run-34/checkpoint-2874/trainer_state.json

{
  "best_metric": 0.8779707495429616,
  "best_model_checkpoint": "berttiny-hate_speech18-bothpretrained\\run-34\\checkpoint-2874",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 2874,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 4.7811152245905167e-05,
      "loss": 0.4795,
      "step": 958
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8670018281535649,
      "eval_loss": 0.47216829657554626,
      "eval_runtime": 10.7445,
      "eval_samples_per_second": 203.639,
      "eval_steps_per_second": 1.675,
      "step": 958
    },
    {
      "epoch": 2.0,
      "learning_rate": 2.3905576122952583e-05,
      "loss": 0.4553,
      "step": 1916
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8711151736745887,
      "eval_loss": 0.47212791442871094,
      "eval_runtime": 10.7069,
      "eval_samples_per_second": 204.353,
      "eval_steps_per_second": 1.681,
      "step": 1916
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0,
      "loss": 0.4449,
      "step": 2874
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8779707495429616,
      "eval_loss": 0.47231972217559814,
      "eval_runtime": 10.7308,
      "eval_samples_per_second": 203.899,
      "eval_steps_per_second": 1.677,
      "step": 2874
    }
  ],
  "logging_steps": 500,
  "max_steps": 2874,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2955417219168.0,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 7.171672836885776e-05,
    "num_train_epochs": 3,
    "per_device_train_batch_size": 8,
    "seed": 35
  }
}