{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002548853016142736,
  "eval_steps": 3,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004248088360237893,
      "grad_norm": 1.3417097330093384,
      "learning_rate": 2e-05,
      "loss": 6.5457,
      "step": 1
    },
    {
      "epoch": 0.0004248088360237893,
      "eval_loss": 1.7954938411712646,
      "eval_runtime": 29.4129,
      "eval_samples_per_second": 33.727,
      "eval_steps_per_second": 16.863,
      "step": 1
    },
    {
      "epoch": 0.0008496176720475786,
      "grad_norm": 1.449083685874939,
      "learning_rate": 4e-05,
      "loss": 7.6285,
      "step": 2
    },
    {
      "epoch": 0.001274426508071368,
      "grad_norm": 1.4717646837234497,
      "learning_rate": 6e-05,
      "loss": 6.897,
      "step": 3
    },
    {
      "epoch": 0.001274426508071368,
      "eval_loss": 1.792671799659729,
      "eval_runtime": 29.458,
      "eval_samples_per_second": 33.675,
      "eval_steps_per_second": 16.838,
      "step": 3
    },
    {
      "epoch": 0.0016992353440951572,
      "grad_norm": 1.2402433156967163,
      "learning_rate": 8e-05,
      "loss": 7.1005,
      "step": 4
    },
    {
      "epoch": 0.0021240441801189465,
      "grad_norm": 1.4624475240707397,
      "learning_rate": 0.0001,
      "loss": 6.9481,
      "step": 5
    },
    {
      "epoch": 0.002548853016142736,
      "grad_norm": 1.6787381172180176,
      "learning_rate": 0.00012,
      "loss": 7.2956,
      "step": 6
    },
    {
      "epoch": 0.002548853016142736,
      "eval_loss": 1.7664850950241089,
      "eval_runtime": 35.0121,
      "eval_samples_per_second": 28.333,
      "eval_steps_per_second": 14.167,
      "step": 6
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 550772026638336.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}