{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0026132048507615043,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006533012126903761,
      "grad_norm": 46.18653106689453,
      "learning_rate": 1e-05,
      "loss": 23.4572,
      "step": 1
    },
    {
      "epoch": 0.0006533012126903761,
      "eval_loss": 1.4371066093444824,
      "eval_runtime": 756.4341,
      "eval_samples_per_second": 3.408,
      "eval_steps_per_second": 1.704,
      "step": 1
    },
    {
      "epoch": 0.0013066024253807521,
      "grad_norm": 37.428977966308594,
      "learning_rate": 2e-05,
      "loss": 21.5933,
      "step": 2
    },
    {
      "epoch": 0.0013066024253807521,
      "eval_loss": 1.426247239112854,
      "eval_runtime": 692.9372,
      "eval_samples_per_second": 3.72,
      "eval_steps_per_second": 1.86,
      "step": 2
    },
    {
      "epoch": 0.0019599036380711283,
      "grad_norm": 60.742000579833984,
      "learning_rate": 3e-05,
      "loss": 24.3975,
      "step": 3
    },
    {
      "epoch": 0.0026132048507615043,
      "grad_norm": 48.638282775878906,
      "learning_rate": 4e-05,
      "loss": 22.398,
      "step": 4
    },
    {
      "epoch": 0.0026132048507615043,
      "eval_loss": 1.3924652338027954,
      "eval_runtime": 340.8043,
      "eval_samples_per_second": 7.564,
      "eval_steps_per_second": 3.782,
      "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": 4250229113094144.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}