{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 77,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012987012987012988,
      "grad_norm": 30.513944625854492,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 4.1013,
      "step": 1
    },
    {
      "epoch": 0.025974025974025976,
      "grad_norm": 30.965682983398438,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 4.1757,
      "step": 2
    },
    {
      "epoch": 0.03896103896103896,
      "grad_norm": 30.834516525268555,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 4.1371,
      "step": 3
    },
    {
      "epoch": 0.05194805194805195,
      "grad_norm": 30.98870849609375,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 4.0543,
      "step": 4
    },
    {
      "epoch": 0.06493506493506493,
      "grad_norm": 30.404874801635742,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 4.09,
      "step": 5
    },
    {
      "epoch": 0.07792207792207792,
      "grad_norm": 31.433774948120117,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 4.1777,
      "step": 6
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 30.850692749023438,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 4.142,
      "step": 7
    },
    {
      "epoch": 0.1038961038961039,
      "grad_norm": 31.00360870361328,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 4.1115,
      "step": 8
    },
    {
      "epoch": 0.11688311688311688,
      "grad_norm": 31.221616744995117,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 4.1585,
      "step": 9
    },
    {
      "epoch": 0.12987012987012986,
      "grad_norm": 30.560623168945312,
      "learning_rate": 5.000000000000001e-07,
      "loss": 4.1155,
      "step": 10
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 30.089527130126953,
      "learning_rate": 5.5e-07,
      "loss": 4.0638,
      "step": 11
    },
    {
      "epoch": 0.15584415584415584,
      "grad_norm": 30.662569046020508,
      "learning_rate": 6.000000000000001e-07,
      "loss": 4.0152,
      "step": 12
    },
    {
      "epoch": 0.16883116883116883,
      "grad_norm": 29.455503463745117,
      "learning_rate": 6.5e-07,
      "loss": 3.9501,
      "step": 13
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 28.851863861083984,
      "learning_rate": 7.000000000000001e-07,
      "loss": 3.9066,
      "step": 14
    },
    {
      "epoch": 0.19480519480519481,
      "grad_norm": 27.41941261291504,
      "learning_rate": 7.5e-07,
      "loss": 3.816,
      "step": 15
    },
    {
      "epoch": 0.2077922077922078,
      "grad_norm": 25.754905700683594,
      "learning_rate": 8.000000000000001e-07,
      "loss": 3.6715,
      "step": 16
    },
    {
      "epoch": 0.22077922077922077,
      "grad_norm": 24.467802047729492,
      "learning_rate": 8.500000000000001e-07,
      "loss": 3.6226,
      "step": 17
    },
    {
      "epoch": 0.23376623376623376,
      "grad_norm": 23.671884536743164,
      "learning_rate": 9.000000000000001e-07,
      "loss": 3.5756,
      "step": 18
    },
    {
      "epoch": 0.24675324675324675,
      "grad_norm": 21.28356170654297,
      "learning_rate": 9.500000000000001e-07,
      "loss": 3.3822,
      "step": 19
    },
    {
      "epoch": 0.2597402597402597,
      "grad_norm": 20.54037857055664,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 3.3799,
      "step": 20
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 18.18222427368164,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 3.1964,
      "step": 21
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 17.782703399658203,
      "learning_rate": 1.1e-06,
      "loss": 3.1745,
      "step": 22
    },
    {
      "epoch": 0.2987012987012987,
      "grad_norm": 15.965900421142578,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 2.9002,
      "step": 23
    },
    {
      "epoch": 0.3116883116883117,
      "grad_norm": 16.00725746154785,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 2.9123,
      "step": 24
    },
    {
      "epoch": 0.3246753246753247,
      "grad_norm": 15.301984786987305,
      "learning_rate": 1.25e-06,
      "loss": 2.6531,
      "step": 25
    },
    {
      "epoch": 0.33766233766233766,
      "grad_norm": 16.359207153320312,
      "learning_rate": 1.3e-06,
      "loss": 2.6089,
      "step": 26
    },
    {
      "epoch": 0.35064935064935066,
      "grad_norm": 17.74176025390625,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 2.4805,
      "step": 27
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 18.702547073364258,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 2.3312,
      "step": 28
    },
    {
      "epoch": 0.37662337662337664,
      "grad_norm": 18.44041633605957,
      "learning_rate": 1.45e-06,
      "loss": 2.2273,
      "step": 29
    },
    {
      "epoch": 0.38961038961038963,
      "grad_norm": 15.867247581481934,
      "learning_rate": 1.5e-06,
      "loss": 2.0514,
      "step": 30
    },
    {
      "epoch": 0.4025974025974026,
      "grad_norm": 13.97642707824707,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 1.8689,
      "step": 31
    },
    {
      "epoch": 0.4155844155844156,
      "grad_norm": 13.599323272705078,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 1.7907,
      "step": 32
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 13.204086303710938,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 1.6537,
      "step": 33
    },
    {
      "epoch": 0.44155844155844154,
      "grad_norm": 13.255966186523438,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 1.5693,
      "step": 34
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 13.00086784362793,
      "learning_rate": 1.75e-06,
      "loss": 1.3916,
      "step": 35
    },
    {
      "epoch": 0.4675324675324675,
      "grad_norm": 12.996549606323242,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 1.2734,
      "step": 36
    },
    {
      "epoch": 0.4805194805194805,
      "grad_norm": 12.506110191345215,
      "learning_rate": 1.85e-06,
      "loss": 1.1444,
      "step": 37
    },
    {
      "epoch": 0.4935064935064935,
      "grad_norm": 12.379636764526367,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 1.033,
      "step": 38
    },
    {
      "epoch": 0.5064935064935064,
      "grad_norm": 12.38772201538086,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 0.8932,
      "step": 39
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 12.370598793029785,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.7914,
      "step": 40
    },
    {
      "epoch": 0.5324675324675324,
      "grad_norm": 11.510255813598633,
      "learning_rate": 2.05e-06,
      "loss": 0.6336,
      "step": 41
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 10.088979721069336,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.5115,
      "step": 42
    },
    {
      "epoch": 0.5584415584415584,
      "grad_norm": 9.241965293884277,
      "learning_rate": 2.15e-06,
      "loss": 0.416,
      "step": 43
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 7.457204341888428,
      "learning_rate": 2.2e-06,
      "loss": 0.2947,
      "step": 44
    },
    {
      "epoch": 0.5844155844155844,
      "grad_norm": 6.164954662322998,
      "learning_rate": 2.25e-06,
      "loss": 0.2202,
      "step": 45
    },
    {
      "epoch": 0.5974025974025974,
      "grad_norm": 4.587556838989258,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.1721,
      "step": 46
    },
    {
      "epoch": 0.6103896103896104,
      "grad_norm": 3.2366952896118164,
      "learning_rate": 2.35e-06,
      "loss": 0.1451,
      "step": 47
    },
    {
      "epoch": 0.6233766233766234,
      "grad_norm": 2.397469997406006,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.1116,
      "step": 48
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 1.872839093208313,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.1,
      "step": 49
    },
    {
      "epoch": 0.6493506493506493,
      "grad_norm": 1.2464176416397095,
      "learning_rate": 2.5e-06,
      "loss": 0.1024,
      "step": 50
    },
    {
      "epoch": 0.6623376623376623,
      "grad_norm": 1.0786665678024292,
      "learning_rate": 2.55e-06,
      "loss": 0.087,
      "step": 51
    },
    {
      "epoch": 0.6753246753246753,
      "grad_norm": 1.10042142868042,
      "learning_rate": 2.6e-06,
      "loss": 0.0838,
      "step": 52
    },
    {
      "epoch": 0.6883116883116883,
      "grad_norm": 0.9031299948692322,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.0804,
      "step": 53
    },
    {
      "epoch": 0.7012987012987013,
      "grad_norm": 0.8072167634963989,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.0786,
      "step": 54
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.6948329210281372,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.0773,
      "step": 55
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.6062957644462585,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.0756,
      "step": 56
    },
    {
      "epoch": 0.7402597402597403,
      "grad_norm": 0.4804394841194153,
      "learning_rate": 2.85e-06,
      "loss": 0.0697,
      "step": 57
    },
    {
      "epoch": 0.7532467532467533,
      "grad_norm": 0.5353919863700867,
      "learning_rate": 2.9e-06,
      "loss": 0.0697,
      "step": 58
    },
    {
      "epoch": 0.7662337662337663,
      "grad_norm": 0.4344547390937805,
      "learning_rate": 2.95e-06,
      "loss": 0.0704,
      "step": 59
    },
    {
      "epoch": 0.7792207792207793,
      "grad_norm": 0.574044942855835,
      "learning_rate": 3e-06,
      "loss": 0.0778,
      "step": 60
    },
    {
      "epoch": 0.7922077922077922,
      "grad_norm": 0.5392284393310547,
      "learning_rate": 3.05e-06,
      "loss": 0.0658,
      "step": 61
    },
    {
      "epoch": 0.8051948051948052,
      "grad_norm": 0.5098194479942322,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.0661,
      "step": 62
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.3733481168746948,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.0667,
      "step": 63
    },
    {
      "epoch": 0.8311688311688312,
      "grad_norm": 0.3714415431022644,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.0635,
      "step": 64
    },
    {
      "epoch": 0.8441558441558441,
      "grad_norm": 0.37473437190055847,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.0661,
      "step": 65
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.35993579030036926,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.0637,
      "step": 66
    },
    {
      "epoch": 0.8701298701298701,
      "grad_norm": 0.41175705194473267,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.0646,
      "step": 67
    },
    {
      "epoch": 0.8831168831168831,
      "grad_norm": 0.29564622044563293,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.0627,
      "step": 68
    },
    {
      "epoch": 0.8961038961038961,
      "grad_norm": 0.3018590211868286,
      "learning_rate": 3.45e-06,
      "loss": 0.0613,
      "step": 69
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.499183714389801,
      "learning_rate": 3.5e-06,
      "loss": 0.0664,
      "step": 70
    },
    {
      "epoch": 0.922077922077922,
      "grad_norm": 0.3450847864151001,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.0589,
      "step": 71
    },
    {
      "epoch": 0.935064935064935,
      "grad_norm": 0.26693543791770935,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.0633,
      "step": 72
    },
    {
      "epoch": 0.948051948051948,
      "grad_norm": 0.2867635190486908,
      "learning_rate": 3.65e-06,
      "loss": 0.062,
      "step": 73
    },
    {
      "epoch": 0.961038961038961,
      "grad_norm": 0.3328873813152313,
      "learning_rate": 3.7e-06,
      "loss": 0.0587,
      "step": 74
    },
    {
      "epoch": 0.974025974025974,
      "grad_norm": 0.33611243963241577,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.058,
      "step": 75
    },
    {
      "epoch": 0.987012987012987,
      "grad_norm": 0.2983446419239044,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.0632,
      "step": 76
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.3246895372867584,
      "learning_rate": 3.85e-06,
      "loss": 0.0583,
      "step": 77
    }
  ],
  "logging_steps": 1,
  "max_steps": 462,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 77,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.721176540965765e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}