trainer_state.json

{
  "best_metric": 0.8930666666666667,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0059/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": 2.5015015015015015e-05,
      "loss": 2.2466,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7602666666666666,
      "eval_loss": 1.0932728052139282,
      "eval_runtime": 6.0778,
      "eval_samples_per_second": 617.0,
      "eval_steps_per_second": 9.707,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 2.0030030030030034e-05,
      "loss": 0.7419,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8458666666666667,
      "eval_loss": 0.5976943969726562,
      "eval_runtime": 6.0807,
      "eval_samples_per_second": 616.701,
      "eval_steps_per_second": 9.703,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.0173591375350952,
      "learning_rate": 1.5030030030030029e-05,
      "loss": 0.4115,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8661333333333333,
      "eval_loss": 0.49821028113365173,
      "eval_runtime": 6.0967,
      "eval_samples_per_second": 615.09,
      "eval_steps_per_second": 9.677,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 23.93303680419922,
      "learning_rate": 1.0030030030030031e-05,
      "loss": 0.268,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8768,
      "eval_loss": 0.42467936873435974,
      "eval_runtime": 6.1368,
      "eval_samples_per_second": 611.067,
      "eval_steps_per_second": 9.614,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.9594457149505615,
      "learning_rate": 5.03003003003003e-06,
      "loss": 0.1784,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8856,
      "eval_loss": 0.3929350972175598,
      "eval_runtime": 6.1847,
      "eval_samples_per_second": 606.33,
      "eval_steps_per_second": 9.54,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.7309562563896179,
      "learning_rate": 3.003003003003003e-08,
      "loss": 0.1287,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8930666666666667,
      "eval_loss": 0.37793540954589844,
      "eval_runtime": 6.1815,
      "eval_samples_per_second": 606.645,
      "eval_steps_per_second": 9.545,
      "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
}