checkpoint-2250/trainer_state.json

{
  "best_metric": 0.04815581813454628,
  "best_model_checkpoint": "ai_vs_real_image_detection/checkpoint-2250",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 2250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.44,
      "grad_norm": 0.6807317733764648,
      "learning_rate": 7.954545454545454e-07,
      "loss": 0.0381,
      "step": 500
    },
    {
      "epoch": 0.89,
      "grad_norm": 3.3560590744018555,
      "learning_rate": 5.681818181818182e-07,
      "loss": 0.036,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9824166666666667,
      "eval_loss": 0.04870710149407387,
      "eval_runtime": 689.2367,
      "eval_samples_per_second": 69.642,
      "eval_steps_per_second": 2.176,
      "step": 1125
    },
    {
      "epoch": 1.33,
      "grad_norm": 2.8861987590789795,
      "learning_rate": 3.4090909090909085e-07,
      "loss": 0.0352,
      "step": 1500
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.27879592776298523,
      "learning_rate": 1.1363636363636363e-07,
      "loss": 0.0334,
      "step": 2000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9825,
      "eval_loss": 0.04815581813454628,
      "eval_runtime": 658.5494,
      "eval_samples_per_second": 72.887,
      "eval_steps_per_second": 2.278,
      "step": 2250
    }
  ],
  "logging_steps": 500,
  "max_steps": 2250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 1.1158846504501248e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}