run-0/checkpoint-1/trainer_state.json

{
  "best_metric": 0.787109375,
  "best_model_checkpoint": "test_trainer\\run-0\\checkpoint-1",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.0,
      "eval_f1": 0.0,
      "eval_loss": 0.787109375,
      "eval_runtime": 0.1522,
      "eval_samples_per_second": 6.568,
      "eval_steps_per_second": 6.568,
      "step": 1
    }
  ],
  "logging_steps": 500,
  "max_steps": 2,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": {
    "gradient_accumulation_steps": 1,
    "learning_rate": 6.404847217172767e-06,
    "num_train_epochs": 2,
    "optimizer": "AdaFactor",
    "seed": 47,
    "warmup_ratio": 0.06373313794247544,
    "warmup_steps": 315,
    "weight_decay": 0.3456353554922866
  }
}