{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.33288948069241014,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003328894806924101,
      "grad_norm": 37.75,
      "learning_rate": 1.9933422103861518e-05,
      "loss": 1.4084,
      "step": 10
    },
    {
      "epoch": 0.006657789613848202,
      "grad_norm": 12.125,
      "learning_rate": 1.9866844207723038e-05,
      "loss": 1.0474,
      "step": 20
    },
    {
      "epoch": 0.009986684420772303,
      "grad_norm": 45.25,
      "learning_rate": 1.9800266311584554e-05,
      "loss": 1.2455,
      "step": 30
    },
    {
      "epoch": 0.013315579227696404,
      "grad_norm": 13.9375,
      "learning_rate": 1.9733688415446073e-05,
      "loss": 1.1969,
      "step": 40
    },
    {
      "epoch": 0.016644474034620507,
      "grad_norm": 32.0,
      "learning_rate": 1.966711051930759e-05,
      "loss": 1.1659,
      "step": 50
    },
    {
      "epoch": 0.019973368841544607,
      "grad_norm": 19.0,
      "learning_rate": 1.960053262316911e-05,
      "loss": 1.1159,
      "step": 60
    },
    {
      "epoch": 0.02330226364846871,
      "grad_norm": 27.5,
      "learning_rate": 1.953395472703063e-05,
      "loss": 1.1861,
      "step": 70
    },
    {
      "epoch": 0.02663115845539281,
      "grad_norm": 17.5,
      "learning_rate": 1.9467376830892145e-05,
      "loss": 1.1073,
      "step": 80
    },
    {
      "epoch": 0.02996005326231691,
      "grad_norm": 33.75,
      "learning_rate": 1.9400798934753665e-05,
      "loss": 1.1506,
      "step": 90
    },
    {
      "epoch": 0.033288948069241014,
      "grad_norm": 9.5,
      "learning_rate": 1.933422103861518e-05,
      "loss": 1.246,
      "step": 100
    },
    {
      "epoch": 0.03661784287616511,
      "grad_norm": 11.3125,
      "learning_rate": 1.92676431424767e-05,
      "loss": 1.1708,
      "step": 110
    },
    {
      "epoch": 0.03994673768308921,
      "grad_norm": 14.375,
      "learning_rate": 1.9201065246338217e-05,
      "loss": 1.1302,
      "step": 120
    },
    {
      "epoch": 0.043275632490013316,
      "grad_norm": 20.625,
      "learning_rate": 1.9134487350199737e-05,
      "loss": 1.0537,
      "step": 130
    },
    {
      "epoch": 0.04660452729693742,
      "grad_norm": 21.75,
      "learning_rate": 1.9067909454061253e-05,
      "loss": 1.0669,
      "step": 140
    },
    {
      "epoch": 0.049933422103861515,
      "grad_norm": 14.125,
      "learning_rate": 1.900133155792277e-05,
      "loss": 1.0482,
      "step": 150
    },
    {
      "epoch": 0.05326231691078562,
      "grad_norm": 27.625,
      "learning_rate": 1.893475366178429e-05,
      "loss": 1.1468,
      "step": 160
    },
    {
      "epoch": 0.05659121171770972,
      "grad_norm": 4.53125,
      "learning_rate": 1.8868175765645805e-05,
      "loss": 1.092,
      "step": 170
    },
    {
      "epoch": 0.05992010652463382,
      "grad_norm": 32.5,
      "learning_rate": 1.8801597869507325e-05,
      "loss": 1.2208,
      "step": 180
    },
    {
      "epoch": 0.06324900133155792,
      "grad_norm": 56.0,
      "learning_rate": 1.873501997336884e-05,
      "loss": 1.2359,
      "step": 190
    },
    {
      "epoch": 0.06657789613848203,
      "grad_norm": 8.375,
      "learning_rate": 1.866844207723036e-05,
      "loss": 1.0712,
      "step": 200
    },
    {
      "epoch": 0.06990679094540612,
      "grad_norm": 26.375,
      "learning_rate": 1.860186418109188e-05,
      "loss": 1.0156,
      "step": 210
    },
    {
      "epoch": 0.07323568575233022,
      "grad_norm": 12.0,
      "learning_rate": 1.8535286284953397e-05,
      "loss": 1.0407,
      "step": 220
    },
    {
      "epoch": 0.07656458055925433,
      "grad_norm": 13.75,
      "learning_rate": 1.8468708388814916e-05,
      "loss": 1.0161,
      "step": 230
    },
    {
      "epoch": 0.07989347536617843,
      "grad_norm": 27.125,
      "learning_rate": 1.8402130492676432e-05,
      "loss": 1.1466,
      "step": 240
    },
    {
      "epoch": 0.08322237017310254,
      "grad_norm": 26.125,
      "learning_rate": 1.8335552596537952e-05,
      "loss": 1.3192,
      "step": 250
    },
    {
      "epoch": 0.08655126498002663,
      "grad_norm": 25.75,
      "learning_rate": 1.826897470039947e-05,
      "loss": 1.0628,
      "step": 260
    },
    {
      "epoch": 0.08988015978695073,
      "grad_norm": 29.25,
      "learning_rate": 1.8202396804260988e-05,
      "loss": 0.967,
      "step": 270
    },
    {
      "epoch": 0.09320905459387484,
      "grad_norm": 29.75,
      "learning_rate": 1.8135818908122504e-05,
      "loss": 1.0356,
      "step": 280
    },
    {
      "epoch": 0.09653794940079893,
      "grad_norm": 11.6875,
      "learning_rate": 1.806924101198402e-05,
      "loss": 0.9853,
      "step": 290
    },
    {
      "epoch": 0.09986684420772303,
      "grad_norm": 27.5,
      "learning_rate": 1.800266311584554e-05,
      "loss": 1.0279,
      "step": 300
    },
    {
      "epoch": 0.10319573901464714,
      "grad_norm": 5.65625,
      "learning_rate": 1.7936085219707056e-05,
      "loss": 1.0115,
      "step": 310
    },
    {
      "epoch": 0.10652463382157124,
      "grad_norm": 8.1875,
      "learning_rate": 1.7869507323568576e-05,
      "loss": 0.942,
      "step": 320
    },
    {
      "epoch": 0.10985352862849534,
      "grad_norm": 65.0,
      "learning_rate": 1.7802929427430096e-05,
      "loss": 1.0208,
      "step": 330
    },
    {
      "epoch": 0.11318242343541944,
      "grad_norm": 9.625,
      "learning_rate": 1.7736351531291612e-05,
      "loss": 1.1729,
      "step": 340
    },
    {
      "epoch": 0.11651131824234354,
      "grad_norm": 17.5,
      "learning_rate": 1.766977363515313e-05,
      "loss": 0.9322,
      "step": 350
    },
    {
      "epoch": 0.11984021304926765,
      "grad_norm": 28.125,
      "learning_rate": 1.7603195739014648e-05,
      "loss": 1.0417,
      "step": 360
    },
    {
      "epoch": 0.12316910785619174,
      "grad_norm": 18.25,
      "learning_rate": 1.7536617842876168e-05,
      "loss": 1.2491,
      "step": 370
    },
    {
      "epoch": 0.12649800266311584,
      "grad_norm": 27.375,
      "learning_rate": 1.7470039946737684e-05,
      "loss": 0.9388,
      "step": 380
    },
    {
      "epoch": 0.12982689747003995,
      "grad_norm": 22.125,
      "learning_rate": 1.7403462050599203e-05,
      "loss": 1.0488,
      "step": 390
    },
    {
      "epoch": 0.13315579227696406,
      "grad_norm": 21.25,
      "learning_rate": 1.733688415446072e-05,
      "loss": 0.9951,
      "step": 400
    },
    {
      "epoch": 0.13648468708388814,
      "grad_norm": 11.75,
      "learning_rate": 1.727030625832224e-05,
      "loss": 0.9212,
      "step": 410
    },
    {
      "epoch": 0.13981358189081225,
      "grad_norm": 16.25,
      "learning_rate": 1.7203728362183756e-05,
      "loss": 1.0548,
      "step": 420
    },
    {
      "epoch": 0.14314247669773636,
      "grad_norm": 19.875,
      "learning_rate": 1.7137150466045275e-05,
      "loss": 1.0238,
      "step": 430
    },
    {
      "epoch": 0.14647137150466044,
      "grad_norm": 18.875,
      "learning_rate": 1.707057256990679e-05,
      "loss": 1.0327,
      "step": 440
    },
    {
      "epoch": 0.14980026631158455,
      "grad_norm": 7.84375,
      "learning_rate": 1.7003994673768308e-05,
      "loss": 1.1155,
      "step": 450
    },
    {
      "epoch": 0.15312916111850866,
      "grad_norm": 14.125,
      "learning_rate": 1.693741677762983e-05,
      "loss": 0.9627,
      "step": 460
    },
    {
      "epoch": 0.15645805592543274,
      "grad_norm": 7.4375,
      "learning_rate": 1.6870838881491347e-05,
      "loss": 1.0216,
      "step": 470
    },
    {
      "epoch": 0.15978695073235685,
      "grad_norm": 9.375,
      "learning_rate": 1.6804260985352863e-05,
      "loss": 1.0489,
      "step": 480
    },
    {
      "epoch": 0.16311584553928096,
      "grad_norm": 19.5,
      "learning_rate": 1.6737683089214383e-05,
      "loss": 1.1254,
      "step": 490
    },
    {
      "epoch": 0.16644474034620507,
      "grad_norm": 26.125,
      "learning_rate": 1.66711051930759e-05,
      "loss": 1.0134,
      "step": 500
    },
    {
      "epoch": 0.16644474034620507,
      "eval_accuracy": 0.5015762402521985,
      "eval_loss": 0.9942083358764648,
      "eval_runtime": 211.8123,
      "eval_samples_per_second": 113.818,
      "eval_steps_per_second": 28.454,
      "step": 500
    },
    {
      "epoch": 0.16977363515312915,
      "grad_norm": 12.3125,
      "learning_rate": 1.660452729693742e-05,
      "loss": 1.0164,
      "step": 510
    },
    {
      "epoch": 0.17310252996005326,
      "grad_norm": 38.75,
      "learning_rate": 1.6537949400798935e-05,
      "loss": 1.0042,
      "step": 520
    },
    {
      "epoch": 0.17643142476697737,
      "grad_norm": 20.125,
      "learning_rate": 1.6471371504660455e-05,
      "loss": 0.9786,
      "step": 530
    },
    {
      "epoch": 0.17976031957390146,
      "grad_norm": 11.4375,
      "learning_rate": 1.640479360852197e-05,
      "loss": 0.9678,
      "step": 540
    },
    {
      "epoch": 0.18308921438082557,
      "grad_norm": 19.375,
      "learning_rate": 1.633821571238349e-05,
      "loss": 1.0477,
      "step": 550
    },
    {
      "epoch": 0.18641810918774968,
      "grad_norm": 16.75,
      "learning_rate": 1.6271637816245007e-05,
      "loss": 1.02,
      "step": 560
    },
    {
      "epoch": 0.18974700399467376,
      "grad_norm": 15.5,
      "learning_rate": 1.6205059920106527e-05,
      "loss": 0.9864,
      "step": 570
    },
    {
      "epoch": 0.19307589880159787,
      "grad_norm": 9.75,
      "learning_rate": 1.6138482023968043e-05,
      "loss": 1.0019,
      "step": 580
    },
    {
      "epoch": 0.19640479360852198,
      "grad_norm": 12.125,
      "learning_rate": 1.6071904127829563e-05,
      "loss": 0.9483,
      "step": 590
    },
    {
      "epoch": 0.19973368841544606,
      "grad_norm": 30.875,
      "learning_rate": 1.6005326231691082e-05,
      "loss": 1.0692,
      "step": 600
    },
    {
      "epoch": 0.20306258322237017,
      "grad_norm": 10.125,
      "learning_rate": 1.59387483355526e-05,
      "loss": 0.9279,
      "step": 610
    },
    {
      "epoch": 0.20639147802929428,
      "grad_norm": 11.6875,
      "learning_rate": 1.5872170439414115e-05,
      "loss": 0.941,
      "step": 620
    },
    {
      "epoch": 0.2097203728362184,
      "grad_norm": 3.03125,
      "learning_rate": 1.5805592543275634e-05,
      "loss": 1.0259,
      "step": 630
    },
    {
      "epoch": 0.21304926764314247,
      "grad_norm": 10.4375,
      "learning_rate": 1.573901464713715e-05,
      "loss": 0.9687,
      "step": 640
    },
    {
      "epoch": 0.21637816245006658,
      "grad_norm": 12.8125,
      "learning_rate": 1.567243675099867e-05,
      "loss": 0.9512,
      "step": 650
    },
    {
      "epoch": 0.2197070572569907,
      "grad_norm": 9.75,
      "learning_rate": 1.5605858854860187e-05,
      "loss": 0.9569,
      "step": 660
    },
    {
      "epoch": 0.22303595206391477,
      "grad_norm": 17.375,
      "learning_rate": 1.5539280958721706e-05,
      "loss": 0.9694,
      "step": 670
    },
    {
      "epoch": 0.22636484687083888,
      "grad_norm": 9.625,
      "learning_rate": 1.5472703062583222e-05,
      "loss": 0.97,
      "step": 680
    },
    {
      "epoch": 0.229693741677763,
      "grad_norm": 21.0,
      "learning_rate": 1.5406125166444742e-05,
      "loss": 1.0506,
      "step": 690
    },
    {
      "epoch": 0.23302263648468707,
      "grad_norm": 10.3125,
      "learning_rate": 1.533954727030626e-05,
      "loss": 0.9184,
      "step": 700
    },
    {
      "epoch": 0.23635153129161118,
      "grad_norm": 21.5,
      "learning_rate": 1.5272969374167778e-05,
      "loss": 1.005,
      "step": 710
    },
    {
      "epoch": 0.2396804260985353,
      "grad_norm": 4.40625,
      "learning_rate": 1.5206391478029296e-05,
      "loss": 0.8624,
      "step": 720
    },
    {
      "epoch": 0.24300932090545938,
      "grad_norm": 13.9375,
      "learning_rate": 1.5139813581890814e-05,
      "loss": 1.0051,
      "step": 730
    },
    {
      "epoch": 0.24633821571238348,
      "grad_norm": 16.625,
      "learning_rate": 1.5073235685752332e-05,
      "loss": 1.0378,
      "step": 740
    },
    {
      "epoch": 0.2496671105193076,
      "grad_norm": 6.4375,
      "learning_rate": 1.500665778961385e-05,
      "loss": 0.9191,
      "step": 750
    },
    {
      "epoch": 0.2529960053262317,
      "grad_norm": 5.5625,
      "learning_rate": 1.4940079893475368e-05,
      "loss": 0.9722,
      "step": 760
    },
    {
      "epoch": 0.2563249001331558,
      "grad_norm": 22.625,
      "learning_rate": 1.4873501997336886e-05,
      "loss": 1.014,
      "step": 770
    },
    {
      "epoch": 0.2596537949400799,
      "grad_norm": 21.0,
      "learning_rate": 1.4806924101198404e-05,
      "loss": 1.0986,
      "step": 780
    },
    {
      "epoch": 0.262982689747004,
      "grad_norm": 10.4375,
      "learning_rate": 1.4740346205059922e-05,
      "loss": 0.9672,
      "step": 790
    },
    {
      "epoch": 0.2663115845539281,
      "grad_norm": 17.0,
      "learning_rate": 1.467376830892144e-05,
      "loss": 0.9605,
      "step": 800
    },
    {
      "epoch": 0.26964047936085217,
      "grad_norm": 31.75,
      "learning_rate": 1.4607190412782957e-05,
      "loss": 1.0308,
      "step": 810
    },
    {
      "epoch": 0.2729693741677763,
      "grad_norm": 12.4375,
      "learning_rate": 1.4540612516644474e-05,
      "loss": 0.9268,
      "step": 820
    },
    {
      "epoch": 0.2762982689747004,
      "grad_norm": 17.125,
      "learning_rate": 1.4474034620505992e-05,
      "loss": 0.9656,
      "step": 830
    },
    {
      "epoch": 0.2796271637816245,
      "grad_norm": 4.53125,
      "learning_rate": 1.440745672436751e-05,
      "loss": 0.9865,
      "step": 840
    },
    {
      "epoch": 0.2829560585885486,
      "grad_norm": 22.625,
      "learning_rate": 1.434087882822903e-05,
      "loss": 1.1118,
      "step": 850
    },
    {
      "epoch": 0.2862849533954727,
      "grad_norm": 13.0,
      "learning_rate": 1.4274300932090547e-05,
      "loss": 1.0043,
      "step": 860
    },
    {
      "epoch": 0.28961384820239683,
      "grad_norm": 9.0625,
      "learning_rate": 1.4207723035952065e-05,
      "loss": 0.9768,
      "step": 870
    },
    {
      "epoch": 0.2929427430093209,
      "grad_norm": 6.75,
      "learning_rate": 1.4141145139813583e-05,
      "loss": 1.0237,
      "step": 880
    },
    {
      "epoch": 0.296271637816245,
      "grad_norm": 10.875,
      "learning_rate": 1.4074567243675101e-05,
      "loss": 1.1597,
      "step": 890
    },
    {
      "epoch": 0.2996005326231691,
      "grad_norm": 5.75,
      "learning_rate": 1.4007989347536619e-05,
      "loss": 0.7993,
      "step": 900
    },
    {
      "epoch": 0.3029294274300932,
      "grad_norm": 31.5,
      "learning_rate": 1.3941411451398137e-05,
      "loss": 0.9802,
      "step": 910
    },
    {
      "epoch": 0.3062583222370173,
      "grad_norm": 12.25,
      "learning_rate": 1.3874833555259655e-05,
      "loss": 0.9565,
      "step": 920
    },
    {
      "epoch": 0.30958721704394143,
      "grad_norm": 11.8125,
      "learning_rate": 1.3808255659121173e-05,
      "loss": 1.0024,
      "step": 930
    },
    {
      "epoch": 0.3129161118508655,
      "grad_norm": 16.625,
      "learning_rate": 1.3741677762982691e-05,
      "loss": 1.0209,
      "step": 940
    },
    {
      "epoch": 0.3162450066577896,
      "grad_norm": 13.375,
      "learning_rate": 1.3675099866844209e-05,
      "loss": 0.8767,
      "step": 950
    },
    {
      "epoch": 0.3195739014647137,
      "grad_norm": 20.875,
      "learning_rate": 1.3608521970705725e-05,
      "loss": 0.9642,
      "step": 960
    },
    {
      "epoch": 0.3229027962716378,
      "grad_norm": 17.25,
      "learning_rate": 1.3541944074567243e-05,
      "loss": 0.9508,
      "step": 970
    },
    {
      "epoch": 0.3262316910785619,
      "grad_norm": 22.25,
      "learning_rate": 1.3475366178428764e-05,
      "loss": 1.1324,
      "step": 980
    },
    {
      "epoch": 0.32956058588548603,
      "grad_norm": 11.5,
      "learning_rate": 1.3408788282290282e-05,
      "loss": 1.0655,
      "step": 990
    },
    {
      "epoch": 0.33288948069241014,
      "grad_norm": 15.625,
      "learning_rate": 1.3342210386151799e-05,
      "loss": 0.9608,
      "step": 1000
    },
    {
      "epoch": 0.33288948069241014,
      "eval_accuracy": 0.507300481168077,
      "eval_loss": 0.9467151165008545,
      "eval_runtime": 211.5004,
      "eval_samples_per_second": 113.986,
      "eval_steps_per_second": 28.496,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 3004,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}