{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "global_step": 675,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 1.9703703703703704e-05,
      "loss": 1.0915,
      "step": 10
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9407407407407407e-05,
      "loss": 1.1,
      "step": 20
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.9111111111111113e-05,
      "loss": 1.0328,
      "step": 30
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.8814814814814816e-05,
      "loss": 0.9874,
      "step": 40
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.851851851851852e-05,
      "loss": 0.824,
      "step": 50
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.8222222222222224e-05,
      "loss": 0.7368,
      "step": 60
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.7925925925925927e-05,
      "loss": 0.6747,
      "step": 70
    },
    {
      "epoch": 0.59,
      "learning_rate": 1.7629629629629633e-05,
      "loss": 0.6592,
      "step": 80
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.7333333333333336e-05,
      "loss": 0.5993,
      "step": 90
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.7037037037037038e-05,
      "loss": 0.4979,
      "step": 100
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.674074074074074e-05,
      "loss": 0.509,
      "step": 110
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.6444444444444444e-05,
      "loss": 0.4791,
      "step": 120
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.614814814814815e-05,
      "loss": 0.4344,
      "step": 130
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.5851851851851852e-05,
      "loss": 0.3372,
      "step": 140
    },
    {
      "epoch": 1.11,
      "learning_rate": 1.555555555555556e-05,
      "loss": 0.3557,
      "step": 150
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.525925925925926e-05,
      "loss": 0.3696,
      "step": 160
    },
    {
      "epoch": 1.26,
      "learning_rate": 1.4962962962962964e-05,
      "loss": 0.3183,
      "step": 170
    },
    {
      "epoch": 1.33,
      "learning_rate": 1.4666666666666666e-05,
      "loss": 0.2915,
      "step": 180
    },
    {
      "epoch": 1.41,
      "learning_rate": 1.4370370370370372e-05,
      "loss": 0.3132,
      "step": 190
    },
    {
      "epoch": 1.48,
      "learning_rate": 1.4074074074074075e-05,
      "loss": 0.3036,
      "step": 200
    },
    {
      "epoch": 1.56,
      "learning_rate": 1.377777777777778e-05,
      "loss": 0.27,
      "step": 210
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.3481481481481482e-05,
      "loss": 0.2615,
      "step": 220
    },
    {
      "epoch": 1.7,
      "learning_rate": 1.3185185185185185e-05,
      "loss": 0.3576,
      "step": 230
    },
    {
      "epoch": 1.78,
      "learning_rate": 1.288888888888889e-05,
      "loss": 0.3569,
      "step": 240
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.2592592592592593e-05,
      "loss": 0.3082,
      "step": 250
    },
    {
      "epoch": 1.93,
      "learning_rate": 1.2296296296296298e-05,
      "loss": 0.3245,
      "step": 260
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.2e-05,
      "loss": 0.3101,
      "step": 270
    },
    {
      "epoch": 2.07,
      "learning_rate": 1.1703703703703703e-05,
      "loss": 0.2436,
      "step": 280
    },
    {
      "epoch": 2.15,
      "learning_rate": 1.1407407407407409e-05,
      "loss": 0.2519,
      "step": 290
    },
    {
      "epoch": 2.22,
      "learning_rate": 1.1111111111111113e-05,
      "loss": 0.1802,
      "step": 300
    },
    {
      "epoch": 2.3,
      "learning_rate": 1.0814814814814816e-05,
      "loss": 0.1915,
      "step": 310
    },
    {
      "epoch": 2.37,
      "learning_rate": 1.0518518518518519e-05,
      "loss": 0.2336,
      "step": 320
    },
    {
      "epoch": 2.44,
      "learning_rate": 1.0222222222222223e-05,
      "loss": 0.2449,
      "step": 330
    },
    {
      "epoch": 2.52,
      "learning_rate": 9.925925925925927e-06,
      "loss": 0.1734,
      "step": 340
    },
    {
      "epoch": 2.59,
      "learning_rate": 9.62962962962963e-06,
      "loss": 0.2296,
      "step": 350
    },
    {
      "epoch": 2.67,
      "learning_rate": 9.333333333333334e-06,
      "loss": 0.1868,
      "step": 360
    },
    {
      "epoch": 2.74,
      "learning_rate": 9.037037037037037e-06,
      "loss": 0.1636,
      "step": 370
    },
    {
      "epoch": 2.81,
      "learning_rate": 8.740740740740741e-06,
      "loss": 0.2715,
      "step": 380
    },
    {
      "epoch": 2.89,
      "learning_rate": 8.444444444444446e-06,
      "loss": 0.2108,
      "step": 390
    },
    {
      "epoch": 2.96,
      "learning_rate": 8.148148148148148e-06,
      "loss": 0.2238,
      "step": 400
    },
    {
      "epoch": 3.04,
      "learning_rate": 7.851851851851853e-06,
      "loss": 0.1861,
      "step": 410
    },
    {
      "epoch": 3.11,
      "learning_rate": 7.555555555555556e-06,
      "loss": 0.2073,
      "step": 420
    },
    {
      "epoch": 3.19,
      "learning_rate": 7.2592592592592605e-06,
      "loss": 0.1836,
      "step": 430
    },
    {
      "epoch": 3.26,
      "learning_rate": 6.962962962962964e-06,
      "loss": 0.1992,
      "step": 440
    },
    {
      "epoch": 3.33,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.1743,
      "step": 450
    },
    {
      "epoch": 3.41,
      "learning_rate": 6.370370370370371e-06,
      "loss": 0.1875,
      "step": 460
    },
    {
      "epoch": 3.48,
      "learning_rate": 6.0740740740740745e-06,
      "loss": 0.1722,
      "step": 470
    },
    {
      "epoch": 3.56,
      "learning_rate": 5.777777777777778e-06,
      "loss": 0.1797,
      "step": 480
    },
    {
      "epoch": 3.63,
      "learning_rate": 5.481481481481482e-06,
      "loss": 0.0975,
      "step": 490
    },
    {
      "epoch": 3.7,
      "learning_rate": 5.185185185185185e-06,
      "loss": 0.1544,
      "step": 500
    },
    {
      "epoch": 3.78,
      "learning_rate": 4.888888888888889e-06,
      "loss": 0.1597,
      "step": 510
    },
    {
      "epoch": 3.85,
      "learning_rate": 4.592592592592593e-06,
      "loss": 0.111,
      "step": 520
    },
    {
      "epoch": 3.93,
      "learning_rate": 4.296296296296296e-06,
      "loss": 0.1499,
      "step": 530
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.172,
      "step": 540
    },
    {
      "epoch": 4.07,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 0.1167,
      "step": 550
    },
    {
      "epoch": 4.15,
      "learning_rate": 3.4074074074074077e-06,
      "loss": 0.1435,
      "step": 560
    },
    {
      "epoch": 4.22,
      "learning_rate": 3.1111111111111116e-06,
      "loss": 0.1135,
      "step": 570
    },
    {
      "epoch": 4.3,
      "learning_rate": 2.814814814814815e-06,
      "loss": 0.1451,
      "step": 580
    },
    {
      "epoch": 4.37,
      "learning_rate": 2.5185185185185186e-06,
      "loss": 0.0731,
      "step": 590
    },
    {
      "epoch": 4.44,
      "learning_rate": 2.222222222222222e-06,
      "loss": 0.1417,
      "step": 600
    },
    {
      "epoch": 4.52,
      "learning_rate": 1.925925925925926e-06,
      "loss": 0.0895,
      "step": 610
    },
    {
      "epoch": 4.59,
      "learning_rate": 1.62962962962963e-06,
      "loss": 0.2134,
      "step": 620
    },
    {
      "epoch": 4.67,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 0.1301,
      "step": 630
    },
    {
      "epoch": 4.74,
      "learning_rate": 1.0370370370370371e-06,
      "loss": 0.1575,
      "step": 640
    },
    {
      "epoch": 4.81,
      "learning_rate": 7.407407407407407e-07,
      "loss": 0.1265,
      "step": 650
    },
    {
      "epoch": 4.89,
      "learning_rate": 4.444444444444445e-07,
      "loss": 0.1399,
      "step": 660
    },
    {
      "epoch": 4.96,
      "learning_rate": 1.4814814814814817e-07,
      "loss": 0.0575,
      "step": 670
    },
    {
      "epoch": 5.0,
      "step": 675,
      "total_flos": 1420483563959040.0,
      "train_loss": 0.31028794209162397,
      "train_runtime": 186.9323,
      "train_samples_per_second": 115.523,
      "train_steps_per_second": 3.611
    }
  ],
  "max_steps": 675,
  "num_train_epochs": 5,
  "total_flos": 1420483563959040.0,
  "trial_name": null,
  "trial_params": null
}