{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 142.85714285714286,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.57,
      "learning_rate": 4.2000000000000006e-07,
      "loss": 3.0968,
      "step": 25
    },
    {
      "epoch": 7.14,
      "learning_rate": 9.200000000000001e-07,
      "loss": 2.4565,
      "step": 50
    },
    {
      "epoch": 10.71,
      "learning_rate": 1.42e-06,
      "loss": 1.9962,
      "step": 75
    },
    {
      "epoch": 14.29,
      "learning_rate": 1.9200000000000003e-06,
      "loss": 1.7133,
      "step": 100
    },
    {
      "epoch": 17.86,
      "learning_rate": 2.42e-06,
      "loss": 1.5526,
      "step": 125
    },
    {
      "epoch": 21.43,
      "learning_rate": 2.92e-06,
      "loss": 1.4427,
      "step": 150
    },
    {
      "epoch": 25.0,
      "learning_rate": 3.4200000000000007e-06,
      "loss": 1.3382,
      "step": 175
    },
    {
      "epoch": 28.57,
      "learning_rate": 3.920000000000001e-06,
      "loss": 1.178,
      "step": 200
    },
    {
      "epoch": 32.14,
      "learning_rate": 4.42e-06,
      "loss": 0.9536,
      "step": 225
    },
    {
      "epoch": 35.71,
      "learning_rate": 4.92e-06,
      "loss": 0.7107,
      "step": 250
    },
    {
      "epoch": 39.29,
      "learning_rate": 5.420000000000001e-06,
      "loss": 0.4791,
      "step": 275
    },
    {
      "epoch": 42.86,
      "learning_rate": 5.92e-06,
      "loss": 0.2683,
      "step": 300
    },
    {
      "epoch": 46.43,
      "learning_rate": 6.42e-06,
      "loss": 0.1293,
      "step": 325
    },
    {
      "epoch": 50.0,
      "learning_rate": 6.92e-06,
      "loss": 0.0561,
      "step": 350
    },
    {
      "epoch": 53.57,
      "learning_rate": 7.420000000000001e-06,
      "loss": 0.03,
      "step": 375
    },
    {
      "epoch": 57.14,
      "learning_rate": 7.92e-06,
      "loss": 0.0178,
      "step": 400
    },
    {
      "epoch": 60.71,
      "learning_rate": 8.42e-06,
      "loss": 0.0134,
      "step": 425
    },
    {
      "epoch": 64.29,
      "learning_rate": 8.920000000000001e-06,
      "loss": 0.0087,
      "step": 450
    },
    {
      "epoch": 67.86,
      "learning_rate": 9.42e-06,
      "loss": 0.008,
      "step": 475
    },
    {
      "epoch": 71.43,
      "learning_rate": 9.920000000000002e-06,
      "loss": 0.0064,
      "step": 500
    },
    {
      "epoch": 75.0,
      "learning_rate": 9.58e-06,
      "loss": 0.0068,
      "step": 525
    },
    {
      "epoch": 78.57,
      "learning_rate": 9.080000000000001e-06,
      "loss": 0.0049,
      "step": 550
    },
    {
      "epoch": 82.14,
      "learning_rate": 8.580000000000001e-06,
      "loss": 0.0035,
      "step": 575
    },
    {
      "epoch": 85.71,
      "learning_rate": 8.08e-06,
      "loss": 0.0022,
      "step": 600
    },
    {
      "epoch": 89.29,
      "learning_rate": 7.58e-06,
      "loss": 0.0015,
      "step": 625
    },
    {
      "epoch": 92.86,
      "learning_rate": 7.08e-06,
      "loss": 0.0017,
      "step": 650
    },
    {
      "epoch": 96.43,
      "learning_rate": 6.5800000000000005e-06,
      "loss": 0.0014,
      "step": 675
    },
    {
      "epoch": 100.0,
      "learning_rate": 6.08e-06,
      "loss": 0.0013,
      "step": 700
    },
    {
      "epoch": 103.57,
      "learning_rate": 5.580000000000001e-06,
      "loss": 0.0006,
      "step": 725
    },
    {
      "epoch": 107.14,
      "learning_rate": 5.0800000000000005e-06,
      "loss": 0.0004,
      "step": 750
    },
    {
      "epoch": 110.71,
      "learning_rate": 4.58e-06,
      "loss": 0.0004,
      "step": 775
    },
    {
      "epoch": 114.29,
      "learning_rate": 4.08e-06,
      "loss": 0.0004,
      "step": 800
    },
    {
      "epoch": 117.86,
      "learning_rate": 3.58e-06,
      "loss": 0.0004,
      "step": 825
    },
    {
      "epoch": 121.43,
      "learning_rate": 3.08e-06,
      "loss": 0.0004,
      "step": 850
    },
    {
      "epoch": 125.0,
      "learning_rate": 2.5800000000000003e-06,
      "loss": 0.0004,
      "step": 875
    },
    {
      "epoch": 128.57,
      "learning_rate": 2.08e-06,
      "loss": 0.0004,
      "step": 900
    },
    {
      "epoch": 132.14,
      "learning_rate": 1.5800000000000001e-06,
      "loss": 0.0004,
      "step": 925
    },
    {
      "epoch": 135.71,
      "learning_rate": 1.08e-06,
      "loss": 0.0004,
      "step": 950
    },
    {
      "epoch": 139.29,
      "learning_rate": 5.800000000000001e-07,
      "loss": 0.0004,
      "step": 975
    },
    {
      "epoch": 142.86,
      "learning_rate": 8e-08,
      "loss": 0.0004,
      "step": 1000
    },
    {
      "epoch": 142.86,
      "step": 1000,
      "total_flos": 1.838750736678912e+19,
      "train_loss": 0.4370949484743178,
      "train_runtime": 4327.5129,
      "train_samples_per_second": 14.789,
      "train_steps_per_second": 0.231
    }
  ],
  "max_steps": 1000,
  "num_train_epochs": 143,
  "total_flos": 1.838750736678912e+19,
  "trial_name": null,
  "trial_params": null
}