{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13461214874642435,
  "eval_steps": 500,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016826518593303045,
      "grad_norm": 5.367858933563703,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 0.9537,
      "step": 10
    },
    {
      "epoch": 0.003365303718660609,
      "grad_norm": 9.386746384686745,
      "learning_rate": 9.999999999999999e-06,
      "loss": 0.943,
      "step": 20
    },
    {
      "epoch": 0.005047955577990914,
      "grad_norm": 7.387362447577942,
      "learning_rate": 1.5e-05,
      "loss": 0.934,
      "step": 30
    },
    {
      "epoch": 0.006730607437321218,
      "grad_norm": 6.9256319824932655,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 0.8376,
      "step": 40
    },
    {
      "epoch": 0.008413259296651522,
      "grad_norm": 9.1148382590838,
      "learning_rate": 2.5e-05,
      "loss": 0.8484,
      "step": 50
    },
    {
      "epoch": 0.010095911155981827,
      "grad_norm": 3.9989232759892426,
      "learning_rate": 3e-05,
      "loss": 0.8097,
      "step": 60
    },
    {
      "epoch": 0.011778563015312132,
      "grad_norm": 3.892371218590039,
      "learning_rate": 2.9999786123888308e-05,
      "loss": 0.7811,
      "step": 70
    },
    {
      "epoch": 0.013461214874642436,
      "grad_norm": 8.096662196282066,
      "learning_rate": 2.9999144501652298e-05,
      "loss": 0.7446,
      "step": 80
    },
    {
      "epoch": 0.01514386673397274,
      "grad_norm": 1.5769306611206149,
      "learning_rate": 2.9998075151588992e-05,
      "loss": 0.7258,
      "step": 90
    },
    {
      "epoch": 0.016826518593303044,
      "grad_norm": 8.47430485487969,
      "learning_rate": 2.999657810419285e-05,
      "loss": 0.7052,
      "step": 100
    },
    {
      "epoch": 0.01850917045263335,
      "grad_norm": 2.363071299913598,
      "learning_rate": 2.999465340215489e-05,
      "loss": 0.7657,
      "step": 110
    },
    {
      "epoch": 0.020191822311963654,
      "grad_norm": 1.9252385425154874,
      "learning_rate": 2.999230110036149e-05,
      "loss": 0.7329,
      "step": 120
    },
    {
      "epoch": 0.02187447417129396,
      "grad_norm": 8.946028475031488,
      "learning_rate": 2.99895212658928e-05,
      "loss": 0.7304,
      "step": 130
    },
    {
      "epoch": 0.023557126030624265,
      "grad_norm": 6.877609312630206,
      "learning_rate": 2.9986313978020846e-05,
      "loss": 0.7453,
      "step": 140
    },
    {
      "epoch": 0.02523977788995457,
      "grad_norm": 2.5256324882367993,
      "learning_rate": 2.9982679328207262e-05,
      "loss": 0.7366,
      "step": 150
    },
    {
      "epoch": 0.02692242974928487,
      "grad_norm": 2.709550398238738,
      "learning_rate": 2.9978617420100692e-05,
      "loss": 0.7258,
      "step": 160
    },
    {
      "epoch": 0.028605081608615177,
      "grad_norm": 1.543550019689774,
      "learning_rate": 2.9974128369533805e-05,
      "loss": 0.7372,
      "step": 170
    },
    {
      "epoch": 0.03028773346794548,
      "grad_norm": 3.3453966881155504,
      "learning_rate": 2.9969212304520034e-05,
      "loss": 0.743,
      "step": 180
    },
    {
      "epoch": 0.03197038532727579,
      "grad_norm": 1.922001656181265,
      "learning_rate": 2.9963869365249895e-05,
      "loss": 0.7819,
      "step": 190
    },
    {
      "epoch": 0.03365303718660609,
      "grad_norm": 2.0611188483400036,
      "learning_rate": 2.995809970408699e-05,
      "loss": 0.7155,
      "step": 200
    },
    {
      "epoch": 0.0353356890459364,
      "grad_norm": 1.5313041833127259,
      "learning_rate": 2.9951903485563685e-05,
      "loss": 0.7322,
      "step": 210
    },
    {
      "epoch": 0.0370183409052667,
      "grad_norm": 2.0124191694435085,
      "learning_rate": 2.99452808863764e-05,
      "loss": 0.6759,
      "step": 220
    },
    {
      "epoch": 0.03870099276459701,
      "grad_norm": 3.182123324389477,
      "learning_rate": 2.993823209538056e-05,
      "loss": 0.6953,
      "step": 230
    },
    {
      "epoch": 0.04038364462392731,
      "grad_norm": 1.6122782177661379,
      "learning_rate": 2.9930757313585238e-05,
      "loss": 0.6953,
      "step": 240
    },
    {
      "epoch": 0.04206629648325761,
      "grad_norm": 2.2027482596695647,
      "learning_rate": 2.9922856754147406e-05,
      "loss": 0.7301,
      "step": 250
    },
    {
      "epoch": 0.04374894834258792,
      "grad_norm": 2.6782477155989213,
      "learning_rate": 2.9914530642365852e-05,
      "loss": 0.6891,
      "step": 260
    },
    {
      "epoch": 0.04543160020191822,
      "grad_norm": 1.9740401144541417,
      "learning_rate": 2.990577921567476e-05,
      "loss": 0.7231,
      "step": 270
    },
    {
      "epoch": 0.04711425206124853,
      "grad_norm": 1.719874620968932,
      "learning_rate": 2.989660272363696e-05,
      "loss": 0.7505,
      "step": 280
    },
    {
      "epoch": 0.04879690392057883,
      "grad_norm": 1.3138364164203409,
      "learning_rate": 2.988700142793676e-05,
      "loss": 0.7116,
      "step": 290
    },
    {
      "epoch": 0.05047955577990914,
      "grad_norm": 5.853627389344256,
      "learning_rate": 2.9876975602372536e-05,
      "loss": 0.719,
      "step": 300
    },
    {
      "epoch": 0.05216220763923944,
      "grad_norm": 2.347259437170711,
      "learning_rate": 2.9866525532848906e-05,
      "loss": 0.6803,
      "step": 310
    },
    {
      "epoch": 0.05384485949856974,
      "grad_norm": 1.937679220955038,
      "learning_rate": 2.9855651517368567e-05,
      "loss": 0.7461,
      "step": 320
    },
    {
      "epoch": 0.05552751135790005,
      "grad_norm": 1.6661300351569575,
      "learning_rate": 2.9844353866023802e-05,
      "loss": 0.7472,
      "step": 330
    },
    {
      "epoch": 0.05721016321723035,
      "grad_norm": 2.357915869204484,
      "learning_rate": 2.9832632900987642e-05,
      "loss": 0.7148,
      "step": 340
    },
    {
      "epoch": 0.05889281507656066,
      "grad_norm": 4.398815186243292,
      "learning_rate": 2.982048895650468e-05,
      "loss": 0.6992,
      "step": 350
    },
    {
      "epoch": 0.06057546693589096,
      "grad_norm": 12.662682224480092,
      "learning_rate": 2.9807922378881537e-05,
      "loss": 0.7539,
      "step": 360
    },
    {
      "epoch": 0.06225811879522127,
      "grad_norm": 0.8642696401357872,
      "learning_rate": 2.979493352647697e-05,
      "loss": 0.7212,
      "step": 370
    },
    {
      "epoch": 0.06394077065455157,
      "grad_norm": 27.047937858232604,
      "learning_rate": 2.9781522769691686e-05,
      "loss": 0.722,
      "step": 380
    },
    {
      "epoch": 0.06562342251388188,
      "grad_norm": 2.598805292448644,
      "learning_rate": 2.9767690490957758e-05,
      "loss": 0.7065,
      "step": 390
    },
    {
      "epoch": 0.06730607437321218,
      "grad_norm": 1.2314762895092763,
      "learning_rate": 2.9753437084727713e-05,
      "loss": 0.7498,
      "step": 400
    },
    {
      "epoch": 0.06898872623254249,
      "grad_norm": 1.6421909669790502,
      "learning_rate": 2.9738762957463292e-05,
      "loss": 0.6992,
      "step": 410
    },
    {
      "epoch": 0.0706713780918728,
      "grad_norm": 2.023552968622588,
      "learning_rate": 2.9723668527623877e-05,
      "loss": 0.6943,
      "step": 420
    },
    {
      "epoch": 0.0723540299512031,
      "grad_norm": 1.5172337910969138,
      "learning_rate": 2.9708154225654526e-05,
      "loss": 0.6987,
      "step": 430
    },
    {
      "epoch": 0.0740366818105334,
      "grad_norm": 1.197852135730745,
      "learning_rate": 2.9692220493973712e-05,
      "loss": 0.7302,
      "step": 440
    },
    {
      "epoch": 0.0757193336698637,
      "grad_norm": 2.4396443837967183,
      "learning_rate": 2.9675867786960718e-05,
      "loss": 0.7318,
      "step": 450
    },
    {
      "epoch": 0.07740198552919401,
      "grad_norm": 1.4599851880563282,
      "learning_rate": 2.9659096570942654e-05,
      "loss": 0.6941,
      "step": 460
    },
    {
      "epoch": 0.07908463738852431,
      "grad_norm": 1.117755825364562,
      "learning_rate": 2.9641907324181194e-05,
      "loss": 0.7399,
      "step": 470
    },
    {
      "epoch": 0.08076728924785462,
      "grad_norm": 2.9235378164576242,
      "learning_rate": 2.96243005368589e-05,
      "loss": 0.7207,
      "step": 480
    },
    {
      "epoch": 0.08244994110718493,
      "grad_norm": 7.308883163781362,
      "learning_rate": 2.960627671106527e-05,
      "loss": 0.682,
      "step": 490
    },
    {
      "epoch": 0.08413259296651522,
      "grad_norm": 3.4394827932955234,
      "learning_rate": 2.9587836360782405e-05,
      "loss": 0.708,
      "step": 500
    },
    {
      "epoch": 0.08581524482584553,
      "grad_norm": 3.2314529856927634,
      "learning_rate": 2.9568980011870357e-05,
      "loss": 0.7335,
      "step": 510
    },
    {
      "epoch": 0.08749789668517584,
      "grad_norm": 1.825724533695325,
      "learning_rate": 2.954970820205214e-05,
      "loss": 0.6951,
      "step": 520
    },
    {
      "epoch": 0.08918054854450615,
      "grad_norm": 3.3231741746640076,
      "learning_rate": 2.9530021480898393e-05,
      "loss": 0.7793,
      "step": 530
    },
    {
      "epoch": 0.09086320040383644,
      "grad_norm": 1.3097651462571123,
      "learning_rate": 2.9509920409811696e-05,
      "loss": 0.7087,
      "step": 540
    },
    {
      "epoch": 0.09254585226316675,
      "grad_norm": 6.685911471215255,
      "learning_rate": 2.9489405562010565e-05,
      "loss": 0.6906,
      "step": 550
    },
    {
      "epoch": 0.09422850412249706,
      "grad_norm": 2.870746617513948,
      "learning_rate": 2.9468477522513132e-05,
      "loss": 0.7028,
      "step": 560
    },
    {
      "epoch": 0.09591115598182735,
      "grad_norm": 1.782555352805469,
      "learning_rate": 2.9447136888120408e-05,
      "loss": 0.6901,
      "step": 570
    },
    {
      "epoch": 0.09759380784115766,
      "grad_norm": 2.336519711000487,
      "learning_rate": 2.9425384267399327e-05,
      "loss": 0.7779,
      "step": 580
    },
    {
      "epoch": 0.09927645970048797,
      "grad_norm": 8.935574410818228,
      "learning_rate": 2.940322028066534e-05,
      "loss": 0.7503,
      "step": 590
    },
    {
      "epoch": 0.10095911155981828,
      "grad_norm": 2.754713786882031,
      "learning_rate": 2.938064555996476e-05,
      "loss": 0.7208,
      "step": 600
    },
    {
      "epoch": 0.10264176341914857,
      "grad_norm": 1.5082503557652136,
      "learning_rate": 2.9357660749056713e-05,
      "loss": 0.7169,
      "step": 610
    },
    {
      "epoch": 0.10432441527847888,
      "grad_norm": 9.04522194526273,
      "learning_rate": 2.9334266503394803e-05,
      "loss": 0.6927,
      "step": 620
    },
    {
      "epoch": 0.10600706713780919,
      "grad_norm": 55.28278686388287,
      "learning_rate": 2.9310463490108397e-05,
      "loss": 0.7107,
      "step": 630
    },
    {
      "epoch": 0.10768971899713949,
      "grad_norm": 3.721916069105249,
      "learning_rate": 2.928625238798362e-05,
      "loss": 0.6951,
      "step": 640
    },
    {
      "epoch": 0.1093723708564698,
      "grad_norm": 2.5040797323750112,
      "learning_rate": 2.9261633887443993e-05,
      "loss": 0.6916,
      "step": 650
    },
    {
      "epoch": 0.1110550227158001,
      "grad_norm": 3.5468924769840617,
      "learning_rate": 2.9236608690530738e-05,
      "loss": 0.7077,
      "step": 660
    },
    {
      "epoch": 0.11273767457513041,
      "grad_norm": 3.0266819778200746,
      "learning_rate": 2.921117751088276e-05,
      "loss": 0.6952,
      "step": 670
    },
    {
      "epoch": 0.1144203264344607,
      "grad_norm": 1.634743894298146,
      "learning_rate": 2.91853410737163e-05,
      "loss": 0.6936,
      "step": 680
    },
    {
      "epoch": 0.11610297829379101,
      "grad_norm": 1.0925365801520501,
      "learning_rate": 2.915910011580426e-05,
      "loss": 0.7317,
      "step": 690
    },
    {
      "epoch": 0.11778563015312132,
      "grad_norm": 1.6959112138540386,
      "learning_rate": 2.9132455385455176e-05,
      "loss": 0.6917,
      "step": 700
    },
    {
      "epoch": 0.11946828201245162,
      "grad_norm": 1.9723433746891168,
      "learning_rate": 2.9105407642491895e-05,
      "loss": 0.7209,
      "step": 710
    },
    {
      "epoch": 0.12115093387178193,
      "grad_norm": 2.1537215293733833,
      "learning_rate": 2.907795765822989e-05,
      "loss": 0.7488,
      "step": 720
    },
    {
      "epoch": 0.12283358573111224,
      "grad_norm": 3.227101869737169,
      "learning_rate": 2.9050106215455283e-05,
      "loss": 0.7152,
      "step": 730
    },
    {
      "epoch": 0.12451623759044254,
      "grad_norm": 2.7222358893572554,
      "learning_rate": 2.9021854108402516e-05,
      "loss": 0.708,
      "step": 740
    },
    {
      "epoch": 0.12619888944977284,
      "grad_norm": 2.1054843767538136,
      "learning_rate": 2.8993202142731693e-05,
      "loss": 0.7251,
      "step": 750
    },
    {
      "epoch": 0.12788154130910315,
      "grad_norm": 2.11845883419618,
      "learning_rate": 2.8964151135505616e-05,
      "loss": 0.7405,
      "step": 760
    },
    {
      "epoch": 0.12956419316843346,
      "grad_norm": 13.171512404187755,
      "learning_rate": 2.8934701915166477e-05,
      "loss": 0.6844,
      "step": 770
    },
    {
      "epoch": 0.13124684502776376,
      "grad_norm": 2.7633375632879127,
      "learning_rate": 2.890485532151225e-05,
      "loss": 0.6766,
      "step": 780
    },
    {
      "epoch": 0.13292949688709407,
      "grad_norm": 1.8420785342693768,
      "learning_rate": 2.887461220567271e-05,
      "loss": 0.7037,
      "step": 790
    },
    {
      "epoch": 0.13461214874642435,
      "grad_norm": 1.5557447509529954,
      "learning_rate": 2.8843973430085204e-05,
      "loss": 0.6991,
      "step": 800
    }
  ],
  "logging_steps": 10,
  "max_steps": 5943,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 400,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.644760786993152e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}