{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006163803066492025,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012327606132984052,
      "grad_norm": 1.080862283706665,
      "learning_rate": 1e-05,
      "loss": 2.0853,
      "step": 1
    },
    {
      "epoch": 0.0012327606132984052,
      "eval_loss": 3.7710342407226562,
      "eval_runtime": 141.3112,
      "eval_samples_per_second": 9.674,
      "eval_steps_per_second": 4.84,
      "step": 1
    },
    {
      "epoch": 0.0024655212265968104,
      "grad_norm": 1.4210823774337769,
      "learning_rate": 2e-05,
      "loss": 2.5696,
      "step": 2
    },
    {
      "epoch": 0.0024655212265968104,
      "eval_loss": 3.7517523765563965,
      "eval_runtime": 42.0384,
      "eval_samples_per_second": 32.518,
      "eval_steps_per_second": 16.271,
      "step": 2
    },
    {
      "epoch": 0.0036982818398952153,
      "grad_norm": 0.9023861885070801,
      "learning_rate": 3e-05,
      "loss": 2.0497,
      "step": 3
    },
    {
      "epoch": 0.004931042453193621,
      "grad_norm": 2.3013174533843994,
      "learning_rate": 4e-05,
      "loss": 2.691,
      "step": 4
    },
    {
      "epoch": 0.004931042453193621,
      "eval_loss": 3.6455137729644775,
      "eval_runtime": 37.968,
      "eval_samples_per_second": 36.004,
      "eval_steps_per_second": 18.015,
      "step": 4
    },
    {
      "epoch": 0.006163803066492025,
      "grad_norm": 1.1438347101211548,
      "learning_rate": 5e-05,
      "loss": 2.1211,
      "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": 2000389322833920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}