{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3002865329512894,
  "global_step": 524,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.9988538681948425e-05,
      "loss": 3.3001,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.970200573065903e-05,
      "loss": 2.9734,
      "step": 26
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.9404011461318052e-05,
      "loss": 2.9919,
      "step": 52
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.910601719197708e-05,
      "loss": 2.9257,
      "step": 78
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.8808022922636103e-05,
      "loss": 2.9255,
      "step": 104
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.851002865329513e-05,
      "loss": 2.9036,
      "step": 130
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.8212034383954157e-05,
      "loss": 2.9194,
      "step": 156
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.791404011461318e-05,
      "loss": 2.726,
      "step": 182
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.7616045845272208e-05,
      "loss": 2.909,
      "step": 208
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.7318051575931235e-05,
      "loss": 2.6554,
      "step": 234
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.702005730659026e-05,
      "loss": 2.7529,
      "step": 260
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.6722063037249286e-05,
      "loss": 2.7147,
      "step": 286
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.642406876790831e-05,
      "loss": 2.695,
      "step": 312
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.6137535816618913e-05,
      "loss": 2.7071,
      "step": 338
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.583954154727794e-05,
      "loss": 2.7039,
      "step": 364
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.5541547277936964e-05,
      "loss": 2.7586,
      "step": 390
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.5243553008595991e-05,
      "loss": 2.8132,
      "step": 416
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.495702005730659e-05,
      "loss": 2.7552,
      "step": 442
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.4659025787965618e-05,
      "loss": 2.7388,
      "step": 468
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.4361031518624645e-05,
      "loss": 2.6576,
      "step": 494
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.4063037249283669e-05,
      "loss": 2.6962,
      "step": 520
    }
  ],
  "max_steps": 1745,
  "num_train_epochs": 1,
  "total_flos": 975816804532224.0,
  "trial_name": null,
  "trial_params": null
}