{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.21181952976064394,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.94e-05,
      "loss": 1.5846,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.88e-05,
      "loss": 1.5243,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.8199999999999998e-05,
      "loss": 1.4602,
      "step": 30
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.7600000000000003e-05,
      "loss": 1.362,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 1.3764,
      "step": 50
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.64e-05,
      "loss": 1.4106,
      "step": 60
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.58e-05,
      "loss": 1.3587,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.52e-05,
      "loss": 1.3161,
      "step": 80
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.4599999999999998e-05,
      "loss": 1.2997,
      "step": 90
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.4e-05,
      "loss": 1.3402,
      "step": 100
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.3400000000000003e-05,
      "loss": 1.3005,
      "step": 110
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.2800000000000002e-05,
      "loss": 1.3074,
      "step": 120
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.22e-05,
      "loss": 1.2483,
      "step": 130
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.16e-05,
      "loss": 1.2623,
      "step": 140
    },
    {
      "epoch": 0.06,
      "learning_rate": 2.1e-05,
      "loss": 1.2441,
      "step": 150
    },
    {
      "epoch": 0.07,
      "learning_rate": 2.04e-05,
      "loss": 1.2898,
      "step": 160
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.98e-05,
      "loss": 1.3296,
      "step": 170
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 1.2303,
      "step": 180
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.86e-05,
      "loss": 1.2231,
      "step": 190
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.8e-05,
      "loss": 1.261,
      "step": 200
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.74e-05,
      "loss": 1.2431,
      "step": 210
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 1.1958,
      "step": 220
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.62e-05,
      "loss": 1.2823,
      "step": 230
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.56e-05,
      "loss": 1.2633,
      "step": 240
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.5e-05,
      "loss": 1.2505,
      "step": 250
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.44e-05,
      "loss": 1.2069,
      "step": 260
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.3800000000000002e-05,
      "loss": 1.2934,
      "step": 270
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.32e-05,
      "loss": 1.2182,
      "step": 280
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.26e-05,
      "loss": 1.3058,
      "step": 290
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.2e-05,
      "loss": 1.2098,
      "step": 300
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.1400000000000001e-05,
      "loss": 1.21,
      "step": 310
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.08e-05,
      "loss": 1.2724,
      "step": 320
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.02e-05,
      "loss": 1.2423,
      "step": 330
    },
    {
      "epoch": 0.14,
      "learning_rate": 9.600000000000001e-06,
      "loss": 1.2259,
      "step": 340
    },
    {
      "epoch": 0.15,
      "learning_rate": 9e-06,
      "loss": 1.2927,
      "step": 350
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.400000000000001e-06,
      "loss": 1.3111,
      "step": 360
    },
    {
      "epoch": 0.16,
      "learning_rate": 7.8e-06,
      "loss": 1.2766,
      "step": 370
    },
    {
      "epoch": 0.16,
      "learning_rate": 7.2e-06,
      "loss": 1.2471,
      "step": 380
    },
    {
      "epoch": 0.17,
      "learning_rate": 6.6e-06,
      "loss": 1.2167,
      "step": 390
    },
    {
      "epoch": 0.17,
      "learning_rate": 6e-06,
      "loss": 1.2754,
      "step": 400
    },
    {
      "epoch": 0.17,
      "learning_rate": 5.4e-06,
      "loss": 1.2609,
      "step": 410
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.800000000000001e-06,
      "loss": 1.2926,
      "step": 420
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 1.2484,
      "step": 430
    },
    {
      "epoch": 0.19,
      "learning_rate": 3.6e-06,
      "loss": 1.2508,
      "step": 440
    },
    {
      "epoch": 0.19,
      "learning_rate": 3e-06,
      "loss": 1.2875,
      "step": 450
    },
    {
      "epoch": 0.19,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 1.2843,
      "step": 460
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.8e-06,
      "loss": 1.2279,
      "step": 470
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.2368,
      "step": 480
    },
    {
      "epoch": 0.21,
      "learning_rate": 6.000000000000001e-07,
      "loss": 1.2537,
      "step": 490
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0,
      "loss": 1.3018,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 7.258955123193446e+16,
  "trial_name": null,
  "trial_params": null
}