{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 169.23076923076923,
  "eval_steps": 100,
  "global_step": 11000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 47.11796188354492,
      "learning_rate": 9.990900000000001e-06,
      "loss": 3.6644,
      "step": 100
    },
    {
      "epoch": 1.5384615384615383,
      "eval_loss": 2.4919605255126953,
      "eval_runtime": 12.5517,
      "eval_samples_per_second": 10.437,
      "eval_steps_per_second": 1.354,
      "step": 100
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 31.28130531311035,
      "learning_rate": 9.980900000000001e-06,
      "loss": 2.2347,
      "step": 200
    },
    {
      "epoch": 3.076923076923077,
      "eval_loss": 2.156316041946411,
      "eval_runtime": 11.1792,
      "eval_samples_per_second": 11.718,
      "eval_steps_per_second": 1.521,
      "step": 200
    },
    {
      "epoch": 4.615384615384615,
      "grad_norm": 39.616390228271484,
      "learning_rate": 9.970900000000001e-06,
      "loss": 2.0254,
      "step": 300
    },
    {
      "epoch": 4.615384615384615,
      "eval_loss": 2.024153709411621,
      "eval_runtime": 11.1934,
      "eval_samples_per_second": 11.703,
      "eval_steps_per_second": 1.519,
      "step": 300
    },
    {
      "epoch": 6.153846153846154,
      "grad_norm": 28.285825729370117,
      "learning_rate": 9.960900000000001e-06,
      "loss": 1.9361,
      "step": 400
    },
    {
      "epoch": 6.153846153846154,
      "eval_loss": 1.9094743728637695,
      "eval_runtime": 11.3855,
      "eval_samples_per_second": 11.506,
      "eval_steps_per_second": 1.493,
      "step": 400
    },
    {
      "epoch": 7.6923076923076925,
      "grad_norm": 34.14302062988281,
      "learning_rate": 9.950900000000002e-06,
      "loss": 1.8531,
      "step": 500
    },
    {
      "epoch": 7.6923076923076925,
      "eval_loss": 1.8729331493377686,
      "eval_runtime": 11.2935,
      "eval_samples_per_second": 11.6,
      "eval_steps_per_second": 1.505,
      "step": 500
    },
    {
      "epoch": 9.23076923076923,
      "grad_norm": 39.09531784057617,
      "learning_rate": 9.940900000000002e-06,
      "loss": 1.7669,
      "step": 600
    },
    {
      "epoch": 9.23076923076923,
      "eval_loss": 1.831756830215454,
      "eval_runtime": 11.0535,
      "eval_samples_per_second": 11.851,
      "eval_steps_per_second": 1.538,
      "step": 600
    },
    {
      "epoch": 10.76923076923077,
      "grad_norm": 93.24444580078125,
      "learning_rate": 9.930900000000002e-06,
      "loss": 1.7518,
      "step": 700
    },
    {
      "epoch": 10.76923076923077,
      "eval_loss": 1.7832175493240356,
      "eval_runtime": 11.1684,
      "eval_samples_per_second": 11.729,
      "eval_steps_per_second": 1.522,
      "step": 700
    },
    {
      "epoch": 12.307692307692308,
      "grad_norm": 32.21013641357422,
      "learning_rate": 9.920900000000002e-06,
      "loss": 1.7149,
      "step": 800
    },
    {
      "epoch": 12.307692307692308,
      "eval_loss": 1.7581098079681396,
      "eval_runtime": 11.101,
      "eval_samples_per_second": 11.801,
      "eval_steps_per_second": 1.531,
      "step": 800
    },
    {
      "epoch": 13.846153846153847,
      "grad_norm": 59.90657043457031,
      "learning_rate": 9.9109e-06,
      "loss": 1.6734,
      "step": 900
    },
    {
      "epoch": 13.846153846153847,
      "eval_loss": 1.7163844108581543,
      "eval_runtime": 11.1167,
      "eval_samples_per_second": 11.784,
      "eval_steps_per_second": 1.529,
      "step": 900
    },
    {
      "epoch": 15.384615384615385,
      "grad_norm": 20.61592674255371,
      "learning_rate": 9.9009e-06,
      "loss": 1.6612,
      "step": 1000
    },
    {
      "epoch": 15.384615384615385,
      "eval_loss": 1.6949567794799805,
      "eval_runtime": 11.0663,
      "eval_samples_per_second": 11.838,
      "eval_steps_per_second": 1.536,
      "step": 1000
    },
    {
      "epoch": 16.923076923076923,
      "grad_norm": 17.60099220275879,
      "learning_rate": 9.8909e-06,
      "loss": 1.6199,
      "step": 1100
    },
    {
      "epoch": 16.923076923076923,
      "eval_loss": 1.6769332885742188,
      "eval_runtime": 11.0531,
      "eval_samples_per_second": 11.852,
      "eval_steps_per_second": 1.538,
      "step": 1100
    },
    {
      "epoch": 18.46153846153846,
      "grad_norm": 20.802692413330078,
      "learning_rate": 9.8809e-06,
      "loss": 1.6008,
      "step": 1200
    },
    {
      "epoch": 18.46153846153846,
      "eval_loss": 1.6524990797042847,
      "eval_runtime": 11.0831,
      "eval_samples_per_second": 11.82,
      "eval_steps_per_second": 1.534,
      "step": 1200
    },
    {
      "epoch": 20.0,
      "grad_norm": 21.809823989868164,
      "learning_rate": 9.8709e-06,
      "loss": 1.5812,
      "step": 1300
    },
    {
      "epoch": 20.0,
      "eval_loss": 1.6428295373916626,
      "eval_runtime": 11.1093,
      "eval_samples_per_second": 11.792,
      "eval_steps_per_second": 1.53,
      "step": 1300
    },
    {
      "epoch": 21.53846153846154,
      "grad_norm": 46.8908576965332,
      "learning_rate": 9.8609e-06,
      "loss": 1.5419,
      "step": 1400
    },
    {
      "epoch": 21.53846153846154,
      "eval_loss": 1.6006404161453247,
      "eval_runtime": 11.2393,
      "eval_samples_per_second": 11.655,
      "eval_steps_per_second": 1.513,
      "step": 1400
    },
    {
      "epoch": 23.076923076923077,
      "grad_norm": 27.15238380432129,
      "learning_rate": 9.8509e-06,
      "loss": 1.5374,
      "step": 1500
    },
    {
      "epoch": 23.076923076923077,
      "eval_loss": 1.5862094163894653,
      "eval_runtime": 11.1815,
      "eval_samples_per_second": 11.716,
      "eval_steps_per_second": 1.52,
      "step": 1500
    },
    {
      "epoch": 24.615384615384617,
      "grad_norm": 40.26778030395508,
      "learning_rate": 9.840900000000001e-06,
      "loss": 1.4923,
      "step": 1600
    },
    {
      "epoch": 24.615384615384617,
      "eval_loss": 1.576373815536499,
      "eval_runtime": 11.1215,
      "eval_samples_per_second": 11.779,
      "eval_steps_per_second": 1.529,
      "step": 1600
    },
    {
      "epoch": 26.153846153846153,
      "grad_norm": 35.266971588134766,
      "learning_rate": 9.830900000000001e-06,
      "loss": 1.4989,
      "step": 1700
    },
    {
      "epoch": 26.153846153846153,
      "eval_loss": 1.5671430826187134,
      "eval_runtime": 11.1873,
      "eval_samples_per_second": 11.71,
      "eval_steps_per_second": 1.52,
      "step": 1700
    },
    {
      "epoch": 27.692307692307693,
      "grad_norm": 26.813480377197266,
      "learning_rate": 9.820900000000001e-06,
      "loss": 1.4711,
      "step": 1800
    },
    {
      "epoch": 27.692307692307693,
      "eval_loss": 1.522908329963684,
      "eval_runtime": 11.2106,
      "eval_samples_per_second": 11.685,
      "eval_steps_per_second": 1.516,
      "step": 1800
    },
    {
      "epoch": 29.23076923076923,
      "grad_norm": 24.576723098754883,
      "learning_rate": 9.810900000000001e-06,
      "loss": 1.4421,
      "step": 1900
    },
    {
      "epoch": 29.23076923076923,
      "eval_loss": 1.5039104223251343,
      "eval_runtime": 11.257,
      "eval_samples_per_second": 11.637,
      "eval_steps_per_second": 1.51,
      "step": 1900
    },
    {
      "epoch": 30.76923076923077,
      "grad_norm": 28.480438232421875,
      "learning_rate": 9.800900000000001e-06,
      "loss": 1.4347,
      "step": 2000
    },
    {
      "epoch": 30.76923076923077,
      "eval_loss": 1.5123459100723267,
      "eval_runtime": 11.187,
      "eval_samples_per_second": 11.71,
      "eval_steps_per_second": 1.52,
      "step": 2000
    },
    {
      "epoch": 32.30769230769231,
      "grad_norm": 56.582088470458984,
      "learning_rate": 9.790900000000001e-06,
      "loss": 1.4212,
      "step": 2100
    },
    {
      "epoch": 32.30769230769231,
      "eval_loss": 1.481844425201416,
      "eval_runtime": 11.2075,
      "eval_samples_per_second": 11.689,
      "eval_steps_per_second": 1.517,
      "step": 2100
    },
    {
      "epoch": 33.84615384615385,
      "grad_norm": 38.5254020690918,
      "learning_rate": 9.780900000000002e-06,
      "loss": 1.3908,
      "step": 2200
    },
    {
      "epoch": 33.84615384615385,
      "eval_loss": 1.4529048204421997,
      "eval_runtime": 11.197,
      "eval_samples_per_second": 11.7,
      "eval_steps_per_second": 1.518,
      "step": 2200
    },
    {
      "epoch": 35.38461538461539,
      "grad_norm": 44.74857711791992,
      "learning_rate": 9.770900000000002e-06,
      "loss": 1.3734,
      "step": 2300
    },
    {
      "epoch": 35.38461538461539,
      "eval_loss": 1.4617427587509155,
      "eval_runtime": 11.1235,
      "eval_samples_per_second": 11.777,
      "eval_steps_per_second": 1.528,
      "step": 2300
    },
    {
      "epoch": 36.92307692307692,
      "grad_norm": 28.926782608032227,
      "learning_rate": 9.760900000000002e-06,
      "loss": 1.365,
      "step": 2400
    },
    {
      "epoch": 36.92307692307692,
      "eval_loss": 1.4297789335250854,
      "eval_runtime": 11.3007,
      "eval_samples_per_second": 11.592,
      "eval_steps_per_second": 1.504,
      "step": 2400
    },
    {
      "epoch": 38.46153846153846,
      "grad_norm": 27.750213623046875,
      "learning_rate": 9.7509e-06,
      "loss": 1.3306,
      "step": 2500
    },
    {
      "epoch": 38.46153846153846,
      "eval_loss": 1.4345914125442505,
      "eval_runtime": 11.2795,
      "eval_samples_per_second": 11.614,
      "eval_steps_per_second": 1.507,
      "step": 2500
    },
    {
      "epoch": 40.0,
      "grad_norm": 35.288352966308594,
      "learning_rate": 9.7409e-06,
      "loss": 1.3677,
      "step": 2600
    },
    {
      "epoch": 40.0,
      "eval_loss": 1.447089433670044,
      "eval_runtime": 11.1366,
      "eval_samples_per_second": 11.763,
      "eval_steps_per_second": 1.527,
      "step": 2600
    },
    {
      "epoch": 41.53846153846154,
      "grad_norm": 65.49736022949219,
      "learning_rate": 9.7309e-06,
      "loss": 1.3453,
      "step": 2700
    },
    {
      "epoch": 41.53846153846154,
      "eval_loss": 1.405300259590149,
      "eval_runtime": 11.1549,
      "eval_samples_per_second": 11.744,
      "eval_steps_per_second": 1.524,
      "step": 2700
    },
    {
      "epoch": 43.07692307692308,
      "grad_norm": 24.333518981933594,
      "learning_rate": 9.7209e-06,
      "loss": 1.3206,
      "step": 2800
    },
    {
      "epoch": 43.07692307692308,
      "eval_loss": 1.4218717813491821,
      "eval_runtime": 11.3113,
      "eval_samples_per_second": 11.581,
      "eval_steps_per_second": 1.503,
      "step": 2800
    },
    {
      "epoch": 44.61538461538461,
      "grad_norm": 45.50777816772461,
      "learning_rate": 9.7109e-06,
      "loss": 1.3363,
      "step": 2900
    },
    {
      "epoch": 44.61538461538461,
      "eval_loss": 1.4220006465911865,
      "eval_runtime": 11.156,
      "eval_samples_per_second": 11.743,
      "eval_steps_per_second": 1.524,
      "step": 2900
    },
    {
      "epoch": 46.15384615384615,
      "grad_norm": 25.898344039916992,
      "learning_rate": 9.7009e-06,
      "loss": 1.2995,
      "step": 3000
    },
    {
      "epoch": 46.15384615384615,
      "eval_loss": 1.3942431211471558,
      "eval_runtime": 11.2282,
      "eval_samples_per_second": 11.667,
      "eval_steps_per_second": 1.514,
      "step": 3000
    },
    {
      "epoch": 47.69230769230769,
      "grad_norm": 56.0889892578125,
      "learning_rate": 9.6909e-06,
      "loss": 1.2994,
      "step": 3100
    },
    {
      "epoch": 47.69230769230769,
      "eval_loss": 1.3970586061477661,
      "eval_runtime": 11.1682,
      "eval_samples_per_second": 11.73,
      "eval_steps_per_second": 1.522,
      "step": 3100
    },
    {
      "epoch": 49.23076923076923,
      "grad_norm": 58.10311508178711,
      "learning_rate": 9.6809e-06,
      "loss": 1.2761,
      "step": 3200
    },
    {
      "epoch": 49.23076923076923,
      "eval_loss": 1.390371561050415,
      "eval_runtime": 11.2406,
      "eval_samples_per_second": 11.654,
      "eval_steps_per_second": 1.512,
      "step": 3200
    },
    {
      "epoch": 50.76923076923077,
      "grad_norm": 17.050870895385742,
      "learning_rate": 9.670900000000001e-06,
      "loss": 1.2712,
      "step": 3300
    },
    {
      "epoch": 50.76923076923077,
      "eval_loss": 1.3936753273010254,
      "eval_runtime": 11.2364,
      "eval_samples_per_second": 11.659,
      "eval_steps_per_second": 1.513,
      "step": 3300
    },
    {
      "epoch": 52.30769230769231,
      "grad_norm": 232.21804809570312,
      "learning_rate": 9.660900000000001e-06,
      "loss": 1.262,
      "step": 3400
    },
    {
      "epoch": 52.30769230769231,
      "eval_loss": 1.4037091732025146,
      "eval_runtime": 11.2231,
      "eval_samples_per_second": 11.672,
      "eval_steps_per_second": 1.515,
      "step": 3400
    },
    {
      "epoch": 53.84615384615385,
      "grad_norm": 35.11832046508789,
      "learning_rate": 9.650900000000001e-06,
      "loss": 1.2788,
      "step": 3500
    },
    {
      "epoch": 53.84615384615385,
      "eval_loss": 1.3545280694961548,
      "eval_runtime": 11.1609,
      "eval_samples_per_second": 11.737,
      "eval_steps_per_second": 1.523,
      "step": 3500
    },
    {
      "epoch": 55.38461538461539,
      "grad_norm": 27.077022552490234,
      "learning_rate": 9.640900000000001e-06,
      "loss": 1.2711,
      "step": 3600
    },
    {
      "epoch": 55.38461538461539,
      "eval_loss": 1.3528518676757812,
      "eval_runtime": 11.2852,
      "eval_samples_per_second": 11.608,
      "eval_steps_per_second": 1.506,
      "step": 3600
    },
    {
      "epoch": 56.92307692307692,
      "grad_norm": 46.97712326049805,
      "learning_rate": 9.630900000000001e-06,
      "loss": 1.2492,
      "step": 3700
    },
    {
      "epoch": 56.92307692307692,
      "eval_loss": 1.3534098863601685,
      "eval_runtime": 11.2368,
      "eval_samples_per_second": 11.658,
      "eval_steps_per_second": 1.513,
      "step": 3700
    },
    {
      "epoch": 58.46153846153846,
      "grad_norm": 42.06857681274414,
      "learning_rate": 9.620900000000001e-06,
      "loss": 1.2506,
      "step": 3800
    },
    {
      "epoch": 58.46153846153846,
      "eval_loss": 1.3613977432250977,
      "eval_runtime": 11.2206,
      "eval_samples_per_second": 11.675,
      "eval_steps_per_second": 1.515,
      "step": 3800
    },
    {
      "epoch": 60.0,
      "grad_norm": 19.298952102661133,
      "learning_rate": 9.610900000000001e-06,
      "loss": 1.2201,
      "step": 3900
    },
    {
      "epoch": 60.0,
      "eval_loss": 1.3586474657058716,
      "eval_runtime": 11.2045,
      "eval_samples_per_second": 11.692,
      "eval_steps_per_second": 1.517,
      "step": 3900
    },
    {
      "epoch": 61.53846153846154,
      "grad_norm": 30.0198974609375,
      "learning_rate": 9.600900000000002e-06,
      "loss": 1.2086,
      "step": 4000
    },
    {
      "epoch": 61.53846153846154,
      "eval_loss": 1.3304755687713623,
      "eval_runtime": 11.193,
      "eval_samples_per_second": 11.704,
      "eval_steps_per_second": 1.519,
      "step": 4000
    },
    {
      "epoch": 63.07692307692308,
      "grad_norm": 37.59902572631836,
      "learning_rate": 9.5909e-06,
      "loss": 1.2375,
      "step": 4100
    },
    {
      "epoch": 63.07692307692308,
      "eval_loss": 1.331407904624939,
      "eval_runtime": 10.6714,
      "eval_samples_per_second": 12.276,
      "eval_steps_per_second": 1.593,
      "step": 4100
    },
    {
      "epoch": 64.61538461538461,
      "grad_norm": 36.82079315185547,
      "learning_rate": 9.5809e-06,
      "loss": 1.2148,
      "step": 4200
    },
    {
      "epoch": 64.61538461538461,
      "eval_loss": 1.3441548347473145,
      "eval_runtime": 10.7472,
      "eval_samples_per_second": 12.189,
      "eval_steps_per_second": 1.582,
      "step": 4200
    },
    {
      "epoch": 66.15384615384616,
      "grad_norm": 30.974130630493164,
      "learning_rate": 9.5709e-06,
      "loss": 1.197,
      "step": 4300
    },
    {
      "epoch": 66.15384615384616,
      "eval_loss": 1.34512197971344,
      "eval_runtime": 10.7398,
      "eval_samples_per_second": 12.198,
      "eval_steps_per_second": 1.583,
      "step": 4300
    },
    {
      "epoch": 67.6923076923077,
      "grad_norm": 20.45345115661621,
      "learning_rate": 9.5609e-06,
      "loss": 1.2361,
      "step": 4400
    },
    {
      "epoch": 67.6923076923077,
      "eval_loss": 1.3371080160140991,
      "eval_runtime": 10.654,
      "eval_samples_per_second": 12.296,
      "eval_steps_per_second": 1.596,
      "step": 4400
    },
    {
      "epoch": 69.23076923076923,
      "grad_norm": 19.758630752563477,
      "learning_rate": 9.5509e-06,
      "loss": 1.2001,
      "step": 4500
    },
    {
      "epoch": 69.23076923076923,
      "eval_loss": 1.3270760774612427,
      "eval_runtime": 10.6928,
      "eval_samples_per_second": 12.251,
      "eval_steps_per_second": 1.59,
      "step": 4500
    },
    {
      "epoch": 70.76923076923077,
      "grad_norm": 45.2899055480957,
      "learning_rate": 9.5409e-06,
      "loss": 1.192,
      "step": 4600
    },
    {
      "epoch": 70.76923076923077,
      "eval_loss": 1.3184590339660645,
      "eval_runtime": 10.7154,
      "eval_samples_per_second": 12.225,
      "eval_steps_per_second": 1.586,
      "step": 4600
    },
    {
      "epoch": 72.3076923076923,
      "grad_norm": 45.60734939575195,
      "learning_rate": 9.5309e-06,
      "loss": 1.2081,
      "step": 4700
    },
    {
      "epoch": 72.3076923076923,
      "eval_loss": 1.3107666969299316,
      "eval_runtime": 10.7029,
      "eval_samples_per_second": 12.24,
      "eval_steps_per_second": 1.588,
      "step": 4700
    },
    {
      "epoch": 73.84615384615384,
      "grad_norm": 26.859603881835938,
      "learning_rate": 9.5209e-06,
      "loss": 1.1729,
      "step": 4800
    },
    {
      "epoch": 73.84615384615384,
      "eval_loss": 1.310062289237976,
      "eval_runtime": 10.7544,
      "eval_samples_per_second": 12.181,
      "eval_steps_per_second": 1.581,
      "step": 4800
    },
    {
      "epoch": 75.38461538461539,
      "grad_norm": 19.90914535522461,
      "learning_rate": 9.5109e-06,
      "loss": 1.1899,
      "step": 4900
    },
    {
      "epoch": 75.38461538461539,
      "eval_loss": 1.3038017749786377,
      "eval_runtime": 10.6532,
      "eval_samples_per_second": 12.297,
      "eval_steps_per_second": 1.596,
      "step": 4900
    },
    {
      "epoch": 76.92307692307692,
      "grad_norm": 22.629934310913086,
      "learning_rate": 9.5009e-06,
      "loss": 1.1875,
      "step": 5000
    },
    {
      "epoch": 76.92307692307692,
      "eval_loss": 1.2785409688949585,
      "eval_runtime": 10.6388,
      "eval_samples_per_second": 12.313,
      "eval_steps_per_second": 1.598,
      "step": 5000
    },
    {
      "epoch": 78.46153846153847,
      "grad_norm": 45.462059020996094,
      "learning_rate": 9.490900000000001e-06,
      "loss": 1.1717,
      "step": 5100
    },
    {
      "epoch": 78.46153846153847,
      "eval_loss": 1.278078317642212,
      "eval_runtime": 10.9666,
      "eval_samples_per_second": 11.945,
      "eval_steps_per_second": 1.55,
      "step": 5100
    },
    {
      "epoch": 80.0,
      "grad_norm": 34.85255432128906,
      "learning_rate": 9.480900000000001e-06,
      "loss": 1.1657,
      "step": 5200
    },
    {
      "epoch": 80.0,
      "eval_loss": 1.2711185216903687,
      "eval_runtime": 11.0211,
      "eval_samples_per_second": 11.886,
      "eval_steps_per_second": 1.543,
      "step": 5200
    },
    {
      "epoch": 81.53846153846153,
      "grad_norm": 19.078449249267578,
      "learning_rate": 9.470900000000001e-06,
      "loss": 1.1814,
      "step": 5300
    },
    {
      "epoch": 81.53846153846153,
      "eval_loss": 1.2781996726989746,
      "eval_runtime": 11.0663,
      "eval_samples_per_second": 11.838,
      "eval_steps_per_second": 1.536,
      "step": 5300
    },
    {
      "epoch": 83.07692307692308,
      "grad_norm": 31.05898094177246,
      "learning_rate": 9.460900000000001e-06,
      "loss": 1.1452,
      "step": 5400
    },
    {
      "epoch": 83.07692307692308,
      "eval_loss": 1.2848775386810303,
      "eval_runtime": 11.01,
      "eval_samples_per_second": 11.898,
      "eval_steps_per_second": 1.544,
      "step": 5400
    },
    {
      "epoch": 84.61538461538461,
      "grad_norm": 28.712461471557617,
      "learning_rate": 9.450900000000001e-06,
      "loss": 1.1465,
      "step": 5500
    },
    {
      "epoch": 84.61538461538461,
      "eval_loss": 1.2928494215011597,
      "eval_runtime": 10.9253,
      "eval_samples_per_second": 11.991,
      "eval_steps_per_second": 1.556,
      "step": 5500
    },
    {
      "epoch": 86.15384615384616,
      "grad_norm": 19.871828079223633,
      "learning_rate": 9.440900000000001e-06,
      "loss": 1.1736,
      "step": 5600
    },
    {
      "epoch": 86.15384615384616,
      "eval_loss": 1.2648124694824219,
      "eval_runtime": 11.0314,
      "eval_samples_per_second": 11.875,
      "eval_steps_per_second": 1.541,
      "step": 5600
    },
    {
      "epoch": 87.6923076923077,
      "grad_norm": 22.47665023803711,
      "learning_rate": 9.4309e-06,
      "loss": 1.1184,
      "step": 5700
    },
    {
      "epoch": 87.6923076923077,
      "eval_loss": 1.2936598062515259,
      "eval_runtime": 10.9322,
      "eval_samples_per_second": 11.983,
      "eval_steps_per_second": 1.555,
      "step": 5700
    },
    {
      "epoch": 89.23076923076923,
      "grad_norm": 38.79877471923828,
      "learning_rate": 9.4209e-06,
      "loss": 1.1616,
      "step": 5800
    },
    {
      "epoch": 89.23076923076923,
      "eval_loss": 1.2650004625320435,
      "eval_runtime": 10.9434,
      "eval_samples_per_second": 11.971,
      "eval_steps_per_second": 1.553,
      "step": 5800
    },
    {
      "epoch": 90.76923076923077,
      "grad_norm": 40.851097106933594,
      "learning_rate": 9.4109e-06,
      "loss": 1.1469,
      "step": 5900
    },
    {
      "epoch": 90.76923076923077,
      "eval_loss": 1.252148151397705,
      "eval_runtime": 10.9867,
      "eval_samples_per_second": 11.923,
      "eval_steps_per_second": 1.547,
      "step": 5900
    },
    {
      "epoch": 92.3076923076923,
      "grad_norm": 21.35544204711914,
      "learning_rate": 9.4009e-06,
      "loss": 1.1489,
      "step": 6000
    },
    {
      "epoch": 92.3076923076923,
      "eval_loss": 1.259344220161438,
      "eval_runtime": 10.9649,
      "eval_samples_per_second": 11.947,
      "eval_steps_per_second": 1.55,
      "step": 6000
    },
    {
      "epoch": 93.84615384615384,
      "grad_norm": 33.265132904052734,
      "learning_rate": 9.3909e-06,
      "loss": 1.1315,
      "step": 6100
    },
    {
      "epoch": 93.84615384615384,
      "eval_loss": 1.252693772315979,
      "eval_runtime": 10.9852,
      "eval_samples_per_second": 11.925,
      "eval_steps_per_second": 1.548,
      "step": 6100
    },
    {
      "epoch": 95.38461538461539,
      "grad_norm": 23.43667221069336,
      "learning_rate": 9.381e-06,
      "loss": 1.119,
      "step": 6200
    },
    {
      "epoch": 95.38461538461539,
      "eval_loss": 1.254772424697876,
      "eval_runtime": 11.0937,
      "eval_samples_per_second": 11.808,
      "eval_steps_per_second": 1.532,
      "step": 6200
    },
    {
      "epoch": 96.92307692307692,
      "grad_norm": 51.93602752685547,
      "learning_rate": 9.371e-06,
      "loss": 1.1333,
      "step": 6300
    },
    {
      "epoch": 96.92307692307692,
      "eval_loss": 1.249408483505249,
      "eval_runtime": 11.0388,
      "eval_samples_per_second": 11.867,
      "eval_steps_per_second": 1.54,
      "step": 6300
    },
    {
      "epoch": 98.46153846153847,
      "grad_norm": 23.473421096801758,
      "learning_rate": 9.361e-06,
      "loss": 1.1164,
      "step": 6400
    },
    {
      "epoch": 98.46153846153847,
      "eval_loss": 1.2438522577285767,
      "eval_runtime": 11.1581,
      "eval_samples_per_second": 11.74,
      "eval_steps_per_second": 1.524,
      "step": 6400
    },
    {
      "epoch": 100.0,
      "grad_norm": 24.228403091430664,
      "learning_rate": 9.351e-06,
      "loss": 1.1333,
      "step": 6500
    },
    {
      "epoch": 100.0,
      "eval_loss": 1.248632788658142,
      "eval_runtime": 10.9675,
      "eval_samples_per_second": 11.944,
      "eval_steps_per_second": 1.55,
      "step": 6500
    },
    {
      "epoch": 101.53846153846153,
      "grad_norm": 18.29631996154785,
      "learning_rate": 9.341000000000001e-06,
      "loss": 1.1082,
      "step": 6600
    },
    {
      "epoch": 101.53846153846153,
      "eval_loss": 1.2509865760803223,
      "eval_runtime": 11.0693,
      "eval_samples_per_second": 11.834,
      "eval_steps_per_second": 1.536,
      "step": 6600
    },
    {
      "epoch": 103.07692307692308,
      "grad_norm": 42.855491638183594,
      "learning_rate": 9.331000000000001e-06,
      "loss": 1.1178,
      "step": 6700
    },
    {
      "epoch": 103.07692307692308,
      "eval_loss": 1.2890292406082153,
      "eval_runtime": 11.0366,
      "eval_samples_per_second": 11.87,
      "eval_steps_per_second": 1.54,
      "step": 6700
    },
    {
      "epoch": 104.61538461538461,
      "grad_norm": 46.675655364990234,
      "learning_rate": 9.321000000000001e-06,
      "loss": 1.1106,
      "step": 6800
    },
    {
      "epoch": 104.61538461538461,
      "eval_loss": 1.2719863653182983,
      "eval_runtime": 11.1266,
      "eval_samples_per_second": 11.774,
      "eval_steps_per_second": 1.528,
      "step": 6800
    },
    {
      "epoch": 106.15384615384616,
      "grad_norm": 26.414846420288086,
      "learning_rate": 9.311000000000001e-06,
      "loss": 1.1216,
      "step": 6900
    },
    {
      "epoch": 106.15384615384616,
      "eval_loss": 1.2423394918441772,
      "eval_runtime": 11.0197,
      "eval_samples_per_second": 11.888,
      "eval_steps_per_second": 1.543,
      "step": 6900
    },
    {
      "epoch": 107.6923076923077,
      "grad_norm": 31.4022274017334,
      "learning_rate": 9.301000000000001e-06,
      "loss": 1.1052,
      "step": 7000
    },
    {
      "epoch": 107.6923076923077,
      "eval_loss": 1.2372961044311523,
      "eval_runtime": 11.1127,
      "eval_samples_per_second": 11.788,
      "eval_steps_per_second": 1.53,
      "step": 7000
    },
    {
      "epoch": 109.23076923076923,
      "grad_norm": 23.16703987121582,
      "learning_rate": 9.291000000000001e-06,
      "loss": 1.0911,
      "step": 7100
    },
    {
      "epoch": 109.23076923076923,
      "eval_loss": 1.2309863567352295,
      "eval_runtime": 10.9572,
      "eval_samples_per_second": 11.956,
      "eval_steps_per_second": 1.551,
      "step": 7100
    },
    {
      "epoch": 110.76923076923077,
      "grad_norm": 21.648773193359375,
      "learning_rate": 9.281000000000001e-06,
      "loss": 1.0956,
      "step": 7200
    },
    {
      "epoch": 110.76923076923077,
      "eval_loss": 1.2261079549789429,
      "eval_runtime": 10.9351,
      "eval_samples_per_second": 11.98,
      "eval_steps_per_second": 1.555,
      "step": 7200
    },
    {
      "epoch": 112.3076923076923,
      "grad_norm": 24.5791072845459,
      "learning_rate": 9.271000000000002e-06,
      "loss": 1.0751,
      "step": 7300
    },
    {
      "epoch": 112.3076923076923,
      "eval_loss": 1.2161471843719482,
      "eval_runtime": 11.1052,
      "eval_samples_per_second": 11.796,
      "eval_steps_per_second": 1.531,
      "step": 7300
    },
    {
      "epoch": 113.84615384615384,
      "grad_norm": 35.867801666259766,
      "learning_rate": 9.261000000000002e-06,
      "loss": 1.086,
      "step": 7400
    },
    {
      "epoch": 113.84615384615384,
      "eval_loss": 1.2092362642288208,
      "eval_runtime": 11.2048,
      "eval_samples_per_second": 11.691,
      "eval_steps_per_second": 1.517,
      "step": 7400
    },
    {
      "epoch": 115.38461538461539,
      "grad_norm": 67.91041564941406,
      "learning_rate": 9.251000000000002e-06,
      "loss": 1.092,
      "step": 7500
    },
    {
      "epoch": 115.38461538461539,
      "eval_loss": 1.241829514503479,
      "eval_runtime": 10.9937,
      "eval_samples_per_second": 11.916,
      "eval_steps_per_second": 1.546,
      "step": 7500
    },
    {
      "epoch": 116.92307692307692,
      "grad_norm": 128.73751831054688,
      "learning_rate": 9.241000000000002e-06,
      "loss": 1.0764,
      "step": 7600
    },
    {
      "epoch": 116.92307692307692,
      "eval_loss": 1.2462713718414307,
      "eval_runtime": 10.9625,
      "eval_samples_per_second": 11.95,
      "eval_steps_per_second": 1.551,
      "step": 7600
    },
    {
      "epoch": 118.46153846153847,
      "grad_norm": 86.5144271850586,
      "learning_rate": 9.231000000000002e-06,
      "loss": 1.0643,
      "step": 7700
    },
    {
      "epoch": 118.46153846153847,
      "eval_loss": 1.2187525033950806,
      "eval_runtime": 10.9492,
      "eval_samples_per_second": 11.964,
      "eval_steps_per_second": 1.553,
      "step": 7700
    },
    {
      "epoch": 120.0,
      "grad_norm": 19.4710750579834,
      "learning_rate": 9.221e-06,
      "loss": 1.0966,
      "step": 7800
    },
    {
      "epoch": 120.0,
      "eval_loss": 1.2282384634017944,
      "eval_runtime": 10.9078,
      "eval_samples_per_second": 12.01,
      "eval_steps_per_second": 1.559,
      "step": 7800
    },
    {
      "epoch": 121.53846153846153,
      "grad_norm": 37.673744201660156,
      "learning_rate": 9.211e-06,
      "loss": 1.0632,
      "step": 7900
    },
    {
      "epoch": 121.53846153846153,
      "eval_loss": 1.2206230163574219,
      "eval_runtime": 11.0018,
      "eval_samples_per_second": 11.907,
      "eval_steps_per_second": 1.545,
      "step": 7900
    },
    {
      "epoch": 123.07692307692308,
      "grad_norm": 25.10326385498047,
      "learning_rate": 9.201e-06,
      "loss": 1.0873,
      "step": 8000
    },
    {
      "epoch": 123.07692307692308,
      "eval_loss": 1.2137339115142822,
      "eval_runtime": 10.9232,
      "eval_samples_per_second": 11.993,
      "eval_steps_per_second": 1.556,
      "step": 8000
    },
    {
      "epoch": 124.61538461538461,
      "grad_norm": 32.02176284790039,
      "learning_rate": 9.191e-06,
      "loss": 1.0568,
      "step": 8100
    },
    {
      "epoch": 124.61538461538461,
      "eval_loss": 1.2065187692642212,
      "eval_runtime": 10.9614,
      "eval_samples_per_second": 11.951,
      "eval_steps_per_second": 1.551,
      "step": 8100
    },
    {
      "epoch": 126.15384615384616,
      "grad_norm": 19.97406005859375,
      "learning_rate": 9.181e-06,
      "loss": 1.065,
      "step": 8200
    },
    {
      "epoch": 126.15384615384616,
      "eval_loss": 1.2094841003417969,
      "eval_runtime": 11.0274,
      "eval_samples_per_second": 11.879,
      "eval_steps_per_second": 1.542,
      "step": 8200
    },
    {
      "epoch": 127.6923076923077,
      "grad_norm": 31.624399185180664,
      "learning_rate": 9.171e-06,
      "loss": 1.0805,
      "step": 8300
    },
    {
      "epoch": 127.6923076923077,
      "eval_loss": 1.2149733304977417,
      "eval_runtime": 11.2014,
      "eval_samples_per_second": 11.695,
      "eval_steps_per_second": 1.518,
      "step": 8300
    },
    {
      "epoch": 129.23076923076923,
      "grad_norm": 29.24848747253418,
      "learning_rate": 9.161000000000001e-06,
      "loss": 1.0463,
      "step": 8400
    },
    {
      "epoch": 129.23076923076923,
      "eval_loss": 1.2077099084854126,
      "eval_runtime": 10.9432,
      "eval_samples_per_second": 11.971,
      "eval_steps_per_second": 1.553,
      "step": 8400
    },
    {
      "epoch": 130.76923076923077,
      "grad_norm": 27.14787483215332,
      "learning_rate": 9.151000000000001e-06,
      "loss": 1.0607,
      "step": 8500
    },
    {
      "epoch": 130.76923076923077,
      "eval_loss": 1.2046644687652588,
      "eval_runtime": 11.001,
      "eval_samples_per_second": 11.908,
      "eval_steps_per_second": 1.545,
      "step": 8500
    },
    {
      "epoch": 132.30769230769232,
      "grad_norm": 32.416194915771484,
      "learning_rate": 9.141000000000001e-06,
      "loss": 1.0365,
      "step": 8600
    },
    {
      "epoch": 132.30769230769232,
      "eval_loss": 1.195080041885376,
      "eval_runtime": 11.0205,
      "eval_samples_per_second": 11.887,
      "eval_steps_per_second": 1.543,
      "step": 8600
    },
    {
      "epoch": 133.84615384615384,
      "grad_norm": 58.863582611083984,
      "learning_rate": 9.131000000000001e-06,
      "loss": 1.0564,
      "step": 8700
    },
    {
      "epoch": 133.84615384615384,
      "eval_loss": 1.1966980695724487,
      "eval_runtime": 10.9043,
      "eval_samples_per_second": 12.014,
      "eval_steps_per_second": 1.559,
      "step": 8700
    },
    {
      "epoch": 135.3846153846154,
      "grad_norm": 26.08232307434082,
      "learning_rate": 9.121000000000001e-06,
      "loss": 1.0507,
      "step": 8800
    },
    {
      "epoch": 135.3846153846154,
      "eval_loss": 1.201367735862732,
      "eval_runtime": 10.9714,
      "eval_samples_per_second": 11.94,
      "eval_steps_per_second": 1.549,
      "step": 8800
    },
    {
      "epoch": 136.92307692307693,
      "grad_norm": 59.368019104003906,
      "learning_rate": 9.111000000000001e-06,
      "loss": 1.0508,
      "step": 8900
    },
    {
      "epoch": 136.92307692307693,
      "eval_loss": 1.208795428276062,
      "eval_runtime": 11.0529,
      "eval_samples_per_second": 11.852,
      "eval_steps_per_second": 1.538,
      "step": 8900
    },
    {
      "epoch": 138.46153846153845,
      "grad_norm": 43.07460021972656,
      "learning_rate": 9.101000000000001e-06,
      "loss": 1.0359,
      "step": 9000
    },
    {
      "epoch": 138.46153846153845,
      "eval_loss": 1.1782392263412476,
      "eval_runtime": 11.1519,
      "eval_samples_per_second": 11.747,
      "eval_steps_per_second": 1.524,
      "step": 9000
    },
    {
      "epoch": 140.0,
      "grad_norm": 22.39567756652832,
      "learning_rate": 9.091000000000002e-06,
      "loss": 1.0584,
      "step": 9100
    },
    {
      "epoch": 140.0,
      "eval_loss": 1.1873483657836914,
      "eval_runtime": 10.8732,
      "eval_samples_per_second": 12.048,
      "eval_steps_per_second": 1.563,
      "step": 9100
    },
    {
      "epoch": 141.53846153846155,
      "grad_norm": 22.813621520996094,
      "learning_rate": 9.081000000000002e-06,
      "loss": 1.0354,
      "step": 9200
    },
    {
      "epoch": 141.53846153846155,
      "eval_loss": 1.1731117963790894,
      "eval_runtime": 11.0847,
      "eval_samples_per_second": 11.818,
      "eval_steps_per_second": 1.534,
      "step": 9200
    },
    {
      "epoch": 143.07692307692307,
      "grad_norm": 31.44073486328125,
      "learning_rate": 9.071000000000002e-06,
      "loss": 1.0457,
      "step": 9300
    },
    {
      "epoch": 143.07692307692307,
      "eval_loss": 1.1962807178497314,
      "eval_runtime": 11.0668,
      "eval_samples_per_second": 11.837,
      "eval_steps_per_second": 1.536,
      "step": 9300
    },
    {
      "epoch": 144.6153846153846,
      "grad_norm": 18.18711280822754,
      "learning_rate": 9.061e-06,
      "loss": 1.0481,
      "step": 9400
    },
    {
      "epoch": 144.6153846153846,
      "eval_loss": 1.185339093208313,
      "eval_runtime": 10.9916,
      "eval_samples_per_second": 11.918,
      "eval_steps_per_second": 1.547,
      "step": 9400
    },
    {
      "epoch": 146.15384615384616,
      "grad_norm": 38.05665969848633,
      "learning_rate": 9.051e-06,
      "loss": 1.0391,
      "step": 9500
    },
    {
      "epoch": 146.15384615384616,
      "eval_loss": 1.1856777667999268,
      "eval_runtime": 11.0391,
      "eval_samples_per_second": 11.867,
      "eval_steps_per_second": 1.54,
      "step": 9500
    },
    {
      "epoch": 147.69230769230768,
      "grad_norm": 19.963260650634766,
      "learning_rate": 9.041e-06,
      "loss": 1.0322,
      "step": 9600
    },
    {
      "epoch": 147.69230769230768,
      "eval_loss": 1.1843148469924927,
      "eval_runtime": 11.0382,
      "eval_samples_per_second": 11.868,
      "eval_steps_per_second": 1.54,
      "step": 9600
    },
    {
      "epoch": 149.23076923076923,
      "grad_norm": 28.58108901977539,
      "learning_rate": 9.031e-06,
      "loss": 1.0369,
      "step": 9700
    },
    {
      "epoch": 149.23076923076923,
      "eval_loss": 1.1637182235717773,
      "eval_runtime": 11.2766,
      "eval_samples_per_second": 11.617,
      "eval_steps_per_second": 1.508,
      "step": 9700
    },
    {
      "epoch": 150.76923076923077,
      "grad_norm": 64.3956527709961,
      "learning_rate": 9.021e-06,
      "loss": 1.0519,
      "step": 9800
    },
    {
      "epoch": 150.76923076923077,
      "eval_loss": 1.1796802282333374,
      "eval_runtime": 11.3418,
      "eval_samples_per_second": 11.55,
      "eval_steps_per_second": 1.499,
      "step": 9800
    },
    {
      "epoch": 152.30769230769232,
      "grad_norm": 18.857580184936523,
      "learning_rate": 9.011e-06,
      "loss": 1.0272,
      "step": 9900
    },
    {
      "epoch": 152.30769230769232,
      "eval_loss": 1.1634279489517212,
      "eval_runtime": 11.6749,
      "eval_samples_per_second": 11.221,
      "eval_steps_per_second": 1.456,
      "step": 9900
    },
    {
      "epoch": 153.84615384615384,
      "grad_norm": 42.541683197021484,
      "learning_rate": 9.001e-06,
      "loss": 1.0287,
      "step": 10000
    },
    {
      "epoch": 153.84615384615384,
      "eval_loss": 1.1698088645935059,
      "eval_runtime": 11.068,
      "eval_samples_per_second": 11.836,
      "eval_steps_per_second": 1.536,
      "step": 10000
    },
    {
      "epoch": 155.3846153846154,
      "grad_norm": 30.52286720275879,
      "learning_rate": 8.991e-06,
      "loss": 1.0237,
      "step": 10100
    },
    {
      "epoch": 155.3846153846154,
      "eval_loss": 1.178311824798584,
      "eval_runtime": 11.1107,
      "eval_samples_per_second": 11.79,
      "eval_steps_per_second": 1.53,
      "step": 10100
    },
    {
      "epoch": 156.92307692307693,
      "grad_norm": 32.60612487792969,
      "learning_rate": 8.981000000000001e-06,
      "loss": 1.0362,
      "step": 10200
    },
    {
      "epoch": 156.92307692307693,
      "eval_loss": 1.157893180847168,
      "eval_runtime": 11.0484,
      "eval_samples_per_second": 11.857,
      "eval_steps_per_second": 1.539,
      "step": 10200
    },
    {
      "epoch": 158.46153846153845,
      "grad_norm": 26.15647315979004,
      "learning_rate": 8.971000000000001e-06,
      "loss": 0.998,
      "step": 10300
    },
    {
      "epoch": 158.46153846153845,
      "eval_loss": 1.1724605560302734,
      "eval_runtime": 11.2323,
      "eval_samples_per_second": 11.663,
      "eval_steps_per_second": 1.513,
      "step": 10300
    },
    {
      "epoch": 160.0,
      "grad_norm": 45.76993942260742,
      "learning_rate": 8.961000000000001e-06,
      "loss": 1.0432,
      "step": 10400
    },
    {
      "epoch": 160.0,
      "eval_loss": 1.1688075065612793,
      "eval_runtime": 11.0984,
      "eval_samples_per_second": 11.803,
      "eval_steps_per_second": 1.532,
      "step": 10400
    },
    {
      "epoch": 161.53846153846155,
      "grad_norm": 40.384578704833984,
      "learning_rate": 8.951000000000001e-06,
      "loss": 1.0421,
      "step": 10500
    },
    {
      "epoch": 161.53846153846155,
      "eval_loss": 1.1621845960617065,
      "eval_runtime": 11.1624,
      "eval_samples_per_second": 11.736,
      "eval_steps_per_second": 1.523,
      "step": 10500
    },
    {
      "epoch": 163.07692307692307,
      "grad_norm": 22.886058807373047,
      "learning_rate": 8.941000000000001e-06,
      "loss": 0.9912,
      "step": 10600
    },
    {
      "epoch": 163.07692307692307,
      "eval_loss": 1.1695055961608887,
      "eval_runtime": 10.9842,
      "eval_samples_per_second": 11.926,
      "eval_steps_per_second": 1.548,
      "step": 10600
    },
    {
      "epoch": 164.6153846153846,
      "grad_norm": 26.940736770629883,
      "learning_rate": 8.931000000000001e-06,
      "loss": 1.011,
      "step": 10700
    },
    {
      "epoch": 164.6153846153846,
      "eval_loss": 1.1458157300949097,
      "eval_runtime": 11.025,
      "eval_samples_per_second": 11.882,
      "eval_steps_per_second": 1.542,
      "step": 10700
    },
    {
      "epoch": 166.15384615384616,
      "grad_norm": 26.5013484954834,
      "learning_rate": 8.921000000000001e-06,
      "loss": 0.9876,
      "step": 10800
    },
    {
      "epoch": 166.15384615384616,
      "eval_loss": 1.1569631099700928,
      "eval_runtime": 11.101,
      "eval_samples_per_second": 11.801,
      "eval_steps_per_second": 1.531,
      "step": 10800
    },
    {
      "epoch": 167.69230769230768,
      "grad_norm": 29.859987258911133,
      "learning_rate": 8.911000000000002e-06,
      "loss": 1.0374,
      "step": 10900
    },
    {
      "epoch": 167.69230769230768,
      "eval_loss": 1.149316668510437,
      "eval_runtime": 11.1242,
      "eval_samples_per_second": 11.776,
      "eval_steps_per_second": 1.528,
      "step": 10900
    },
    {
      "epoch": 169.23076923076923,
      "grad_norm": 27.777738571166992,
      "learning_rate": 8.901e-06,
      "loss": 0.985,
      "step": 11000
    },
    {
      "epoch": 169.23076923076923,
      "eval_loss": 1.1608328819274902,
      "eval_runtime": 11.2215,
      "eval_samples_per_second": 11.674,
      "eval_steps_per_second": 1.515,
      "step": 11000
    }
  ],
  "logging_steps": 100,
  "max_steps": 100000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1539,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.222258013933568e+19,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}