{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.526315789473684,
  "eval_steps": 500,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21,
      "grad_norm": 7.686335725067591,
      "learning_rate": 5e-07,
      "loss": 1.4116,
      "step": 1
    },
    {
      "epoch": 0.84,
      "eval_loss": 1.558627963066101,
      "eval_runtime": 5.3458,
      "eval_samples_per_second": 11.972,
      "eval_steps_per_second": 0.748,
      "step": 4
    },
    {
      "epoch": 1.05,
      "grad_norm": 7.287253588921336,
      "learning_rate": 7.938926261462365e-07,
      "loss": 1.4074,
      "step": 5
    },
    {
      "epoch": 1.89,
      "eval_loss": 1.517771601676941,
      "eval_runtime": 5.2983,
      "eval_samples_per_second": 12.079,
      "eval_steps_per_second": 0.755,
      "step": 9
    },
    {
      "epoch": 2.11,
      "grad_norm": 6.50356839675754,
      "learning_rate": 9.549150281252632e-08,
      "loss": 1.3759,
      "step": 10
    },
    {
      "epoch": 2.53,
      "eval_loss": 1.5166064500808716,
      "eval_runtime": 5.4659,
      "eval_samples_per_second": 11.709,
      "eval_steps_per_second": 0.732,
      "step": 12
    },
    {
      "epoch": 2.53,
      "step": 12,
      "total_flos": 2460210954240.0,
      "train_loss": 1.3832212686538696,
      "train_runtime": 213.2984,
      "train_samples_per_second": 4.149,
      "train_steps_per_second": 0.056
    }
  ],
  "logging_steps": 5,
  "max_steps": 12,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2460210954240.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}