{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0014097413124691618,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001409741312469162,
      "grad_norm": 0.2717847526073456,
      "learning_rate": 2e-05,
      "loss": 0.9669,
      "step": 1
    },
    {
      "epoch": 0.0001409741312469162,
      "eval_loss": 0.9859963655471802,
      "eval_runtime": 202.0635,
      "eval_samples_per_second": 14.782,
      "eval_steps_per_second": 7.394,
      "step": 1
    },
    {
      "epoch": 0.0002819482624938324,
      "grad_norm": 0.28975191712379456,
      "learning_rate": 4e-05,
      "loss": 1.0655,
      "step": 2
    },
    {
      "epoch": 0.00042292239374074856,
      "grad_norm": 0.2648659646511078,
      "learning_rate": 6e-05,
      "loss": 1.1036,
      "step": 3
    },
    {
      "epoch": 0.00042292239374074856,
      "eval_loss": 0.9850538969039917,
      "eval_runtime": 200.4708,
      "eval_samples_per_second": 14.9,
      "eval_steps_per_second": 7.452,
      "step": 3
    },
    {
      "epoch": 0.0005638965249876648,
      "grad_norm": 0.2997431457042694,
      "learning_rate": 8e-05,
      "loss": 1.0173,
      "step": 4
    },
    {
      "epoch": 0.0007048706562345809,
      "grad_norm": 0.3512895405292511,
      "learning_rate": 0.0001,
      "loss": 1.0832,
      "step": 5
    },
    {
      "epoch": 0.0008458447874814971,
      "grad_norm": 0.3070140779018402,
      "learning_rate": 0.00012,
      "loss": 0.98,
      "step": 6
    },
    {
      "epoch": 0.0008458447874814971,
      "eval_loss": 0.9751449227333069,
      "eval_runtime": 200.6256,
      "eval_samples_per_second": 14.888,
      "eval_steps_per_second": 7.447,
      "step": 6
    },
    {
      "epoch": 0.0009868189187284134,
      "grad_norm": 0.331495076417923,
      "learning_rate": 0.00014,
      "loss": 0.9225,
      "step": 7
    },
    {
      "epoch": 0.0011277930499753296,
      "grad_norm": 0.353227436542511,
      "learning_rate": 0.00016,
      "loss": 0.9801,
      "step": 8
    },
    {
      "epoch": 0.0012687671812222456,
      "grad_norm": 0.42658260464668274,
      "learning_rate": 0.00018,
      "loss": 1.0292,
      "step": 9
    },
    {
      "epoch": 0.0012687671812222456,
      "eval_loss": 0.9365012049674988,
      "eval_runtime": 200.6108,
      "eval_samples_per_second": 14.89,
      "eval_steps_per_second": 7.447,
      "step": 9
    },
    {
      "epoch": 0.0014097413124691618,
      "grad_norm": 0.40287280082702637,
      "learning_rate": 0.0002,
      "loss": 0.8795,
      "step": 10
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4353532467609600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}