run-0/checkpoint-434/trainer_state.json

{
  "best_metric": 0.3752525252525252,
  "best_model_checkpoint": "tinybert-toxigen-bothpretrained\\run-0\\checkpoint-434",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 434,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 9.727904240831156e-07,
      "loss": 0.1834,
      "step": 217
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.37424242424242427,
      "eval_loss": 0.18295247852802277,
      "eval_runtime": 3.4165,
      "eval_samples_per_second": 579.533,
      "eval_steps_per_second": 18.147,
      "step": 217
    },
    {
      "epoch": 2.0,
      "learning_rate": 4.863952120415578e-07,
      "loss": 0.1833,
      "step": 434
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.3752525252525252,
      "eval_loss": 0.18277868628501892,
      "eval_runtime": 3.3644,
      "eval_samples_per_second": 588.515,
      "eval_steps_per_second": 18.428,
      "step": 434
    }
  ],
  "logging_steps": 500,
  "max_steps": 651,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1339410961920.0,
  "trial_name": null,
  "trial_params": {
    "alpha": 0.2540144352572642,
    "learning_rate": 1.4591856361246734e-06,
    "num_train_epochs": 3,
    "temperature": 2
  }
}