{
  "best_metric": 0.9406243361397153,
  "best_model_checkpoint": "model_saves/roberta-large_lemon-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": 0.9406243361397153,
      "eval_loss": 0.4359196722507477,
      "eval_runtime": 3.4132,
      "eval_samples_per_second": 1283.853,
      "eval_steps_per_second": 10.254,
      "step": 268
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9399031742304811,
      "eval_loss": 0.4492127299308777,
      "eval_runtime": 3.4096,
      "eval_samples_per_second": 1285.204,
      "eval_steps_per_second": 10.265,
      "step": 536
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9398584510113038,
      "eval_loss": 0.47432807087898254,
      "eval_runtime": 3.412,
      "eval_samples_per_second": 1284.309,
      "eval_steps_per_second": 10.258,
      "step": 804
    },
    {
      "epoch": 3.73,
      "learning_rate": 1e-05,
      "loss": 0.2873,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9395286172698711,
      "eval_loss": 0.5154682397842407,
      "eval_runtime": 3.414,
      "eval_samples_per_second": 1283.521,
      "eval_steps_per_second": 10.252,
      "step": 1072
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9388801305918,
      "eval_loss": 0.5666933655738831,
      "eval_runtime": 3.407,
      "eval_samples_per_second": 1286.159,
      "eval_steps_per_second": 10.273,
      "step": 1340
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9391149274924809,
      "eval_loss": 0.6480990648269653,
      "eval_runtime": 3.4094,
      "eval_samples_per_second": 1285.264,
      "eval_steps_per_second": 10.266,
      "step": 1608
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9381198358657856,
      "eval_loss": 0.6873353123664856,
      "eval_runtime": 3.4201,
      "eval_samples_per_second": 1281.243,
      "eval_steps_per_second": 10.234,
      "step": 1876
    },
    {
      "epoch": 7.0,
      "step": 1876,
      "total_flos": 2.4706569119727616e+16,
      "train_loss": 0.0609761097792115,
      "train_runtime": 253.2053,
      "train_samples_per_second": 2032.185,
      "train_steps_per_second": 15.876
    }
  ],
  "max_steps": 4020,
  "num_train_epochs": 15,
  "total_flos": 2.4706569119727616e+16,
  "trial_name": null,
  "trial_params": null
}