checkpoint-600/trainer_state.json

{
  "best_metric": 0.3020975887775421,
  "best_model_checkpoint": "food_beverages_japan_image_detection/checkpoint-600",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8921775898520085,
      "eval_loss": 0.3085739016532898,
      "eval_runtime": 8.7055,
      "eval_samples_per_second": 54.333,
      "eval_steps_per_second": 6.892,
      "step": 60
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8900634249471459,
      "eval_loss": 0.3083186745643616,
      "eval_runtime": 8.628,
      "eval_samples_per_second": 54.822,
      "eval_steps_per_second": 6.954,
      "step": 120
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8900634249471459,
      "eval_loss": 0.3071586787700653,
      "eval_runtime": 8.7844,
      "eval_samples_per_second": 53.846,
      "eval_steps_per_second": 6.83,
      "step": 180
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8921775898520085,
      "eval_loss": 0.30538779497146606,
      "eval_runtime": 8.805,
      "eval_samples_per_second": 53.719,
      "eval_steps_per_second": 6.814,
      "step": 240
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8942917547568711,
      "eval_loss": 0.30612456798553467,
      "eval_runtime": 8.6067,
      "eval_samples_per_second": 54.957,
      "eval_steps_per_second": 6.971,
      "step": 300
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8900634249471459,
      "eval_loss": 0.30368173122406006,
      "eval_runtime": 8.435,
      "eval_samples_per_second": 56.076,
      "eval_steps_per_second": 7.113,
      "step": 360
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8900634249471459,
      "eval_loss": 0.30304276943206787,
      "eval_runtime": 8.513,
      "eval_samples_per_second": 55.562,
      "eval_steps_per_second": 7.048,
      "step": 420
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8921775898520085,
      "eval_loss": 0.3024144768714905,
      "eval_runtime": 8.6904,
      "eval_samples_per_second": 54.428,
      "eval_steps_per_second": 6.904,
      "step": 480
    },
    {
      "epoch": 8.33,
      "grad_norm": 4.706602096557617,
      "learning_rate": 1.818181818181818e-07,
      "loss": 0.1807,
      "step": 500
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8942917547568711,
      "eval_loss": 0.30235838890075684,
      "eval_runtime": 8.6893,
      "eval_samples_per_second": 54.435,
      "eval_steps_per_second": 6.905,
      "step": 540
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.8942917547568711,
      "eval_loss": 0.3020975887775421,
      "eval_runtime": 8.6487,
      "eval_samples_per_second": 54.691,
      "eval_steps_per_second": 6.937,
      "step": 600
    }
  ],
  "logging_steps": 500,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 1.4653735236119347e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}