{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 0.0,
      "loss": 0.7227,
      "step": 10
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 0.7667,
      "step": 20
    },
    {
      "epoch": 0.1,
      "learning_rate": 1e-05,
      "loss": 0.2428,
      "step": 30
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.8333333333333333e-05,
      "loss": 0.0194,
      "step": 40
    },
    {
      "epoch": 0.17,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.0071,
      "step": 50
    },
    {
      "epoch": 0.2,
      "learning_rate": 3.5e-05,
      "loss": 0.0131,
      "step": 60
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 0.0079,
      "step": 70
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.981481481481482e-05,
      "loss": 0.0094,
      "step": 80
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.888888888888889e-05,
      "loss": 0.0177,
      "step": 90
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.796296296296296e-05,
      "loss": 0.0083,
      "step": 100
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.703703703703704e-05,
      "loss": 0.0226,
      "step": 110
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.6111111111111115e-05,
      "loss": 0.0102,
      "step": 120
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.518518518518519e-05,
      "loss": 0.0197,
      "step": 130
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.425925925925926e-05,
      "loss": 0.0312,
      "step": 140
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 0.0282,
      "step": 150
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.240740740740741e-05,
      "loss": 0.0231,
      "step": 160
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.148148148148148e-05,
      "loss": 0.0376,
      "step": 170
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.055555555555556e-05,
      "loss": 0.0209,
      "step": 180
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.981481481481482e-05,
      "loss": 0.058,
      "step": 190
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.0302,
      "step": 200
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.7962962962962964e-05,
      "loss": 0.0434,
      "step": 210
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 0.0432,
      "step": 220
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.611111111111111e-05,
      "loss": 0.0493,
      "step": 230
    },
    {
      "epoch": 0.8,
      "learning_rate": 3.527777777777778e-05,
      "loss": 0.0588,
      "step": 240
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.435185185185185e-05,
      "loss": 0.0725,
      "step": 250
    },
    {
      "epoch": 0.87,
      "learning_rate": 3.3425925925925924e-05,
      "loss": 0.0859,
      "step": 260
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.2500000000000004e-05,
      "loss": 0.0535,
      "step": 270
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.157407407407408e-05,
      "loss": 0.0475,
      "step": 280
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.064814814814815e-05,
      "loss": 0.0291,
      "step": 290
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.9722222222222223e-05,
      "loss": 0.0327,
      "step": 300
    },
    {
      "epoch": 1.03,
      "learning_rate": 2.87962962962963e-05,
      "loss": 0.0254,
      "step": 310
    },
    {
      "epoch": 1.07,
      "learning_rate": 2.7870370370370375e-05,
      "loss": 0.0486,
      "step": 320
    },
    {
      "epoch": 1.1,
      "learning_rate": 2.6944444444444445e-05,
      "loss": 0.0413,
      "step": 330
    },
    {
      "epoch": 1.13,
      "learning_rate": 2.601851851851852e-05,
      "loss": 0.0229,
      "step": 340
    },
    {
      "epoch": 1.17,
      "learning_rate": 2.5092592592592594e-05,
      "loss": 0.0191,
      "step": 350
    },
    {
      "epoch": 1.2,
      "learning_rate": 2.4166666666666667e-05,
      "loss": 0.0378,
      "step": 360
    },
    {
      "epoch": 1.23,
      "learning_rate": 2.324074074074074e-05,
      "loss": 0.0244,
      "step": 370
    },
    {
      "epoch": 1.27,
      "learning_rate": 2.2314814814814816e-05,
      "loss": 0.014,
      "step": 380
    },
    {
      "epoch": 1.3,
      "learning_rate": 2.138888888888889e-05,
      "loss": 0.0264,
      "step": 390
    },
    {
      "epoch": 1.33,
      "learning_rate": 2.0462962962962965e-05,
      "loss": 0.043,
      "step": 400
    },
    {
      "epoch": 1.37,
      "learning_rate": 1.9537037037037038e-05,
      "loss": 0.0356,
      "step": 410
    },
    {
      "epoch": 1.4,
      "learning_rate": 1.861111111111111e-05,
      "loss": 0.023,
      "step": 420
    },
    {
      "epoch": 1.43,
      "learning_rate": 1.7685185185185184e-05,
      "loss": 0.0285,
      "step": 430
    },
    {
      "epoch": 1.47,
      "learning_rate": 1.675925925925926e-05,
      "loss": 0.0189,
      "step": 440
    },
    {
      "epoch": 1.5,
      "learning_rate": 1.5833333333333333e-05,
      "loss": 0.0296,
      "step": 450
    },
    {
      "epoch": 1.53,
      "learning_rate": 1.490740740740741e-05,
      "loss": 0.0189,
      "step": 460
    },
    {
      "epoch": 1.57,
      "learning_rate": 1.3981481481481482e-05,
      "loss": 0.0357,
      "step": 470
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.3055555555555557e-05,
      "loss": 0.0235,
      "step": 480
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.212962962962963e-05,
      "loss": 0.0396,
      "step": 490
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.1203703703703704e-05,
      "loss": 0.0236,
      "step": 500
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.0277777777777777e-05,
      "loss": 0.0147,
      "step": 510
    },
    {
      "epoch": 1.73,
      "learning_rate": 9.351851851851852e-06,
      "loss": 0.0135,
      "step": 520
    },
    {
      "epoch": 1.77,
      "learning_rate": 8.425925925925926e-06,
      "loss": 0.0138,
      "step": 530
    },
    {
      "epoch": 1.8,
      "learning_rate": 7.5e-06,
      "loss": 0.024,
      "step": 540
    },
    {
      "epoch": 1.83,
      "learning_rate": 6.574074074074074e-06,
      "loss": 0.0181,
      "step": 550
    },
    {
      "epoch": 1.87,
      "learning_rate": 5.6481481481481485e-06,
      "loss": 0.0201,
      "step": 560
    },
    {
      "epoch": 1.9,
      "learning_rate": 4.722222222222222e-06,
      "loss": 0.0276,
      "step": 570
    },
    {
      "epoch": 1.93,
      "learning_rate": 3.7962962962962964e-06,
      "loss": 0.0287,
      "step": 580
    },
    {
      "epoch": 1.97,
      "learning_rate": 2.8703703703703706e-06,
      "loss": 0.0256,
      "step": 590
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.9444444444444444e-06,
      "loss": 0.018,
      "step": 600
    },
    {
      "epoch": 2.0,
      "step": 600,
      "total_flos": 1.5734632955772928e+17,
      "train_loss": 0.05660845875740051,
      "train_runtime": 609.6094,
      "train_samples_per_second": 19.685,
      "train_steps_per_second": 0.984
    }
  ],
  "logging_steps": 10,
  "max_steps": 600,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 1.5734632955772928e+17,
  "trial_name": null,
  "trial_params": null
}