trainer_state.json

{
  "best_metric": 0.928,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0672/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": 4.227148056030273,
      "learning_rate": 2.5015015015015015e-05,
      "loss": 0.7834,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8773333333333333,
      "eval_loss": 0.354803204536438,
      "eval_runtime": 11.1851,
      "eval_samples_per_second": 335.268,
      "eval_steps_per_second": 5.275,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.8607847690582275,
      "learning_rate": 2.0015015015015016e-05,
      "loss": 0.1979,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9016,
      "eval_loss": 0.2975940406322479,
      "eval_runtime": 10.9315,
      "eval_samples_per_second": 343.045,
      "eval_steps_per_second": 5.397,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.04974592104554176,
      "learning_rate": 1.5015015015015016e-05,
      "loss": 0.0933,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9128,
      "eval_loss": 0.26388365030288696,
      "eval_runtime": 10.8201,
      "eval_samples_per_second": 346.577,
      "eval_steps_per_second": 5.453,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.008352010510861874,
      "learning_rate": 1.0015015015015017e-05,
      "loss": 0.0443,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9162666666666667,
      "eval_loss": 0.2759251594543457,
      "eval_runtime": 11.1866,
      "eval_samples_per_second": 335.223,
      "eval_steps_per_second": 5.274,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 38.45092010498047,
      "learning_rate": 5.0150150150150156e-06,
      "loss": 0.0213,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.928,
      "eval_loss": 0.23930516839027405,
      "eval_runtime": 11.1843,
      "eval_samples_per_second": 335.291,
      "eval_steps_per_second": 5.275,
      "step": 1665
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.2370660311296e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}