{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.5460181263189355,
      "las": 87.1808,
      "step": 222,
      "uas": 89.7152
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.42474964938807386,
      "las": 89.36319999999999,
      "step": 444,
      "uas": 91.664
    },
    {
      "epoch": 2.2522522522522523,
      "grad_norm": 2.3735365867614746,
      "learning_rate": 0.00010990990990990993,
      "loss": 0.6722,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.41265829258105335,
      "las": 90.4192,
      "step": 666,
      "uas": 92.3328
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.43467319249605935,
      "las": 91.2544,
      "step": 888,
      "uas": 93.14240000000001
    },
    {
      "epoch": 4.504504504504505,
      "grad_norm": 1.5686553716659546,
      "learning_rate": 1.981981981981982e-05,
      "loss": 0.1683,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.4915140597384517,
      "las": 91.5616,
      "step": 1110,
      "uas": 93.2608
    },
    {
      "epoch": 5.0,
      "step": 1110,
      "total_flos": 1.216861487350272e+16,
      "train_loss": 0.38584868027283264,
      "train_runtime": 897.5203,
      "train_samples_per_second": 78.962,
      "train_steps_per_second": 1.237
    }
  ],
  "logging_steps": 500,
  "max_steps": 1110,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.216861487350272e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}