{
  "best_metric": 0.9394112188195306,
  "best_model_checkpoint": "model_saves/roberta-large_lemon_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": 0.9393497243931618,
      "eval_loss": 0.4459913671016693,
      "eval_runtime": 3.4398,
      "eval_samples_per_second": 1273.909,
      "eval_steps_per_second": 10.175,
      "step": 268
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9394112188195306,
      "eval_loss": 0.46163710951805115,
      "eval_runtime": 3.4301,
      "eval_samples_per_second": 1277.515,
      "eval_steps_per_second": 10.204,
      "step": 536
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.938237234316126,
      "eval_loss": 0.5016078352928162,
      "eval_runtime": 3.4314,
      "eval_samples_per_second": 1277.037,
      "eval_steps_per_second": 10.2,
      "step": 804
    },
    {
      "epoch": 3.73,
      "learning_rate": 1e-05,
      "loss": 0.2628,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9388969017989915,
      "eval_loss": 0.5514333248138428,
      "eval_runtime": 4.6434,
      "eval_samples_per_second": 943.704,
      "eval_steps_per_second": 7.538,
      "step": 1072
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9377396885027784,
      "eval_loss": 0.6031810641288757,
      "eval_runtime": 3.437,
      "eval_samples_per_second": 1274.931,
      "eval_steps_per_second": 10.183,
      "step": 1340
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9375440244188776,
      "eval_loss": 0.6418653130531311,
      "eval_runtime": 3.5192,
      "eval_samples_per_second": 1245.154,
      "eval_steps_per_second": 9.945,
      "step": 1608
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9377396885027784,
      "eval_loss": 0.7208025455474854,
      "eval_runtime": 3.4571,
      "eval_samples_per_second": 1267.546,
      "eval_steps_per_second": 10.124,
      "step": 1876
    },
    {
      "epoch": 7.46,
      "learning_rate": 1e-05,
      "loss": 0.1093,
      "step": 2000
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9376390612596295,
      "eval_loss": 0.7791202068328857,
      "eval_runtime": 3.4736,
      "eval_samples_per_second": 1261.504,
      "eval_steps_per_second": 10.076,
      "step": 2144
    },
    {
      "epoch": 8.0,
      "step": 2144,
      "total_flos": 2.8204045344702464e+16,
      "train_loss": 0.039562054534456624,
      "train_runtime": 261.1202,
      "train_samples_per_second": 1970.587,
      "train_steps_per_second": 15.395
    }
  ],
  "max_steps": 4020,
  "num_train_epochs": 15,
  "total_flos": 2.8204045344702464e+16,
  "trial_name": null,
  "trial_params": null
}