{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.967741935483871,
  "eval_steps": 500,
  "global_step": 82,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024193548387096774,
      "grad_norm": 33.12635803222656,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 2.4997,
      "step": 1
    },
    {
      "epoch": 0.04838709677419355,
      "grad_norm": 32.004058837890625,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 2.4277,
      "step": 2
    },
    {
      "epoch": 0.07258064516129033,
      "grad_norm": 34.234554290771484,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 2.6112,
      "step": 3
    },
    {
      "epoch": 0.0967741935483871,
      "grad_norm": 32.96908187866211,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 2.5017,
      "step": 4
    },
    {
      "epoch": 0.12096774193548387,
      "grad_norm": 35.06013870239258,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 2.6115,
      "step": 5
    },
    {
      "epoch": 0.14516129032258066,
      "grad_norm": 33.552955627441406,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 2.5234,
      "step": 6
    },
    {
      "epoch": 0.1693548387096774,
      "grad_norm": 32.13972091674805,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 2.4724,
      "step": 7
    },
    {
      "epoch": 0.1935483870967742,
      "grad_norm": 32.68510055541992,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 2.4925,
      "step": 8
    },
    {
      "epoch": 0.21774193548387097,
      "grad_norm": 32.32320785522461,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 2.4983,
      "step": 9
    },
    {
      "epoch": 0.24193548387096775,
      "grad_norm": 32.311553955078125,
      "learning_rate": 5.000000000000001e-07,
      "loss": 2.4833,
      "step": 10
    },
    {
      "epoch": 0.2661290322580645,
      "grad_norm": 31.869163513183594,
      "learning_rate": 5.5e-07,
      "loss": 2.4362,
      "step": 11
    },
    {
      "epoch": 0.2903225806451613,
      "grad_norm": 31.329313278198242,
      "learning_rate": 6.000000000000001e-07,
      "loss": 2.4228,
      "step": 12
    },
    {
      "epoch": 0.31451612903225806,
      "grad_norm": 29.42159652709961,
      "learning_rate": 6.5e-07,
      "loss": 2.2499,
      "step": 13
    },
    {
      "epoch": 0.3387096774193548,
      "grad_norm": 31.27863311767578,
      "learning_rate": 7.000000000000001e-07,
      "loss": 2.3354,
      "step": 14
    },
    {
      "epoch": 0.3629032258064516,
      "grad_norm": 31.095605850219727,
      "learning_rate": 7.5e-07,
      "loss": 2.2723,
      "step": 15
    },
    {
      "epoch": 0.3870967741935484,
      "grad_norm": 30.90537452697754,
      "learning_rate": 8.000000000000001e-07,
      "loss": 2.2003,
      "step": 16
    },
    {
      "epoch": 0.4112903225806452,
      "grad_norm": 30.878215789794922,
      "learning_rate": 8.500000000000001e-07,
      "loss": 2.0797,
      "step": 17
    },
    {
      "epoch": 0.43548387096774194,
      "grad_norm": 32.37583541870117,
      "learning_rate": 9.000000000000001e-07,
      "loss": 1.9855,
      "step": 18
    },
    {
      "epoch": 0.4596774193548387,
      "grad_norm": 32.957889556884766,
      "learning_rate": 9.500000000000001e-07,
      "loss": 1.8497,
      "step": 19
    },
    {
      "epoch": 0.4838709677419355,
      "grad_norm": 33.7425537109375,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.7037,
      "step": 20
    },
    {
      "epoch": 0.5080645161290323,
      "grad_norm": 35.177791595458984,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 1.645,
      "step": 21
    },
    {
      "epoch": 0.532258064516129,
      "grad_norm": 34.37784957885742,
      "learning_rate": 1.1e-06,
      "loss": 1.4705,
      "step": 22
    },
    {
      "epoch": 0.5564516129032258,
      "grad_norm": 32.561283111572266,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 1.3819,
      "step": 23
    },
    {
      "epoch": 0.5806451612903226,
      "grad_norm": 28.166706085205078,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.1496,
      "step": 24
    },
    {
      "epoch": 0.6048387096774194,
      "grad_norm": 30.428386688232422,
      "learning_rate": 1.25e-06,
      "loss": 1.0998,
      "step": 25
    },
    {
      "epoch": 0.6290322580645161,
      "grad_norm": 34.153076171875,
      "learning_rate": 1.3e-06,
      "loss": 0.9278,
      "step": 26
    },
    {
      "epoch": 0.6532258064516129,
      "grad_norm": 39.16960906982422,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 0.7463,
      "step": 27
    },
    {
      "epoch": 0.6774193548387096,
      "grad_norm": 39.09505081176758,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.5676,
      "step": 28
    },
    {
      "epoch": 0.7016129032258065,
      "grad_norm": 38.89931869506836,
      "learning_rate": 1.45e-06,
      "loss": 0.4015,
      "step": 29
    },
    {
      "epoch": 0.7258064516129032,
      "grad_norm": 23.554725646972656,
      "learning_rate": 1.5e-06,
      "loss": 0.2364,
      "step": 30
    },
    {
      "epoch": 0.75,
      "grad_norm": 11.884359359741211,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 0.1429,
      "step": 31
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 5.657749176025391,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.136,
      "step": 32
    },
    {
      "epoch": 0.7983870967741935,
      "grad_norm": 3.42618465423584,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 0.0964,
      "step": 33
    },
    {
      "epoch": 0.8225806451612904,
      "grad_norm": 2.808098554611206,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.0826,
      "step": 34
    },
    {
      "epoch": 0.8467741935483871,
      "grad_norm": 2.475355625152588,
      "learning_rate": 1.75e-06,
      "loss": 0.0781,
      "step": 35
    },
    {
      "epoch": 0.8709677419354839,
      "grad_norm": 1.9219006299972534,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.0637,
      "step": 36
    },
    {
      "epoch": 0.8951612903225806,
      "grad_norm": 1.8285995721817017,
      "learning_rate": 1.85e-06,
      "loss": 0.0708,
      "step": 37
    },
    {
      "epoch": 0.9193548387096774,
      "grad_norm": 1.9102882146835327,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.0865,
      "step": 38
    },
    {
      "epoch": 0.9435483870967742,
      "grad_norm": 2.190868854522705,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 0.0732,
      "step": 39
    },
    {
      "epoch": 0.967741935483871,
      "grad_norm": 1.923084020614624,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0767,
      "step": 40
    },
    {
      "epoch": 0.9919354838709677,
      "grad_norm": 1.8931093215942383,
      "learning_rate": 2.05e-06,
      "loss": 0.0868,
      "step": 41
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.8931093215942383,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.138,
      "step": 42
    },
    {
      "epoch": 1.0241935483870968,
      "grad_norm": 6.719915866851807,
      "learning_rate": 2.15e-06,
      "loss": 0.0736,
      "step": 43
    },
    {
      "epoch": 1.0483870967741935,
      "grad_norm": 1.6687527894973755,
      "learning_rate": 2.2e-06,
      "loss": 0.0675,
      "step": 44
    },
    {
      "epoch": 1.0725806451612903,
      "grad_norm": 1.6767126321792603,
      "learning_rate": 2.25e-06,
      "loss": 0.0629,
      "step": 45
    },
    {
      "epoch": 1.096774193548387,
      "grad_norm": 1.3529062271118164,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.0614,
      "step": 46
    },
    {
      "epoch": 1.120967741935484,
      "grad_norm": 2.1146080493927,
      "learning_rate": 2.35e-06,
      "loss": 0.0602,
      "step": 47
    },
    {
      "epoch": 1.1451612903225807,
      "grad_norm": 1.1904520988464355,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.0639,
      "step": 48
    },
    {
      "epoch": 1.1693548387096775,
      "grad_norm": 1.1737815141677856,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.0478,
      "step": 49
    },
    {
      "epoch": 1.1935483870967742,
      "grad_norm": 1.3181250095367432,
      "learning_rate": 2.5e-06,
      "loss": 0.0564,
      "step": 50
    },
    {
      "epoch": 1.217741935483871,
      "grad_norm": 2.057123899459839,
      "learning_rate": 2.55e-06,
      "loss": 0.0432,
      "step": 51
    },
    {
      "epoch": 1.2419354838709677,
      "grad_norm": 1.1123464107513428,
      "learning_rate": 2.6e-06,
      "loss": 0.051,
      "step": 52
    },
    {
      "epoch": 1.2661290322580645,
      "grad_norm": 1.5854344367980957,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.0494,
      "step": 53
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 1.2793511152267456,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.0464,
      "step": 54
    },
    {
      "epoch": 1.314516129032258,
      "grad_norm": 1.3535298109054565,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.0477,
      "step": 55
    },
    {
      "epoch": 1.3387096774193548,
      "grad_norm": 1.186978816986084,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.0375,
      "step": 56
    },
    {
      "epoch": 1.3629032258064515,
      "grad_norm": 1.4667912721633911,
      "learning_rate": 2.85e-06,
      "loss": 0.0424,
      "step": 57
    },
    {
      "epoch": 1.3870967741935485,
      "grad_norm": 1.0930287837982178,
      "learning_rate": 2.9e-06,
      "loss": 0.0417,
      "step": 58
    },
    {
      "epoch": 1.4112903225806452,
      "grad_norm": 1.5085082054138184,
      "learning_rate": 2.95e-06,
      "loss": 0.0479,
      "step": 59
    },
    {
      "epoch": 1.435483870967742,
      "grad_norm": 1.4030777215957642,
      "learning_rate": 3e-06,
      "loss": 0.0413,
      "step": 60
    },
    {
      "epoch": 1.4596774193548387,
      "grad_norm": 1.6423301696777344,
      "learning_rate": 3.05e-06,
      "loss": 0.0349,
      "step": 61
    },
    {
      "epoch": 1.4838709677419355,
      "grad_norm": 1.3811825513839722,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.0482,
      "step": 62
    },
    {
      "epoch": 1.5080645161290323,
      "grad_norm": 1.2499895095825195,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.0308,
      "step": 63
    },
    {
      "epoch": 1.532258064516129,
      "grad_norm": 1.1597909927368164,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.0293,
      "step": 64
    },
    {
      "epoch": 1.5564516129032258,
      "grad_norm": 1.1042351722717285,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.035,
      "step": 65
    },
    {
      "epoch": 1.5806451612903225,
      "grad_norm": 1.13418710231781,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.0254,
      "step": 66
    },
    {
      "epoch": 1.6048387096774195,
      "grad_norm": 0.934019148349762,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.0283,
      "step": 67
    },
    {
      "epoch": 1.629032258064516,
      "grad_norm": 1.468568205833435,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.0325,
      "step": 68
    },
    {
      "epoch": 1.653225806451613,
      "grad_norm": 1.3268495798110962,
      "learning_rate": 3.45e-06,
      "loss": 0.027,
      "step": 69
    },
    {
      "epoch": 1.6774193548387095,
      "grad_norm": 0.8941407203674316,
      "learning_rate": 3.5e-06,
      "loss": 0.0244,
      "step": 70
    },
    {
      "epoch": 1.7016129032258065,
      "grad_norm": 1.0857181549072266,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.0225,
      "step": 71
    },
    {
      "epoch": 1.7258064516129032,
      "grad_norm": 1.1653308868408203,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.029,
      "step": 72
    },
    {
      "epoch": 1.75,
      "grad_norm": 1.0501737594604492,
      "learning_rate": 3.65e-06,
      "loss": 0.0199,
      "step": 73
    },
    {
      "epoch": 1.7741935483870968,
      "grad_norm": 0.8470718264579773,
      "learning_rate": 3.7e-06,
      "loss": 0.0219,
      "step": 74
    },
    {
      "epoch": 1.7983870967741935,
      "grad_norm": 0.8664724826812744,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0161,
      "step": 75
    },
    {
      "epoch": 1.8225806451612905,
      "grad_norm": 1.5050084590911865,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.0246,
      "step": 76
    },
    {
      "epoch": 1.846774193548387,
      "grad_norm": 1.6326985359191895,
      "learning_rate": 3.85e-06,
      "loss": 0.0253,
      "step": 77
    },
    {
      "epoch": 1.870967741935484,
      "grad_norm": 1.5506129264831543,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.0133,
      "step": 78
    },
    {
      "epoch": 1.8951612903225805,
      "grad_norm": 0.7956012487411499,
      "learning_rate": 3.95e-06,
      "loss": 0.0093,
      "step": 79
    },
    {
      "epoch": 1.9193548387096775,
      "grad_norm": 1.898987054824829,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0142,
      "step": 80
    },
    {
      "epoch": 1.9435483870967742,
      "grad_norm": 0.832822859287262,
      "learning_rate": 4.05e-06,
      "loss": 0.0177,
      "step": 81
    },
    {
      "epoch": 1.967741935483871,
      "grad_norm": 0.9572640657424927,
      "learning_rate": 4.1e-06,
      "loss": 0.0077,
      "step": 82
    }
  ],
  "logging_steps": 1,
  "max_steps": 246,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 41,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.0481947549564928e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}