{
  "best_metric": 0.9409150370643679,
  "best_model_checkpoint": "model_saves/roberta-large_spell_10k_2_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": 0.9409150370643679,
      "eval_loss": 0.42563650012016296,
      "eval_runtime": 3.411,
      "eval_samples_per_second": 1284.661,
      "eval_steps_per_second": 10.261,
      "step": 268
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9408311810284105,
      "eval_loss": 0.4377546012401581,
      "eval_runtime": 3.4157,
      "eval_samples_per_second": 1282.899,
      "eval_steps_per_second": 10.247,
      "step": 536
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9401267903263677,
      "eval_loss": 0.4636364281177521,
      "eval_runtime": 3.4059,
      "eval_samples_per_second": 1286.575,
      "eval_steps_per_second": 10.276,
      "step": 804
    },
    {
      "epoch": 3.73,
      "learning_rate": 1e-05,
      "loss": 0.3125,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9389360346157717,
      "eval_loss": 0.49778589606285095,
      "eval_runtime": 3.4265,
      "eval_samples_per_second": 1278.858,
      "eval_steps_per_second": 10.215,
      "step": 1072
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9396851485369917,
      "eval_loss": 0.5484528541564941,
      "eval_runtime": 3.4032,
      "eval_samples_per_second": 1287.628,
      "eval_steps_per_second": 10.285,
      "step": 1340
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.938678876105502,
      "eval_loss": 0.5954769253730774,
      "eval_runtime": 3.4051,
      "eval_samples_per_second": 1286.887,
      "eval_steps_per_second": 10.279,
      "step": 1608
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9379018101722962,
      "eval_loss": 0.6462979316711426,
      "eval_runtime": 3.4098,
      "eval_samples_per_second": 1285.133,
      "eval_steps_per_second": 10.265,
      "step": 1876
    },
    {
      "epoch": 7.0,
      "step": 1876,
      "total_flos": 2.4688986932903936e+16,
      "train_loss": 0.06808348861076176,
      "train_runtime": 256.0914,
      "train_samples_per_second": 2009.283,
      "train_steps_per_second": 15.698
    }
  ],
  "max_steps": 4020,
  "num_train_epochs": 15,
  "total_flos": 2.4688986932903936e+16,
  "trial_name": null,
  "trial_params": null
}