{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "global_step": 665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 1.9699248120300753e-05,
      "loss": 1.1917,
      "step": 10
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.9398496240601504e-05,
      "loss": 1.1026,
      "step": 20
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.909774436090226e-05,
      "loss": 1.0748,
      "step": 30
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.879699248120301e-05,
      "loss": 1.0498,
      "step": 40
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.849624060150376e-05,
      "loss": 1.0187,
      "step": 50
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.8195488721804512e-05,
      "loss": 0.98,
      "step": 60
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.7894736842105264e-05,
      "loss": 0.9141,
      "step": 70
    },
    {
      "epoch": 0.6,
      "learning_rate": 1.7593984962406015e-05,
      "loss": 0.8803,
      "step": 80
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.729323308270677e-05,
      "loss": 0.8601,
      "step": 90
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.699248120300752e-05,
      "loss": 0.8136,
      "step": 100
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.6691729323308272e-05,
      "loss": 0.7096,
      "step": 110
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.6390977443609023e-05,
      "loss": 0.7317,
      "step": 120
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.6090225563909775e-05,
      "loss": 0.6692,
      "step": 130
    },
    {
      "epoch": 1.05,
      "learning_rate": 1.578947368421053e-05,
      "loss": 0.6096,
      "step": 140
    },
    {
      "epoch": 1.13,
      "learning_rate": 1.548872180451128e-05,
      "loss": 0.5641,
      "step": 150
    },
    {
      "epoch": 1.2,
      "learning_rate": 1.5187969924812032e-05,
      "loss": 0.4964,
      "step": 160
    },
    {
      "epoch": 1.28,
      "learning_rate": 1.4887218045112783e-05,
      "loss": 0.5387,
      "step": 170
    },
    {
      "epoch": 1.35,
      "learning_rate": 1.4586466165413536e-05,
      "loss": 0.5217,
      "step": 180
    },
    {
      "epoch": 1.43,
      "learning_rate": 1.4285714285714287e-05,
      "loss": 0.5162,
      "step": 190
    },
    {
      "epoch": 1.5,
      "learning_rate": 1.3984962406015038e-05,
      "loss": 0.5539,
      "step": 200
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.3684210526315791e-05,
      "loss": 0.5228,
      "step": 210
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.3383458646616543e-05,
      "loss": 0.4894,
      "step": 220
    },
    {
      "epoch": 1.73,
      "learning_rate": 1.3082706766917295e-05,
      "loss": 0.4383,
      "step": 230
    },
    {
      "epoch": 1.8,
      "learning_rate": 1.2781954887218047e-05,
      "loss": 0.4828,
      "step": 240
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.2481203007518798e-05,
      "loss": 0.4547,
      "step": 250
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.2180451127819551e-05,
      "loss": 0.4474,
      "step": 260
    },
    {
      "epoch": 2.03,
      "learning_rate": 1.1879699248120302e-05,
      "loss": 0.4464,
      "step": 270
    },
    {
      "epoch": 2.11,
      "learning_rate": 1.1578947368421053e-05,
      "loss": 0.3985,
      "step": 280
    },
    {
      "epoch": 2.18,
      "learning_rate": 1.1278195488721806e-05,
      "loss": 0.4307,
      "step": 290
    },
    {
      "epoch": 2.26,
      "learning_rate": 1.0977443609022558e-05,
      "loss": 0.3886,
      "step": 300
    },
    {
      "epoch": 2.33,
      "learning_rate": 1.0676691729323309e-05,
      "loss": 0.3797,
      "step": 310
    },
    {
      "epoch": 2.41,
      "learning_rate": 1.0375939849624062e-05,
      "loss": 0.4167,
      "step": 320
    },
    {
      "epoch": 2.48,
      "learning_rate": 1.0075187969924813e-05,
      "loss": 0.3893,
      "step": 330
    },
    {
      "epoch": 2.56,
      "learning_rate": 9.774436090225564e-06,
      "loss": 0.3829,
      "step": 340
    },
    {
      "epoch": 2.63,
      "learning_rate": 9.473684210526315e-06,
      "loss": 0.3509,
      "step": 350
    },
    {
      "epoch": 2.71,
      "learning_rate": 9.172932330827068e-06,
      "loss": 0.3744,
      "step": 360
    },
    {
      "epoch": 2.78,
      "learning_rate": 8.87218045112782e-06,
      "loss": 0.3572,
      "step": 370
    },
    {
      "epoch": 2.86,
      "learning_rate": 8.571428571428571e-06,
      "loss": 0.3117,
      "step": 380
    },
    {
      "epoch": 2.93,
      "learning_rate": 8.270676691729324e-06,
      "loss": 0.3674,
      "step": 390
    },
    {
      "epoch": 3.01,
      "learning_rate": 7.969924812030075e-06,
      "loss": 0.4052,
      "step": 400
    },
    {
      "epoch": 3.08,
      "learning_rate": 7.669172932330828e-06,
      "loss": 0.3358,
      "step": 410
    },
    {
      "epoch": 3.16,
      "learning_rate": 7.368421052631579e-06,
      "loss": 0.3145,
      "step": 420
    },
    {
      "epoch": 3.23,
      "learning_rate": 7.067669172932331e-06,
      "loss": 0.2775,
      "step": 430
    },
    {
      "epoch": 3.31,
      "learning_rate": 6.766917293233083e-06,
      "loss": 0.3636,
      "step": 440
    },
    {
      "epoch": 3.38,
      "learning_rate": 6.466165413533835e-06,
      "loss": 0.3496,
      "step": 450
    },
    {
      "epoch": 3.46,
      "learning_rate": 6.165413533834587e-06,
      "loss": 0.3813,
      "step": 460
    },
    {
      "epoch": 3.53,
      "learning_rate": 5.864661654135339e-06,
      "loss": 0.3815,
      "step": 470
    },
    {
      "epoch": 3.61,
      "learning_rate": 5.56390977443609e-06,
      "loss": 0.3607,
      "step": 480
    },
    {
      "epoch": 3.68,
      "learning_rate": 5.263157894736842e-06,
      "loss": 0.3558,
      "step": 490
    },
    {
      "epoch": 3.76,
      "learning_rate": 4.962406015037594e-06,
      "loss": 0.3188,
      "step": 500
    },
    {
      "epoch": 3.83,
      "learning_rate": 4.661654135338346e-06,
      "loss": 0.3371,
      "step": 510
    },
    {
      "epoch": 3.91,
      "learning_rate": 4.360902255639098e-06,
      "loss": 0.2918,
      "step": 520
    },
    {
      "epoch": 3.98,
      "learning_rate": 4.06015037593985e-06,
      "loss": 0.2726,
      "step": 530
    },
    {
      "epoch": 4.06,
      "learning_rate": 3.7593984962406014e-06,
      "loss": 0.2971,
      "step": 540
    },
    {
      "epoch": 4.14,
      "learning_rate": 3.4586466165413535e-06,
      "loss": 0.2796,
      "step": 550
    },
    {
      "epoch": 4.21,
      "learning_rate": 3.157894736842105e-06,
      "loss": 0.2947,
      "step": 560
    },
    {
      "epoch": 4.29,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 0.3396,
      "step": 570
    },
    {
      "epoch": 4.36,
      "learning_rate": 2.556390977443609e-06,
      "loss": 0.2181,
      "step": 580
    },
    {
      "epoch": 4.44,
      "learning_rate": 2.255639097744361e-06,
      "loss": 0.3021,
      "step": 590
    },
    {
      "epoch": 4.51,
      "learning_rate": 1.9548872180451127e-06,
      "loss": 0.3,
      "step": 600
    },
    {
      "epoch": 4.59,
      "learning_rate": 1.6541353383458648e-06,
      "loss": 0.2801,
      "step": 610
    },
    {
      "epoch": 4.66,
      "learning_rate": 1.3533834586466167e-06,
      "loss": 0.2505,
      "step": 620
    },
    {
      "epoch": 4.74,
      "learning_rate": 1.0526315789473685e-06,
      "loss": 0.288,
      "step": 630
    },
    {
      "epoch": 4.81,
      "learning_rate": 7.518796992481203e-07,
      "loss": 0.2711,
      "step": 640
    },
    {
      "epoch": 4.89,
      "learning_rate": 4.511278195488722e-07,
      "loss": 0.3521,
      "step": 650
    },
    {
      "epoch": 4.96,
      "learning_rate": 1.5037593984962406e-07,
      "loss": 0.3088,
      "step": 660
    },
    {
      "epoch": 5.0,
      "step": 665,
      "total_flos": 1390554412692480.0,
      "train_loss": 0.48537510767915193,
      "train_runtime": 260.1502,
      "train_samples_per_second": 81.261,
      "train_steps_per_second": 2.556
    }
  ],
  "max_steps": 665,
  "num_train_epochs": 5,
  "total_flos": 1390554412692480.0,
  "trial_name": null,
  "trial_params": null
}