{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.815122757398668e-05,
  "eval_steps": 2,
  "global_step": 2,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.407561378699334e-05,
      "grad_norm": 2.638183116912842,
      "learning_rate": 1e-05,
      "loss": 44.3756,
      "step": 1
    },
    {
      "epoch": 3.407561378699334e-05,
      "eval_loss": 11.093536376953125,
      "eval_runtime": 113.9897,
      "eval_samples_per_second": 108.405,
      "eval_steps_per_second": 54.207,
      "step": 1
    },
    {
      "epoch": 6.815122757398668e-05,
      "grad_norm": 2.178905963897705,
      "learning_rate": 2e-05,
      "loss": 44.2993,
      "step": 2
    },
    {
      "epoch": 6.815122757398668e-05,
      "eval_loss": 11.093539237976074,
      "eval_runtime": 114.5009,
      "eval_samples_per_second": 107.921,
      "eval_steps_per_second": 53.965,
      "step": 2
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6083051520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}