trainer_state.json

{
  "best_metric": 0.5885333333333334,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0872/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "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": 0.00046670262931309826,
      "loss": 3.0914,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.26426666666666665,
      "eval_loss": 2.722311019897461,
      "eval_runtime": 12.6718,
      "eval_samples_per_second": 295.933,
      "eval_steps_per_second": 4.656,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00037568023640968044,
      "loss": 2.4441,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.37546666666666667,
      "eval_loss": 2.248300790786743,
      "eval_runtime": 13.3062,
      "eval_samples_per_second": 281.823,
      "eval_steps_per_second": 4.434,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00025117927214825806,
      "loss": 1.9488,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.4728,
      "eval_loss": 1.8507720232009888,
      "eval_runtime": 12.4307,
      "eval_samples_per_second": 301.673,
      "eval_steps_per_second": 4.746,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 8.07583999633789,
      "learning_rate": 0.00012602267032890265,
      "loss": 1.4581,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5376,
      "eval_loss": 1.6366866827011108,
      "eval_runtime": 13.5831,
      "eval_samples_per_second": 276.078,
      "eval_steps_per_second": 4.344,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 8.942485809326172,
      "learning_rate": 3.408569387468488e-05,
      "loss": 0.9199,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5776,
      "eval_loss": 1.5055789947509766,
      "eval_runtime": 12.3077,
      "eval_samples_per_second": 304.687,
      "eval_steps_per_second": 4.794,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 9.935223579406738,
      "learning_rate": 2.7813810714871766e-09,
      "loss": 0.5381,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.5885333333333334,
      "eval_loss": 1.4833040237426758,
      "eval_runtime": 13.0193,
      "eval_samples_per_second": 288.034,
      "eval_steps_per_second": 4.532,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}