{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0010864988931292526,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00021729977862585052,
      "grad_norm": 1.0945476293563843,
      "learning_rate": 1e-05,
      "loss": 10.396,
      "step": 1
    },
    {
      "epoch": 0.00021729977862585052,
      "eval_loss": 10.412221908569336,
      "eval_runtime": 21.094,
      "eval_samples_per_second": 367.451,
      "eval_steps_per_second": 183.749,
      "step": 1
    },
    {
      "epoch": 0.00043459955725170103,
      "grad_norm": 0.9328057765960693,
      "learning_rate": 2e-05,
      "loss": 10.4047,
      "step": 2
    },
    {
      "epoch": 0.00043459955725170103,
      "eval_loss": 10.412049293518066,
      "eval_runtime": 9.1507,
      "eval_samples_per_second": 847.038,
      "eval_steps_per_second": 423.574,
      "step": 2
    },
    {
      "epoch": 0.0006518993358775515,
      "grad_norm": 1.0089765787124634,
      "learning_rate": 3e-05,
      "loss": 10.4085,
      "step": 3
    },
    {
      "epoch": 0.0008691991145034021,
      "grad_norm": 0.993450403213501,
      "learning_rate": 4e-05,
      "loss": 10.4218,
      "step": 4
    },
    {
      "epoch": 0.0008691991145034021,
      "eval_loss": 10.41109848022461,
      "eval_runtime": 9.166,
      "eval_samples_per_second": 845.622,
      "eval_steps_per_second": 422.865,
      "step": 4
    },
    {
      "epoch": 0.0010864988931292526,
      "grad_norm": 1.0228772163391113,
      "learning_rate": 5e-05,
      "loss": 10.4167,
      "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": 258618163200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}