{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9969512195121951,
  "eval_steps": 500,
  "global_step": 109,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009146341463414634,
      "grad_norm": 40.05127716064453,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 5.1282,
      "step": 1
    },
    {
      "epoch": 0.018292682926829267,
      "grad_norm": 39.01039505004883,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 5.0586,
      "step": 2
    },
    {
      "epoch": 0.027439024390243903,
      "grad_norm": 40.20766067504883,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 5.0311,
      "step": 3
    },
    {
      "epoch": 0.036585365853658534,
      "grad_norm": 38.70350646972656,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 5.1598,
      "step": 4
    },
    {
      "epoch": 0.04573170731707317,
      "grad_norm": 39.230979919433594,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 5.0812,
      "step": 5
    },
    {
      "epoch": 0.054878048780487805,
      "grad_norm": 39.45293045043945,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 5.0841,
      "step": 6
    },
    {
      "epoch": 0.06402439024390244,
      "grad_norm": 38.92170333862305,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 5.022,
      "step": 7
    },
    {
      "epoch": 0.07317073170731707,
      "grad_norm": 38.932369232177734,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 5.0876,
      "step": 8
    },
    {
      "epoch": 0.08231707317073171,
      "grad_norm": 39.60245132446289,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 5.0798,
      "step": 9
    },
    {
      "epoch": 0.09146341463414634,
      "grad_norm": 39.53607177734375,
      "learning_rate": 5.000000000000001e-07,
      "loss": 5.0105,
      "step": 10
    },
    {
      "epoch": 0.10060975609756098,
      "grad_norm": 39.50700378417969,
      "learning_rate": 5.5e-07,
      "loss": 4.9951,
      "step": 11
    },
    {
      "epoch": 0.10975609756097561,
      "grad_norm": 39.52376174926758,
      "learning_rate": 6.000000000000001e-07,
      "loss": 4.9163,
      "step": 12
    },
    {
      "epoch": 0.11890243902439024,
      "grad_norm": 39.15214157104492,
      "learning_rate": 6.5e-07,
      "loss": 4.9634,
      "step": 13
    },
    {
      "epoch": 0.12804878048780488,
      "grad_norm": 37.795066833496094,
      "learning_rate": 7.000000000000001e-07,
      "loss": 4.819,
      "step": 14
    },
    {
      "epoch": 0.13719512195121952,
      "grad_norm": 38.23014450073242,
      "learning_rate": 7.5e-07,
      "loss": 4.8756,
      "step": 15
    },
    {
      "epoch": 0.14634146341463414,
      "grad_norm": 38.57551574707031,
      "learning_rate": 8.000000000000001e-07,
      "loss": 4.81,
      "step": 16
    },
    {
      "epoch": 0.15548780487804878,
      "grad_norm": 36.06121063232422,
      "learning_rate": 8.500000000000001e-07,
      "loss": 4.7901,
      "step": 17
    },
    {
      "epoch": 0.16463414634146342,
      "grad_norm": 34.38008117675781,
      "learning_rate": 9.000000000000001e-07,
      "loss": 4.5775,
      "step": 18
    },
    {
      "epoch": 0.17378048780487804,
      "grad_norm": 32.60890579223633,
      "learning_rate": 9.500000000000001e-07,
      "loss": 4.3737,
      "step": 19
    },
    {
      "epoch": 0.18292682926829268,
      "grad_norm": 31.983110427856445,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 4.3773,
      "step": 20
    },
    {
      "epoch": 0.19207317073170732,
      "grad_norm": 27.69571876525879,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 4.1276,
      "step": 21
    },
    {
      "epoch": 0.20121951219512196,
      "grad_norm": 26.542314529418945,
      "learning_rate": 1.1e-06,
      "loss": 4.0641,
      "step": 22
    },
    {
      "epoch": 0.21036585365853658,
      "grad_norm": 23.26603126525879,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 4.0197,
      "step": 23
    },
    {
      "epoch": 0.21951219512195122,
      "grad_norm": 21.04385757446289,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 4.0179,
      "step": 24
    },
    {
      "epoch": 0.22865853658536586,
      "grad_norm": 19.790103912353516,
      "learning_rate": 1.25e-06,
      "loss": 3.8334,
      "step": 25
    },
    {
      "epoch": 0.23780487804878048,
      "grad_norm": 18.2396183013916,
      "learning_rate": 1.3e-06,
      "loss": 3.7027,
      "step": 26
    },
    {
      "epoch": 0.24695121951219512,
      "grad_norm": 18.725860595703125,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 3.7268,
      "step": 27
    },
    {
      "epoch": 0.25609756097560976,
      "grad_norm": 18.91561508178711,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 3.52,
      "step": 28
    },
    {
      "epoch": 0.2652439024390244,
      "grad_norm": 18.196651458740234,
      "learning_rate": 1.45e-06,
      "loss": 3.4765,
      "step": 29
    },
    {
      "epoch": 0.27439024390243905,
      "grad_norm": 17.778606414794922,
      "learning_rate": 1.5e-06,
      "loss": 3.3573,
      "step": 30
    },
    {
      "epoch": 0.28353658536585363,
      "grad_norm": 16.23012924194336,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 3.2783,
      "step": 31
    },
    {
      "epoch": 0.2926829268292683,
      "grad_norm": 15.836565017700195,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 3.2319,
      "step": 32
    },
    {
      "epoch": 0.3018292682926829,
      "grad_norm": 11.919289588928223,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 3.1345,
      "step": 33
    },
    {
      "epoch": 0.31097560975609756,
      "grad_norm": 11.086843490600586,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 3.1153,
      "step": 34
    },
    {
      "epoch": 0.3201219512195122,
      "grad_norm": 7.563486576080322,
      "learning_rate": 1.75e-06,
      "loss": 2.9784,
      "step": 35
    },
    {
      "epoch": 0.32926829268292684,
      "grad_norm": 7.60545539855957,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 2.8568,
      "step": 36
    },
    {
      "epoch": 0.3384146341463415,
      "grad_norm": 7.071218013763428,
      "learning_rate": 1.85e-06,
      "loss": 2.8879,
      "step": 37
    },
    {
      "epoch": 0.3475609756097561,
      "grad_norm": 8.200672149658203,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 2.7437,
      "step": 38
    },
    {
      "epoch": 0.3567073170731707,
      "grad_norm": 12.079374313354492,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 2.7589,
      "step": 39
    },
    {
      "epoch": 0.36585365853658536,
      "grad_norm": 12.21938705444336,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.7098,
      "step": 40
    },
    {
      "epoch": 0.375,
      "grad_norm": 10.224228858947754,
      "learning_rate": 2.05e-06,
      "loss": 2.6803,
      "step": 41
    },
    {
      "epoch": 0.38414634146341464,
      "grad_norm": 10.054616928100586,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 2.4658,
      "step": 42
    },
    {
      "epoch": 0.3932926829268293,
      "grad_norm": 8.074049949645996,
      "learning_rate": 2.15e-06,
      "loss": 2.6341,
      "step": 43
    },
    {
      "epoch": 0.4024390243902439,
      "grad_norm": 5.721987724304199,
      "learning_rate": 2.2e-06,
      "loss": 2.3848,
      "step": 44
    },
    {
      "epoch": 0.4115853658536585,
      "grad_norm": 4.646566390991211,
      "learning_rate": 2.25e-06,
      "loss": 2.4323,
      "step": 45
    },
    {
      "epoch": 0.42073170731707316,
      "grad_norm": 4.591104984283447,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 2.4022,
      "step": 46
    },
    {
      "epoch": 0.4298780487804878,
      "grad_norm": 4.822715759277344,
      "learning_rate": 2.35e-06,
      "loss": 2.2768,
      "step": 47
    },
    {
      "epoch": 0.43902439024390244,
      "grad_norm": 5.176568984985352,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 2.281,
      "step": 48
    },
    {
      "epoch": 0.4481707317073171,
      "grad_norm": 4.731242656707764,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 2.235,
      "step": 49
    },
    {
      "epoch": 0.4573170731707317,
      "grad_norm": 4.6343865394592285,
      "learning_rate": 2.5e-06,
      "loss": 2.1465,
      "step": 50
    },
    {
      "epoch": 0.46646341463414637,
      "grad_norm": 4.669382095336914,
      "learning_rate": 2.55e-06,
      "loss": 2.0969,
      "step": 51
    },
    {
      "epoch": 0.47560975609756095,
      "grad_norm": 4.207769870758057,
      "learning_rate": 2.6e-06,
      "loss": 2.0308,
      "step": 52
    },
    {
      "epoch": 0.4847560975609756,
      "grad_norm": 5.222470760345459,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 1.9445,
      "step": 53
    },
    {
      "epoch": 0.49390243902439024,
      "grad_norm": 5.10925817489624,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 1.7763,
      "step": 54
    },
    {
      "epoch": 0.5030487804878049,
      "grad_norm": 4.8151044845581055,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 1.7661,
      "step": 55
    },
    {
      "epoch": 0.5121951219512195,
      "grad_norm": 6.155700206756592,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 1.6665,
      "step": 56
    },
    {
      "epoch": 0.5213414634146342,
      "grad_norm": 4.719021320343018,
      "learning_rate": 2.85e-06,
      "loss": 1.5532,
      "step": 57
    },
    {
      "epoch": 0.5304878048780488,
      "grad_norm": 4.591799259185791,
      "learning_rate": 2.9e-06,
      "loss": 1.5244,
      "step": 58
    },
    {
      "epoch": 0.5396341463414634,
      "grad_norm": 5.483795642852783,
      "learning_rate": 2.95e-06,
      "loss": 1.3816,
      "step": 59
    },
    {
      "epoch": 0.5487804878048781,
      "grad_norm": 4.32553768157959,
      "learning_rate": 3e-06,
      "loss": 1.4268,
      "step": 60
    },
    {
      "epoch": 0.5579268292682927,
      "grad_norm": 8.296231269836426,
      "learning_rate": 3.05e-06,
      "loss": 1.2887,
      "step": 61
    },
    {
      "epoch": 0.5670731707317073,
      "grad_norm": 5.07594108581543,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 1.228,
      "step": 62
    },
    {
      "epoch": 0.5762195121951219,
      "grad_norm": 8.427435874938965,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 1.1724,
      "step": 63
    },
    {
      "epoch": 0.5853658536585366,
      "grad_norm": 22.45092010498047,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 1.0871,
      "step": 64
    },
    {
      "epoch": 0.5945121951219512,
      "grad_norm": 20.67412567138672,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 1.0108,
      "step": 65
    },
    {
      "epoch": 0.6036585365853658,
      "grad_norm": 4.921634674072266,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.9775,
      "step": 66
    },
    {
      "epoch": 0.6128048780487805,
      "grad_norm": 4.477286338806152,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.9554,
      "step": 67
    },
    {
      "epoch": 0.6219512195121951,
      "grad_norm": 8.190194129943848,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.8583,
      "step": 68
    },
    {
      "epoch": 0.6310975609756098,
      "grad_norm": 29.21201515197754,
      "learning_rate": 3.45e-06,
      "loss": 0.8499,
      "step": 69
    },
    {
      "epoch": 0.6402439024390244,
      "grad_norm": 33.81047439575195,
      "learning_rate": 3.5e-06,
      "loss": 0.858,
      "step": 70
    },
    {
      "epoch": 0.649390243902439,
      "grad_norm": 3.5125606060028076,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.7227,
      "step": 71
    },
    {
      "epoch": 0.6585365853658537,
      "grad_norm": 18.493423461914062,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.7447,
      "step": 72
    },
    {
      "epoch": 0.6676829268292683,
      "grad_norm": 24.923927307128906,
      "learning_rate": 3.65e-06,
      "loss": 0.8423,
      "step": 73
    },
    {
      "epoch": 0.676829268292683,
      "grad_norm": 9.870631217956543,
      "learning_rate": 3.7e-06,
      "loss": 0.6934,
      "step": 74
    },
    {
      "epoch": 0.6859756097560976,
      "grad_norm": 20.598569869995117,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.7005,
      "step": 75
    },
    {
      "epoch": 0.6951219512195121,
      "grad_norm": 30.662466049194336,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.6226,
      "step": 76
    },
    {
      "epoch": 0.7042682926829268,
      "grad_norm": 28.930774688720703,
      "learning_rate": 3.85e-06,
      "loss": 0.6357,
      "step": 77
    },
    {
      "epoch": 0.7134146341463414,
      "grad_norm": 7.140467166900635,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.6129,
      "step": 78
    },
    {
      "epoch": 0.7225609756097561,
      "grad_norm": 6.322911739349365,
      "learning_rate": 3.95e-06,
      "loss": 0.6086,
      "step": 79
    },
    {
      "epoch": 0.7317073170731707,
      "grad_norm": 5.404141426086426,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.5986,
      "step": 80
    },
    {
      "epoch": 0.7408536585365854,
      "grad_norm": 24.445228576660156,
      "learning_rate": 4.05e-06,
      "loss": 0.5932,
      "step": 81
    },
    {
      "epoch": 0.75,
      "grad_norm": 14.275381088256836,
      "learning_rate": 4.1e-06,
      "loss": 0.5286,
      "step": 82
    },
    {
      "epoch": 0.7591463414634146,
      "grad_norm": 9.77132511138916,
      "learning_rate": 4.15e-06,
      "loss": 0.4814,
      "step": 83
    },
    {
      "epoch": 0.7682926829268293,
      "grad_norm": 11.043930053710938,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.4953,
      "step": 84
    },
    {
      "epoch": 0.7774390243902439,
      "grad_norm": 3.1333775520324707,
      "learning_rate": 4.25e-06,
      "loss": 0.4794,
      "step": 85
    },
    {
      "epoch": 0.7865853658536586,
      "grad_norm": 9.50448989868164,
      "learning_rate": 4.3e-06,
      "loss": 0.4451,
      "step": 86
    },
    {
      "epoch": 0.7957317073170732,
      "grad_norm": 5.867074489593506,
      "learning_rate": 4.350000000000001e-06,
      "loss": 0.4224,
      "step": 87
    },
    {
      "epoch": 0.8048780487804879,
      "grad_norm": 12.556106567382812,
      "learning_rate": 4.4e-06,
      "loss": 0.4224,
      "step": 88
    },
    {
      "epoch": 0.8140243902439024,
      "grad_norm": 7.916622638702393,
      "learning_rate": 4.450000000000001e-06,
      "loss": 0.4091,
      "step": 89
    },
    {
      "epoch": 0.823170731707317,
      "grad_norm": 2.970932722091675,
      "learning_rate": 4.5e-06,
      "loss": 0.4181,
      "step": 90
    },
    {
      "epoch": 0.8323170731707317,
      "grad_norm": 17.468870162963867,
      "learning_rate": 4.5500000000000005e-06,
      "loss": 0.4031,
      "step": 91
    },
    {
      "epoch": 0.8414634146341463,
      "grad_norm": 15.861083984375,
      "learning_rate": 4.600000000000001e-06,
      "loss": 0.3604,
      "step": 92
    },
    {
      "epoch": 0.850609756097561,
      "grad_norm": 6.715958118438721,
      "learning_rate": 4.65e-06,
      "loss": 0.3489,
      "step": 93
    },
    {
      "epoch": 0.8597560975609756,
      "grad_norm": 5.439844608306885,
      "learning_rate": 4.7e-06,
      "loss": 0.3339,
      "step": 94
    },
    {
      "epoch": 0.8689024390243902,
      "grad_norm": 4.650434494018555,
      "learning_rate": 4.75e-06,
      "loss": 0.3189,
      "step": 95
    },
    {
      "epoch": 0.8780487804878049,
      "grad_norm": 15.319528579711914,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.3347,
      "step": 96
    },
    {
      "epoch": 0.8871951219512195,
      "grad_norm": 5.151925563812256,
      "learning_rate": 4.85e-06,
      "loss": 0.3043,
      "step": 97
    },
    {
      "epoch": 0.8963414634146342,
      "grad_norm": 6.351178169250488,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.2939,
      "step": 98
    },
    {
      "epoch": 0.9054878048780488,
      "grad_norm": 3.942911148071289,
      "learning_rate": 4.95e-06,
      "loss": 0.2887,
      "step": 99
    },
    {
      "epoch": 0.9146341463414634,
      "grad_norm": 3.0885493755340576,
      "learning_rate": 5e-06,
      "loss": 0.2992,
      "step": 100
    },
    {
      "epoch": 0.9237804878048781,
      "grad_norm": 7.023274898529053,
      "learning_rate": 4.999959803423605e-06,
      "loss": 0.2607,
      "step": 101
    },
    {
      "epoch": 0.9329268292682927,
      "grad_norm": 8.774216651916504,
      "learning_rate": 4.9998392149870315e-06,
      "loss": 0.2674,
      "step": 102
    },
    {
      "epoch": 0.9420731707317073,
      "grad_norm": 3.5439791679382324,
      "learning_rate": 4.999638238568072e-06,
      "loss": 0.2602,
      "step": 103
    },
    {
      "epoch": 0.9512195121951219,
      "grad_norm": 7.669381618499756,
      "learning_rate": 4.999356880629579e-06,
      "loss": 0.2718,
      "step": 104
    },
    {
      "epoch": 0.9603658536585366,
      "grad_norm": 6.9407854080200195,
      "learning_rate": 4.998995150219252e-06,
      "loss": 0.2494,
      "step": 105
    },
    {
      "epoch": 0.9695121951219512,
      "grad_norm": 12.144411087036133,
      "learning_rate": 4.998553058969352e-06,
      "loss": 0.2297,
      "step": 106
    },
    {
      "epoch": 0.9786585365853658,
      "grad_norm": 6.956138610839844,
      "learning_rate": 4.998030621096322e-06,
      "loss": 0.2386,
      "step": 107
    },
    {
      "epoch": 0.9878048780487805,
      "grad_norm": 8.304037094116211,
      "learning_rate": 4.997427853400333e-06,
      "loss": 0.23,
      "step": 108
    },
    {
      "epoch": 0.9969512195121951,
      "grad_norm": 7.031365394592285,
      "learning_rate": 4.996744775264743e-06,
      "loss": 0.2346,
      "step": 109
    }
  ],
  "logging_steps": 1,
  "max_steps": 654,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 109,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.308236123527971e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}