{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010917030567685589,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002183406113537118,
      "grad_norm": 13.170251846313477,
      "learning_rate": 1e-05,
      "loss": 4.9792,
      "step": 1
    },
    {
      "epoch": 0.002183406113537118,
      "eval_loss": 4.99370813369751,
      "eval_runtime": 88.5649,
      "eval_samples_per_second": 8.717,
      "eval_steps_per_second": 4.358,
      "step": 1
    },
    {
      "epoch": 0.004366812227074236,
      "grad_norm": 13.93147087097168,
      "learning_rate": 2e-05,
      "loss": 5.057,
      "step": 2
    },
    {
      "epoch": 0.004366812227074236,
      "eval_loss": 4.5278849601745605,
      "eval_runtime": 29.0078,
      "eval_samples_per_second": 26.614,
      "eval_steps_per_second": 13.307,
      "step": 2
    },
    {
      "epoch": 0.006550218340611353,
      "grad_norm": 12.372949600219727,
      "learning_rate": 3e-05,
      "loss": 4.6319,
      "step": 3
    },
    {
      "epoch": 0.008733624454148471,
      "grad_norm": 11.142926216125488,
      "learning_rate": 4e-05,
      "loss": 4.2611,
      "step": 4
    },
    {
      "epoch": 0.008733624454148471,
      "eval_loss": 3.969254732131958,
      "eval_runtime": 29.599,
      "eval_samples_per_second": 26.082,
      "eval_steps_per_second": 13.041,
      "step": 4
    },
    {
      "epoch": 0.010917030567685589,
      "grad_norm": 9.851216316223145,
      "learning_rate": 5e-05,
      "loss": 3.9583,
      "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": 1371213272186880.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}