{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 84,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.023809523809523808,
      "grad_norm": 26.742956161499023,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 4.1563,
      "step": 1
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 26.336389541625977,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 4.0633,
      "step": 2
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 28.836008071899414,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 4.3575,
      "step": 3
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 27.459413528442383,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 4.1943,
      "step": 4
    },
    {
      "epoch": 0.11904761904761904,
      "grad_norm": 27.914960861206055,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 4.3336,
      "step": 5
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 27.47397232055664,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 4.2354,
      "step": 6
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 26.212989807128906,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 4.1001,
      "step": 7
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 26.80431365966797,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 4.1827,
      "step": 8
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 27.641605377197266,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 4.2596,
      "step": 9
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 27.783071517944336,
      "learning_rate": 5.000000000000001e-07,
      "loss": 4.2694,
      "step": 10
    },
    {
      "epoch": 0.2619047619047619,
      "grad_norm": 26.553335189819336,
      "learning_rate": 5.5e-07,
      "loss": 4.0739,
      "step": 11
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 26.77140998840332,
      "learning_rate": 6.000000000000001e-07,
      "loss": 4.1049,
      "step": 12
    },
    {
      "epoch": 0.30952380952380953,
      "grad_norm": 25.07087516784668,
      "learning_rate": 6.5e-07,
      "loss": 3.8982,
      "step": 13
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 25.834062576293945,
      "learning_rate": 7.000000000000001e-07,
      "loss": 4.0768,
      "step": 14
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 25.00474739074707,
      "learning_rate": 7.5e-07,
      "loss": 4.0104,
      "step": 15
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 23.692975997924805,
      "learning_rate": 8.000000000000001e-07,
      "loss": 3.8469,
      "step": 16
    },
    {
      "epoch": 0.40476190476190477,
      "grad_norm": 22.197919845581055,
      "learning_rate": 8.500000000000001e-07,
      "loss": 3.7738,
      "step": 17
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 20.92680549621582,
      "learning_rate": 9.000000000000001e-07,
      "loss": 3.6514,
      "step": 18
    },
    {
      "epoch": 0.4523809523809524,
      "grad_norm": 20.251178741455078,
      "learning_rate": 9.500000000000001e-07,
      "loss": 3.6739,
      "step": 19
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 17.55536460876465,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 3.2675,
      "step": 20
    },
    {
      "epoch": 0.5,
      "grad_norm": 17.066797256469727,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 3.4232,
      "step": 21
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 16.1475887298584,
      "learning_rate": 1.1e-06,
      "loss": 3.1988,
      "step": 22
    },
    {
      "epoch": 0.5476190476190477,
      "grad_norm": 15.61026382446289,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 3.1338,
      "step": 23
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 15.409480094909668,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 2.9836,
      "step": 24
    },
    {
      "epoch": 0.5952380952380952,
      "grad_norm": 15.391901969909668,
      "learning_rate": 1.25e-06,
      "loss": 2.9064,
      "step": 25
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 16.92401885986328,
      "learning_rate": 1.3e-06,
      "loss": 2.906,
      "step": 26
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 17.880958557128906,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 2.702,
      "step": 27
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 18.114517211914062,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 2.4876,
      "step": 28
    },
    {
      "epoch": 0.6904761904761905,
      "grad_norm": 17.608840942382812,
      "learning_rate": 1.45e-06,
      "loss": 2.2996,
      "step": 29
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 17.055673599243164,
      "learning_rate": 1.5e-06,
      "loss": 2.2709,
      "step": 30
    },
    {
      "epoch": 0.7380952380952381,
      "grad_norm": 14.92151927947998,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 2.0406,
      "step": 31
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 13.657073020935059,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 1.8564,
      "step": 32
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 13.274576187133789,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 1.7382,
      "step": 33
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 13.728348731994629,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 1.6629,
      "step": 34
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 13.521151542663574,
      "learning_rate": 1.75e-06,
      "loss": 1.5301,
      "step": 35
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 13.709525108337402,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 1.4122,
      "step": 36
    },
    {
      "epoch": 0.8809523809523809,
      "grad_norm": 12.587928771972656,
      "learning_rate": 1.85e-06,
      "loss": 1.2014,
      "step": 37
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 13.494888305664062,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 1.1793,
      "step": 38
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 13.417922019958496,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 1.0282,
      "step": 39
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 12.754359245300293,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.8525,
      "step": 40
    },
    {
      "epoch": 0.9761904761904762,
      "grad_norm": 12.766407012939453,
      "learning_rate": 2.05e-06,
      "loss": 0.7043,
      "step": 41
    },
    {
      "epoch": 1.0,
      "grad_norm": 11.440421104431152,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.6245,
      "step": 42
    },
    {
      "epoch": 1.0238095238095237,
      "grad_norm": 9.672205924987793,
      "learning_rate": 2.15e-06,
      "loss": 0.4768,
      "step": 43
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 7.8501057624816895,
      "learning_rate": 2.2e-06,
      "loss": 0.3679,
      "step": 44
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": 6.751816749572754,
      "learning_rate": 2.25e-06,
      "loss": 0.2708,
      "step": 45
    },
    {
      "epoch": 1.0952380952380953,
      "grad_norm": 5.267884731292725,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.2143,
      "step": 46
    },
    {
      "epoch": 1.119047619047619,
      "grad_norm": 3.251101016998291,
      "learning_rate": 2.35e-06,
      "loss": 0.1759,
      "step": 47
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 2.585360050201416,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.1855,
      "step": 48
    },
    {
      "epoch": 1.1666666666666667,
      "grad_norm": 2.0107483863830566,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.1251,
      "step": 49
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 1.941689133644104,
      "learning_rate": 2.5e-06,
      "loss": 0.1441,
      "step": 50
    },
    {
      "epoch": 1.2142857142857142,
      "grad_norm": 1.4036344289779663,
      "learning_rate": 2.55e-06,
      "loss": 0.1097,
      "step": 51
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 1.2856179475784302,
      "learning_rate": 2.6e-06,
      "loss": 0.1303,
      "step": 52
    },
    {
      "epoch": 1.2619047619047619,
      "grad_norm": 1.3184994459152222,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.1021,
      "step": 53
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 1.144294261932373,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.115,
      "step": 54
    },
    {
      "epoch": 1.3095238095238095,
      "grad_norm": 0.9276831150054932,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.1028,
      "step": 55
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.9152742028236389,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.0979,
      "step": 56
    },
    {
      "epoch": 1.3571428571428572,
      "grad_norm": 0.8525308966636658,
      "learning_rate": 2.85e-06,
      "loss": 0.0908,
      "step": 57
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 0.9806348085403442,
      "learning_rate": 2.9e-06,
      "loss": 0.0817,
      "step": 58
    },
    {
      "epoch": 1.4047619047619047,
      "grad_norm": 0.606792151927948,
      "learning_rate": 2.95e-06,
      "loss": 0.0904,
      "step": 59
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.7274054884910583,
      "learning_rate": 3e-06,
      "loss": 0.0811,
      "step": 60
    },
    {
      "epoch": 1.4523809523809523,
      "grad_norm": 1.0523946285247803,
      "learning_rate": 3.05e-06,
      "loss": 0.0881,
      "step": 61
    },
    {
      "epoch": 1.4761904761904763,
      "grad_norm": 0.5840473175048828,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.0848,
      "step": 62
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.7410831451416016,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.0788,
      "step": 63
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 0.828996479511261,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.0866,
      "step": 64
    },
    {
      "epoch": 1.5476190476190477,
      "grad_norm": 0.7505109310150146,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.076,
      "step": 65
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.9672189354896545,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.0765,
      "step": 66
    },
    {
      "epoch": 1.5952380952380953,
      "grad_norm": 0.5925746560096741,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.0706,
      "step": 67
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 0.6671133637428284,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.0713,
      "step": 68
    },
    {
      "epoch": 1.6428571428571428,
      "grad_norm": 0.5542609095573425,
      "learning_rate": 3.45e-06,
      "loss": 0.0715,
      "step": 69
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.541200578212738,
      "learning_rate": 3.5e-06,
      "loss": 0.0701,
      "step": 70
    },
    {
      "epoch": 1.6904761904761905,
      "grad_norm": 0.4222320020198822,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.0669,
      "step": 71
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.717410147190094,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.0782,
      "step": 72
    },
    {
      "epoch": 1.7380952380952381,
      "grad_norm": 0.6776471734046936,
      "learning_rate": 3.65e-06,
      "loss": 0.0695,
      "step": 73
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 0.5480474829673767,
      "learning_rate": 3.7e-06,
      "loss": 0.0662,
      "step": 74
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 0.4779343605041504,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0743,
      "step": 75
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 0.43138471245765686,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.0666,
      "step": 76
    },
    {
      "epoch": 1.8333333333333335,
      "grad_norm": 0.6058762669563293,
      "learning_rate": 3.85e-06,
      "loss": 0.0696,
      "step": 77
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 1.3352755308151245,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.0891,
      "step": 78
    },
    {
      "epoch": 1.880952380952381,
      "grad_norm": 0.5319089293479919,
      "learning_rate": 3.95e-06,
      "loss": 0.0617,
      "step": 79
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.5629184246063232,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0622,
      "step": 80
    },
    {
      "epoch": 1.9285714285714286,
      "grad_norm": 0.37953704595565796,
      "learning_rate": 4.05e-06,
      "loss": 0.0676,
      "step": 81
    },
    {
      "epoch": 1.9523809523809523,
      "grad_norm": 0.37576770782470703,
      "learning_rate": 4.1e-06,
      "loss": 0.0719,
      "step": 82
    },
    {
      "epoch": 1.9761904761904763,
      "grad_norm": 0.4720636010169983,
      "learning_rate": 4.15e-06,
      "loss": 0.0662,
      "step": 83
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.4793304204940796,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.0664,
      "step": 84
    }
  ],
  "logging_steps": 1,
  "max_steps": 252,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 42,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.8817201233670963e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}