{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.7123287671232876,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.7063,
      "step": 10
    },
    {
      "epoch": 0.07,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.6727,
      "step": 20
    },
    {
      "epoch": 0.1,
      "learning_rate": 3e-06,
      "loss": 0.6957,
      "step": 30
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.6775,
      "step": 40
    },
    {
      "epoch": 0.17,
      "learning_rate": 5e-06,
      "loss": 0.6918,
      "step": 50
    },
    {
      "epoch": 0.21,
      "learning_rate": 6e-06,
      "loss": 0.6939,
      "step": 60
    },
    {
      "epoch": 0.24,
      "learning_rate": 7.000000000000001e-06,
      "loss": 0.6684,
      "step": 70
    },
    {
      "epoch": 0.27,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.6312,
      "step": 80
    },
    {
      "epoch": 0.31,
      "learning_rate": 9e-06,
      "loss": 0.5444,
      "step": 90
    },
    {
      "epoch": 0.34,
      "learning_rate": 1e-05,
      "loss": 0.435,
      "step": 100
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.3208,
      "step": 110
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.2e-05,
      "loss": 0.3709,
      "step": 120
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.4004,
      "step": 130
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.3061,
      "step": 140
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.5e-05,
      "loss": 0.3556,
      "step": 150
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.2945,
      "step": 160
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 0.3984,
      "step": 170
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.8e-05,
      "loss": 0.3539,
      "step": 180
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.9e-05,
      "loss": 0.4119,
      "step": 190
    },
    {
      "epoch": 0.68,
      "learning_rate": 2e-05,
      "loss": 0.3457,
      "step": 200
    },
    {
      "epoch": 0.72,
      "learning_rate": 2.1e-05,
      "loss": 0.3241,
      "step": 210
    },
    {
      "epoch": 0.75,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.4169,
      "step": 220
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 0.3863,
      "step": 230
    },
    {
      "epoch": 0.82,
      "learning_rate": 2.4e-05,
      "loss": 0.2749,
      "step": 240
    },
    {
      "epoch": 0.86,
      "learning_rate": 2.5e-05,
      "loss": 0.3399,
      "step": 250
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.2771,
      "step": 260
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 0.3155,
      "step": 270
    },
    {
      "epoch": 0.96,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.3677,
      "step": 280
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.9e-05,
      "loss": 0.2678,
      "step": 290
    },
    {
      "epoch": 1.03,
      "learning_rate": 3e-05,
      "loss": 0.2909,
      "step": 300
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.1e-05,
      "loss": 0.2997,
      "step": 310
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.2799,
      "step": 320
    },
    {
      "epoch": 1.13,
      "learning_rate": 3.3e-05,
      "loss": 0.2793,
      "step": 330
    },
    {
      "epoch": 1.16,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.2785,
      "step": 340
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.5e-05,
      "loss": 0.292,
      "step": 350
    },
    {
      "epoch": 1.23,
      "learning_rate": 3.6e-05,
      "loss": 0.2058,
      "step": 360
    },
    {
      "epoch": 1.27,
      "learning_rate": 3.7e-05,
      "loss": 0.2439,
      "step": 370
    },
    {
      "epoch": 1.3,
      "learning_rate": 3.8e-05,
      "loss": 0.4566,
      "step": 380
    },
    {
      "epoch": 1.34,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 0.5624,
      "step": 390
    },
    {
      "epoch": 1.37,
      "learning_rate": 4e-05,
      "loss": 0.2315,
      "step": 400
    },
    {
      "epoch": 1.4,
      "learning_rate": 4.1e-05,
      "loss": 0.184,
      "step": 410
    },
    {
      "epoch": 1.44,
      "learning_rate": 4.2e-05,
      "loss": 0.3491,
      "step": 420
    },
    {
      "epoch": 1.47,
      "learning_rate": 4.3e-05,
      "loss": 0.3401,
      "step": 430
    },
    {
      "epoch": 1.51,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.2944,
      "step": 440
    },
    {
      "epoch": 1.54,
      "learning_rate": 4.5e-05,
      "loss": 0.244,
      "step": 450
    },
    {
      "epoch": 1.58,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.3155,
      "step": 460
    },
    {
      "epoch": 1.61,
      "learning_rate": 4.7e-05,
      "loss": 0.2387,
      "step": 470
    },
    {
      "epoch": 1.64,
      "learning_rate": 4.8e-05,
      "loss": 0.2712,
      "step": 480
    },
    {
      "epoch": 1.68,
      "learning_rate": 4.9e-05,
      "loss": 0.3125,
      "step": 490
    },
    {
      "epoch": 1.71,
      "learning_rate": 5e-05,
      "loss": 0.2915,
      "step": 500
    }
  ],
  "max_steps": 1460,
  "num_train_epochs": 5,
  "total_flos": 1059606721849344.0,
  "trial_name": null,
  "trial_params": null
}