{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.23157894736842105,
  "eval_steps": 500,
  "global_step": 550,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1e-05,
      "loss": 4.8744,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 2e-05,
      "loss": 4.1114,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 3e-05,
      "loss": 3.528,
      "step": 30
    },
    {
      "epoch": 0.02,
      "learning_rate": 4e-05,
      "loss": 3.2573,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 5e-05,
      "loss": 3.1417,
      "step": 50
    },
    {
      "epoch": 0.03,
      "learning_rate": 6e-05,
      "loss": 3.0506,
      "step": 60
    },
    {
      "epoch": 0.03,
      "learning_rate": 7e-05,
      "loss": 2.9644,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 8e-05,
      "loss": 2.8399,
      "step": 80
    },
    {
      "epoch": 0.04,
      "learning_rate": 9e-05,
      "loss": 2.6935,
      "step": 90
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001,
      "loss": 2.5259,
      "step": 100
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.956043956043956e-05,
      "loss": 2.3713,
      "step": 110
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.912087912087913e-05,
      "loss": 2.2237,
      "step": 120
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.868131868131869e-05,
      "loss": 2.0999,
      "step": 130
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.824175824175824e-05,
      "loss": 2.0211,
      "step": 140
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.780219780219781e-05,
      "loss": 1.949,
      "step": 150
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.736263736263737e-05,
      "loss": 1.8819,
      "step": 160
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.692307692307692e-05,
      "loss": 1.8244,
      "step": 170
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.64835164835165e-05,
      "loss": 1.7849,
      "step": 180
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.604395604395605e-05,
      "loss": 1.7288,
      "step": 190
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.560439560439561e-05,
      "loss": 1.6914,
      "step": 200
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.516483516483517e-05,
      "loss": 1.6534,
      "step": 210
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.472527472527473e-05,
      "loss": 1.6332,
      "step": 220
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.428571428571429e-05,
      "loss": 1.5944,
      "step": 230
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.384615384615386e-05,
      "loss": 1.5789,
      "step": 240
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.340659340659341e-05,
      "loss": 1.5583,
      "step": 250
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.296703296703297e-05,
      "loss": 1.5485,
      "step": 260
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.252747252747253e-05,
      "loss": 1.5124,
      "step": 270
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.208791208791209e-05,
      "loss": 1.5004,
      "step": 280
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.164835164835165e-05,
      "loss": 1.5042,
      "step": 290
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.12087912087912e-05,
      "loss": 1.4991,
      "step": 300
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.076923076923078e-05,
      "loss": 1.4692,
      "step": 310
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.032967032967033e-05,
      "loss": 1.4628,
      "step": 320
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.989010989010989e-05,
      "loss": 1.4481,
      "step": 330
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.945054945054946e-05,
      "loss": 1.454,
      "step": 340
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.901098901098901e-05,
      "loss": 1.4409,
      "step": 350
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.857142857142857e-05,
      "loss": 1.4339,
      "step": 360
    },
    {
      "epoch": 0.16,
      "learning_rate": 8.813186813186814e-05,
      "loss": 1.4262,
      "step": 370
    },
    {
      "epoch": 0.16,
      "learning_rate": 8.76923076923077e-05,
      "loss": 1.4298,
      "step": 380
    },
    {
      "epoch": 0.16,
      "learning_rate": 8.725274725274725e-05,
      "loss": 1.4247,
      "step": 390
    },
    {
      "epoch": 0.17,
      "learning_rate": 8.681318681318682e-05,
      "loss": 1.4191,
      "step": 400
    },
    {
      "epoch": 0.17,
      "learning_rate": 8.637362637362638e-05,
      "loss": 1.4156,
      "step": 410
    },
    {
      "epoch": 0.18,
      "learning_rate": 8.593406593406593e-05,
      "loss": 1.4102,
      "step": 420
    },
    {
      "epoch": 0.18,
      "learning_rate": 8.54945054945055e-05,
      "loss": 1.4121,
      "step": 430
    },
    {
      "epoch": 0.19,
      "learning_rate": 8.505494505494506e-05,
      "loss": 1.4033,
      "step": 440
    },
    {
      "epoch": 0.19,
      "learning_rate": 8.461538461538461e-05,
      "loss": 1.3986,
      "step": 450
    },
    {
      "epoch": 0.19,
      "learning_rate": 8.417582417582419e-05,
      "loss": 1.3935,
      "step": 460
    },
    {
      "epoch": 0.2,
      "learning_rate": 8.373626373626374e-05,
      "loss": 1.399,
      "step": 470
    },
    {
      "epoch": 0.2,
      "learning_rate": 8.32967032967033e-05,
      "loss": 1.3888,
      "step": 480
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.285714285714287e-05,
      "loss": 1.3958,
      "step": 490
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.241758241758242e-05,
      "loss": 1.3758,
      "step": 500
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.197802197802198e-05,
      "loss": 1.3779,
      "step": 510
    },
    {
      "epoch": 0.22,
      "learning_rate": 8.153846153846155e-05,
      "loss": 1.3754,
      "step": 520
    },
    {
      "epoch": 0.22,
      "learning_rate": 8.10989010989011e-05,
      "loss": 1.3754,
      "step": 530
    },
    {
      "epoch": 0.23,
      "learning_rate": 8.065934065934066e-05,
      "loss": 1.3854,
      "step": 540
    },
    {
      "epoch": 0.23,
      "learning_rate": 8.021978021978022e-05,
      "loss": 1.3579,
      "step": 550
    }
  ],
  "logging_steps": 10,
  "max_steps": 2375,
  "num_train_epochs": 1,
  "save_steps": 50,
  "total_flos": 271592074027008.0,
  "trial_name": null,
  "trial_params": null
}