trainer_state.json

{
  "best_metric": 0.916,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0984/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": 10.66498851776123,
      "learning_rate": 6.536577206836604e-05,
      "loss": 0.8219,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8376,
      "eval_loss": 0.5254166126251221,
      "eval_runtime": 8.6728,
      "eval_samples_per_second": 432.387,
      "eval_steps_per_second": 6.803,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 5.264278445269635e-05,
      "loss": 0.2854,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8789333333333333,
      "eval_loss": 0.41615286469459534,
      "eval_runtime": 7.5958,
      "eval_samples_per_second": 493.692,
      "eval_steps_per_second": 7.767,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.004815848544239998,
      "learning_rate": 3.516509810075613e-05,
      "loss": 0.1267,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8802666666666666,
      "eval_loss": 0.40859290957450867,
      "eval_runtime": 7.8729,
      "eval_samples_per_second": 476.316,
      "eval_steps_per_second": 7.494,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 53.875640869140625,
      "learning_rate": 1.764317384604637e-05,
      "loss": 0.0485,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9018666666666667,
      "eval_loss": 0.36356309056282043,
      "eval_runtime": 6.9064,
      "eval_samples_per_second": 542.974,
      "eval_steps_per_second": 8.543,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.6460883617401123,
      "learning_rate": 4.771997142455883e-06,
      "loss": 0.011,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9157333333333333,
      "eval_loss": 0.3202899992465973,
      "eval_runtime": 7.0039,
      "eval_samples_per_second": 535.419,
      "eval_steps_per_second": 8.424,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.5354772210121155,
      "learning_rate": 3.893933500082047e-10,
      "loss": 0.0032,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.916,
      "eval_loss": 0.312288373708725,
      "eval_runtime": 7.062,
      "eval_samples_per_second": 531.012,
      "eval_steps_per_second": 8.355,
      "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
}