{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 42,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.023809523809523808,
      "grad_norm": 0.35546875,
      "learning_rate": 4e-05,
      "loss": 0.9948,
      "step": 1
    },
    {
      "epoch": 0.11904761904761904,
      "grad_norm": 0.31640625,
      "learning_rate": 0.0002,
      "loss": 1.1099,
      "step": 5
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 0.31640625,
      "learning_rate": 0.0001911228490388136,
      "loss": 1.048,
      "step": 10
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00016606747233900815,
      "loss": 0.9912,
      "step": 15
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.2578125,
      "learning_rate": 0.00012928227712765504,
      "loss": 0.9396,
      "step": 20
    },
    {
      "epoch": 0.5952380952380952,
      "grad_norm": 0.2294921875,
      "learning_rate": 8.729821802531212e-05,
      "loss": 0.997,
      "step": 25
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.2421875,
      "learning_rate": 4.756927164427685e-05,
      "loss": 1.0419,
      "step": 30
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.248046875,
      "learning_rate": 1.7149035075615794e-05,
      "loss": 1.0231,
      "step": 35
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.208984375,
      "learning_rate": 1.4384089652291543e-06,
      "loss": 0.9758,
      "step": 40
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.0181750059127808,
      "eval_runtime": 88.1603,
      "eval_samples_per_second": 3.755,
      "eval_steps_per_second": 0.476,
      "step": 42
    },
    {
      "epoch": 1.0,
      "step": 42,
      "total_flos": 2.935565656994611e+16,
      "train_loss": 1.0143198739914667,
      "train_runtime": 408.5529,
      "train_samples_per_second": 0.818,
      "train_steps_per_second": 0.103
    }
  ],
  "logging_steps": 5,
  "max_steps": 42,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "total_flos": 2.935565656994611e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}