{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01644398766700925,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00328879753340185,
      "grad_norm": 2.4023971557617188,
      "learning_rate": 1e-05,
      "loss": 2.3082,
      "step": 1
    },
    {
      "epoch": 0.00328879753340185,
      "eval_loss": 2.2111148834228516,
      "eval_runtime": 146.7757,
      "eval_samples_per_second": 3.495,
      "eval_steps_per_second": 1.751,
      "step": 1
    },
    {
      "epoch": 0.0065775950668037,
      "grad_norm": 2.4387238025665283,
      "learning_rate": 2e-05,
      "loss": 2.1125,
      "step": 2
    },
    {
      "epoch": 0.0065775950668037,
      "eval_loss": 2.1599221229553223,
      "eval_runtime": 14.7763,
      "eval_samples_per_second": 34.718,
      "eval_steps_per_second": 17.393,
      "step": 2
    },
    {
      "epoch": 0.00986639260020555,
      "grad_norm": 2.3505756855010986,
      "learning_rate": 3e-05,
      "loss": 2.0936,
      "step": 3
    },
    {
      "epoch": 0.0131551901336074,
      "grad_norm": 2.850027561187744,
      "learning_rate": 4e-05,
      "loss": 1.9464,
      "step": 4
    },
    {
      "epoch": 0.0131551901336074,
      "eval_loss": 2.004474401473999,
      "eval_runtime": 17.0079,
      "eval_samples_per_second": 30.163,
      "eval_steps_per_second": 15.111,
      "step": 4
    },
    {
      "epoch": 0.01644398766700925,
      "grad_norm": 2.3386075496673584,
      "learning_rate": 5e-05,
      "loss": 2.0456,
      "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": 4395510257418240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}