{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9956108266276518,
  "eval_steps": 500,
  "global_step": 1023,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029261155815654718,
      "grad_norm": 1.4015444467822036,
      "learning_rate": 5e-06,
      "loss": 0.7996,
      "step": 10
    },
    {
      "epoch": 0.058522311631309436,
      "grad_norm": 1.2657884873720076,
      "learning_rate": 5e-06,
      "loss": 0.7383,
      "step": 20
    },
    {
      "epoch": 0.08778346744696415,
      "grad_norm": 1.2853443307857617,
      "learning_rate": 5e-06,
      "loss": 0.7065,
      "step": 30
    },
    {
      "epoch": 0.11704462326261887,
      "grad_norm": 1.092609029300215,
      "learning_rate": 5e-06,
      "loss": 0.6961,
      "step": 40
    },
    {
      "epoch": 0.14630577907827358,
      "grad_norm": 1.1461752520371735,
      "learning_rate": 5e-06,
      "loss": 0.6866,
      "step": 50
    },
    {
      "epoch": 0.1755669348939283,
      "grad_norm": 0.9006655574575179,
      "learning_rate": 5e-06,
      "loss": 0.6763,
      "step": 60
    },
    {
      "epoch": 0.20482809070958302,
      "grad_norm": 0.5991449701861865,
      "learning_rate": 5e-06,
      "loss": 0.6697,
      "step": 70
    },
    {
      "epoch": 0.23408924652523774,
      "grad_norm": 0.42048613921733907,
      "learning_rate": 5e-06,
      "loss": 0.6646,
      "step": 80
    },
    {
      "epoch": 0.26335040234089246,
      "grad_norm": 0.430405040916768,
      "learning_rate": 5e-06,
      "loss": 0.6618,
      "step": 90
    },
    {
      "epoch": 0.29261155815654716,
      "grad_norm": 0.4594025425656112,
      "learning_rate": 5e-06,
      "loss": 0.6542,
      "step": 100
    },
    {
      "epoch": 0.3218727139722019,
      "grad_norm": 0.3994331184639397,
      "learning_rate": 5e-06,
      "loss": 0.6631,
      "step": 110
    },
    {
      "epoch": 0.3511338697878566,
      "grad_norm": 0.37951451802607,
      "learning_rate": 5e-06,
      "loss": 0.668,
      "step": 120
    },
    {
      "epoch": 0.38039502560351135,
      "grad_norm": 0.37938408152223546,
      "learning_rate": 5e-06,
      "loss": 0.6518,
      "step": 130
    },
    {
      "epoch": 0.40965618141916604,
      "grad_norm": 0.3682764375063777,
      "learning_rate": 5e-06,
      "loss": 0.6525,
      "step": 140
    },
    {
      "epoch": 0.4389173372348208,
      "grad_norm": 0.3506753294754763,
      "learning_rate": 5e-06,
      "loss": 0.6479,
      "step": 150
    },
    {
      "epoch": 0.4681784930504755,
      "grad_norm": 0.38739237025714635,
      "learning_rate": 5e-06,
      "loss": 0.6498,
      "step": 160
    },
    {
      "epoch": 0.49743964886613024,
      "grad_norm": 0.3641990199038121,
      "learning_rate": 5e-06,
      "loss": 0.6549,
      "step": 170
    },
    {
      "epoch": 0.5267008046817849,
      "grad_norm": 0.3387262148596558,
      "learning_rate": 5e-06,
      "loss": 0.6545,
      "step": 180
    },
    {
      "epoch": 0.5559619604974396,
      "grad_norm": 0.35583454417742927,
      "learning_rate": 5e-06,
      "loss": 0.643,
      "step": 190
    },
    {
      "epoch": 0.5852231163130943,
      "grad_norm": 0.3439858964156482,
      "learning_rate": 5e-06,
      "loss": 0.6443,
      "step": 200
    },
    {
      "epoch": 0.6144842721287491,
      "grad_norm": 0.339501405550569,
      "learning_rate": 5e-06,
      "loss": 0.6508,
      "step": 210
    },
    {
      "epoch": 0.6437454279444038,
      "grad_norm": 0.354200530410764,
      "learning_rate": 5e-06,
      "loss": 0.6388,
      "step": 220
    },
    {
      "epoch": 0.6730065837600585,
      "grad_norm": 0.36478465091491635,
      "learning_rate": 5e-06,
      "loss": 0.6387,
      "step": 230
    },
    {
      "epoch": 0.7022677395757132,
      "grad_norm": 0.3350250502378,
      "learning_rate": 5e-06,
      "loss": 0.6456,
      "step": 240
    },
    {
      "epoch": 0.731528895391368,
      "grad_norm": 0.3434477503899696,
      "learning_rate": 5e-06,
      "loss": 0.644,
      "step": 250
    },
    {
      "epoch": 0.7607900512070227,
      "grad_norm": 0.341252472448644,
      "learning_rate": 5e-06,
      "loss": 0.6466,
      "step": 260
    },
    {
      "epoch": 0.7900512070226774,
      "grad_norm": 0.37592505438246726,
      "learning_rate": 5e-06,
      "loss": 0.6489,
      "step": 270
    },
    {
      "epoch": 0.8193123628383321,
      "grad_norm": 0.3419586714412142,
      "learning_rate": 5e-06,
      "loss": 0.6476,
      "step": 280
    },
    {
      "epoch": 0.8485735186539868,
      "grad_norm": 0.33854473212092273,
      "learning_rate": 5e-06,
      "loss": 0.6399,
      "step": 290
    },
    {
      "epoch": 0.8778346744696416,
      "grad_norm": 0.3551824692503222,
      "learning_rate": 5e-06,
      "loss": 0.6318,
      "step": 300
    },
    {
      "epoch": 0.9070958302852963,
      "grad_norm": 0.35666494542849303,
      "learning_rate": 5e-06,
      "loss": 0.6449,
      "step": 310
    },
    {
      "epoch": 0.936356986100951,
      "grad_norm": 0.33636053152251066,
      "learning_rate": 5e-06,
      "loss": 0.6369,
      "step": 320
    },
    {
      "epoch": 0.9656181419166057,
      "grad_norm": 0.3803771266748499,
      "learning_rate": 5e-06,
      "loss": 0.6401,
      "step": 330
    },
    {
      "epoch": 0.9948792977322605,
      "grad_norm": 0.35250821963156515,
      "learning_rate": 5e-06,
      "loss": 0.6361,
      "step": 340
    },
    {
      "epoch": 0.9978054133138259,
      "eval_loss": 0.640618622303009,
      "eval_runtime": 345.7926,
      "eval_samples_per_second": 26.632,
      "eval_steps_per_second": 0.416,
      "step": 341
    },
    {
      "epoch": 1.025237746891002,
      "grad_norm": 0.3721731893063918,
      "learning_rate": 5e-06,
      "loss": 0.6512,
      "step": 350
    },
    {
      "epoch": 1.054498902706657,
      "grad_norm": 0.3492849036972559,
      "learning_rate": 5e-06,
      "loss": 0.6055,
      "step": 360
    },
    {
      "epoch": 1.0837600585223117,
      "grad_norm": 0.4115188835261346,
      "learning_rate": 5e-06,
      "loss": 0.6088,
      "step": 370
    },
    {
      "epoch": 1.1130212143379663,
      "grad_norm": 0.3443680714255078,
      "learning_rate": 5e-06,
      "loss": 0.6062,
      "step": 380
    },
    {
      "epoch": 1.142282370153621,
      "grad_norm": 0.39688431726948026,
      "learning_rate": 5e-06,
      "loss": 0.6115,
      "step": 390
    },
    {
      "epoch": 1.1715435259692757,
      "grad_norm": 0.35729977553611475,
      "learning_rate": 5e-06,
      "loss": 0.6129,
      "step": 400
    },
    {
      "epoch": 1.2008046817849305,
      "grad_norm": 0.3587917316338556,
      "learning_rate": 5e-06,
      "loss": 0.6127,
      "step": 410
    },
    {
      "epoch": 1.2300658376005853,
      "grad_norm": 0.3978792090841637,
      "learning_rate": 5e-06,
      "loss": 0.6008,
      "step": 420
    },
    {
      "epoch": 1.2593269934162399,
      "grad_norm": 0.36180899559468804,
      "learning_rate": 5e-06,
      "loss": 0.611,
      "step": 430
    },
    {
      "epoch": 1.2885881492318947,
      "grad_norm": 0.3442675552815694,
      "learning_rate": 5e-06,
      "loss": 0.6036,
      "step": 440
    },
    {
      "epoch": 1.3178493050475493,
      "grad_norm": 0.3717062017395999,
      "learning_rate": 5e-06,
      "loss": 0.6074,
      "step": 450
    },
    {
      "epoch": 1.347110460863204,
      "grad_norm": 0.3796535325867537,
      "learning_rate": 5e-06,
      "loss": 0.605,
      "step": 460
    },
    {
      "epoch": 1.3763716166788589,
      "grad_norm": 0.3273244882099893,
      "learning_rate": 5e-06,
      "loss": 0.6024,
      "step": 470
    },
    {
      "epoch": 1.4056327724945135,
      "grad_norm": 0.3727174937863657,
      "learning_rate": 5e-06,
      "loss": 0.6033,
      "step": 480
    },
    {
      "epoch": 1.4348939283101683,
      "grad_norm": 0.34694786322227344,
      "learning_rate": 5e-06,
      "loss": 0.6096,
      "step": 490
    },
    {
      "epoch": 1.464155084125823,
      "grad_norm": 0.33919862390827415,
      "learning_rate": 5e-06,
      "loss": 0.5979,
      "step": 500
    },
    {
      "epoch": 1.4934162399414777,
      "grad_norm": 0.34508821585413224,
      "learning_rate": 5e-06,
      "loss": 0.6059,
      "step": 510
    },
    {
      "epoch": 1.5226773957571325,
      "grad_norm": 0.38883434839268116,
      "learning_rate": 5e-06,
      "loss": 0.6083,
      "step": 520
    },
    {
      "epoch": 1.5519385515727873,
      "grad_norm": 0.35107933222108867,
      "learning_rate": 5e-06,
      "loss": 0.6069,
      "step": 530
    },
    {
      "epoch": 1.5811997073884418,
      "grad_norm": 0.3691057135251824,
      "learning_rate": 5e-06,
      "loss": 0.6135,
      "step": 540
    },
    {
      "epoch": 1.6104608632040964,
      "grad_norm": 0.35119977655218887,
      "learning_rate": 5e-06,
      "loss": 0.6045,
      "step": 550
    },
    {
      "epoch": 1.6397220190197512,
      "grad_norm": 0.3513289449211162,
      "learning_rate": 5e-06,
      "loss": 0.6062,
      "step": 560
    },
    {
      "epoch": 1.668983174835406,
      "grad_norm": 0.3249818476095366,
      "learning_rate": 5e-06,
      "loss": 0.5968,
      "step": 570
    },
    {
      "epoch": 1.6982443306510606,
      "grad_norm": 0.3517967607582011,
      "learning_rate": 5e-06,
      "loss": 0.6062,
      "step": 580
    },
    {
      "epoch": 1.7275054864667154,
      "grad_norm": 0.4030178347069804,
      "learning_rate": 5e-06,
      "loss": 0.6064,
      "step": 590
    },
    {
      "epoch": 1.7567666422823702,
      "grad_norm": 0.34207358553045886,
      "learning_rate": 5e-06,
      "loss": 0.6033,
      "step": 600
    },
    {
      "epoch": 1.7860277980980248,
      "grad_norm": 0.3457052497930087,
      "learning_rate": 5e-06,
      "loss": 0.6058,
      "step": 610
    },
    {
      "epoch": 1.8152889539136796,
      "grad_norm": 0.32108048224719427,
      "learning_rate": 5e-06,
      "loss": 0.6061,
      "step": 620
    },
    {
      "epoch": 1.8445501097293344,
      "grad_norm": 0.3567570067525494,
      "learning_rate": 5e-06,
      "loss": 0.6052,
      "step": 630
    },
    {
      "epoch": 1.873811265544989,
      "grad_norm": 0.3281186537149481,
      "learning_rate": 5e-06,
      "loss": 0.6001,
      "step": 640
    },
    {
      "epoch": 1.9030724213606436,
      "grad_norm": 0.36018189397498207,
      "learning_rate": 5e-06,
      "loss": 0.6058,
      "step": 650
    },
    {
      "epoch": 1.9323335771762986,
      "grad_norm": 0.3502425747015856,
      "learning_rate": 5e-06,
      "loss": 0.6063,
      "step": 660
    },
    {
      "epoch": 1.9615947329919532,
      "grad_norm": 0.33148897222711265,
      "learning_rate": 5e-06,
      "loss": 0.5952,
      "step": 670
    },
    {
      "epoch": 1.9908558888076078,
      "grad_norm": 0.3580118082608882,
      "learning_rate": 5e-06,
      "loss": 0.6096,
      "step": 680
    },
    {
      "epoch": 1.9967081199707388,
      "eval_loss": 0.6332002878189087,
      "eval_runtime": 346.5687,
      "eval_samples_per_second": 26.572,
      "eval_steps_per_second": 0.416,
      "step": 682
    },
    {
      "epoch": 2.0212143379663496,
      "grad_norm": 0.39037400649762577,
      "learning_rate": 5e-06,
      "loss": 0.6196,
      "step": 690
    },
    {
      "epoch": 2.050475493782004,
      "grad_norm": 0.4434429381232548,
      "learning_rate": 5e-06,
      "loss": 0.5673,
      "step": 700
    },
    {
      "epoch": 2.0797366495976592,
      "grad_norm": 0.3497622377865716,
      "learning_rate": 5e-06,
      "loss": 0.5693,
      "step": 710
    },
    {
      "epoch": 2.108997805413314,
      "grad_norm": 0.3773856223516478,
      "learning_rate": 5e-06,
      "loss": 0.5704,
      "step": 720
    },
    {
      "epoch": 2.1382589612289684,
      "grad_norm": 0.3522556629706183,
      "learning_rate": 5e-06,
      "loss": 0.5722,
      "step": 730
    },
    {
      "epoch": 2.1675201170446234,
      "grad_norm": 0.3506219317591605,
      "learning_rate": 5e-06,
      "loss": 0.5775,
      "step": 740
    },
    {
      "epoch": 2.196781272860278,
      "grad_norm": 0.3147645395001558,
      "learning_rate": 5e-06,
      "loss": 0.5761,
      "step": 750
    },
    {
      "epoch": 2.2260424286759326,
      "grad_norm": 0.371033572143663,
      "learning_rate": 5e-06,
      "loss": 0.5736,
      "step": 760
    },
    {
      "epoch": 2.255303584491587,
      "grad_norm": 0.33096335665510035,
      "learning_rate": 5e-06,
      "loss": 0.5724,
      "step": 770
    },
    {
      "epoch": 2.284564740307242,
      "grad_norm": 0.3367058473599436,
      "learning_rate": 5e-06,
      "loss": 0.5715,
      "step": 780
    },
    {
      "epoch": 2.313825896122897,
      "grad_norm": 0.326433950142472,
      "learning_rate": 5e-06,
      "loss": 0.5698,
      "step": 790
    },
    {
      "epoch": 2.3430870519385514,
      "grad_norm": 0.3603804154225191,
      "learning_rate": 5e-06,
      "loss": 0.5776,
      "step": 800
    },
    {
      "epoch": 2.3723482077542064,
      "grad_norm": 0.3388463555889941,
      "learning_rate": 5e-06,
      "loss": 0.5728,
      "step": 810
    },
    {
      "epoch": 2.401609363569861,
      "grad_norm": 0.33023802442966366,
      "learning_rate": 5e-06,
      "loss": 0.5791,
      "step": 820
    },
    {
      "epoch": 2.4308705193855156,
      "grad_norm": 0.31991052482202714,
      "learning_rate": 5e-06,
      "loss": 0.5713,
      "step": 830
    },
    {
      "epoch": 2.4601316752011706,
      "grad_norm": 0.35182055756947245,
      "learning_rate": 5e-06,
      "loss": 0.5718,
      "step": 840
    },
    {
      "epoch": 2.489392831016825,
      "grad_norm": 0.3436348657090354,
      "learning_rate": 5e-06,
      "loss": 0.574,
      "step": 850
    },
    {
      "epoch": 2.5186539868324798,
      "grad_norm": 0.3558300443060959,
      "learning_rate": 5e-06,
      "loss": 0.5671,
      "step": 860
    },
    {
      "epoch": 2.547915142648135,
      "grad_norm": 0.39457846380123907,
      "learning_rate": 5e-06,
      "loss": 0.5695,
      "step": 870
    },
    {
      "epoch": 2.5771762984637894,
      "grad_norm": 0.3540156892398613,
      "learning_rate": 5e-06,
      "loss": 0.5737,
      "step": 880
    },
    {
      "epoch": 2.606437454279444,
      "grad_norm": 0.3611060327105372,
      "learning_rate": 5e-06,
      "loss": 0.573,
      "step": 890
    },
    {
      "epoch": 2.6356986100950985,
      "grad_norm": 0.33749542282346184,
      "learning_rate": 5e-06,
      "loss": 0.5776,
      "step": 900
    },
    {
      "epoch": 2.6649597659107536,
      "grad_norm": 0.36124194708101637,
      "learning_rate": 5e-06,
      "loss": 0.5778,
      "step": 910
    },
    {
      "epoch": 2.694220921726408,
      "grad_norm": 0.35710662173949104,
      "learning_rate": 5e-06,
      "loss": 0.5721,
      "step": 920
    },
    {
      "epoch": 2.723482077542063,
      "grad_norm": 0.3566062701794353,
      "learning_rate": 5e-06,
      "loss": 0.5758,
      "step": 930
    },
    {
      "epoch": 2.7527432333577178,
      "grad_norm": 0.34964975557486105,
      "learning_rate": 5e-06,
      "loss": 0.5747,
      "step": 940
    },
    {
      "epoch": 2.7820043891733723,
      "grad_norm": 0.34002257310230194,
      "learning_rate": 5e-06,
      "loss": 0.5735,
      "step": 950
    },
    {
      "epoch": 2.811265544989027,
      "grad_norm": 0.37468803583644683,
      "learning_rate": 5e-06,
      "loss": 0.5773,
      "step": 960
    },
    {
      "epoch": 2.840526700804682,
      "grad_norm": 0.34310179408919084,
      "learning_rate": 5e-06,
      "loss": 0.573,
      "step": 970
    },
    {
      "epoch": 2.8697878566203365,
      "grad_norm": 0.38021125890295365,
      "learning_rate": 5e-06,
      "loss": 0.5729,
      "step": 980
    },
    {
      "epoch": 2.899049012435991,
      "grad_norm": 0.3239775742376659,
      "learning_rate": 5e-06,
      "loss": 0.5658,
      "step": 990
    },
    {
      "epoch": 2.928310168251646,
      "grad_norm": 0.3262461836425964,
      "learning_rate": 5e-06,
      "loss": 0.5736,
      "step": 1000
    },
    {
      "epoch": 2.9575713240673007,
      "grad_norm": 0.34333695957920457,
      "learning_rate": 5e-06,
      "loss": 0.5654,
      "step": 1010
    },
    {
      "epoch": 2.9868324798829553,
      "grad_norm": 0.3358081690176178,
      "learning_rate": 5e-06,
      "loss": 0.5771,
      "step": 1020
    },
    {
      "epoch": 2.9956108266276518,
      "eval_loss": 0.6331179141998291,
      "eval_runtime": 344.5727,
      "eval_samples_per_second": 26.726,
      "eval_steps_per_second": 0.418,
      "step": 1023
    },
    {
      "epoch": 2.9956108266276518,
      "step": 1023,
      "total_flos": 2144987064041472.0,
      "train_loss": 0.6140813032786051,
      "train_runtime": 55371.2357,
      "train_samples_per_second": 9.479,
      "train_steps_per_second": 0.018
    }
  ],
  "logging_steps": 10,
  "max_steps": 1023,
  "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": 2144987064041472.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}