{
  "best_metric": 0.7338050007820129,
  "best_model_checkpoint": "distilbert_final_tweet_dataset/checkpoint-230",
  "epoch": 9.0,
  "global_step": 1035,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6697530864197531,
      "eval_f1": 0.6499850953895071,
      "eval_loss": 0.7421407103538513,
      "eval_runtime": 0.6143,
      "eval_samples_per_second": 527.407,
      "eval_steps_per_second": 34.184,
      "step": 115
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6790123456790124,
      "eval_f1": 0.6838827857278376,
      "eval_loss": 0.7338050007820129,
      "eval_runtime": 0.6427,
      "eval_samples_per_second": 504.157,
      "eval_steps_per_second": 32.677,
      "step": 230
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6882716049382716,
      "eval_f1": 0.6857209215904868,
      "eval_loss": 0.7727181315422058,
      "eval_runtime": 0.6497,
      "eval_samples_per_second": 498.708,
      "eval_steps_per_second": 32.324,
      "step": 345
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6790123456790124,
      "eval_f1": 0.6817694597817456,
      "eval_loss": 0.9093312621116638,
      "eval_runtime": 0.6428,
      "eval_samples_per_second": 504.017,
      "eval_steps_per_second": 32.668,
      "step": 460
    },
    {
      "epoch": 4.35,
      "learning_rate": 1.565217391304348e-05,
      "loss": 0.5516,
      "step": 500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6419753086419753,
      "eval_f1": 0.6363565693286525,
      "eval_loss": 1.324772834777832,
      "eval_runtime": 0.6556,
      "eval_samples_per_second": 494.18,
      "eval_steps_per_second": 32.03,
      "step": 575
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6666666666666666,
      "eval_f1": 0.6676168306175064,
      "eval_loss": 1.3643816709518433,
      "eval_runtime": 0.7097,
      "eval_samples_per_second": 456.529,
      "eval_steps_per_second": 29.59,
      "step": 690
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6820987654320988,
      "eval_f1": 0.6823242911293225,
      "eval_loss": 1.4371545314788818,
      "eval_runtime": 0.6959,
      "eval_samples_per_second": 465.597,
      "eval_steps_per_second": 30.178,
      "step": 805
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6759259259259259,
      "eval_f1": 0.676371996194909,
      "eval_loss": 1.6721471548080444,
      "eval_runtime": 0.6651,
      "eval_samples_per_second": 487.168,
      "eval_steps_per_second": 31.576,
      "step": 920
    },
    {
      "epoch": 8.7,
      "learning_rate": 1.1304347826086957e-05,
      "loss": 0.0927,
      "step": 1000
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.6975308641975309,
      "eval_f1": 0.6972341482806598,
      "eval_loss": 1.571859359741211,
      "eval_runtime": 0.6896,
      "eval_samples_per_second": 469.806,
      "eval_steps_per_second": 30.45,
      "step": 1035
    }
  ],
  "max_steps": 2300,
  "num_train_epochs": 20,
  "total_flos": 334014740521956.0,
  "trial_name": null,
  "trial_params": null
}