trainer_state.json

{
  "best_metric": 0.9224,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0976/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": Infinity,
      "learning_rate": 9e-05,
      "loss": 0.6673,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9098666666666667,
      "eval_loss": 0.3024669289588928,
      "eval_runtime": 11.2856,
      "eval_samples_per_second": 332.282,
      "eval_steps_per_second": 5.228,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.12493127584457397,
      "learning_rate": 9e-05,
      "loss": 0.1758,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9168,
      "eval_loss": 0.2776244282722473,
      "eval_runtime": 10.9053,
      "eval_samples_per_second": 343.868,
      "eval_steps_per_second": 5.41,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.030259694904088974,
      "learning_rate": 9e-05,
      "loss": 0.1024,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9221333333333334,
      "eval_loss": 0.29227444529533386,
      "eval_runtime": 11.4286,
      "eval_samples_per_second": 328.124,
      "eval_steps_per_second": 5.162,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.12459619343280792,
      "learning_rate": 9e-05,
      "loss": 0.0715,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9173333333333333,
      "eval_loss": 0.31042876839637756,
      "eval_runtime": 11.0625,
      "eval_samples_per_second": 338.983,
      "eval_steps_per_second": 5.333,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.8665522336959839,
      "learning_rate": 9e-05,
      "loss": 0.0543,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9224,
      "eval_loss": 0.3028394281864166,
      "eval_runtime": 11.4415,
      "eval_samples_per_second": 327.755,
      "eval_steps_per_second": 5.157,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}