{
  "best_metric": 0.9393105915763816,
  "best_model_checkpoint": "model_saves/xlnet-large_lemon_10k_3_p3/checkpoint-536",
  "epoch": 5.0,
  "global_step": 1340,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9384943928263957,
      "eval_loss": 0.46198156476020813,
      "eval_runtime": 4.8579,
      "eval_samples_per_second": 902.043,
      "eval_steps_per_second": 7.205,
      "step": 268
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9393105915763816,
      "eval_loss": 0.48935213685035706,
      "eval_runtime": 4.844,
      "eval_samples_per_second": 904.624,
      "eval_steps_per_second": 7.225,
      "step": 536
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9390590234685092,
      "eval_loss": 0.5319147706031799,
      "eval_runtime": 4.8445,
      "eval_samples_per_second": 904.537,
      "eval_steps_per_second": 7.225,
      "step": 804
    },
    {
      "epoch": 3.73,
      "learning_rate": 1e-05,
      "loss": 0.2703,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9389024922013887,
      "eval_loss": 0.5782092213630676,
      "eval_runtime": 4.8528,
      "eval_samples_per_second": 902.992,
      "eval_steps_per_second": 7.212,
      "step": 1072
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9386844665078993,
      "eval_loss": 0.6263871192932129,
      "eval_runtime": 4.8681,
      "eval_samples_per_second": 900.146,
      "eval_steps_per_second": 7.19,
      "step": 1340
    },
    {
      "epoch": 5.0,
      "step": 1340,
      "total_flos": 2.160766720199885e+16,
      "train_loss": 0.24448578962639197,
      "train_runtime": 567.5305,
      "train_samples_per_second": 906.665,
      "train_steps_per_second": 7.083
    }
  ],
  "max_steps": 4020,
  "num_train_epochs": 15,
  "total_flos": 2.160766720199885e+16,
  "trial_name": null,
  "trial_params": null
}