{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 114,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008771929824561403,
      "grad_norm": 39.56407165527344,
      "learning_rate": 5.0000000000000004e-08,
      "loss": 5.1375,
      "step": 1
    },
    {
      "epoch": 0.017543859649122806,
      "grad_norm": 40.30452346801758,
      "learning_rate": 1.0000000000000001e-07,
      "loss": 5.1185,
      "step": 2
    },
    {
      "epoch": 0.02631578947368421,
      "grad_norm": 40.062313079833984,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 5.0762,
      "step": 3
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 39.17148208618164,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 5.016,
      "step": 4
    },
    {
      "epoch": 0.043859649122807015,
      "grad_norm": 40.67367172241211,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 5.0428,
      "step": 5
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 38.18095016479492,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 5.2025,
      "step": 6
    },
    {
      "epoch": 0.06140350877192982,
      "grad_norm": 39.12940979003906,
      "learning_rate": 3.5000000000000004e-07,
      "loss": 4.9896,
      "step": 7
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 38.84568405151367,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 5.1078,
      "step": 8
    },
    {
      "epoch": 0.07894736842105263,
      "grad_norm": 39.38333511352539,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 5.0808,
      "step": 9
    },
    {
      "epoch": 0.08771929824561403,
      "grad_norm": 39.427650451660156,
      "learning_rate": 5.000000000000001e-07,
      "loss": 5.0534,
      "step": 10
    },
    {
      "epoch": 0.09649122807017543,
      "grad_norm": 39.29513168334961,
      "learning_rate": 5.5e-07,
      "loss": 5.058,
      "step": 11
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 39.641231536865234,
      "learning_rate": 6.000000000000001e-07,
      "loss": 5.0317,
      "step": 12
    },
    {
      "epoch": 0.11403508771929824,
      "grad_norm": 37.91259765625,
      "learning_rate": 6.5e-07,
      "loss": 4.912,
      "step": 13
    },
    {
      "epoch": 0.12280701754385964,
      "grad_norm": 38.203548431396484,
      "learning_rate": 7.000000000000001e-07,
      "loss": 4.9705,
      "step": 14
    },
    {
      "epoch": 0.13157894736842105,
      "grad_norm": 39.15998840332031,
      "learning_rate": 7.5e-07,
      "loss": 4.6962,
      "step": 15
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 37.754669189453125,
      "learning_rate": 8.000000000000001e-07,
      "loss": 4.6262,
      "step": 16
    },
    {
      "epoch": 0.14912280701754385,
      "grad_norm": 35.871490478515625,
      "learning_rate": 8.500000000000001e-07,
      "loss": 4.5422,
      "step": 17
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 36.16888427734375,
      "learning_rate": 9.000000000000001e-07,
      "loss": 4.664,
      "step": 18
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 33.520118713378906,
      "learning_rate": 9.500000000000001e-07,
      "loss": 4.4697,
      "step": 19
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 30.896282196044922,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 4.3568,
      "step": 20
    },
    {
      "epoch": 0.18421052631578946,
      "grad_norm": 29.944643020629883,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 4.2269,
      "step": 21
    },
    {
      "epoch": 0.19298245614035087,
      "grad_norm": 25.224485397338867,
      "learning_rate": 1.1e-06,
      "loss": 4.1272,
      "step": 22
    },
    {
      "epoch": 0.20175438596491227,
      "grad_norm": 24.410480499267578,
      "learning_rate": 1.1500000000000002e-06,
      "loss": 4.0585,
      "step": 23
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 21.480648040771484,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 3.9472,
      "step": 24
    },
    {
      "epoch": 0.21929824561403508,
      "grad_norm": 20.61946678161621,
      "learning_rate": 1.25e-06,
      "loss": 3.8879,
      "step": 25
    },
    {
      "epoch": 0.22807017543859648,
      "grad_norm": 19.578271865844727,
      "learning_rate": 1.3e-06,
      "loss": 3.6783,
      "step": 26
    },
    {
      "epoch": 0.23684210526315788,
      "grad_norm": 17.418983459472656,
      "learning_rate": 1.3500000000000002e-06,
      "loss": 3.6826,
      "step": 27
    },
    {
      "epoch": 0.24561403508771928,
      "grad_norm": 18.160301208496094,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 3.478,
      "step": 28
    },
    {
      "epoch": 0.2543859649122807,
      "grad_norm": 17.573204040527344,
      "learning_rate": 1.45e-06,
      "loss": 3.459,
      "step": 29
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 17.1265869140625,
      "learning_rate": 1.5e-06,
      "loss": 3.3999,
      "step": 30
    },
    {
      "epoch": 0.2719298245614035,
      "grad_norm": 15.527145385742188,
      "learning_rate": 1.5500000000000002e-06,
      "loss": 3.2817,
      "step": 31
    },
    {
      "epoch": 0.2807017543859649,
      "grad_norm": 14.773847579956055,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 3.234,
      "step": 32
    },
    {
      "epoch": 0.2894736842105263,
      "grad_norm": 12.039301872253418,
      "learning_rate": 1.6500000000000003e-06,
      "loss": 3.132,
      "step": 33
    },
    {
      "epoch": 0.2982456140350877,
      "grad_norm": 9.217979431152344,
      "learning_rate": 1.7000000000000002e-06,
      "loss": 3.0548,
      "step": 34
    },
    {
      "epoch": 0.30701754385964913,
      "grad_norm": 7.575639724731445,
      "learning_rate": 1.75e-06,
      "loss": 2.9529,
      "step": 35
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 7.496004104614258,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 2.8967,
      "step": 36
    },
    {
      "epoch": 0.32456140350877194,
      "grad_norm": 7.45414924621582,
      "learning_rate": 1.85e-06,
      "loss": 2.8837,
      "step": 37
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 8.555658340454102,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 2.7473,
      "step": 38
    },
    {
      "epoch": 0.34210526315789475,
      "grad_norm": 10.03805160522461,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 2.7355,
      "step": 39
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 9.30649471282959,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.6587,
      "step": 40
    },
    {
      "epoch": 0.35964912280701755,
      "grad_norm": 8.510339736938477,
      "learning_rate": 2.05e-06,
      "loss": 2.5977,
      "step": 41
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 4.709080696105957,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 2.6286,
      "step": 42
    },
    {
      "epoch": 0.37719298245614036,
      "grad_norm": 5.128961086273193,
      "learning_rate": 2.15e-06,
      "loss": 2.4558,
      "step": 43
    },
    {
      "epoch": 0.38596491228070173,
      "grad_norm": 5.190136432647705,
      "learning_rate": 2.2e-06,
      "loss": 2.4432,
      "step": 44
    },
    {
      "epoch": 0.39473684210526316,
      "grad_norm": 4.893551349639893,
      "learning_rate": 2.25e-06,
      "loss": 2.4939,
      "step": 45
    },
    {
      "epoch": 0.40350877192982454,
      "grad_norm": 5.2434983253479,
      "learning_rate": 2.3000000000000004e-06,
      "loss": 2.3381,
      "step": 46
    },
    {
      "epoch": 0.41228070175438597,
      "grad_norm": 5.122412204742432,
      "learning_rate": 2.35e-06,
      "loss": 2.313,
      "step": 47
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 4.577274799346924,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 2.2236,
      "step": 48
    },
    {
      "epoch": 0.4298245614035088,
      "grad_norm": 4.722769737243652,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 2.1987,
      "step": 49
    },
    {
      "epoch": 0.43859649122807015,
      "grad_norm": 5.059235095977783,
      "learning_rate": 2.5e-06,
      "loss": 2.1415,
      "step": 50
    },
    {
      "epoch": 0.4473684210526316,
      "grad_norm": 4.454439640045166,
      "learning_rate": 2.55e-06,
      "loss": 2.0466,
      "step": 51
    },
    {
      "epoch": 0.45614035087719296,
      "grad_norm": 4.94586706161499,
      "learning_rate": 2.6e-06,
      "loss": 1.8762,
      "step": 52
    },
    {
      "epoch": 0.4649122807017544,
      "grad_norm": 4.704402446746826,
      "learning_rate": 2.6500000000000005e-06,
      "loss": 1.8012,
      "step": 53
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 6.125903129577637,
      "learning_rate": 2.7000000000000004e-06,
      "loss": 1.7669,
      "step": 54
    },
    {
      "epoch": 0.4824561403508772,
      "grad_norm": 4.5356059074401855,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 1.6607,
      "step": 55
    },
    {
      "epoch": 0.49122807017543857,
      "grad_norm": 6.56803035736084,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 1.6291,
      "step": 56
    },
    {
      "epoch": 0.5,
      "grad_norm": 4.910050392150879,
      "learning_rate": 2.85e-06,
      "loss": 1.5545,
      "step": 57
    },
    {
      "epoch": 0.5087719298245614,
      "grad_norm": 8.733433723449707,
      "learning_rate": 2.9e-06,
      "loss": 1.4206,
      "step": 58
    },
    {
      "epoch": 0.5175438596491229,
      "grad_norm": 8.582486152648926,
      "learning_rate": 2.95e-06,
      "loss": 1.3912,
      "step": 59
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 13.710689544677734,
      "learning_rate": 3e-06,
      "loss": 1.3297,
      "step": 60
    },
    {
      "epoch": 0.5350877192982456,
      "grad_norm": 23.400312423706055,
      "learning_rate": 3.05e-06,
      "loss": 1.296,
      "step": 61
    },
    {
      "epoch": 0.543859649122807,
      "grad_norm": 5.678805351257324,
      "learning_rate": 3.1000000000000004e-06,
      "loss": 1.2259,
      "step": 62
    },
    {
      "epoch": 0.5526315789473685,
      "grad_norm": 14.700899124145508,
      "learning_rate": 3.1500000000000003e-06,
      "loss": 1.1087,
      "step": 63
    },
    {
      "epoch": 0.5614035087719298,
      "grad_norm": 19.38919448852539,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 1.1805,
      "step": 64
    },
    {
      "epoch": 0.5701754385964912,
      "grad_norm": 8.460039138793945,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 1.0963,
      "step": 65
    },
    {
      "epoch": 0.5789473684210527,
      "grad_norm": 13.371014595031738,
      "learning_rate": 3.3000000000000006e-06,
      "loss": 1.0627,
      "step": 66
    },
    {
      "epoch": 0.5877192982456141,
      "grad_norm": 22.380569458007812,
      "learning_rate": 3.3500000000000005e-06,
      "loss": 1.0869,
      "step": 67
    },
    {
      "epoch": 0.5964912280701754,
      "grad_norm": 5.780513286590576,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 0.9991,
      "step": 68
    },
    {
      "epoch": 0.6052631578947368,
      "grad_norm": 19.850841522216797,
      "learning_rate": 3.45e-06,
      "loss": 0.9683,
      "step": 69
    },
    {
      "epoch": 0.6140350877192983,
      "grad_norm": 17.160703659057617,
      "learning_rate": 3.5e-06,
      "loss": 0.845,
      "step": 70
    },
    {
      "epoch": 0.6228070175438597,
      "grad_norm": 14.264311790466309,
      "learning_rate": 3.5500000000000003e-06,
      "loss": 0.8059,
      "step": 71
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 26.39459991455078,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.85,
      "step": 72
    },
    {
      "epoch": 0.6403508771929824,
      "grad_norm": 51.10348892211914,
      "learning_rate": 3.65e-06,
      "loss": 0.9755,
      "step": 73
    },
    {
      "epoch": 0.6491228070175439,
      "grad_norm": 28.795856475830078,
      "learning_rate": 3.7e-06,
      "loss": 0.8966,
      "step": 74
    },
    {
      "epoch": 0.6578947368421053,
      "grad_norm": 4.6617937088012695,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.7716,
      "step": 75
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 15.729666709899902,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 0.7578,
      "step": 76
    },
    {
      "epoch": 0.6754385964912281,
      "grad_norm": 7.109970569610596,
      "learning_rate": 3.85e-06,
      "loss": 0.7055,
      "step": 77
    },
    {
      "epoch": 0.6842105263157895,
      "grad_norm": 20.84659194946289,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.7458,
      "step": 78
    },
    {
      "epoch": 0.6929824561403509,
      "grad_norm": 21.601303100585938,
      "learning_rate": 3.95e-06,
      "loss": 0.6879,
      "step": 79
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 3.6914751529693604,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.6179,
      "step": 80
    },
    {
      "epoch": 0.7105263157894737,
      "grad_norm": 16.539325714111328,
      "learning_rate": 4.05e-06,
      "loss": 0.5716,
      "step": 81
    },
    {
      "epoch": 0.7192982456140351,
      "grad_norm": 13.931925773620605,
      "learning_rate": 4.1e-06,
      "loss": 0.558,
      "step": 82
    },
    {
      "epoch": 0.7280701754385965,
      "grad_norm": 10.52951717376709,
      "learning_rate": 4.15e-06,
      "loss": 0.6018,
      "step": 83
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 17.337060928344727,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.5501,
      "step": 84
    },
    {
      "epoch": 0.7456140350877193,
      "grad_norm": 13.500468254089355,
      "learning_rate": 4.25e-06,
      "loss": 0.5214,
      "step": 85
    },
    {
      "epoch": 0.7543859649122807,
      "grad_norm": 10.290645599365234,
      "learning_rate": 4.3e-06,
      "loss": 0.4996,
      "step": 86
    },
    {
      "epoch": 0.7631578947368421,
      "grad_norm": 9.757556915283203,
      "learning_rate": 4.350000000000001e-06,
      "loss": 0.498,
      "step": 87
    },
    {
      "epoch": 0.7719298245614035,
      "grad_norm": 9.325140953063965,
      "learning_rate": 4.4e-06,
      "loss": 0.4721,
      "step": 88
    },
    {
      "epoch": 0.7807017543859649,
      "grad_norm": 2.9322128295898438,
      "learning_rate": 4.450000000000001e-06,
      "loss": 0.4528,
      "step": 89
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 10.484073638916016,
      "learning_rate": 4.5e-06,
      "loss": 0.445,
      "step": 90
    },
    {
      "epoch": 0.7982456140350878,
      "grad_norm": 32.7827262878418,
      "learning_rate": 4.5500000000000005e-06,
      "loss": 0.5105,
      "step": 91
    },
    {
      "epoch": 0.8070175438596491,
      "grad_norm": 2.8477306365966797,
      "learning_rate": 4.600000000000001e-06,
      "loss": 0.4117,
      "step": 92
    },
    {
      "epoch": 0.8157894736842105,
      "grad_norm": 2.7680225372314453,
      "learning_rate": 4.65e-06,
      "loss": 0.3653,
      "step": 93
    },
    {
      "epoch": 0.8245614035087719,
      "grad_norm": 2.6512742042541504,
      "learning_rate": 4.7e-06,
      "loss": 0.3878,
      "step": 94
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 6.453914165496826,
      "learning_rate": 4.75e-06,
      "loss": 0.3611,
      "step": 95
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 3.4594080448150635,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.3817,
      "step": 96
    },
    {
      "epoch": 0.8508771929824561,
      "grad_norm": 3.6144917011260986,
      "learning_rate": 4.85e-06,
      "loss": 0.3618,
      "step": 97
    },
    {
      "epoch": 0.8596491228070176,
      "grad_norm": 5.349407196044922,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.3218,
      "step": 98
    },
    {
      "epoch": 0.868421052631579,
      "grad_norm": 13.671236991882324,
      "learning_rate": 4.95e-06,
      "loss": 0.3329,
      "step": 99
    },
    {
      "epoch": 0.8771929824561403,
      "grad_norm": 5.84046745300293,
      "learning_rate": 5e-06,
      "loss": 0.2967,
      "step": 100
    },
    {
      "epoch": 0.8859649122807017,
      "grad_norm": 14.005338668823242,
      "learning_rate": 4.999963827125897e-06,
      "loss": 0.303,
      "step": 101
    },
    {
      "epoch": 0.8947368421052632,
      "grad_norm": 9.18114185333252,
      "learning_rate": 4.999855309550366e-06,
      "loss": 0.2762,
      "step": 102
    },
    {
      "epoch": 0.9035087719298246,
      "grad_norm": 3.0800487995147705,
      "learning_rate": 4.999674450413725e-06,
      "loss": 0.2628,
      "step": 103
    },
    {
      "epoch": 0.9122807017543859,
      "grad_norm": 82.03578186035156,
      "learning_rate": 4.999421254949728e-06,
      "loss": 0.4065,
      "step": 104
    },
    {
      "epoch": 0.9210526315789473,
      "grad_norm": 77.66315460205078,
      "learning_rate": 4.99909573048542e-06,
      "loss": 0.4307,
      "step": 105
    },
    {
      "epoch": 0.9298245614035088,
      "grad_norm": 18.28767967224121,
      "learning_rate": 4.998697886440927e-06,
      "loss": 0.2571,
      "step": 106
    },
    {
      "epoch": 0.9385964912280702,
      "grad_norm": 5.960445880889893,
      "learning_rate": 4.998227734329177e-06,
      "loss": 0.2847,
      "step": 107
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 5.437699794769287,
      "learning_rate": 4.9976852877555755e-06,
      "loss": 0.2728,
      "step": 108
    },
    {
      "epoch": 0.956140350877193,
      "grad_norm": 3.379631280899048,
      "learning_rate": 4.997070562417602e-06,
      "loss": 0.2467,
      "step": 109
    },
    {
      "epoch": 0.9649122807017544,
      "grad_norm": 3.1625075340270996,
      "learning_rate": 4.996383576104362e-06,
      "loss": 0.2273,
      "step": 110
    },
    {
      "epoch": 0.9736842105263158,
      "grad_norm": 15.588600158691406,
      "learning_rate": 4.995624348696071e-06,
      "loss": 0.2486,
      "step": 111
    },
    {
      "epoch": 0.9824561403508771,
      "grad_norm": 2.631044387817383,
      "learning_rate": 4.9947929021634815e-06,
      "loss": 0.1964,
      "step": 112
    },
    {
      "epoch": 0.9912280701754386,
      "grad_norm": 4.706504821777344,
      "learning_rate": 4.993889260567239e-06,
      "loss": 0.1901,
      "step": 113
    },
    {
      "epoch": 1.0,
      "grad_norm": 10.368465423583984,
      "learning_rate": 4.9929134500571954e-06,
      "loss": 0.1996,
      "step": 114
    }
  ],
  "logging_steps": 1,
  "max_steps": 684,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 114,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.45999007414852e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}