checkpoint-640/trainer_state.json

{
  "best_metric": 0.04739821329712868,
  "best_model_checkpoint": "lemon_quality_image_detection/checkpoint-640",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 640,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.055141426622867584,
      "eval_runtime": 13.4768,
      "eval_samples_per_second": 100.172,
      "eval_steps_per_second": 12.54,
      "step": 64
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.053136058151721954,
      "eval_runtime": 13.1869,
      "eval_samples_per_second": 102.374,
      "eval_steps_per_second": 12.816,
      "step": 128
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.051570698618888855,
      "eval_runtime": 13.3667,
      "eval_samples_per_second": 100.998,
      "eval_steps_per_second": 12.643,
      "step": 192
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.05022797733545303,
      "eval_runtime": 14.0377,
      "eval_samples_per_second": 96.169,
      "eval_steps_per_second": 12.039,
      "step": 256
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.04957624524831772,
      "eval_runtime": 13.7563,
      "eval_samples_per_second": 98.137,
      "eval_steps_per_second": 12.285,
      "step": 320
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.04869816452264786,
      "eval_runtime": 13.6457,
      "eval_samples_per_second": 98.932,
      "eval_steps_per_second": 12.385,
      "step": 384
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.048136912286281586,
      "eval_runtime": 13.4759,
      "eval_samples_per_second": 100.179,
      "eval_steps_per_second": 12.541,
      "step": 448
    },
    {
      "epoch": 7.81,
      "grad_norm": 0.1739039421081543,
      "learning_rate": 1.1864406779661017e-07,
      "loss": 0.0361,
      "step": 500
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.04772254824638367,
      "eval_runtime": 13.428,
      "eval_samples_per_second": 100.536,
      "eval_steps_per_second": 12.586,
      "step": 512
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.04746958240866661,
      "eval_runtime": 13.3671,
      "eval_samples_per_second": 100.994,
      "eval_steps_per_second": 12.643,
      "step": 576
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 1.0,
      "eval_loss": 0.04739821329712868,
      "eval_runtime": 13.6007,
      "eval_samples_per_second": 99.259,
      "eval_steps_per_second": 12.426,
      "step": 640
    }
  ],
  "logging_steps": 500,
  "max_steps": 640,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 1.569226854053376e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}