{
  "best_metric": null,
  "best_metric_at_epoch": null,
  "best_model_checkpoint": null,
  "epoch": 14.598540145985401,
  "global_step": 36000,
  "latest_metric": null,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 4.9324141659908085e-05,
      "loss": 1.7428,
      "step": 500
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.864828331981617e-05,
      "loss": 1.2225,
      "step": 1000
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.797242497972425e-05,
      "loss": 1.0975,
      "step": 1500
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.729656663963233e-05,
      "loss": 1.0237,
      "step": 2000
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.6620708299540416e-05,
      "loss": 0.9755,
      "step": 2500
    },
    {
      "epoch": 1.22,
      "learning_rate": 4.59448499594485e-05,
      "loss": 0.9379,
      "step": 3000
    },
    {
      "epoch": 1.42,
      "learning_rate": 4.526899161935659e-05,
      "loss": 0.9069,
      "step": 3500
    },
    {
      "epoch": 1.62,
      "learning_rate": 4.459313327926467e-05,
      "loss": 0.882,
      "step": 4000
    },
    {
      "epoch": 1.82,
      "learning_rate": 4.3917274939172754e-05,
      "loss": 0.8649,
      "step": 4500
    },
    {
      "epoch": 2.03,
      "learning_rate": 4.3241416599080836e-05,
      "loss": 0.8487,
      "step": 5000
    },
    {
      "epoch": 2.23,
      "learning_rate": 4.256555825898892e-05,
      "loss": 0.8321,
      "step": 5500
    },
    {
      "epoch": 2.43,
      "learning_rate": 4.1889699918897e-05,
      "loss": 0.818,
      "step": 6000
    },
    {
      "epoch": 2.64,
      "learning_rate": 4.1213841578805084e-05,
      "loss": 0.8052,
      "step": 6500
    },
    {
      "epoch": 2.84,
      "learning_rate": 4.053798323871317e-05,
      "loss": 0.7936,
      "step": 7000
    },
    {
      "epoch": 3.04,
      "learning_rate": 3.986212489862125e-05,
      "loss": 0.7868,
      "step": 7500
    },
    {
      "epoch": 3.24,
      "learning_rate": 3.918626655852933e-05,
      "loss": 0.7777,
      "step": 8000
    },
    {
      "epoch": 3.45,
      "learning_rate": 3.8510408218437415e-05,
      "loss": 0.7685,
      "step": 8500
    },
    {
      "epoch": 3.65,
      "learning_rate": 3.78345498783455e-05,
      "loss": 0.7632,
      "step": 9000
    },
    {
      "epoch": 3.85,
      "learning_rate": 3.715869153825358e-05,
      "loss": 0.754,
      "step": 9500
    },
    {
      "epoch": 4.06,
      "learning_rate": 3.648283319816166e-05,
      "loss": 0.7486,
      "step": 10000
    },
    {
      "epoch": 4.26,
      "learning_rate": 3.580697485806975e-05,
      "loss": 0.742,
      "step": 10500
    },
    {
      "epoch": 4.46,
      "learning_rate": 3.5131116517977835e-05,
      "loss": 0.7353,
      "step": 11000
    },
    {
      "epoch": 4.66,
      "learning_rate": 3.445525817788592e-05,
      "loss": 0.7304,
      "step": 11500
    },
    {
      "epoch": 4.87,
      "learning_rate": 3.3779399837794e-05,
      "loss": 0.7271,
      "step": 12000
    },
    {
      "epoch": 5.07,
      "learning_rate": 3.3103541497702084e-05,
      "loss": 0.7213,
      "step": 12500
    },
    {
      "epoch": 5.27,
      "learning_rate": 3.2427683157610166e-05,
      "loss": 0.7156,
      "step": 13000
    },
    {
      "epoch": 5.47,
      "learning_rate": 3.175182481751825e-05,
      "loss": 0.7111,
      "step": 13500
    },
    {
      "epoch": 5.68,
      "learning_rate": 3.107596647742633e-05,
      "loss": 0.7087,
      "step": 14000
    },
    {
      "epoch": 5.88,
      "learning_rate": 3.0400108137334414e-05,
      "loss": 0.7067,
      "step": 14500
    },
    {
      "epoch": 6.08,
      "learning_rate": 2.9724249797242497e-05,
      "loss": 0.7015,
      "step": 15000
    },
    {
      "epoch": 6.29,
      "learning_rate": 2.904839145715058e-05,
      "loss": 0.6951,
      "step": 15500
    },
    {
      "epoch": 6.49,
      "learning_rate": 2.8372533117058663e-05,
      "loss": 0.6922,
      "step": 16000
    },
    {
      "epoch": 6.69,
      "learning_rate": 2.7696674776966745e-05,
      "loss": 0.6917,
      "step": 16500
    },
    {
      "epoch": 6.89,
      "learning_rate": 2.7020816436874835e-05,
      "loss": 0.6869,
      "step": 17000
    },
    {
      "epoch": 7.1,
      "learning_rate": 2.6344958096782917e-05,
      "loss": 0.6834,
      "step": 17500
    },
    {
      "epoch": 7.3,
      "learning_rate": 2.5669099756691e-05,
      "loss": 0.6819,
      "step": 18000
    },
    {
      "epoch": 7.5,
      "learning_rate": 2.499324141659908e-05,
      "loss": 0.6801,
      "step": 18500
    },
    {
      "epoch": 7.7,
      "learning_rate": 2.4317383076507166e-05,
      "loss": 0.6755,
      "step": 19000
    },
    {
      "epoch": 7.91,
      "learning_rate": 2.3641524736415248e-05,
      "loss": 0.6734,
      "step": 19500
    },
    {
      "epoch": 8.11,
      "learning_rate": 2.296566639632333e-05,
      "loss": 0.6706,
      "step": 20000
    },
    {
      "epoch": 8.31,
      "learning_rate": 2.2289808056231414e-05,
      "loss": 0.6688,
      "step": 20500
    },
    {
      "epoch": 8.52,
      "learning_rate": 2.1613949716139496e-05,
      "loss": 0.6662,
      "step": 21000
    },
    {
      "epoch": 8.72,
      "learning_rate": 2.093809137604758e-05,
      "loss": 0.6636,
      "step": 21500
    },
    {
      "epoch": 8.92,
      "learning_rate": 2.0262233035955662e-05,
      "loss": 0.6622,
      "step": 22000
    },
    {
      "epoch": 9.12,
      "learning_rate": 1.9586374695863748e-05,
      "loss": 0.6593,
      "step": 22500
    },
    {
      "epoch": 9.33,
      "learning_rate": 1.891051635577183e-05,
      "loss": 0.6568,
      "step": 23000
    },
    {
      "epoch": 9.53,
      "learning_rate": 1.8234658015679913e-05,
      "loss": 0.6563,
      "step": 23500
    },
    {
      "epoch": 9.73,
      "learning_rate": 1.7558799675587996e-05,
      "loss": 0.6542,
      "step": 24000
    },
    {
      "epoch": 9.94,
      "learning_rate": 1.688294133549608e-05,
      "loss": 0.6535,
      "step": 24500
    },
    {
      "epoch": 10.14,
      "learning_rate": 1.620708299540416e-05,
      "loss": 0.6486,
      "step": 25000
    },
    {
      "epoch": 10.34,
      "learning_rate": 1.5531224655312247e-05,
      "loss": 0.6485,
      "step": 25500
    },
    {
      "epoch": 10.54,
      "learning_rate": 1.4855366315220332e-05,
      "loss": 0.6474,
      "step": 26000
    },
    {
      "epoch": 10.75,
      "learning_rate": 1.4179507975128415e-05,
      "loss": 0.647,
      "step": 26500
    },
    {
      "epoch": 10.95,
      "learning_rate": 1.3503649635036497e-05,
      "loss": 0.6451,
      "step": 27000
    },
    {
      "epoch": 11.15,
      "learning_rate": 1.282779129494458e-05,
      "loss": 0.6426,
      "step": 27500
    },
    {
      "epoch": 11.35,
      "learning_rate": 1.2151932954852663e-05,
      "loss": 0.6431,
      "step": 28000
    },
    {
      "epoch": 11.56,
      "learning_rate": 1.1476074614760747e-05,
      "loss": 0.641,
      "step": 28500
    },
    {
      "epoch": 11.76,
      "learning_rate": 1.080021627466883e-05,
      "loss": 0.6414,
      "step": 29000
    },
    {
      "epoch": 11.96,
      "learning_rate": 1.0124357934576913e-05,
      "loss": 0.6382,
      "step": 29500
    },
    {
      "epoch": 12.17,
      "learning_rate": 9.448499594484997e-06,
      "loss": 0.635,
      "step": 30000
    },
    {
      "epoch": 12.37,
      "learning_rate": 8.77264125439308e-06,
      "loss": 0.6357,
      "step": 30500
    },
    {
      "epoch": 12.57,
      "learning_rate": 8.096782914301162e-06,
      "loss": 0.634,
      "step": 31000
    },
    {
      "epoch": 12.77,
      "learning_rate": 7.420924574209247e-06,
      "loss": 0.6338,
      "step": 31500
    },
    {
      "epoch": 12.98,
      "learning_rate": 6.7450662341173294e-06,
      "loss": 0.633,
      "step": 32000
    },
    {
      "epoch": 13.18,
      "learning_rate": 6.069207894025412e-06,
      "loss": 0.6301,
      "step": 32500
    },
    {
      "epoch": 13.38,
      "learning_rate": 5.393349553933496e-06,
      "loss": 0.6313,
      "step": 33000
    },
    {
      "epoch": 13.58,
      "learning_rate": 4.717491213841578e-06,
      "loss": 0.6294,
      "step": 33500
    },
    {
      "epoch": 13.79,
      "learning_rate": 4.041632873749662e-06,
      "loss": 0.6311,
      "step": 34000
    },
    {
      "epoch": 13.99,
      "learning_rate": 3.365774533657746e-06,
      "loss": 0.631,
      "step": 34500
    },
    {
      "epoch": 14.19,
      "learning_rate": 2.6899161935658286e-06,
      "loss": 0.6274,
      "step": 35000
    },
    {
      "epoch": 14.4,
      "learning_rate": 2.014057853473912e-06,
      "loss": 0.6274,
      "step": 35500
    },
    {
      "epoch": 14.6,
      "learning_rate": 1.3381995133819951e-06,
      "loss": 0.6273,
      "step": 36000
    }
  ],
  "max_steps": 36990,
  "num_train_epochs": 15,
  "start_time": 1624121724.3048394,
  "total_flos": 0
}