{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.21474105684632e-05,
  "eval_steps": 3,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.40491368561544e-05,
      "grad_norm": 11.456639289855957,
      "learning_rate": 2e-05,
      "loss": 10.8262,
      "step": 1
    },
    {
      "epoch": 1.40491368561544e-05,
      "eval_loss": 12.163054466247559,
      "eval_runtime": 413.6256,
      "eval_samples_per_second": 72.457,
      "eval_steps_per_second": 36.228,
      "step": 1
    },
    {
      "epoch": 2.80982737123088e-05,
      "grad_norm": 5.828180313110352,
      "learning_rate": 4e-05,
      "loss": 10.0953,
      "step": 2
    },
    {
      "epoch": 4.21474105684632e-05,
      "grad_norm": 7.734110355377197,
      "learning_rate": 6e-05,
      "loss": 10.6375,
      "step": 3
    },
    {
      "epoch": 4.21474105684632e-05,
      "eval_loss": 12.15479564666748,
      "eval_runtime": 419.0796,
      "eval_samples_per_second": 71.514,
      "eval_steps_per_second": 35.757,
      "step": 3
    }
  ],
  "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": 10287795142656.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}