{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9801324503311258,
  "eval_steps": 500,
  "global_step": 37,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "grad_norm": 5.132448196411133,
      "learning_rate": 0.0001911228490388136,
      "loss": 1.8153,
      "step": 5
    },
    {
      "epoch": 0.26,
      "grad_norm": 2.215226411819458,
      "learning_rate": 0.00016606747233900815,
      "loss": 0.3952,
      "step": 10
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.2212655544281006,
      "learning_rate": 0.00012928227712765504,
      "loss": 0.2029,
      "step": 15
    },
    {
      "epoch": 0.53,
      "grad_norm": 1.6850711107254028,
      "learning_rate": 8.729821802531212e-05,
      "loss": 0.1657,
      "step": 20
    },
    {
      "epoch": 0.66,
      "grad_norm": 1.355529546737671,
      "learning_rate": 4.756927164427685e-05,
      "loss": 0.1042,
      "step": 25
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.9691661596298218,
      "learning_rate": 1.7149035075615794e-05,
      "loss": 0.1004,
      "step": 30
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.6373167037963867,
      "learning_rate": 1.4384089652291543e-06,
      "loss": 0.0942,
      "step": 35
    },
    {
      "epoch": 0.98,
      "step": 37,
      "total_flos": 7654509483393024.0,
      "train_loss": 0.3938806479847109,
      "train_runtime": 8367.9218,
      "train_samples_per_second": 0.289,
      "train_steps_per_second": 0.004
    }
  ],
  "logging_steps": 5,
  "max_steps": 37,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 7654509483393024.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}