{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 105,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 14.89224330607143,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 2.5522,
      "step": 1
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 15.539699880062319,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 2.7538,
      "step": 2
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 14.657089316711287,
      "learning_rate": 5e-06,
      "loss": 2.5233,
      "step": 3
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 14.62037927049032,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.4911,
      "step": 4
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 13.46259512513815,
      "learning_rate": 8.333333333333334e-06,
      "loss": 2.4234,
      "step": 5
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 9.898120389403246,
      "learning_rate": 1e-05,
      "loss": 2.1563,
      "step": 6
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 9.15703720284808,
      "learning_rate": 9.8989898989899e-06,
      "loss": 2.2352,
      "step": 7
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 4.103699760876183,
      "learning_rate": 9.797979797979798e-06,
      "loss": 1.8147,
      "step": 8
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 3.3294698206083173,
      "learning_rate": 9.696969696969698e-06,
      "loss": 1.7331,
      "step": 9
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 3.0493914343303423,
      "learning_rate": 9.595959595959597e-06,
      "loss": 1.6996,
      "step": 10
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 1.8606361454328066,
      "learning_rate": 9.494949494949497e-06,
      "loss": 1.5212,
      "step": 11
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.875005980024111,
      "learning_rate": 9.393939393939396e-06,
      "loss": 1.5432,
      "step": 12
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 1.6406263147681137,
      "learning_rate": 9.292929292929294e-06,
      "loss": 1.6781,
      "step": 13
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.4190959915763945,
      "learning_rate": 9.191919191919193e-06,
      "loss": 1.5315,
      "step": 14
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.2550062123023145,
      "learning_rate": 9.090909090909091e-06,
      "loss": 1.518,
      "step": 15
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 1.1358445444435004,
      "learning_rate": 8.98989898989899e-06,
      "loss": 1.4821,
      "step": 16
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 0.8998525427278421,
      "learning_rate": 8.888888888888888e-06,
      "loss": 1.494,
      "step": 17
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.8421569585870735,
      "learning_rate": 8.787878787878788e-06,
      "loss": 1.5041,
      "step": 18
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 0.7895704548382987,
      "learning_rate": 8.686868686868687e-06,
      "loss": 1.3214,
      "step": 19
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.7080170636071926,
      "learning_rate": 8.585858585858587e-06,
      "loss": 1.3607,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6214750636769658,
      "learning_rate": 8.484848484848486e-06,
      "loss": 1.2858,
      "step": 21
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 0.5489588435770981,
      "learning_rate": 8.383838383838384e-06,
      "loss": 1.2929,
      "step": 22
    },
    {
      "epoch": 1.0952380952380953,
      "grad_norm": 0.5968285780172078,
      "learning_rate": 8.282828282828283e-06,
      "loss": 1.3771,
      "step": 23
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.5721944443617278,
      "learning_rate": 8.181818181818183e-06,
      "loss": 1.3974,
      "step": 24
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 0.5210716671654823,
      "learning_rate": 8.08080808080808e-06,
      "loss": 1.2787,
      "step": 25
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 0.5008527555694218,
      "learning_rate": 7.97979797979798e-06,
      "loss": 1.3384,
      "step": 26
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.4730386150994334,
      "learning_rate": 7.87878787878788e-06,
      "loss": 1.3143,
      "step": 27
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.445033830021487,
      "learning_rate": 7.77777777777778e-06,
      "loss": 1.2948,
      "step": 28
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 0.47943182831450376,
      "learning_rate": 7.676767676767677e-06,
      "loss": 1.3185,
      "step": 29
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.44918422682493503,
      "learning_rate": 7.5757575757575764e-06,
      "loss": 1.2411,
      "step": 30
    },
    {
      "epoch": 1.4761904761904763,
      "grad_norm": 0.49304050988609094,
      "learning_rate": 7.474747474747476e-06,
      "loss": 1.3767,
      "step": 31
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 0.44759642687737294,
      "learning_rate": 7.373737373737374e-06,
      "loss": 1.2838,
      "step": 32
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.4385917365277406,
      "learning_rate": 7.272727272727273e-06,
      "loss": 1.3151,
      "step": 33
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 0.43604531117027284,
      "learning_rate": 7.171717171717172e-06,
      "loss": 1.283,
      "step": 34
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.4187068690825293,
      "learning_rate": 7.070707070707071e-06,
      "loss": 1.3236,
      "step": 35
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.41197700020648137,
      "learning_rate": 6.969696969696971e-06,
      "loss": 1.196,
      "step": 36
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 0.3444153776479967,
      "learning_rate": 6.868686868686869e-06,
      "loss": 1.2148,
      "step": 37
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 0.37604108583459445,
      "learning_rate": 6.767676767676769e-06,
      "loss": 1.1686,
      "step": 38
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.4174196433676207,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.3629,
      "step": 39
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.47458542010811544,
      "learning_rate": 6.565656565656566e-06,
      "loss": 1.3593,
      "step": 40
    },
    {
      "epoch": 1.9523809523809523,
      "grad_norm": 0.36724713294085326,
      "learning_rate": 6.464646464646466e-06,
      "loss": 1.2944,
      "step": 41
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.31518625069343653,
      "learning_rate": 6.363636363636364e-06,
      "loss": 1.1552,
      "step": 42
    },
    {
      "epoch": 2.0476190476190474,
      "grad_norm": 0.344554495131319,
      "learning_rate": 6.262626262626264e-06,
      "loss": 1.2759,
      "step": 43
    },
    {
      "epoch": 2.0952380952380953,
      "grad_norm": 0.3446885665486226,
      "learning_rate": 6.1616161616161615e-06,
      "loss": 1.189,
      "step": 44
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.33717381896772436,
      "learning_rate": 6.060606060606061e-06,
      "loss": 1.2492,
      "step": 45
    },
    {
      "epoch": 2.1904761904761907,
      "grad_norm": 0.3280948740040612,
      "learning_rate": 5.95959595959596e-06,
      "loss": 1.2314,
      "step": 46
    },
    {
      "epoch": 2.238095238095238,
      "grad_norm": 0.2890810803339315,
      "learning_rate": 5.858585858585859e-06,
      "loss": 1.2048,
      "step": 47
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.3394693792852931,
      "learning_rate": 5.7575757575757586e-06,
      "loss": 1.2662,
      "step": 48
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.2862820306411597,
      "learning_rate": 5.656565656565657e-06,
      "loss": 1.2312,
      "step": 49
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.34632749098863364,
      "learning_rate": 5.555555555555557e-06,
      "loss": 1.2763,
      "step": 50
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.30179234294037277,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 1.2303,
      "step": 51
    },
    {
      "epoch": 2.4761904761904763,
      "grad_norm": 0.2975693504613476,
      "learning_rate": 5.353535353535354e-06,
      "loss": 1.1631,
      "step": 52
    },
    {
      "epoch": 2.5238095238095237,
      "grad_norm": 0.27666974601669986,
      "learning_rate": 5.252525252525253e-06,
      "loss": 1.1244,
      "step": 53
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.28043374872375093,
      "learning_rate": 5.151515151515152e-06,
      "loss": 1.242,
      "step": 54
    },
    {
      "epoch": 2.619047619047619,
      "grad_norm": 0.30742763111053134,
      "learning_rate": 5.0505050505050515e-06,
      "loss": 1.3342,
      "step": 55
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.2793281238406044,
      "learning_rate": 4.94949494949495e-06,
      "loss": 1.2335,
      "step": 56
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 0.2992649920538676,
      "learning_rate": 4.848484848484849e-06,
      "loss": 1.1731,
      "step": 57
    },
    {
      "epoch": 2.761904761904762,
      "grad_norm": 0.2516677851919719,
      "learning_rate": 4.747474747474748e-06,
      "loss": 1.1738,
      "step": 58
    },
    {
      "epoch": 2.8095238095238093,
      "grad_norm": 0.25703969553779876,
      "learning_rate": 4.646464646464647e-06,
      "loss": 1.1219,
      "step": 59
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.2771120831417692,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 1.1897,
      "step": 60
    },
    {
      "epoch": 2.9047619047619047,
      "grad_norm": 0.3008836565157165,
      "learning_rate": 4.444444444444444e-06,
      "loss": 1.2315,
      "step": 61
    },
    {
      "epoch": 2.9523809523809526,
      "grad_norm": 0.29790533918875145,
      "learning_rate": 4.343434343434344e-06,
      "loss": 1.2526,
      "step": 62
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.28406351295636223,
      "learning_rate": 4.242424242424243e-06,
      "loss": 1.2434,
      "step": 63
    },
    {
      "epoch": 3.0476190476190474,
      "grad_norm": 0.25871244869366494,
      "learning_rate": 4.141414141414142e-06,
      "loss": 1.194,
      "step": 64
    },
    {
      "epoch": 3.0952380952380953,
      "grad_norm": 0.2379858174426084,
      "learning_rate": 4.04040404040404e-06,
      "loss": 1.1213,
      "step": 65
    },
    {
      "epoch": 3.142857142857143,
      "grad_norm": 0.24756050709789792,
      "learning_rate": 3.93939393939394e-06,
      "loss": 1.1504,
      "step": 66
    },
    {
      "epoch": 3.1904761904761907,
      "grad_norm": 0.3038852476118342,
      "learning_rate": 3.8383838383838385e-06,
      "loss": 1.1873,
      "step": 67
    },
    {
      "epoch": 3.238095238095238,
      "grad_norm": 0.26678814053612043,
      "learning_rate": 3.737373737373738e-06,
      "loss": 1.1745,
      "step": 68
    },
    {
      "epoch": 3.2857142857142856,
      "grad_norm": 0.2622502936946242,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 1.183,
      "step": 69
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.24734711135761614,
      "learning_rate": 3.5353535353535356e-06,
      "loss": 1.2031,
      "step": 70
    },
    {
      "epoch": 3.380952380952381,
      "grad_norm": 0.2784016904597275,
      "learning_rate": 3.4343434343434347e-06,
      "loss": 1.1921,
      "step": 71
    },
    {
      "epoch": 3.4285714285714284,
      "grad_norm": 0.2527842539604257,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.2118,
      "step": 72
    },
    {
      "epoch": 3.4761904761904763,
      "grad_norm": 0.2808863675491137,
      "learning_rate": 3.232323232323233e-06,
      "loss": 1.2681,
      "step": 73
    },
    {
      "epoch": 3.5238095238095237,
      "grad_norm": 0.2709284949017584,
      "learning_rate": 3.131313131313132e-06,
      "loss": 1.2303,
      "step": 74
    },
    {
      "epoch": 3.571428571428571,
      "grad_norm": 0.24579184853323682,
      "learning_rate": 3.0303030303030305e-06,
      "loss": 1.1675,
      "step": 75
    },
    {
      "epoch": 3.619047619047619,
      "grad_norm": 0.2567760564484168,
      "learning_rate": 2.9292929292929295e-06,
      "loss": 1.1281,
      "step": 76
    },
    {
      "epoch": 3.6666666666666665,
      "grad_norm": 0.28004652650623546,
      "learning_rate": 2.8282828282828286e-06,
      "loss": 1.2511,
      "step": 77
    },
    {
      "epoch": 3.7142857142857144,
      "grad_norm": 0.25035015207810946,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 1.1477,
      "step": 78
    },
    {
      "epoch": 3.761904761904762,
      "grad_norm": 0.23986994231881037,
      "learning_rate": 2.6262626262626267e-06,
      "loss": 1.2483,
      "step": 79
    },
    {
      "epoch": 3.8095238095238093,
      "grad_norm": 0.2514435710438361,
      "learning_rate": 2.5252525252525258e-06,
      "loss": 1.1493,
      "step": 80
    },
    {
      "epoch": 3.857142857142857,
      "grad_norm": 0.2663207237347971,
      "learning_rate": 2.4242424242424244e-06,
      "loss": 1.1941,
      "step": 81
    },
    {
      "epoch": 3.9047619047619047,
      "grad_norm": 0.2555836186438156,
      "learning_rate": 2.3232323232323234e-06,
      "loss": 1.2208,
      "step": 82
    },
    {
      "epoch": 3.9523809523809526,
      "grad_norm": 0.23688421879368227,
      "learning_rate": 2.222222222222222e-06,
      "loss": 1.126,
      "step": 83
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.25629204491071833,
      "learning_rate": 2.1212121212121216e-06,
      "loss": 1.2274,
      "step": 84
    },
    {
      "epoch": 4.0476190476190474,
      "grad_norm": 0.23982760230871947,
      "learning_rate": 2.02020202020202e-06,
      "loss": 1.1455,
      "step": 85
    },
    {
      "epoch": 4.095238095238095,
      "grad_norm": 0.216069064199628,
      "learning_rate": 1.9191919191919192e-06,
      "loss": 1.1537,
      "step": 86
    },
    {
      "epoch": 4.142857142857143,
      "grad_norm": 0.25496395263662563,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 1.2443,
      "step": 87
    },
    {
      "epoch": 4.190476190476191,
      "grad_norm": 0.2620044850423424,
      "learning_rate": 1.7171717171717173e-06,
      "loss": 1.236,
      "step": 88
    },
    {
      "epoch": 4.238095238095238,
      "grad_norm": 0.25242976204202006,
      "learning_rate": 1.6161616161616164e-06,
      "loss": 1.2011,
      "step": 89
    },
    {
      "epoch": 4.285714285714286,
      "grad_norm": 0.2414833014306595,
      "learning_rate": 1.5151515151515152e-06,
      "loss": 1.1781,
      "step": 90
    },
    {
      "epoch": 4.333333333333333,
      "grad_norm": 0.23581982450333464,
      "learning_rate": 1.4141414141414143e-06,
      "loss": 1.1297,
      "step": 91
    },
    {
      "epoch": 4.380952380952381,
      "grad_norm": 0.23055696388945487,
      "learning_rate": 1.3131313131313134e-06,
      "loss": 1.1346,
      "step": 92
    },
    {
      "epoch": 4.428571428571429,
      "grad_norm": 0.2509888294983581,
      "learning_rate": 1.2121212121212122e-06,
      "loss": 1.1492,
      "step": 93
    },
    {
      "epoch": 4.476190476190476,
      "grad_norm": 0.24544882675629903,
      "learning_rate": 1.111111111111111e-06,
      "loss": 1.1536,
      "step": 94
    },
    {
      "epoch": 4.523809523809524,
      "grad_norm": 0.24608695262616462,
      "learning_rate": 1.01010101010101e-06,
      "loss": 1.1878,
      "step": 95
    },
    {
      "epoch": 4.571428571428571,
      "grad_norm": 0.23650412613326433,
      "learning_rate": 9.090909090909091e-07,
      "loss": 1.1343,
      "step": 96
    },
    {
      "epoch": 4.619047619047619,
      "grad_norm": 0.24076304542724297,
      "learning_rate": 8.080808080808082e-07,
      "loss": 1.1248,
      "step": 97
    },
    {
      "epoch": 4.666666666666667,
      "grad_norm": 0.22064086123289745,
      "learning_rate": 7.070707070707071e-07,
      "loss": 1.1448,
      "step": 98
    },
    {
      "epoch": 4.714285714285714,
      "grad_norm": 0.23402063351460475,
      "learning_rate": 6.060606060606061e-07,
      "loss": 1.1709,
      "step": 99
    },
    {
      "epoch": 4.761904761904762,
      "grad_norm": 0.2583142296284132,
      "learning_rate": 5.05050505050505e-07,
      "loss": 1.194,
      "step": 100
    },
    {
      "epoch": 4.809523809523809,
      "grad_norm": 0.23970304773690995,
      "learning_rate": 4.040404040404041e-07,
      "loss": 1.1636,
      "step": 101
    },
    {
      "epoch": 4.857142857142857,
      "grad_norm": 0.24747127695363272,
      "learning_rate": 3.0303030303030305e-07,
      "loss": 1.1643,
      "step": 102
    },
    {
      "epoch": 4.904761904761905,
      "grad_norm": 0.2419422150091483,
      "learning_rate": 2.0202020202020205e-07,
      "loss": 1.1896,
      "step": 103
    },
    {
      "epoch": 4.9523809523809526,
      "grad_norm": 0.2629807724519166,
      "learning_rate": 1.0101010101010103e-07,
      "loss": 1.2151,
      "step": 104
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.25920794740624253,
      "learning_rate": 0.0,
      "loss": 1.2562,
      "step": 105
    },
    {
      "epoch": 5.0,
      "step": 105,
      "total_flos": 47859357450240.0,
      "train_loss": 0.0,
      "train_runtime": 0.7265,
      "train_samples_per_second": 2271.007,
      "train_steps_per_second": 144.519
    }
  ],
  "logging_steps": 1,
  "max_steps": 105,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 47859357450240.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}