{
  "best_metric": 0.8082191780821918,
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-3/checkpoint-2338",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 2338,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.43,
      "grad_norm": 67.371826171875,
      "learning_rate": 2.9568390590325436e-05,
      "loss": 0.7154,
      "step": 500
    },
    {
      "epoch": 0.86,
      "grad_norm": 29.5689697265625,
      "learning_rate": 2.1524758764883263e-05,
      "loss": 0.5977,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7756849315068494,
      "eval_loss": 0.5732079148292542,
      "eval_runtime": 3.3767,
      "eval_samples_per_second": 172.951,
      "eval_steps_per_second": 10.958,
      "step": 1169
    },
    {
      "epoch": 1.28,
      "grad_norm": 6.523064613342285,
      "learning_rate": 1.3481126939441087e-05,
      "loss": 0.4226,
      "step": 1500
    },
    {
      "epoch": 1.71,
      "grad_norm": 27.283645629882812,
      "learning_rate": 5.437495113998911e-06,
      "loss": 0.3952,
      "step": 2000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8082191780821918,
      "eval_loss": 0.6110640168190002,
      "eval_runtime": 3.3736,
      "eval_samples_per_second": 173.11,
      "eval_steps_per_second": 10.968,
      "step": 2338
    }
  ],
  "logging_steps": 500,
  "max_steps": 2338,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 633133530754164.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 3.761202241576761e-05,
    "num_train_epochs": 2,
    "per_device_train_batch_size": 4,
    "seed": 34
  }
}