run-2/checkpoint-563/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 563,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8880994671403197,
      "grad_norm": 6.189607620239258,
      "learning_rate": 1.9291695717112818e-05,
      "loss": 0.8502,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8006666666666666,
      "eval_loss": 0.5115787386894226,
      "eval_runtime": 48.9112,
      "eval_samples_per_second": 184.007,
      "eval_steps_per_second": 2.883,
      "step": 563
    }
  ],
  "logging_steps": 500,
  "max_steps": 563,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 1562235917760000.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.9291695717112818e-05,
    "num_train_epochs": 1,
    "per_device_train_batch_size": 64,
    "seed": 12
  }
}