run-19/checkpoint-1650/trainer_state.json

{
  "best_metric": 0.9142857142857143,
  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-19\\checkpoint-1650",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1650,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.91,
      "learning_rate": 4.3587497718473865e-05,
      "loss": 1.2013,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8816326530612245,
      "eval_loss": 0.4765537679195404,
      "eval_runtime": 1.211,
      "eval_samples_per_second": 202.313,
      "eval_steps_per_second": 13.212,
      "step": 550
    },
    {
      "epoch": 1.82,
      "learning_rate": 3.0767645448334495e-05,
      "loss": 0.4355,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8979591836734694,
      "eval_loss": 0.3723006844520569,
      "eval_runtime": 1.249,
      "eval_samples_per_second": 196.157,
      "eval_steps_per_second": 12.81,
      "step": 1100
    },
    {
      "epoch": 2.73,
      "learning_rate": 1.794779317819512e-05,
      "loss": 0.3042,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9142857142857143,
      "eval_loss": 0.34826746582984924,
      "eval_runtime": 1.219,
      "eval_samples_per_second": 200.984,
      "eval_steps_per_second": 13.126,
      "step": 1650
    }
  ],
  "logging_steps": 500,
  "max_steps": 2200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 2922430465500.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 5.640734998861324e-05,
    "num_train_epochs": 4,
    "per_device_train_batch_size": 4,
    "seed": 36
  }
}