{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.0,
  "global_step": 1368,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 2.965881397238018e-05,
      "loss": 1.3459,
      "step": 152
    },
    {
      "epoch": 2.0,
      "learning_rate": 2.5954508529650693e-05,
      "loss": 0.7067,
      "step": 304
    },
    {
      "epoch": 3.0,
      "learning_rate": 2.22502030869212e-05,
      "loss": 0.2494,
      "step": 456
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.8545897644191714e-05,
      "loss": 0.0634,
      "step": 608
    },
    {
      "epoch": 5.0,
      "learning_rate": 1.4841592201462226e-05,
      "loss": 0.0222,
      "step": 760
    },
    {
      "epoch": 6.0,
      "learning_rate": 1.1137286758732738e-05,
      "loss": 0.0062,
      "step": 912
    },
    {
      "epoch": 7.0,
      "learning_rate": 7.4329813160032494e-06,
      "loss": 0.0047,
      "step": 1064
    },
    {
      "epoch": 8.0,
      "learning_rate": 3.728675873273761e-06,
      "loss": 0.002,
      "step": 1216
    },
    {
      "epoch": 9.0,
      "learning_rate": 2.437043054427295e-08,
      "loss": 0.0017,
      "step": 1368
    },
    {
      "epoch": 9.0,
      "step": 1368,
      "total_flos": 3267933886955520.0,
      "train_loss": 0.26691262162568274,
      "train_runtime": 934.9288,
      "train_samples_per_second": 13.169,
      "train_steps_per_second": 1.463
    }
  ],
  "max_steps": 1368,
  "num_train_epochs": 9,
  "total_flos": 3267933886955520.0,
  "trial_name": null,
  "trial_params": null
}