{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6535947712418301,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "grad_norm": 2.2709479331970215,
      "learning_rate": 1.893939393939394e-05,
      "loss": 2.1535,
      "step": 25
    },
    {
      "epoch": 0.16,
      "eval_loss": 0.8891100883483887,
      "eval_runtime": 557.5601,
      "eval_samples_per_second": 0.549,
      "eval_steps_per_second": 0.07,
      "step": 25
    },
    {
      "epoch": 0.33,
      "grad_norm": 1.444481372833252,
      "learning_rate": 1.2626262626262628e-05,
      "loss": 0.6036,
      "step": 50
    },
    {
      "epoch": 0.33,
      "eval_loss": 0.5400559902191162,
      "eval_runtime": 559.0343,
      "eval_samples_per_second": 0.547,
      "eval_steps_per_second": 0.07,
      "step": 50
    },
    {
      "epoch": 0.49,
      "grad_norm": 1.2420704364776611,
      "learning_rate": 6.313131313131314e-06,
      "loss": 0.5241,
      "step": 75
    },
    {
      "epoch": 0.49,
      "eval_loss": 0.50448077917099,
      "eval_runtime": 558.8357,
      "eval_samples_per_second": 0.548,
      "eval_steps_per_second": 0.07,
      "step": 75
    },
    {
      "epoch": 0.65,
      "grad_norm": 11.422951698303223,
      "learning_rate": 0.0,
      "loss": 0.4877,
      "step": 100
    },
    {
      "epoch": 0.65,
      "eval_loss": 0.498330295085907,
      "eval_runtime": 560.039,
      "eval_samples_per_second": 0.546,
      "eval_steps_per_second": 0.07,
      "step": 100
    }
  ],
  "logging_steps": 25,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "total_flos": 4109385282355200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}