run-11/checkpoint-552/trainer_state.json

{
  "best_metric": 0.926530612244898,
  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-11\\checkpoint-414",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 552,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8693877551020408,
      "eval_loss": 0.6436439752578735,
      "eval_runtime": 1.194,
      "eval_samples_per_second": 205.193,
      "eval_steps_per_second": 13.4,
      "step": 138
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8938775510204081,
      "eval_loss": 0.3989887535572052,
      "eval_runtime": 1.195,
      "eval_samples_per_second": 205.021,
      "eval_steps_per_second": 13.389,
      "step": 276
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.926530612244898,
      "eval_loss": 0.3359505534172058,
      "eval_runtime": 1.277,
      "eval_samples_per_second": 191.856,
      "eval_steps_per_second": 12.529,
      "step": 414
    },
    {
      "epoch": 3.62,
      "learning_rate": 2.743363501825591e-05,
      "loss": 0.6493,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9224489795918367,
      "eval_loss": 0.315531462430954,
      "eval_runtime": 1.346,
      "eval_samples_per_second": 182.021,
      "eval_steps_per_second": 11.887,
      "step": 552
    }
  ],
  "logging_steps": 500,
  "max_steps": 690,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 6141098220600.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 9.962741138208726e-05,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 16,
    "seed": 40
  }
}