{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 76,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013157894736842105,
      "grad_norm": 37.79440689086914,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 3.1402,
      "step": 1
    },
    {
      "epoch": 0.02631578947368421,
      "grad_norm": 38.45823287963867,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 3.1787,
      "step": 2
    },
    {
      "epoch": 0.039473684210526314,
      "grad_norm": 38.25625228881836,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 3.1316,
      "step": 3
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 37.2024040222168,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 3.1011,
      "step": 4
    },
    {
      "epoch": 0.06578947368421052,
      "grad_norm": 38.17294692993164,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 3.133,
      "step": 5
    },
    {
      "epoch": 0.07894736842105263,
      "grad_norm": 37.374794006347656,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 3.0731,
      "step": 6
    },
    {
      "epoch": 0.09210526315789473,
      "grad_norm": 37.226966857910156,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 3.069,
      "step": 7
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 38.40094757080078,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 3.1223,
      "step": 8
    },
    {
      "epoch": 0.11842105263157894,
      "grad_norm": 37.86320877075195,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 3.062,
      "step": 9
    },
    {
      "epoch": 0.13157894736842105,
      "grad_norm": 38.02171325683594,
      "learning_rate": 5.000000000000001e-07,
      "loss": 3.0008,
      "step": 10
    },
    {
      "epoch": 0.14473684210526316,
      "grad_norm": 38.5522346496582,
      "learning_rate": 5.5e-07,
      "loss": 3.0047,
      "step": 11
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 37.72829818725586,
      "learning_rate": 6.000000000000001e-07,
      "loss": 2.9274,
      "step": 12
    },
    {
      "epoch": 0.17105263157894737,
      "grad_norm": 38.488494873046875,
      "learning_rate": 6.5e-07,
      "loss": 2.8727,
      "step": 13
    },
    {
      "epoch": 0.18421052631578946,
      "grad_norm": 38.87471389770508,
      "learning_rate": 7.000000000000001e-07,
      "loss": 2.8422,
      "step": 14
    },
    {
      "epoch": 0.19736842105263158,
      "grad_norm": 37.584896087646484,
      "learning_rate": 7.5e-07,
      "loss": 2.6728,
      "step": 15
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 37.04607391357422,
      "learning_rate": 8.000000000000001e-07,
      "loss": 2.5215,
      "step": 16
    },
    {
      "epoch": 0.2236842105263158,
      "grad_norm": 37.30121994018555,
      "learning_rate": 8.500000000000001e-07,
      "loss": 2.4689,
      "step": 17
    },
    {
      "epoch": 0.23684210526315788,
      "grad_norm": 35.99961853027344,
      "learning_rate": 9.000000000000001e-07,
      "loss": 2.3,
      "step": 18
    },
    {
      "epoch": 0.25,
      "grad_norm": 35.817543029785156,
      "learning_rate": 9.500000000000001e-07,
      "loss": 2.1423,
      "step": 19
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 35.056915283203125,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.9639,
      "step": 20
    },
    {
      "epoch": 0.27631578947368424,
      "grad_norm": 34.83850860595703,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 1.7845,
      "step": 21
    },
    {
      "epoch": 0.2894736842105263,
      "grad_norm": 34.32366943359375,
      "learning_rate": 1.1e-06,
      "loss": 1.5864,
      "step": 22
    },
    {
      "epoch": 0.3026315789473684,
      "grad_norm": 33.79611587524414,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 1.4011,
      "step": 23
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 32.596031188964844,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.195,
      "step": 24
    },
    {
      "epoch": 0.32894736842105265,
      "grad_norm": 30.045007705688477,
      "learning_rate": 1.25e-06,
      "loss": 0.9883,
      "step": 25
    },
    {
      "epoch": 0.34210526315789475,
      "grad_norm": 24.89093589782715,
      "learning_rate": 1.3e-06,
      "loss": 0.7669,
      "step": 26
    },
    {
      "epoch": 0.35526315789473684,
      "grad_norm": 23.454408645629883,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 0.6304,
      "step": 27
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 19.837312698364258,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 0.4717,
      "step": 28
    },
    {
      "epoch": 0.3815789473684211,
      "grad_norm": 15.185093879699707,
      "learning_rate": 1.45e-06,
      "loss": 0.363,
      "step": 29
    },
    {
      "epoch": 0.39473684210526316,
      "grad_norm": 9.057796478271484,
      "learning_rate": 1.5e-06,
      "loss": 0.2439,
      "step": 30
    },
    {
      "epoch": 0.40789473684210525,
      "grad_norm": 5.976982593536377,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 0.1864,
      "step": 31
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 3.067375421524048,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.1134,
      "step": 32
    },
    {
      "epoch": 0.4342105263157895,
      "grad_norm": 2.3589119911193848,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 0.0985,
      "step": 33
    },
    {
      "epoch": 0.4473684210526316,
      "grad_norm": 2.0044353008270264,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 0.0859,
      "step": 34
    },
    {
      "epoch": 0.4605263157894737,
      "grad_norm": 1.4279972314834595,
      "learning_rate": 1.75e-06,
      "loss": 0.0728,
      "step": 35
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 0.9807674288749695,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 0.061,
      "step": 36
    },
    {
      "epoch": 0.4868421052631579,
      "grad_norm": 0.906160295009613,
      "learning_rate": 1.85e-06,
      "loss": 0.0676,
      "step": 37
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.8837690353393555,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.0622,
      "step": 38
    },
    {
      "epoch": 0.5131578947368421,
      "grad_norm": 0.9579435586929321,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 0.0557,
      "step": 39
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.8149510622024536,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0555,
      "step": 40
    },
    {
      "epoch": 0.5394736842105263,
      "grad_norm": 0.8899760246276855,
      "learning_rate": 2.05e-06,
      "loss": 0.0517,
      "step": 41
    },
    {
      "epoch": 0.5526315789473685,
      "grad_norm": 0.6007645130157471,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 0.0518,
      "step": 42
    },
    {
      "epoch": 0.5657894736842105,
      "grad_norm": 0.48819127678871155,
      "learning_rate": 2.15e-06,
      "loss": 0.0429,
      "step": 43
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 0.42939358949661255,
      "learning_rate": 2.2e-06,
      "loss": 0.0459,
      "step": 44
    },
    {
      "epoch": 0.5921052631578947,
      "grad_norm": 0.5706579685211182,
      "learning_rate": 2.25e-06,
      "loss": 0.0453,
      "step": 45
    },
    {
      "epoch": 0.6052631578947368,
      "grad_norm": 0.3034597337245941,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 0.0421,
      "step": 46
    },
    {
      "epoch": 0.618421052631579,
      "grad_norm": 0.5601783394813538,
      "learning_rate": 2.35e-06,
      "loss": 0.0411,
      "step": 47
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.35388317704200745,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.04,
      "step": 48
    },
    {
      "epoch": 0.6447368421052632,
      "grad_norm": 0.48609891533851624,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 0.04,
      "step": 49
    },
    {
      "epoch": 0.6578947368421053,
      "grad_norm": 0.4638507068157196,
      "learning_rate": 2.5e-06,
      "loss": 0.0369,
      "step": 50
    },
    {
      "epoch": 0.6710526315789473,
      "grad_norm": 0.5685771703720093,
      "learning_rate": 2.55e-06,
      "loss": 0.0428,
      "step": 51
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 0.46358174085617065,
      "learning_rate": 2.6e-06,
      "loss": 0.0483,
      "step": 52
    },
    {
      "epoch": 0.6973684210526315,
      "grad_norm": 0.35054436326026917,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 0.0391,
      "step": 53
    },
    {
      "epoch": 0.7105263157894737,
      "grad_norm": 0.3350559175014496,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 0.039,
      "step": 54
    },
    {
      "epoch": 0.7236842105263158,
      "grad_norm": 0.2875112295150757,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.0383,
      "step": 55
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 0.4492928683757782,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 0.0358,
      "step": 56
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.29484888911247253,
      "learning_rate": 2.85e-06,
      "loss": 0.0355,
      "step": 57
    },
    {
      "epoch": 0.7631578947368421,
      "grad_norm": 0.36551928520202637,
      "learning_rate": 2.9e-06,
      "loss": 0.0403,
      "step": 58
    },
    {
      "epoch": 0.7763157894736842,
      "grad_norm": 0.4458053708076477,
      "learning_rate": 2.95e-06,
      "loss": 0.0342,
      "step": 59
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 0.34047460556030273,
      "learning_rate": 3e-06,
      "loss": 0.0302,
      "step": 60
    },
    {
      "epoch": 0.8026315789473685,
      "grad_norm": 0.3420606255531311,
      "learning_rate": 3.05e-06,
      "loss": 0.034,
      "step": 61
    },
    {
      "epoch": 0.8157894736842105,
      "grad_norm": 0.3902851939201355,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 0.0327,
      "step": 62
    },
    {
      "epoch": 0.8289473684210527,
      "grad_norm": 0.29165828227996826,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 0.0341,
      "step": 63
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.40872958302497864,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.035,
      "step": 64
    },
    {
      "epoch": 0.8552631578947368,
      "grad_norm": 0.36295783519744873,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.0323,
      "step": 65
    },
    {
      "epoch": 0.868421052631579,
      "grad_norm": 0.3857724368572235,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 0.0336,
      "step": 66
    },
    {
      "epoch": 0.881578947368421,
      "grad_norm": 0.3207017481327057,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 0.0332,
      "step": 67
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 0.2903987169265747,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.0327,
      "step": 68
    },
    {
      "epoch": 0.9078947368421053,
      "grad_norm": 0.3386954963207245,
      "learning_rate": 3.45e-06,
      "loss": 0.0308,
      "step": 69
    },
    {
      "epoch": 0.9210526315789473,
      "grad_norm": 0.4339621365070343,
      "learning_rate": 3.5e-06,
      "loss": 0.0361,
      "step": 70
    },
    {
      "epoch": 0.9342105263157895,
      "grad_norm": 0.28095564246177673,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.0306,
      "step": 71
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 0.4141469895839691,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.028,
      "step": 72
    },
    {
      "epoch": 0.9605263157894737,
      "grad_norm": 0.35212820768356323,
      "learning_rate": 3.65e-06,
      "loss": 0.032,
      "step": 73
    },
    {
      "epoch": 0.9736842105263158,
      "grad_norm": 0.26956063508987427,
      "learning_rate": 3.7e-06,
      "loss": 0.0294,
      "step": 74
    },
    {
      "epoch": 0.9868421052631579,
      "grad_norm": 0.32735681533813477,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.0272,
      "step": 75
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.4906782805919647,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.0324,
      "step": 76
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 76,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.889219280312205e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}