{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07398843930635839,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018497109826589597,
      "grad_norm": 7.31365442276001,
      "learning_rate": 1e-05,
      "loss": 8.4539,
      "step": 1
    },
    {
      "epoch": 0.018497109826589597,
      "eval_loss": 8.333340644836426,
      "eval_runtime": 74.1964,
      "eval_samples_per_second": 1.24,
      "eval_steps_per_second": 0.62,
      "step": 1
    },
    {
      "epoch": 0.03699421965317919,
      "grad_norm": 8.863042831420898,
      "learning_rate": 2e-05,
      "loss": 8.7065,
      "step": 2
    },
    {
      "epoch": 0.03699421965317919,
      "eval_loss": 8.021866798400879,
      "eval_runtime": 2.096,
      "eval_samples_per_second": 43.893,
      "eval_steps_per_second": 21.946,
      "step": 2
    },
    {
      "epoch": 0.055491329479768786,
      "grad_norm": 8.059940338134766,
      "learning_rate": 3e-05,
      "loss": 7.9229,
      "step": 3
    },
    {
      "epoch": 0.07398843930635839,
      "grad_norm": 6.737138748168945,
      "learning_rate": 4e-05,
      "loss": 7.8336,
      "step": 4
    },
    {
      "epoch": 0.07398843930635839,
      "eval_loss": 7.648785591125488,
      "eval_runtime": 2.1349,
      "eval_samples_per_second": 43.094,
      "eval_steps_per_second": 21.547,
      "step": 4
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1558092463472640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}