{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9955156950672646,
  "eval_steps": 500,
  "global_step": 74,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013452914798206279,
      "grad_norm": 95.4926986694336,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 12.2856,
      "step": 1
    },
    {
      "epoch": 0.026905829596412557,
      "grad_norm": 93.69285583496094,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 12.2383,
      "step": 2
    },
    {
      "epoch": 0.04035874439461883,
      "grad_norm": 95.09840393066406,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 12.1293,
      "step": 3
    },
    {
      "epoch": 0.053811659192825115,
      "grad_norm": 95.04216766357422,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 12.1453,
      "step": 4
    },
    {
      "epoch": 0.06726457399103139,
      "grad_norm": 93.44210052490234,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 12.165,
      "step": 5
    },
    {
      "epoch": 0.08071748878923767,
      "grad_norm": 93.28514862060547,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 12.063,
      "step": 6
    },
    {
      "epoch": 0.09417040358744394,
      "grad_norm": 95.3654556274414,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 11.9676,
      "step": 7
    },
    {
      "epoch": 0.10762331838565023,
      "grad_norm": 96.05154418945312,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 12.0911,
      "step": 8
    },
    {
      "epoch": 0.1210762331838565,
      "grad_norm": 97.69881439208984,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 12.0717,
      "step": 9
    },
    {
      "epoch": 0.13452914798206278,
      "grad_norm": 95.55254364013672,
      "learning_rate": 5.000000000000001e-07,
      "loss": 11.9752,
      "step": 10
    },
    {
      "epoch": 0.14798206278026907,
      "grad_norm": 95.9182357788086,
      "learning_rate": 5.5e-07,
      "loss": 11.9413,
      "step": 11
    },
    {
      "epoch": 0.16143497757847533,
      "grad_norm": 95.40771484375,
      "learning_rate": 6.000000000000001e-07,
      "loss": 11.7523,
      "step": 12
    },
    {
      "epoch": 0.17488789237668162,
      "grad_norm": 94.40055847167969,
      "learning_rate": 6.5e-07,
      "loss": 11.6384,
      "step": 13
    },
    {
      "epoch": 0.18834080717488788,
      "grad_norm": 93.58352661132812,
      "learning_rate": 7.000000000000001e-07,
      "loss": 11.4293,
      "step": 14
    },
    {
      "epoch": 0.20179372197309417,
      "grad_norm": 94.48737335205078,
      "learning_rate": 7.5e-07,
      "loss": 11.1445,
      "step": 15
    },
    {
      "epoch": 0.21524663677130046,
      "grad_norm": 92.44265747070312,
      "learning_rate": 8.000000000000001e-07,
      "loss": 10.7705,
      "step": 16
    },
    {
      "epoch": 0.22869955156950672,
      "grad_norm": 90.97422790527344,
      "learning_rate": 8.500000000000001e-07,
      "loss": 10.3754,
      "step": 17
    },
    {
      "epoch": 0.242152466367713,
      "grad_norm": 88.54856872558594,
      "learning_rate": 9.000000000000001e-07,
      "loss": 10.0019,
      "step": 18
    },
    {
      "epoch": 0.2556053811659193,
      "grad_norm": 88.39138793945312,
      "learning_rate": 9.500000000000001e-07,
      "loss": 9.5093,
      "step": 19
    },
    {
      "epoch": 0.26905829596412556,
      "grad_norm": 86.55109405517578,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 9.2342,
      "step": 20
    },
    {
      "epoch": 0.2825112107623318,
      "grad_norm": 80.62335205078125,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 8.597,
      "step": 21
    },
    {
      "epoch": 0.29596412556053814,
      "grad_norm": 73.67768859863281,
      "learning_rate": 1.1e-06,
      "loss": 8.1122,
      "step": 22
    },
    {
      "epoch": 0.3094170403587444,
      "grad_norm": 64.57353210449219,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 7.6455,
      "step": 23
    },
    {
      "epoch": 0.32286995515695066,
      "grad_norm": 55.2818603515625,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 7.2493,
      "step": 24
    },
    {
      "epoch": 0.336322869955157,
      "grad_norm": 48.274452209472656,
      "learning_rate": 1.25e-06,
      "loss": 7.0377,
      "step": 25
    },
    {
      "epoch": 0.34977578475336324,
      "grad_norm": 42.7370491027832,
      "learning_rate": 1.3e-06,
      "loss": 6.5782,
      "step": 26
    },
    {
      "epoch": 0.3632286995515695,
      "grad_norm": 39.297462463378906,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 6.2558,
      "step": 27
    },
    {
      "epoch": 0.37668161434977576,
      "grad_norm": 37.91667938232422,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 5.9809,
      "step": 28
    },
    {
      "epoch": 0.3901345291479821,
      "grad_norm": 37.87322998046875,
      "learning_rate": 1.45e-06,
      "loss": 5.7268,
      "step": 29
    },
    {
      "epoch": 0.40358744394618834,
      "grad_norm": 36.48906707763672,
      "learning_rate": 1.5e-06,
      "loss": 5.449,
      "step": 30
    },
    {
      "epoch": 0.4170403587443946,
      "grad_norm": 36.38510513305664,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 5.1884,
      "step": 31
    },
    {
      "epoch": 0.4304932735426009,
      "grad_norm": 35.656829833984375,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 4.899,
      "step": 32
    },
    {
      "epoch": 0.4439461883408072,
      "grad_norm": 34.09960174560547,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 4.5842,
      "step": 33
    },
    {
      "epoch": 0.45739910313901344,
      "grad_norm": 32.74240493774414,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 4.3009,
      "step": 34
    },
    {
      "epoch": 0.47085201793721976,
      "grad_norm": 31.867507934570312,
      "learning_rate": 1.75e-06,
      "loss": 3.9865,
      "step": 35
    },
    {
      "epoch": 0.484304932735426,
      "grad_norm": 30.741374969482422,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 3.6916,
      "step": 36
    },
    {
      "epoch": 0.4977578475336323,
      "grad_norm": 27.8775577545166,
      "learning_rate": 1.85e-06,
      "loss": 3.3719,
      "step": 37
    },
    {
      "epoch": 0.5112107623318386,
      "grad_norm": 25.97083282470703,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 3.0907,
      "step": 38
    },
    {
      "epoch": 0.5246636771300448,
      "grad_norm": 23.62006950378418,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 2.8336,
      "step": 39
    },
    {
      "epoch": 0.5381165919282511,
      "grad_norm": 23.80520248413086,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.5717,
      "step": 40
    },
    {
      "epoch": 0.5515695067264574,
      "grad_norm": 25.32924461364746,
      "learning_rate": 2.05e-06,
      "loss": 2.3658,
      "step": 41
    },
    {
      "epoch": 0.5650224215246636,
      "grad_norm": 26.20570182800293,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 2.2443,
      "step": 42
    },
    {
      "epoch": 0.57847533632287,
      "grad_norm": 24.581693649291992,
      "learning_rate": 2.15e-06,
      "loss": 1.926,
      "step": 43
    },
    {
      "epoch": 0.5919282511210763,
      "grad_norm": 24.414310455322266,
      "learning_rate": 2.2e-06,
      "loss": 1.7034,
      "step": 44
    },
    {
      "epoch": 0.6053811659192825,
      "grad_norm": 22.691083908081055,
      "learning_rate": 2.25e-06,
      "loss": 1.4857,
      "step": 45
    },
    {
      "epoch": 0.6188340807174888,
      "grad_norm": 20.669803619384766,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 1.2415,
      "step": 46
    },
    {
      "epoch": 0.6322869955156951,
      "grad_norm": 20.149641036987305,
      "learning_rate": 2.35e-06,
      "loss": 0.997,
      "step": 47
    },
    {
      "epoch": 0.6457399103139013,
      "grad_norm": 18.632596969604492,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.7552,
      "step": 48
    },
    {
      "epoch": 0.6591928251121076,
      "grad_norm": 16.93793296813965,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.5883,
      "step": 49
    },
    {
      "epoch": 0.672645739910314,
      "grad_norm": 14.432519912719727,
      "learning_rate": 2.5e-06,
      "loss": 0.4382,
      "step": 50
    },
    {
      "epoch": 0.6860986547085202,
      "grad_norm": 11.829660415649414,
      "learning_rate": 2.55e-06,
      "loss": 0.2983,
      "step": 51
    },
    {
      "epoch": 0.6995515695067265,
      "grad_norm": 8.680500030517578,
      "learning_rate": 2.6e-06,
      "loss": 0.1988,
      "step": 52
    },
    {
      "epoch": 0.7130044843049327,
      "grad_norm": 6.53156852722168,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.1589,
      "step": 53
    },
    {
      "epoch": 0.726457399103139,
      "grad_norm": 2.9756624698638916,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.0686,
      "step": 54
    },
    {
      "epoch": 0.7399103139013453,
      "grad_norm": 5.545580863952637,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.0865,
      "step": 55
    },
    {
      "epoch": 0.7533632286995515,
      "grad_norm": 4.045405387878418,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.0949,
      "step": 56
    },
    {
      "epoch": 0.7668161434977578,
      "grad_norm": 1.6688120365142822,
      "learning_rate": 2.85e-06,
      "loss": 0.0396,
      "step": 57
    },
    {
      "epoch": 0.7802690582959642,
      "grad_norm": 2.4520657062530518,
      "learning_rate": 2.9e-06,
      "loss": 0.0439,
      "step": 58
    },
    {
      "epoch": 0.7937219730941704,
      "grad_norm": 2.608729600906372,
      "learning_rate": 2.95e-06,
      "loss": 0.057,
      "step": 59
    },
    {
      "epoch": 0.8071748878923767,
      "grad_norm": 2.365234851837158,
      "learning_rate": 3e-06,
      "loss": 0.0547,
      "step": 60
    },
    {
      "epoch": 0.820627802690583,
      "grad_norm": 0.787550687789917,
      "learning_rate": 3.05e-06,
      "loss": 0.0209,
      "step": 61
    },
    {
      "epoch": 0.8340807174887892,
      "grad_norm": 0.7686442732810974,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.0221,
      "step": 62
    },
    {
      "epoch": 0.8475336322869955,
      "grad_norm": 1.2510555982589722,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.0165,
      "step": 63
    },
    {
      "epoch": 0.8609865470852018,
      "grad_norm": 0.8923770189285278,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.0187,
      "step": 64
    },
    {
      "epoch": 0.874439461883408,
      "grad_norm": 0.8052615523338318,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.0266,
      "step": 65
    },
    {
      "epoch": 0.8878923766816144,
      "grad_norm": 0.6710303425788879,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.0154,
      "step": 66
    },
    {
      "epoch": 0.9013452914798207,
      "grad_norm": 0.5213025212287903,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.0085,
      "step": 67
    },
    {
      "epoch": 0.9147982062780269,
      "grad_norm": 0.5758580565452576,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.0133,
      "step": 68
    },
    {
      "epoch": 0.9282511210762332,
      "grad_norm": 0.6828752160072327,
      "learning_rate": 3.45e-06,
      "loss": 0.0186,
      "step": 69
    },
    {
      "epoch": 0.9417040358744395,
      "grad_norm": 0.6814988255500793,
      "learning_rate": 3.5e-06,
      "loss": 0.0215,
      "step": 70
    },
    {
      "epoch": 0.9551569506726457,
      "grad_norm": 0.718296229839325,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.0204,
      "step": 71
    },
    {
      "epoch": 0.968609865470852,
      "grad_norm": 0.7816944122314453,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.0184,
      "step": 72
    },
    {
      "epoch": 0.9820627802690582,
      "grad_norm": 0.6058817505836487,
      "learning_rate": 3.65e-06,
      "loss": 0.0179,
      "step": 73
    },
    {
      "epoch": 0.9955156950672646,
      "grad_norm": 1.0496101379394531,
      "learning_rate": 3.7e-06,
      "loss": 0.032,
      "step": 74
    }
  ],
  "logging_steps": 1,
  "max_steps": 444,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 74,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6577058229662515e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}