{
  "best_metric": 0.9391987835284383,
  "best_model_checkpoint": "model_saves/roberta-large_lemon-spell_10k_3_p3/checkpoint-536",
  "epoch": 8.0,
  "global_step": 2144,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9390254810541263,
      "eval_loss": 0.44537773728370667,
      "eval_runtime": 3.4219,
      "eval_samples_per_second": 1280.586,
      "eval_steps_per_second": 10.228,
      "step": 268
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9391987835284383,
      "eval_loss": 0.4579298198223114,
      "eval_runtime": 3.4255,
      "eval_samples_per_second": 1279.228,
      "eval_steps_per_second": 10.217,
      "step": 536
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9387291897270765,
      "eval_loss": 0.5054779052734375,
      "eval_runtime": 3.4395,
      "eval_samples_per_second": 1274.039,
      "eval_steps_per_second": 10.176,
      "step": 804
    },
    {
      "epoch": 3.73,
      "learning_rate": 1e-05,
      "loss": 0.2672,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9386006104719418,
      "eval_loss": 0.5471222400665283,
      "eval_runtime": 3.4404,
      "eval_samples_per_second": 1273.684,
      "eval_steps_per_second": 10.173,
      "step": 1072
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9378123637339416,
      "eval_loss": 0.5999845266342163,
      "eval_runtime": 3.4383,
      "eval_samples_per_second": 1274.48,
      "eval_steps_per_second": 10.18,
      "step": 1340
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9375048916020975,
      "eval_loss": 0.6507896184921265,
      "eval_runtime": 3.4302,
      "eval_samples_per_second": 1277.466,
      "eval_steps_per_second": 10.203,
      "step": 1608
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9374210355661401,
      "eval_loss": 0.7333407998085022,
      "eval_runtime": 3.4249,
      "eval_samples_per_second": 1279.458,
      "eval_steps_per_second": 10.219,
      "step": 1876
    },
    {
      "epoch": 7.46,
      "learning_rate": 1e-05,
      "loss": 0.1123,
      "step": 2000
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9374825299925088,
      "eval_loss": 0.7822133302688599,
      "eval_runtime": 3.4201,
      "eval_samples_per_second": 1281.26,
      "eval_steps_per_second": 10.234,
      "step": 2144
    },
    {
      "epoch": 8.0,
      "step": 2144,
      "total_flos": 2.8204045344702464e+16,
      "train_loss": 0.040641184173413177,
      "train_runtime": 251.7898,
      "train_samples_per_second": 2043.61,
      "train_steps_per_second": 15.966
    }
  ],
  "max_steps": 4020,
  "num_train_epochs": 15,
  "total_flos": 2.8204045344702464e+16,
  "trial_name": null,
  "trial_params": null
}