{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 61.53846153846154,
  "eval_steps": 100,
  "global_step": 4000,
  "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
    }
  ],
  "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": 1.528972664832e+19,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}