{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 51.282051282051285,
  "eval_steps": 100,
  "global_step": 10000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 81.8341293334961,
      "learning_rate": 9.990900000000001e-06,
      "loss": 3.5606,
      "step": 100
    },
    {
      "epoch": 0.5128205128205128,
      "eval_loss": 2.2667126655578613,
      "eval_runtime": 33.7385,
      "eval_samples_per_second": 11.648,
      "eval_steps_per_second": 1.482,
      "step": 100
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 30.16681671142578,
      "learning_rate": 9.980900000000001e-06,
      "loss": 2.1841,
      "step": 200
    },
    {
      "epoch": 1.0256410256410255,
      "eval_loss": 2.059685230255127,
      "eval_runtime": 33.6897,
      "eval_samples_per_second": 11.665,
      "eval_steps_per_second": 1.484,
      "step": 200
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 67.16844177246094,
      "learning_rate": 9.970900000000001e-06,
      "loss": 2.0949,
      "step": 300
    },
    {
      "epoch": 1.5384615384615383,
      "eval_loss": 1.9054155349731445,
      "eval_runtime": 33.6472,
      "eval_samples_per_second": 11.68,
      "eval_steps_per_second": 1.486,
      "step": 300
    },
    {
      "epoch": 2.051282051282051,
      "grad_norm": 46.190330505371094,
      "learning_rate": 9.960900000000001e-06,
      "loss": 1.9236,
      "step": 400
    },
    {
      "epoch": 2.051282051282051,
      "eval_loss": 1.8464823961257935,
      "eval_runtime": 33.8143,
      "eval_samples_per_second": 11.622,
      "eval_steps_per_second": 1.479,
      "step": 400
    },
    {
      "epoch": 2.564102564102564,
      "grad_norm": 42.82326889038086,
      "learning_rate": 9.950900000000002e-06,
      "loss": 1.937,
      "step": 500
    },
    {
      "epoch": 2.564102564102564,
      "eval_loss": 1.8186373710632324,
      "eval_runtime": 33.9112,
      "eval_samples_per_second": 11.589,
      "eval_steps_per_second": 1.474,
      "step": 500
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 68.72016906738281,
      "learning_rate": 9.940900000000002e-06,
      "loss": 1.8648,
      "step": 600
    },
    {
      "epoch": 3.076923076923077,
      "eval_loss": 1.7807129621505737,
      "eval_runtime": 33.4957,
      "eval_samples_per_second": 11.733,
      "eval_steps_per_second": 1.493,
      "step": 600
    },
    {
      "epoch": 3.58974358974359,
      "grad_norm": 51.390071868896484,
      "learning_rate": 9.930900000000002e-06,
      "loss": 1.8162,
      "step": 700
    },
    {
      "epoch": 3.58974358974359,
      "eval_loss": 1.7275961637496948,
      "eval_runtime": 33.6095,
      "eval_samples_per_second": 11.693,
      "eval_steps_per_second": 1.488,
      "step": 700
    },
    {
      "epoch": 4.102564102564102,
      "grad_norm": 33.017948150634766,
      "learning_rate": 9.920900000000002e-06,
      "loss": 1.7331,
      "step": 800
    },
    {
      "epoch": 4.102564102564102,
      "eval_loss": 1.701725959777832,
      "eval_runtime": 33.9602,
      "eval_samples_per_second": 11.572,
      "eval_steps_per_second": 1.472,
      "step": 800
    },
    {
      "epoch": 4.615384615384615,
      "grad_norm": 43.55423355102539,
      "learning_rate": 9.9109e-06,
      "loss": 1.7091,
      "step": 900
    },
    {
      "epoch": 4.615384615384615,
      "eval_loss": 1.6944857835769653,
      "eval_runtime": 33.6785,
      "eval_samples_per_second": 11.669,
      "eval_steps_per_second": 1.485,
      "step": 900
    },
    {
      "epoch": 5.128205128205128,
      "grad_norm": 67.6618881225586,
      "learning_rate": 9.9009e-06,
      "loss": 1.7258,
      "step": 1000
    },
    {
      "epoch": 5.128205128205128,
      "eval_loss": 1.65646493434906,
      "eval_runtime": 33.8316,
      "eval_samples_per_second": 11.616,
      "eval_steps_per_second": 1.478,
      "step": 1000
    },
    {
      "epoch": 5.641025641025641,
      "grad_norm": 35.863487243652344,
      "learning_rate": 9.8909e-06,
      "loss": 1.661,
      "step": 1100
    },
    {
      "epoch": 5.641025641025641,
      "eval_loss": 1.6175495386123657,
      "eval_runtime": 33.57,
      "eval_samples_per_second": 11.707,
      "eval_steps_per_second": 1.489,
      "step": 1100
    },
    {
      "epoch": 6.153846153846154,
      "grad_norm": 56.98338317871094,
      "learning_rate": 9.8809e-06,
      "loss": 1.6368,
      "step": 1200
    },
    {
      "epoch": 6.153846153846154,
      "eval_loss": 1.6185818910598755,
      "eval_runtime": 33.6954,
      "eval_samples_per_second": 11.663,
      "eval_steps_per_second": 1.484,
      "step": 1200
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 90.9850845336914,
      "learning_rate": 9.8709e-06,
      "loss": 1.6771,
      "step": 1300
    },
    {
      "epoch": 6.666666666666667,
      "eval_loss": 1.597514033317566,
      "eval_runtime": 33.5635,
      "eval_samples_per_second": 11.709,
      "eval_steps_per_second": 1.49,
      "step": 1300
    },
    {
      "epoch": 7.17948717948718,
      "grad_norm": 83.6468276977539,
      "learning_rate": 9.8609e-06,
      "loss": 1.5796,
      "step": 1400
    },
    {
      "epoch": 7.17948717948718,
      "eval_loss": 1.57249116897583,
      "eval_runtime": 33.6053,
      "eval_samples_per_second": 11.695,
      "eval_steps_per_second": 1.488,
      "step": 1400
    },
    {
      "epoch": 7.6923076923076925,
      "grad_norm": 42.52065658569336,
      "learning_rate": 9.8509e-06,
      "loss": 1.6012,
      "step": 1500
    },
    {
      "epoch": 7.6923076923076925,
      "eval_loss": 1.5940505266189575,
      "eval_runtime": 33.6416,
      "eval_samples_per_second": 11.682,
      "eval_steps_per_second": 1.486,
      "step": 1500
    },
    {
      "epoch": 8.205128205128204,
      "grad_norm": 64.46149444580078,
      "learning_rate": 9.840900000000001e-06,
      "loss": 1.6107,
      "step": 1600
    },
    {
      "epoch": 8.205128205128204,
      "eval_loss": 1.57711923122406,
      "eval_runtime": 33.8072,
      "eval_samples_per_second": 11.625,
      "eval_steps_per_second": 1.479,
      "step": 1600
    },
    {
      "epoch": 8.717948717948717,
      "grad_norm": 47.13843536376953,
      "learning_rate": 9.830900000000001e-06,
      "loss": 1.6094,
      "step": 1700
    },
    {
      "epoch": 8.717948717948717,
      "eval_loss": 1.5567021369934082,
      "eval_runtime": 33.6256,
      "eval_samples_per_second": 11.688,
      "eval_steps_per_second": 1.487,
      "step": 1700
    },
    {
      "epoch": 9.23076923076923,
      "grad_norm": 60.96649932861328,
      "learning_rate": 9.820900000000001e-06,
      "loss": 1.5679,
      "step": 1800
    },
    {
      "epoch": 9.23076923076923,
      "eval_loss": 1.5404459238052368,
      "eval_runtime": 33.5651,
      "eval_samples_per_second": 11.709,
      "eval_steps_per_second": 1.49,
      "step": 1800
    },
    {
      "epoch": 9.743589743589745,
      "grad_norm": 48.0488395690918,
      "learning_rate": 9.810900000000001e-06,
      "loss": 1.541,
      "step": 1900
    },
    {
      "epoch": 9.743589743589745,
      "eval_loss": 1.5000860691070557,
      "eval_runtime": 33.729,
      "eval_samples_per_second": 11.652,
      "eval_steps_per_second": 1.482,
      "step": 1900
    },
    {
      "epoch": 10.256410256410255,
      "grad_norm": 21.072124481201172,
      "learning_rate": 9.800900000000001e-06,
      "loss": 1.4747,
      "step": 2000
    },
    {
      "epoch": 10.256410256410255,
      "eval_loss": 1.4845048189163208,
      "eval_runtime": 33.6789,
      "eval_samples_per_second": 11.669,
      "eval_steps_per_second": 1.485,
      "step": 2000
    },
    {
      "epoch": 10.76923076923077,
      "grad_norm": 60.55208969116211,
      "learning_rate": 9.790900000000001e-06,
      "loss": 1.5105,
      "step": 2100
    },
    {
      "epoch": 10.76923076923077,
      "eval_loss": 1.4587421417236328,
      "eval_runtime": 33.4313,
      "eval_samples_per_second": 11.755,
      "eval_steps_per_second": 1.496,
      "step": 2100
    },
    {
      "epoch": 11.282051282051283,
      "grad_norm": 26.457704544067383,
      "learning_rate": 9.780900000000002e-06,
      "loss": 1.4769,
      "step": 2200
    },
    {
      "epoch": 11.282051282051283,
      "eval_loss": 1.4588648080825806,
      "eval_runtime": 33.5978,
      "eval_samples_per_second": 11.697,
      "eval_steps_per_second": 1.488,
      "step": 2200
    },
    {
      "epoch": 11.794871794871796,
      "grad_norm": 23.801916122436523,
      "learning_rate": 9.770900000000002e-06,
      "loss": 1.4555,
      "step": 2300
    },
    {
      "epoch": 11.794871794871796,
      "eval_loss": 1.4805899858474731,
      "eval_runtime": 33.4947,
      "eval_samples_per_second": 11.733,
      "eval_steps_per_second": 1.493,
      "step": 2300
    },
    {
      "epoch": 12.307692307692308,
      "grad_norm": 24.780275344848633,
      "learning_rate": 9.760900000000002e-06,
      "loss": 1.4537,
      "step": 2400
    },
    {
      "epoch": 12.307692307692308,
      "eval_loss": 1.4648451805114746,
      "eval_runtime": 33.6877,
      "eval_samples_per_second": 11.666,
      "eval_steps_per_second": 1.484,
      "step": 2400
    },
    {
      "epoch": 12.820512820512821,
      "grad_norm": 65.28894805908203,
      "learning_rate": 9.7509e-06,
      "loss": 1.4788,
      "step": 2500
    },
    {
      "epoch": 12.820512820512821,
      "eval_loss": 1.4453215599060059,
      "eval_runtime": 33.972,
      "eval_samples_per_second": 11.568,
      "eval_steps_per_second": 1.472,
      "step": 2500
    },
    {
      "epoch": 13.333333333333334,
      "grad_norm": 23.36334800720215,
      "learning_rate": 9.7409e-06,
      "loss": 1.4397,
      "step": 2600
    },
    {
      "epoch": 13.333333333333334,
      "eval_loss": 1.4110159873962402,
      "eval_runtime": 33.3905,
      "eval_samples_per_second": 11.77,
      "eval_steps_per_second": 1.497,
      "step": 2600
    },
    {
      "epoch": 13.846153846153847,
      "grad_norm": 24.13091468811035,
      "learning_rate": 9.7309e-06,
      "loss": 1.42,
      "step": 2700
    },
    {
      "epoch": 13.846153846153847,
      "eval_loss": 1.3875733613967896,
      "eval_runtime": 33.5662,
      "eval_samples_per_second": 11.708,
      "eval_steps_per_second": 1.49,
      "step": 2700
    },
    {
      "epoch": 14.35897435897436,
      "grad_norm": 41.02390670776367,
      "learning_rate": 9.7209e-06,
      "loss": 1.3833,
      "step": 2800
    },
    {
      "epoch": 14.35897435897436,
      "eval_loss": 1.3958121538162231,
      "eval_runtime": 33.6111,
      "eval_samples_per_second": 11.693,
      "eval_steps_per_second": 1.488,
      "step": 2800
    },
    {
      "epoch": 14.871794871794872,
      "grad_norm": 25.11317253112793,
      "learning_rate": 9.7109e-06,
      "loss": 1.3839,
      "step": 2900
    },
    {
      "epoch": 14.871794871794872,
      "eval_loss": 1.4024689197540283,
      "eval_runtime": 33.5271,
      "eval_samples_per_second": 11.722,
      "eval_steps_per_second": 1.491,
      "step": 2900
    },
    {
      "epoch": 15.384615384615385,
      "grad_norm": 32.921974182128906,
      "learning_rate": 9.7009e-06,
      "loss": 1.3998,
      "step": 3000
    },
    {
      "epoch": 15.384615384615385,
      "eval_loss": 1.3834290504455566,
      "eval_runtime": 33.4449,
      "eval_samples_per_second": 11.751,
      "eval_steps_per_second": 1.495,
      "step": 3000
    },
    {
      "epoch": 15.897435897435898,
      "grad_norm": 71.14076232910156,
      "learning_rate": 9.6909e-06,
      "loss": 1.3753,
      "step": 3100
    },
    {
      "epoch": 15.897435897435898,
      "eval_loss": 1.371915578842163,
      "eval_runtime": 33.5787,
      "eval_samples_per_second": 11.704,
      "eval_steps_per_second": 1.489,
      "step": 3100
    },
    {
      "epoch": 16.41025641025641,
      "grad_norm": 85.71231842041016,
      "learning_rate": 9.6809e-06,
      "loss": 1.3639,
      "step": 3200
    },
    {
      "epoch": 16.41025641025641,
      "eval_loss": 1.3810721635818481,
      "eval_runtime": 33.5802,
      "eval_samples_per_second": 11.703,
      "eval_steps_per_second": 1.489,
      "step": 3200
    },
    {
      "epoch": 16.923076923076923,
      "grad_norm": 39.7967529296875,
      "learning_rate": 9.670900000000001e-06,
      "loss": 1.3609,
      "step": 3300
    },
    {
      "epoch": 16.923076923076923,
      "eval_loss": 1.3853365182876587,
      "eval_runtime": 33.6581,
      "eval_samples_per_second": 11.676,
      "eval_steps_per_second": 1.486,
      "step": 3300
    },
    {
      "epoch": 17.435897435897434,
      "grad_norm": 19.84697723388672,
      "learning_rate": 9.660900000000001e-06,
      "loss": 1.3314,
      "step": 3400
    },
    {
      "epoch": 17.435897435897434,
      "eval_loss": 1.3581265211105347,
      "eval_runtime": 33.4833,
      "eval_samples_per_second": 11.737,
      "eval_steps_per_second": 1.493,
      "step": 3400
    },
    {
      "epoch": 17.94871794871795,
      "grad_norm": 43.280426025390625,
      "learning_rate": 9.650900000000001e-06,
      "loss": 1.3408,
      "step": 3500
    },
    {
      "epoch": 17.94871794871795,
      "eval_loss": 1.3400689363479614,
      "eval_runtime": 33.4394,
      "eval_samples_per_second": 11.753,
      "eval_steps_per_second": 1.495,
      "step": 3500
    },
    {
      "epoch": 18.46153846153846,
      "grad_norm": 35.393314361572266,
      "learning_rate": 9.640900000000001e-06,
      "loss": 1.3471,
      "step": 3600
    },
    {
      "epoch": 18.46153846153846,
      "eval_loss": 1.3405698537826538,
      "eval_runtime": 33.6347,
      "eval_samples_per_second": 11.684,
      "eval_steps_per_second": 1.487,
      "step": 3600
    },
    {
      "epoch": 18.974358974358974,
      "grad_norm": 32.50804138183594,
      "learning_rate": 9.630900000000001e-06,
      "loss": 1.3213,
      "step": 3700
    },
    {
      "epoch": 18.974358974358974,
      "eval_loss": 1.3345987796783447,
      "eval_runtime": 33.5369,
      "eval_samples_per_second": 11.718,
      "eval_steps_per_second": 1.491,
      "step": 3700
    },
    {
      "epoch": 19.487179487179485,
      "grad_norm": 28.999061584472656,
      "learning_rate": 9.620900000000001e-06,
      "loss": 1.3251,
      "step": 3800
    },
    {
      "epoch": 19.487179487179485,
      "eval_loss": 1.3227241039276123,
      "eval_runtime": 33.5001,
      "eval_samples_per_second": 11.731,
      "eval_steps_per_second": 1.493,
      "step": 3800
    },
    {
      "epoch": 20.0,
      "grad_norm": 41.793636322021484,
      "learning_rate": 9.610900000000001e-06,
      "loss": 1.3297,
      "step": 3900
    },
    {
      "epoch": 20.0,
      "eval_loss": 1.3213008642196655,
      "eval_runtime": 33.561,
      "eval_samples_per_second": 11.71,
      "eval_steps_per_second": 1.49,
      "step": 3900
    },
    {
      "epoch": 20.51282051282051,
      "grad_norm": 53.55360794067383,
      "learning_rate": 9.600900000000002e-06,
      "loss": 1.331,
      "step": 4000
    },
    {
      "epoch": 20.51282051282051,
      "eval_loss": 1.3293949365615845,
      "eval_runtime": 33.5542,
      "eval_samples_per_second": 11.712,
      "eval_steps_per_second": 1.49,
      "step": 4000
    },
    {
      "epoch": 21.025641025641026,
      "grad_norm": 73.3389892578125,
      "learning_rate": 9.5909e-06,
      "loss": 1.2856,
      "step": 4100
    },
    {
      "epoch": 21.025641025641026,
      "eval_loss": 1.316487193107605,
      "eval_runtime": 33.5602,
      "eval_samples_per_second": 11.71,
      "eval_steps_per_second": 1.49,
      "step": 4100
    },
    {
      "epoch": 21.53846153846154,
      "grad_norm": 62.724456787109375,
      "learning_rate": 9.5809e-06,
      "loss": 1.3186,
      "step": 4200
    },
    {
      "epoch": 21.53846153846154,
      "eval_loss": 1.3179290294647217,
      "eval_runtime": 33.621,
      "eval_samples_per_second": 11.689,
      "eval_steps_per_second": 1.487,
      "step": 4200
    },
    {
      "epoch": 22.05128205128205,
      "grad_norm": 30.242937088012695,
      "learning_rate": 9.5709e-06,
      "loss": 1.2623,
      "step": 4300
    },
    {
      "epoch": 22.05128205128205,
      "eval_loss": 1.2920558452606201,
      "eval_runtime": 33.6166,
      "eval_samples_per_second": 11.691,
      "eval_steps_per_second": 1.487,
      "step": 4300
    },
    {
      "epoch": 22.564102564102566,
      "grad_norm": 17.423118591308594,
      "learning_rate": 9.5609e-06,
      "loss": 1.3045,
      "step": 4400
    },
    {
      "epoch": 22.564102564102566,
      "eval_loss": 1.302635669708252,
      "eval_runtime": 33.7322,
      "eval_samples_per_second": 11.651,
      "eval_steps_per_second": 1.482,
      "step": 4400
    },
    {
      "epoch": 23.076923076923077,
      "grad_norm": 115.05293273925781,
      "learning_rate": 9.5509e-06,
      "loss": 1.2997,
      "step": 4500
    },
    {
      "epoch": 23.076923076923077,
      "eval_loss": 1.2834452390670776,
      "eval_runtime": 33.5349,
      "eval_samples_per_second": 11.719,
      "eval_steps_per_second": 1.491,
      "step": 4500
    },
    {
      "epoch": 23.58974358974359,
      "grad_norm": 35.13385009765625,
      "learning_rate": 9.5409e-06,
      "loss": 1.2591,
      "step": 4600
    },
    {
      "epoch": 23.58974358974359,
      "eval_loss": 1.2677439451217651,
      "eval_runtime": 33.5991,
      "eval_samples_per_second": 11.697,
      "eval_steps_per_second": 1.488,
      "step": 4600
    },
    {
      "epoch": 24.102564102564102,
      "grad_norm": 22.429704666137695,
      "learning_rate": 9.5309e-06,
      "loss": 1.3057,
      "step": 4700
    },
    {
      "epoch": 24.102564102564102,
      "eval_loss": 1.2759162187576294,
      "eval_runtime": 33.8336,
      "eval_samples_per_second": 11.616,
      "eval_steps_per_second": 1.478,
      "step": 4700
    },
    {
      "epoch": 24.615384615384617,
      "grad_norm": 19.258209228515625,
      "learning_rate": 9.5209e-06,
      "loss": 1.2526,
      "step": 4800
    },
    {
      "epoch": 24.615384615384617,
      "eval_loss": 1.2712483406066895,
      "eval_runtime": 33.585,
      "eval_samples_per_second": 11.702,
      "eval_steps_per_second": 1.489,
      "step": 4800
    },
    {
      "epoch": 25.128205128205128,
      "grad_norm": 18.289043426513672,
      "learning_rate": 9.5109e-06,
      "loss": 1.2436,
      "step": 4900
    },
    {
      "epoch": 25.128205128205128,
      "eval_loss": 1.277999758720398,
      "eval_runtime": 33.6639,
      "eval_samples_per_second": 11.674,
      "eval_steps_per_second": 1.485,
      "step": 4900
    },
    {
      "epoch": 25.641025641025642,
      "grad_norm": 53.41452407836914,
      "learning_rate": 9.501000000000001e-06,
      "loss": 1.2768,
      "step": 5000
    },
    {
      "epoch": 25.641025641025642,
      "eval_loss": 1.2602609395980835,
      "eval_runtime": 33.6751,
      "eval_samples_per_second": 11.67,
      "eval_steps_per_second": 1.485,
      "step": 5000
    },
    {
      "epoch": 26.153846153846153,
      "grad_norm": 28.17922019958496,
      "learning_rate": 9.491000000000001e-06,
      "loss": 1.2221,
      "step": 5100
    },
    {
      "epoch": 26.153846153846153,
      "eval_loss": 1.28999662399292,
      "eval_runtime": 33.8104,
      "eval_samples_per_second": 11.624,
      "eval_steps_per_second": 1.479,
      "step": 5100
    },
    {
      "epoch": 26.666666666666668,
      "grad_norm": 28.119773864746094,
      "learning_rate": 9.481000000000001e-06,
      "loss": 1.233,
      "step": 5200
    },
    {
      "epoch": 26.666666666666668,
      "eval_loss": 1.2724733352661133,
      "eval_runtime": 33.9553,
      "eval_samples_per_second": 11.574,
      "eval_steps_per_second": 1.473,
      "step": 5200
    },
    {
      "epoch": 27.17948717948718,
      "grad_norm": 102.97128295898438,
      "learning_rate": 9.471000000000001e-06,
      "loss": 1.2667,
      "step": 5300
    },
    {
      "epoch": 27.17948717948718,
      "eval_loss": 1.265009880065918,
      "eval_runtime": 33.7879,
      "eval_samples_per_second": 11.631,
      "eval_steps_per_second": 1.48,
      "step": 5300
    },
    {
      "epoch": 27.692307692307693,
      "grad_norm": 23.439664840698242,
      "learning_rate": 9.461000000000001e-06,
      "loss": 1.2255,
      "step": 5400
    },
    {
      "epoch": 27.692307692307693,
      "eval_loss": 1.2421387434005737,
      "eval_runtime": 33.867,
      "eval_samples_per_second": 11.604,
      "eval_steps_per_second": 1.476,
      "step": 5400
    },
    {
      "epoch": 28.205128205128204,
      "grad_norm": 34.7141227722168,
      "learning_rate": 9.451000000000002e-06,
      "loss": 1.2557,
      "step": 5500
    },
    {
      "epoch": 28.205128205128204,
      "eval_loss": 1.2613080739974976,
      "eval_runtime": 33.9538,
      "eval_samples_per_second": 11.575,
      "eval_steps_per_second": 1.473,
      "step": 5500
    },
    {
      "epoch": 28.71794871794872,
      "grad_norm": 60.65612030029297,
      "learning_rate": 9.441000000000002e-06,
      "loss": 1.2407,
      "step": 5600
    },
    {
      "epoch": 28.71794871794872,
      "eval_loss": 1.2578727006912231,
      "eval_runtime": 33.8423,
      "eval_samples_per_second": 11.613,
      "eval_steps_per_second": 1.477,
      "step": 5600
    },
    {
      "epoch": 29.23076923076923,
      "grad_norm": 39.73835754394531,
      "learning_rate": 9.431000000000002e-06,
      "loss": 1.2436,
      "step": 5700
    },
    {
      "epoch": 29.23076923076923,
      "eval_loss": 1.2593867778778076,
      "eval_runtime": 33.6929,
      "eval_samples_per_second": 11.664,
      "eval_steps_per_second": 1.484,
      "step": 5700
    },
    {
      "epoch": 29.743589743589745,
      "grad_norm": 24.647741317749023,
      "learning_rate": 9.421000000000002e-06,
      "loss": 1.207,
      "step": 5800
    },
    {
      "epoch": 29.743589743589745,
      "eval_loss": 1.2388144731521606,
      "eval_runtime": 33.7238,
      "eval_samples_per_second": 11.654,
      "eval_steps_per_second": 1.483,
      "step": 5800
    },
    {
      "epoch": 30.256410256410255,
      "grad_norm": 63.13822937011719,
      "learning_rate": 9.411000000000002e-06,
      "loss": 1.2287,
      "step": 5900
    },
    {
      "epoch": 30.256410256410255,
      "eval_loss": 1.2804478406906128,
      "eval_runtime": 33.7389,
      "eval_samples_per_second": 11.648,
      "eval_steps_per_second": 1.482,
      "step": 5900
    },
    {
      "epoch": 30.76923076923077,
      "grad_norm": 27.123302459716797,
      "learning_rate": 9.401000000000002e-06,
      "loss": 1.2249,
      "step": 6000
    },
    {
      "epoch": 30.76923076923077,
      "eval_loss": 1.2437323331832886,
      "eval_runtime": 33.6856,
      "eval_samples_per_second": 11.667,
      "eval_steps_per_second": 1.484,
      "step": 6000
    },
    {
      "epoch": 31.28205128205128,
      "grad_norm": 27.28360366821289,
      "learning_rate": 9.391e-06,
      "loss": 1.2101,
      "step": 6100
    },
    {
      "epoch": 31.28205128205128,
      "eval_loss": 1.227403998374939,
      "eval_runtime": 33.648,
      "eval_samples_per_second": 11.68,
      "eval_steps_per_second": 1.486,
      "step": 6100
    },
    {
      "epoch": 31.794871794871796,
      "grad_norm": 55.08905029296875,
      "learning_rate": 9.381e-06,
      "loss": 1.1843,
      "step": 6200
    },
    {
      "epoch": 31.794871794871796,
      "eval_loss": 1.225257158279419,
      "eval_runtime": 33.8349,
      "eval_samples_per_second": 11.615,
      "eval_steps_per_second": 1.478,
      "step": 6200
    },
    {
      "epoch": 32.30769230769231,
      "grad_norm": 39.94312286376953,
      "learning_rate": 9.371e-06,
      "loss": 1.1908,
      "step": 6300
    },
    {
      "epoch": 32.30769230769231,
      "eval_loss": 1.2344192266464233,
      "eval_runtime": 33.9417,
      "eval_samples_per_second": 11.579,
      "eval_steps_per_second": 1.473,
      "step": 6300
    },
    {
      "epoch": 32.82051282051282,
      "grad_norm": 25.61664581298828,
      "learning_rate": 9.361e-06,
      "loss": 1.1832,
      "step": 6400
    },
    {
      "epoch": 32.82051282051282,
      "eval_loss": 1.2213290929794312,
      "eval_runtime": 33.8461,
      "eval_samples_per_second": 11.611,
      "eval_steps_per_second": 1.477,
      "step": 6400
    },
    {
      "epoch": 33.333333333333336,
      "grad_norm": 31.0895938873291,
      "learning_rate": 9.351e-06,
      "loss": 1.2104,
      "step": 6500
    },
    {
      "epoch": 33.333333333333336,
      "eval_loss": 1.2290922403335571,
      "eval_runtime": 33.8119,
      "eval_samples_per_second": 11.623,
      "eval_steps_per_second": 1.479,
      "step": 6500
    },
    {
      "epoch": 33.84615384615385,
      "grad_norm": 35.208988189697266,
      "learning_rate": 9.341000000000001e-06,
      "loss": 1.2007,
      "step": 6600
    },
    {
      "epoch": 33.84615384615385,
      "eval_loss": 1.2198638916015625,
      "eval_runtime": 33.6979,
      "eval_samples_per_second": 11.662,
      "eval_steps_per_second": 1.484,
      "step": 6600
    },
    {
      "epoch": 34.35897435897436,
      "grad_norm": 46.61259841918945,
      "learning_rate": 9.331000000000001e-06,
      "loss": 1.182,
      "step": 6700
    },
    {
      "epoch": 34.35897435897436,
      "eval_loss": 1.202943205833435,
      "eval_runtime": 33.8788,
      "eval_samples_per_second": 11.6,
      "eval_steps_per_second": 1.476,
      "step": 6700
    },
    {
      "epoch": 34.87179487179487,
      "grad_norm": 27.606361389160156,
      "learning_rate": 9.321000000000001e-06,
      "loss": 1.1843,
      "step": 6800
    },
    {
      "epoch": 34.87179487179487,
      "eval_loss": 1.2101120948791504,
      "eval_runtime": 33.92,
      "eval_samples_per_second": 11.586,
      "eval_steps_per_second": 1.474,
      "step": 6800
    },
    {
      "epoch": 35.38461538461539,
      "grad_norm": 1141.704833984375,
      "learning_rate": 9.311000000000001e-06,
      "loss": 1.1926,
      "step": 6900
    },
    {
      "epoch": 35.38461538461539,
      "eval_loss": 1.1979094743728638,
      "eval_runtime": 33.9794,
      "eval_samples_per_second": 11.566,
      "eval_steps_per_second": 1.471,
      "step": 6900
    },
    {
      "epoch": 35.8974358974359,
      "grad_norm": 29.9624080657959,
      "learning_rate": 9.301000000000001e-06,
      "loss": 1.1475,
      "step": 7000
    },
    {
      "epoch": 35.8974358974359,
      "eval_loss": 1.1987537145614624,
      "eval_runtime": 33.7554,
      "eval_samples_per_second": 11.643,
      "eval_steps_per_second": 1.481,
      "step": 7000
    },
    {
      "epoch": 36.41025641025641,
      "grad_norm": 23.925745010375977,
      "learning_rate": 9.291000000000001e-06,
      "loss": 1.1692,
      "step": 7100
    },
    {
      "epoch": 36.41025641025641,
      "eval_loss": 1.1971298456192017,
      "eval_runtime": 33.682,
      "eval_samples_per_second": 11.668,
      "eval_steps_per_second": 1.484,
      "step": 7100
    },
    {
      "epoch": 36.92307692307692,
      "grad_norm": 22.790334701538086,
      "learning_rate": 9.281000000000001e-06,
      "loss": 1.1381,
      "step": 7200
    },
    {
      "epoch": 36.92307692307692,
      "eval_loss": 1.1832250356674194,
      "eval_runtime": 33.8924,
      "eval_samples_per_second": 11.596,
      "eval_steps_per_second": 1.475,
      "step": 7200
    },
    {
      "epoch": 37.43589743589744,
      "grad_norm": 21.8422794342041,
      "learning_rate": 9.271000000000002e-06,
      "loss": 1.189,
      "step": 7300
    },
    {
      "epoch": 37.43589743589744,
      "eval_loss": 1.2060439586639404,
      "eval_runtime": 34.2775,
      "eval_samples_per_second": 11.465,
      "eval_steps_per_second": 1.459,
      "step": 7300
    },
    {
      "epoch": 37.94871794871795,
      "grad_norm": 28.315584182739258,
      "learning_rate": 9.261000000000002e-06,
      "loss": 1.139,
      "step": 7400
    },
    {
      "epoch": 37.94871794871795,
      "eval_loss": 1.191786527633667,
      "eval_runtime": 33.8013,
      "eval_samples_per_second": 11.627,
      "eval_steps_per_second": 1.479,
      "step": 7400
    },
    {
      "epoch": 38.46153846153846,
      "grad_norm": 30.92888641357422,
      "learning_rate": 9.2511e-06,
      "loss": 1.1509,
      "step": 7500
    },
    {
      "epoch": 38.46153846153846,
      "eval_loss": 1.1886085271835327,
      "eval_runtime": 33.8579,
      "eval_samples_per_second": 11.607,
      "eval_steps_per_second": 1.477,
      "step": 7500
    },
    {
      "epoch": 38.97435897435897,
      "grad_norm": 21.603288650512695,
      "learning_rate": 9.2411e-06,
      "loss": 1.1592,
      "step": 7600
    },
    {
      "epoch": 38.97435897435897,
      "eval_loss": 1.1912109851837158,
      "eval_runtime": 33.7856,
      "eval_samples_per_second": 11.632,
      "eval_steps_per_second": 1.48,
      "step": 7600
    },
    {
      "epoch": 39.48717948717949,
      "grad_norm": 42.09080123901367,
      "learning_rate": 9.2311e-06,
      "loss": 1.1501,
      "step": 7700
    },
    {
      "epoch": 39.48717948717949,
      "eval_loss": 1.1855125427246094,
      "eval_runtime": 33.7703,
      "eval_samples_per_second": 11.637,
      "eval_steps_per_second": 1.481,
      "step": 7700
    },
    {
      "epoch": 40.0,
      "grad_norm": 27.183298110961914,
      "learning_rate": 9.2211e-06,
      "loss": 1.1287,
      "step": 7800
    },
    {
      "epoch": 40.0,
      "eval_loss": 1.1904667615890503,
      "eval_runtime": 33.7348,
      "eval_samples_per_second": 11.65,
      "eval_steps_per_second": 1.482,
      "step": 7800
    },
    {
      "epoch": 40.51282051282051,
      "grad_norm": 62.908424377441406,
      "learning_rate": 9.2111e-06,
      "loss": 1.1598,
      "step": 7900
    },
    {
      "epoch": 40.51282051282051,
      "eval_loss": 1.1837190389633179,
      "eval_runtime": 34.0069,
      "eval_samples_per_second": 11.556,
      "eval_steps_per_second": 1.47,
      "step": 7900
    },
    {
      "epoch": 41.02564102564103,
      "grad_norm": 33.93372344970703,
      "learning_rate": 9.2011e-06,
      "loss": 1.1308,
      "step": 8000
    },
    {
      "epoch": 41.02564102564103,
      "eval_loss": 1.1925432682037354,
      "eval_runtime": 33.8881,
      "eval_samples_per_second": 11.597,
      "eval_steps_per_second": 1.475,
      "step": 8000
    },
    {
      "epoch": 41.53846153846154,
      "grad_norm": 45.57182312011719,
      "learning_rate": 9.1911e-06,
      "loss": 1.1496,
      "step": 8100
    },
    {
      "epoch": 41.53846153846154,
      "eval_loss": 1.204172968864441,
      "eval_runtime": 33.8945,
      "eval_samples_per_second": 11.595,
      "eval_steps_per_second": 1.475,
      "step": 8100
    },
    {
      "epoch": 42.05128205128205,
      "grad_norm": 25.79231834411621,
      "learning_rate": 9.181100000000001e-06,
      "loss": 1.098,
      "step": 8200
    },
    {
      "epoch": 42.05128205128205,
      "eval_loss": 1.1738271713256836,
      "eval_runtime": 34.3546,
      "eval_samples_per_second": 11.44,
      "eval_steps_per_second": 1.455,
      "step": 8200
    },
    {
      "epoch": 42.56410256410256,
      "grad_norm": 27.62971305847168,
      "learning_rate": 9.171100000000001e-06,
      "loss": 1.1275,
      "step": 8300
    },
    {
      "epoch": 42.56410256410256,
      "eval_loss": 1.1773978471755981,
      "eval_runtime": 33.7608,
      "eval_samples_per_second": 11.641,
      "eval_steps_per_second": 1.481,
      "step": 8300
    },
    {
      "epoch": 43.07692307692308,
      "grad_norm": 20.703998565673828,
      "learning_rate": 9.161100000000001e-06,
      "loss": 1.1524,
      "step": 8400
    },
    {
      "epoch": 43.07692307692308,
      "eval_loss": 1.1819504499435425,
      "eval_runtime": 33.9332,
      "eval_samples_per_second": 11.582,
      "eval_steps_per_second": 1.473,
      "step": 8400
    },
    {
      "epoch": 43.58974358974359,
      "grad_norm": 29.18483543395996,
      "learning_rate": 9.151100000000001e-06,
      "loss": 1.1022,
      "step": 8500
    },
    {
      "epoch": 43.58974358974359,
      "eval_loss": 1.1720554828643799,
      "eval_runtime": 33.872,
      "eval_samples_per_second": 11.602,
      "eval_steps_per_second": 1.476,
      "step": 8500
    },
    {
      "epoch": 44.1025641025641,
      "grad_norm": 34.14143371582031,
      "learning_rate": 9.141100000000001e-06,
      "loss": 1.1303,
      "step": 8600
    },
    {
      "epoch": 44.1025641025641,
      "eval_loss": 1.1805644035339355,
      "eval_runtime": 33.9223,
      "eval_samples_per_second": 11.585,
      "eval_steps_per_second": 1.474,
      "step": 8600
    },
    {
      "epoch": 44.61538461538461,
      "grad_norm": 43.17974853515625,
      "learning_rate": 9.1311e-06,
      "loss": 1.0919,
      "step": 8700
    },
    {
      "epoch": 44.61538461538461,
      "eval_loss": 1.1851396560668945,
      "eval_runtime": 33.9872,
      "eval_samples_per_second": 11.563,
      "eval_steps_per_second": 1.471,
      "step": 8700
    },
    {
      "epoch": 45.12820512820513,
      "grad_norm": 31.169639587402344,
      "learning_rate": 9.1211e-06,
      "loss": 1.1156,
      "step": 8800
    },
    {
      "epoch": 45.12820512820513,
      "eval_loss": 1.1849329471588135,
      "eval_runtime": 33.8263,
      "eval_samples_per_second": 11.618,
      "eval_steps_per_second": 1.478,
      "step": 8800
    },
    {
      "epoch": 45.64102564102564,
      "grad_norm": 47.28102493286133,
      "learning_rate": 9.1111e-06,
      "loss": 1.1201,
      "step": 8900
    },
    {
      "epoch": 45.64102564102564,
      "eval_loss": 1.1575498580932617,
      "eval_runtime": 33.7801,
      "eval_samples_per_second": 11.634,
      "eval_steps_per_second": 1.48,
      "step": 8900
    },
    {
      "epoch": 46.15384615384615,
      "grad_norm": 62.14609146118164,
      "learning_rate": 9.1011e-06,
      "loss": 1.0987,
      "step": 9000
    },
    {
      "epoch": 46.15384615384615,
      "eval_loss": 1.16815185546875,
      "eval_runtime": 33.7678,
      "eval_samples_per_second": 11.638,
      "eval_steps_per_second": 1.481,
      "step": 9000
    },
    {
      "epoch": 46.666666666666664,
      "grad_norm": 77.31022644042969,
      "learning_rate": 9.0911e-06,
      "loss": 1.119,
      "step": 9100
    },
    {
      "epoch": 46.666666666666664,
      "eval_loss": 1.1787101030349731,
      "eval_runtime": 34.2194,
      "eval_samples_per_second": 11.485,
      "eval_steps_per_second": 1.461,
      "step": 9100
    },
    {
      "epoch": 47.17948717948718,
      "grad_norm": 17.737777709960938,
      "learning_rate": 9.0811e-06,
      "loss": 1.1152,
      "step": 9200
    },
    {
      "epoch": 47.17948717948718,
      "eval_loss": 1.1642876863479614,
      "eval_runtime": 33.9617,
      "eval_samples_per_second": 11.572,
      "eval_steps_per_second": 1.472,
      "step": 9200
    },
    {
      "epoch": 47.69230769230769,
      "grad_norm": 22.58513069152832,
      "learning_rate": 9.0711e-06,
      "loss": 1.0801,
      "step": 9300
    },
    {
      "epoch": 47.69230769230769,
      "eval_loss": 1.1710031032562256,
      "eval_runtime": 33.6338,
      "eval_samples_per_second": 11.685,
      "eval_steps_per_second": 1.487,
      "step": 9300
    },
    {
      "epoch": 48.205128205128204,
      "grad_norm": 17.689064025878906,
      "learning_rate": 9.0611e-06,
      "loss": 1.1669,
      "step": 9400
    },
    {
      "epoch": 48.205128205128204,
      "eval_loss": 1.1800153255462646,
      "eval_runtime": 33.5397,
      "eval_samples_per_second": 11.717,
      "eval_steps_per_second": 1.491,
      "step": 9400
    },
    {
      "epoch": 48.717948717948715,
      "grad_norm": 20.76385498046875,
      "learning_rate": 9.0511e-06,
      "loss": 1.0969,
      "step": 9500
    },
    {
      "epoch": 48.717948717948715,
      "eval_loss": 1.170789361000061,
      "eval_runtime": 33.4901,
      "eval_samples_per_second": 11.735,
      "eval_steps_per_second": 1.493,
      "step": 9500
    },
    {
      "epoch": 49.23076923076923,
      "grad_norm": 53.716548919677734,
      "learning_rate": 9.0411e-06,
      "loss": 1.1053,
      "step": 9600
    },
    {
      "epoch": 49.23076923076923,
      "eval_loss": 1.1888952255249023,
      "eval_runtime": 33.3262,
      "eval_samples_per_second": 11.793,
      "eval_steps_per_second": 1.5,
      "step": 9600
    },
    {
      "epoch": 49.743589743589745,
      "grad_norm": 70.57758331298828,
      "learning_rate": 9.0311e-06,
      "loss": 1.088,
      "step": 9700
    },
    {
      "epoch": 49.743589743589745,
      "eval_loss": 1.1654279232025146,
      "eval_runtime": 33.4095,
      "eval_samples_per_second": 11.763,
      "eval_steps_per_second": 1.497,
      "step": 9700
    },
    {
      "epoch": 50.256410256410255,
      "grad_norm": 48.835018157958984,
      "learning_rate": 9.0211e-06,
      "loss": 1.1185,
      "step": 9800
    },
    {
      "epoch": 50.256410256410255,
      "eval_loss": 1.174896240234375,
      "eval_runtime": 33.655,
      "eval_samples_per_second": 11.677,
      "eval_steps_per_second": 1.486,
      "step": 9800
    },
    {
      "epoch": 50.76923076923077,
      "grad_norm": 27.838232040405273,
      "learning_rate": 9.011100000000001e-06,
      "loss": 1.0741,
      "step": 9900
    },
    {
      "epoch": 50.76923076923077,
      "eval_loss": 1.1926134824752808,
      "eval_runtime": 33.5437,
      "eval_samples_per_second": 11.716,
      "eval_steps_per_second": 1.491,
      "step": 9900
    },
    {
      "epoch": 51.282051282051285,
      "grad_norm": 36.455204010009766,
      "learning_rate": 9.001100000000001e-06,
      "loss": 1.1212,
      "step": 10000
    },
    {
      "epoch": 51.282051282051285,
      "eval_loss": 1.1525243520736694,
      "eval_runtime": 33.5794,
      "eval_samples_per_second": 11.704,
      "eval_steps_per_second": 1.489,
      "step": 10000
    }
  ],
  "logging_steps": 100,
  "max_steps": 100000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 513,
  "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": 3.82243166208e+19,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}