trainer_state.json

{
  "best_metric": 0.9173333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0971/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.7164051532745361,
      "learning_rate": 0.0004522542485937369,
      "loss": 0.8473,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8261333333333334,
      "eval_loss": 0.5922415852546692,
      "eval_runtime": 7.4762,
      "eval_samples_per_second": 501.591,
      "eval_steps_per_second": 7.892,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00032770273425644284,
      "loss": 0.4193,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8312,
      "eval_loss": 0.5678139328956604,
      "eval_runtime": 7.368,
      "eval_samples_per_second": 508.958,
      "eval_steps_per_second": 8.008,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.6426312923431396,
      "learning_rate": 0.00017319451210748358,
      "loss": 0.1985,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8864,
      "eval_loss": 0.3947169780731201,
      "eval_runtime": 7.5808,
      "eval_samples_per_second": 494.669,
      "eval_steps_per_second": 7.783,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 13.307428359985352,
      "learning_rate": 4.802337581094707e-05,
      "loss": 0.0557,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.912,
      "eval_loss": 0.32546234130859375,
      "eval_runtime": 7.2823,
      "eval_samples_per_second": 514.948,
      "eval_steps_per_second": 8.102,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.006037747021764517,
      "learning_rate": 4.4502166460236306e-10,
      "loss": 0.0129,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9173333333333333,
      "eval_loss": 0.315297931432724,
      "eval_runtime": 8.2033,
      "eval_samples_per_second": 457.134,
      "eval_steps_per_second": 7.192,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}