{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07048458149779736,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014096916299559472,
      "grad_norm": 27.41485023498535,
      "learning_rate": 1e-05,
      "loss": 10.1421,
      "step": 1
    },
    {
      "epoch": 0.014096916299559472,
      "eval_loss": 10.102472305297852,
      "eval_runtime": 57.6428,
      "eval_samples_per_second": 2.082,
      "eval_steps_per_second": 1.041,
      "step": 1
    },
    {
      "epoch": 0.028193832599118944,
      "grad_norm": 26.613746643066406,
      "learning_rate": 2e-05,
      "loss": 9.9812,
      "step": 2
    },
    {
      "epoch": 0.028193832599118944,
      "eval_loss": 9.332456588745117,
      "eval_runtime": 5.7433,
      "eval_samples_per_second": 20.894,
      "eval_steps_per_second": 10.447,
      "step": 2
    },
    {
      "epoch": 0.04229074889867841,
      "grad_norm": 26.700958251953125,
      "learning_rate": 3e-05,
      "loss": 9.6083,
      "step": 3
    },
    {
      "epoch": 0.05638766519823789,
      "grad_norm": 28.18412208557129,
      "learning_rate": 4e-05,
      "loss": 8.8679,
      "step": 4
    },
    {
      "epoch": 0.05638766519823789,
      "eval_loss": 7.889341831207275,
      "eval_runtime": 5.789,
      "eval_samples_per_second": 20.729,
      "eval_steps_per_second": 10.364,
      "step": 4
    },
    {
      "epoch": 0.07048458149779736,
      "grad_norm": 28.531749725341797,
      "learning_rate": 5e-05,
      "loss": 7.8716,
      "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": 3699128496291840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}