checkpoint-2565/trainer_state.json

{
  "best_metric": 0.05002307519316673,
  "best_model_checkpoint": "diamond_types_image_detection/checkpoint-2565",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 2565,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19,
      "grad_norm": 0.18087689578533173,
      "learning_rate": 2.4632206759443343e-06,
      "loss": 0.0554,
      "step": 500
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.23432385921478271,
      "learning_rate": 1.8667992047713717e-06,
      "loss": 0.0533,
      "step": 1000
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.11465876549482346,
      "learning_rate": 1.2703777335984097e-06,
      "loss": 0.0495,
      "step": 1500
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.04937751218676567,
      "learning_rate": 6.739562624254474e-07,
      "loss": 0.0484,
      "step": 2000
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.04795745760202408,
      "learning_rate": 7.75347912524851e-08,
      "loss": 0.0484,
      "step": 2500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9913906558455802,
      "eval_loss": 0.05002307519316673,
      "eval_runtime": 215.3589,
      "eval_samples_per_second": 84.677,
      "eval_steps_per_second": 2.647,
      "step": 2565
    }
  ],
  "logging_steps": 500,
  "max_steps": 2565,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 1.2718359274598498e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}