{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.23007555447233732,
  "eval_steps": 500,
  "global_step": 59,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2e-05,
      "loss": 2.2943,
      "step": 1
    },
    {
      "epoch": 0.02,
      "learning_rate": 2e-05,
      "loss": 2.2924,
      "step": 5
    },
    {
      "epoch": 0.04,
      "learning_rate": 2e-05,
      "loss": 2.2901,
      "step": 10
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.9987954562051724e-05,
      "loss": 2.2728,
      "step": 15
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.995184726672197e-05,
      "loss": 2.2135,
      "step": 20
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9873014181578588e-05,
      "loss": 2.152,
      "step": 25
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9757021300385288e-05,
      "loss": 2.1002,
      "step": 30
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.960430519415566e-05,
      "loss": 2.0584,
      "step": 35
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.941544065183021e-05,
      "loss": 2.0218,
      "step": 40
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.919113851690058e-05,
      "loss": 1.9985,
      "step": 45
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.8932243011955154e-05,
      "loss": 1.9756,
      "step": 50
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.863972856121587e-05,
      "loss": 1.9655,
      "step": 55
    },
    {
      "epoch": 0.23,
      "eval_loss": 1.939131736755371,
      "eval_runtime": 5104.2894,
      "eval_samples_per_second": 2.583,
      "eval_steps_per_second": 0.323,
      "step": 59
    },
    {
      "epoch": 0.23,
      "step": 59,
      "total_flos": 1.1270411199184896e+16,
      "train_loss": 2.1341428110155007,
      "train_runtime": 96692.089,
      "train_samples_per_second": 1.358,
      "train_steps_per_second": 0.003
    }
  ],
  "logging_steps": 5,
  "max_steps": 256,
  "num_train_epochs": 1,
  "save_steps": 25,
  "total_flos": 1.1270411199184896e+16,
  "trial_name": null,
  "trial_params": null
}