{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03436426116838488,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006872852233676976,
      "grad_norm": 10.828211784362793,
      "learning_rate": 1e-05,
      "loss": 6.5286,
      "step": 1
    },
    {
      "epoch": 0.006872852233676976,
      "eval_loss": 6.855241775512695,
      "eval_runtime": 117.8687,
      "eval_samples_per_second": 2.079,
      "eval_steps_per_second": 1.044,
      "step": 1
    },
    {
      "epoch": 0.013745704467353952,
      "grad_norm": 10.8191556930542,
      "learning_rate": 2e-05,
      "loss": 6.7796,
      "step": 2
    },
    {
      "epoch": 0.013745704467353952,
      "eval_loss": 6.450685977935791,
      "eval_runtime": 22.6046,
      "eval_samples_per_second": 10.839,
      "eval_steps_per_second": 5.441,
      "step": 2
    },
    {
      "epoch": 0.020618556701030927,
      "grad_norm": 11.414745330810547,
      "learning_rate": 3e-05,
      "loss": 6.1633,
      "step": 3
    },
    {
      "epoch": 0.027491408934707903,
      "grad_norm": 11.88432502746582,
      "learning_rate": 4e-05,
      "loss": 6.3005,
      "step": 4
    },
    {
      "epoch": 0.027491408934707903,
      "eval_loss": 5.8977460861206055,
      "eval_runtime": 22.6937,
      "eval_samples_per_second": 10.796,
      "eval_steps_per_second": 5.42,
      "step": 4
    },
    {
      "epoch": 0.03436426116838488,
      "grad_norm": 12.588489532470703,
      "learning_rate": 5e-05,
      "loss": 5.7054,
      "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": 1640097329971200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}