trainer_state.json

{
  "best_metric": 0.3128,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0510/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": 25.71416473388672,
      "learning_rate": 0.0005,
      "loss": 3.4238,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.16933333333333334,
      "eval_loss": 3.1503145694732666,
      "eval_runtime": 6.737,
      "eval_samples_per_second": 556.626,
      "eval_steps_per_second": 8.758,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 14.919692993164062,
      "learning_rate": 0.0005,
      "loss": 2.9185,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.23333333333333334,
      "eval_loss": 2.835447072982788,
      "eval_runtime": 6.6871,
      "eval_samples_per_second": 560.777,
      "eval_steps_per_second": 8.823,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 20.4703426361084,
      "learning_rate": 0.0005,
      "loss": 2.749,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.268,
      "eval_loss": 2.6976261138916016,
      "eval_runtime": 7.1973,
      "eval_samples_per_second": 521.028,
      "eval_steps_per_second": 8.198,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 16.890403747558594,
      "learning_rate": 0.0005,
      "loss": 2.6374,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.26426666666666665,
      "eval_loss": 2.6848459243774414,
      "eval_runtime": 7.1933,
      "eval_samples_per_second": 521.321,
      "eval_steps_per_second": 8.202,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 21.04191780090332,
      "learning_rate": 0.0005,
      "loss": 2.5652,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.31066666666666665,
      "eval_loss": 2.5117383003234863,
      "eval_runtime": 6.6845,
      "eval_samples_per_second": 560.995,
      "eval_steps_per_second": 8.826,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 23.997509002685547,
      "learning_rate": 0.0005,
      "loss": 2.4823,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.3128,
      "eval_loss": 2.5479564666748047,
      "eval_runtime": 6.8003,
      "eval_samples_per_second": 551.449,
      "eval_steps_per_second": 8.676,
      "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
}