{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.4603174603174602,
  "eval_steps": 500,
  "global_step": 126,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19,
      "learning_rate": 0.00018461538461538463,
      "loss": 1.6312,
      "step": 12
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00018053097345132742,
      "loss": 1.5761,
      "step": 24
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001592920353982301,
      "loss": 1.6254,
      "step": 36
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00013805309734513276,
      "loss": 1.6214,
      "step": 48
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00011681415929203541,
      "loss": 1.6554,
      "step": 60
    },
    {
      "epoch": 1.14,
      "learning_rate": 9.557522123893806e-05,
      "loss": 1.6088,
      "step": 72
    },
    {
      "epoch": 1.33,
      "learning_rate": 7.433628318584072e-05,
      "loss": 1.7079,
      "step": 84
    },
    {
      "epoch": 1.52,
      "learning_rate": 5.309734513274337e-05,
      "loss": 1.7,
      "step": 96
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.185840707964602e-05,
      "loss": 1.6297,
      "step": 108
    },
    {
      "epoch": 1.37,
      "learning_rate": 1.0619469026548673e-05,
      "loss": 1.5316,
      "step": 120
    }
  ],
  "logging_steps": 12,
  "max_steps": 126,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 8.153799992121754e+16,
  "trial_name": null,
  "trial_params": null
}