grad_norm": 0.5136516604177849,
      "learning_rate": 5e-06,
      "loss": 0.6322,
      "step": 280
    },
    {
      "epoch": 0.7309388783868935,
      "grad_norm": 0.5270426246043673,
      "learning_rate": 5e-06,
      "loss": 0.6243,
      "step": 290
    },
    {
      "epoch": 0.7561436672967864,
      "grad_norm": 0.5453025715363531,
      "learning_rate": 5e-06,
      "loss": 0.6224,
      "step": 300
    },
    {
      "epoch": 0.7813484562066793,
      "grad_norm": 0.5116409906154713,
      "learning_rate": 5e-06,
      "loss": 0.6155,
      "step": 310
    },
    {
      "epoch": 0.8065532451165721,
      "grad_norm": 0.5849562966179552,
      "learning_rate": 5e-06,
      "loss": 0.6212,
      "step": 320
    },
    {
      "epoch": 0.831758034026465,
      "grad_norm": 0.6135737091827808,
      "learning_rate": 5e-06,
      "loss": 0.6258,
      "step": 330
    },
    {
      "epoch": 0.856962822936358,
      "grad_norm": 0.5181177544801595,
      "learning_rate": 5e-06,
      "loss": 0.6238,
      "step": 340
    },
    {
      "epoch": 0.8821676118462508,
      "grad_norm": 0.627205460376999,
      "learning_rate": 5e-06,
      "loss": 0.6167,
      "step": 350
    },
    {
      "epoch": 0.9073724007561437,
      "grad_norm": 0.5261678739160346,
      "learning_rate": 5e-06,
      "loss": 0.6117,
      "step": 360
    },
    {
      "epoch": 0.9325771896660365,
      "grad_norm": 0.6244352371075516,
      "learning_rate": 5e-06,
      "loss": 0.6153,
      "step": 370
    },
    {
      "epoch": 0.9577819785759294,
      "grad_norm": 0.48330689120915904,
      "learning_rate": 5e-06,
      "loss": 0.6157,
      "step": 380
    },
    {
      "epoch": 0.9829867674858223,
      "grad_norm": 0.5423735222942331,
      "learning_rate": 5e-06,
      "loss": 0.6132,
      "step": 390
    },
    {
      "epoch": 0.998109640831758,
      "eval_loss": 0.6147013306617737,
      "eval_runtime": 212.3997,
      "eval_samples_per_second": 50.334,
      "eval_steps_per_second": 0.395,
      "step": 396
    },
    {
      "epoch": 1.0081915563957151,
      "grad_norm": 0.5070359483563761,
      "learning_rate": 5e-06,
      "loss": 0.6024,
      "step": 400
    },
    {
      "epoch": 1.033396345305608,
      "grad_norm": 0.5765247476192352,
      "learning_rate": 5e-06,
      "loss": 0.5805,
      "step": 410
    },
    {
      "epoch": 1.0586011342155008,
      "grad_norm": 0.6110502474250971,
      "learning_rate": 5e-06,
      "loss": 0.5715,
      "step": 420
    },
    {
      "epoch": 1.0838059231253938,
      "grad_norm": 0.7545087966794868,
      "learning_rate": 5e-06,
      "loss": 0.5797,
      "step": 430
    },
    {
      "epoch": 1.1090107120352868,
      "grad_norm": 0.6365159456598485,
      "learning_rate": 5e-06,
      "loss": 0.5751,
      "step": 440
    },
    {
      "epoch": 1.1342155009451795,
      "grad_norm": 0.6056198671024684,
      "learning_rate": 5e-06,
      "loss": 0.5742,
      "step": 450
    },
    {
      "epoch": 1.1594202898550725,
      "grad_norm": 0.5291507949595291,
      "learning_rate": 5e-06,
      "loss": 0.5761,
      "step": 460
    },
    {
      "epoch": 1.1846250787649653,
      "grad_norm": 0.6153628132427752,
      "learning_rate": 5e-06,
      "loss": 0.5779,
      "step": 470
    },
    {
      "epoch": 1.2098298676748582,
      "grad_norm": 0.5060871095129219,
      "learning_rate": 5e-06,
      "loss": 0.574,
      "step": 480
    },
    {
      "epoch": 1.2350346565847512,
      "grad_norm": 0.6456813781855114,
      "learning_rate": 5e-06,
      "loss": 0.5759,
      "step": 490
    },
    {
      "epoch": 1.260239445494644,
      "grad_norm": 0.5052335738280048,
      "learning_rate": 5e-06,
      "loss": 0.5756,
      "step": 500
    },
    {
      "epoch": 1.285444234404537,
      "grad_norm": 0.5653893528313595,
      "learning_rate": 5e-06,
      "loss": 0.5754,
      "step": 510
    },
    {
      "epoch": 1.3106490233144297,
      "grad_norm": 0.5278634789290781,
      "learning_rate": 5e-06,
      "loss": 0.5733,
      "step": 520
    },
    {
      "epoch": 1.3358538122243226,
      "grad_norm": 0.5245168937373562,
      "learning_rate": 5e-06,
      "loss": 0.5721,
      "step": 530
    },
    {
      "epoch": 1.3610586011342156,
      "grad_norm": 0.5215086066445794,
      "learning_rate": 5e-06,
      "loss": 0.5733,
      "step": 540
    },
    {
      "epoch": 1.3862633900441084,
      "grad_norm": 0.5370456877329636,
      "learning_rate": 5e-06,
      "loss": 0.571,
      "step": 550
    },
    {
      "epoch": 1.4114681789540013,
      "grad_norm": 0.5521665579415627,
      "learning_rate": 5e-06,
      "loss": 0.5698,
      "step": 560
    },
    {
      "epoch": 1.436672967863894,
      "grad_norm": 0.7002009297394419,
      "learning_rate": 5e-06,
      "loss": 0.5672,
      "step": 570
    },
    {
      "epoch": 1.461877756773787,
      "grad_norm": 0.5738916744555749,
      "learning_rate": 5e-06,
      "loss": 0.5646,
      "step": 580
    },
    {
      "epoch": 1.48708254568368,
      "grad_norm": 0.47370527901117226,
      "learning_rate": 5e-06,
      "loss": 0.5717,
      "step": 590
    },
    {
      "epoch": 1.5122873345935728,
      "grad_norm": 0.554049330965348,
      "learning_rate": 5e-06,
      "loss": 0.567,
      "step": 600
    },
    {
      "epoch": 1.5374921235034655,
      "grad_norm": 0.5960178872278222,
      "learning_rate": 5e-06,
      "loss": 0.5667,
      "step": 610
    },
    {
      "epoch": 1.5626969124133585,
      "grad_norm": 0.5085168346574576,
      "learning_rate": 5e-06,
      "loss": 0.5682,
      "step": 620
    },
    {
      "epoch": 1.5879017013232515,
      "grad_norm": 0.6537267193437978,
      "learning_rate": 5e-06,
      "loss": 0.5629,
      "step": 630
    },
    {
      "epoch": 1.6131064902331445,
      "grad_norm": 0.5874046443880916,
      "learning_rate": 5e-06,
      "loss": 0.5686,
      "step": 640
    },
    {
      "epoch": 1.6383112791430372,
      "grad_norm": 0.5727374180932888,
      "learning_rate": 5e-06,
      "loss": 0.5634,
      "step": 650
    },
    {
      "epoch": 1.66351606805293,
      "grad_norm": 0.4739882267214101,
      "learning_rate": 5e-06,
      "loss": 0.5643,
      "step": 660
    },
    {
      "epoch": 1.688720856962823,
      "grad_norm": 0.5225576157310349,
      "learning_rate": 5e-06,
      "loss": 0.5585,
      "step": 670
    },
    {
      "epoch": 1.713925645872716,
      "grad_norm": 0.5180601277471911,
      "learning_rate": 5e-06,
      "loss": 0.5656,
      "step": 680
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 0.4742139859545316,
      "learning_rate": 5e-06,
      "loss": 0.5601,
      "step": 690
    },
    {
      "epoch": 1.7643352236925016,
      "grad_norm": 0.569511350039058,
      "learning_rate": 5e-06,
      "loss": 0.5601,
      "step": 700
    },
    {
      "epoch": 1.7895400126023944,
      "grad_norm": 0.5632608053135445,
      "learning_rate": 5e-06,
      "loss": 0.5622,
      "step": 710
    },
    {
      "epoch": 1.8147448015122873,
      "grad_norm": 0.7901163025671061,
      "learning_rate": 5e-06,
      "loss": 0.5617,
      "step": 720
    },
    {
      "epoch": 1.8399495904221803,
      "grad_norm": 0.7242318592229516,
      "learning_rate": 5e-06,
      "loss": 0.5681,
      "step": 730
    },
    {
      "epoch": 1.865154379332073,
      "grad_norm": 0.5903083920098006,
      "learning_rate": 5e-06,
      "loss": 0.561,
      "step": 740
    },
    {
      "epoch": 1.8903591682419658,
      "grad_norm": 0.7074496398717507,
      "learning_rate": 5e-06,
      "loss": 0.5618,
      "step": 750
    },
    {
      "epoch": 1.9155639571518588,
      "grad_norm": 0.6211817411184037,
      "learning_rate": 5e-06,
      "loss": 0.5602,
      "step": 760
    },
    {
      "epoch": 1.9407687460617518,
      "grad_norm": 0.7491153337871396,
      "learning_rate": 5e-06,
      "loss": 0.5563,
      "step": 770
    },
    {
      "epoch": 1.9659735349716447,
      "grad_norm": 0.4814370775695788,
      "learning_rate": 5e-06,
      "loss": 0.5575,
      "step": 780
    },
    {
      "epoch": 1.9911783238815375,
      "grad_norm": 0.4983004502393923,
      "learning_rate": 5e-06,
      "loss": 0.5614,
      "step": 790
    },
    {
      "epoch": 1.9987397605545052,
      "eval_loss": 0.5889107584953308,
      "eval_runtime": 212.4952,
      "eval_samples_per_second": 50.312,
      "eval_steps_per_second": 0.395,
      "step": 793
    },
    {
      "epoch": 2.0163831127914302,
      "grad_norm": 0.6245989305076182,
      "learning_rate": 5e-06,
      "loss": 0.5329,
      "step": 800
    },
    {
      "epoch": 2.041587901701323,
      "grad_norm": 0.5453952668705114,
      "learning_rate": 5e-06,
      "loss": 0.5187,
      "step": 810
    },
    {
      "epoch": 2.066792690611216,
      "grad_norm": 0.4731173438501679,
      "learning_rate": 5e-06,
      "loss": 0.5157,
      "step": 820
    },
    {
      "epoch": 2.091997479521109,
      "grad_norm": 0.5441667804629673,
      "learning_rate": 5e-06,
      "loss": 0.5227,
      "step": 830
    },
    {
      "epoch": 2.1172022684310017,
      "grad_norm": 0.5708819169258152,
      "learning_rate": 5e-06,
      "loss": 0.5229,
      "step": 840
    },
    {
      "epoch": 2.1424070573408946,
      "grad_norm": 0.523183963336559,
      "learning_rate": 5e-06,
      "loss": 0.5262,
      "step": 850
    },
    {
      "epoch": 2.1676118462507876,
      "grad_norm": 0.5229800543372238,
      "learning_rate": 5e-06,
      "loss": 0.5235,
      "step": 860
    },
    {
      "epoch": 2.1928166351606806,
      "grad_norm": 0.5691473122380714,
      "learning_rate": 5e-06,
      "loss": 0.5177,
      "step": 870
    },
    {
      "epoch": 2.2180214240705736,
      "grad_norm": 0.5400039287033931,
      "learning_rate": 5e-06,
      "loss": 0.5273,
      "step": 880
    },
    {
      "epoch": 2.243226212980466,
      "grad_norm": 0.5107824302626609,
      "learning_rate": 5e-06,
      "loss": 0.5323,
      "step": 890
    },
    {
      "epoch": 2.268431001890359,
      "grad_norm": 0.5059906821559053,
      "learning_rate": 5e-06,
      "loss": 0.5202,
      "step": 900
    },
    {
      "epoch": 2.293635790800252,
      "grad_norm": 0.5379755140149425,
      "learning_rate": 5e-06,
      "loss": 0.5245,
      "step": 910
    },
    {
      "epoch": 2.318840579710145,
      "grad_norm": 0.5628132546435494,
      "learning_rate": 5e-06,
      "loss": 0.5227,
      "step": 920
    },
    {
      "epoch": 2.344045368620038,
      "grad_norm": 0.5940730599429787,
      "learning_rate": 5e-06,
      "loss": 0.5244,
      "step": 930
    },
    {
      "epoch": 2.3692501575299305,
      "grad_norm": 0.4876405401032709,
      "learning_rate": 5e-06,
      "loss": 0.5231,
      "step": 940
    },
    {
      "epoch": 2.3944549464398235,
      "grad_norm": 0.5287351322876084,
      "learning_rate": 5e-06,
      "loss": 0.5282,
      "step": 950
    },
    {
      "epoch": 2.4196597353497165,
      "grad_norm": 0.5497856784965347,
      "learning_rate": 5e-06,
      "loss": 0.5224,
      "step": 960
    },
    {
      "epoch": 2.4448645242596094,
      "grad_norm": 0.5169812352131126,
      "learning_rate": 5e-06,
      "loss": 0.5186,
      "step": 970
    },
    {
      "epoch": 2.4700693131695024,
      "grad_norm": 0.5065988236822105,
      "learning_rate": 5e-06,
      "loss": 0.5175,
      "step": 980
    },
    {
      "epoch": 2.495274102079395,
      "grad_norm": 0.5210233733825254,
      "learning_rate": 5e-06,
      "loss": 0.5167,
      "step": 990
    },
    {
      "epoch": 2.520478890989288,
      "grad_norm": 0.5188140313597245,
      "learning_rate": 5e-06,
      "loss": 0.518,
      "step": 1000
    },
    {
      "epoch": 2.545683679899181,
      "grad_norm": 0.5405876217592858,
      "learning_rate": 5e-06,
      "loss": 0.5193,
      "step": 1010
    },
    {
      "epoch": 2.570888468809074,
      "grad_norm": 0.46633858042210613,
      "learning_rate": 5e-06,
      "loss": 0.5248,
      "step": 1020
    },
    {
      "epoch": 2.596093257718967,
      "grad_norm": 0.5030938635404251,
      "learning_rate": 5e-06,
      "loss": 0.5171,
      "step": 1030
    },
    {
      "epoch": 2.6212980466288593,
      "grad_norm": 0.7552264831047579,
      "learning_rate": 5e-06,
      "loss": 0.5208,
      "step": 1040
    },
    {
      "epoch": 2.6465028355387523,
      "grad_norm": 0.6446011609995526,
      "learning_rate": 5e-06,
      "loss": 0.5226,
      "step": 1050
    },
    {
      "epoch": 2.6717076244486453,
      "grad_norm": 0.598720313170294,
      "learning_rate": 5e-06,
      "loss": 0.5201,
      "step": 1060
    },
    {
      "epoch": 2.6969124133585383,
      "grad_norm": 0.5646013331239497,
      "learning_rate": 5e-06,
      "loss": 0.5247,
      "step": 1070
    },
    {
      "epoch": 2.7221172022684312,
      "grad_norm": 0.5205190466062173,
      "learning_rate": 5e-06,
      "loss": 0.5228,
      "step": 1080
    },
    {
      "epoch": 2.7473219911783238,
      "grad_norm": 0.6675587237327031,
      "learning_rate": 5e-06,
      "loss": 0.5238,
      "step": 1090
    },
    {
      "epoch": 2.7725267800882167,
      "grad_norm": 0.5888446017638219,
      "learning_rate": 5e-06,
      "loss": 0.5246,
      "step": 1100
    },
    {
      "epoch": 2.7977315689981097,
      "grad_norm": 0.5291240035154432,
      "learning_rate": 5e-06,
      "loss": 0.5207,
      "step": 1110
    },
    {
      "epoch": 2.8229363579080027,
      "grad_norm": 0.5322435909276529,
      "learning_rate": 5e-06,
      "loss": 0.5167,
      "step": 1120
    },
    {
      "epoch": 2.8481411468178957,
      "grad_norm": 0.4603004988767882,
      "learning_rate": 5e-06,
      "loss": 0.5236,
      "step": 1130
    },
    {
      "epoch": 2.873345935727788,
      "grad_norm": 0.48682290640941545,
      "learning_rate": 5e-06,
      "loss": 0.5252,
      "step": 1140
    },
    {
      "epoch": 2.898550724637681,
      "grad_norm": 0.5361316970255996,
      "learning_rate": 5e-06,
      "loss": 0.5264,
      "step": 1150
    },
    {
      "epoch": 2.923755513547574,
      "grad_norm": 0.6157284870441493,
      "learning_rate": 5e-06,
      "loss": 0.5188,
      "step": 1160
    },
    {
      "epoch": 2.9489603024574667,
      "grad_norm": 0.5584802223169939,
      "learning_rate": 5e-06,
      "loss": 0.5189,
      "step": 1170
    },
    {
      "epoch": 2.97416509136736,
      "grad_norm": 0.5261737585816265,
      "learning_rate": 5e-06,
      "loss": 0.5205,
      "step": 1180
    },
    {
      "epoch": 2.9943289224952743,
      "eval_loss": 0.58283931016922,
      "eval_runtime": 213.9304,
      "eval_samples_per_second": 49.974,
      "eval_steps_per_second": 0.393,
      "step": 1188
    },
    {
      "epoch": 2.9943289224952743,
      "step": 1188,
      "total_flos": 1989525488271360.0,
      "train_loss": 0.5829599999418162,
      "train_runtime": 35401.3525,
      "train_samples_per_second": 17.213,
      "train_steps_per_second": 0.034
    }
  ],
  "logging_steps": 10,
  "max_steps": 1188,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1989525488271360.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}