{
  "best_metric": 0.5371652447937805,
  "best_model_checkpoint": "../output/roberta-base-sst/checkpoint-900",
  "epoch": 3.370786516853933,
  "global_step": 900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.37,
      "eval_accuracy": 0.44868301544050865,
      "eval_f1": 0.40183269902596275,
      "eval_loss": 1.2189757823944092,
      "eval_precision": 0.45215636701421513,
      "eval_recall": 0.4461052071145046,
      "eval_runtime": 5.4464,
      "eval_samples_per_second": 202.152,
      "step": 100
    },
    {
      "epoch": 0.75,
      "eval_accuracy": 0.4713896457765668,
      "eval_f1": 0.45576264052480686,
      "eval_loss": 1.1674168109893799,
      "eval_precision": 0.47342618027935013,
      "eval_recall": 0.4617929878424363,
      "eval_runtime": 5.5186,
      "eval_samples_per_second": 199.508,
      "step": 200
    },
    {
      "epoch": 1.12,
      "eval_accuracy": 0.48047229791099,
      "eval_f1": 0.4608418062575635,
      "eval_loss": 1.208803415298462,
      "eval_precision": 0.47412277926758095,
      "eval_recall": 0.49066121993560535,
      "eval_runtime": 5.5423,
      "eval_samples_per_second": 198.655,
      "step": 300
    },
    {
      "epoch": 1.5,
      "eval_accuracy": 0.49954586739327883,
      "eval_f1": 0.45326478521487196,
      "eval_loss": 1.203087329864502,
      "eval_precision": 0.5081235548351334,
      "eval_recall": 0.48943672347517797,
      "eval_runtime": 5.5675,
      "eval_samples_per_second": 197.754,
      "step": 400
    },
    {
      "epoch": 1.87,
      "learning_rate": 1.250936329588015e-05,
      "loss": 1.1064,
      "step": 500
    },
    {
      "epoch": 1.87,
      "eval_accuracy": 0.5313351498637602,
      "eval_f1": 0.4925849403824431,
      "eval_loss": 1.1195186376571655,
      "eval_precision": 0.5255318894371125,
      "eval_recall": 0.5062241091371705,
      "eval_runtime": 5.5664,
      "eval_samples_per_second": 197.795,
      "step": 500
    },
    {
      "epoch": 2.25,
      "eval_accuracy": 0.5277020890099909,
      "eval_f1": 0.5219048999186475,
      "eval_loss": 1.1405118703842163,
      "eval_precision": 0.5220602599838614,
      "eval_recall": 0.5368465194722578,
      "eval_runtime": 5.5771,
      "eval_samples_per_second": 197.414,
      "step": 600
    },
    {
      "epoch": 2.62,
      "eval_accuracy": 0.5267938237965486,
      "eval_f1": 0.513698109548222,
      "eval_loss": 1.1393935680389404,
      "eval_precision": 0.519160589267,
      "eval_recall": 0.5237418576297002,
      "eval_runtime": 5.5559,
      "eval_samples_per_second": 198.168,
      "step": 700
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5413260672116258,
      "eval_f1": 0.5350818496505353,
      "eval_loss": 1.1169188022613525,
      "eval_precision": 0.545000483462316,
      "eval_recall": 0.5401851524056742,
      "eval_runtime": 5.5649,
      "eval_samples_per_second": 197.849,
      "step": 800
    },
    {
      "epoch": 3.37,
      "eval_accuracy": 0.5504087193460491,
      "eval_f1": 0.5371652447937805,
      "eval_loss": 1.1948559284210205,
      "eval_precision": 0.5461602569131191,
      "eval_recall": 0.5513573384419186,
      "eval_runtime": 5.7609,
      "eval_samples_per_second": 191.116,
      "step": 900
    }
  ],
  "max_steps": 1335,
  "num_train_epochs": 5,
  "total_flos": 2757046992076800,
  "trial_name": null,
  "trial_params": null
}