{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006082725060827251,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012165450121654502,
      "grad_norm": 6.326965808868408,
      "learning_rate": 1e-05,
      "loss": 6.1355,
      "step": 1
    },
    {
      "epoch": 0.0012165450121654502,
      "eval_loss": 6.7928876876831055,
      "eval_runtime": 176.1708,
      "eval_samples_per_second": 7.862,
      "eval_steps_per_second": 3.934,
      "step": 1
    },
    {
      "epoch": 0.0024330900243309003,
      "grad_norm": 4.92700719833374,
      "learning_rate": 2e-05,
      "loss": 6.6496,
      "step": 2
    },
    {
      "epoch": 0.0024330900243309003,
      "eval_loss": 6.703327178955078,
      "eval_runtime": 108.7558,
      "eval_samples_per_second": 12.735,
      "eval_steps_per_second": 6.372,
      "step": 2
    },
    {
      "epoch": 0.0036496350364963502,
      "grad_norm": 5.465456008911133,
      "learning_rate": 3e-05,
      "loss": 6.5394,
      "step": 3
    },
    {
      "epoch": 0.004866180048661801,
      "grad_norm": 5.515636444091797,
      "learning_rate": 4e-05,
      "loss": 6.0983,
      "step": 4
    },
    {
      "epoch": 0.004866180048661801,
      "eval_loss": 6.56418514251709,
      "eval_runtime": 90.214,
      "eval_samples_per_second": 15.352,
      "eval_steps_per_second": 7.682,
      "step": 4
    },
    {
      "epoch": 0.006082725060827251,
      "grad_norm": 5.421800136566162,
      "learning_rate": 5e-05,
      "loss": 6.1747,
      "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": 7398385841602560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}