{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002077328555477656,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00041546571109553115,
      "grad_norm": 1.653911828994751,
      "learning_rate": 1e-05,
      "loss": 1.5878,
      "step": 1
    },
    {
      "epoch": 0.00041546571109553115,
      "eval_loss": 1.569108486175537,
      "eval_runtime": 206.2206,
      "eval_samples_per_second": 19.659,
      "eval_steps_per_second": 9.829,
      "step": 1
    },
    {
      "epoch": 0.0008309314221910623,
      "grad_norm": 2.7106523513793945,
      "learning_rate": 2e-05,
      "loss": 1.5468,
      "step": 2
    },
    {
      "epoch": 0.0008309314221910623,
      "eval_loss": 1.558651328086853,
      "eval_runtime": 145.4617,
      "eval_samples_per_second": 27.87,
      "eval_steps_per_second": 13.935,
      "step": 2
    },
    {
      "epoch": 0.0012463971332865934,
      "grad_norm": 1.1992127895355225,
      "learning_rate": 3e-05,
      "loss": 1.4672,
      "step": 3
    },
    {
      "epoch": 0.0016618628443821246,
      "grad_norm": 1.383958101272583,
      "learning_rate": 4e-05,
      "loss": 1.6033,
      "step": 4
    },
    {
      "epoch": 0.0016618628443821246,
      "eval_loss": 1.5340737104415894,
      "eval_runtime": 147.6418,
      "eval_samples_per_second": 27.458,
      "eval_steps_per_second": 13.729,
      "step": 4
    },
    {
      "epoch": 0.002077328555477656,
      "grad_norm": 1.5105040073394775,
      "learning_rate": 5e-05,
      "loss": 1.3671,
      "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": 562742352150528.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}