{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 522,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11,
      "global_step": 20,
      "learning_rate": 3.7735849056603776e-05,
      "loss": 0.2804,
      "step": 20
    },
    {
      "epoch": 0.23,
      "global_step": 40,
      "learning_rate": 7.547169811320755e-05,
      "loss": 0.2879,
      "step": 40
    },
    {
      "epoch": 0.34,
      "global_step": 60,
      "learning_rate": 0.0001,
      "loss": 0.2889,
      "step": 60
    },
    {
      "epoch": 0.46,
      "global_step": 80,
      "learning_rate": 0.0001,
      "loss": 0.2898,
      "step": 80
    },
    {
      "epoch": 0.57,
      "global_step": 100,
      "learning_rate": 0.0001,
      "loss": 0.2622,
      "step": 100
    },
    {
      "epoch": 0.69,
      "global_step": 120,
      "learning_rate": 0.0001,
      "loss": 0.2734,
      "step": 120
    },
    {
      "epoch": 0.8,
      "global_step": 140,
      "learning_rate": 0.0001,
      "loss": 0.2923,
      "step": 140
    },
    {
      "epoch": 0.92,
      "global_step": 160,
      "learning_rate": 0.0001,
      "loss": 0.2827,
      "step": 160
    },
    {
      "epoch": 1.03,
      "global_step": 180,
      "learning_rate": 0.0001,
      "loss": 0.2054,
      "step": 180
    },
    {
      "epoch": 1.15,
      "global_step": 200,
      "learning_rate": 0.0001,
      "loss": 0.1518,
      "step": 200
    },
    {
      "epoch": 1.26,
      "global_step": 220,
      "learning_rate": 0.0001,
      "loss": 0.1561,
      "step": 220
    },
    {
      "epoch": 1.38,
      "global_step": 240,
      "learning_rate": 0.0001,
      "loss": 0.1274,
      "step": 240
    },
    {
      "epoch": 1.49,
      "global_step": 260,
      "learning_rate": 0.0001,
      "loss": 0.1318,
      "step": 260
    },
    {
      "epoch": 1.61,
      "global_step": 280,
      "learning_rate": 0.0001,
      "loss": 0.1201,
      "step": 280
    },
    {
      "epoch": 1.72,
      "global_step": 300,
      "learning_rate": 0.0001,
      "loss": 0.1661,
      "step": 300
    },
    {
      "epoch": 1.84,
      "global_step": 320,
      "learning_rate": 0.0001,
      "loss": 0.1922,
      "step": 320
    },
    {
      "epoch": 1.95,
      "global_step": 340,
      "learning_rate": 0.0001,
      "loss": 0.1123,
      "step": 340
    },
    {
      "epoch": 2.07,
      "global_step": 360,
      "learning_rate": 0.0001,
      "loss": 0.0836,
      "step": 360
    },
    {
      "epoch": 2.18,
      "global_step": 380,
      "learning_rate": 0.0001,
      "loss": 0.0435,
      "step": 380
    },
    {
      "epoch": 2.3,
      "global_step": 400,
      "learning_rate": 0.0001,
      "loss": 0.0541,
      "step": 400
    },
    {
      "epoch": 2.41,
      "global_step": 420,
      "learning_rate": 0.0001,
      "loss": 0.0895,
      "step": 420
    },
    {
      "epoch": 2.53,
      "global_step": 440,
      "learning_rate": 0.0001,
      "loss": 0.0636,
      "step": 440
    },
    {
      "epoch": 2.64,
      "global_step": 460,
      "learning_rate": 0.0001,
      "loss": 0.0681,
      "step": 460
    },
    {
      "epoch": 2.76,
      "global_step": 480,
      "learning_rate": 0.0001,
      "loss": 0.0669,
      "step": 480
    },
    {
      "epoch": 2.87,
      "global_step": 500,
      "learning_rate": 0.0001,
      "loss": 0.0711,
      "step": 500
    },
    {
      "epoch": 2.99,
      "global_step": 520,
      "learning_rate": 0.0001,
      "loss": 0.0772,
      "step": 520
    },
    {
      "epoch": 3.0,
      "step": 522,
      "total_flos": 2.6811251459044147e+17,
      "train_loss": 0.16264161262018928,
      "train_runtime": 12144.157,
      "train_samples_per_second": 0.858,
      "train_steps_per_second": 0.043
    }
  ],
  "logging_steps": 20,
  "max_steps": 522,
  "num_train_epochs": 3,
  "save_steps": 300,
  "total_flos": 2.6811251459044147e+17,
  "trial_name": null,
  "trial_params": null
}