{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03276003276003276,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003276003276003276,
      "grad_norm": 3.9740049839019775,
      "learning_rate": 2e-05,
      "loss": 2.1377,
      "step": 1
    },
    {
      "epoch": 0.003276003276003276,
      "eval_loss": 1.9867568016052246,
      "eval_runtime": 5.342,
      "eval_samples_per_second": 24.148,
      "eval_steps_per_second": 12.168,
      "step": 1
    },
    {
      "epoch": 0.006552006552006552,
      "grad_norm": 3.5100481510162354,
      "learning_rate": 4e-05,
      "loss": 1.9086,
      "step": 2
    },
    {
      "epoch": 0.009828009828009828,
      "grad_norm": 3.365212917327881,
      "learning_rate": 6e-05,
      "loss": 2.0272,
      "step": 3
    },
    {
      "epoch": 0.009828009828009828,
      "eval_loss": 1.9318634271621704,
      "eval_runtime": 3.967,
      "eval_samples_per_second": 32.518,
      "eval_steps_per_second": 16.385,
      "step": 3
    },
    {
      "epoch": 0.013104013104013105,
      "grad_norm": 3.4388458728790283,
      "learning_rate": 8e-05,
      "loss": 1.9754,
      "step": 4
    },
    {
      "epoch": 0.01638001638001638,
      "grad_norm": 3.839658737182617,
      "learning_rate": 0.0001,
      "loss": 1.7734,
      "step": 5
    },
    {
      "epoch": 0.019656019656019656,
      "grad_norm": 3.5367302894592285,
      "learning_rate": 0.00012,
      "loss": 1.4113,
      "step": 6
    },
    {
      "epoch": 0.019656019656019656,
      "eval_loss": 0.946590006351471,
      "eval_runtime": 4.041,
      "eval_samples_per_second": 31.922,
      "eval_steps_per_second": 16.085,
      "step": 6
    },
    {
      "epoch": 0.02293202293202293,
      "grad_norm": 3.532106876373291,
      "learning_rate": 0.00014,
      "loss": 0.9183,
      "step": 7
    },
    {
      "epoch": 0.02620802620802621,
      "grad_norm": 2.7059402465820312,
      "learning_rate": 0.00016,
      "loss": 0.5712,
      "step": 8
    },
    {
      "epoch": 0.029484029484029485,
      "grad_norm": 2.746583938598633,
      "learning_rate": 0.00018,
      "loss": 0.3506,
      "step": 9
    },
    {
      "epoch": 0.029484029484029485,
      "eval_loss": 0.1640888750553131,
      "eval_runtime": 4.0068,
      "eval_samples_per_second": 32.195,
      "eval_steps_per_second": 16.222,
      "step": 9
    },
    {
      "epoch": 0.03276003276003276,
      "grad_norm": 2.743062734603882,
      "learning_rate": 0.0002,
      "loss": 0.1903,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1849564248145920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}