{
  "best_metric": 0.9404286720558146,
  "best_model_checkpoint": "model_saves/roberta-large_spell_10k_3_p3/checkpoint-268",
  "epoch": 7.0,
  "global_step": 1876,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9404286720558146,
      "eval_loss": 0.43499499559402466,
      "eval_runtime": 3.4383,
      "eval_samples_per_second": 1274.481,
      "eval_steps_per_second": 10.18,
      "step": 268
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9394000380147363,
      "eval_loss": 0.44501230120658875,
      "eval_runtime": 3.4139,
      "eval_samples_per_second": 1283.577,
      "eval_steps_per_second": 10.252,
      "step": 536
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9388018649582397,
      "eval_loss": 0.4803008735179901,
      "eval_runtime": 3.4256,
      "eval_samples_per_second": 1279.203,
      "eval_steps_per_second": 10.217,
      "step": 804
    },
    {
      "epoch": 3.73,
      "learning_rate": 1e-05,
      "loss": 0.2844,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9386453336911191,
      "eval_loss": 0.5239610075950623,
      "eval_runtime": 3.4117,
      "eval_samples_per_second": 1284.408,
      "eval_steps_per_second": 10.259,
      "step": 1072
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9383658135712608,
      "eval_loss": 0.5639445185661316,
      "eval_runtime": 3.4115,
      "eval_samples_per_second": 1284.484,
      "eval_steps_per_second": 10.259,
      "step": 1340
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9387068281174878,
      "eval_loss": 0.6260917782783508,
      "eval_runtime": 3.4116,
      "eval_samples_per_second": 1284.434,
      "eval_steps_per_second": 10.259,
      "step": 1608
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.938813045763034,
      "eval_loss": 0.6880903840065002,
      "eval_runtime": 3.411,
      "eval_samples_per_second": 1284.683,
      "eval_steps_per_second": 10.261,
      "step": 1876
    },
    {
      "epoch": 7.0,
      "step": 1876,
      "total_flos": 2.4671163623931904e+16,
      "train_loss": 0.060420924920771425,
      "train_runtime": 252.2572,
      "train_samples_per_second": 2039.823,
      "train_steps_per_second": 15.936
    }
  ],
  "max_steps": 4020,
  "num_train_epochs": 15,
  "total_flos": 2.4671163623931904e+16,
  "trial_name": null,
  "trial_params": null
}