{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 169,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11834319526627218,
      "grad_norm": 0.85546875,
      "learning_rate": 2.9411764705882355e-06,
      "loss": 1.5092,
      "step": 20
    },
    {
      "epoch": 0.23668639053254437,
      "grad_norm": 0.9609375,
      "learning_rate": 4.975670171853926e-06,
      "loss": 1.4576,
      "step": 40
    },
    {
      "epoch": 0.35502958579881655,
      "grad_norm": 0.71875,
      "learning_rate": 4.556187738201656e-06,
      "loss": 1.4078,
      "step": 60
    },
    {
      "epoch": 0.47337278106508873,
      "grad_norm": 0.6015625,
      "learning_rate": 3.699282783125616e-06,
      "loss": 1.3452,
      "step": 80
    },
    {
      "epoch": 0.591715976331361,
      "grad_norm": 0.62109375,
      "learning_rate": 2.587248741756253e-06,
      "loss": 1.3563,
      "step": 100
    },
    {
      "epoch": 0.7100591715976331,
      "grad_norm": 0.6171875,
      "learning_rate": 1.4566538637954556e-06,
      "loss": 1.2719,
      "step": 120
    },
    {
      "epoch": 0.8284023668639053,
      "grad_norm": 0.66796875,
      "learning_rate": 5.48014933308352e-07,
      "loss": 1.2821,
      "step": 140
    },
    {
      "epoch": 0.9467455621301775,
      "grad_norm": 0.6953125,
      "learning_rate": 5.463099816548578e-08,
      "loss": 1.2609,
      "step": 160
    },
    {
      "epoch": 1.0,
      "step": 169,
      "total_flos": 3.1131346491408384e+16,
      "train_loss": 1.3569896573851095,
      "train_runtime": 1247.7147,
      "train_samples_per_second": 0.542,
      "train_steps_per_second": 0.135
    }
  ],
  "logging_steps": 20,
  "max_steps": 169,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 3.1131346491408384e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}