{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00021064660608821354,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.2129321217642704e-05,
      "grad_norm": 0.020388737320899963,
      "learning_rate": 1e-05,
      "loss": 10.3781,
      "step": 1
    },
    {
      "epoch": 4.2129321217642704e-05,
      "eval_loss": 10.377666473388672,
      "eval_runtime": 177.3775,
      "eval_samples_per_second": 225.384,
      "eval_steps_per_second": 112.692,
      "step": 1
    },
    {
      "epoch": 8.425864243528541e-05,
      "grad_norm": 0.023491423577070236,
      "learning_rate": 2e-05,
      "loss": 10.3788,
      "step": 2
    },
    {
      "epoch": 8.425864243528541e-05,
      "eval_loss": 10.377660751342773,
      "eval_runtime": 169.8716,
      "eval_samples_per_second": 235.342,
      "eval_steps_per_second": 117.671,
      "step": 2
    },
    {
      "epoch": 0.00012638796365292812,
      "grad_norm": 0.020947178825736046,
      "learning_rate": 3e-05,
      "loss": 10.3779,
      "step": 3
    },
    {
      "epoch": 0.00016851728487057082,
      "grad_norm": 0.021885480731725693,
      "learning_rate": 4e-05,
      "loss": 10.3768,
      "step": 4
    },
    {
      "epoch": 0.00016851728487057082,
      "eval_loss": 10.37763786315918,
      "eval_runtime": 181.5026,
      "eval_samples_per_second": 220.261,
      "eval_steps_per_second": 110.131,
      "step": 4
    },
    {
      "epoch": 0.00021064660608821354,
      "grad_norm": 0.02301969937980175,
      "learning_rate": 5e-05,
      "loss": 10.3768,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 320039976960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}