trainer_state.json

{
  "best_metric": 0.35333333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0481/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": 18.904613494873047,
      "learning_rate": 0.0005,
      "loss": 3.3175,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.19733333333333333,
      "eval_loss": 2.9993250370025635,
      "eval_runtime": 10.7564,
      "eval_samples_per_second": 348.63,
      "eval_steps_per_second": 5.485,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 15.936320304870605,
      "learning_rate": 0.0005,
      "loss": 2.7952,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.27946666666666664,
      "eval_loss": 2.6506786346435547,
      "eval_runtime": 10.7073,
      "eval_samples_per_second": 350.229,
      "eval_steps_per_second": 5.51,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 16.583332061767578,
      "learning_rate": 0.0005,
      "loss": 2.6332,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.28186666666666665,
      "eval_loss": 2.6198244094848633,
      "eval_runtime": 11.2168,
      "eval_samples_per_second": 334.321,
      "eval_steps_per_second": 5.26,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 19.012924194335938,
      "learning_rate": 0.0005,
      "loss": 2.5039,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.29386666666666666,
      "eval_loss": 2.5596671104431152,
      "eval_runtime": 11.1548,
      "eval_samples_per_second": 336.177,
      "eval_steps_per_second": 5.289,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 11.844913482666016,
      "learning_rate": 0.0005,
      "loss": 2.3917,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.3274666666666667,
      "eval_loss": 2.4864487648010254,
      "eval_runtime": 10.6442,
      "eval_samples_per_second": 352.305,
      "eval_steps_per_second": 5.543,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 12.502264976501465,
      "learning_rate": 0.0005,
      "loss": 2.302,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.35333333333333333,
      "eval_loss": 2.3544797897338867,
      "eval_runtime": 10.723,
      "eval_samples_per_second": 349.717,
      "eval_steps_per_second": 5.502,
      "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
}