{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "grad_norm": 0.9758233428001404,
      "learning_rate": 1.8e-06,
      "loss": 1.1603,
      "step": 10
    },
    {
      "grad_norm": 0.42593392729759216,
      "learning_rate": 3.8e-06,
      "loss": 1.1479,
      "step": 20
    },
    {
      "grad_norm": 0.21856296062469482,
      "learning_rate": 5.8e-06,
      "loss": 1.1204,
      "step": 30
    },
    {
      "grad_norm": 0.1426735520362854,
      "learning_rate": 7.8e-06,
      "loss": 1.1026,
      "step": 40
    },
    {
      "grad_norm": 0.13335095345973969,
      "learning_rate": 9.800000000000001e-06,
      "loss": 1.0891,
      "step": 50
    },
    {
      "grad_norm": 0.11337289214134216,
      "learning_rate": 1.18e-05,
      "loss": 1.0658,
      "step": 60
    },
    {
      "grad_norm": 0.09717453271150589,
      "learning_rate": 1.3800000000000002e-05,
      "loss": 1.0543,
      "step": 70
    },
    {
      "grad_norm": 0.10322871059179306,
      "learning_rate": 1.58e-05,
      "loss": 1.0375,
      "step": 80
    },
    {
      "grad_norm": 0.17508411407470703,
      "learning_rate": 1.78e-05,
      "loss": 1.0261,
      "step": 90
    },
    {
      "grad_norm": 0.29097145795822144,
      "learning_rate": 1.9800000000000004e-05,
      "loss": 1.0143,
      "step": 100
    },
    {
      "grad_norm": 0.28556156158447266,
      "learning_rate": 2.18e-05,
      "loss": 0.9888,
      "step": 110
    },
    {
      "grad_norm": 0.7807521224021912,
      "learning_rate": 2.38e-05,
      "loss": 0.943,
      "step": 120
    },
    {
      "grad_norm": 0.6720882654190063,
      "learning_rate": 2.58e-05,
      "loss": 0.8726,
      "step": 130
    },
    {
      "grad_norm": 0.867290198802948,
      "learning_rate": 2.7800000000000005e-05,
      "loss": 0.7941,
      "step": 140
    },
    {
      "grad_norm": 0.7180277705192566,
      "learning_rate": 2.98e-05,
      "loss": 0.731,
      "step": 150
    },
    {
      "grad_norm": 0.6411461234092712,
      "learning_rate": 3.18e-05,
      "loss": 0.6729,
      "step": 160
    },
    {
      "grad_norm": 0.8856205344200134,
      "learning_rate": 3.38e-05,
      "loss": 0.6213,
      "step": 170
    },
    {
      "grad_norm": 1.1326690912246704,
      "learning_rate": 3.58e-05,
      "loss": 0.5673,
      "step": 180
    },
    {
      "grad_norm": 0.8645981550216675,
      "learning_rate": 3.7800000000000004e-05,
      "loss": 0.5007,
      "step": 190
    },
    {
      "grad_norm": 1.4590177536010742,
      "learning_rate": 3.9800000000000005e-05,
      "loss": 0.4514,
      "step": 200
    },
    {
      "grad_norm": 1.0651799440383911,
      "learning_rate": 4.18e-05,
      "loss": 0.4098,
      "step": 210
    },
    {
      "grad_norm": 0.9970216155052185,
      "learning_rate": 4.38e-05,
      "loss": 0.3782,
      "step": 220
    },
    {
      "grad_norm": 1.4383465051651,
      "learning_rate": 4.58e-05,
      "loss": 0.3505,
      "step": 230
    },
    {
      "grad_norm": 1.0782465934753418,
      "learning_rate": 4.78e-05,
      "loss": 0.3158,
      "step": 240
    },
    {
      "grad_norm": 1.101946234703064,
      "learning_rate": 4.9800000000000004e-05,
      "loss": 0.2916,
      "step": 250
    },
    {
      "grad_norm": 1.587511420249939,
      "learning_rate": 5.1800000000000005e-05,
      "loss": 0.261,
      "step": 260
    },
    {
      "grad_norm": 1.435607671737671,
      "learning_rate": 5.380000000000001e-05,
      "loss": 0.2437,
      "step": 270
    },
    {
      "grad_norm": 0.9712788462638855,
      "learning_rate": 5.580000000000001e-05,
      "loss": 0.2171,
      "step": 280
    },
    {
      "grad_norm": 1.7632523775100708,
      "learning_rate": 5.7799999999999995e-05,
      "loss": 0.2055,
      "step": 290
    },
    {
      "grad_norm": 1.7171282768249512,
      "learning_rate": 5.9800000000000003e-05,
      "loss": 0.1883,
      "step": 300
    },
    {
      "grad_norm": 1.374088168144226,
      "learning_rate": 6.18e-05,
      "loss": 0.1745,
      "step": 310
    },
    {
      "grad_norm": 1.4401962757110596,
      "learning_rate": 6.38e-05,
      "loss": 0.1576,
      "step": 320
    },
    {
      "grad_norm": 1.3337668180465698,
      "learning_rate": 6.58e-05,
      "loss": 0.1363,
      "step": 330
    },
    {
      "grad_norm": 0.9742352366447449,
      "learning_rate": 6.780000000000001e-05,
      "loss": 0.1193,
      "step": 340
    },
    {
      "grad_norm": 1.369019865989685,
      "learning_rate": 6.98e-05,
      "loss": 0.1097,
      "step": 350
    },
    {
      "grad_norm": 1.2735106945037842,
      "learning_rate": 7.18e-05,
      "loss": 0.0989,
      "step": 360
    },
    {
      "grad_norm": 1.1764349937438965,
      "learning_rate": 7.38e-05,
      "loss": 0.0924,
      "step": 370
    },
    {
      "grad_norm": 1.46502685546875,
      "learning_rate": 7.58e-05,
      "loss": 0.0892,
      "step": 380
    },
    {
      "grad_norm": 1.2585327625274658,
      "learning_rate": 7.780000000000001e-05,
      "loss": 0.0867,
      "step": 390
    },
    {
      "grad_norm": 1.3663945198059082,
      "learning_rate": 7.98e-05,
      "loss": 0.0823,
      "step": 400
    },
    {
      "grad_norm": 1.3091000318527222,
      "learning_rate": 8.18e-05,
      "loss": 0.0749,
      "step": 410
    },
    {
      "grad_norm": 1.0578632354736328,
      "learning_rate": 8.38e-05,
      "loss": 0.0772,
      "step": 420
    },
    {
      "grad_norm": 1.354399561882019,
      "learning_rate": 8.58e-05,
      "loss": 0.0747,
      "step": 430
    },
    {
      "grad_norm": 0.9889944195747375,
      "learning_rate": 8.78e-05,
      "loss": 0.0741,
      "step": 440
    },
    {
      "grad_norm": 1.1401726007461548,
      "learning_rate": 8.98e-05,
      "loss": 0.0722,
      "step": 450
    },
    {
      "grad_norm": 0.9166666269302368,
      "learning_rate": 9.180000000000001e-05,
      "loss": 0.0656,
      "step": 460
    },
    {
      "grad_norm": 1.3585307598114014,
      "learning_rate": 9.38e-05,
      "loss": 0.0714,
      "step": 470
    },
    {
      "grad_norm": 1.211781620979309,
      "learning_rate": 9.58e-05,
      "loss": 0.0692,
      "step": 480
    },
    {
      "grad_norm": 1.2247947454452515,
      "learning_rate": 9.78e-05,
      "loss": 0.0648,
      "step": 490
    },
    {
      "grad_norm": 0.8823159337043762,
      "learning_rate": 9.98e-05,
      "loss": 0.0669,
      "step": 500
    },
    {
      "grad_norm": 1.1154427528381348,
      "learning_rate": 9.9999778549206e-05,
      "loss": 0.0639,
      "step": 510
    },
    {
      "grad_norm": 0.8653926253318787,
      "learning_rate": 9.999901304280685e-05,
      "loss": 0.0567,
      "step": 520
    },
    {
      "grad_norm": 0.831631064414978,
      "learning_rate": 9.999770075521164e-05,
      "loss": 0.0538,
      "step": 530
    },
    {
      "grad_norm": 0.8719817399978638,
      "learning_rate": 9.99958417007713e-05,
      "loss": 0.0591,
      "step": 540
    },
    {
      "grad_norm": 0.9873416423797607,
      "learning_rate": 9.999343589981615e-05,
      "loss": 0.0542,
      "step": 550
    },
    {
      "grad_norm": 0.9876612424850464,
      "learning_rate": 9.999048337865568e-05,
      "loss": 0.0522,
      "step": 560
    },
    {
      "grad_norm": 1.1858694553375244,
      "learning_rate": 9.998698416957815e-05,
      "loss": 0.0558,
      "step": 570
    },
    {
      "grad_norm": 0.646891176700592,
      "learning_rate": 9.998293831085037e-05,
      "loss": 0.0517,
      "step": 580
    },
    {
      "grad_norm": 0.6390032768249512,
      "learning_rate": 9.997834584671719e-05,
      "loss": 0.0537,
      "step": 590
    },
    {
      "grad_norm": 0.8343250751495361,
      "learning_rate": 9.997320682740107e-05,
      "loss": 0.0517,
      "step": 600
    },
    {
      "grad_norm": 0.7489078640937805,
      "learning_rate": 9.996752130910149e-05,
      "loss": 0.0489,
      "step": 610
    },
    {
      "grad_norm": 0.8712443113327026,
      "learning_rate": 9.99612893539944e-05,
      "loss": 0.0501,
      "step": 620
    },
    {
      "grad_norm": 0.9857075810432434,
      "learning_rate": 9.995451103023144e-05,
      "loss": 0.0477,
      "step": 630
    },
    {
      "grad_norm": 0.7690502405166626,
      "learning_rate": 9.994718641193928e-05,
      "loss": 0.0493,
      "step": 640
    },
    {
      "grad_norm": 1.0277982950210571,
      "learning_rate": 9.993931557921874e-05,
      "loss": 0.0481,
      "step": 650
    },
    {
      "grad_norm": 0.7521364688873291,
      "learning_rate": 9.993089861814402e-05,
      "loss": 0.0445,
      "step": 660
    },
    {
      "grad_norm": 0.7378376722335815,
      "learning_rate": 9.992193562076166e-05,
      "loss": 0.0519,
      "step": 670
    },
    {
      "grad_norm": 0.848283052444458,
      "learning_rate": 9.991242668508954e-05,
      "loss": 0.0468,
      "step": 680
    },
    {
      "grad_norm": 0.8540059328079224,
      "learning_rate": 9.990237191511587e-05,
      "loss": 0.0438,
      "step": 690
    },
    {
      "grad_norm": 0.8540256023406982,
      "learning_rate": 9.989177142079802e-05,
      "loss": 0.0436,
      "step": 700
    },
    {
      "grad_norm": 0.8738433718681335,
      "learning_rate": 9.988062531806126e-05,
      "loss": 0.0423,
      "step": 710
    },
    {
      "grad_norm": 0.7137842178344727,
      "learning_rate": 9.986893372879762e-05,
      "loss": 0.0423,
      "step": 720
    },
    {
      "grad_norm": 0.8221761584281921,
      "learning_rate": 9.985669678086443e-05,
      "loss": 0.0454,
      "step": 730
    },
    {
      "grad_norm": 0.7644378542900085,
      "learning_rate": 9.984391460808298e-05,
      "loss": 0.043,
      "step": 740
    },
    {
      "grad_norm": 0.9529057145118713,
      "learning_rate": 9.983058735023709e-05,
      "loss": 0.0412,
      "step": 750
    },
    {
      "grad_norm": 0.5925287008285522,
      "learning_rate": 9.98167151530715e-05,
      "loss": 0.0412,
      "step": 760
    },
    {
      "grad_norm": 0.9713786840438843,
      "learning_rate": 9.980229816829034e-05,
      "loss": 0.0438,
      "step": 770
    },
    {
      "grad_norm": 0.8202999830245972,
      "learning_rate": 9.978733655355544e-05,
      "loss": 0.0426,
      "step": 780
    },
    {
      "grad_norm": 0.8735260367393494,
      "learning_rate": 9.977183047248464e-05,
      "loss": 0.0417,
      "step": 790
    },
    {
      "grad_norm": 0.780419647693634,
      "learning_rate": 9.975578009464992e-05,
      "loss": 0.0442,
      "step": 800
    },
    {
      "grad_norm": 0.6911860108375549,
      "learning_rate": 9.97391855955757e-05,
      "loss": 0.0387,
      "step": 810
    },
    {
      "grad_norm": 0.7028207182884216,
      "learning_rate": 9.972204715673669e-05,
      "loss": 0.0406,
      "step": 820
    },
    {
      "grad_norm": 0.6863601207733154,
      "learning_rate": 9.970436496555617e-05,
      "loss": 0.0365,
      "step": 830
    },
    {
      "grad_norm": 0.8116464614868164,
      "learning_rate": 9.968613921540373e-05,
      "loss": 0.0403,
      "step": 840
    },
    {
      "grad_norm": 0.5927073359489441,
      "learning_rate": 9.966737010559326e-05,
      "loss": 0.0457,
      "step": 850
    },
    {
      "grad_norm": 0.7573205828666687,
      "learning_rate": 9.964805784138072e-05,
      "loss": 0.0386,
      "step": 860
    },
    {
      "grad_norm": 0.777636706829071,
      "learning_rate": 9.962820263396195e-05,
      "loss": 0.0377,
      "step": 870
    },
    {
      "grad_norm": 0.6754245758056641,
      "learning_rate": 9.960780470047033e-05,
      "loss": 0.0402,
      "step": 880
    },
    {
      "grad_norm": 0.7781431674957275,
      "learning_rate": 9.958686426397437e-05,
      "loss": 0.0392,
      "step": 890
    },
    {
      "grad_norm": 0.7408170104026794,
      "learning_rate": 9.956538155347534e-05,
      "loss": 0.0397,
      "step": 900
    },
    {
      "grad_norm": 0.7765600085258484,
      "learning_rate": 9.95433568039047e-05,
      "loss": 0.0368,
      "step": 910
    },
    {
      "grad_norm": 0.7626947164535522,
      "learning_rate": 9.952079025612162e-05,
      "loss": 0.0375,
      "step": 920
    },
    {
      "grad_norm": 0.7383814454078674,
      "learning_rate": 9.949768215691022e-05,
      "loss": 0.0396,
      "step": 930
    },
    {
      "grad_norm": 0.5346885919570923,
      "learning_rate": 9.9474032758977e-05,
      "loss": 0.038,
      "step": 940
    },
    {
      "grad_norm": 0.649907648563385,
      "learning_rate": 9.944984232094794e-05,
      "loss": 0.0377,
      "step": 950
    },
    {
      "grad_norm": 0.7877050042152405,
      "learning_rate": 9.942511110736584e-05,
      "loss": 0.0359,
      "step": 960
    },
    {
      "grad_norm": 0.7351949214935303,
      "learning_rate": 9.939983938868726e-05,
      "loss": 0.0372,
      "step": 970
    },
    {
      "grad_norm": 1.1521971225738525,
      "learning_rate": 9.93740274412797e-05,
      "loss": 0.0361,
      "step": 980
    },
    {
      "grad_norm": 0.817077100276947,
      "learning_rate": 9.934767554741846e-05,
      "loss": 0.0377,
      "step": 990
    },
    {
      "grad_norm": 0.5828076601028442,
      "learning_rate": 9.932078399528361e-05,
      "loss": 0.0365,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 10000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 1000,
  "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": 128,
  "trial_name": null,
  "trial_params": null
}