{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.970873786407767,
  "eval_steps": 20,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 1.9393939393939395e-05,
      "loss": 1.8315,
      "step": 20
    },
    {
      "epoch": 0.05,
      "eval_loss": 1.8022956848144531,
      "eval_runtime": 192.4256,
      "eval_samples_per_second": 1.949,
      "eval_steps_per_second": 0.197,
      "step": 20
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.8585858585858588e-05,
      "loss": 1.7689,
      "step": 40
    },
    {
      "epoch": 0.1,
      "eval_loss": 1.7563962936401367,
      "eval_runtime": 192.2202,
      "eval_samples_per_second": 1.951,
      "eval_steps_per_second": 0.198,
      "step": 40
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.7777777777777777e-05,
      "loss": 1.7292,
      "step": 60
    },
    {
      "epoch": 0.15,
      "eval_loss": 1.7281174659729004,
      "eval_runtime": 192.2275,
      "eval_samples_per_second": 1.951,
      "eval_steps_per_second": 0.198,
      "step": 60
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.6969696969696972e-05,
      "loss": 1.7028,
      "step": 80
    },
    {
      "epoch": 0.19,
      "eval_loss": 1.7117385864257812,
      "eval_runtime": 192.209,
      "eval_samples_per_second": 1.951,
      "eval_steps_per_second": 0.198,
      "step": 80
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.616161616161616e-05,
      "loss": 1.6939,
      "step": 100
    },
    {
      "epoch": 0.24,
      "eval_loss": 1.701405644416809,
      "eval_runtime": 192.2738,
      "eval_samples_per_second": 1.95,
      "eval_steps_per_second": 0.198,
      "step": 100
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.5353535353535354e-05,
      "loss": 1.6889,
      "step": 120
    },
    {
      "epoch": 0.29,
      "eval_loss": 1.6941999197006226,
      "eval_runtime": 192.278,
      "eval_samples_per_second": 1.95,
      "eval_steps_per_second": 0.198,
      "step": 120
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.4545454545454546e-05,
      "loss": 1.6827,
      "step": 140
    },
    {
      "epoch": 0.34,
      "eval_loss": 1.6888084411621094,
      "eval_runtime": 192.3059,
      "eval_samples_per_second": 1.95,
      "eval_steps_per_second": 0.198,
      "step": 140
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.3737373737373739e-05,
      "loss": 1.6611,
      "step": 160
    },
    {
      "epoch": 0.39,
      "eval_loss": 1.6843013763427734,
      "eval_runtime": 192.286,
      "eval_samples_per_second": 1.95,
      "eval_steps_per_second": 0.198,
      "step": 160
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.2929292929292931e-05,
      "loss": 1.6672,
      "step": 180
    },
    {
      "epoch": 0.44,
      "eval_loss": 1.6804944276809692,
      "eval_runtime": 192.2525,
      "eval_samples_per_second": 1.951,
      "eval_steps_per_second": 0.198,
      "step": 180
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.2121212121212122e-05,
      "loss": 1.6435,
      "step": 200
    },
    {
      "epoch": 0.49,
      "eval_loss": 1.676919937133789,
      "eval_runtime": 192.2677,
      "eval_samples_per_second": 1.95,
      "eval_steps_per_second": 0.198,
      "step": 200
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.1313131313131314e-05,
      "loss": 1.6804,
      "step": 220
    },
    {
      "epoch": 0.53,
      "eval_loss": 1.6742541790008545,
      "eval_runtime": 192.263,
      "eval_samples_per_second": 1.95,
      "eval_steps_per_second": 0.198,
      "step": 220
    },
    {
      "epoch": 0.58,
      "learning_rate": 1.0505050505050507e-05,
      "loss": 1.6542,
      "step": 240
    },
    {
      "epoch": 0.58,
      "eval_loss": 1.6716855764389038,
      "eval_runtime": 192.2148,
      "eval_samples_per_second": 1.951,
      "eval_steps_per_second": 0.198,
      "step": 240
    },
    {
      "epoch": 0.63,
      "learning_rate": 9.696969696969698e-06,
      "loss": 1.6417,
      "step": 260
    },
    {
      "epoch": 0.63,
      "eval_loss": 1.6693024635314941,
      "eval_runtime": 192.2366,
      "eval_samples_per_second": 1.951,
      "eval_steps_per_second": 0.198,
      "step": 260
    },
    {
      "epoch": 0.68,
      "learning_rate": 8.888888888888888e-06,
      "loss": 1.6895,
      "step": 280
    },
    {
      "epoch": 0.68,
      "eval_loss": 1.667194128036499,
      "eval_runtime": 192.2439,
      "eval_samples_per_second": 1.951,
      "eval_steps_per_second": 0.198,
      "step": 280
    },
    {
      "epoch": 0.73,
      "learning_rate": 8.08080808080808e-06,
      "loss": 1.6637,
      "step": 300
    },
    {
      "epoch": 0.73,
      "eval_loss": 1.6655081510543823,
      "eval_runtime": 192.2484,
      "eval_samples_per_second": 1.951,
      "eval_steps_per_second": 0.198,
      "step": 300
    },
    {
      "epoch": 0.78,
      "learning_rate": 7.272727272727273e-06,
      "loss": 1.6537,
      "step": 320
    },
    {
      "epoch": 0.78,
      "eval_loss": 1.663667917251587,
      "eval_runtime": 192.2591,
      "eval_samples_per_second": 1.95,
      "eval_steps_per_second": 0.198,
      "step": 320
    },
    {
      "epoch": 0.83,
      "learning_rate": 6.464646464646466e-06,
      "loss": 1.6489,
      "step": 340
    },
    {
      "epoch": 0.83,
      "eval_loss": 1.6618822813034058,
      "eval_runtime": 192.2528,
      "eval_samples_per_second": 1.951,
      "eval_steps_per_second": 0.198,
      "step": 340
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.656565656565657e-06,
      "loss": 1.6555,
      "step": 360
    },
    {
      "epoch": 0.87,
      "eval_loss": 1.6608922481536865,
      "eval_runtime": 192.2301,
      "eval_samples_per_second": 1.951,
      "eval_steps_per_second": 0.198,
      "step": 360
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.848484848484849e-06,
      "loss": 1.6515,
      "step": 380
    },
    {
      "epoch": 0.92,
      "eval_loss": 1.6594582796096802,
      "eval_runtime": 192.2624,
      "eval_samples_per_second": 1.95,
      "eval_steps_per_second": 0.198,
      "step": 380
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.04040404040404e-06,
      "loss": 1.6337,
      "step": 400
    },
    {
      "epoch": 0.97,
      "eval_loss": 1.658281922340393,
      "eval_runtime": 192.2205,
      "eval_samples_per_second": 1.951,
      "eval_steps_per_second": 0.198,
      "step": 400
    }
  ],
  "logging_steps": 20,
  "max_steps": 500,
  "num_train_epochs": 2,
  "save_steps": 20,
  "total_flos": 2.804385205714944e+17,
  "trial_name": null,
  "trial_params": null
}