{
  "best_metric": 0.7326732673267327,
  "best_model_checkpoint": "distilhubert-finetuned-not-a-word2/run-0/checkpoint-24",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 24,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21,
      "grad_norm": 1.6479910612106323,
      "learning_rate": 3.3535706116592527e-06,
      "loss": 0.699,
      "step": 5
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.6159653663635254,
      "learning_rate": 6.707141223318505e-06,
      "loss": 0.6932,
      "step": 10
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.5607424974441528,
      "learning_rate": 1.0060711834977758e-05,
      "loss": 0.6812,
      "step": 15
    },
    {
      "epoch": 0.83,
      "grad_norm": 1.401130199432373,
      "learning_rate": 1.341428244663701e-05,
      "loss": 0.6633,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.7326732673267327,
      "eval_loss": 0.680633544921875,
      "eval_runtime": 1.3853,
      "eval_samples_per_second": 46.201,
      "eval_steps_per_second": 5.775,
      "step": 24
    }
  ],
  "logging_steps": 5,
  "max_steps": 240,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 670768569859200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.6097138935964413e-05,
    "per_device_train_batch_size": 8
  }
}