{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.9891959276958238,
  "eval_steps": 500,
  "global_step": 2400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.83108248493663,
      "grad_norm": 0.14865632355213165,
      "learning_rate": 3.9704658901830285e-05,
      "loss": 0.2378,
      "step": 500
    },
    {
      "epoch": 1.66216496987326,
      "grad_norm": 0.1823558658361435,
      "learning_rate": 2.930532445923461e-05,
      "loss": 0.0861,
      "step": 1000
    },
    {
      "epoch": 2.49324745480989,
      "grad_norm": 0.21770212054252625,
      "learning_rate": 1.8905990016638937e-05,
      "loss": 0.0776,
      "step": 1500
    },
    {
      "epoch": 3.32432993974652,
      "grad_norm": 0.14866091310977936,
      "learning_rate": 8.50665557404326e-06,
      "loss": 0.0738,
      "step": 2000
    }
  ],
  "logging_steps": 500,
  "max_steps": 2404,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.00336140288e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}